From 436afa4a61116035e069801650551e8bd84c57f9 Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Thu, 18 Dec 2025 15:55:30 +0100
Subject: [PATCH 01/59] fix tag count by including type in grouping

---
 internal/repository/tags.go     | 9 +++++----
 internal/routerConfig/routes.go | 4 ++--
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/internal/repository/tags.go b/internal/repository/tags.go
index 5ca13382..8a076e8a 100644
--- a/internal/repository/tags.go
+++ b/internal/repository/tags.go
@@ -224,10 +224,10 @@ func (r *JobRepository) CountTags(user *schema.User) (tags []schema.Tag, counts
 	}
 
 	// Query and Count Jobs with attached Tags
-	q := sq.Select("t.tag_name, t.id, count(jt.tag_id)").
+	q := sq.Select("t.tag_type, t.tag_name, t.id, count(jt.tag_id)").
 		From("tag t").
 		LeftJoin("jobtag jt ON t.id = jt.tag_id").
-		GroupBy("t.tag_name")
+		GroupBy("t.tag_type, t.tag_name")
 
 	// Build scope list for filtering
 	var scopeBuilder strings.Builder
@@ -260,14 +260,15 @@ func (r *JobRepository) CountTags(user *schema.User) (tags []schema.Tag, counts
 
 	counts = make(map[string]int)
 	for rows.Next() {
+		var tagType string
 		var tagName string
 		var tagId int
 		var count int
-		if err = rows.Scan(&tagName, &tagId, &count); err != nil {
+		if err = rows.Scan(&tagType, &tagName, &tagId, &count); err != nil {
 			return nil, nil, err
 		}
 		// Use tagId as second Map-Key component to differentiate tags with identical names
-		counts[fmt.Sprint(tagName, tagId)] = count
+		counts[fmt.Sprint(tagType, tagName, tagId)] = count
 	}
 	err = rows.Err()
 
diff --git a/internal/routerConfig/routes.go b/internal/routerConfig/routes.go
index c2126cd0..4466034d 100644
--- a/internal/routerConfig/routes.go
+++ b/internal/routerConfig/routes.go
@@ -205,13 +205,13 @@ func setupTaglistRoute(i InfoType, r *http.Request) InfoType {
 				"id":    tag.ID,
 				"name":  tag.Name,
 				"scope": tag.Scope,
-				"count": counts[fmt.Sprint(tag.Name, tag.ID)],
+				"count": counts[fmt.Sprint(tag.Type, tag.Name, tag.ID)],
 			}
 			tagMap[tag.Type] = append(tagMap[tag.Type], tagItem)
 		}
 	} else if userAuthlevel < 4 && userAuthlevel >= 2 { // User+ : Show global and admin scope only if at least 1 tag used, private scope regardless of count
 		for _, tag := range tags {
-			tagCount := counts[fmt.Sprint(tag.Name, tag.ID)]
+			tagCount := counts[fmt.Sprint(tag.Type, tag.Name, tag.ID)]
 			if ((tag.Scope == "global" || tag.Scope == "admin") && tagCount >= 1) || (tag.Scope != "global" && tag.Scope != "admin") {
 				tagItem := map[string]interface{}{
 					"id":    tag.ID,

From c58b01a602543d893c0ffdecb34461ce4964a725 Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Fri, 19 Dec 2025 14:42:02 +0100
Subject: [PATCH 02/59] fix wrong render condition order in nodeList

---
 web/frontend/src/systems/NodeList.svelte | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/web/frontend/src/systems/NodeList.svelte b/web/frontend/src/systems/NodeList.svelte
index c01ef237..e904076e 100644
--- a/web/frontend/src/systems/NodeList.svelte
+++ b/web/frontend/src/systems/NodeList.svelte
@@ -246,16 +246,7 @@
               <Card body color="danger">{$nodesQuery.error.message}</Card>
             </Col>
           </Row>
-        {:else}
-          {#each nodes as nodeData (nodeData.host)}
-            <NodeListRow {nodeData} {cluster} {selectedMetrics}/>
-          {:else}
-            <tr>
-              <td colspan={selectedMetrics.length + 1}> No nodes found </td>
-            </tr>
-          {/each}
-        {/if}
-        {#if $nodesQuery.fetching || !$nodesQuery.data}
+        {:else if $nodesQuery.fetching || !$nodesQuery.data}
           <tr>
             <td colspan={selectedMetrics.length + 1}>
               <div style="text-align:center;">
@@ -272,6 +263,14 @@
               </div>
             </td>
           </tr>
+        {:else}
+          {#each nodes as nodeData (nodeData.host)}
+            <NodeListRow {nodeData} {cluster} {selectedMetrics}/>
+          {:else}
+            <tr>
+              <td colspan={selectedMetrics.length + 1}> No nodes found </td>
+            </tr>
+          {/each}
         {/if}
       </tbody>
     </Table>

From 7a0975b94d8af215139c2202c55f2dbfa0a2153a Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Fri, 19 Dec 2025 15:10:15 +0100
Subject: [PATCH 03/59] final fix render race condition if metrics change in
 nodeList

---
 web/frontend/src/Systems.root.svelte          |  2 +-
 web/frontend/src/systems/NodeList.svelte      | 24 ++++++++++---------
 .../src/systems/nodelist/NodeListRow.svelte   | 18 ++++++++++++++
 3 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/web/frontend/src/Systems.root.svelte b/web/frontend/src/Systems.root.svelte
index b27cefa9..d81a64cd 100644
--- a/web/frontend/src/Systems.root.svelte
+++ b/web/frontend/src/Systems.root.svelte
@@ -269,7 +269,7 @@
     <NodeOverview {cluster} {ccconfig} {selectedMetric} {from} {to} {hostnameFilter} {hoststateFilter}/>
   {:else}
     <!-- ROW2-2: Node List (Grid Included)-->
-    <NodeList {cluster} {subCluster} {ccconfig} {selectedMetrics} {selectedResolution} {hostnameFilter} {hoststateFilter} {from} {to} {presetSystemUnits}/>
+    <NodeList {cluster} {subCluster} {ccconfig} pendingSelectedMetrics={selectedMetrics} {selectedResolution} {hostnameFilter} {hoststateFilter} {from} {to} {presetSystemUnits}/>
   {/if}
 {/if}
 
diff --git a/web/frontend/src/systems/NodeList.svelte b/web/frontend/src/systems/NodeList.svelte
index e904076e..fa758c18 100644
--- a/web/frontend/src/systems/NodeList.svelte
+++ b/web/frontend/src/systems/NodeList.svelte
@@ -5,7 +5,7 @@
   - `cluster String`: The nodes' cluster
   - `subCluster String`: The nodes' subCluster [Default: ""]
   - `ccconfig Object?`: The ClusterCockpit Config Context [Default: null]
-  - `selectedMetrics [String]`: The array of selected metrics [Default []]
+  - `pendingSelectedMetrics [String]`: The array of selected metrics [Default []]
   - `selectedResolution Number?`: The selected data resolution [Default: 0]
   - `hostnameFilter String?`: The active hostnamefilter [Default: ""]
   - `hoststateFilter String?`: The active hoststatefilter [Default: ""]
@@ -27,7 +27,7 @@
     cluster,
     subCluster = "",
     ccconfig = null,
-    selectedMetrics = [],
+    pendingSelectedMetrics = [],
     selectedResolution = 0,
     hostnameFilter = "",
     hoststateFilter = "",
@@ -94,6 +94,7 @@
 
   /* State Init */
   let nodes = $state([]);
+  let selectedMetrics = $state(pendingSelectedMetrics);
   let page = $state(1);
   let itemsPerPage = $state(usePaging ? (ccconfig?.nodeList_nodesPerPage || 10) : 10);
   let headerPaddingTop = $state(0);
@@ -110,7 +111,7 @@
       stateFilter: hoststateFilter,
       nodeFilter: hostnameFilter,
       scopes: ["core", "socket", "accelerator"],
-      metrics: selectedMetrics,
+      metrics: pendingSelectedMetrics,
       from: from.toISOString(),
       to: to.toISOString(),
       paging: paging,
@@ -140,15 +141,17 @@
   $effect(() => {
     if ($nodesQuery?.data) {
       untrack(() => {
-        handleNodes($nodesQuery?.data?.nodeMetricsList);
+        nodes = handleNodes($nodesQuery?.data?.nodeMetricsList);
+        matchedNodes = $nodesQuery?.data?.totalNodes || 0;
       });
+      selectedMetrics = [...pendingSelectedMetrics]; // Trigger Rerender in NodeListRow Only After Data is Fetched
     };
   });
 
   $effect(() => {
     // Triggers (Except Paging)
     from, to
-    selectedMetrics, selectedResolution
+    pendingSelectedMetrics, selectedResolution
     hostnameFilter, hoststateFilter
     // Continous Scroll: Paging if parameters change: Existing entries will not match new selections
     // Nodes Array Reset in HandleNodes func
@@ -162,17 +165,16 @@
     if (data) {
       if (usePaging) {
         // console.log('New Paging', $state.snapshot(paging))
-        nodes = [...data.items].sort((a, b) => a.host.localeCompare(b.host));
+        return [...data.items].sort((a, b) => a.host.localeCompare(b.host));
       } else {
         if ($state.snapshot(page) == 1) {
           // console.log('Page 1 Reset', [...data.items])
-          nodes = [...data.items].sort((a, b) => a.host.localeCompare(b.host));
+          return [...data.items].sort((a, b) => a.host.localeCompare(b.host));
         } else {
           // console.log('Add Nodes', $state.snapshot(nodes), [...data.items])
-          nodes = nodes.concat([...data.items])
+          return nodes.concat([...data.items])
         }
       }
-      matchedNodes = data.totalNodes;
     };
   };
 
@@ -228,7 +230,7 @@
             {/if}
           </th>
 
-          {#each selectedMetrics as metric (metric)}
+          {#each pendingSelectedMetrics as metric (metric)}
             <th
               class="position-sticky top-0 text-center"
               scope="col"
@@ -248,7 +250,7 @@
           </Row>
         {:else if $nodesQuery.fetching || !$nodesQuery.data}
           <tr>
-            <td colspan={selectedMetrics.length + 1}>
+            <td colspan={pendingSelectedMetrics.length + 1}>
               <div style="text-align:center;">
                 {#if !usePaging}
                   <p><b>
diff --git a/web/frontend/src/systems/nodelist/NodeListRow.svelte b/web/frontend/src/systems/nodelist/NodeListRow.svelte
index bc93a323..e7e095ea 100644
--- a/web/frontend/src/systems/nodelist/NodeListRow.svelte
+++ b/web/frontend/src/systems/nodelist/NodeListRow.svelte
@@ -128,6 +128,24 @@
     }
     return pendingExtendedLegendData;
   }
+
+  /* Inspect */
+  // $inspect(selectedMetrics).with((type, selectedMetrics) => {
+  //   console.log(type, 'selectedMetrics', selectedMetrics)
+	// });
+
+  // $inspect(nodeData).with((type, nodeData) => {
+  //   console.log(type, 'nodeData', nodeData)
+	// });
+
+  // $inspect(refinedData).with((type, refinedData) => {
+  //   console.log(type, 'refinedData', refinedData)
+	// });
+
+  // $inspect(dataHealth).with((type, dataHealth) => {
+  //   console.log(type, 'dataHealth', dataHealth)
+	// });
+
 </script>
 
 <tr>

From 91b90d033e8703acffe5740872310a2f094fdcd2 Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Fri, 19 Dec 2025 15:27:35 +0100
Subject: [PATCH 04/59] fix metric select drag and drop

---
 .../src/generic/select/MetricSelection.svelte | 20 ++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/web/frontend/src/generic/select/MetricSelection.svelte b/web/frontend/src/generic/select/MetricSelection.svelte
index 8bcaefcb..eeab56d7 100644
--- a/web/frontend/src/generic/select/MetricSelection.svelte
+++ b/web/frontend/src/generic/select/MetricSelection.svelte
@@ -107,13 +107,18 @@
     }
   }
 
+  function columnsDragOver(event) {
+		event.preventDefault();
+		event.dataTransfer.dropEffect = 'move';
+  }
+
   function columnsDragStart(event, i) {
     event.dataTransfer.effectAllowed = "move";
     event.dataTransfer.dropEffect = "move";
     event.dataTransfer.setData("text/plain", i);
   }
 
-  function columnsDrag(event, target) {
+  function columnsDrop(event, target) {
     event.dataTransfer.dropEffect = "move";
     const start = Number.parseInt(event.dataTransfer.getData("text/plain"));
 
@@ -182,19 +187,18 @@
       {/if}
       {#each listedMetrics as metric, index (metric)}
         <li
-          draggable
+          draggable={true}
           class="cc-config-column list-group-item"
           class:is-active={columnHovering === index}
           ondragover={(event) => {
-            event.preventDefault()
-            return false
+            columnsDragOver(event)
           }}
           ondragstart={(event) => {
             columnsDragStart(event, index)
           }}
           ondrop={(event) => {
             event.preventDefault()
-            columnsDrag(event, index)
+            columnsDrop(event, index)
           }}
           ondragenter={() => (columnHovering = index)}
         >
@@ -237,4 +241,10 @@
     color: #fff;
     cursor: grabbing;
   }
+
+  li.prevent-select {
+  -webkit-user-select: none; /* Safari */
+  -ms-user-select: none; /* IE 10 and IE 11 */
+  user-select: none; /* Standard syntax */
+}
 </style>

From af7d208c21c9dfbd539d2baa9c6bd6d4ea95d85c Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Fri, 19 Dec 2025 16:16:57 +0100
Subject: [PATCH 05/59] remove unused class

---
 web/frontend/src/generic/select/MetricSelection.svelte | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/web/frontend/src/generic/select/MetricSelection.svelte b/web/frontend/src/generic/select/MetricSelection.svelte
index eeab56d7..67bbbd01 100644
--- a/web/frontend/src/generic/select/MetricSelection.svelte
+++ b/web/frontend/src/generic/select/MetricSelection.svelte
@@ -241,10 +241,4 @@
     color: #fff;
     cursor: grabbing;
   }
-
-  li.prevent-select {
-  -webkit-user-select: none; /* Safari */
-  -ms-user-select: none; /* IE 10 and IE 11 */
-  user-select: none; /* Standard syntax */
-}
 </style>

From 7acc89e42d6b23f0250f387f93dc72223cce1655 Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Fri, 19 Dec 2025 17:52:21 +0100
Subject: [PATCH 06/59] move public dash close button

---
 web/frontend/src/DashPublic.root.svelte | 27 +++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/web/frontend/src/DashPublic.root.svelte b/web/frontend/src/DashPublic.root.svelte
index 36e6703e..25e2683c 100644
--- a/web/frontend/src/DashPublic.root.svelte
+++ b/web/frontend/src/DashPublic.root.svelte
@@ -338,7 +338,7 @@
 </script>
 
 <Card style="height: 98vh;">
-  <CardBody class="align-content-center">
+  <CardBody class="align-content-center p-1">
     <Row>
       <Col>
         <Refresher
@@ -354,11 +354,6 @@
           }}
         />
       </Col>
-      <Col class="d-flex justify-content-end">
-        <Button outline class="mb-1" size="sm" color="light" href="/">
-          <Icon name="x"/>
-        </Button>
-      </Col>
     </Row>
     {#if $statusQuery.fetching || $statesTimed.fetching}
       <Row class="justify-content-center">
@@ -368,6 +363,13 @@
       </Row>
 
     {:else if $statusQuery.error || $statesTimed.error}
+      <Row class="mb-2">
+        <Col class="d-flex justify-content-end">
+          <Button color="secondary" href="/">
+            <Icon name="x"/>
+          </Button>
+        </Col>
+      </Row>
       <Row cols={{xs:1, md:2}}>
         {#if $statusQuery.error}
           <Col>
@@ -385,8 +387,17 @@
       <Row cols={{xs:1, md:2}}>
         <Col> <!-- General Cluster Info Card -->
            <Card class="h-100">
-            <CardHeader class="text-center">
-              <h2 class="mb-0">Cluster {presetCluster.charAt(0).toUpperCase() + presetCluster.slice(1)}</h2>
+            <CardHeader>
+              <Row>
+                <Col xs="11" class="text-center">
+                  <h2 class="mb-0">Cluster {presetCluster.charAt(0).toUpperCase() + presetCluster.slice(1)}</h2>
+                </Col>
+                <Col xs="1" class="d-flex justify-content-end">
+                  <Button color="light" href="/">
+                    <Icon name="x"/>
+                  </Button>
+                </Col>
+              </Row>
             </CardHeader>
             <CardBody>
               <h4>CPU(s)</h4><p><strong>{[...clusterInfo?.processorTypes].join(', ')}</strong></p>

From fdee4f89386aa8c712effe19467cf755d97807e8 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Sat, 20 Dec 2025 09:21:58 +0100
Subject: [PATCH 07/59] Integrate NATS API.

Only start either REST start/stop API or NATS start/stop API
---
 cmd/cc-backend/server.go | 26 +++++++++++++++++---------
 internal/api/rest.go     |  7 +++++--
 2 files changed, 22 insertions(+), 11 deletions(-)

diff --git a/cmd/cc-backend/server.go b/cmd/cc-backend/server.go
index 2c5ce8bc..4ed79622 100644
--- a/cmd/cc-backend/server.go
+++ b/cmd/cc-backend/server.go
@@ -49,9 +49,10 @@ const (
 
 // Server encapsulates the HTTP server state and dependencies
 type Server struct {
-	router    *mux.Router
-	server    *http.Server
-	apiHandle *api.RestAPI
+	router        *mux.Router
+	server        *http.Server
+	restAPIHandle *api.RestAPI
+	natsAPIHandle *api.NatsAPI
 }
 
 func onFailureResponse(rw http.ResponseWriter, r *http.Request, err error) {
@@ -104,7 +105,7 @@ func (s *Server) init() error {
 
 	authHandle := auth.GetAuthInstance()
 
-	s.apiHandle = api.New()
+	s.restAPIHandle = api.New()
 
 	info := map[string]any{}
 	info["hasOpenIDConnect"] = false
@@ -240,13 +241,20 @@ func (s *Server) init() error {
 
 	// Mount all /monitoring/... and /api/... routes.
 	routerConfig.SetupRoutes(secured, buildInfo)
-	s.apiHandle.MountAPIRoutes(securedapi)
-	s.apiHandle.MountUserAPIRoutes(userapi)
-	s.apiHandle.MountConfigAPIRoutes(configapi)
-	s.apiHandle.MountFrontendAPIRoutes(frontendapi)
+	s.restAPIHandle.MountAPIRoutes(securedapi)
+	s.restAPIHandle.MountUserAPIRoutes(userapi)
+	s.restAPIHandle.MountConfigAPIRoutes(configapi)
+	s.restAPIHandle.MountFrontendAPIRoutes(frontendapi)
+
+	if config.Keys.APISubjects != nil {
+		s.natsAPIHandle = api.NewNatsAPI()
+		if err := s.natsAPIHandle.StartSubscriptions(); err != nil {
+			return fmt.Errorf("starting NATS subscriptions: %w", err)
+		}
+	}
 
 	if memorystore.InternalCCMSFlag {
-		s.apiHandle.MountMetricStoreAPIRoutes(metricstoreapi)
+		s.restAPIHandle.MountMetricStoreAPIRoutes(metricstoreapi)
 	}
 
 	if config.Keys.EmbedStaticFiles {
diff --git a/internal/api/rest.go b/internal/api/rest.go
index 8232b64e..ebcf31ed 100644
--- a/internal/api/rest.go
+++ b/internal/api/rest.go
@@ -79,8 +79,11 @@ func (api *RestAPI) MountAPIRoutes(r *mux.Router) {
 	// Slurm node state
 	r.HandleFunc("/nodestate/", api.updateNodeStates).Methods(http.MethodPost, http.MethodPut)
 	// Job Handler
-	r.HandleFunc("/jobs/start_job/", api.startJob).Methods(http.MethodPost, http.MethodPut)
-	r.HandleFunc("/jobs/stop_job/", api.stopJobByRequest).Methods(http.MethodPost, http.MethodPut)
+	if config.Keys.APISubjects == nil {
+		cclog.Info("Enabling REST start/stop job API")
+		r.HandleFunc("/jobs/start_job/", api.startJob).Methods(http.MethodPost, http.MethodPut)
+		r.HandleFunc("/jobs/stop_job/", api.stopJobByRequest).Methods(http.MethodPost, http.MethodPut)
+	}
 	r.HandleFunc("/jobs/", api.getJobs).Methods(http.MethodGet)
 	r.HandleFunc("/jobs/{id}", api.getJobByID).Methods(http.MethodPost)
 	r.HandleFunc("/jobs/{id}", api.getCompleteJobByID).Methods(http.MethodGet)

From e56532e5c8b8b52f9e1089552cc949fb6844db43 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Sat, 20 Dec 2025 09:35:54 +0100
Subject: [PATCH 08/59] Add example json API payloads

---
 configs/startJobPayload.json | 22 ++++++++++++++++++++++
 configs/stopJobPayload.json  |  7 +++++++
 2 files changed, 29 insertions(+)
 create mode 100644 configs/startJobPayload.json
 create mode 100644 configs/stopJobPayload.json

diff --git a/configs/startJobPayload.json b/configs/startJobPayload.json
new file mode 100644
index 00000000..9517876f
--- /dev/null
+++ b/configs/startJobPayload.json
@@ -0,0 +1,22 @@
+{
+  "cluster": "fritz",
+  "jobId": 123000,
+  "jobState": "running",
+  "numAcc": 0,
+  "numHwthreads": 72,
+  "numNodes": 1,
+  "partition": "main",
+  "requestedMemory": 128000,
+  "resources": [{ "hostname": "f0726" }],
+  "startTime": 1649723812,
+  "subCluster": "main",
+  "submitTime": 1649723812,
+  "user": "k106eb10",
+  "project": "k106eb",
+  "walltime": 86400,
+  "metaData": {
+    "slurmInfo": "JobId=398759\nJobName=myJob\nUserId=dummyUser\nGroupId=dummyGroup\nAccount=dummyAccount\nQOS=normal Requeue=False Restarts=0 BatchFlag=True\nTimeLimit=1439'\nSubmitTime=2023-02-09T14:10:18\nPartition=singlenode\nNodeList=xx\nNumNodes=xx NumCPUs=72 NumTasks=72 CPUs/Task=1\nNTasksPerNode:Socket:Core=0:None:None\nTRES_req=cpu=72,mem=250000M,node=1,billing=72\nTRES_alloc=cpu=72,node=1,billing=72\nCommand=myCmd\nWorkDir=myDir\nStdErr=\nStdOut=\n",
+    "jobScript": "#!/bin/bash  -l\n#SBATCH --job-name=dummy_job\n#SBATCH --time=23:59:00\n#SBATCH --partition=singlenode\n#SBATCH --ntasks=72\n#SBATCH --hint=multithread\n#SBATCH --chdir=/home/atuin/k106eb/dummy/\n#SBATCH --export=NONE\nunset SLURM_EXPORT_ENV\n\n#This is a dummy job script\n./mybinary\n",
+    "jobName": "ams_pipeline"
+  }
+}
diff --git a/configs/stopJobPayload.json b/configs/stopJobPayload.json
new file mode 100644
index 00000000..baf76f95
--- /dev/null
+++ b/configs/stopJobPayload.json
@@ -0,0 +1,7 @@
+{
+  "cluster": "fritz",
+  "jobId": 123000,
+  "jobState": "completed",
+  "startTime": 1649723812,
+  "stopTime": 1649763839
+}

From 3cfcd301281c14af88f60e10790c4d52e44c213b Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Sat, 20 Dec 2025 10:17:54 +0100
Subject: [PATCH 09/59] Add CLAUDE.md documentation for Claude Code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Provides architecture overview, build commands, and development workflows
to help future Claude Code instances work productively in this codebase.
Includes guidance on GraphQL/REST API patterns, database migrations, and
the repository/metric data architecture.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---
 CLAUDE.md | 198 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 198 insertions(+)
 create mode 100644 CLAUDE.md

diff --git a/CLAUDE.md b/CLAUDE.md
new file mode 100644
index 00000000..2bb08c98
--- /dev/null
+++ b/CLAUDE.md
@@ -0,0 +1,198 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+ClusterCockpit is a job-specific performance monitoring framework for HPC clusters. This is a Golang backend that provides REST and GraphQL APIs, serves a Svelte-based frontend, and manages job archives and metric data from various time-series databases.
+
+## Build and Development Commands
+
+### Building
+
+```bash
+# Build everything (frontend + backend)
+make
+
+# Build only the frontend
+make frontend
+
+# Build only the backend (requires frontend to be built first)
+go build -ldflags='-s -X main.date=$(date +"%Y-%m-%d:T%H:%M:%S") -X main.version=1.4.4 -X main.commit=$(git rev-parse --short HEAD)' ./cmd/cc-backend
+```
+
+### Testing
+
+```bash
+# Run all tests
+make test
+
+# Run tests with verbose output
+go test -v ./...
+
+# Run tests for a specific package
+go test ./internal/repository
+```
+
+### Code Generation
+
+```bash
+# Regenerate GraphQL schema and resolvers (after modifying api/*.graphqls)
+make graphql
+
+# Regenerate Swagger/OpenAPI docs (after modifying API comments)
+make swagger
+```
+
+### Frontend Development
+
+```bash
+cd web/frontend
+
+# Install dependencies
+npm install
+
+# Build for production
+npm run build
+
+# Development mode with watch
+npm run dev
+```
+
+### Running
+
+```bash
+# Initialize database and create admin user
+./cc-backend -init-db -add-user demo:admin:demo
+
+# Start server in development mode (enables GraphQL Playground and Swagger UI)
+./cc-backend -server -dev -loglevel info
+
+# Start demo with sample data
+./startDemo.sh
+```
+
+## Architecture
+
+### Backend Structure
+
+The backend follows a layered architecture with clear separation of concerns:
+
+- **cmd/cc-backend**: Entry point, orchestrates initialization of all subsystems
+- **internal/repository**: Data access layer using repository pattern
+  - Abstracts database operations (SQLite/MySQL)
+  - Implements LRU caching for performance
+  - Provides repositories for Job, User, Node, and Tag entities
+  - Transaction support for batch operations
+- **internal/api**: REST API endpoints (Swagger/OpenAPI documented)
+- **internal/graph**: GraphQL API (uses gqlgen)
+  - Schema in `api/*.graphqls`
+  - Generated code in `internal/graph/generated/`
+  - Resolvers in `internal/graph/schema.resolvers.go`
+- **internal/auth**: Authentication layer
+  - Supports local accounts, LDAP, OIDC, and JWT tokens
+  - Implements rate limiting for login attempts
+- **internal/metricdata**: Metric data repository abstraction
+  - Pluggable backends: cc-metric-store, Prometheus, InfluxDB
+  - Each cluster can have a different metric data backend
+- **internal/archiver**: Job archiving to file-based archive
+- **pkg/archive**: Job archive backend implementations
+  - File system backend (default)
+  - S3 backend
+  - SQLite backend (experimental)
+- **pkg/nats**: NATS integration for metric ingestion
+
+### Frontend Structure
+
+- **web/frontend**: Svelte 5 application
+  - Uses Rollup for building
+  - Components organized by feature (analysis, job, user, etc.)
+  - GraphQL client using @urql/svelte
+  - Bootstrap 5 + SvelteStrap for UI
+  - uPlot for time-series visualization
+- **web/templates**: Server-side Go templates
+
+### Key Concepts
+
+**Job Archive**: Completed jobs are stored in a file-based archive following the [ClusterCockpit job-archive specification](https://github.com/ClusterCockpit/cc-specifications/tree/master/job-archive). Each job has a `meta.json` file with metadata and metric data files.
+
+**Metric Data Repositories**: Time-series metric data is stored separately from job metadata. The system supports multiple backends (cc-metric-store is recommended). Configuration is per-cluster in `config.json`.
+
+**Authentication Flow**:
+1. Multiple authenticators can be configured (local, LDAP, OIDC, JWT)
+2. Each authenticator's `CanLogin` method is called to determine if it should handle the request
+3. The first authenticator that returns true performs the actual `Login`
+4. JWT tokens are used for API authentication
+
+**Database Migrations**: SQL migrations in `internal/repository/migrations/` are applied automatically on startup. Version tracking in `version` table.
+
+**Scopes**: Metrics can be collected at different scopes:
+- Node scope (always available)
+- Core scope (for jobs with ≤8 nodes)
+- Accelerator scope (for GPU/accelerator metrics)
+
+## Configuration
+
+- **config.json**: Main configuration (clusters, metric repositories, archive settings)
+- **.env**: Environment variables (secrets like JWT keys)
+  - Copy from `configs/env-template.txt`
+  - NEVER commit this file
+- **cluster.json**: Cluster topology and metric definitions (loaded from archive or config)
+
+## Database
+
+- Default: SQLite 3 (`./var/job.db`)
+- Optional: MySQL/MariaDB
+- Connection managed by `internal/repository`
+- Schema version in `internal/repository/migration.go`
+
+## Code Generation
+
+**GraphQL** (gqlgen):
+- Schema: `api/*.graphqls`
+- Config: `gqlgen.yml`
+- Generated code: `internal/graph/generated/`
+- Custom resolvers: `internal/graph/schema.resolvers.go`
+- Run `make graphql` after schema changes
+
+**Swagger/OpenAPI**:
+- Annotations in `internal/api/*.go`
+- Generated docs: `api/docs.go`, `api/swagger.yaml`
+- Run `make swagger` after API changes
+
+## Testing Conventions
+
+- Test files use `_test.go` suffix
+- Test data in `testdata/` subdirectories
+- Repository tests use in-memory SQLite
+- API tests use httptest
+
+## Common Workflows
+
+### Adding a new GraphQL field
+1. Edit schema in `api/*.graphqls`
+2. Run `make graphql`
+3. Implement resolver in `internal/graph/schema.resolvers.go`
+
+### Adding a new REST endpoint
+1. Add handler in `internal/api/*.go`
+2. Add route in `internal/api/rest.go`
+3. Add Swagger annotations
+4. Run `make swagger`
+
+### Adding a new metric data backend
+1. Implement `MetricDataRepository` interface in `internal/metricdata/`
+2. Register in `metricdata.Init()` switch statement
+3. Update config.json schema documentation
+
+### Modifying database schema
+1. Create new migration in `internal/repository/migrations/`
+2. Increment `repository.Version`
+3. Test with fresh database and existing database
+
+## Dependencies
+
+- Go 1.24.0+ (check go.mod for exact version)
+- Node.js (for frontend builds)
+- SQLite 3 or MySQL/MariaDB
+- Optional: NATS server for metric ingestion

From b35172e2f7bc56fad47a12ef36398ddba376d6db Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Sat, 20 Dec 2025 11:13:02 +0100
Subject: [PATCH 10/59] Add context information for CLAUDE coding agent

---
 CLAUDE.md | 33 +++++++++++++++++++++++++--------
 1 file changed, 25 insertions(+), 8 deletions(-)

diff --git a/CLAUDE.md b/CLAUDE.md
index 2bb08c98..379b4dbb 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -1,10 +1,14 @@
 # CLAUDE.md
 
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+This file provides guidance to Claude Code (claude.ai/code) when working with
+code in this repository.
 
 ## Project Overview
 
-ClusterCockpit is a job-specific performance monitoring framework for HPC clusters. This is a Golang backend that provides REST and GraphQL APIs, serves a Svelte-based frontend, and manages job archives and metric data from various time-series databases.
+ClusterCockpit is a job-specific performance monitoring framework for HPC
+clusters. This is a Golang backend that provides REST and GraphQL APIs, serves a
+Svelte-based frontend, and manages job archives and metric data from various
+time-series databases.
 
 ## Build and Development Commands
 
@@ -80,7 +84,7 @@ The backend follows a layered architecture with clear separation of concerns:
 
 - **cmd/cc-backend**: Entry point, orchestrates initialization of all subsystems
 - **internal/repository**: Data access layer using repository pattern
-  - Abstracts database operations (SQLite/MySQL)
+  - Abstracts database operations (SQLite3 only)
   - Implements LRU caching for performance
   - Provides repositories for Job, User, Node, and Tag entities
   - Transaction support for batch operations
@@ -114,19 +118,27 @@ The backend follows a layered architecture with clear separation of concerns:
 
 ### Key Concepts
 
-**Job Archive**: Completed jobs are stored in a file-based archive following the [ClusterCockpit job-archive specification](https://github.com/ClusterCockpit/cc-specifications/tree/master/job-archive). Each job has a `meta.json` file with metadata and metric data files.
+**Job Archive**: Completed jobs are stored in a file-based archive following the
+[ClusterCockpit job-archive
+specification](https://github.com/ClusterCockpit/cc-specifications/tree/master/job-archive).
+Each job has a `meta.json` file with metadata and metric data files.
 
-**Metric Data Repositories**: Time-series metric data is stored separately from job metadata. The system supports multiple backends (cc-metric-store is recommended). Configuration is per-cluster in `config.json`.
+**Metric Data Repositories**: Time-series metric data is stored separately from
+job metadata. The system supports multiple backends (cc-metric-store is
+recommended). Configuration is per-cluster in `config.json`.
 
 **Authentication Flow**:
+
 1. Multiple authenticators can be configured (local, LDAP, OIDC, JWT)
 2. Each authenticator's `CanLogin` method is called to determine if it should handle the request
 3. The first authenticator that returns true performs the actual `Login`
 4. JWT tokens are used for API authentication
 
-**Database Migrations**: SQL migrations in `internal/repository/migrations/` are applied automatically on startup. Version tracking in `version` table.
+**Database Migrations**: SQL migrations in `internal/repository/migrations/` are
+applied automatically on startup. Version tracking in `version` table.
 
 **Scopes**: Metrics can be collected at different scopes:
+
 - Node scope (always available)
 - Core scope (for jobs with ≤8 nodes)
 - Accelerator scope (for GPU/accelerator metrics)
@@ -142,13 +154,13 @@ The backend follows a layered architecture with clear separation of concerns:
 ## Database
 
 - Default: SQLite 3 (`./var/job.db`)
-- Optional: MySQL/MariaDB
 - Connection managed by `internal/repository`
 - Schema version in `internal/repository/migration.go`
 
 ## Code Generation
 
 **GraphQL** (gqlgen):
+
 - Schema: `api/*.graphqls`
 - Config: `gqlgen.yml`
 - Generated code: `internal/graph/generated/`
@@ -156,6 +168,7 @@ The backend follows a layered architecture with clear separation of concerns:
 - Run `make graphql` after schema changes
 
 **Swagger/OpenAPI**:
+
 - Annotations in `internal/api/*.go`
 - Generated docs: `api/docs.go`, `api/swagger.yaml`
 - Run `make swagger` after API changes
@@ -170,22 +183,26 @@ The backend follows a layered architecture with clear separation of concerns:
 ## Common Workflows
 
 ### Adding a new GraphQL field
+
 1. Edit schema in `api/*.graphqls`
 2. Run `make graphql`
 3. Implement resolver in `internal/graph/schema.resolvers.go`
 
 ### Adding a new REST endpoint
+
 1. Add handler in `internal/api/*.go`
 2. Add route in `internal/api/rest.go`
 3. Add Swagger annotations
 4. Run `make swagger`
 
 ### Adding a new metric data backend
+
 1. Implement `MetricDataRepository` interface in `internal/metricdata/`
 2. Register in `metricdata.Init()` switch statement
 3. Update config.json schema documentation
 
 ### Modifying database schema
+
 1. Create new migration in `internal/repository/migrations/`
 2. Increment `repository.Version`
 3. Test with fresh database and existing database
@@ -194,5 +211,5 @@ The backend follows a layered architecture with clear separation of concerns:
 
 - Go 1.24.0+ (check go.mod for exact version)
 - Node.js (for frontend builds)
-- SQLite 3 or MySQL/MariaDB
+- SQLite 3 (only supported database)
 - Optional: NATS server for metric ingestion

From 1cd4a57bd3206e1f3115c1cbc58fcad5cbfb87a5 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Sat, 20 Dec 2025 11:13:41 +0100
Subject: [PATCH 11/59] Remove support for mysql/mariadb

---
 README.md                                     |  11 +-
 cmd/cc-backend/init.go                        |   4 +-
 cmd/cc-backend/main.go                        |  19 ++-
 configs/config-mariadb.json                   |  64 ---------
 go.mod                                        |   2 -
 go.sum                                        |  49 +------
 init/clustercockpit.service                   |   2 +-
 internal/api/api_test.go                      |   2 +-
 internal/config/config.go                     |   4 +-
 internal/config/schema.go                     |   2 +-
 internal/importer/importer_test.go            |   2 +-
 internal/repository/dbConnection.go           |  56 ++++----
 internal/repository/job.go                    |  52 ++------
 internal/repository/migration.go              |  89 ++++---------
 .../migrations/mysql/01_init-schema.down.sql  |   5 -
 .../migrations/mysql/01_init-schema.up.sql    |  66 ----------
 .../migrations/mysql/02_add-index.down.sql    |   8 --
 .../migrations/mysql/02_add-index.up.sql      |   8 --
 .../mysql/03_add-userprojects.down.sql        |   1 -
 .../mysql/03_add-userprojects.up.sql          |   1 -
 .../mysql/04_alter-table-job.down.sql         |   5 -
 .../mysql/04_alter-table-job.up.sql           |   5 -
 .../migrations/mysql/05_extend-tags.down.sql  |   2 -
 .../migrations/mysql/05_extend-tags.up.sql    |   2 -
 .../mysql/06_change-config.down.sql           |   1 -
 .../migrations/mysql/06_change-config.up.sql  |   1 -
 .../migrations/mysql/07_fix-tag-id.down.sql   |   3 -
 .../migrations/mysql/07_fix-tag-id.up.sql     |   3 -
 .../mysql/08_add-footprint.down.sql           |  83 ------------
 .../migrations/mysql/08_add-footprint.up.sql  | 123 ------------------
 internal/repository/node_test.go              |   2 +-
 internal/repository/repository_test.go        |   2 +-
 internal/repository/stats.go                  |  49 +++----
 internal/repository/userConfig_test.go        |   2 +-
 internal/tagger/detectApp_test.go             |   2 +-
 35 files changed, 104 insertions(+), 628 deletions(-)
 delete mode 100644 configs/config-mariadb.json
 delete mode 100644 internal/repository/migrations/mysql/01_init-schema.down.sql
 delete mode 100644 internal/repository/migrations/mysql/01_init-schema.up.sql
 delete mode 100644 internal/repository/migrations/mysql/02_add-index.down.sql
 delete mode 100644 internal/repository/migrations/mysql/02_add-index.up.sql
 delete mode 100644 internal/repository/migrations/mysql/03_add-userprojects.down.sql
 delete mode 100644 internal/repository/migrations/mysql/03_add-userprojects.up.sql
 delete mode 100644 internal/repository/migrations/mysql/04_alter-table-job.down.sql
 delete mode 100644 internal/repository/migrations/mysql/04_alter-table-job.up.sql
 delete mode 100644 internal/repository/migrations/mysql/05_extend-tags.down.sql
 delete mode 100644 internal/repository/migrations/mysql/05_extend-tags.up.sql
 delete mode 100644 internal/repository/migrations/mysql/06_change-config.down.sql
 delete mode 100644 internal/repository/migrations/mysql/06_change-config.up.sql
 delete mode 100644 internal/repository/migrations/mysql/07_fix-tag-id.down.sql
 delete mode 100644 internal/repository/migrations/mysql/07_fix-tag-id.up.sql
 delete mode 100644 internal/repository/migrations/mysql/08_add-footprint.down.sql
 delete mode 100644 internal/repository/migrations/mysql/08_add-footprint.up.sql

diff --git a/README.md b/README.md
index 0799bd92..a0352d17 100644
--- a/README.md
+++ b/README.md
@@ -29,12 +29,11 @@ is also served by the backend using [Svelte](https://svelte.dev/) components.
 Layout and styling are based on [Bootstrap 5](https://getbootstrap.com/) using
 [Bootstrap Icons](https://icons.getbootstrap.com/).
 
-The backend uses [SQLite 3](https://sqlite.org/) as a relational SQL database by
-default. Optionally it can use a MySQL/MariaDB database server. While there are
-metric data backends for the InfluxDB and Prometheus time series databases, the
-only tested and supported setup is to use cc-metric-store as the metric data
-backend. Documentation on how to integrate ClusterCockpit with other time series
-databases will be added in the future.
+The backend uses [SQLite 3](https://sqlite.org/) as the relational SQL database.
+While there are metric data backends for the InfluxDB and Prometheus time series
+databases, the only tested and supported setup is to use cc-metric-store as the
+metric data backend. Documentation on how to integrate ClusterCockpit with other
+time series databases will be added in the future.
 
 Completed batch jobs are stored in a file-based job archive according to
 [this specification](https://github.com/ClusterCockpit/cc-specifications/tree/master/job-archive).
diff --git a/cmd/cc-backend/init.go b/cmd/cc-backend/init.go
index ee60b12c..151eee9e 100644
--- a/cmd/cc-backend/init.go
+++ b/cmd/cc-backend/init.go
@@ -105,9 +105,9 @@ func initEnv() {
 		cclog.Abortf("Could not create default ./var folder with permissions '0o777'. Application initialization failed, exited.\nError: %s\n", err.Error())
 	}
 
-	err := repository.MigrateDB("sqlite3", "./var/job.db")
+	err := repository.MigrateDB("./var/job.db")
 	if err != nil {
-		cclog.Abortf("Could not initialize default sqlite3 database as './var/job.db'. Application initialization failed, exited.\nError: %s\n", err.Error())
+		cclog.Abortf("Could not initialize default SQLite database as './var/job.db'. Application initialization failed, exited.\nError: %s\n", err.Error())
 	}
 	if err := os.Mkdir("var/job-archive", 0o777); err != nil {
 		cclog.Abortf("Could not create default ./var/job-archive folder with permissions '0o777'. Application initialization failed, exited.\nError: %s\n", err.Error())
diff --git a/cmd/cc-backend/main.go b/cmd/cc-backend/main.go
index 6239d36c..9464ccf4 100644
--- a/cmd/cc-backend/main.go
+++ b/cmd/cc-backend/main.go
@@ -40,7 +40,6 @@ import (
 	"github.com/google/gops/agent"
 	"github.com/joho/godotenv"
 
-	_ "github.com/go-sql-driver/mysql"
 	_ "github.com/mattn/go-sqlite3"
 )
 
@@ -120,30 +119,30 @@ func initDatabase() error {
 
 func handleDatabaseCommands() error {
 	if flagMigrateDB {
-		err := repository.MigrateDB(config.Keys.DBDriver, config.Keys.DB)
+		err := repository.MigrateDB(config.Keys.DB)
 		if err != nil {
 			return fmt.Errorf("migrating database to version %d: %w", repository.Version, err)
 		}
-		cclog.Exitf("MigrateDB Success: Migrated '%s' database at location '%s' to version %d.\n",
-			config.Keys.DBDriver, config.Keys.DB, repository.Version)
+		cclog.Exitf("MigrateDB Success: Migrated SQLite database at '%s' to version %d.\n",
+			config.Keys.DB, repository.Version)
 	}
 
 	if flagRevertDB {
-		err := repository.RevertDB(config.Keys.DBDriver, config.Keys.DB)
+		err := repository.RevertDB(config.Keys.DB)
 		if err != nil {
 			return fmt.Errorf("reverting database to version %d: %w", repository.Version-1, err)
 		}
-		cclog.Exitf("RevertDB Success: Reverted '%s' database at location '%s' to version %d.\n",
-			config.Keys.DBDriver, config.Keys.DB, repository.Version-1)
+		cclog.Exitf("RevertDB Success: Reverted SQLite database at '%s' to version %d.\n",
+			config.Keys.DB, repository.Version-1)
 	}
 
 	if flagForceDB {
-		err := repository.ForceDB(config.Keys.DBDriver, config.Keys.DB)
+		err := repository.ForceDB(config.Keys.DB)
 		if err != nil {
 			return fmt.Errorf("forcing database to version %d: %w", repository.Version, err)
 		}
-		cclog.Exitf("ForceDB Success: Forced '%s' database at location '%s' to version %d.\n",
-			config.Keys.DBDriver, config.Keys.DB, repository.Version)
+		cclog.Exitf("ForceDB Success: Forced SQLite database at '%s' to version %d.\n",
+			config.Keys.DB, repository.Version)
 	}
 
 	return nil
diff --git a/configs/config-mariadb.json b/configs/config-mariadb.json
deleted file mode 100644
index 38bb8a93..00000000
--- a/configs/config-mariadb.json
+++ /dev/null
@@ -1,64 +0,0 @@
-{
-  "addr": "127.0.0.1:8080",
-  "short-running-jobs-duration": 300,
-  "archive": {
-    "kind": "file",
-    "path": "./var/job-archive"
-  },
-  "jwts": {
-    "max-age": "2000h"
-  },
-  "db-driver": "mysql",
-  "db": "clustercockpit:demo@tcp(127.0.0.1:3306)/clustercockpit",
-  "enable-resampling": {
-    "trigger": 30,
-    "resolutions": [600, 300, 120, 60]
-  },
-  "emission-constant": 317,
-  "clusters": [
-    {
-      "name": "fritz",
-      "metricDataRepository": {
-        "kind": "cc-metric-store",
-        "url": "http://localhost:8082",
-        "token": ""
-      },
-      "filterRanges": {
-        "numNodes": {
-          "from": 1,
-          "to": 64
-        },
-        "duration": {
-          "from": 0,
-          "to": 86400
-        },
-        "startTime": {
-          "from": "2022-01-01T00:00:00Z",
-          "to": null
-        }
-      }
-    },
-    {
-      "name": "alex",
-      "metricDataRepository": {
-        "kind": "cc-metric-store",
-        "url": "http://localhost:8082",
-        "token": ""
-      },
-      "filterRanges": {
-        "numNodes": {
-          "from": 1,
-          "to": 64
-        },
-        "duration": {
-          "from": 0,
-          "to": 86400
-        },
-        "startTime": {
-          "from": "2022-01-01T00:00:00Z",
-          "to": null
-        }
-      }
-    }
-  ]
-}
diff --git a/go.mod b/go.mod
index df8e1fb9..eb061de7 100644
--- a/go.mod
+++ b/go.mod
@@ -21,7 +21,6 @@ require (
 	github.com/expr-lang/expr v1.17.6
 	github.com/go-co-op/gocron/v2 v2.18.2
 	github.com/go-ldap/ldap/v3 v3.4.12
-	github.com/go-sql-driver/mysql v1.9.3
 	github.com/golang-jwt/jwt/v5 v5.3.0
 	github.com/golang-migrate/migrate/v4 v4.19.1
 	github.com/google/gops v0.3.28
@@ -48,7 +47,6 @@ require (
 )
 
 require (
-	filippo.io/edwards25519 v1.1.0 // indirect
 	github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358 // indirect
 	github.com/KyleBanks/depth v1.2.1 // indirect
 	github.com/agnivade/levenshtein v1.2.1 // indirect
diff --git a/go.sum b/go.sum
index 711c5551..fd4980da 100644
--- a/go.sum
+++ b/go.sum
@@ -2,8 +2,6 @@ filippo.io/edwards25519 v1.1.0 h1:FNf4tywRC1HmFuKW5xopWpigGjJKiJSV0Cqo0cJWDaA=
 filippo.io/edwards25519 v1.1.0/go.mod h1:BxyFTGdWcka3PhytdK4V28tE5sGfRvvvRV7EaN4VDT4=
 github.com/99designs/gqlgen v0.17.84 h1:iVMdiStgUVx/BFkMb0J5GAXlqfqtQ7bqMCYK6v52kQ0=
 github.com/99designs/gqlgen v0.17.84/go.mod h1:qjoUqzTeiejdo+bwUg8unqSpeYG42XrcrQboGIezmFA=
-github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161 h1:L/gRVlceqvL25UVaW/CKtUDjefjrs0SPonmDGUVOYP0=
-github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161/go.mod h1:xomTg63KZ2rFqZQzSB4Vz2SUXa1BpHTVz9L5PTmPC4E=
 github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358 h1:mFRzDkZVAjdal+s7s0MwaRv9igoPqLRdzOLzw/8Xvq8=
 github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358/go.mod h1:chxPXzSsl7ZWRAuOIE23GDNzjWuZquvFlgA8xmpunjU=
 github.com/ClusterCockpit/cc-lib v1.0.2 h1:ZWn3oZkXgxrr3zSigBdlOOfayZ4Om4xL20DhmritPPg=
@@ -12,8 +10,6 @@ github.com/KyleBanks/depth v1.2.1 h1:5h8fQADFrWtarTdtDudMmGsC7GPbOAu6RVB3ffsVFHc
 github.com/KyleBanks/depth v1.2.1/go.mod h1:jzSb9d0L43HxTQfT+oSA1EEp2q+ne2uh6XgeJcm8brE=
 github.com/Masterminds/squirrel v1.5.4 h1:uUcX/aBc8O7Fg9kaISIUsHXdKuqehiXAMQTYX8afzqM=
 github.com/Masterminds/squirrel v1.5.4/go.mod h1:NNaOrjSoIDfDA40n7sr2tPNZRfjzjA400rg+riTZj10=
-github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
-github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
 github.com/NVIDIA/go-nvml v0.13.0-1 h1:OLX8Jq3dONuPOQPC7rndB6+iDmDakw0XTYgzMxObkEw=
 github.com/NVIDIA/go-nvml v0.13.0-1/go.mod h1:+KNA7c7gIBH7SKSJ1ntlwkfN80zdx8ovl4hrK3LmPt4=
 github.com/PuerkitoBio/goquery v1.11.0 h1:jZ7pwMQXIITcUXNH83LLk+txlaEy6NVOfTuP43xxfqw=
@@ -70,10 +66,6 @@ github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/containerd/errdefs v1.0.0 h1:tg5yIfIlQIrxYtu9ajqY42W3lpS19XqdxRQeEwYG8PI=
-github.com/containerd/errdefs v1.0.0/go.mod h1:+YBYIdtsnF4Iw6nWZhJcqGSg/dwvV7tyJ/kCkyJ2k+M=
-github.com/containerd/errdefs/pkg v0.3.0 h1:9IKJ06FvyNlexW690DXuQNx2KA2cUJXx151Xdx3ZPPE=
-github.com/containerd/errdefs/pkg v0.3.0/go.mod h1:NJw6s9HwNuRhnjJhM7pylWwMyAkmCQvQ4GpJHEqRLVk=
 github.com/coreos/go-oidc/v3 v3.16.0 h1:qRQUCFstKpXwmEjDQTIbyY/5jF00+asXzSkmkoa/mow=
 github.com/coreos/go-oidc/v3 v3.16.0/go.mod h1:wqPbKFrVnE90vty060SB40FCJ8fTHTxSwyXJqZH+sI8=
 github.com/cpuguy83/go-md2man/v2 v2.0.7 h1:zbFlGlXEAKlwXpmvle3d8Oe3YnkKIK4xSRTd3sHPnBo=
@@ -85,16 +77,6 @@ github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dgryski/trifles v0.0.0-20230903005119-f50d829f2e54 h1:SG7nF6SRlWhcT7cNTs5R6Hk4V2lcmLz2NsG2VnInyNo=
 github.com/dgryski/trifles v0.0.0-20230903005119-f50d829f2e54/go.mod h1:if7Fbed8SFyPtHLHbg49SI7NAdJiC5WIA09pe59rfAA=
-github.com/dhui/dktest v0.4.6 h1:+DPKyScKSEp3VLtbMDHcUq6V5Lm5zfZZVb0Sk7Ahom4=
-github.com/dhui/dktest v0.4.6/go.mod h1:JHTSYDtKkvFNFHJKqCzVzqXecyv+tKt8EzceOmQOgbU=
-github.com/distribution/reference v0.6.0 h1:0IXCQ5g4/QMHHkarYzh5l+u8T3t73zM5QvfrDyIgxBk=
-github.com/distribution/reference v0.6.0/go.mod h1:BbU0aIcezP1/5jX/8MP0YiH4SdvB5Y4f/wlDRiLyi3E=
-github.com/docker/docker v28.3.3+incompatible h1:Dypm25kh4rmk49v1eiVbsAtpAsYURjYkaKubwuBdxEI=
-github.com/docker/docker v28.3.3+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk=
-github.com/docker/go-connections v0.5.0 h1:USnMq7hx7gwdVZq1L49hLXaFtUdTADjXGp+uj1Br63c=
-github.com/docker/go-connections v0.5.0/go.mod h1:ov60Kzw0kKElRwhNs9UlUHAE/F9Fe6GLaXnqyDdmEXc=
-github.com/docker/go-units v0.5.0 h1:69rxXcBk27SvSaaxTtLh/8llcHD8vYHT7WSdRZ/jvr4=
-github.com/docker/go-units v0.5.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
 github.com/expr-lang/expr v1.17.6 h1:1h6i8ONk9cexhDmowO/A64VPxHScu7qfSl2k8OlINec=
 github.com/expr-lang/expr v1.17.6/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
 github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
@@ -113,10 +95,6 @@ github.com/go-jose/go-jose/v4 v4.1.3 h1:CVLmWDhDVRa6Mi/IgCgaopNosCaHz7zrMeF9MlZR
 github.com/go-jose/go-jose/v4 v4.1.3/go.mod h1:x4oUasVrzR7071A4TnHLGSPpNOm2a21K9Kf04k1rs08=
 github.com/go-ldap/ldap/v3 v3.4.12 h1:1b81mv7MagXZ7+1r7cLTWmyuTqVqdwbtJSjC0DAp9s4=
 github.com/go-ldap/ldap/v3 v3.4.12/go.mod h1:+SPAGcTtOfmGsCb3h1RFiq4xpp4N636G75OEace8lNo=
-github.com/go-logr/logr v1.4.3 h1:CjnDlHq8ikf6E492q6eKboGOC0T8CDaOvkHCIg8idEI=
-github.com/go-logr/logr v1.4.3/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
-github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
-github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
 github.com/go-openapi/jsonpointer v0.22.3 h1:dKMwfV4fmt6Ah90zloTbUKWMD+0he+12XYAsPotrkn8=
 github.com/go-openapi/jsonpointer v0.22.3/go.mod h1:0lBbqeRsQ5lIanv3LHZBrmRGHLHcQoOXQnf88fHlGWo=
 github.com/go-openapi/jsonreference v0.21.3 h1:96Dn+MRPa0nYAR8DR1E03SblB5FJvh7W6krPI0Z7qMc=
@@ -145,15 +123,12 @@ github.com/go-openapi/testify/enable/yaml/v2 v2.0.2/go.mod h1:kme83333GCtJQHXQ8U
 github.com/go-openapi/testify/v2 v2.0.2 h1:X999g3jeLcoY8qctY/c/Z8iBHTbwLz7R2WXd6Ub6wls=
 github.com/go-openapi/testify/v2 v2.0.2/go.mod h1:HCPmvFFnheKK2BuwSA0TbbdxJ3I16pjwMkYkP4Ywn54=
 github.com/go-sql-driver/mysql v1.4.1/go.mod h1:zAC/RDZ24gD3HViQzih4MyKcchzm+sOG5ZlKdlhCg5w=
+github.com/go-sql-driver/mysql v1.8.1 h1:LedoTUt/eveggdHS9qUFC1EFSa8bU2+1pZjSRpvNJ1Y=
 github.com/go-sql-driver/mysql v1.8.1/go.mod h1:wEBSXgmK//2ZFJyE+qWnIsVGmvmEKlqwuVSjsCm7DZg=
-github.com/go-sql-driver/mysql v1.9.3 h1:U/N249h2WzJ3Ukj8SowVFjdtZKfu9vlLZxjPXV1aweo=
-github.com/go-sql-driver/mysql v1.9.3/go.mod h1:qn46aNg1333BRMNU69Lq93t8du/dwxI64Gl8i5p1WMU=
 github.com/go-viper/mapstructure/v2 v2.4.0 h1:EBsztssimR/CONLSZZ04E8qAkxNYq4Qp9LvH92wZUgs=
 github.com/go-viper/mapstructure/v2 v2.4.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
 github.com/goccy/go-yaml v1.19.0 h1:EmkZ9RIsX+Uq4DYFowegAuJo8+xdX3T/2dwNPXbxEYE=
 github.com/goccy/go-yaml v1.19.0/go.mod h1:XBurs7gK8ATbW4ZPGKgcbrY1Br56PdM69F7LkFRi1kA=
-github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
-github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
 github.com/golang-jwt/jwt/v5 v5.3.0 h1:pv4AsKCKKZuqlgs5sUmn4x8UlGa0kEVt/puTpKx9vvo=
 github.com/golang-jwt/jwt/v5 v5.3.0/go.mod h1:fxCRLWMO43lRc8nhHWY6LGqRcf+1gQWArsqaEUEa5bE=
 github.com/golang-migrate/migrate/v4 v4.19.1 h1:OCyb44lFuQfYXYLx1SCxPZQGU7mcaZ7gH9yH4jSFbBA=
@@ -241,17 +216,11 @@ github.com/mattn/go-sqlite3 v1.10.0/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsO
 github.com/mattn/go-sqlite3 v1.14.22/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
 github.com/mattn/go-sqlite3 v1.14.32 h1:JD12Ag3oLy1zQA+BNn74xRgaBbdhbNIDYvQUEuuErjs=
 github.com/mattn/go-sqlite3 v1.14.32/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
-github.com/moby/docker-image-spec v1.3.1 h1:jMKff3w6PgbfSa69GfNg+zN/XLhfXJGnEx3Nl2EsFP0=
-github.com/moby/docker-image-spec v1.3.1/go.mod h1:eKmb5VW8vQEh/BAr2yvVNvuiJuY6UIocYsFu/DxxRpo=
-github.com/moby/term v0.5.0 h1:xt8Q1nalod/v7BqbG21f8mQPqH+xAaC9C3N3wfWbVP0=
-github.com/moby/term v0.5.0/go.mod h1:8FzsFHVUBGZdbDsJw/ot+X+d5HLUbvklYLJ9uGfcI3Y=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
-github.com/morikuni/aec v1.0.0 h1:nP9CBfwrvYnBRgY6qfDQkygYDmYwOilePFkwzv4dU8A=
-github.com/morikuni/aec v1.0.0/go.mod h1:BbKIizmSmc5MMPqRYbxO4ZU0S0+P200+tUnFx7PXmsc=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
 github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f h1:KUppIJq7/+SVif2QVs3tOP0zanoHgBEVAwHxUSIzRqU=
@@ -265,13 +234,7 @@ github.com/nats-io/nuid v1.0.1/go.mod h1:19wcPz3Ph3q0Jbyiqsd0kePYG7A95tJPxeL+1OS
 github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
 github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmtpMYro=
 github.com/oapi-codegen/runtime v1.1.1/go.mod h1:SK9X900oXmPWilYR5/WKPzt3Kqxn/uS/+lbpREv+eCg=
-github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
-github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM=
-github.com/opencontainers/image-spec v1.1.0 h1:8SG7/vwALn54lVB/0yZ/MMwhFrPYtpEHQb2IpWsCzug=
-github.com/opencontainers/image-spec v1.1.0/go.mod h1:W4s4sFTMaBeK1BQLXbG4AdM2szdn85PY75RI83NrTrM=
 github.com/opentracing/opentracing-go v1.1.0/go.mod h1:UkNAQd3GIcIGf0SeVgPpRdFStlNbqXla1AfSYxPUl2o=
-github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
-github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
@@ -323,16 +286,6 @@ github.com/vektah/gqlparser/v2 v2.5.31/go.mod h1:c1I28gSOVNzlfc4WuDlqU7voQnsqI6O
 github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342 h1:FnBeRrxr7OU4VvAzt5X7s6266i6cSVkkFPS0TuXWbIg=
 github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342/go.mod h1:Ohn+xnUBiLI6FVj/9LpzZWtj1/D6lUovWYBkxHVV3aM=
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
-go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
-go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
-go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0 h1:F7Jx+6hwnZ41NSFTO5q4LYDtJRXBf2PD0rNBkeB/lus=
-go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0/go.mod h1:UHB22Z8QsdRDrnAtX4PntOl36ajSxcdUMt1sF7Y6E7Q=
-go.opentelemetry.io/otel v1.37.0 h1:9zhNfelUvx0KBfu/gb+ZgeAfAgtWrfHJZcAqFC228wQ=
-go.opentelemetry.io/otel v1.37.0/go.mod h1:ehE/umFRLnuLa/vSccNq9oS1ErUlkkK71gMcN34UG8I=
-go.opentelemetry.io/otel/metric v1.37.0 h1:mvwbQS5m0tbmqML4NqK+e3aDiO02vsf/WgbsdpcPoZE=
-go.opentelemetry.io/otel/metric v1.37.0/go.mod h1:04wGrZurHYKOc+RKeye86GwKiTb9FKm1WHtO+4EVr2E=
-go.opentelemetry.io/otel/trace v1.37.0 h1:HLdcFNbRQBE2imdSEgm/kwqmQj1Or1l/7bW6mxVK7z4=
-go.opentelemetry.io/otel/trace v1.37.0/go.mod h1:TlgrlQ+PtQO5XFerSPUYG0JSgGyryXewPGyayAWSBS0=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
 go.yaml.in/yaml/v2 v2.4.3 h1:6gvOSjQoTB3vt1l+CU+tSyi/HOjfOjRLJ4YwYZGwRO0=
diff --git a/init/clustercockpit.service b/init/clustercockpit.service
index 0a9448de..b4ed8bfa 100644
--- a/init/clustercockpit.service
+++ b/init/clustercockpit.service
@@ -3,7 +3,7 @@ Description=ClusterCockpit Web Server
 Documentation=https://github.com/ClusterCockpit/cc-backend
 Wants=network-online.target
 After=network-online.target
-After=mariadb.service mysql.service
+# Database is file-based SQLite - no service dependency required
 
 [Service]
 WorkingDirectory=/opt/monitoring/cc-backend
diff --git a/internal/api/api_test.go b/internal/api/api_test.go
index 70b0f0aa..d311767c 100644
--- a/internal/api/api_test.go
+++ b/internal/api/api_test.go
@@ -141,7 +141,7 @@ func setup(t *testing.T) *api.RestAPI {
 	}
 
 	dbfilepath := filepath.Join(tmpdir, "test.db")
-	err := repository.MigrateDB("sqlite3", dbfilepath)
+	err := repository.MigrateDB(dbfilepath)
 	if err != nil {
 		t.Fatal(err)
 	}
diff --git a/internal/config/config.go b/internal/config/config.go
index 25ca27eb..b7b8ed06 100644
--- a/internal/config/config.go
+++ b/internal/config/config.go
@@ -37,10 +37,10 @@ type ProgramConfig struct {
 	EmbedStaticFiles bool   `json:"embed-static-files"`
 	StaticFiles      string `json:"static-files"`
 
-	// 'sqlite3' or 'mysql' (mysql will work for mariadb as well)
+	// Database driver - only 'sqlite3' is supported
 	DBDriver string `json:"db-driver"`
 
-	// For sqlite3 a filename, for mysql a DSN in this format: https://github.com/go-sql-driver/mysql#dsn-data-source-name (Without query parameters!).
+	// Path to SQLite database file
 	DB string `json:"db"`
 
 	// Keep all metric data in the metric data repositories,
diff --git a/internal/config/schema.go b/internal/config/schema.go
index ed1f42d8..b171f96a 100644
--- a/internal/config/schema.go
+++ b/internal/config/schema.go
@@ -41,7 +41,7 @@ var configSchema = `
       "type": "string"
     },
     "db": {
-      "description": "For sqlite3 a filename, for mysql a DSN in this format: https://github.com/go-sql-driver/mysql#dsn-data-source-name (Without query parameters!).",
+      "description": "Path to SQLite database file (e.g., './var/job.db')",
       "type": "string"
     },
     "disable-archive": {
diff --git a/internal/importer/importer_test.go b/internal/importer/importer_test.go
index 2aa007da..470f7603 100644
--- a/internal/importer/importer_test.go
+++ b/internal/importer/importer_test.go
@@ -107,7 +107,7 @@ func setup(t *testing.T) *repository.JobRepository {
 	}
 
 	dbfilepath := filepath.Join(tmpdir, "test.db")
-	err := repository.MigrateDB("sqlite3", dbfilepath)
+	err := repository.MigrateDB(dbfilepath)
 	if err != nil {
 		t.Fatal(err)
 	}
diff --git a/internal/repository/dbConnection.go b/internal/repository/dbConnection.go
index 1c14c956..0f7536b7 100644
--- a/internal/repository/dbConnection.go
+++ b/internal/repository/dbConnection.go
@@ -55,6 +55,10 @@ func Connect(driver string, db string) {
 	var err error
 	var dbHandle *sqlx.DB
 
+	if driver != "sqlite3" {
+		cclog.Abortf("Unsupported database driver '%s'. Only 'sqlite3' is supported.\n", driver)
+	}
+
 	dbConnOnce.Do(func() {
 		opts := DatabaseOptions{
 			URL:                   db,
@@ -64,39 +68,31 @@ func Connect(driver string, db string) {
 			ConnectionMaxIdleTime: repoConfig.ConnectionMaxIdleTime,
 		}
 
-		switch driver {
-		case "sqlite3":
-			// TODO: Have separate DB handles for Writes and Reads
-			// Optimize SQLite connection: https://kerkour.com/sqlite-for-servers
-			connectionURLParams := make(url.Values)
-			connectionURLParams.Add("_txlock", "immediate")
-			connectionURLParams.Add("_journal_mode", "WAL")
-			connectionURLParams.Add("_busy_timeout", "5000")
-			connectionURLParams.Add("_synchronous", "NORMAL")
-			connectionURLParams.Add("_cache_size", "1000000000")
-			connectionURLParams.Add("_foreign_keys", "true")
-			opts.URL = fmt.Sprintf("file:%s?%s", opts.URL, connectionURLParams.Encode())
+		// TODO: Have separate DB handles for Writes and Reads
+		// Optimize SQLite connection: https://kerkour.com/sqlite-for-servers
+		connectionURLParams := make(url.Values)
+		connectionURLParams.Add("_txlock", "immediate")
+		connectionURLParams.Add("_journal_mode", "WAL")
+		connectionURLParams.Add("_busy_timeout", "5000")
+		connectionURLParams.Add("_synchronous", "NORMAL")
+		connectionURLParams.Add("_cache_size", "1000000000")
+		connectionURLParams.Add("_foreign_keys", "true")
+		opts.URL = fmt.Sprintf("file:%s?%s", opts.URL, connectionURLParams.Encode())
 
-			if cclog.Loglevel() == "debug" {
-				sql.Register("sqlite3WithHooks", sqlhooks.Wrap(&sqlite3.SQLiteDriver{}, &Hooks{}))
-				dbHandle, err = sqlx.Open("sqlite3WithHooks", opts.URL)
-			} else {
-				dbHandle, err = sqlx.Open("sqlite3", opts.URL)
-			}
-
-			err = setupSqlite(dbHandle.DB)
-			if err != nil {
-				cclog.Abortf("Failed sqlite db setup.\nError: %s\n", err.Error())
-			}
-		case "mysql":
-			opts.URL += "?multiStatements=true"
-			dbHandle, err = sqlx.Open("mysql", opts.URL)
-		default:
-			cclog.Abortf("DB Connection: Unsupported database driver '%s'.\n", driver)
+		if cclog.Loglevel() == "debug" {
+			sql.Register("sqlite3WithHooks", sqlhooks.Wrap(&sqlite3.SQLiteDriver{}, &Hooks{}))
+			dbHandle, err = sqlx.Open("sqlite3WithHooks", opts.URL)
+		} else {
+			dbHandle, err = sqlx.Open("sqlite3", opts.URL)
 		}
 
 		if err != nil {
-			cclog.Abortf("DB Connection: Could not connect to '%s' database with sqlx.Open().\nError: %s\n", driver, err.Error())
+			cclog.Abortf("DB Connection: Could not connect to SQLite database with sqlx.Open().\nError: %s\n", err.Error())
+		}
+
+		err = setupSqlite(dbHandle.DB)
+		if err != nil {
+			cclog.Abortf("Failed sqlite db setup.\nError: %s\n", err.Error())
 		}
 
 		dbHandle.SetMaxOpenConns(opts.MaxOpenConnections)
@@ -105,7 +101,7 @@ func Connect(driver string, db string) {
 		dbHandle.SetConnMaxIdleTime(opts.ConnectionMaxIdleTime)
 
 		dbConnInstance = &DBConnection{DB: dbHandle, Driver: driver}
-		err = checkDBVersion(driver, dbHandle.DB)
+		err = checkDBVersion(dbHandle.DB)
 		if err != nil {
 			cclog.Abortf("DB Connection: Failed DB version check.\nError: %s\n", err.Error())
 		}
diff --git a/internal/repository/job.go b/internal/repository/job.go
index f23a14cf..47959379 100644
--- a/internal/repository/job.go
+++ b/internal/repository/job.go
@@ -14,8 +14,6 @@
 // Initialize the database connection before using any repository:
 //
 //	repository.Connect("sqlite3", "./var/job.db")
-//	// or for MySQL:
-//	repository.Connect("mysql", "user:password@tcp(localhost:3306)/dbname")
 //
 // # Configuration
 //
@@ -158,52 +156,22 @@ func scanJob(row interface{ Scan(...any) error }) (*schema.Job, error) {
 }
 
 func (r *JobRepository) Optimize() error {
-	var err error
-
-	switch r.driver {
-	case "sqlite3":
-		if _, err = r.DB.Exec(`VACUUM`); err != nil {
-			return err
-		}
-	case "mysql":
-		cclog.Info("Optimize currently not supported for mysql driver")
+	if _, err := r.DB.Exec(`VACUUM`); err != nil {
+		return err
 	}
-
 	return nil
 }
 
 func (r *JobRepository) Flush() error {
-	var err error
-
-	switch r.driver {
-	case "sqlite3":
-		if _, err = r.DB.Exec(`DELETE FROM jobtag`); err != nil {
-			return err
-		}
-		if _, err = r.DB.Exec(`DELETE FROM tag`); err != nil {
-			return err
-		}
-		if _, err = r.DB.Exec(`DELETE FROM job`); err != nil {
-			return err
-		}
-	case "mysql":
-		if _, err = r.DB.Exec(`SET FOREIGN_KEY_CHECKS = 0`); err != nil {
-			return err
-		}
-		if _, err = r.DB.Exec(`TRUNCATE TABLE jobtag`); err != nil {
-			return err
-		}
-		if _, err = r.DB.Exec(`TRUNCATE TABLE tag`); err != nil {
-			return err
-		}
-		if _, err = r.DB.Exec(`TRUNCATE TABLE job`); err != nil {
-			return err
-		}
-		if _, err = r.DB.Exec(`SET FOREIGN_KEY_CHECKS = 1`); err != nil {
-			return err
-		}
+	if _, err := r.DB.Exec(`DELETE FROM jobtag`); err != nil {
+		return err
+	}
+	if _, err := r.DB.Exec(`DELETE FROM tag`); err != nil {
+		return err
+	}
+	if _, err := r.DB.Exec(`DELETE FROM job`); err != nil {
+		return err
 	}
-
 	return nil
 }
 
diff --git a/internal/repository/migration.go b/internal/repository/migration.go
index dec93a94..43e913cc 100644
--- a/internal/repository/migration.go
+++ b/internal/repository/migration.go
@@ -12,7 +12,6 @@ import (
 
 	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 	"github.com/golang-migrate/migrate/v4"
-	"github.com/golang-migrate/migrate/v4/database/mysql"
 	"github.com/golang-migrate/migrate/v4/database/sqlite3"
 	"github.com/golang-migrate/migrate/v4/source/iofs"
 )
@@ -22,40 +21,19 @@ const Version uint = 10
 //go:embed migrations/*
 var migrationFiles embed.FS
 
-func checkDBVersion(backend string, db *sql.DB) error {
-	var m *migrate.Migrate
+func checkDBVersion(db *sql.DB) error {
+	driver, err := sqlite3.WithInstance(db, &sqlite3.Config{})
+	if err != nil {
+		return err
+	}
+	d, err := iofs.New(migrationFiles, "migrations/sqlite3")
+	if err != nil {
+		return err
+	}
 
-	switch backend {
-	case "sqlite3":
-		driver, err := sqlite3.WithInstance(db, &sqlite3.Config{})
-		if err != nil {
-			return err
-		}
-		d, err := iofs.New(migrationFiles, "migrations/sqlite3")
-		if err != nil {
-			return err
-		}
-
-		m, err = migrate.NewWithInstance("iofs", d, "sqlite3", driver)
-		if err != nil {
-			return err
-		}
-	case "mysql":
-		driver, err := mysql.WithInstance(db, &mysql.Config{})
-		if err != nil {
-			return err
-		}
-		d, err := iofs.New(migrationFiles, "migrations/mysql")
-		if err != nil {
-			return err
-		}
-
-		m, err = migrate.NewWithInstance("iofs", d, "mysql", driver)
-		if err != nil {
-			return err
-		}
-	default:
-		cclog.Abortf("Migration: Unsupported database backend '%s'.\n", backend)
+	m, err := migrate.NewWithInstance("iofs", d, "sqlite3", driver)
+	if err != nil {
+		return err
 	}
 
 	v, dirty, err := m.Version()
@@ -80,37 +58,22 @@ func checkDBVersion(backend string, db *sql.DB) error {
 	return nil
 }
 
-func getMigrateInstance(backend string, db string) (m *migrate.Migrate, err error) {
-	switch backend {
-	case "sqlite3":
-		d, err := iofs.New(migrationFiles, "migrations/sqlite3")
-		if err != nil {
-			cclog.Fatal(err)
-		}
+func getMigrateInstance(db string) (m *migrate.Migrate, err error) {
+	d, err := iofs.New(migrationFiles, "migrations/sqlite3")
+	if err != nil {
+		return nil, err
+	}
 
-		m, err = migrate.NewWithSourceInstance("iofs", d, fmt.Sprintf("sqlite3://%s?_foreign_keys=on", db))
-		if err != nil {
-			return m, err
-		}
-	case "mysql":
-		d, err := iofs.New(migrationFiles, "migrations/mysql")
-		if err != nil {
-			return m, err
-		}
-
-		m, err = migrate.NewWithSourceInstance("iofs", d, fmt.Sprintf("mysql://%s?multiStatements=true", db))
-		if err != nil {
-			return m, err
-		}
-	default:
-		cclog.Abortf("Migration: Unsupported database backend '%s'.\n", backend)
+	m, err = migrate.NewWithSourceInstance("iofs", d, fmt.Sprintf("sqlite3://%s?_foreign_keys=on", db))
+	if err != nil {
+		return nil, err
 	}
 
 	return m, nil
 }
 
-func MigrateDB(backend string, db string) error {
-	m, err := getMigrateInstance(backend, db)
+func MigrateDB(db string) error {
+	m, err := getMigrateInstance(db)
 	if err != nil {
 		return err
 	}
@@ -144,8 +107,8 @@ func MigrateDB(backend string, db string) error {
 	return nil
 }
 
-func RevertDB(backend string, db string) error {
-	m, err := getMigrateInstance(backend, db)
+func RevertDB(db string) error {
+	m, err := getMigrateInstance(db)
 	if err != nil {
 		return err
 	}
@@ -162,8 +125,8 @@ func RevertDB(backend string, db string) error {
 	return nil
 }
 
-func ForceDB(backend string, db string) error {
-	m, err := getMigrateInstance(backend, db)
+func ForceDB(db string) error {
+	m, err := getMigrateInstance(db)
 	if err != nil {
 		return err
 	}
diff --git a/internal/repository/migrations/mysql/01_init-schema.down.sql b/internal/repository/migrations/mysql/01_init-schema.down.sql
deleted file mode 100644
index 68da6469..00000000
--- a/internal/repository/migrations/mysql/01_init-schema.down.sql
+++ /dev/null
@@ -1,5 +0,0 @@
-DROP TABLE IF EXISTS job;
-DROP TABLE IF EXISTS tags;
-DROP TABLE IF EXISTS jobtag;
-DROP TABLE IF EXISTS configuration;
-DROP TABLE IF EXISTS user;
diff --git a/internal/repository/migrations/mysql/01_init-schema.up.sql b/internal/repository/migrations/mysql/01_init-schema.up.sql
deleted file mode 100644
index 3a6930cd..00000000
--- a/internal/repository/migrations/mysql/01_init-schema.up.sql
+++ /dev/null
@@ -1,66 +0,0 @@
-CREATE TABLE IF NOT EXISTS job (
-    id                INTEGER AUTO_INCREMENT PRIMARY KEY ,
-    job_id            BIGINT NOT NULL,
-    cluster           VARCHAR(255) NOT NULL,
-    subcluster        VARCHAR(255) NOT NULL,
-    start_time        BIGINT NOT NULL, -- Unix timestamp
-
-    user              VARCHAR(255) NOT NULL,
-    project           VARCHAR(255) NOT NULL,
-    `partition`       VARCHAR(255) NOT NULL,
-    array_job_id      BIGINT NOT NULL,
-    duration          INT NOT NULL DEFAULT 0,
-    walltime          INT NOT NULL DEFAULT 0,
-    job_state         VARCHAR(255) NOT NULL 
-    CHECK(job_state IN ('running', 'completed', 'failed', 'cancelled',
-            'stopped', 'timeout', 'preempted', 'out_of_memory')),
-    meta_data         TEXT,          -- JSON
-    resources         TEXT NOT NULL, -- JSON
-
-    num_nodes         INT NOT NULL,
-    num_hwthreads     INT NOT NULL,
-    num_acc           INT NOT NULL,
-    smt               TINYINT NOT NULL DEFAULT 1 CHECK(smt               IN (0, 1   )),
-    exclusive         TINYINT NOT NULL DEFAULT 1 CHECK(exclusive         IN (0, 1, 2)),
-    monitoring_status TINYINT NOT NULL DEFAULT 1 CHECK(monitoring_status IN (0, 1, 2, 3)),
-
-    mem_used_max        REAL NOT NULL DEFAULT 0.0,
-    flops_any_avg       REAL NOT NULL DEFAULT 0.0,
-    mem_bw_avg          REAL NOT NULL DEFAULT 0.0,
-    load_avg            REAL NOT NULL DEFAULT 0.0,
-    net_bw_avg          REAL NOT NULL DEFAULT 0.0,
-    net_data_vol_total  REAL NOT NULL DEFAULT 0.0,
-    file_bw_avg         REAL NOT NULL DEFAULT 0.0,
-    file_data_vol_total REAL NOT NULL DEFAULT 0.0,
-    UNIQUE (job_id, cluster, start_time)
-    );
-
-CREATE TABLE IF NOT EXISTS tag (
-    id       INTEGER PRIMARY KEY,
-    tag_type VARCHAR(255) NOT NULL,
-    tag_name VARCHAR(255) NOT NULL,
-    UNIQUE (tag_type, tag_name));
-
-CREATE TABLE IF NOT EXISTS jobtag (
-    job_id INTEGER,
-    tag_id INTEGER,
-    PRIMARY KEY (job_id, tag_id),
-    FOREIGN KEY (job_id) REFERENCES job (id) ON DELETE CASCADE,
-    FOREIGN KEY (tag_id) REFERENCES tag (id) ON DELETE CASCADE);
-
-CREATE TABLE IF NOT EXISTS user (
-	username varchar(255) PRIMARY KEY NOT NULL,
-	password varchar(255) DEFAULT NULL,
-	ldap     tinyint      NOT NULL DEFAULT 0, /* col called "ldap" for historic reasons, fills the "AuthSource" */
-	name     varchar(255) DEFAULT NULL,
-	roles    varchar(255) NOT NULL DEFAULT "[]",
-	email    varchar(255) DEFAULT NULL);
-
-CREATE TABLE IF NOT EXISTS configuration (
-	username varchar(255),
-	confkey  varchar(255),
-	value    varchar(255),
-	PRIMARY KEY (username, confkey),
-	FOREIGN KEY (username) REFERENCES user (username) ON DELETE CASCADE ON UPDATE NO ACTION);
-
-
diff --git a/internal/repository/migrations/mysql/02_add-index.down.sql b/internal/repository/migrations/mysql/02_add-index.down.sql
deleted file mode 100644
index 1392c45c..00000000
--- a/internal/repository/migrations/mysql/02_add-index.down.sql
+++ /dev/null
@@ -1,8 +0,0 @@
-DROP INDEX IF EXISTS job_stats;
-DROP INDEX IF EXISTS job_by_user;
-DROP INDEX IF EXISTS job_by_starttime;
-DROP INDEX IF EXISTS job_by_job_id;
-DROP INDEX IF EXISTS job_list;
-DROP INDEX IF EXISTS job_list_user;
-DROP INDEX IF EXISTS job_list_users;
-DROP INDEX IF EXISTS job_list_users_start;
diff --git a/internal/repository/migrations/mysql/02_add-index.up.sql b/internal/repository/migrations/mysql/02_add-index.up.sql
deleted file mode 100644
index 2524bd93..00000000
--- a/internal/repository/migrations/mysql/02_add-index.up.sql
+++ /dev/null
@@ -1,8 +0,0 @@
-CREATE INDEX IF NOT EXISTS job_stats        ON job (cluster,subcluster,user);
-CREATE INDEX IF NOT EXISTS job_by_user      ON job (user);
-CREATE INDEX IF NOT EXISTS job_by_starttime ON job (start_time);
-CREATE INDEX IF NOT EXISTS job_by_job_id    ON job (job_id);
-CREATE INDEX IF NOT EXISTS job_list         ON job (cluster, job_state);
-CREATE INDEX IF NOT EXISTS job_list_user    ON job (user, cluster, job_state);
-CREATE INDEX IF NOT EXISTS job_list_users   ON job (user, job_state);
-CREATE INDEX IF NOT EXISTS job_list_users_start ON job (start_time, user, job_state);
diff --git a/internal/repository/migrations/mysql/03_add-userprojects.down.sql b/internal/repository/migrations/mysql/03_add-userprojects.down.sql
deleted file mode 100644
index bbf1e649..00000000
--- a/internal/repository/migrations/mysql/03_add-userprojects.down.sql
+++ /dev/null
@@ -1 +0,0 @@
-ALTER TABLE user DROP COLUMN projects;
diff --git a/internal/repository/migrations/mysql/03_add-userprojects.up.sql b/internal/repository/migrations/mysql/03_add-userprojects.up.sql
deleted file mode 100644
index d0f19c21..00000000
--- a/internal/repository/migrations/mysql/03_add-userprojects.up.sql
+++ /dev/null
@@ -1 +0,0 @@
-ALTER TABLE user ADD COLUMN projects varchar(255) NOT NULL DEFAULT "[]";
diff --git a/internal/repository/migrations/mysql/04_alter-table-job.down.sql b/internal/repository/migrations/mysql/04_alter-table-job.down.sql
deleted file mode 100644
index ebc74549..00000000
--- a/internal/repository/migrations/mysql/04_alter-table-job.down.sql
+++ /dev/null
@@ -1,5 +0,0 @@
-ALTER TABLE job
-    MODIFY `partition` VARCHAR(255) NOT NULL,
-    MODIFY array_job_id BIGINT NOT NULL,
-    MODIFY num_hwthreads INT NOT NULL,
-    MODIFY num_acc INT NOT NULL;
diff --git a/internal/repository/migrations/mysql/04_alter-table-job.up.sql b/internal/repository/migrations/mysql/04_alter-table-job.up.sql
deleted file mode 100644
index 9fe76208..00000000
--- a/internal/repository/migrations/mysql/04_alter-table-job.up.sql
+++ /dev/null
@@ -1,5 +0,0 @@
-ALTER TABLE job
-    MODIFY `partition` VARCHAR(255),
-    MODIFY array_job_id BIGINT,
-    MODIFY num_hwthreads INT,
-    MODIFY num_acc INT;
diff --git a/internal/repository/migrations/mysql/05_extend-tags.down.sql b/internal/repository/migrations/mysql/05_extend-tags.down.sql
deleted file mode 100644
index 925c9f8f..00000000
--- a/internal/repository/migrations/mysql/05_extend-tags.down.sql
+++ /dev/null
@@ -1,2 +0,0 @@
-ALTER TABLE tag DROP COLUMN insert_time;
-ALTER TABLE jobtag DROP COLUMN insert_time;
diff --git a/internal/repository/migrations/mysql/05_extend-tags.up.sql b/internal/repository/migrations/mysql/05_extend-tags.up.sql
deleted file mode 100644
index 4577564a..00000000
--- a/internal/repository/migrations/mysql/05_extend-tags.up.sql
+++ /dev/null
@@ -1,2 +0,0 @@
-ALTER TABLE tag ADD COLUMN insert_time TIMESTAMP DEFAULT CURRENT_TIMESTAMP;
-ALTER TABLE jobtag ADD COLUMN insert_time TIMESTAMP DEFAULT CURRENT_TIMESTAMP;
diff --git a/internal/repository/migrations/mysql/06_change-config.down.sql b/internal/repository/migrations/mysql/06_change-config.down.sql
deleted file mode 100644
index 0651790c..00000000
--- a/internal/repository/migrations/mysql/06_change-config.down.sql
+++ /dev/null
@@ -1 +0,0 @@
-ALTER TABLE configuration MODIFY value VARCHAR(255);
diff --git a/internal/repository/migrations/mysql/06_change-config.up.sql b/internal/repository/migrations/mysql/06_change-config.up.sql
deleted file mode 100644
index e35ff195..00000000
--- a/internal/repository/migrations/mysql/06_change-config.up.sql
+++ /dev/null
@@ -1 +0,0 @@
-ALTER TABLE configuration MODIFY value TEXT;
diff --git a/internal/repository/migrations/mysql/07_fix-tag-id.down.sql b/internal/repository/migrations/mysql/07_fix-tag-id.down.sql
deleted file mode 100644
index 9f9959ac..00000000
--- a/internal/repository/migrations/mysql/07_fix-tag-id.down.sql
+++ /dev/null
@@ -1,3 +0,0 @@
-SET FOREIGN_KEY_CHECKS = 0;
-ALTER TABLE tag MODIFY id INTEGER;
-SET FOREIGN_KEY_CHECKS = 1;
diff --git a/internal/repository/migrations/mysql/07_fix-tag-id.up.sql b/internal/repository/migrations/mysql/07_fix-tag-id.up.sql
deleted file mode 100644
index 1abc4b35..00000000
--- a/internal/repository/migrations/mysql/07_fix-tag-id.up.sql
+++ /dev/null
@@ -1,3 +0,0 @@
-SET FOREIGN_KEY_CHECKS = 0;
-ALTER TABLE tag MODIFY id INTEGER AUTO_INCREMENT;
-SET FOREIGN_KEY_CHECKS = 1;
diff --git a/internal/repository/migrations/mysql/08_add-footprint.down.sql b/internal/repository/migrations/mysql/08_add-footprint.down.sql
deleted file mode 100644
index 57f2145c..00000000
--- a/internal/repository/migrations/mysql/08_add-footprint.down.sql
+++ /dev/null
@@ -1,83 +0,0 @@
-ALTER TABLE job DROP energy;
-ALTER TABLE job DROP energy_footprint;
-ALTER TABLE job ADD COLUMN flops_any_avg;
-ALTER TABLE job ADD COLUMN mem_bw_avg;
-ALTER TABLE job ADD COLUMN mem_used_max;
-ALTER TABLE job ADD COLUMN load_avg;
-ALTER TABLE job ADD COLUMN net_bw_avg;
-ALTER TABLE job ADD COLUMN net_data_vol_total;
-ALTER TABLE job ADD COLUMN file_bw_avg;
-ALTER TABLE job ADD COLUMN file_data_vol_total;
-
-UPDATE job SET flops_any_avg = json_extract(footprint, '$.flops_any_avg');
-UPDATE job SET mem_bw_avg = json_extract(footprint, '$.mem_bw_avg');
-UPDATE job SET mem_used_max = json_extract(footprint, '$.mem_used_max');
-UPDATE job SET load_avg = json_extract(footprint, '$.cpu_load_avg');
-UPDATE job SET net_bw_avg = json_extract(footprint, '$.net_bw_avg');
-UPDATE job SET net_data_vol_total = json_extract(footprint, '$.net_data_vol_total');
-UPDATE job SET file_bw_avg = json_extract(footprint, '$.file_bw_avg');
-UPDATE job SET file_data_vol_total = json_extract(footprint, '$.file_data_vol_total');
-
-ALTER TABLE job DROP footprint;
--- Do not use reserved keywords anymore
-RENAME TABLE hpc_user TO `user`;
-ALTER TABLE job RENAME COLUMN hpc_user TO `user`;
-ALTER TABLE job RENAME COLUMN cluster_partition TO `partition`;
-
-DROP INDEX IF EXISTS jobs_cluster;
-DROP INDEX IF EXISTS jobs_cluster_user;
-DROP INDEX IF EXISTS jobs_cluster_project;
-DROP INDEX IF EXISTS jobs_cluster_subcluster;
-DROP INDEX IF EXISTS jobs_cluster_starttime;
-DROP INDEX IF EXISTS jobs_cluster_duration;
-DROP INDEX IF EXISTS jobs_cluster_numnodes;
-
-DROP INDEX IF EXISTS jobs_cluster_partition;
-DROP INDEX IF EXISTS jobs_cluster_partition_starttime;
-DROP INDEX IF EXISTS jobs_cluster_partition_duration;
-DROP INDEX IF EXISTS jobs_cluster_partition_numnodes;
-
-DROP INDEX IF EXISTS jobs_cluster_partition_jobstate;
-DROP INDEX IF EXISTS jobs_cluster_partition_jobstate_user;
-DROP INDEX IF EXISTS jobs_cluster_partition_jobstate_project;
-DROP INDEX IF EXISTS jobs_cluster_partition_jobstate_starttime;
-DROP INDEX IF EXISTS jobs_cluster_partition_jobstate_duration;
-DROP INDEX IF EXISTS jobs_cluster_partition_jobstate_numnodes;
-
-DROP INDEX IF EXISTS jobs_cluster_jobstate;
-DROP INDEX IF EXISTS jobs_cluster_jobstate_user;
-DROP INDEX IF EXISTS jobs_cluster_jobstate_project;
-
-DROP INDEX IF EXISTS jobs_cluster_jobstate_starttime;
-DROP INDEX IF EXISTS jobs_cluster_jobstate_duration;
-DROP INDEX IF EXISTS jobs_cluster_jobstate_numnodes;
-
-DROP INDEX IF EXISTS jobs_user;
-DROP INDEX IF EXISTS jobs_user_starttime;
-DROP INDEX IF EXISTS jobs_user_duration;
-DROP INDEX IF EXISTS jobs_user_numnodes;
-
-DROP INDEX IF EXISTS jobs_project;
-DROP INDEX IF EXISTS jobs_project_user;
-DROP INDEX IF EXISTS jobs_project_starttime;
-DROP INDEX IF EXISTS jobs_project_duration;
-DROP INDEX IF EXISTS jobs_project_numnodes;
-
-DROP INDEX IF EXISTS jobs_jobstate;
-DROP INDEX IF EXISTS jobs_jobstate_user;
-DROP INDEX IF EXISTS jobs_jobstate_project;
-DROP INDEX IF EXISTS jobs_jobstate_starttime;
-DROP INDEX IF EXISTS jobs_jobstate_duration;
-DROP INDEX IF EXISTS jobs_jobstate_numnodes;
-
-DROP INDEX IF EXISTS jobs_arrayjobid_starttime;
-DROP INDEX IF EXISTS jobs_cluster_arrayjobid_starttime;
-
-DROP INDEX IF EXISTS jobs_starttime;
-DROP INDEX IF EXISTS jobs_duration;
-DROP INDEX IF EXISTS jobs_numnodes;
-
-DROP INDEX IF EXISTS jobs_duration_starttime;
-DROP INDEX IF EXISTS jobs_numnodes_starttime;
-DROP INDEX IF EXISTS jobs_numacc_starttime;
-DROP INDEX IF EXISTS jobs_energy_starttime;
diff --git a/internal/repository/migrations/mysql/08_add-footprint.up.sql b/internal/repository/migrations/mysql/08_add-footprint.up.sql
deleted file mode 100644
index 207ccf9e..00000000
--- a/internal/repository/migrations/mysql/08_add-footprint.up.sql
+++ /dev/null
@@ -1,123 +0,0 @@
-DROP INDEX IF EXISTS job_stats ON job;
-DROP INDEX IF EXISTS job_by_user ON job;
-DROP INDEX IF EXISTS job_by_starttime ON job;
-DROP INDEX IF EXISTS job_by_job_id ON job;
-DROP INDEX IF EXISTS job_list ON job;
-DROP INDEX IF EXISTS job_list_user ON job;
-DROP INDEX IF EXISTS job_list_users ON job;
-DROP INDEX IF EXISTS job_list_users_start ON job;
-
-ALTER TABLE job ADD COLUMN energy REAL NOT NULL DEFAULT 0.0;
-ALTER TABLE job ADD COLUMN energy_footprint JSON;
-
-ALTER TABLE job ADD COLUMN footprint JSON;
-ALTER TABLE tag ADD COLUMN tag_scope TEXT NOT NULL DEFAULT 'global';
-
--- Do not use reserved keywords anymore
-RENAME TABLE `user` TO hpc_user;
-ALTER TABLE job RENAME COLUMN `user` TO hpc_user;
-ALTER TABLE job RENAME COLUMN `partition` TO cluster_partition;
-
-ALTER TABLE job MODIFY COLUMN cluster VARCHAR(50);
-ALTER TABLE job MODIFY COLUMN hpc_user VARCHAR(50);
-ALTER TABLE job MODIFY COLUMN subcluster VARCHAR(50);
-ALTER TABLE job MODIFY COLUMN project VARCHAR(50);
-ALTER TABLE job MODIFY COLUMN cluster_partition VARCHAR(50);
-ALTER TABLE job MODIFY COLUMN job_state VARCHAR(25);
-
-UPDATE job SET footprint = '{"flops_any_avg": 0.0}';
-UPDATE job SET footprint = json_replace(footprint, '$.flops_any_avg', job.flops_any_avg);
-UPDATE job SET footprint = json_insert(footprint, '$.mem_bw_avg', job.mem_bw_avg);
-UPDATE job SET footprint = json_insert(footprint, '$.mem_used_max', job.mem_used_max);
-UPDATE job SET footprint = json_insert(footprint, '$.cpu_load_avg', job.load_avg);
-UPDATE job SET footprint = json_insert(footprint, '$.net_bw_avg', job.net_bw_avg) WHERE job.net_bw_avg != 0;
-UPDATE job SET footprint = json_insert(footprint, '$.net_data_vol_total', job.net_data_vol_total) WHERE job.net_data_vol_total != 0;
-UPDATE job SET footprint = json_insert(footprint, '$.file_bw_avg', job.file_bw_avg) WHERE job.file_bw_avg != 0;
-UPDATE job SET footprint = json_insert(footprint, '$.file_data_vol_total', job.file_data_vol_total) WHERE job.file_data_vol_total != 0;
-
-ALTER TABLE job DROP flops_any_avg;
-ALTER TABLE job DROP mem_bw_avg;
-ALTER TABLE job DROP mem_used_max;
-ALTER TABLE job DROP load_avg;
-ALTER TABLE job DROP net_bw_avg;
-ALTER TABLE job DROP net_data_vol_total;
-ALTER TABLE job DROP file_bw_avg;
-ALTER TABLE job DROP file_data_vol_total;
-
--- Indices for: Single filters, combined filters, sorting, sorting with filters
--- Cluster Filter
-CREATE INDEX IF NOT EXISTS jobs_cluster ON job (cluster);
-CREATE INDEX IF NOT EXISTS jobs_cluster_user ON job (cluster, hpc_user);
-CREATE INDEX IF NOT EXISTS jobs_cluster_project ON job (cluster, project);
-CREATE INDEX IF NOT EXISTS jobs_cluster_subcluster ON job (cluster, subcluster);
--- Cluster Filter Sorting
-CREATE INDEX IF NOT EXISTS jobs_cluster_starttime ON job (cluster, start_time);
-CREATE INDEX IF NOT EXISTS jobs_cluster_duration ON job (cluster, duration);
-CREATE INDEX IF NOT EXISTS jobs_cluster_numnodes ON job (cluster, num_nodes);
-
--- Cluster+Partition Filter
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition ON job (cluster, cluster_partition);
--- Cluster+Partition Filter Sorting
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_starttime ON job (cluster, cluster_partition, start_time);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_duration ON job (cluster, cluster_partition, duration);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_numnodes ON job (cluster, cluster_partition, num_nodes);
-
--- Cluster+Partition+Jobstate Filter
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate ON job (cluster, cluster_partition, job_state);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_user ON job (cluster, cluster_partition, job_state, hpc_user);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_project ON job (cluster, cluster_partition, job_state, project);
--- Cluster+Partition+Jobstate Filter Sorting
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_starttime ON job (cluster, cluster_partition, job_state, start_time);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_duration ON job (cluster, cluster_partition, job_state, duration);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_numnodes ON job (cluster, cluster_partition, job_state, num_nodes);
-
--- Cluster+JobState Filter
-CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate ON job (cluster, job_state);
-CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_user ON job (cluster, job_state, hpc_user);
-CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_project ON job (cluster, job_state, project);
--- Cluster+JobState Filter Sorting
-CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_starttime ON job (cluster, job_state, start_time);
-CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_duration ON job (cluster, job_state, duration);
-CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_numnodes ON job (cluster, job_state, num_nodes);
-
--- User Filter
-CREATE INDEX IF NOT EXISTS jobs_user ON job (hpc_user);
--- User Filter Sorting
-CREATE INDEX IF NOT EXISTS jobs_user_starttime ON job (hpc_user, start_time);
-CREATE INDEX IF NOT EXISTS jobs_user_duration ON job (hpc_user, duration);
-CREATE INDEX IF NOT EXISTS jobs_user_numnodes ON job (hpc_user, num_nodes);
-
--- Project Filter
-CREATE INDEX IF NOT EXISTS jobs_project ON job (project);
-CREATE INDEX IF NOT EXISTS jobs_project_user ON job (project, hpc_user);
--- Project Filter Sorting
-CREATE INDEX IF NOT EXISTS jobs_project_starttime ON job (project, start_time);
-CREATE INDEX IF NOT EXISTS jobs_project_duration ON job (project, duration);
-CREATE INDEX IF NOT EXISTS jobs_project_numnodes ON job (project, num_nodes);
-
--- JobState Filter
-CREATE INDEX IF NOT EXISTS jobs_jobstate ON job (job_state);
-CREATE INDEX IF NOT EXISTS jobs_jobstate_user ON job (job_state, hpc_user);
-CREATE INDEX IF NOT EXISTS jobs_jobstate_project ON job (job_state, project);
-CREATE INDEX IF NOT EXISTS jobs_jobstate_cluster ON job (job_state, cluster);
--- JobState Filter Sorting
-CREATE INDEX IF NOT EXISTS jobs_jobstate_starttime ON job (job_state, start_time);
-CREATE INDEX IF NOT EXISTS jobs_jobstate_duration ON job (job_state, duration);
-CREATE INDEX IF NOT EXISTS jobs_jobstate_numnodes ON job (job_state, num_nodes);
-
--- ArrayJob Filter
-CREATE INDEX IF NOT EXISTS jobs_arrayjobid_starttime ON job (array_job_id, start_time);
-CREATE INDEX IF NOT EXISTS jobs_cluster_arrayjobid_starttime ON job (cluster, array_job_id, start_time);
-
--- Sorting without active filters
-CREATE INDEX IF NOT EXISTS jobs_starttime ON job (start_time);
-CREATE INDEX IF NOT EXISTS jobs_duration ON job (duration);
-CREATE INDEX IF NOT EXISTS jobs_numnodes ON job (num_nodes);
-
--- Single filters with default starttime sorting
-CREATE INDEX IF NOT EXISTS jobs_duration_starttime ON job (duration, start_time);
-CREATE INDEX IF NOT EXISTS jobs_numnodes_starttime ON job (num_nodes, start_time);
-CREATE INDEX IF NOT EXISTS jobs_numacc_starttime ON job (num_acc, start_time);
-CREATE INDEX IF NOT EXISTS jobs_energy_starttime ON job (energy, start_time);
-
--- Optimize DB index usage
diff --git a/internal/repository/node_test.go b/internal/repository/node_test.go
index b42e09b8..466f51ee 100644
--- a/internal/repository/node_test.go
+++ b/internal/repository/node_test.go
@@ -130,7 +130,7 @@ func nodeTestSetup(t *testing.T) {
 	}
 
 	dbfilepath := filepath.Join(tmpdir, "test.db")
-	err := MigrateDB("sqlite3", dbfilepath)
+	err := MigrateDB(dbfilepath)
 	if err != nil {
 		t.Fatal(err)
 	}
diff --git a/internal/repository/repository_test.go b/internal/repository/repository_test.go
index 1346e4da..e3dec7fc 100644
--- a/internal/repository/repository_test.go
+++ b/internal/repository/repository_test.go
@@ -149,7 +149,7 @@ func setup(tb testing.TB) *JobRepository {
 	tb.Helper()
 	cclog.Init("warn", true)
 	dbfile := "testdata/job.db"
-	err := MigrateDB("sqlite3", dbfile)
+	err := MigrateDB(dbfile)
 	noErr(tb, err)
 	Connect("sqlite3", dbfile)
 	return GetJobRepository()
diff --git a/internal/repository/stats.go b/internal/repository/stats.go
index ba0d09f5..c92f5193 100644
--- a/internal/repository/stats.go
+++ b/internal/repository/stats.go
@@ -73,9 +73,6 @@ func (r *JobRepository) buildStatsQuery(
 	col string,
 ) sq.SelectBuilder {
 	var query sq.SelectBuilder
-	castType := r.getCastType()
-
-	// fmt.Sprintf(`CAST(ROUND((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) / 3600) as %s) as value`, time.Now().Unix(), castType)
 
 	if col != "" {
 		// Scan columns: id, name, totalJobs, totalUsers, totalWalltime, totalNodes, totalNodeHours, totalCores, totalCoreHours, totalAccs, totalAccHours
@@ -84,26 +81,26 @@ func (r *JobRepository) buildStatsQuery(
 			"name",
 			"COUNT(job.id) as totalJobs",
 			"COUNT(DISTINCT job.hpc_user) AS totalUsers",
-			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END)) / 3600) as %s) as totalWalltime`, time.Now().Unix(), castType),
-			fmt.Sprintf(`CAST(SUM(job.num_nodes) as %s) as totalNodes`, castType),
-			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_nodes) / 3600) as %s) as totalNodeHours`, time.Now().Unix(), castType),
-			fmt.Sprintf(`CAST(SUM(job.num_hwthreads) as %s) as totalCores`, castType),
-			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_hwthreads) / 3600) as %s) as totalCoreHours`, time.Now().Unix(), castType),
-			fmt.Sprintf(`CAST(SUM(job.num_acc) as %s) as totalAccs`, castType),
-			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_acc) / 3600) as %s) as totalAccHours`, time.Now().Unix(), castType),
+			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END)) / 3600) as int) as totalWalltime`, time.Now().Unix()),
+			fmt.Sprintf(`CAST(SUM(job.num_nodes) as int) as totalNodes`),
+			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_nodes) / 3600) as int) as totalNodeHours`, time.Now().Unix()),
+			fmt.Sprintf(`CAST(SUM(job.num_hwthreads) as int) as totalCores`),
+			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_hwthreads) / 3600) as int) as totalCoreHours`, time.Now().Unix()),
+			fmt.Sprintf(`CAST(SUM(job.num_acc) as int) as totalAccs`),
+			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_acc) / 3600) as int) as totalAccHours`, time.Now().Unix()),
 		).From("job").LeftJoin("hpc_user ON hpc_user.username = job.hpc_user").GroupBy(col)
 	} else {
 		// Scan columns: totalJobs, totalUsers, totalWalltime, totalNodes, totalNodeHours, totalCores, totalCoreHours, totalAccs, totalAccHours
 		query = sq.Select(
 			"COUNT(job.id) as totalJobs",
 			"COUNT(DISTINCT job.hpc_user) AS totalUsers",
-			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END)) / 3600) as %s)`, time.Now().Unix(), castType),
-			fmt.Sprintf(`CAST(SUM(job.num_nodes) as %s)`, castType),
-			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_nodes) / 3600) as %s)`, time.Now().Unix(), castType),
-			fmt.Sprintf(`CAST(SUM(job.num_hwthreads) as %s)`, castType),
-			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_hwthreads) / 3600) as %s)`, time.Now().Unix(), castType),
-			fmt.Sprintf(`CAST(SUM(job.num_acc) as %s)`, castType),
-			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_acc) / 3600) as %s)`, time.Now().Unix(), castType),
+			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END)) / 3600) as int)`, time.Now().Unix()),
+			fmt.Sprintf(`CAST(SUM(job.num_nodes) as int)`),
+			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_nodes) / 3600) as int)`, time.Now().Unix()),
+			fmt.Sprintf(`CAST(SUM(job.num_hwthreads) as int)`),
+			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_hwthreads) / 3600) as int)`, time.Now().Unix()),
+			fmt.Sprintf(`CAST(SUM(job.num_acc) as int)`),
+			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_acc) / 3600) as int)`, time.Now().Unix()),
 		).From("job")
 	}
 
@@ -114,21 +111,6 @@ func (r *JobRepository) buildStatsQuery(
 	return query
 }
 
-func (r *JobRepository) getCastType() string {
-	var castType string
-
-	switch r.driver {
-	case "sqlite3":
-		castType = "int"
-	case "mysql":
-		castType = "unsigned"
-	default:
-		castType = ""
-	}
-
-	return castType
-}
-
 func (r *JobRepository) JobsStatsGrouped(
 	ctx context.Context,
 	filter []*model.JobFilter,
@@ -477,10 +459,9 @@ func (r *JobRepository) AddHistograms(
 		targetBinSize = 3600
 	}
 
-	castType := r.getCastType()
 	var err error
 	// Return X-Values always as seconds, will be formatted into minutes and hours in frontend
-	value := fmt.Sprintf(`CAST(ROUND(((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) / %d) + 1) as %s) as value`, time.Now().Unix(), targetBinSize, castType)
+	value := fmt.Sprintf(`CAST(ROUND(((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) / %d) + 1) as int) as value`, time.Now().Unix(), targetBinSize)
 	stat.HistDuration, err = r.jobsDurationStatisticsHistogram(ctx, value, filter, targetBinSize, &targetBinCount)
 	if err != nil {
 		cclog.Warn("Error while loading job statistics histogram: job duration")
diff --git a/internal/repository/userConfig_test.go b/internal/repository/userConfig_test.go
index 0d6dc374..b6f68430 100644
--- a/internal/repository/userConfig_test.go
+++ b/internal/repository/userConfig_test.go
@@ -42,7 +42,7 @@ func setupUserTest(t *testing.T) *UserCfgRepo {
 
 	cclog.Init("info", true)
 	dbfilepath := "testdata/job.db"
-	err := MigrateDB("sqlite3", dbfilepath)
+	err := MigrateDB(dbfilepath)
 	if err != nil {
 		t.Fatal(err)
 	}
diff --git a/internal/tagger/detectApp_test.go b/internal/tagger/detectApp_test.go
index f9fc91d0..7145d04f 100644
--- a/internal/tagger/detectApp_test.go
+++ b/internal/tagger/detectApp_test.go
@@ -15,7 +15,7 @@ func setup(tb testing.TB) *repository.JobRepository {
 	tb.Helper()
 	cclog.Init("warn", true)
 	dbfile := "../repository/testdata/job.db"
-	err := repository.MigrateDB("sqlite3", dbfile)
+	err := repository.MigrateDB(dbfile)
 	noErr(tb, err)
 	repository.Connect("sqlite3", dbfile)
 	return repository.GetJobRepository()

From 89875db4a9a8d7dc53dacb480a6c144ae847772a Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Mon, 22 Dec 2025 10:39:40 +0100
Subject: [PATCH 12/59] dashboard layout fixes

---
 web/frontend/src/DashPublic.root.svelte       |  8 ++++----
 web/frontend/src/generic/plots/Stacked.svelte |  2 +-
 web/frontend/src/status/DashInternal.svelte   | 10 ++++++----
 3 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/web/frontend/src/DashPublic.root.svelte b/web/frontend/src/DashPublic.root.svelte
index 25e2683c..c69b28f6 100644
--- a/web/frontend/src/DashPublic.root.svelte
+++ b/web/frontend/src/DashPublic.root.svelte
@@ -338,7 +338,7 @@
 </script>
 
 <Card style="height: 98vh;">
-  <CardBody class="align-content-center p-1">
+  <CardBody class="align-content-center p-2">
     <Row>
       <Col>
         <Refresher
@@ -506,7 +506,7 @@
                 useColors={false}
                 useLegend={false}
                 allowSizeChange
-                width={colWidthRoof - 10}
+                width={colWidthRoof}
                 height={300}
                 cluster={presetCluster}
                 subCluster={clusterInfo?.roofData ? clusterInfo.roofData : null}
@@ -574,8 +574,8 @@
             {#key $statesTimed?.data?.nodeStatesTimed}
               <Stacked
                 data={$statesTimed?.data?.nodeStatesTimed}
-                width={colWidthStacked * 0.95}
-                xlabel="Time"
+                width={colWidthStacked}
+                height={260}
                 ylabel="Nodes"
                 yunit = "#Count"
                 title = "Cluster Status"
diff --git a/web/frontend/src/generic/plots/Stacked.svelte b/web/frontend/src/generic/plots/Stacked.svelte
index d4babb16..06dd83e4 100644
--- a/web/frontend/src/generic/plots/Stacked.svelte
+++ b/web/frontend/src/generic/plots/Stacked.svelte
@@ -23,7 +23,7 @@
     width = 0,
     height = 300,
     data = null,
-    xlabel = "",
+    xlabel = null,
     ylabel = "",
     yunit = "",
     title = "",
diff --git a/web/frontend/src/status/DashInternal.svelte b/web/frontend/src/status/DashInternal.svelte
index 47a841a3..40ef4d91 100644
--- a/web/frontend/src/status/DashInternal.svelte
+++ b/web/frontend/src/status/DashInternal.svelte
@@ -355,7 +355,7 @@
 
 </script>
 
-<Card style="height: 88vh;">
+<Card>
   <CardBody class="align-content-center">
     <Row>
       <Col>
@@ -540,7 +540,7 @@
               <Roofline
                 useColors={true}
                 allowSizeChange
-                width={colWidthRoof - 10}
+                width={colWidthRoof}
                 height={300}
                 subCluster={clusterInfo?.roofData ? clusterInfo.roofData : null}
                 roofData={transformJobsStatsToData($statusQuery?.data?.jobsMetricStats)}
@@ -568,7 +568,8 @@
             {#key $statesTimed?.data?.nodeStates}
               <Stacked
                 data={$statesTimed?.data?.nodeStates}
-                width={colWidthStacked1 * 0.95}
+                width={colWidthStacked1}
+                height={330}
                 xlabel="Time"
                 ylabel="Nodes"
                 yunit = "#Count"
@@ -584,7 +585,8 @@
             {#key $statesTimed?.data?.healthStates}
               <Stacked
                 data={$statesTimed?.data?.healthStates}
-                width={colWidthStacked2 * 0.95}
+                width={colWidthStacked2}
+                height={330}
                 xlabel="Time"
                 ylabel="Nodes"
                 yunit = "#Count"

From 502d7e9084f281943c17b66a1d64955691b5f04e Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Mon, 22 Dec 2025 17:26:56 +0100
Subject: [PATCH 13/59] Rework info panel in public dashboard

- change to bootstrap grid from table
- add infos, use badges
- remove non required query
---
 internal/metricdata/cc-metric-store.go  |  30 ++--
 web/frontend/src/DashPublic.root.svelte | 219 ++++++++++++++----------
 web/frontend/src/generic/units.js       |   2 +-
 3 files changed, 146 insertions(+), 105 deletions(-)

diff --git a/internal/metricdata/cc-metric-store.go b/internal/metricdata/cc-metric-store.go
index 6d446d17..be2e956e 100644
--- a/internal/metricdata/cc-metric-store.go
+++ b/internal/metricdata/cc-metric-store.go
@@ -770,21 +770,25 @@ func (ccms *CCMetricStore) LoadNodeData(
 		}
 
 		mc := archive.GetMetricConfig(cluster, metric)
-		hostdata[metric] = append(hostdata[metric], &schema.JobMetric{
-			Unit:     mc.Unit,
-			Timestep: mc.Timestep,
-			Series: []schema.Series{
-				{
-					Hostname: query.Hostname,
-					Data:     qdata.Data,
-					Statistics: schema.MetricStatistics{
-						Avg: float64(qdata.Avg),
-						Min: float64(qdata.Min),
-						Max: float64(qdata.Max),
+		if mc != nil {
+			hostdata[metric] = append(hostdata[metric], &schema.JobMetric{
+				Unit:     mc.Unit,
+				Timestep: mc.Timestep,
+				Series: []schema.Series{
+					{
+						Hostname: query.Hostname,
+						Data:     qdata.Data,
+						Statistics: schema.MetricStatistics{
+							Avg: float64(qdata.Avg),
+							Min: float64(qdata.Min),
+							Max: float64(qdata.Max),
+						},
 					},
 				},
-			},
-		})
+			})
+		} else {
+			cclog.Warnf("Metric '%s' not configured for cluster '%s': Skipped in LoadNodeData() Return!", metric, cluster)
+		}
 	}
 
 	if len(errors) != 0 {
diff --git a/web/frontend/src/DashPublic.root.svelte b/web/frontend/src/DashPublic.root.svelte
index c69b28f6..fbbf486d 100644
--- a/web/frontend/src/DashPublic.root.svelte
+++ b/web/frontend/src/DashPublic.root.svelte
@@ -30,7 +30,8 @@
     Table,
     Progress,
     Icon,
-    Button
+    Button,
+    Badge
   } from "@sveltestrap/sveltestrap";
   import Roofline from "./generic/plots/Roofline.svelte";
   import Pie, { colors } from "./generic/plots/Pie.svelte";
@@ -85,7 +86,8 @@
     query: gql`
       query (
         $cluster: String!
-        $metrics: [String!]
+        $nmetrics: [String!]
+        $cmetrics: [String!]
         $from: Time!
         $to: Time!
         $clusterFrom: Time!
@@ -97,7 +99,7 @@
         # Node 5 Minute Averages for Roofline
         nodeMetrics(
           cluster: $cluster
-          metrics: $metrics
+          metrics: $nmetrics
           from: $from
           to: $to
         ) {
@@ -106,6 +108,10 @@
           metrics {
             name
             metric {
+              unit {
+                base
+                prefix
+              }
               series {
                 statistics {
                   avg
@@ -114,21 +120,6 @@
             }
           }
         }
-        # Running Job Metric Average for Rooflines
-        jobsMetricStats(filter: $jobFilter, metrics: $metrics) {
-          id
-          jobId
-          duration
-          numNodes
-          numAccelerators
-          subCluster
-          stats {
-            name
-            data {
-              avg
-            }
-          }
-        }
         # Get Jobs for Per-Node Counts
         jobs(filter: $jobFilter, order: $sorting, page: $paging) {
           items {
@@ -175,7 +166,7 @@
         # ClusterMetrics for doubleMetricPlot
         clusterMetrics(
           cluster: $cluster
-          metrics: $metrics
+          metrics: $cmetrics
           from: $clusterFrom
           to: $to
         ) {
@@ -194,7 +185,8 @@
     `,
     variables: {
       cluster: presetCluster,
-      metrics: ["flops_any", "mem_bw"], // Metrics For Cluster Plot and Roofline
+      nmetrics: ["flops_any", "mem_bw", "cpu_power", "acc_power"], // Metrics For Roofline and Stats
+      cmetrics: ["flops_any", "mem_bw"], // Metrics For Cluster Plot
       from: from.toISOString(),
       clusterFrom: clusterFrom.toISOString(),
       to: to.toISOString(),
@@ -258,6 +250,11 @@
         }
       }
 
+      // Get Idle Infos after Sums
+      if (!rawInfos['idleNodes']) rawInfos['idleNodes'] = rawInfos['totalNodes'] - rawInfos['allocatedNodes'];
+      if (!rawInfos['idleCores']) rawInfos['idleCores'] = rawInfos['totalCores'] - rawInfos['allocatedCores'];
+      if (!rawInfos['idleAccs']) rawInfos['idleAccs'] = rawInfos['totalAccs'] - rawInfos['allocatedAccs'];
+
       // Keymetrics (Data on Cluster-Scope)
       let rawFlops = $statusQuery?.data?.nodeMetrics?.reduce((sum, node) =>
         sum + (node.metrics.find((m) => m.name == 'flops_any')?.metric?.series[0]?.statistics?.avg || 0),
@@ -271,6 +268,26 @@
       ) || 0;
       rawInfos['memBwRate'] = Math.floor((rawMemBw * 100) / 100)
 
+      let rawCpuPwr = $statusQuery?.data?.nodeMetrics?.reduce((sum, node) =>
+        sum + (node.metrics.find((m) => m.name == 'cpu_power')?.metric?.series[0]?.statistics?.avg || 0),
+        0, // Initial Value
+      ) || 0;
+      rawInfos['cpuPwr'] = Math.floor((rawCpuPwr * 100) / 100)
+      if (!rawInfos['cpuPwrUnit']) {
+        let rawCpuUnit = $statusQuery?.data?.nodeMetrics[0]?.metrics.find((m) => m.name == 'cpu_power')?.metric?.unit || null
+        rawInfos['cpuPwrUnit'] = rawCpuUnit ? rawCpuUnit.prefix + rawCpuUnit.base : ''
+      }
+
+      let rawGpuPwr = $statusQuery?.data?.nodeMetrics?.reduce((sum, node) =>
+        sum + (node.metrics.find((m) => m.name == 'acc_power')?.metric?.series[0]?.statistics?.avg || 0),
+        0, // Initial Value
+      ) || 0;
+      rawInfos['gpuPwr'] = Math.floor((rawGpuPwr * 100) / 100)
+      if (!rawInfos['gpuPwrUnit']) {
+        let rawGpuUnit = $statusQuery?.data?.nodeMetrics[0]?.metrics.find((m) => m.name == 'acc_power')?.metric?.unit || null
+        rawInfos['gpuPwrUnit'] = rawGpuUnit ? rawGpuUnit.prefix + rawGpuUnit.base : ''
+      }
+
       return rawInfos
     } else {
       return {};
@@ -408,79 +425,99 @@
         <Col> <!-- Utilization Info Card -->
           <Card class="h-100">
             <CardBody>
-              <Table borderless>
-                <tr class="py-2">
-                  <td style="font-size:x-large;">{clusterInfo?.runningJobs} Running Jobs</td>
-                  <td colspan="2" style="font-size:x-large;">{clusterInfo?.activeUsers} Active Users</td>
-                </tr>
-                <hr class="my-1"/>
-                <tr class="pt-2">
-                  <td style="font-size: large;">
-                    Flop Rate (<span style="cursor: help;" title="Flops[Any] = (Flops[Double] x 2) + Flops[Single]">Any</span>)
-                  </td>
-                  <td colspan="2" style="font-size: large;">
-                    Memory BW Rate
-                  </td>
-                </tr>
-                <tr class="pb-2">
-                  <td style="font-size:x-large;">
-                    {clusterInfo?.flopRate} 
-                    {clusterInfo?.flopRateUnit}
-                  </td>
-                  <td colspan="2" style="font-size:x-large;">
-                    {clusterInfo?.memBwRate} 
-                    {clusterInfo?.memBwRateUnit}
-                  </td>
-                </tr>
-                <hr class="my-1"/>
-                <tr class="py-2">
-                  <th scope="col">Allocated Nodes</th>
-                  <td style="min-width: 100px;"
-                    ><div class="col">
-                      <Progress
-                        value={clusterInfo?.allocatedNodes}
-                        max={clusterInfo?.totalNodes}
-                      />
-                    </div></td
-                  >
-                  <td
-                    >{clusterInfo?.allocatedNodes} / {clusterInfo?.totalNodes}
-                    Nodes</td
-                  >
-                </tr>
-                <tr class="py-2">
-                  <th scope="col">Allocated Cores</th>
-                  <td style="min-width: 100px;"
-                    ><div class="col">
-                      <Progress
-                        value={clusterInfo?.allocatedCores}
-                        max={clusterInfo?.totalCores}
-                      />
-                    </div></td
-                  >
-                  <td
-                    >{formatNumber(clusterInfo?.allocatedCores)} / {formatNumber(clusterInfo?.totalCores)}
-                    Cores</td
-                  >
-                </tr>
+              <Row class="mb-1">
+                <Col xs={4} class="d-inline-flex align-items-center justify-content-center">
+                  <Badge color="primary" style="font-size:x-large;margin-right:0.25rem;">
+                    {clusterInfo?.runningJobs}
+                  </Badge>
+                  <div style="font-size:large;">
+                    Running Jobs
+                  </div>
+                </Col>
+                <Col xs={4} class="d-inline-flex align-items-center justify-content-center">
+                  <Badge color="primary" style="font-size:x-large;margin-right:0.25rem;">
+                    {clusterInfo?.activeUsers}
+                  </Badge>
+                  <div style="font-size:large;">
+                    Active Users
+                  </div>
+                </Col>
+                <Col xs={4} class="d-inline-flex align-items-center justify-content-center">
+                  <Badge color="primary" style="font-size:x-large;margin-right:0.25rem;">
+                    {clusterInfo?.allocatedNodes}
+                  </Badge>
+                  <div style="font-size:large;">
+                    Active Nodes
+                  </div>
+                </Col>
+              </Row>
+              <Row class="mt-1 mb-2">
+                <Col xs={4} class="d-inline-flex align-items-center justify-content-center">
+                  <Badge color="secondary" style="font-size:x-large;margin-right:0.25rem;">
+                    {clusterInfo?.flopRate} {clusterInfo?.flopRateUnit}
+                  </Badge>
+                  <div style="font-size:large;">
+                    Total Flop Rate
+                  </div>
+                </Col>
+                <Col xs={4} class="d-inline-flex align-items-center justify-content-center">
+                  <Badge color="secondary" style="font-size:x-large;margin-right:0.25rem;">
+                    {clusterInfo?.memBwRate} {clusterInfo?.memBwRateUnit}
+                  </Badge>
+                  <div style="font-size:large;">
+                    Total Memory Bandwidth
+                  </div>
+                </Col>
                 {#if clusterInfo?.totalAccs !== 0}
-                  <tr class="py-2">
-                    <th scope="col">Allocated Accelerators</th>
-                    <td style="min-width: 100px;"
-                      ><div class="col">
-                        <Progress
-                          value={clusterInfo?.allocatedAccs}
-                          max={clusterInfo?.totalAccs}
-                        />
-                      </div></td
-                    >
-                    <td
-                      >{clusterInfo?.allocatedAccs} / {clusterInfo?.totalAccs}
-                      Accelerators</td
-                    >
-                  </tr>
+                  <Col xs={4} class="d-inline-flex align-items-center justify-content-center">
+                    <Badge color="secondary" style="font-size:x-large;margin-right:0.25rem;">
+                      {clusterInfo?.gpuPwr} {clusterInfo?.gpuPwrUnit}
+                    </Badge>
+                    <div style="font-size:large;">
+                      Total GPU Power
+                    </div>
+                  </Col>
+                {:else}
+                  <Col xs={4} class="d-inline-flex align-items-center justify-content-center">
+                    <Badge color="secondary" style="font-size:x-large;margin-right:0.25rem;">
+                      {clusterInfo?.cpuPwr} {clusterInfo?.cpuPwrUnit}
+                    </Badge>
+                    <div style="font-size:large;">
+                      Total CPU Power
+                    </div>
+                  </Col>
                 {/if}
-              </Table>
+              </Row>
+              <Row class="my-1 align-items-baseline">
+                <Col xs={2} style="font-size:large;">
+                  Active Cores
+                </Col>
+                <Col xs={8}>
+                  <Progress multi style="height:2.5rem;font-size:x-large;">
+                    <Progress bar color="success" value={clusterInfo?.allocatedCores}>{formatNumber(clusterInfo?.allocatedCores)}</Progress>
+                    <Progress bar color="light" value={clusterInfo?.idleCores}>{formatNumber(clusterInfo?.idleCores)}</Progress>
+                  </Progress>
+                </Col>
+                <Col xs={2} style="font-size:large;">
+                  Idle Cores
+                </Col>
+              </Row>
+              {#if clusterInfo?.totalAccs !== 0}
+                <Row class="my-1 align-items-baseline">
+                  <Col xs={2} style="font-size:large;">
+                    Active GPU
+                  </Col>
+                  <Col xs={8}>
+                    <Progress multi style="height:2.5rem;font-size:x-large;">
+                      <Progress bar color="success" value={clusterInfo?.allocatedAccs}>{formatNumber(clusterInfo?.allocatedAccs)}</Progress>
+                      <Progress bar color="light" value={clusterInfo?.idleAccs}>{formatNumber(clusterInfo?.idleAccs)}</Progress>
+                    </Progress>
+                  </Col>
+                  <Col xs={2} style="font-size:large;">
+                    Idle GPU
+                  </Col>
+                </Row>
+              {/if}
             </CardBody>
           </Card>
         </Col>
diff --git a/web/frontend/src/generic/units.js b/web/frontend/src/generic/units.js
index 1737b977..3e251fbf 100644
--- a/web/frontend/src/generic/units.js
+++ b/web/frontend/src/generic/units.js
@@ -3,7 +3,7 @@
 */
 
 const power  = [1, 1e3, 1e6, 1e9, 1e12, 1e15, 1e18, 1e21]
-const prefix = ['', 'K', 'M', 'G', 'T', 'P', 'E']
+const prefix = ['', 'k', 'M', 'G', 'T', 'P', 'E']
 
 export function formatNumber(x) {
     if ( isNaN(x) || x == null) {

From 0bc26aa1943cf281165084f46a2273c95ffe8d90 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 23 Dec 2025 05:56:46 +0100
Subject: [PATCH 14/59] Add error check

---
 internal/api/nats.go | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/internal/api/nats.go b/internal/api/nats.go
index 1bfe9051..61cbd979 100644
--- a/internal/api/nats.go
+++ b/internal/api/nats.go
@@ -224,7 +224,10 @@ func (api *NatsAPI) handleNodeState(subject string, data []byte) {
 			JobsRunning:     node.JobsRunning,
 		}
 
-		repo.UpdateNodeState(node.Hostname, req.Cluster, &nodeState)
+		if err := repo.UpdateNodeState(node.Hostname, req.Cluster, &nodeState); err != nil {
+			cclog.Errorf("NATS %s: updating node state for %s on %s failed: %v",
+				subject, node.Hostname, req.Cluster, err)
+		}
 	}
 
 	cclog.Debugf("NATS %s: updated %d node states for cluster %s", subject, len(req.Nodes), req.Cluster)

From c1135531ba26d3267791113b77c0f4bcc4f71234 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 23 Dec 2025 07:56:13 +0100
Subject: [PATCH 15/59] Port NATS api to ccMessages

---
 go.mod                    |  5 +++
 go.sum                    |  4 ++
 internal/api/nats.go      | 94 +++++++++++++++++++++++++++------------
 internal/config/config.go |  3 +-
 pkg/nats/influxDecoder.go | 59 ++++++++++++++++++++++++
 5 files changed, 134 insertions(+), 31 deletions(-)
 create mode 100644 pkg/nats/influxDecoder.go

diff --git a/go.mod b/go.mod
index eb061de7..b821f7bf 100644
--- a/go.mod
+++ b/go.mod
@@ -50,6 +50,7 @@ require (
 	github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358 // indirect
 	github.com/KyleBanks/depth v1.2.1 // indirect
 	github.com/agnivade/levenshtein v1.2.1 // indirect
+	github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.3 // indirect
 	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.13 // indirect
 	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.13 // indirect
@@ -89,6 +90,8 @@ require (
 	github.com/gorilla/securecookie v1.1.2 // indirect
 	github.com/gorilla/websocket v1.5.3 // indirect
 	github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
+	github.com/influxdata/influxdb-client-go/v2 v2.14.0 // indirect
+	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf // indirect
 	github.com/jonboulle/clockwork v0.5.0 // indirect
 	github.com/jpillora/backoff v1.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
@@ -101,6 +104,7 @@ require (
 	github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f // indirect
 	github.com/nats-io/nkeys v0.4.11 // indirect
 	github.com/nats-io/nuid v1.0.1 // indirect
+	github.com/oapi-codegen/runtime v1.1.1 // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/client_model v0.6.2 // indirect
 	github.com/prometheus/procfs v0.16.1 // indirect
@@ -114,6 +118,7 @@ require (
 	github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342 // indirect
 	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
+	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect
 	golang.org/x/mod v0.30.0 // indirect
 	golang.org/x/net v0.47.0 // indirect
 	golang.org/x/sync v0.18.0 // indirect
diff --git a/go.sum b/go.sum
index fd4980da..04e2514b 100644
--- a/go.sum
+++ b/go.sum
@@ -14,6 +14,7 @@ github.com/NVIDIA/go-nvml v0.13.0-1 h1:OLX8Jq3dONuPOQPC7rndB6+iDmDakw0XTYgzMxObk
 github.com/NVIDIA/go-nvml v0.13.0-1/go.mod h1:+KNA7c7gIBH7SKSJ1ntlwkfN80zdx8ovl4hrK3LmPt4=
 github.com/PuerkitoBio/goquery v1.11.0 h1:jZ7pwMQXIITcUXNH83LLk+txlaEy6NVOfTuP43xxfqw=
 github.com/PuerkitoBio/goquery v1.11.0/go.mod h1:wQHgxUOU3JGuj3oD/QFfxUdlzW6xPHfqyHre6VMY4DQ=
+github.com/RaveNoX/go-jsoncommentstrip v1.0.0/go.mod h1:78ihd09MekBnJnxpICcwzCMzGrKSKYe4AqU6PDYYpjk=
 github.com/agnivade/levenshtein v1.2.1 h1:EHBY3UOn1gwdy/VbFwgo4cxecRznFk7fKWN1KOX7eoM=
 github.com/agnivade/levenshtein v1.2.1/go.mod h1:QVVI16kDrtSuwcpd0p1+xMC6Z/VfhtCyDIjcwga4/DU=
 github.com/alexbrainman/sspi v0.0.0-20250919150558-7d374ff0d59e h1:4dAU9FXIyQktpoUAgOJK3OTFc/xug0PCXYCqU0FgDKI=
@@ -64,6 +65,7 @@ github.com/aws/smithy-go v1.24.0 h1:LpilSUItNPFr1eY85RYgTIg5eIEPtvFbskaFcmmIUnk=
 github.com/aws/smithy-go v1.24.0/go.mod h1:LEj2LM3rBRQJxPZTB4KuzZkaZYnZPnvgIhb4pu07mx0=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
+github.com/bmatcuk/doublestar v1.1.1/go.mod h1:UD6OnuiIn0yFxxA2le/rnRU1G4RaI4UvFv1sNto9p6w=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/coreos/go-oidc/v3 v3.16.0 h1:qRQUCFstKpXwmEjDQTIbyY/5jF00+asXzSkmkoa/mow=
@@ -194,6 +196,7 @@ github.com/jpillora/backoff v1.0.0 h1:uvFg412JmmHBHw7iwprIxkPMI+sGQ4kzOWsMeHnm2E
 github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX5e0EB2j4=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
+github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
 github.com/klauspost/compress v1.18.1 h1:bcSGx7UbpBqMChDtsF28Lw6v/G94LPrrbMbdC3JH2co=
 github.com/klauspost/compress v1.18.1/go.mod h1:ZQFFVG+MdnR0P+l6wpXgIL4NTtwiKIdBnrBd8Nrxr+0=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
@@ -260,6 +263,7 @@ github.com/sergi/go-diff v1.3.1 h1:xkr+Oxo4BOQKmkn/B9eMK0g5Kg/983T9DqqPHwYqD+8=
 github.com/sergi/go-diff v1.3.1/go.mod h1:aMJSSKb2lpPvRNec0+w3fl7LP9IOFzdc9Pa4NFbPK1I=
 github.com/sosodev/duration v1.3.1 h1:qtHBDMQ6lvMQsL15g4aopM4HEfOaYuhWBw3NPTtlqq4=
 github.com/sosodev/duration v1.3.1/go.mod h1:RQIBBX0+fMLc/D9+Jb/fwvVmo0eZvDDEERAikUR6SDg=
+github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
 github.com/stretchr/objx v0.5.2 h1:xuMeJ0Sdp5ZMRXx/aWO6RZxdr3beISkG5/G/aIRr3pY=
diff --git a/internal/api/nats.go b/internal/api/nats.go
index 1bfe9051..745e7acb 100644
--- a/internal/api/nats.go
+++ b/internal/api/nats.go
@@ -9,6 +9,7 @@ import (
 	"bytes"
 	"database/sql"
 	"encoding/json"
+	"strings"
 	"sync"
 	"time"
 
@@ -18,7 +19,9 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/nats"
 	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 	"github.com/ClusterCockpit/cc-lib/schema"
+	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
 )
 
 // NatsAPI provides NATS subscription-based handlers for Job and Node operations.
@@ -50,11 +53,7 @@ func (api *NatsAPI) StartSubscriptions() error {
 
 		s := config.Keys.APISubjects
 
-		if err := client.Subscribe(s.SubjectJobStart, api.handleStartJob); err != nil {
-			return err
-		}
-
-		if err := client.Subscribe(s.SubjectJobStop, api.handleStopJob); err != nil {
+		if err := client.Subscribe(s.SubjectJobEvent, api.handleJobEvent); err != nil {
 			return err
 		}
 
@@ -67,26 +66,63 @@ func (api *NatsAPI) StartSubscriptions() error {
 	return nil
 }
 
+func (api *NatsAPI) processJobEvent(msg lp.CCMessage) {
+	function, ok := msg.GetTag("function")
+	if !ok {
+		cclog.Errorf("Job event is missing tag 'function': %+v", msg)
+		return
+	}
+
+	switch function {
+	case "start_job":
+		api.handleStartJob(msg.GetEventValue())
+
+	case "stop_job":
+		api.handleStopJob(msg.GetEventValue())
+	default:
+		cclog.Warnf("Unimplemented job event: %+v", msg)
+	}
+}
+
+func (api *NatsAPI) handleJobEvent(subject string, data []byte) {
+	d := influx.NewDecoderWithBytes(data)
+
+	for d.Next() {
+		m, err := nats.DecodeInfluxMessage(d)
+		if err != nil {
+			cclog.Errorf("NATS %s:  Failed to decode message: %v", subject, err)
+			return
+		}
+
+		if m.IsEvent() {
+			if m.Name() == "job" {
+				api.processJobEvent(m)
+			}
+		}
+
+	}
+}
+
 // handleStartJob processes job start messages received via NATS.
 // Expected JSON payload follows the schema.Job structure.
-func (api *NatsAPI) handleStartJob(subject string, data []byte) {
+func (api *NatsAPI) handleStartJob(payload string) {
 	req := schema.Job{
 		Shared:           "none",
 		MonitoringStatus: schema.MonitoringStatusRunningOrArchiving,
 	}
 
-	dec := json.NewDecoder(bytes.NewReader(data))
+	dec := json.NewDecoder(strings.NewReader(payload))
 	dec.DisallowUnknownFields()
 	if err := dec.Decode(&req); err != nil {
-		cclog.Errorf("NATS %s: parsing request failed: %v", subject, err)
+		cclog.Errorf("NATS start job: parsing request failed: %v", err)
 		return
 	}
 
-	cclog.Debugf("NATS %s: %s", subject, req.GoString())
+	cclog.Debugf("NATS start job: %s", req.GoString())
 	req.State = schema.JobStateRunning
 
 	if err := importer.SanityChecks(&req); err != nil {
-		cclog.Errorf("NATS %s: sanity check failed: %v", subject, err)
+		cclog.Errorf("NATS start job: sanity check failed: %v", err)
 		return
 	}
 
@@ -96,14 +132,14 @@ func (api *NatsAPI) handleStartJob(subject string, data []byte) {
 
 	jobs, err := api.JobRepository.FindAll(&req.JobID, &req.Cluster, nil)
 	if err != nil && err != sql.ErrNoRows {
-		cclog.Errorf("NATS %s: checking for duplicate failed: %v", subject, err)
+		cclog.Errorf("NATS start job: checking for duplicate failed: %v", err)
 		return
 	}
 	if err == nil {
 		for _, job := range jobs {
 			if (req.StartTime - job.StartTime) < secondsPerDay {
-				cclog.Errorf("NATS %s: job with jobId %d, cluster %s already exists (dbid: %d)",
-					subject, req.JobID, req.Cluster, job.ID)
+				cclog.Errorf("NATS start job: job with jobId %d, cluster %s already exists (dbid: %d)",
+					req.JobID, req.Cluster, job.ID)
 				return
 			}
 		}
@@ -111,14 +147,14 @@ func (api *NatsAPI) handleStartJob(subject string, data []byte) {
 
 	id, err := api.JobRepository.Start(&req)
 	if err != nil {
-		cclog.Errorf("NATS %s: insert into database failed: %v", subject, err)
+		cclog.Errorf("NATS start job: insert into database failed: %v", err)
 		return
 	}
 	unlockOnce.Do(api.RepositoryMutex.Unlock)
 
 	for _, tag := range req.Tags {
 		if _, err := api.JobRepository.AddTagOrCreate(nil, id, tag.Type, tag.Name, tag.Scope); err != nil {
-			cclog.Errorf("NATS %s: adding tag to new job %d failed: %v", subject, id, err)
+			cclog.Errorf("NATS start job: adding tag to new job %d failed: %v", id, err)
 			return
 		}
 	}
@@ -129,18 +165,18 @@ func (api *NatsAPI) handleStartJob(subject string, data []byte) {
 
 // handleStopJob processes job stop messages received via NATS.
 // Expected JSON payload follows the StopJobAPIRequest structure.
-func (api *NatsAPI) handleStopJob(subject string, data []byte) {
+func (api *NatsAPI) handleStopJob(payload string) {
 	var req StopJobAPIRequest
 
-	dec := json.NewDecoder(bytes.NewReader(data))
+	dec := json.NewDecoder(strings.NewReader(payload))
 	dec.DisallowUnknownFields()
 	if err := dec.Decode(&req); err != nil {
-		cclog.Errorf("NATS %s: parsing request failed: %v", subject, err)
+		cclog.Errorf("NATS job stop: parsing request failed: %v", err)
 		return
 	}
 
 	if req.JobID == nil {
-		cclog.Errorf("NATS %s: the field 'jobId' is required", subject)
+		cclog.Errorf("NATS job stop: the field 'jobId' is required")
 		return
 	}
 
@@ -148,28 +184,28 @@ func (api *NatsAPI) handleStopJob(subject string, data []byte) {
 	if err != nil {
 		cachedJob, cachedErr := api.JobRepository.FindCached(req.JobID, req.Cluster, req.StartTime)
 		if cachedErr != nil {
-			cclog.Errorf("NATS %s: finding job failed: %v (cached lookup also failed: %v)",
-				subject, err, cachedErr)
+			cclog.Errorf("NATS job stop: finding job failed: %v (cached lookup also failed: %v)",
+				err, cachedErr)
 			return
 		}
 		job = cachedJob
 	}
 
 	if job.State != schema.JobStateRunning {
-		cclog.Errorf("NATS %s: jobId %d (id %d) on %s: job has already been stopped (state is: %s)",
-			subject, job.JobID, job.ID, job.Cluster, job.State)
+		cclog.Errorf("NATS job stop: jobId %d (id %d) on %s: job has already been stopped (state is: %s)",
+			job.JobID, job.ID, job.Cluster, job.State)
 		return
 	}
 
 	if job.StartTime > req.StopTime {
-		cclog.Errorf("NATS %s: jobId %d (id %d) on %s: stopTime %d must be >= startTime %d",
-			subject, job.JobID, job.ID, job.Cluster, req.StopTime, job.StartTime)
+		cclog.Errorf("NATS job stop: jobId %d (id %d) on %s: stopTime %d must be >= startTime %d",
+			job.JobID, job.ID, job.Cluster, req.StopTime, job.StartTime)
 		return
 	}
 
 	if req.State != "" && !req.State.Valid() {
-		cclog.Errorf("NATS %s: jobId %d (id %d) on %s: invalid job state: %#v",
-			subject, job.JobID, job.ID, job.Cluster, req.State)
+		cclog.Errorf("NATS job stop: jobId %d (id %d) on %s: invalid job state: %#v",
+			job.JobID, job.ID, job.Cluster, req.State)
 		return
 	} else if req.State == "" {
 		req.State = schema.JobStateCompleted
@@ -182,8 +218,8 @@ func (api *NatsAPI) handleStopJob(subject string, data []byte) {
 
 	if err := api.JobRepository.Stop(*job.ID, job.Duration, job.State, job.MonitoringStatus); err != nil {
 		if err := api.JobRepository.StopCached(*job.ID, job.Duration, job.State, job.MonitoringStatus); err != nil {
-			cclog.Errorf("NATS %s: jobId %d (id %d) on %s: marking job as '%s' failed: %v",
-				subject, job.JobID, job.ID, job.Cluster, job.State, err)
+			cclog.Errorf("NATS job stop: jobId %d (id %d) on %s: marking job as '%s' failed: %v",
+				job.JobID, job.ID, job.Cluster, job.State, err)
 			return
 		}
 	}
diff --git a/internal/config/config.go b/internal/config/config.go
index b7b8ed06..3c88bcfd 100644
--- a/internal/config/config.go
+++ b/internal/config/config.go
@@ -90,8 +90,7 @@ type ResampleConfig struct {
 }
 
 type NATSConfig struct {
-	SubjectJobStart  string `json:"subjectJobStart"`
-	SubjectJobStop   string `json:"subjectJobStop"`
+	SubjectJobEvent  string `json:"subjectJobEvent"`
 	SubjectNodeState string `json:"subjectNodeState"`
 }
 
diff --git a/pkg/nats/influxDecoder.go b/pkg/nats/influxDecoder.go
new file mode 100644
index 00000000..412f85e9
--- /dev/null
+++ b/pkg/nats/influxDecoder.go
@@ -0,0 +1,59 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package nats
+
+import (
+	"time"
+
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
+)
+
+// DecodeInfluxMessage decodes a single InfluxDB line protocol message from the decoder
+// Returns the decoded CCMessage or an error if decoding fails
+func DecodeInfluxMessage(d *influx.Decoder) (lp.CCMessage, error) {
+	measurement, err := d.Measurement()
+	if err != nil {
+		return nil, err
+	}
+
+	tags := make(map[string]string)
+	for {
+		key, value, err := d.NextTag()
+		if err != nil {
+			return nil, err
+		}
+		if key == nil {
+			break
+		}
+		tags[string(key)] = string(value)
+	}
+
+	fields := make(map[string]interface{})
+	for {
+		key, value, err := d.NextField()
+		if err != nil {
+			return nil, err
+		}
+		if key == nil {
+			break
+		}
+		fields[string(key)] = value.Interface()
+	}
+
+	t, err := d.Time(influx.Nanosecond, time.Time{})
+	if err != nil {
+		return nil, err
+	}
+
+	return lp.NewMessage(
+		string(measurement),
+		tags,
+		nil,
+		fields,
+		t,
+	)
+}

From 64fef9774cce32caf35b8e20adbef51896205315 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 23 Dec 2025 09:22:57 +0100
Subject: [PATCH 16/59] Add unit test for NATS API

---
 internal/api/api_test.go            |  10 +-
 internal/api/nats_test.go           | 892 ++++++++++++++++++++++++++++
 internal/repository/dbConnection.go |  23 +
 3 files changed, 920 insertions(+), 5 deletions(-)
 create mode 100644 internal/api/nats_test.go

diff --git a/internal/api/api_test.go b/internal/api/api_test.go
index d311767c..3030b1c1 100644
--- a/internal/api/api_test.go
+++ b/internal/api/api_test.go
@@ -36,6 +36,8 @@ import (
 )
 
 func setup(t *testing.T) *api.RestAPI {
+	repository.ResetConnection()
+
 	const testconfig = `{
 		"main": {
 	"addr":            "0.0.0.0:8080",
@@ -190,11 +192,9 @@ func setup(t *testing.T) *api.RestAPI {
 }
 
 func cleanup() {
-	// Gracefully shutdown archiver with timeout
 	if err := archiver.Shutdown(5 * time.Second); err != nil {
 		cclog.Warnf("Archiver shutdown timeout in tests: %v", err)
 	}
-	// TODO: Clear all caches, reset all modules, etc...
 }
 
 /*
@@ -230,7 +230,7 @@ func TestRestApi(t *testing.T) {
 	r.StrictSlash(true)
 	restapi.MountAPIRoutes(r)
 
-	var TestJobId int64 = 123
+	var TestJobID int64 = 123
 	TestClusterName := "testcluster"
 	var TestStartTime int64 = 123456789
 
@@ -280,7 +280,7 @@ func TestRestApi(t *testing.T) {
 		}
 		// resolver := graph.GetResolverInstance()
 		restapi.JobRepository.SyncJobs()
-		job, err := restapi.JobRepository.Find(&TestJobId, &TestClusterName, &TestStartTime)
+		job, err := restapi.JobRepository.Find(&TestJobID, &TestClusterName, &TestStartTime)
 		if err != nil {
 			t.Fatal(err)
 		}
@@ -338,7 +338,7 @@ func TestRestApi(t *testing.T) {
 		}
 
 		// Archiving happens asynchronously, will be completed in cleanup
-		job, err := restapi.JobRepository.Find(&TestJobId, &TestClusterName, &TestStartTime)
+		job, err := restapi.JobRepository.Find(&TestJobID, &TestClusterName, &TestStartTime)
 		if err != nil {
 			t.Fatal(err)
 		}
diff --git a/internal/api/nats_test.go b/internal/api/nats_test.go
new file mode 100644
index 00000000..420a359c
--- /dev/null
+++ b/internal/api/nats_test.go
@@ -0,0 +1,892 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+package api
+
+import (
+	"context"
+	"database/sql"
+	"encoding/json"
+	"fmt"
+	"os"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"github.com/ClusterCockpit/cc-backend/internal/archiver"
+	"github.com/ClusterCockpit/cc-backend/internal/auth"
+	"github.com/ClusterCockpit/cc-backend/internal/config"
+	"github.com/ClusterCockpit/cc-backend/internal/graph"
+	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
+	"github.com/ClusterCockpit/cc-backend/internal/repository"
+	"github.com/ClusterCockpit/cc-backend/pkg/archive"
+	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	"github.com/ClusterCockpit/cc-lib/schema"
+
+	_ "github.com/mattn/go-sqlite3"
+)
+
+func setupNatsTest(t *testing.T) *NatsAPI {
+	repository.ResetConnection()
+
+	const testconfig = `{
+		"main": {
+	"addr":            "0.0.0.0:8080",
+	"validate": false,
+  "apiAllowedIPs": [
+    "*"
+  ]
+	},
+	"archive": {
+		"kind": "file",
+		"path": "./var/job-archive"
+	},
+	"auth": {
+  "jwts": {
+      "max-age": "2m"
+  }
+	},
+	"clusters": [
+	{
+	   "name": "testcluster",
+	   "metricDataRepository": {"kind": "test", "url": "bla:8081"},
+	   "filterRanges": {
+		"numNodes": { "from": 1, "to": 64 },
+		"duration": { "from": 0, "to": 86400 },
+		"startTime": { "from": "2022-01-01T00:00:00Z", "to": null }
+	   }
+	}
+	]
+}`
+	const testclusterJSON = `{
+        "name": "testcluster",
+		"subClusters": [
+			{
+				"name": "sc1",
+				"nodes": "host123,host124,host125",
+				"processorType": "Intel Core i7-4770",
+				"socketsPerNode": 1,
+				"coresPerSocket": 4,
+				"threadsPerCore": 2,
+                "flopRateScalar": {
+                  "unit": {
+                    "prefix": "G",
+                    "base": "F/s"
+                  },
+                  "value": 14
+                },
+                "flopRateSimd": {
+                  "unit": {
+                    "prefix": "G",
+                    "base": "F/s"
+                  },
+                  "value": 112
+                },
+                "memoryBandwidth": {
+                  "unit": {
+                    "prefix": "G",
+                    "base": "B/s"
+                  },
+                  "value": 24
+                },
+                "numberOfNodes": 70,
+				"topology": {
+					"node": [0, 1, 2, 3, 4, 5, 6, 7],
+					"socket": [[0, 1, 2, 3, 4, 5, 6, 7]],
+					"memoryDomain": [[0, 1, 2, 3, 4, 5, 6, 7]],
+					"die": [[0, 1, 2, 3, 4, 5, 6, 7]],
+					"core": [[0], [1], [2], [3], [4], [5], [6], [7]]
+				}
+			}
+		],
+		"metricConfig": [
+			{
+				"name": "load_one",
+			    "unit": { "base": ""},
+				"scope": "node",
+				"timestep": 60,
+                "aggregation": "avg",
+				"peak": 8,
+				"normal": 0,
+				"caution": 0,
+				"alert": 0
+			}
+		]
+	}`
+
+	cclog.Init("info", true)
+	tmpdir := t.TempDir()
+	jobarchive := filepath.Join(tmpdir, "job-archive")
+	if err := os.Mkdir(jobarchive, 0o777); err != nil {
+		t.Fatal(err)
+	}
+
+	if err := os.WriteFile(filepath.Join(jobarchive, "version.txt"), fmt.Appendf(nil, "%d", 3), 0o666); err != nil {
+		t.Fatal(err)
+	}
+
+	if err := os.Mkdir(filepath.Join(jobarchive, "testcluster"), 0o777); err != nil {
+		t.Fatal(err)
+	}
+
+	if err := os.WriteFile(filepath.Join(jobarchive, "testcluster", "cluster.json"), []byte(testclusterJSON), 0o666); err != nil {
+		t.Fatal(err)
+	}
+
+	dbfilepath := filepath.Join(tmpdir, "test.db")
+	err := repository.MigrateDB(dbfilepath)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	cfgFilePath := filepath.Join(tmpdir, "config.json")
+	if err := os.WriteFile(cfgFilePath, []byte(testconfig), 0o666); err != nil {
+		t.Fatal(err)
+	}
+
+	ccconf.Init(cfgFilePath)
+
+	// Load and check main configuration
+	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
+		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
+			config.Init(cfg, clustercfg)
+		} else {
+			cclog.Abort("Cluster configuration must be present")
+		}
+	} else {
+		cclog.Abort("Main configuration must be present")
+	}
+	archiveCfg := fmt.Sprintf("{\"kind\": \"file\",\"path\": \"%s\"}", jobarchive)
+
+	repository.Connect("sqlite3", dbfilepath)
+
+	if err := archive.Init(json.RawMessage(archiveCfg), config.Keys.DisableArchive); err != nil {
+		t.Fatal(err)
+	}
+
+	if err := metricdata.Init(); err != nil {
+		t.Fatal(err)
+	}
+
+	archiver.Start(repository.GetJobRepository(), context.Background())
+
+	if cfg := ccconf.GetPackageConfig("auth"); cfg != nil {
+		auth.Init(&cfg)
+	} else {
+		cclog.Warn("Authentication disabled due to missing configuration")
+		auth.Init(nil)
+	}
+
+	graph.Init()
+
+	return NewNatsAPI()
+}
+
+func cleanupNatsTest() {
+	if err := archiver.Shutdown(5 * time.Second); err != nil {
+		cclog.Warnf("Archiver shutdown timeout in tests: %v", err)
+	}
+}
+
+func TestNatsHandleStartJob(t *testing.T) {
+	natsAPI := setupNatsTest(t)
+	t.Cleanup(cleanupNatsTest)
+
+	tests := []struct {
+		name          string
+		payload       string
+		expectError   bool
+		validateJob   func(t *testing.T, job *schema.Job)
+		shouldFindJob bool
+	}{
+		{
+			name: "valid job start",
+			payload: `{
+				"jobId": 1001,
+				"user": "testuser1",
+				"project": "testproj1",
+				"cluster": "testcluster",
+				"partition": "main",
+				"walltime": 7200,
+				"numNodes": 1,
+				"numHwthreads": 8,
+				"numAcc": 0,
+				"shared": "none",
+				"monitoringStatus": 1,
+				"smt": 1,
+				"resources": [
+					{
+						"hostname": "host123",
+						"hwthreads": [0, 1, 2, 3, 4, 5, 6, 7]
+					}
+				],
+				"startTime": 1234567890
+			}`,
+			expectError:   false,
+			shouldFindJob: true,
+			validateJob: func(t *testing.T, job *schema.Job) {
+				if job.JobID != 1001 {
+					t.Errorf("expected JobID 1001, got %d", job.JobID)
+				}
+				if job.User != "testuser1" {
+					t.Errorf("expected user testuser1, got %s", job.User)
+				}
+				if job.State != schema.JobStateRunning {
+					t.Errorf("expected state running, got %s", job.State)
+				}
+			},
+		},
+		{
+			name: "invalid JSON",
+			payload: `{
+				"jobId": "not a number",
+				"user": "testuser2"
+			}`,
+			expectError:   true,
+			shouldFindJob: false,
+		},
+		{
+			name: "missing required fields",
+			payload: `{
+				"jobId": 1002
+			}`,
+			expectError:   true,
+			shouldFindJob: false,
+		},
+		{
+			name: "job with unknown fields (should fail due to DisallowUnknownFields)",
+			payload: `{
+				"jobId": 1003,
+				"user": "testuser3",
+				"project": "testproj3",
+				"cluster": "testcluster",
+				"partition": "main",
+				"walltime": 3600,
+				"numNodes": 1,
+				"numHwthreads": 8,
+				"unknownField": "should cause error",
+				"startTime": 1234567900
+			}`,
+			expectError:   true,
+			shouldFindJob: false,
+		},
+		{
+			name: "job with tags",
+			payload: `{
+				"jobId": 1004,
+				"user": "testuser4",
+				"project": "testproj4",
+				"cluster": "testcluster",
+				"partition": "main",
+				"walltime": 3600,
+				"numNodes": 1,
+				"numHwthreads": 8,
+				"numAcc": 0,
+				"shared": "none",
+				"monitoringStatus": 1,
+				"smt": 1,
+				"resources": [
+					{
+						"hostname": "host123",
+						"hwthreads": [0, 1, 2, 3]
+					}
+				],
+				"tags": [
+					{
+						"type": "test",
+						"name": "testtag",
+						"scope": "testuser4"
+					}
+				],
+				"startTime": 1234567910
+			}`,
+			expectError:   false,
+			shouldFindJob: true,
+			validateJob: func(t *testing.T, job *schema.Job) {
+				if job.JobID != 1004 {
+					t.Errorf("expected JobID 1004, got %d", job.JobID)
+				}
+			},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			natsAPI.handleStartJob(tt.payload)
+			natsAPI.JobRepository.SyncJobs()
+
+			// Allow some time for async operations
+			time.Sleep(100 * time.Millisecond)
+
+			if tt.shouldFindJob {
+				// Extract jobId from payload
+				var payloadMap map[string]any
+				json.Unmarshal([]byte(tt.payload), &payloadMap)
+				jobID := int64(payloadMap["jobId"].(float64))
+				cluster := payloadMap["cluster"].(string)
+				startTime := int64(payloadMap["startTime"].(float64))
+
+				job, err := natsAPI.JobRepository.Find(&jobID, &cluster, &startTime)
+				if err != nil {
+					if !tt.expectError {
+						t.Fatalf("expected to find job, but got error: %v", err)
+					}
+					return
+				}
+
+				if tt.validateJob != nil {
+					tt.validateJob(t, job)
+				}
+			}
+		})
+	}
+}
+
+func TestNatsHandleStopJob(t *testing.T) {
+	natsAPI := setupNatsTest(t)
+	t.Cleanup(cleanupNatsTest)
+
+	// First, create a running job
+	startPayload := `{
+		"jobId": 2001,
+		"user": "testuser",
+		"project": "testproj",
+		"cluster": "testcluster",
+		"partition": "main",
+		"walltime": 3600,
+		"numNodes": 1,
+		"numHwthreads": 8,
+		"numAcc": 0,
+		"shared": "none",
+		"monitoringStatus": 1,
+		"smt": 1,
+		"resources": [
+			{
+				"hostname": "host123",
+				"hwthreads": [0, 1, 2, 3, 4, 5, 6, 7]
+			}
+		],
+		"startTime": 1234567890
+	}`
+
+	natsAPI.handleStartJob(startPayload)
+	natsAPI.JobRepository.SyncJobs()
+	time.Sleep(100 * time.Millisecond)
+
+	tests := []struct {
+		name         string
+		payload      string
+		expectError  bool
+		validateJob  func(t *testing.T, job *schema.Job)
+		setupJobFunc func() // Optional: create specific test job
+	}{
+		{
+			name: "valid job stop - completed",
+			payload: `{
+				"jobId": 2001,
+				"cluster": "testcluster",
+				"startTime": 1234567890,
+				"jobState": "completed",
+				"stopTime": 1234571490
+			}`,
+			expectError: false,
+			validateJob: func(t *testing.T, job *schema.Job) {
+				if job.State != schema.JobStateCompleted {
+					t.Errorf("expected state completed, got %s", job.State)
+				}
+				expectedDuration := int32(1234571490 - 1234567890)
+				if job.Duration != expectedDuration {
+					t.Errorf("expected duration %d, got %d", expectedDuration, job.Duration)
+				}
+			},
+		},
+		{
+			name: "valid job stop - failed",
+			setupJobFunc: func() {
+				startPayloadFailed := `{
+					"jobId": 2002,
+					"user": "testuser",
+					"project": "testproj",
+					"cluster": "testcluster",
+					"partition": "main",
+					"walltime": 3600,
+					"numNodes": 1,
+					"numHwthreads": 8,
+					"numAcc": 0,
+					"shared": "none",
+					"monitoringStatus": 1,
+					"smt": 1,
+					"resources": [
+						{
+							"hostname": "host123",
+							"hwthreads": [0, 1, 2, 3]
+						}
+					],
+					"startTime": 1234567900
+				}`
+				natsAPI.handleStartJob(startPayloadFailed)
+				natsAPI.JobRepository.SyncJobs()
+				time.Sleep(100 * time.Millisecond)
+			},
+			payload: `{
+				"jobId": 2002,
+				"cluster": "testcluster",
+				"startTime": 1234567900,
+				"jobState": "failed",
+				"stopTime": 1234569900
+			}`,
+			expectError: false,
+			validateJob: func(t *testing.T, job *schema.Job) {
+				if job.State != schema.JobStateFailed {
+					t.Errorf("expected state failed, got %s", job.State)
+				}
+			},
+		},
+		{
+			name: "invalid JSON",
+			payload: `{
+				"jobId": "not a number"
+			}`,
+			expectError: true,
+		},
+		{
+			name: "missing jobId",
+			payload: `{
+				"cluster": "testcluster",
+				"jobState": "completed",
+				"stopTime": 1234571490
+			}`,
+			expectError: true,
+		},
+		{
+			name: "invalid job state",
+			setupJobFunc: func() {
+				startPayloadInvalid := `{
+					"jobId": 2003,
+					"user": "testuser",
+					"project": "testproj",
+					"cluster": "testcluster",
+					"partition": "main",
+					"walltime": 3600,
+					"numNodes": 1,
+					"numHwthreads": 8,
+					"numAcc": 0,
+					"shared": "none",
+					"monitoringStatus": 1,
+					"smt": 1,
+					"resources": [
+						{
+							"hostname": "host123",
+							"hwthreads": [0, 1]
+						}
+					],
+					"startTime": 1234567910
+				}`
+				natsAPI.handleStartJob(startPayloadInvalid)
+				natsAPI.JobRepository.SyncJobs()
+				time.Sleep(100 * time.Millisecond)
+			},
+			payload: `{
+				"jobId": 2003,
+				"cluster": "testcluster",
+				"startTime": 1234567910,
+				"jobState": "invalid_state",
+				"stopTime": 1234571510
+			}`,
+			expectError: true,
+		},
+		{
+			name: "stopTime before startTime",
+			setupJobFunc: func() {
+				startPayloadTime := `{
+					"jobId": 2004,
+					"user": "testuser",
+					"project": "testproj",
+					"cluster": "testcluster",
+					"partition": "main",
+					"walltime": 3600,
+					"numNodes": 1,
+					"numHwthreads": 8,
+					"numAcc": 0,
+					"shared": "none",
+					"monitoringStatus": 1,
+					"smt": 1,
+					"resources": [
+						{
+							"hostname": "host123",
+							"hwthreads": [0]
+						}
+					],
+					"startTime": 1234567920
+				}`
+				natsAPI.handleStartJob(startPayloadTime)
+				natsAPI.JobRepository.SyncJobs()
+				time.Sleep(100 * time.Millisecond)
+			},
+			payload: `{
+				"jobId": 2004,
+				"cluster": "testcluster",
+				"startTime": 1234567920,
+				"jobState": "completed",
+				"stopTime": 1234567900
+			}`,
+			expectError: true,
+		},
+		{
+			name: "job not found",
+			payload: `{
+				"jobId": 99999,
+				"cluster": "testcluster",
+				"startTime": 1234567890,
+				"jobState": "completed",
+				"stopTime": 1234571490
+			}`,
+			expectError: true,
+		},
+	}
+
+	testData := schema.JobData{
+		"load_one": map[schema.MetricScope]*schema.JobMetric{
+			schema.MetricScopeNode: {
+				Unit:     schema.Unit{Base: "load"},
+				Timestep: 60,
+				Series: []schema.Series{
+					{
+						Hostname:   "host123",
+						Statistics: schema.MetricStatistics{Min: 0.1, Avg: 0.2, Max: 0.3},
+						Data:       []schema.Float{0.1, 0.1, 0.1, 0.2, 0.2, 0.2, 0.3, 0.3, 0.3},
+					},
+				},
+			},
+		},
+	}
+
+	metricdata.TestLoadDataCallback = func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) {
+		return testData, nil
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if tt.setupJobFunc != nil {
+				tt.setupJobFunc()
+			}
+
+			natsAPI.handleStopJob(tt.payload)
+
+			// Allow some time for async operations
+			time.Sleep(100 * time.Millisecond)
+
+			if !tt.expectError && tt.validateJob != nil {
+				// Extract job details from payload
+				var payloadMap map[string]any
+				json.Unmarshal([]byte(tt.payload), &payloadMap)
+				jobID := int64(payloadMap["jobId"].(float64))
+				cluster := payloadMap["cluster"].(string)
+
+				var startTime *int64
+				if st, ok := payloadMap["startTime"]; ok {
+					t := int64(st.(float64))
+					startTime = &t
+				}
+
+				job, err := natsAPI.JobRepository.Find(&jobID, &cluster, startTime)
+				if err != nil {
+					t.Fatalf("expected to find job, but got error: %v", err)
+				}
+
+				tt.validateJob(t, job)
+			}
+		})
+	}
+}
+
+func TestNatsHandleNodeState(t *testing.T) {
+	natsAPI := setupNatsTest(t)
+	t.Cleanup(cleanupNatsTest)
+
+	tests := []struct {
+		name        string
+		payload     string
+		expectError bool
+		validateFn  func(t *testing.T)
+	}{
+		{
+			name: "valid node state update",
+			payload: `{
+				"cluster": "testcluster",
+				"nodes": [
+					{
+						"hostname": "host123",
+						"states": ["allocated"],
+						"cpusAllocated": 8,
+						"memoryAllocated": 16384,
+						"gpusAllocated": 0,
+						"jobsRunning": 1
+					}
+				]
+			}`,
+			expectError: false,
+			validateFn: func(t *testing.T) {
+				// In a full test, we would verify the node state was updated in the database
+				// For now, just ensure no error occurred
+			},
+		},
+		{
+			name: "multiple nodes",
+			payload: `{
+				"cluster": "testcluster",
+				"nodes": [
+					{
+						"hostname": "host123",
+						"states": ["idle"],
+						"cpusAllocated": 0,
+						"memoryAllocated": 0,
+						"gpusAllocated": 0,
+						"jobsRunning": 0
+					},
+					{
+						"hostname": "host124",
+						"states": ["allocated"],
+						"cpusAllocated": 4,
+						"memoryAllocated": 8192,
+						"gpusAllocated": 1,
+						"jobsRunning": 1
+					}
+				]
+			}`,
+			expectError: false,
+		},
+		{
+			name: "invalid JSON",
+			payload: `{
+				"cluster": "testcluster",
+				"nodes": "not an array"
+			}`,
+			expectError: true,
+		},
+		{
+			name: "empty nodes array",
+			payload: `{
+				"cluster": "testcluster",
+				"nodes": []
+			}`,
+			expectError: false, // Empty array should not cause error
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			natsAPI.handleNodeState("test.subject", []byte(tt.payload))
+
+			// Allow some time for async operations
+			time.Sleep(50 * time.Millisecond)
+
+			if tt.validateFn != nil {
+				tt.validateFn(t)
+			}
+		})
+	}
+}
+
+func TestNatsProcessJobEvent(t *testing.T) {
+	natsAPI := setupNatsTest(t)
+	t.Cleanup(cleanupNatsTest)
+
+	msgStartJob, err := lp.NewMessage(
+		"job",
+		map[string]string{"function": "start_job"},
+		nil,
+		map[string]any{
+			"event": `{
+				"jobId": 3001,
+				"user": "testuser",
+				"project": "testproj",
+				"cluster": "testcluster",
+				"partition": "main",
+				"walltime": 3600,
+				"numNodes": 1,
+				"numHwthreads": 8,
+				"numAcc": 0,
+				"shared": "none",
+				"monitoringStatus": 1,
+				"smt": 1,
+				"resources": [
+					{
+						"hostname": "host123",
+						"hwthreads": [0, 1, 2, 3]
+					}
+				],
+				"startTime": 1234567890
+			}`,
+		},
+		time.Now(),
+	)
+	if err != nil {
+		t.Fatalf("failed to create test message: %v", err)
+	}
+
+	msgMissingTag, err := lp.NewMessage(
+		"job",
+		map[string]string{},
+		nil,
+		map[string]any{
+			"event": `{}`,
+		},
+		time.Now(),
+	)
+	if err != nil {
+		t.Fatalf("failed to create test message: %v", err)
+	}
+
+	msgUnknownFunc, err := lp.NewMessage(
+		"job",
+		map[string]string{"function": "unknown_function"},
+		nil,
+		map[string]any{
+			"event": `{}`,
+		},
+		time.Now(),
+	)
+	if err != nil {
+		t.Fatalf("failed to create test message: %v", err)
+	}
+
+	tests := []struct {
+		name        string
+		message     lp.CCMessage
+		expectError bool
+	}{
+		{
+			name:        "start_job function",
+			message:     msgStartJob,
+			expectError: false,
+		},
+		{
+			name:        "missing function tag",
+			message:     msgMissingTag,
+			expectError: true,
+		},
+		{
+			name:        "unknown function",
+			message:     msgUnknownFunc,
+			expectError: false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			natsAPI.processJobEvent(tt.message)
+			time.Sleep(50 * time.Millisecond)
+		})
+	}
+}
+
+func TestNatsHandleJobEvent(t *testing.T) {
+	natsAPI := setupNatsTest(t)
+	t.Cleanup(cleanupNatsTest)
+
+	tests := []struct {
+		name        string
+		data        []byte
+		expectError bool
+	}{
+		{
+			name:        "valid influx line protocol",
+			data:        []byte(`job,function=start_job event="{\"jobId\":4001,\"user\":\"testuser\",\"project\":\"testproj\",\"cluster\":\"testcluster\",\"partition\":\"main\",\"walltime\":3600,\"numNodes\":1,\"numHwthreads\":8,\"numAcc\":0,\"shared\":\"none\",\"monitoringStatus\":1,\"smt\":1,\"resources\":[{\"hostname\":\"host123\",\"hwthreads\":[0,1,2,3]}],\"startTime\":1234567890}"`),
+			expectError: false,
+		},
+		{
+			name:        "invalid influx line protocol",
+			data:        []byte(`invalid line protocol format`),
+			expectError: true,
+		},
+		{
+			name:        "empty data",
+			data:        []byte(``),
+			expectError: false, // Decoder should handle empty input gracefully
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			// HandleJobEvent doesn't return errors, it logs them
+			// We're just ensuring it doesn't panic
+			natsAPI.handleJobEvent("test.subject", tt.data)
+			time.Sleep(50 * time.Millisecond)
+		})
+	}
+}
+
+func TestNatsHandleStartJobDuplicatePrevention(t *testing.T) {
+	natsAPI := setupNatsTest(t)
+	t.Cleanup(cleanupNatsTest)
+
+	// Start a job
+	payload := `{
+		"jobId": 5001,
+		"user": "testuser",
+		"project": "testproj",
+		"cluster": "testcluster",
+		"partition": "main",
+		"walltime": 3600,
+		"numNodes": 1,
+		"numHwthreads": 8,
+		"numAcc": 0,
+		"shared": "none",
+		"monitoringStatus": 1,
+		"smt": 1,
+		"resources": [
+			{
+				"hostname": "host123",
+				"hwthreads": [0, 1, 2, 3]
+			}
+		],
+		"startTime": 1234567890
+	}`
+
+	natsAPI.handleStartJob(payload)
+	natsAPI.JobRepository.SyncJobs()
+	time.Sleep(100 * time.Millisecond)
+
+	// Try to start the same job again (within 24 hours)
+	duplicatePayload := `{
+		"jobId": 5001,
+		"user": "testuser",
+		"project": "testproj",
+		"cluster": "testcluster",
+		"partition": "main",
+		"walltime": 3600,
+		"numNodes": 1,
+		"numHwthreads": 8,
+		"numAcc": 0,
+		"shared": "none",
+		"monitoringStatus": 1,
+		"smt": 1,
+		"resources": [
+			{
+				"hostname": "host123",
+				"hwthreads": [0, 1, 2, 3]
+			}
+		],
+		"startTime": 1234567900
+	}`
+
+	natsAPI.handleStartJob(duplicatePayload)
+	natsAPI.JobRepository.SyncJobs()
+	time.Sleep(100 * time.Millisecond)
+
+	// Verify only one job exists
+	jobID := int64(5001)
+	cluster := "testcluster"
+	jobs, err := natsAPI.JobRepository.FindAll(&jobID, &cluster, nil)
+	if err != nil && err != sql.ErrNoRows {
+		t.Fatalf("unexpected error: %v", err)
+	}
+
+	if len(jobs) != 1 {
+		t.Errorf("expected 1 job, got %d", len(jobs))
+	}
+}
diff --git a/internal/repository/dbConnection.go b/internal/repository/dbConnection.go
index 0f7536b7..be0b161b 100644
--- a/internal/repository/dbConnection.go
+++ b/internal/repository/dbConnection.go
@@ -115,3 +115,26 @@ func GetConnection() *DBConnection {
 
 	return dbConnInstance
 }
+
+// ResetConnection closes the current database connection and resets the connection state.
+// This function is intended for testing purposes only to allow test isolation.
+func ResetConnection() error {
+	if dbConnInstance != nil && dbConnInstance.DB != nil {
+		if err := dbConnInstance.DB.Close(); err != nil {
+			return fmt.Errorf("failed to close database connection: %w", err)
+		}
+	}
+
+	dbConnInstance = nil
+	dbConnOnce = sync.Once{}
+	jobRepoInstance = nil
+	jobRepoOnce = sync.Once{}
+	nodeRepoInstance = nil
+	nodeRepoOnce = sync.Once{}
+	userRepoInstance = nil
+	userRepoOnce = sync.Once{}
+	userCfgRepoInstance = nil
+	userCfgRepoOnce = sync.Once{}
+
+	return nil
+}

From 9bf5c5dc1a0b5eae739a8ef8971d470059def827 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 23 Dec 2025 09:34:09 +0100
Subject: [PATCH 17/59] Update README and config schema

---
 CLAUDE.md                 | 94 ++++++++++++++++++++++++++++++++++++++-
 README.md                 | 62 +++++++++++++++++++++-----
 configs/config-demo.json  | 12 ++---
 configs/config.json       |  4 ++
 internal/config/schema.go | 15 +++++++
 5 files changed, 165 insertions(+), 22 deletions(-)

diff --git a/CLAUDE.md b/CLAUDE.md
index 379b4dbb..67412a76 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -100,11 +100,15 @@ The backend follows a layered architecture with clear separation of concerns:
   - Pluggable backends: cc-metric-store, Prometheus, InfluxDB
   - Each cluster can have a different metric data backend
 - **internal/archiver**: Job archiving to file-based archive
+- **internal/api/nats.go**: NATS-based API for job and node operations
+  - Subscribes to NATS subjects for job events (start/stop)
+  - Handles node state updates via NATS
+  - Uses InfluxDB line protocol message format
 - **pkg/archive**: Job archive backend implementations
   - File system backend (default)
   - S3 backend
   - SQLite backend (experimental)
-- **pkg/nats**: NATS integration for metric ingestion
+- **pkg/nats**: NATS client and message decoding utilities
 
 ### Frontend Structure
 
@@ -146,6 +150,14 @@ applied automatically on startup. Version tracking in `version` table.
 ## Configuration
 
 - **config.json**: Main configuration (clusters, metric repositories, archive settings)
+  - `main.apiSubjects`: NATS subject configuration (optional)
+    - `subjectJobEvent`: Subject for job start/stop events (e.g., "cc.job.event")
+    - `subjectNodeState`: Subject for node state updates (e.g., "cc.node.state")
+  - `nats`: NATS client connection configuration (optional)
+    - `address`: NATS server address (e.g., "nats://localhost:4222")
+    - `username`: Authentication username (optional)
+    - `password`: Authentication password (optional)
+    - `creds-file-path`: Path to NATS credentials file (optional)
 - **.env**: Environment variables (secrets like JWT keys)
   - Copy from `configs/env-template.txt`
   - NEVER commit this file
@@ -207,9 +219,87 @@ applied automatically on startup. Version tracking in `version` table.
 2. Increment `repository.Version`
 3. Test with fresh database and existing database
 
+## NATS API
+
+The backend supports a NATS-based API as an alternative to the REST API for job and node operations.
+
+### Setup
+
+1. Configure NATS client connection in `config.json`:
+   ```json
+   {
+     "nats": {
+       "address": "nats://localhost:4222",
+       "username": "user",
+       "password": "pass"
+     }
+   }
+   ```
+
+2. Configure API subjects in `config.json` under `main`:
+   ```json
+   {
+     "main": {
+       "apiSubjects": {
+         "subjectJobEvent": "cc.job.event",
+         "subjectNodeState": "cc.node.state"
+       }
+     }
+   }
+   ```
+
+### Message Format
+
+Messages use **InfluxDB line protocol** format with the following structure:
+
+#### Job Events
+
+**Start Job:**
+```
+job,function=start_job event="{\"jobId\":123,\"user\":\"alice\",\"cluster\":\"test\", ...}" 1234567890000000000
+```
+
+**Stop Job:**
+```
+job,function=stop_job event="{\"jobId\":123,\"cluster\":\"test\",\"startTime\":1234567890,\"stopTime\":1234571490,\"jobState\":\"completed\"}" 1234571490000000000
+```
+
+**Tags:**
+- `function`: Either `start_job` or `stop_job`
+
+**Fields:**
+- `event`: JSON payload containing job data (see REST API documentation for schema)
+
+#### Node State Updates
+
+```json
+{
+  "cluster": "testcluster",
+  "nodes": [
+    {
+      "hostname": "node001",
+      "states": ["allocated"],
+      "cpusAllocated": 8,
+      "memoryAllocated": 16384,
+      "gpusAllocated": 0,
+      "jobsRunning": 1
+    }
+  ]
+}
+```
+
+### Implementation Notes
+
+- NATS API mirrors REST API functionality but uses messaging
+- Job start/stop events are processed asynchronously
+- Duplicate job detection is handled (same as REST API)
+- All validation rules from REST API apply
+- Messages are logged; no responses are sent back to publishers
+- If NATS client is unavailable, API subscriptions are skipped (logged as warning)
+
 ## Dependencies
 
 - Go 1.24.0+ (check go.mod for exact version)
 - Node.js (for frontend builds)
 - SQLite 3 (only supported database)
-- Optional: NATS server for metric ingestion
+- Optional: NATS server for NATS API integration
diff --git a/README.md b/README.md
index a0352d17..468a12ad 100644
--- a/README.md
+++ b/README.md
@@ -22,11 +22,12 @@ switching from PHP Symfony to a Golang based solution are explained
 ## Overview
 
 This is a Golang web backend for the ClusterCockpit job-specific performance
-monitoring framework. It provides a REST API for integrating ClusterCockpit with
-an HPC cluster batch system and external analysis scripts. Data exchange between
-the web front-end and the back-end is based on a GraphQL API. The web frontend
-is also served by the backend using [Svelte](https://svelte.dev/) components.
-Layout and styling are based on [Bootstrap 5](https://getbootstrap.com/) using
+monitoring framework. It provides a REST API and an optional NATS-based messaging
+API for integrating ClusterCockpit with an HPC cluster batch system and external
+analysis scripts. Data exchange between the web front-end and the back-end is
+based on a GraphQL API. The web frontend is also served by the backend using
+[Svelte](https://svelte.dev/) components. Layout and styling are based on
+[Bootstrap 5](https://getbootstrap.com/) using
 [Bootstrap Icons](https://icons.getbootstrap.com/).
 
 The backend uses [SQLite 3](https://sqlite.org/) as the relational SQL database.
@@ -35,6 +36,10 @@ databases, the only tested and supported setup is to use cc-metric-store as the
 metric data backend. Documentation on how to integrate ClusterCockpit with other
 time series databases will be added in the future.
 
+For real-time integration with HPC systems, the backend can subscribe to
+[NATS](https://nats.io/) subjects to receive job start/stop events and node
+state updates, providing an alternative to REST API polling.
+
 Completed batch jobs are stored in a file-based job archive according to
 [this specification](https://github.com/ClusterCockpit/cc-specifications/tree/master/job-archive).
 The backend supports authentication via local accounts, an external LDAP
@@ -130,27 +135,60 @@ ln -s <your-existing-job-archive> ./var/job-archive
 
 ## Project file structure
 
+- [`.github/`](https://github.com/ClusterCockpit/cc-backend/tree/master/.github)
+  GitHub Actions workflows and dependabot configuration for CI/CD.
 - [`api/`](https://github.com/ClusterCockpit/cc-backend/tree/master/api)
   contains the API schema files for the REST and GraphQL APIs. The REST API is
   documented in the OpenAPI 3.0 format in
-  [./api/openapi.yaml](./api/openapi.yaml).
+  [./api/swagger.yaml](./api/swagger.yaml). The GraphQL schema is in
+  [./api/schema.graphqls](./api/schema.graphqls).
 - [`cmd/cc-backend`](https://github.com/ClusterCockpit/cc-backend/tree/master/cmd/cc-backend)
-  contains `main.go` for the main application.
+  contains the main application entry point and CLI implementation.
 - [`configs/`](https://github.com/ClusterCockpit/cc-backend/tree/master/configs)
   contains documentation about configuration and command line options and required
-  environment variables. A sample configuration file is provided.
-- [`docs/`](https://github.com/ClusterCockpit/cc-backend/tree/master/docs)
-  contains more in-depth documentation.
+  environment variables. Sample configuration files are provided.
 - [`init/`](https://github.com/ClusterCockpit/cc-backend/tree/master/init)
   contains an example of setting up systemd for production use.
 - [`internal/`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal)
   contains library source code that is not intended for use by others.
+  - [`api`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/api)
+    REST API handlers and NATS integration
+  - [`archiver`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/archiver)
+    Job archiving functionality
+  - [`auth`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/auth)
+    Authentication (local, LDAP, OIDC) and JWT token handling
+  - [`config`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/config)
+    Configuration management and validation
+  - [`graph`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/graph)
+    GraphQL schema and resolvers
+  - [`importer`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/importer)
+    Job data import and database initialization
+  - [`memorystore`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/memorystore)
+    In-memory metric data store with checkpointing
+  - [`metricdata`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/metricdata)
+    Metric data repository implementations (cc-metric-store, Prometheus)
+  - [`metricDataDispatcher`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/metricDataDispatcher)
+    Dispatches metric data loading to appropriate backends
+  - [`repository`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/repository)
+    Database repository layer for jobs and metadata
+  - [`routerConfig`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/routerConfig)
+    HTTP router configuration and middleware
+  - [`tagger`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/tagger)
+    Job classification and application detection
+  - [`taskmanager`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/taskmanager)
+    Background task management and scheduled jobs
 - [`pkg/`](https://github.com/ClusterCockpit/cc-backend/tree/master/pkg)
   contains Go packages that can be used by other projects.
+  - [`archive`](https://github.com/ClusterCockpit/cc-backend/tree/master/pkg/archive)
+    Job archive backend implementations (filesystem, S3)
+  - [`nats`](https://github.com/ClusterCockpit/cc-backend/tree/master/pkg/nats)
+    NATS client and message handling
 - [`tools/`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools)
   Additional command line helper tools.
   - [`archive-manager`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools/archive-manager)
-    Commands for getting infos about and existing job archive.
+    Commands for getting infos about an existing job archive.
+  - [`archive-migration`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools/archive-migration)
+    Tool for migrating job archives between formats.
   - [`convert-pem-pubkey`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools/convert-pem-pubkey)
     Tool to convert external pubkey for use in `cc-backend`.
   - [`gen-keypair`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools/gen-keypair)
@@ -162,7 +200,7 @@ ln -s <your-existing-job-archive> ./var/job-archive
   - [`frontend`](https://github.com/ClusterCockpit/cc-backend/tree/master/web/frontend)
     Svelte components and static assets for the frontend UI
   - [`templates`](https://github.com/ClusterCockpit/cc-backend/tree/master/web/templates)
-    Server-side Go templates
+    Server-side Go templates, including monitoring views
 - [`gqlgen.yml`](https://github.com/ClusterCockpit/cc-backend/blob/master/gqlgen.yml)
   Configures the behaviour and generation of
   [gqlgen](https://github.com/99designs/gqlgen).
diff --git a/configs/config-demo.json b/configs/config-demo.json
index 58366fb5..aa388316 100644
--- a/configs/config-demo.json
+++ b/configs/config-demo.json
@@ -5,14 +5,9 @@
     "resampling": {
       "minimumPoints": 600,
       "trigger": 180,
-      "resolutions": [
-        240,
-        60
-      ]
+      "resolutions": [240, 60]
     },
-    "apiAllowedIPs": [
-      "*"
-    ],
+    "apiAllowedIPs": ["*"],
     "emission-constant": 317
   },
   "cron": {
@@ -103,4 +98,5 @@
       }
     ]
   }
-}
\ No newline at end of file
+}
+
diff --git a/configs/config.json b/configs/config.json
index 88a9e930..41d8ecac 100644
--- a/configs/config.json
+++ b/configs/config.json
@@ -15,6 +15,10 @@
         240,
         60
       ]
+    },
+    "apiSubjects": {
+      "subjectJobEvent": "cc.job.event",
+      "subjectNodeState": "cc.node.state"
     }
   },
   "cron": {
diff --git a/internal/config/schema.go b/internal/config/schema.go
index b171f96a..ff8d0c92 100644
--- a/internal/config/schema.go
+++ b/internal/config/schema.go
@@ -119,6 +119,21 @@ var configSchema = `
         }
       },
       "required": ["trigger", "resolutions"]
+    },
+    "apiSubjects": {
+      "description": "NATS subjects configuration for subscribing to job and node events.",
+      "type": "object",
+      "properties": {
+        "subjectJobEvent": {
+          "description": "NATS subject for job events (start_job, stop_job)",
+          "type": "string"
+        },
+        "subjectNodeState": {
+          "description": "NATS subject for node state updates",
+          "type": "string"
+        }
+      },
+      "required": ["subjectJobEvent", "subjectNodeState"]
     }
 	},
   "required": ["apiAllowedIPs"]

From 8576ae458d11d5df74faca4088f9ff4d0a0c7774 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 24 Dec 2025 09:24:18 +0100
Subject: [PATCH 18/59] Switch to cc-lib v2

---
 cmd/cc-backend/init.go                        |   4 +-
 cmd/cc-backend/main.go                        |  14 ++---
 cmd/cc-backend/server.go                      |   6 +-
 go.mod                                        |  16 ++---
 go.sum                                        |  32 +++++-----
 gqlgen.yml                                    |  52 +++++++--------
 internal/api/api_test.go                      |   6 +-
 internal/api/cluster.go                       |   2 +-
 internal/api/job.go                           |   4 +-
 internal/api/memorystore.go                   |   2 +-
 internal/api/nats.go                          |  21 +++++--
 internal/api/nats_test.go                     |   8 +--
 internal/api/node.go                          |   2 +-
 internal/api/rest.go                          |   6 +-
 internal/api/user.go                          |   4 +-
 internal/archiver/archiveWorker.go            |   4 +-
 internal/archiver/archiver.go                 |   4 +-
 internal/auth/auth.go                         |   6 +-
 internal/auth/jwt.go                          |   4 +-
 internal/auth/jwtCookieSession.go             |   4 +-
 internal/auth/jwtHelpers.go                   |   4 +-
 internal/auth/jwtHelpers_test.go              |   2 +-
 internal/auth/jwtSession.go                   |   4 +-
 internal/auth/ldap.go                         |   4 +-
 internal/auth/local.go                        |   4 +-
 internal/auth/oidc.go                         |   4 +-
 internal/config/config.go                     |   4 +-
 internal/config/config_test.go                |   4 +-
 internal/config/validate.go                   |   2 +-
 internal/graph/generated/generated.go         |   2 +-
 internal/graph/model/models_gen.go            |   2 +-
 internal/graph/resolver.go                    |   2 +-
 internal/graph/schema.resolvers.go            |   4 +-
 internal/graph/util.go                        |   4 +-
 internal/importer/handleImport.go             |   4 +-
 internal/importer/importer_test.go            |   4 +-
 internal/importer/initDB.go                   |   4 +-
 internal/importer/normalize.go                |   2 +-
 internal/importer/normalize_test.go           |   2 +-
 internal/memorystore/api.go                   |   4 +-
 internal/memorystore/archive.go               |   2 +-
 internal/memorystore/avroCheckpoint.go        |   4 +-
 internal/memorystore/avroHelper.go            |   2 +-
 internal/memorystore/avroStruct.go            |   2 +-
 internal/memorystore/buffer.go                |   2 +-
 internal/memorystore/checkpoint.go            |   4 +-
 internal/memorystore/level.go                 |   2 +-
 internal/memorystore/lineprotocol.go          |   4 +-
 internal/memorystore/memorystore.go           |   8 +--
 internal/memorystore/memorystore_test.go      |   2 +-
 internal/memorystore/stats.go                 |   2 +-
 internal/metricDataDispatcher/dataLoader.go   |   8 +--
 .../metricdata/cc-metric-store-internal.go    |   4 +-
 internal/metricdata/cc-metric-store.go        |   4 +-
 internal/metricdata/metricdata.go             |   4 +-
 internal/metricdata/prometheus.go             |   4 +-
 internal/metricdata/utils.go                  |   2 +-
 internal/repository/dbConnection.go           |   2 +-
 internal/repository/hooks.go                  |   2 +-
 internal/repository/job.go                    |   6 +-
 internal/repository/jobCreate.go              |   4 +-
 internal/repository/jobFind.go                |   4 +-
 internal/repository/jobHooks.go               |   2 +-
 internal/repository/jobQuery.go               |   4 +-
 internal/repository/job_test.go               |   2 +-
 internal/repository/migration.go              |   2 +-
 internal/repository/node.go                   |   6 +-
 internal/repository/node_test.go              |   6 +-
 internal/repository/repository_test.go        |   4 +-
 internal/repository/stats.go                  |   4 +-
 internal/repository/tags.go                   |   4 +-
 internal/repository/testdata/job.db           | Bin 987136 -> 987136 bytes
 internal/repository/user.go                   |   4 +-
 internal/repository/userConfig.go             |   6 +-
 internal/repository/userConfig_test.go        |   6 +-
 internal/routerConfig/routes.go               |   6 +-
 internal/tagger/classifyJob.go                |   6 +-
 internal/tagger/classifyJob_test.go           |   2 +-
 internal/tagger/detectApp.go                  |   6 +-
 internal/tagger/detectApp_test.go             |   2 +-
 internal/tagger/tagger.go                     |   4 +-
 internal/tagger/tagger_test.go                |   2 +-
 internal/taskmanager/commitJobService.go      |   2 +-
 internal/taskmanager/compressionService.go    |   4 +-
 internal/taskmanager/ldapSyncService.go       |   2 +-
 internal/taskmanager/retentionService.go      |   2 +-
 internal/taskmanager/stopJobsExceedTime.go    |   2 +-
 internal/taskmanager/taskManager.go           |   2 +-
 internal/taskmanager/updateDurationService.go |   2 +-
 .../taskmanager/updateFootprintService.go     |   4 +-
 pkg/archive/archive.go                        |   6 +-
 pkg/archive/archive_test.go                   |   4 +-
 pkg/archive/clusterConfig.go                  |   4 +-
 pkg/archive/fsBackend.go                      |   6 +-
 pkg/archive/fsBackend_test.go                 |   4 +-
 pkg/archive/json.go                           |   4 +-
 pkg/archive/nodelist.go                       |   2 +-
 pkg/archive/s3Backend.go                      |   6 +-
 pkg/archive/s3Backend_test.go                 |   2 +-
 pkg/archive/sqliteBackend.go                  |   6 +-
 pkg/archive/sqliteBackend_test.go             |   2 +-
 pkg/nats/client.go                            |   2 +-
 pkg/nats/config.go                            |   2 +-
 pkg/nats/influxDecoder.go                     |  59 ------------------
 tools/archive-manager/import_test.go          |   4 +-
 tools/archive-manager/main.go                 |   4 +-
 tools/archive-migration/main.go               |   2 +-
 tools/archive-migration/transforms.go         |   2 +-
 web/web.go                                    |   6 +-
 web/webConfig_test.go                         |   2 +-
 110 files changed, 261 insertions(+), 311 deletions(-)
 delete mode 100644 pkg/nats/influxDecoder.go

diff --git a/cmd/cc-backend/init.go b/cmd/cc-backend/init.go
index 151eee9e..025396be 100644
--- a/cmd/cc-backend/init.go
+++ b/cmd/cc-backend/init.go
@@ -15,8 +15,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
 const envString = `
diff --git a/cmd/cc-backend/main.go b/cmd/cc-backend/main.go
index 9464ccf4..f8b4aea1 100644
--- a/cmd/cc-backend/main.go
+++ b/cmd/cc-backend/main.go
@@ -32,11 +32,11 @@ import (
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
 	"github.com/ClusterCockpit/cc-backend/pkg/nats"
 	"github.com/ClusterCockpit/cc-backend/web"
-	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/runtimeEnv"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/runtime"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 	"github.com/google/gops/agent"
 	"github.com/joho/godotenv"
 
@@ -371,7 +371,7 @@ func runServer(ctx context.Context) error {
 		case <-ctx.Done():
 		}
 
-		runtimeEnv.SystemdNotifiy(false, "Shutting down ...")
+		runtime.SystemdNotify(false, "Shutting down ...")
 		srv.Shutdown(ctx)
 		util.FsWatcherShutdown()
 		taskmanager.Shutdown()
@@ -381,7 +381,7 @@ func runServer(ctx context.Context) error {
 	if os.Getenv(envGOGC) == "" {
 		debug.SetGCPercent(25)
 	}
-	runtimeEnv.SystemdNotifiy(true, "running")
+	runtime.SystemdNotify(true, "running")
 
 	// Wait for completion or error
 	go func() {
diff --git a/cmd/cc-backend/server.go b/cmd/cc-backend/server.go
index 4ed79622..53e24c88 100644
--- a/cmd/cc-backend/server.go
+++ b/cmd/cc-backend/server.go
@@ -33,8 +33,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/routerConfig"
 	"github.com/ClusterCockpit/cc-backend/pkg/nats"
 	"github.com/ClusterCockpit/cc-backend/web"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/runtimeEnv"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/runtime"
 	"github.com/gorilla/handlers"
 	"github.com/gorilla/mux"
 	httpSwagger "github.com/swaggo/http-swagger"
@@ -347,7 +347,7 @@ func (s *Server) Start(ctx context.Context) error {
 	// Because this program will want to bind to a privileged port (like 80), the listener must
 	// be established first, then the user can be changed, and after that,
 	// the actual http server can be started.
-	if err := runtimeEnv.DropPrivileges(config.Keys.Group, config.Keys.User); err != nil {
+	if err := runtime.DropPrivileges(config.Keys.Group, config.Keys.User); err != nil {
 		return fmt.Errorf("dropping privileges: %w", err)
 	}
 
diff --git a/go.mod b/go.mod
index b821f7bf..36ce47b9 100644
--- a/go.mod
+++ b/go.mod
@@ -11,14 +11,14 @@ tool (
 
 require (
 	github.com/99designs/gqlgen v0.17.84
-	github.com/ClusterCockpit/cc-lib v1.0.2
+	github.com/ClusterCockpit/cc-lib/v2 v2.0.0
 	github.com/Masterminds/squirrel v1.5.4
 	github.com/aws/aws-sdk-go-v2 v1.41.0
 	github.com/aws/aws-sdk-go-v2/config v1.31.20
 	github.com/aws/aws-sdk-go-v2/credentials v1.18.24
 	github.com/aws/aws-sdk-go-v2/service/s3 v1.90.2
 	github.com/coreos/go-oidc/v3 v3.16.0
-	github.com/expr-lang/expr v1.17.6
+	github.com/expr-lang/expr v1.17.7
 	github.com/go-co-op/gocron/v2 v2.18.2
 	github.com/go-ldap/ldap/v3 v3.4.12
 	github.com/golang-jwt/jwt/v5 v5.3.0
@@ -41,7 +41,7 @@ require (
 	github.com/swaggo/http-swagger v1.3.4
 	github.com/swaggo/swag v1.16.6
 	github.com/vektah/gqlparser/v2 v2.5.31
-	golang.org/x/crypto v0.45.0
+	golang.org/x/crypto v0.46.0
 	golang.org/x/oauth2 v0.32.0
 	golang.org/x/time v0.14.0
 )
@@ -95,14 +95,14 @@ require (
 	github.com/jonboulle/clockwork v0.5.0 // indirect
 	github.com/jpillora/backoff v1.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
-	github.com/klauspost/compress v1.18.1 // indirect
+	github.com/klauspost/compress v1.18.2 // indirect
 	github.com/lann/builder v0.0.0-20180802200727-47ae307949d0 // indirect
 	github.com/lann/ps v0.0.0-20150810152359-62de8c46ede0 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f // indirect
-	github.com/nats-io/nkeys v0.4.11 // indirect
+	github.com/nats-io/nkeys v0.4.12 // indirect
 	github.com/nats-io/nuid v1.0.1 // indirect
 	github.com/oapi-codegen/runtime v1.1.1 // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
@@ -121,9 +121,9 @@ require (
 	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect
 	golang.org/x/mod v0.30.0 // indirect
 	golang.org/x/net v0.47.0 // indirect
-	golang.org/x/sync v0.18.0 // indirect
-	golang.org/x/sys v0.38.0 // indirect
-	golang.org/x/text v0.31.0 // indirect
+	golang.org/x/sync v0.19.0 // indirect
+	golang.org/x/sys v0.39.0 // indirect
+	golang.org/x/text v0.32.0 // indirect
 	golang.org/x/tools v0.39.0 // indirect
 	google.golang.org/protobuf v1.36.10 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
diff --git a/go.sum b/go.sum
index 04e2514b..9038d960 100644
--- a/go.sum
+++ b/go.sum
@@ -4,8 +4,8 @@ github.com/99designs/gqlgen v0.17.84 h1:iVMdiStgUVx/BFkMb0J5GAXlqfqtQ7bqMCYK6v52
 github.com/99designs/gqlgen v0.17.84/go.mod h1:qjoUqzTeiejdo+bwUg8unqSpeYG42XrcrQboGIezmFA=
 github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358 h1:mFRzDkZVAjdal+s7s0MwaRv9igoPqLRdzOLzw/8Xvq8=
 github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358/go.mod h1:chxPXzSsl7ZWRAuOIE23GDNzjWuZquvFlgA8xmpunjU=
-github.com/ClusterCockpit/cc-lib v1.0.2 h1:ZWn3oZkXgxrr3zSigBdlOOfayZ4Om4xL20DhmritPPg=
-github.com/ClusterCockpit/cc-lib v1.0.2/go.mod h1:UGdOvXEnjFqlnPSxtvtFwO6BtXYW6NnXFoud9FtN93k=
+github.com/ClusterCockpit/cc-lib/v2 v2.0.0 h1:OjDADx8mf9SflqeeKUuhy5pamu4YDucae6wUX6vvNNA=
+github.com/ClusterCockpit/cc-lib/v2 v2.0.0/go.mod h1:JuxMAuEOaLLNEnnL9U3ejha8kMvsSatLdKPZEgJw6iw=
 github.com/KyleBanks/depth v1.2.1 h1:5h8fQADFrWtarTdtDudMmGsC7GPbOAu6RVB3ffsVFHc=
 github.com/KyleBanks/depth v1.2.1/go.mod h1:jzSb9d0L43HxTQfT+oSA1EEp2q+ne2uh6XgeJcm8brE=
 github.com/Masterminds/squirrel v1.5.4 h1:uUcX/aBc8O7Fg9kaISIUsHXdKuqehiXAMQTYX8afzqM=
@@ -79,8 +79,8 @@ github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dgryski/trifles v0.0.0-20230903005119-f50d829f2e54 h1:SG7nF6SRlWhcT7cNTs5R6Hk4V2lcmLz2NsG2VnInyNo=
 github.com/dgryski/trifles v0.0.0-20230903005119-f50d829f2e54/go.mod h1:if7Fbed8SFyPtHLHbg49SI7NAdJiC5WIA09pe59rfAA=
-github.com/expr-lang/expr v1.17.6 h1:1h6i8ONk9cexhDmowO/A64VPxHScu7qfSl2k8OlINec=
-github.com/expr-lang/expr v1.17.6/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
+github.com/expr-lang/expr v1.17.7 h1:Q0xY/e/2aCIp8g9s/LGvMDCC5PxYlvHgDZRQ4y16JX8=
+github.com/expr-lang/expr v1.17.7/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
 github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
 github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
 github.com/frankban/quicktest v1.11.0/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
@@ -197,8 +197,8 @@ github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
-github.com/klauspost/compress v1.18.1 h1:bcSGx7UbpBqMChDtsF28Lw6v/G94LPrrbMbdC3JH2co=
-github.com/klauspost/compress v1.18.1/go.mod h1:ZQFFVG+MdnR0P+l6wpXgIL4NTtwiKIdBnrBd8Nrxr+0=
+github.com/klauspost/compress v1.18.2 h1:iiPHWW0YrcFgpBYhsA6D1+fqHssJscY/Tm/y2Uqnapk=
+github.com/klauspost/compress v1.18.2/go.mod h1:R0h/fSBs8DE4ENlcrlib3PsXS61voFxhIs2DeRhCvJ4=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
 github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
@@ -230,8 +230,8 @@ github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f h1:KUppIJq7/+
 github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
 github.com/nats-io/nats.go v1.47.0 h1:YQdADw6J/UfGUd2Oy6tn4Hq6YHxCaJrVKayxxFqYrgM=
 github.com/nats-io/nats.go v1.47.0/go.mod h1:iRWIPokVIFbVijxuMQq4y9ttaBTMe0SFdlZfMDd+33g=
-github.com/nats-io/nkeys v0.4.11 h1:q44qGV008kYd9W1b1nEBkNzvnWxtRSQ7A8BoqRrcfa0=
-github.com/nats-io/nkeys v0.4.11/go.mod h1:szDimtgmfOi9n25JpfIdGw12tZFYXqhGxjhVxsatHVE=
+github.com/nats-io/nkeys v0.4.12 h1:nssm7JKOG9/x4J8II47VWCL1Ds29avyiQDRn0ckMvDc=
+github.com/nats-io/nkeys v0.4.12/go.mod h1:MT59A1HYcjIcyQDJStTfaOY6vhy9XTUjOFo+SVsvpBg=
 github.com/nats-io/nuid v1.0.1 h1:5iA8DT8V7q8WK2EScv2padNa/rTESc1KdnPw4TC2paw=
 github.com/nats-io/nuid v1.0.1/go.mod h1:19wcPz3Ph3q0Jbyiqsd0kePYG7A95tJPxeL+1OSON2c=
 github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
@@ -298,8 +298,8 @@ go.yaml.in/yaml/v3 v3.0.4 h1:tfq32ie2Jv2UxXFdLJdh3jXuOzWiL1fo0bu/FbuKpbc=
 go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.45.0 h1:jMBrvKuj23MTlT0bQEOBcAE0mjg8mK9RXFhRH6nyF3Q=
-golang.org/x/crypto v0.45.0/go.mod h1:XTGrrkGJve7CYK7J8PEww4aY7gM3qMCElcJQ8n8JdX4=
+golang.org/x/crypto v0.46.0 h1:cKRW/pmt1pKAfetfu+RCEvjvZkA9RimPbh7bhFjGVBU=
+golang.org/x/crypto v0.46.0/go.mod h1:Evb/oLKmMraqjZ2iQTwDwvCtJkczlDuTmdJXoZVzqU0=
 golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b h1:M2rDM6z3Fhozi9O7NWsxAkg/yqS/lQJ6PmkyIV3YP+o=
 golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b/go.mod h1:3//PLf8L/X+8b4vuAfHzxeRUl04Adcb341+IGKfnqS8=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
@@ -315,16 +315,16 @@ golang.org/x/oauth2 v0.32.0 h1:jsCblLleRMDrxMN29H3z/k1KliIvpLgCkE6R8FXXNgY=
 golang.org/x/oauth2 v0.32.0/go.mod h1:lzm5WQJQwKZ3nwavOZ3IS5Aulzxi68dUSgRHujetwEA=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.18.0 h1:kr88TuHDroi+UVf+0hZnirlk8o8T+4MrK6mr60WkH/I=
-golang.org/x/sync v0.18.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
+golang.org/x/sync v0.19.0 h1:vV+1eWNmZ5geRlYjzm2adRgW2/mcpevXNg50YZtPCE4=
+golang.org/x/sync v0.19.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.38.0 h1:3yZWxaJjBmCWXqhN1qh02AkOnCQ1poK6oF+a7xWL6Gc=
-golang.org/x/sys v0.38.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
+golang.org/x/sys v0.39.0 h1:CvCKL8MeisomCi6qNZ+wbb0DN9E5AATixKsvNtMoMFk=
+golang.org/x/sys v0.39.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
@@ -332,8 +332,8 @@ golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
-golang.org/x/text v0.31.0 h1:aC8ghyu4JhP8VojJ2lEHBnochRno1sgL6nEi9WGFGMM=
-golang.org/x/text v0.31.0/go.mod h1:tKRAlv61yKIjGGHX/4tP1LTbc13YSec1pxVEWXzfoeM=
+golang.org/x/text v0.32.0 h1:ZD01bjUt1FQ9WJ0ClOL5vxgxOI/sVCNgX1YtKwcY0mU=
+golang.org/x/text v0.32.0/go.mod h1:o/rUWzghvpD5TXrTIBuJU77MTaN0ljMWE47kxGJQ7jY=
 golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
 golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
diff --git a/gqlgen.yml b/gqlgen.yml
index 5f5272b4..40410b48 100644
--- a/gqlgen.yml
+++ b/gqlgen.yml
@@ -52,51 +52,51 @@ models:
       - github.com/99designs/gqlgen/graphql.Int64
       - github.com/99designs/gqlgen/graphql.Int32
   Job:
-    model: "github.com/ClusterCockpit/cc-lib/schema.Job"
+    model: "github.com/ClusterCockpit/cc-lib/v2/schema.Job"
     fields:
       tags:
         resolver: true
       metaData:
         resolver: true
   Cluster:
-    model: "github.com/ClusterCockpit/cc-lib/schema.Cluster"
+    model: "github.com/ClusterCockpit/cc-lib/v2/schema.Cluster"
     fields:
       partitions:
         resolver: true
   # Node:
-  #   model: "github.com/ClusterCockpit/cc-lib/schema.Node"
+  #   model: "github.com/ClusterCockpit/cc-lib/v2/schema.Node"
   #   fields:
   #     metaData:
   #       resolver: true
-  NullableFloat: { model: "github.com/ClusterCockpit/cc-lib/schema.Float" }
-  MetricScope: { model: "github.com/ClusterCockpit/cc-lib/schema.MetricScope" }
-  MetricValue: { model: "github.com/ClusterCockpit/cc-lib/schema.MetricValue" }
+  NullableFloat: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.Float" }
+  MetricScope: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.MetricScope" }
+  MetricValue: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.MetricValue" }
   JobStatistics:
-    { model: "github.com/ClusterCockpit/cc-lib/schema.JobStatistics" }
+    { model: "github.com/ClusterCockpit/cc-lib/v2/schema.JobStatistics" }
   GlobalMetricListItem:
-    { model: "github.com/ClusterCockpit/cc-lib/schema.GlobalMetricListItem" }
+    { model: "github.com/ClusterCockpit/cc-lib/v2/schema.GlobalMetricListItem" }
   ClusterSupport:
-    { model: "github.com/ClusterCockpit/cc-lib/schema.ClusterSupport" }
-  Tag: { model: "github.com/ClusterCockpit/cc-lib/schema.Tag" }
-  Resource: { model: "github.com/ClusterCockpit/cc-lib/schema.Resource" }
-  JobState: { model: "github.com/ClusterCockpit/cc-lib/schema.JobState" }
-  Node: { model: "github.com/ClusterCockpit/cc-lib/schema.Node" }
+    { model: "github.com/ClusterCockpit/cc-lib/v2/schema.ClusterSupport" }
+  Tag: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.Tag" }
+  Resource: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.Resource" }
+  JobState: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.JobState" }
+  Node: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.Node" }
   SchedulerState:
-    { model: "github.com/ClusterCockpit/cc-lib/schema.SchedulerState" }
+    { model: "github.com/ClusterCockpit/cc-lib/v2/schema.SchedulerState" }
   HealthState:
-    { model: "github.com/ClusterCockpit/cc-lib/schema.MonitoringState" }
-  JobMetric: { model: "github.com/ClusterCockpit/cc-lib/schema.JobMetric" }
-  Series: { model: "github.com/ClusterCockpit/cc-lib/schema.Series" }
+    { model: "github.com/ClusterCockpit/cc-lib/v2/schema.MonitoringState" }
+  JobMetric: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.JobMetric" }
+  Series: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.Series" }
   MetricStatistics:
-    { model: "github.com/ClusterCockpit/cc-lib/schema.MetricStatistics" }
+    { model: "github.com/ClusterCockpit/cc-lib/v2/schema.MetricStatistics" }
   MetricConfig:
-    { model: "github.com/ClusterCockpit/cc-lib/schema.MetricConfig" }
+    { model: "github.com/ClusterCockpit/cc-lib/v2/schema.MetricConfig" }
   SubClusterConfig:
-    { model: "github.com/ClusterCockpit/cc-lib/schema.SubClusterConfig" }
-  Accelerator: { model: "github.com/ClusterCockpit/cc-lib/schema.Accelerator" }
-  Topology: { model: "github.com/ClusterCockpit/cc-lib/schema.Topology" }
+    { model: "github.com/ClusterCockpit/cc-lib/v2/schema.SubClusterConfig" }
+  Accelerator: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.Accelerator" }
+  Topology: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.Topology" }
   FilterRanges:
-    { model: "github.com/ClusterCockpit/cc-lib/schema.FilterRanges" }
-  SubCluster: { model: "github.com/ClusterCockpit/cc-lib/schema.SubCluster" }
-  StatsSeries: { model: "github.com/ClusterCockpit/cc-lib/schema.StatsSeries" }
-  Unit: { model: "github.com/ClusterCockpit/cc-lib/schema.Unit" }
+    { model: "github.com/ClusterCockpit/cc-lib/v2/schema.FilterRanges" }
+  SubCluster: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.SubCluster" }
+  StatsSeries: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.StatsSeries" }
+  Unit: { model: "github.com/ClusterCockpit/cc-lib/v2/schema.Unit" }
diff --git a/internal/api/api_test.go b/internal/api/api_test.go
index 3030b1c1..50605f7b 100644
--- a/internal/api/api_test.go
+++ b/internal/api/api_test.go
@@ -27,9 +27,9 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/gorilla/mux"
 
 	_ "github.com/mattn/go-sqlite3"
diff --git a/internal/api/cluster.go b/internal/api/cluster.go
index 28d7c109..b6f41244 100644
--- a/internal/api/cluster.go
+++ b/internal/api/cluster.go
@@ -13,7 +13,7 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 // GetClustersAPIResponse model
diff --git a/internal/api/job.go b/internal/api/job.go
index 919772f4..9b970c2e 100644
--- a/internal/api/job.go
+++ b/internal/api/job.go
@@ -25,8 +25,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/gorilla/mux"
 )
 
diff --git a/internal/api/memorystore.go b/internal/api/memorystore.go
index 1b883792..56c396e2 100644
--- a/internal/api/memorystore.go
+++ b/internal/api/memorystore.go
@@ -16,7 +16,7 @@ import (
 	"strings"
 
 	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 
 	"github.com/influxdata/line-protocol/v2/lineprotocol"
 )
diff --git a/internal/api/nats.go b/internal/api/nats.go
index a309a915..efd04406 100644
--- a/internal/api/nats.go
+++ b/internal/api/nats.go
@@ -18,9 +18,10 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/importer"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/nats"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/v2/ccMessage"
+	"github.com/ClusterCockpit/cc-lib/v2/receivers"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
 )
 
@@ -75,10 +76,18 @@ func (api *NatsAPI) processJobEvent(msg lp.CCMessage) {
 
 	switch function {
 	case "start_job":
-		api.handleStartJob(msg.GetEventValue())
+		v, ok := msg.GetEventValue()
+		if !ok {
+			cclog.Errorf("Job event is missing event value: %+v", msg)
+		}
+		api.handleStartJob(v)
 
 	case "stop_job":
-		api.handleStopJob(msg.GetEventValue())
+		v, ok := msg.GetEventValue()
+		if !ok {
+			cclog.Errorf("Job event is missing event value: %+v", msg)
+		}
+		api.handleStopJob(v)
 	default:
 		cclog.Warnf("Unimplemented job event: %+v", msg)
 	}
@@ -88,7 +97,7 @@ func (api *NatsAPI) handleJobEvent(subject string, data []byte) {
 	d := influx.NewDecoderWithBytes(data)
 
 	for d.Next() {
-		m, err := nats.DecodeInfluxMessage(d)
+		m, err := receivers.DecodeInfluxMessage(d)
 		if err != nil {
 			cclog.Errorf("NATS %s:  Failed to decode message: %v", subject, err)
 			return
diff --git a/internal/api/nats_test.go b/internal/api/nats_test.go
index 420a359c..c9415afc 100644
--- a/internal/api/nats_test.go
+++ b/internal/api/nats_test.go
@@ -21,10 +21,10 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/v2/ccMessage"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 
 	_ "github.com/mattn/go-sqlite3"
 )
diff --git a/internal/api/node.go b/internal/api/node.go
index 8953e5b9..350f097d 100644
--- a/internal/api/node.go
+++ b/internal/api/node.go
@@ -12,7 +12,7 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 type UpdateNodeStatesRequest struct {
diff --git a/internal/api/rest.go b/internal/api/rest.go
index ebcf31ed..195de826 100644
--- a/internal/api/rest.go
+++ b/internal/api/rest.go
@@ -22,9 +22,9 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/auth"
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 	"github.com/gorilla/mux"
 )
 
diff --git a/internal/api/user.go b/internal/api/user.go
index f9ddee33..1821b69b 100644
--- a/internal/api/user.go
+++ b/internal/api/user.go
@@ -11,8 +11,8 @@ import (
 	"net/http"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/gorilla/mux"
 )
 
diff --git a/internal/archiver/archiveWorker.go b/internal/archiver/archiveWorker.go
index 0434844d..ecdd1756 100644
--- a/internal/archiver/archiveWorker.go
+++ b/internal/archiver/archiveWorker.go
@@ -54,8 +54,8 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 )
 
diff --git a/internal/archiver/archiver.go b/internal/archiver/archiver.go
index b88199aa..46ce8126 100644
--- a/internal/archiver/archiver.go
+++ b/internal/archiver/archiver.go
@@ -12,8 +12,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 // ArchiveJob archives a completed job's metric data to the configured archive backend.
diff --git a/internal/auth/auth.go b/internal/auth/auth.go
index 5d947353..3be1768e 100644
--- a/internal/auth/auth.go
+++ b/internal/auth/auth.go
@@ -25,9 +25,9 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 	"github.com/gorilla/sessions"
 )
 
diff --git a/internal/auth/jwt.go b/internal/auth/jwt.go
index 4f1f3f54..be642219 100644
--- a/internal/auth/jwt.go
+++ b/internal/auth/jwt.go
@@ -14,8 +14,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/golang-jwt/jwt/v5"
 )
 
diff --git a/internal/auth/jwtCookieSession.go b/internal/auth/jwtCookieSession.go
index 44c64a0c..42f7439e 100644
--- a/internal/auth/jwtCookieSession.go
+++ b/internal/auth/jwtCookieSession.go
@@ -12,8 +12,8 @@ import (
 	"net/http"
 	"os"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/golang-jwt/jwt/v5"
 )
 
diff --git a/internal/auth/jwtHelpers.go b/internal/auth/jwtHelpers.go
index 792722a8..5bfc91ef 100644
--- a/internal/auth/jwtHelpers.go
+++ b/internal/auth/jwtHelpers.go
@@ -11,8 +11,8 @@ import (
 	"fmt"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/golang-jwt/jwt/v5"
 )
 
diff --git a/internal/auth/jwtHelpers_test.go b/internal/auth/jwtHelpers_test.go
index 5cee1df5..84a1f2e0 100644
--- a/internal/auth/jwtHelpers_test.go
+++ b/internal/auth/jwtHelpers_test.go
@@ -8,7 +8,7 @@ package auth
 import (
 	"testing"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/golang-jwt/jwt/v5"
 )
 
diff --git a/internal/auth/jwtSession.go b/internal/auth/jwtSession.go
index 15e58347..107afcb8 100644
--- a/internal/auth/jwtSession.go
+++ b/internal/auth/jwtSession.go
@@ -13,8 +13,8 @@ import (
 	"os"
 	"strings"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/golang-jwt/jwt/v5"
 )
 
diff --git a/internal/auth/ldap.go b/internal/auth/ldap.go
index e96e732b..4cbb80c5 100644
--- a/internal/auth/ldap.go
+++ b/internal/auth/ldap.go
@@ -13,8 +13,8 @@ import (
 	"strings"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/go-ldap/ldap/v3"
 )
 
diff --git a/internal/auth/local.go b/internal/auth/local.go
index 1c9b0372..b1a7362c 100644
--- a/internal/auth/local.go
+++ b/internal/auth/local.go
@@ -9,8 +9,8 @@ import (
 	"fmt"
 	"net/http"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"golang.org/x/crypto/bcrypt"
 )
 
diff --git a/internal/auth/oidc.go b/internal/auth/oidc.go
index 9e361302..a3fc09cc 100644
--- a/internal/auth/oidc.go
+++ b/internal/auth/oidc.go
@@ -15,8 +15,8 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/coreos/go-oidc/v3/oidc"
 	"github.com/gorilla/mux"
 	"golang.org/x/oauth2"
diff --git a/internal/config/config.go b/internal/config/config.go
index 3c88bcfd..af8ec944 100644
--- a/internal/config/config.go
+++ b/internal/config/config.go
@@ -11,8 +11,8 @@ import (
 	"encoding/json"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/resampler"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/resampler"
 )
 
 type ProgramConfig struct {
diff --git a/internal/config/config_test.go b/internal/config/config_test.go
index 35e1c65e..396a80a1 100644
--- a/internal/config/config_test.go
+++ b/internal/config/config_test.go
@@ -8,8 +8,8 @@ package config
 import (
 	"testing"
 
-	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 func TestInit(t *testing.T) {
diff --git a/internal/config/validate.go b/internal/config/validate.go
index 6ac67f5e..af8591ca 100644
--- a/internal/config/validate.go
+++ b/internal/config/validate.go
@@ -8,7 +8,7 @@ package config
 import (
 	"encoding/json"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/santhosh-tekuri/jsonschema/v5"
 )
 
diff --git a/internal/graph/generated/generated.go b/internal/graph/generated/generated.go
index 1cb348e5..d96ccf1d 100644
--- a/internal/graph/generated/generated.go
+++ b/internal/graph/generated/generated.go
@@ -16,7 +16,7 @@ import (
 	"github.com/99designs/gqlgen/graphql/introspection"
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	gqlparser "github.com/vektah/gqlparser/v2"
 	"github.com/vektah/gqlparser/v2/ast"
 )
diff --git a/internal/graph/model/models_gen.go b/internal/graph/model/models_gen.go
index 63b2da5d..31ba03ab 100644
--- a/internal/graph/model/models_gen.go
+++ b/internal/graph/model/models_gen.go
@@ -10,7 +10,7 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 type ClusterMetricWithName struct {
diff --git a/internal/graph/resolver.go b/internal/graph/resolver.go
index 990014c7..d1b04de6 100644
--- a/internal/graph/resolver.go
+++ b/internal/graph/resolver.go
@@ -4,7 +4,7 @@ import (
 	"sync"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/jmoiron/sqlx"
 )
 
diff --git a/internal/graph/schema.resolvers.go b/internal/graph/schema.resolvers.go
index cd4af057..32499b8c 100644
--- a/internal/graph/schema.resolvers.go
+++ b/internal/graph/schema.resolvers.go
@@ -22,8 +22,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 // Partitions is the resolver for the partitions field.
diff --git a/internal/graph/util.go b/internal/graph/util.go
index 220c3a84..42a1d2fb 100644
--- a/internal/graph/util.go
+++ b/internal/graph/util.go
@@ -14,8 +14,8 @@ import (
 	"github.com/99designs/gqlgen/graphql"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
 	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 const MAX_JOBS_FOR_ANALYSIS = 500
diff --git a/internal/importer/handleImport.go b/internal/importer/handleImport.go
index 482b328c..4b217475 100644
--- a/internal/importer/handleImport.go
+++ b/internal/importer/handleImport.go
@@ -14,8 +14,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 // HandleImportFlag imports jobs from file pairs specified in a comma-separated flag string.
diff --git a/internal/importer/importer_test.go b/internal/importer/importer_test.go
index 470f7603..bffb8bf6 100644
--- a/internal/importer/importer_test.go
+++ b/internal/importer/importer_test.go
@@ -16,8 +16,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/importer"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 // copyFile copies a file from source path to destination path.
diff --git a/internal/importer/initDB.go b/internal/importer/initDB.go
index 12f49010..d88be7c7 100644
--- a/internal/importer/initDB.go
+++ b/internal/importer/initDB.go
@@ -22,8 +22,8 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 const (
diff --git a/internal/importer/normalize.go b/internal/importer/normalize.go
index 943ceb26..c6e84d4b 100644
--- a/internal/importer/normalize.go
+++ b/internal/importer/normalize.go
@@ -7,7 +7,7 @@ package importer
 import (
 	"math"
 
-	ccunits "github.com/ClusterCockpit/cc-lib/ccUnits"
+	ccunits "github.com/ClusterCockpit/cc-lib/v2/ccUnits"
 )
 
 // getNormalizationFactor calculates the scaling factor needed to normalize a value
diff --git a/internal/importer/normalize_test.go b/internal/importer/normalize_test.go
index 6aa1ed2e..039a3cfc 100644
--- a/internal/importer/normalize_test.go
+++ b/internal/importer/normalize_test.go
@@ -8,7 +8,7 @@ import (
 	"fmt"
 	"testing"
 
-	ccunits "github.com/ClusterCockpit/cc-lib/ccUnits"
+	ccunits "github.com/ClusterCockpit/cc-lib/v2/ccUnits"
 )
 
 // TestNormalizeFactor tests the normalization of large byte values to gigabyte prefix.
diff --git a/internal/memorystore/api.go b/internal/memorystore/api.go
index b96dc1fd..41c53a18 100644
--- a/internal/memorystore/api.go
+++ b/internal/memorystore/api.go
@@ -9,8 +9,8 @@ import (
 	"errors"
 	"math"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
 var (
diff --git a/internal/memorystore/archive.go b/internal/memorystore/archive.go
index 5019ee7a..fc46dac6 100644
--- a/internal/memorystore/archive.go
+++ b/internal/memorystore/archive.go
@@ -18,7 +18,7 @@ import (
 	"sync/atomic"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 func Archiving(wg *sync.WaitGroup, ctx context.Context) {
diff --git a/internal/memorystore/avroCheckpoint.go b/internal/memorystore/avroCheckpoint.go
index 42e5f623..b0b0cf42 100644
--- a/internal/memorystore/avroCheckpoint.go
+++ b/internal/memorystore/avroCheckpoint.go
@@ -19,8 +19,8 @@ import (
 	"sync/atomic"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/linkedin/goavro/v2"
 )
 
diff --git a/internal/memorystore/avroHelper.go b/internal/memorystore/avroHelper.go
index a6f6c9bf..93a293bd 100644
--- a/internal/memorystore/avroHelper.go
+++ b/internal/memorystore/avroHelper.go
@@ -11,7 +11,7 @@ import (
 	"strconv"
 	"sync"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 func DataStaging(wg *sync.WaitGroup, ctx context.Context) {
diff --git a/internal/memorystore/avroStruct.go b/internal/memorystore/avroStruct.go
index bde9e02b..2643a9a7 100644
--- a/internal/memorystore/avroStruct.go
+++ b/internal/memorystore/avroStruct.go
@@ -8,7 +8,7 @@ package memorystore
 import (
 	"sync"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 var (
diff --git a/internal/memorystore/buffer.go b/internal/memorystore/buffer.go
index 55be2ada..15e29b3a 100644
--- a/internal/memorystore/buffer.go
+++ b/internal/memorystore/buffer.go
@@ -9,7 +9,7 @@ import (
 	"errors"
 	"sync"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 // BufferCap is the default buffer capacity.
diff --git a/internal/memorystore/checkpoint.go b/internal/memorystore/checkpoint.go
index c676977c..c48c2fd8 100644
--- a/internal/memorystore/checkpoint.go
+++ b/internal/memorystore/checkpoint.go
@@ -23,8 +23,8 @@ import (
 	"sync/atomic"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/linkedin/goavro/v2"
 )
 
diff --git a/internal/memorystore/level.go b/internal/memorystore/level.go
index f3b3d3f5..bce2a7a6 100644
--- a/internal/memorystore/level.go
+++ b/internal/memorystore/level.go
@@ -9,7 +9,7 @@ import (
 	"sync"
 	"unsafe"
 
-	"github.com/ClusterCockpit/cc-lib/util"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
 // Could also be called "node" as this forms a node in a tree structure.
diff --git a/internal/memorystore/lineprotocol.go b/internal/memorystore/lineprotocol.go
index 6404361f..ca8cc811 100644
--- a/internal/memorystore/lineprotocol.go
+++ b/internal/memorystore/lineprotocol.go
@@ -12,8 +12,8 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/pkg/nats"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/influxdata/line-protocol/v2/lineprotocol"
 )
 
diff --git a/internal/memorystore/memorystore.go b/internal/memorystore/memorystore.go
index 259a86ed..7c5ea0eb 100644
--- a/internal/memorystore/memorystore.go
+++ b/internal/memorystore/memorystore.go
@@ -30,10 +30,10 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/resampler"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/resampler"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
 var (
diff --git a/internal/memorystore/memorystore_test.go b/internal/memorystore/memorystore_test.go
index b8ab090a..57ea6938 100644
--- a/internal/memorystore/memorystore_test.go
+++ b/internal/memorystore/memorystore_test.go
@@ -8,7 +8,7 @@ package memorystore
 import (
 	"testing"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 func TestAssignAggregationStrategy(t *testing.T) {
diff --git a/internal/memorystore/stats.go b/internal/memorystore/stats.go
index b2cb539a..c931ab35 100644
--- a/internal/memorystore/stats.go
+++ b/internal/memorystore/stats.go
@@ -9,7 +9,7 @@ import (
 	"errors"
 	"math"
 
-	"github.com/ClusterCockpit/cc-lib/util"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
 type Stats struct {
diff --git a/internal/metricDataDispatcher/dataLoader.go b/internal/metricDataDispatcher/dataLoader.go
index 780eb73e..6d1338fa 100644
--- a/internal/metricDataDispatcher/dataLoader.go
+++ b/internal/metricDataDispatcher/dataLoader.go
@@ -13,10 +13,10 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/lrucache"
-	"github.com/ClusterCockpit/cc-lib/resampler"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/lrucache"
+	"github.com/ClusterCockpit/cc-lib/v2/resampler"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 var cache *lrucache.Cache = lrucache.New(128 * 1024 * 1024)
diff --git a/internal/metricdata/cc-metric-store-internal.go b/internal/metricdata/cc-metric-store-internal.go
index 9f0cd74a..741ce358 100644
--- a/internal/metricdata/cc-metric-store-internal.go
+++ b/internal/metricdata/cc-metric-store-internal.go
@@ -15,8 +15,8 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 // Bloat Code
diff --git a/internal/metricdata/cc-metric-store.go b/internal/metricdata/cc-metric-store.go
index be2e956e..6c146f22 100644
--- a/internal/metricdata/cc-metric-store.go
+++ b/internal/metricdata/cc-metric-store.go
@@ -15,8 +15,8 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 type CCMetricStoreConfig struct {
diff --git a/internal/metricdata/metricdata.go b/internal/metricdata/metricdata.go
index 0748a8d5..ab0e19fb 100644
--- a/internal/metricdata/metricdata.go
+++ b/internal/metricdata/metricdata.go
@@ -13,8 +13,8 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 type MetricDataRepository interface {
diff --git a/internal/metricdata/prometheus.go b/internal/metricdata/prometheus.go
index 66c5bc1e..3fb94d51 100644
--- a/internal/metricdata/prometheus.go
+++ b/internal/metricdata/prometheus.go
@@ -21,8 +21,8 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	promapi "github.com/prometheus/client_golang/api"
 	promv1 "github.com/prometheus/client_golang/api/prometheus/v1"
 	promcfg "github.com/prometheus/common/config"
diff --git a/internal/metricdata/utils.go b/internal/metricdata/utils.go
index 0b2bb7ec..21dfbcac 100644
--- a/internal/metricdata/utils.go
+++ b/internal/metricdata/utils.go
@@ -10,7 +10,7 @@ import (
 	"encoding/json"
 	"time"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 var TestLoadDataCallback func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) = func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) {
diff --git a/internal/repository/dbConnection.go b/internal/repository/dbConnection.go
index be0b161b..3141cf86 100644
--- a/internal/repository/dbConnection.go
+++ b/internal/repository/dbConnection.go
@@ -12,7 +12,7 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/jmoiron/sqlx"
 	"github.com/mattn/go-sqlite3"
 	"github.com/qustavo/sqlhooks/v2"
diff --git a/internal/repository/hooks.go b/internal/repository/hooks.go
index 54330723..c916b57e 100644
--- a/internal/repository/hooks.go
+++ b/internal/repository/hooks.go
@@ -8,7 +8,7 @@ import (
 	"context"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 // Hooks satisfies the sqlhook.Hooks interface
diff --git a/internal/repository/job.go b/internal/repository/job.go
index 47959379..99970ce1 100644
--- a/internal/repository/job.go
+++ b/internal/repository/job.go
@@ -71,9 +71,9 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/lrucache"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/lrucache"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 	"github.com/jmoiron/sqlx"
 )
diff --git a/internal/repository/jobCreate.go b/internal/repository/jobCreate.go
index efd262b8..6114ae5e 100644
--- a/internal/repository/jobCreate.go
+++ b/internal/repository/jobCreate.go
@@ -9,8 +9,8 @@ import (
 	"encoding/json"
 	"fmt"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 )
 
diff --git a/internal/repository/jobFind.go b/internal/repository/jobFind.go
index c4051e7f..ff2c27aa 100644
--- a/internal/repository/jobFind.go
+++ b/internal/repository/jobFind.go
@@ -12,8 +12,8 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 )
 
diff --git a/internal/repository/jobHooks.go b/internal/repository/jobHooks.go
index 824b5cde..c449d308 100644
--- a/internal/repository/jobHooks.go
+++ b/internal/repository/jobHooks.go
@@ -7,7 +7,7 @@ package repository
 import (
 	"sync"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 type JobHook interface {
diff --git a/internal/repository/jobQuery.go b/internal/repository/jobQuery.go
index 00dabea3..8c341afb 100644
--- a/internal/repository/jobQuery.go
+++ b/internal/repository/jobQuery.go
@@ -14,8 +14,8 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 )
 
diff --git a/internal/repository/job_test.go b/internal/repository/job_test.go
index c89225b3..17766c69 100644
--- a/internal/repository/job_test.go
+++ b/internal/repository/job_test.go
@@ -10,7 +10,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	_ "github.com/mattn/go-sqlite3"
 )
 
diff --git a/internal/repository/migration.go b/internal/repository/migration.go
index 43e913cc..a47f9fcd 100644
--- a/internal/repository/migration.go
+++ b/internal/repository/migration.go
@@ -10,7 +10,7 @@ import (
 	"embed"
 	"fmt"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/golang-migrate/migrate/v4"
 	"github.com/golang-migrate/migrate/v4/database/sqlite3"
 	"github.com/golang-migrate/migrate/v4/source/iofs"
diff --git a/internal/repository/node.go b/internal/repository/node.go
index 3b597eda..752a36fa 100644
--- a/internal/repository/node.go
+++ b/internal/repository/node.go
@@ -17,9 +17,9 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/lrucache"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/lrucache"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 	"github.com/jmoiron/sqlx"
 )
diff --git a/internal/repository/node_test.go b/internal/repository/node_test.go
index 466f51ee..e1d6ca93 100644
--- a/internal/repository/node_test.go
+++ b/internal/repository/node_test.go
@@ -15,9 +15,9 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	_ "github.com/mattn/go-sqlite3"
 )
 
diff --git a/internal/repository/repository_test.go b/internal/repository/repository_test.go
index e3dec7fc..9d07b026 100644
--- a/internal/repository/repository_test.go
+++ b/internal/repository/repository_test.go
@@ -9,8 +9,8 @@ import (
 	"testing"
 
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	_ "github.com/mattn/go-sqlite3"
 )
 
diff --git a/internal/repository/stats.go b/internal/repository/stats.go
index c92f5193..d1e16eb8 100644
--- a/internal/repository/stats.go
+++ b/internal/repository/stats.go
@@ -14,8 +14,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
 	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 )
 
diff --git a/internal/repository/tags.go b/internal/repository/tags.go
index 8a076e8a..9bc9abae 100644
--- a/internal/repository/tags.go
+++ b/internal/repository/tags.go
@@ -11,8 +11,8 @@ import (
 	"strings"
 
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 )
 
diff --git a/internal/repository/testdata/job.db b/internal/repository/testdata/job.db
index 5c5a692585a4736a9e0456d1caf7b4878c936f74..729cac965265a81bf187475d23d21de268a42ccd 100644
GIT binary patch
delta 914
zcma)4O=}ZT6n$^r?U+fEUfYnG7-A{`$-=;V<YNpiNV^eSn13KKrmZlTV5UM>DY$Se
z#O{lKKrvu9Lfwix7t*>hG!#i8Vy#+Rvhcp7q_I_Sao(HZoO3@8Z)I(IWo`Ne=qkq+
z!&YNl-@;^st1J=^u*GuKHO!P-s=7sIsp^&<REvh6F$S1mxQS2E!30@CSepfvMdz%r
z)Vj-+QtvJ-+%~eAOgfXY?5vTo4a?AV-PFx=(lC=|YD%|r#<g53yWo`X6r3wUWr3g-
zE>tQH3)RX%XGxuv%9-iDZdN(d%W&P}W~r=gXVQjc+vXq5P8X?f-n!}otTX(EukkI`
zX^%%(OF(pv|Hl&GgFuiUPb&WDIyH^rhd@{(S7q5<EZ^@(xyo<{-{EsyWvmgPA@U&r
zjax7X;3TMv0u*lX88P5a_6jM|rTm4d@04S->$co=8{2qDyS~Q@D(N|Zhe~oPDSH2k
z(m1S*PSJa4Gi;Oa6JDN#NL)Mn807dIn+%&I`+!rIxR+5$#S;r^_ijFm-{8%H<CKd9
zw{&-Y$#Gu3f$LOvkKrB}K4W-H#I>Qv<?Yq$FzgWB!srCV1H(K$zP@Ci;XX;)==X`3
zHt6w6=WxCOPktfv+U39Fq&CF&%?At*$lSrO2ehCjm68Ct?+*&+3my@@h2tPJ4yvGV
zW`z7!){ko3t5cA>47>Ofzv3<_KjOrQkU7dz2ze^X<L(A0$XgJAFhWoX=LjBxM(`3w
N2|j{<y}L06`QHG3{OAAx

delta 212
zcmXZVEe^s!5Cz~}nB}JhW*ZU`RMDs&0KpC53OE#0U{J+jNl4ID)HXC>WjO@`bTufF
zk`+7x;!9?pcyAMrHt{H>AfZ%gLpycl{cSQdG?h>8b^Fa(7>4WBe7R@~AtV=q3*%{d
z=Y6sCYm!UBrSW3*;H-??!M`U~mQNQN8^YzEQ$;$VKw{zhAF*{nmXUt3c}LO-&}0SM
fUsDxRTboO$KotlS)SwOxXo3SSw4iNl-l6FS=Yv%5

diff --git a/internal/repository/user.go b/internal/repository/user.go
index 5cab2b0d..770915b6 100644
--- a/internal/repository/user.go
+++ b/internal/repository/user.go
@@ -15,8 +15,8 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 	"github.com/jmoiron/sqlx"
 	"golang.org/x/crypto/bcrypt"
diff --git a/internal/repository/userConfig.go b/internal/repository/userConfig.go
index beeffbf5..75e7119f 100644
--- a/internal/repository/userConfig.go
+++ b/internal/repository/userConfig.go
@@ -12,9 +12,9 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/web"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/lrucache"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/lrucache"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/jmoiron/sqlx"
 )
 
diff --git a/internal/repository/userConfig_test.go b/internal/repository/userConfig_test.go
index b6f68430..02c70d0f 100644
--- a/internal/repository/userConfig_test.go
+++ b/internal/repository/userConfig_test.go
@@ -10,9 +10,9 @@ import (
 	"testing"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
-	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	_ "github.com/mattn/go-sqlite3"
 )
 
diff --git a/internal/routerConfig/routes.go b/internal/routerConfig/routes.go
index 4466034d..436031ef 100644
--- a/internal/routerConfig/routes.go
+++ b/internal/routerConfig/routes.go
@@ -17,9 +17,9 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/web"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 	"github.com/gorilla/mux"
 )
 
diff --git a/internal/tagger/classifyJob.go b/internal/tagger/classifyJob.go
index 4e46f370..70399218 100644
--- a/internal/tagger/classifyJob.go
+++ b/internal/tagger/classifyJob.go
@@ -16,9 +16,9 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 	"github.com/expr-lang/expr"
 	"github.com/expr-lang/expr/vm"
 )
diff --git a/internal/tagger/classifyJob_test.go b/internal/tagger/classifyJob_test.go
index 3795a60a..bed7a8f0 100644
--- a/internal/tagger/classifyJob_test.go
+++ b/internal/tagger/classifyJob_test.go
@@ -3,7 +3,7 @@ package tagger
 import (
 	"testing"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/mock"
 )
diff --git a/internal/tagger/detectApp.go b/internal/tagger/detectApp.go
index 4e8f858d..0b8e3e7e 100644
--- a/internal/tagger/detectApp.go
+++ b/internal/tagger/detectApp.go
@@ -16,9 +16,9 @@ import (
 	"strings"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
 //go:embed apps/*
diff --git a/internal/tagger/detectApp_test.go b/internal/tagger/detectApp_test.go
index 7145d04f..1c44f670 100644
--- a/internal/tagger/detectApp_test.go
+++ b/internal/tagger/detectApp_test.go
@@ -8,7 +8,7 @@ import (
 	"testing"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 func setup(tb testing.TB) *repository.JobRepository {
diff --git a/internal/tagger/tagger.go b/internal/tagger/tagger.go
index 2ba18a14..0839603d 100644
--- a/internal/tagger/tagger.go
+++ b/internal/tagger/tagger.go
@@ -13,8 +13,8 @@ import (
 	"sync"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 // Tagger is the interface that must be implemented by all tagging components.
diff --git a/internal/tagger/tagger_test.go b/internal/tagger/tagger_test.go
index fb4bc54e..d24ad7f7 100644
--- a/internal/tagger/tagger_test.go
+++ b/internal/tagger/tagger_test.go
@@ -8,7 +8,7 @@ import (
 	"testing"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 func TestInit(t *testing.T) {
diff --git a/internal/taskmanager/commitJobService.go b/internal/taskmanager/commitJobService.go
index 4f21c86b..4a070284 100644
--- a/internal/taskmanager/commitJobService.go
+++ b/internal/taskmanager/commitJobService.go
@@ -9,7 +9,7 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/go-co-op/gocron/v2"
 )
 
diff --git a/internal/taskmanager/compressionService.go b/internal/taskmanager/compressionService.go
index 1da2f68d..ab01ce8f 100644
--- a/internal/taskmanager/compressionService.go
+++ b/internal/taskmanager/compressionService.go
@@ -9,8 +9,8 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/go-co-op/gocron/v2"
 )
 
diff --git a/internal/taskmanager/ldapSyncService.go b/internal/taskmanager/ldapSyncService.go
index e410af9e..9e99a261 100644
--- a/internal/taskmanager/ldapSyncService.go
+++ b/internal/taskmanager/ldapSyncService.go
@@ -9,7 +9,7 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/auth"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/go-co-op/gocron/v2"
 )
 
diff --git a/internal/taskmanager/retentionService.go b/internal/taskmanager/retentionService.go
index acd07307..5678cd14 100644
--- a/internal/taskmanager/retentionService.go
+++ b/internal/taskmanager/retentionService.go
@@ -9,7 +9,7 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/go-co-op/gocron/v2"
 )
 
diff --git a/internal/taskmanager/stopJobsExceedTime.go b/internal/taskmanager/stopJobsExceedTime.go
index b763f561..ce9cfd77 100644
--- a/internal/taskmanager/stopJobsExceedTime.go
+++ b/internal/taskmanager/stopJobsExceedTime.go
@@ -9,7 +9,7 @@ import (
 	"runtime"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/go-co-op/gocron/v2"
 )
 
diff --git a/internal/taskmanager/taskManager.go b/internal/taskmanager/taskManager.go
index 57f2d883..06e4f28f 100644
--- a/internal/taskmanager/taskManager.go
+++ b/internal/taskmanager/taskManager.go
@@ -13,7 +13,7 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/auth"
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/go-co-op/gocron/v2"
 )
 
diff --git a/internal/taskmanager/updateDurationService.go b/internal/taskmanager/updateDurationService.go
index 9c52da79..f1dde74a 100644
--- a/internal/taskmanager/updateDurationService.go
+++ b/internal/taskmanager/updateDurationService.go
@@ -8,7 +8,7 @@ package taskmanager
 import (
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/go-co-op/gocron/v2"
 )
 
diff --git a/internal/taskmanager/updateFootprintService.go b/internal/taskmanager/updateFootprintService.go
index ae9512cd..979a6137 100644
--- a/internal/taskmanager/updateFootprintService.go
+++ b/internal/taskmanager/updateFootprintService.go
@@ -12,8 +12,8 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 	"github.com/go-co-op/gocron/v2"
 )
diff --git a/pkg/archive/archive.go b/pkg/archive/archive.go
index 71933f2b..f9ce4314 100644
--- a/pkg/archive/archive.go
+++ b/pkg/archive/archive.go
@@ -85,9 +85,9 @@ import (
 	"sync"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/lrucache"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/lrucache"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 // Version is the current archive schema version.
diff --git a/pkg/archive/archive_test.go b/pkg/archive/archive_test.go
index 34ea831a..595315c3 100644
--- a/pkg/archive/archive_test.go
+++ b/pkg/archive/archive_test.go
@@ -11,8 +11,8 @@ import (
 	"testing"
 
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
 var jobs []*schema.Job
diff --git a/pkg/archive/clusterConfig.go b/pkg/archive/clusterConfig.go
index 696601b7..6e4866eb 100644
--- a/pkg/archive/clusterConfig.go
+++ b/pkg/archive/clusterConfig.go
@@ -8,8 +8,8 @@ package archive
 import (
 	"fmt"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 var (
diff --git a/pkg/archive/fsBackend.go b/pkg/archive/fsBackend.go
index b8d2a94b..020f2aa4 100644
--- a/pkg/archive/fsBackend.go
+++ b/pkg/archive/fsBackend.go
@@ -23,9 +23,9 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 	"github.com/santhosh-tekuri/jsonschema/v5"
 )
 
diff --git a/pkg/archive/fsBackend_test.go b/pkg/archive/fsBackend_test.go
index a43a6c3a..05491f61 100644
--- a/pkg/archive/fsBackend_test.go
+++ b/pkg/archive/fsBackend_test.go
@@ -10,8 +10,8 @@ import (
 	"path/filepath"
 	"testing"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
 func TestInitEmptyPath(t *testing.T) {
diff --git a/pkg/archive/json.go b/pkg/archive/json.go
index 75c39531..cf1b0a38 100644
--- a/pkg/archive/json.go
+++ b/pkg/archive/json.go
@@ -10,8 +10,8 @@ import (
 	"io"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 func DecodeJobData(r io.Reader, k string) (schema.JobData, error) {
diff --git a/pkg/archive/nodelist.go b/pkg/archive/nodelist.go
index ffb5f563..7a3784c3 100644
--- a/pkg/archive/nodelist.go
+++ b/pkg/archive/nodelist.go
@@ -10,7 +10,7 @@ import (
 	"strconv"
 	"strings"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 type NodeList [][]interface {
diff --git a/pkg/archive/s3Backend.go b/pkg/archive/s3Backend.go
index c874a320..a9933a9f 100644
--- a/pkg/archive/s3Backend.go
+++ b/pkg/archive/s3Backend.go
@@ -22,9 +22,9 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 	"github.com/aws/aws-sdk-go-v2/aws"
 	awsconfig "github.com/aws/aws-sdk-go-v2/config"
 	"github.com/aws/aws-sdk-go-v2/credentials"
diff --git a/pkg/archive/s3Backend_test.go b/pkg/archive/s3Backend_test.go
index 06324cd3..2b79db7f 100644
--- a/pkg/archive/s3Backend_test.go
+++ b/pkg/archive/s3Backend_test.go
@@ -13,7 +13,7 @@ import (
 	"strings"
 	"testing"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	"github.com/aws/aws-sdk-go-v2/aws"
 	"github.com/aws/aws-sdk-go-v2/service/s3"
 	"github.com/aws/aws-sdk-go-v2/service/s3/types"
diff --git a/pkg/archive/sqliteBackend.go b/pkg/archive/sqliteBackend.go
index 0b7a22d2..5bce9cea 100644
--- a/pkg/archive/sqliteBackend.go
+++ b/pkg/archive/sqliteBackend.go
@@ -21,9 +21,9 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 	_ "github.com/mattn/go-sqlite3"
 )
 
diff --git a/pkg/archive/sqliteBackend_test.go b/pkg/archive/sqliteBackend_test.go
index b72b8f6c..5d05e14e 100644
--- a/pkg/archive/sqliteBackend_test.go
+++ b/pkg/archive/sqliteBackend_test.go
@@ -9,7 +9,7 @@ import (
 	"os"
 	"testing"
 
-	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
 func TestSqliteInitEmptyPath(t *testing.T) {
diff --git a/pkg/nats/client.go b/pkg/nats/client.go
index 822a7b26..a32ebdca 100644
--- a/pkg/nats/client.go
+++ b/pkg/nats/client.go
@@ -54,7 +54,7 @@ import (
 	"fmt"
 	"sync"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/nats-io/nats.go"
 )
 
diff --git a/pkg/nats/config.go b/pkg/nats/config.go
index 32a0bbda..c9ab48a5 100644
--- a/pkg/nats/config.go
+++ b/pkg/nats/config.go
@@ -9,7 +9,7 @@ import (
 	"bytes"
 	"encoding/json"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 // NatsConfig holds the configuration for connecting to a NATS server.
diff --git a/pkg/nats/influxDecoder.go b/pkg/nats/influxDecoder.go
deleted file mode 100644
index 412f85e9..00000000
--- a/pkg/nats/influxDecoder.go
+++ /dev/null
@@ -1,59 +0,0 @@
-// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved. This file is part of cc-backend.
-// Use of this source code is governed by a MIT-style
-// license that can be found in the LICENSE file.
-
-package nats
-
-import (
-	"time"
-
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
-	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
-)
-
-// DecodeInfluxMessage decodes a single InfluxDB line protocol message from the decoder
-// Returns the decoded CCMessage or an error if decoding fails
-func DecodeInfluxMessage(d *influx.Decoder) (lp.CCMessage, error) {
-	measurement, err := d.Measurement()
-	if err != nil {
-		return nil, err
-	}
-
-	tags := make(map[string]string)
-	for {
-		key, value, err := d.NextTag()
-		if err != nil {
-			return nil, err
-		}
-		if key == nil {
-			break
-		}
-		tags[string(key)] = string(value)
-	}
-
-	fields := make(map[string]interface{})
-	for {
-		key, value, err := d.NextField()
-		if err != nil {
-			return nil, err
-		}
-		if key == nil {
-			break
-		}
-		fields[string(key)] = value.Interface()
-	}
-
-	t, err := d.Time(influx.Nanosecond, time.Time{})
-	if err != nil {
-		return nil, err
-	}
-
-	return lp.NewMessage(
-		string(measurement),
-		tags,
-		nil,
-		fields,
-		t,
-	)
-}
diff --git a/tools/archive-manager/import_test.go b/tools/archive-manager/import_test.go
index b1032118..57294d50 100644
--- a/tools/archive-manager/import_test.go
+++ b/tools/archive-manager/import_test.go
@@ -12,8 +12,8 @@ import (
 	"testing"
 
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
 // TestImportFileToSqlite tests importing jobs from file backend to SQLite backend
diff --git a/tools/archive-manager/main.go b/tools/archive-manager/main.go
index 4972fe96..f5f8b836 100644
--- a/tools/archive-manager/main.go
+++ b/tools/archive-manager/main.go
@@ -23,8 +23,8 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 func parseDate(in string) int64 {
diff --git a/tools/archive-migration/main.go b/tools/archive-migration/main.go
index 9bbed121..8375ee98 100644
--- a/tools/archive-migration/main.go
+++ b/tools/archive-migration/main.go
@@ -12,7 +12,7 @@ import (
 	"path/filepath"
 	"strings"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 func main() {
diff --git a/tools/archive-migration/transforms.go b/tools/archive-migration/transforms.go
index 6558e47a..ef4ba5eb 100644
--- a/tools/archive-migration/transforms.go
+++ b/tools/archive-migration/transforms.go
@@ -12,7 +12,7 @@ import (
 	"sync"
 	"sync/atomic"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
 // transformExclusiveToShared converts the old 'exclusive' field to the new 'shared' field
diff --git a/web/web.go b/web/web.go
index 31d7002e..d2ae8700 100644
--- a/web/web.go
+++ b/web/web.go
@@ -16,9 +16,9 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/schema"
-	"github.com/ClusterCockpit/cc-lib/util"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
 type WebConfig struct {
diff --git a/web/webConfig_test.go b/web/webConfig_test.go
index 4bd84330..514fdabb 100644
--- a/web/webConfig_test.go
+++ b/web/webConfig_test.go
@@ -10,7 +10,7 @@ import (
 	"fmt"
 	"testing"
 
-	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
+	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
 )
 
 func TestInit(t *testing.T) {

From 11ec2267daaf67cbc6602e3ba395a16ede96503e Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 25 Dec 2025 08:42:54 +0100
Subject: [PATCH 19/59] Major refactor of metric data handling

- make the  internal memory store required and default
- Rename memorystore to metricstore
- Rename metricDataDispatcher to metricdispatch
- Remove metricdata package
- Introduce metricsync package for upstream metric data pull
---
 CLAUDE.md                                     |   10 +-
 README.md                                     |    8 +-
 cmd/cc-backend/main.go                        |   21 +-
 cmd/cc-backend/server.go                      |   10 +-
 internal/api/api_test.go                      |   12 +-
 internal/api/job.go                           |    6 +-
 .../api/{memorystore.go => metricstore.go}    |   12 +-
 internal/api/nats_test.go                     |    9 +-
 internal/archiver/README.md                   |    4 +-
 internal/archiver/archiver.go                 |    4 +-
 internal/graph/schema.resolvers.go            |   16 +-
 internal/graph/util.go                        |    6 +-
 internal/metricDataDispatcher/dataLoader.go   |  381 -----
 internal/metricdata/cc-metric-store.go        | 1226 -----------------
 internal/metricdata/metricdata.go             |   88 --
 internal/metricdata/prometheus.go             |  587 --------
 internal/metricdata/utils.go                  |  118 --
 internal/metricdispatch/dataLoader.go         |  490 +++++++
 internal/metricdispatch/dataLoader_test.go    |  125 ++
 internal/{memorystore => metricstore}/api.go  |    6 +-
 .../{memorystore => metricstore}/archive.go   |    2 +-
 .../avroCheckpoint.go                         |    2 +-
 .../avroHelper.go                             |    2 +-
 .../avroStruct.go                             |    2 +-
 .../{memorystore => metricstore}/buffer.go    |    2 +-
 .../checkpoint.go                             |    2 +-
 .../{memorystore => metricstore}/config.go    |    4 +-
 .../configSchema.go                           |    2 +-
 .../{memorystore => metricstore}/debug.go     |    2 +-
 .../healthcheck.go                            |    2 +-
 .../{memorystore => metricstore}/level.go     |    2 +-
 .../lineprotocol.go                           |    2 +-
 .../memorystore.go                            |    4 +-
 .../memorystore_test.go                       |    2 +-
 .../query.go}                                 |  146 +-
 .../{memorystore => metricstore}/stats.go     |    2 +-
 internal/metricsync/metricdata.go             |   60 +
 internal/repository/stats.go                  |    4 +-
 .../taskmanager/updateFootprintService.go     |   10 +-
 39 files changed, 815 insertions(+), 2578 deletions(-)
 rename internal/api/{memorystore.go => metricstore.go} (95%)
 delete mode 100644 internal/metricDataDispatcher/dataLoader.go
 delete mode 100644 internal/metricdata/cc-metric-store.go
 delete mode 100644 internal/metricdata/metricdata.go
 delete mode 100644 internal/metricdata/prometheus.go
 delete mode 100644 internal/metricdata/utils.go
 create mode 100644 internal/metricdispatch/dataLoader.go
 create mode 100644 internal/metricdispatch/dataLoader_test.go
 rename internal/{memorystore => metricstore}/api.go (98%)
 rename internal/{memorystore => metricstore}/archive.go (99%)
 rename internal/{memorystore => metricstore}/avroCheckpoint.go (99%)
 rename internal/{memorystore => metricstore}/avroHelper.go (99%)
 rename internal/{memorystore => metricstore}/avroStruct.go (99%)
 rename internal/{memorystore => metricstore}/buffer.go (99%)
 rename internal/{memorystore => metricstore}/checkpoint.go (99%)
 rename internal/{memorystore => metricstore}/config.go (98%)
 rename internal/{memorystore => metricstore}/configSchema.go (99%)
 rename internal/{memorystore => metricstore}/debug.go (99%)
 rename internal/{memorystore => metricstore}/healthcheck.go (99%)
 rename internal/{memorystore => metricstore}/level.go (99%)
 rename internal/{memorystore => metricstore}/lineprotocol.go (99%)
 rename internal/{memorystore => metricstore}/memorystore.go (99%)
 rename internal/{memorystore => metricstore}/memorystore_test.go (99%)
 rename internal/{metricdata/cc-metric-store-internal.go => metricstore/query.go} (87%)
 rename internal/{memorystore => metricstore}/stats.go (99%)
 create mode 100644 internal/metricsync/metricdata.go

diff --git a/CLAUDE.md b/CLAUDE.md
index 67412a76..f30c3923 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -96,9 +96,9 @@ The backend follows a layered architecture with clear separation of concerns:
 - **internal/auth**: Authentication layer
   - Supports local accounts, LDAP, OIDC, and JWT tokens
   - Implements rate limiting for login attempts
-- **internal/metricdata**: Metric data repository abstraction
-  - Pluggable backends: cc-metric-store, Prometheus, InfluxDB
-  - Each cluster can have a different metric data backend
+- **internal/metricstore**: Metric store with data loading API
+  - In-memory metric storage with checkpointing
+  - Query API for loading job metric data
 - **internal/archiver**: Job archiving to file-based archive
 - **internal/api/nats.go**: NATS-based API for job and node operations
   - Subscribes to NATS subjects for job events (start/stop)
@@ -209,8 +209,8 @@ applied automatically on startup. Version tracking in `version` table.
 
 ### Adding a new metric data backend
 
-1. Implement `MetricDataRepository` interface in `internal/metricdata/`
-2. Register in `metricdata.Init()` switch statement
+1. Implement metric loading functions in `internal/metricstore/query.go`
+2. Add cluster configuration to metric store initialization
 3. Update config.json schema documentation
 
 ### Modifying database schema
diff --git a/README.md b/README.md
index 468a12ad..00bcb119 100644
--- a/README.md
+++ b/README.md
@@ -163,11 +163,9 @@ ln -s <your-existing-job-archive> ./var/job-archive
     GraphQL schema and resolvers
   - [`importer`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/importer)
     Job data import and database initialization
-  - [`memorystore`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/memorystore)
-    In-memory metric data store with checkpointing
-  - [`metricdata`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/metricdata)
-    Metric data repository implementations (cc-metric-store, Prometheus)
-  - [`metricDataDispatcher`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/metricDataDispatcher)
+  - [`metricstore`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/metricstore)
+    In-memory metric data store with checkpointing and metric loading
+  - [`metricdispatch`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/metricdispatch)
     Dispatches metric data loading to appropriate backends
   - [`repository`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal/repository)
     Database repository layer for jobs and metadata
diff --git a/cmd/cc-backend/main.go b/cmd/cc-backend/main.go
index f8b4aea1..331df4f6 100644
--- a/cmd/cc-backend/main.go
+++ b/cmd/cc-backend/main.go
@@ -24,8 +24,7 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/auth"
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/importer"
-	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
-	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
+	"github.com/ClusterCockpit/cc-backend/internal/metricstore"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/internal/tagger"
 	"github.com/ClusterCockpit/cc-backend/internal/taskmanager"
@@ -283,10 +282,7 @@ func initSubsystems() error {
 		return fmt.Errorf("initializing archive: %w", err)
 	}
 
-	// Initialize metricdata
-	if err := metricdata.Init(); err != nil {
-		return fmt.Errorf("initializing metricdata repository: %w", err)
-	}
+	// Note: metricstore.Init() is called later in runServer() with proper configuration
 
 	// Handle database re-initialization
 	if flagReinitDB {
@@ -322,13 +318,12 @@ func initSubsystems() error {
 func runServer(ctx context.Context) error {
 	var wg sync.WaitGroup
 
-	// Start metric store if enabled
-	if memorystore.InternalCCMSFlag {
-		mscfg := ccconf.GetPackageConfig("metric-store")
-		if mscfg == nil {
-			return fmt.Errorf("metric store configuration must be present")
-		}
-		memorystore.Init(mscfg, &wg)
+	// Initialize metric store if configuration is provided
+	mscfg := ccconf.GetPackageConfig("metric-store")
+	if mscfg != nil {
+		metricstore.Init(mscfg, &wg)
+	} else {
+		cclog.Debug("Metric store configuration not found, skipping metricstore initialization")
 	}
 
 	// Start archiver and task manager
diff --git a/cmd/cc-backend/server.go b/cmd/cc-backend/server.go
index 53e24c88..8d700823 100644
--- a/cmd/cc-backend/server.go
+++ b/cmd/cc-backend/server.go
@@ -29,7 +29,7 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/generated"
-	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
+	"github.com/ClusterCockpit/cc-backend/internal/metricstore"
 	"github.com/ClusterCockpit/cc-backend/internal/routerConfig"
 	"github.com/ClusterCockpit/cc-backend/pkg/nats"
 	"github.com/ClusterCockpit/cc-backend/web"
@@ -253,9 +253,7 @@ func (s *Server) init() error {
 		}
 	}
 
-	if memorystore.InternalCCMSFlag {
-		s.restAPIHandle.MountMetricStoreAPIRoutes(metricstoreapi)
-	}
+	s.restAPIHandle.MountMetricStoreAPIRoutes(metricstoreapi)
 
 	if config.Keys.EmbedStaticFiles {
 		if i, err := os.Stat("./var/img"); err == nil {
@@ -383,9 +381,7 @@ func (s *Server) Shutdown(ctx context.Context) {
 	}
 
 	// Archive all the metric store data
-	if memorystore.InternalCCMSFlag {
-		memorystore.Shutdown()
-	}
+	metricstore.Shutdown()
 
 	// Shutdown archiver with 10 second timeout for fast shutdown
 	if err := archiver.Shutdown(10 * time.Second); err != nil {
diff --git a/internal/api/api_test.go b/internal/api/api_test.go
index 50605f7b..a2283013 100644
--- a/internal/api/api_test.go
+++ b/internal/api/api_test.go
@@ -23,8 +23,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/auth"
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph"
-	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
-	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
+	"github.com/ClusterCockpit/cc-backend/internal/metricdispatch"
+	"github.com/ClusterCockpit/cc-backend/internal/metricstore"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
 	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
@@ -173,9 +173,7 @@ func setup(t *testing.T) *api.RestAPI {
 		t.Fatal(err)
 	}
 
-	if err := metricdata.Init(); err != nil {
-		t.Fatal(err)
-	}
+	// metricstore initialization removed - it's initialized via callback in tests
 
 	archiver.Start(repository.GetJobRepository(), context.Background())
 
@@ -221,7 +219,7 @@ func TestRestApi(t *testing.T) {
 		},
 	}
 
-	metricdata.TestLoadDataCallback = func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) {
+	metricstore.TestLoadDataCallback = func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) {
 		return testData, nil
 	}
 
@@ -366,7 +364,7 @@ func TestRestApi(t *testing.T) {
 	}
 
 	t.Run("CheckArchive", func(t *testing.T) {
-		data, err := metricDataDispatcher.LoadData(stoppedJob, []string{"load_one"}, []schema.MetricScope{schema.MetricScopeNode}, context.Background(), 60)
+		data, err := metricdispatch.LoadData(stoppedJob, []string{"load_one"}, []schema.MetricScope{schema.MetricScopeNode}, context.Background(), 60)
 		if err != nil {
 			t.Fatal(err)
 		}
diff --git a/internal/api/job.go b/internal/api/job.go
index 9b970c2e..09f7b22c 100644
--- a/internal/api/job.go
+++ b/internal/api/job.go
@@ -22,7 +22,7 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/graph"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
 	"github.com/ClusterCockpit/cc-backend/internal/importer"
-	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
+	"github.com/ClusterCockpit/cc-backend/internal/metricdispatch"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
 	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
@@ -293,7 +293,7 @@ func (api *RestAPI) getCompleteJobByID(rw http.ResponseWriter, r *http.Request)
 	}
 
 	if r.URL.Query().Get("all-metrics") == "true" {
-		data, err = metricDataDispatcher.LoadData(job, nil, scopes, r.Context(), resolution)
+		data, err = metricdispatch.LoadData(job, nil, scopes, r.Context(), resolution)
 		if err != nil {
 			cclog.Warnf("REST: error while loading all-metrics job data for JobID %d on %s", job.JobID, job.Cluster)
 			return
@@ -389,7 +389,7 @@ func (api *RestAPI) getJobByID(rw http.ResponseWriter, r *http.Request) {
 		resolution = max(resolution, mc.Timestep)
 	}
 
-	data, err := metricDataDispatcher.LoadData(job, metrics, scopes, r.Context(), resolution)
+	data, err := metricdispatch.LoadData(job, metrics, scopes, r.Context(), resolution)
 	if err != nil {
 		cclog.Warnf("REST: error while loading job data for JobID %d on %s", job.JobID, job.Cluster)
 		return
diff --git a/internal/api/memorystore.go b/internal/api/metricstore.go
similarity index 95%
rename from internal/api/memorystore.go
rename to internal/api/metricstore.go
index 56c396e2..d4ab1dfe 100644
--- a/internal/api/memorystore.go
+++ b/internal/api/metricstore.go
@@ -15,7 +15,7 @@ import (
 	"strconv"
 	"strings"
 
-	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
+	"github.com/ClusterCockpit/cc-backend/internal/metricstore"
 	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 
 	"github.com/influxdata/line-protocol/v2/lineprotocol"
@@ -58,7 +58,7 @@ func freeMetrics(rw http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	ms := memorystore.GetMemoryStore()
+	ms := metricstore.GetMemoryStore()
 	n := 0
 	for _, sel := range selectors {
 		bn, err := ms.Free(sel, to)
@@ -97,9 +97,9 @@ func writeMetrics(rw http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	ms := memorystore.GetMemoryStore()
+	ms := metricstore.GetMemoryStore()
 	dec := lineprotocol.NewDecoderWithBytes(bytes)
-	if err := memorystore.DecodeLine(dec, ms, r.URL.Query().Get("cluster")); err != nil {
+	if err := metricstore.DecodeLine(dec, ms, r.URL.Query().Get("cluster")); err != nil {
 		cclog.Errorf("/api/write error: %s", err.Error())
 		handleError(err, http.StatusBadRequest, rw)
 		return
@@ -129,7 +129,7 @@ func debugMetrics(rw http.ResponseWriter, r *http.Request) {
 		selector = strings.Split(raw, ":")
 	}
 
-	ms := memorystore.GetMemoryStore()
+	ms := metricstore.GetMemoryStore()
 	if err := ms.DebugDump(bufio.NewWriter(rw), selector); err != nil {
 		handleError(err, http.StatusBadRequest, rw)
 		return
@@ -162,7 +162,7 @@ func metricsHealth(rw http.ResponseWriter, r *http.Request) {
 
 	selector := []string{rawCluster, rawNode}
 
-	ms := memorystore.GetMemoryStore()
+	ms := metricstore.GetMemoryStore()
 	if err := ms.HealthCheck(bufio.NewWriter(rw), selector); err != nil {
 		handleError(err, http.StatusBadRequest, rw)
 		return
diff --git a/internal/api/nats_test.go b/internal/api/nats_test.go
index c9415afc..9e1fa2b5 100644
--- a/internal/api/nats_test.go
+++ b/internal/api/nats_test.go
@@ -18,7 +18,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/auth"
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph"
-	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
+	"github.com/ClusterCockpit/cc-backend/internal/importer"
+	"github.com/ClusterCockpit/cc-backend/internal/metricstore"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
 	ccconf "github.com/ClusterCockpit/cc-lib/v2/ccConfig"
@@ -167,9 +168,7 @@ func setupNatsTest(t *testing.T) *NatsAPI {
 		t.Fatal(err)
 	}
 
-	if err := metricdata.Init(); err != nil {
-		t.Fatal(err)
-	}
+	// metricstore initialization removed - it's initialized via callback in tests
 
 	archiver.Start(repository.GetJobRepository(), context.Background())
 
@@ -564,7 +563,7 @@ func TestNatsHandleStopJob(t *testing.T) {
 		},
 	}
 
-	metricdata.TestLoadDataCallback = func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) {
+	metricstore.TestLoadDataCallback = func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) {
 		return testData, nil
 	}
 
diff --git a/internal/archiver/README.md b/internal/archiver/README.md
index 0fae04ea..48aed797 100644
--- a/internal/archiver/README.md
+++ b/internal/archiver/README.md
@@ -106,7 +106,7 @@ Data is archived at the highest available resolution (typically 60s intervals).
 
 ```go
 // In archiver.go ArchiveJob() function
-jobData, err := metricDataDispatcher.LoadData(job, allMetrics, scopes, ctx, 300)
+jobData, err := metricdispatch.LoadData(job, allMetrics, scopes, ctx, 300)
 // 0 = highest resolution
 // 300 = 5-minute resolution
 ```
@@ -185,6 +185,6 @@ Internal state is protected by:
 ## Dependencies
 
 - `internal/repository`: Database operations for job metadata
-- `internal/metricDataDispatcher`: Loading metric data from various backends
+- `internal/metricdispatch`: Loading metric data from various backends
 - `pkg/archive`: Archive backend abstraction (filesystem, S3, SQLite)
 - `cc-lib/schema`: Job and metric data structures
diff --git a/internal/archiver/archiver.go b/internal/archiver/archiver.go
index 46ce8126..4e0b6473 100644
--- a/internal/archiver/archiver.go
+++ b/internal/archiver/archiver.go
@@ -10,7 +10,7 @@ import (
 	"math"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
-	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
+	"github.com/ClusterCockpit/cc-backend/internal/metricdispatch"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
 	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
@@ -60,7 +60,7 @@ func ArchiveJob(job *schema.Job, ctx context.Context) (*schema.Job, error) {
 		scopes = append(scopes, schema.MetricScopeAccelerator)
 	}
 
-	jobData, err := metricDataDispatcher.LoadData(job, allMetrics, scopes, ctx, 0) // 0 Resulotion-Value retrieves highest res (60s)
+	jobData, err := metricdispatch.LoadData(job, allMetrics, scopes, ctx, 0) // 0 Resulotion-Value retrieves highest res (60s)
 	if err != nil {
 		cclog.Error("Error wile loading job data for archiving")
 		return nil, err
diff --git a/internal/graph/schema.resolvers.go b/internal/graph/schema.resolvers.go
index 32499b8c..34bbf393 100644
--- a/internal/graph/schema.resolvers.go
+++ b/internal/graph/schema.resolvers.go
@@ -19,7 +19,7 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/generated"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
+	"github.com/ClusterCockpit/cc-backend/internal/metricdispatch"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
 	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
@@ -484,7 +484,7 @@ func (r *queryResolver) JobMetrics(ctx context.Context, id string, metrics []str
 		return nil, err
 	}
 
-	data, err := metricDataDispatcher.LoadData(job, metrics, scopes, ctx, *resolution)
+	data, err := metricdispatch.LoadData(job, metrics, scopes, ctx, *resolution)
 	if err != nil {
 		cclog.Warn("Error while loading job data")
 		return nil, err
@@ -512,7 +512,7 @@ func (r *queryResolver) JobStats(ctx context.Context, id string, metrics []strin
 		return nil, err
 	}
 
-	data, err := metricDataDispatcher.LoadJobStats(job, metrics, ctx)
+	data, err := metricdispatch.LoadJobStats(job, metrics, ctx)
 	if err != nil {
 		cclog.Warnf("Error while loading jobStats data for job id %s", id)
 		return nil, err
@@ -537,7 +537,7 @@ func (r *queryResolver) ScopedJobStats(ctx context.Context, id string, metrics [
 		return nil, err
 	}
 
-	data, err := metricDataDispatcher.LoadScopedJobStats(job, metrics, scopes, ctx)
+	data, err := metricdispatch.LoadScopedJobStats(job, metrics, scopes, ctx)
 	if err != nil {
 		cclog.Warnf("Error while loading scopedJobStats data for job id %s", id)
 		return nil, err
@@ -702,7 +702,7 @@ func (r *queryResolver) JobsMetricStats(ctx context.Context, filter []*model.Job
 
 	res := []*model.JobStats{}
 	for _, job := range jobs {
-		data, err := metricDataDispatcher.LoadJobStats(job, metrics, ctx)
+		data, err := metricdispatch.LoadJobStats(job, metrics, ctx)
 		if err != nil {
 			cclog.Warnf("Error while loading comparison jobStats data for job id %d", job.JobID)
 			continue
@@ -759,7 +759,7 @@ func (r *queryResolver) NodeMetrics(ctx context.Context, cluster string, nodes [
 		}
 	}
 
-	data, err := metricDataDispatcher.LoadNodeData(cluster, metrics, nodes, scopes, from, to, ctx)
+	data, err := metricdispatch.LoadNodeData(cluster, metrics, nodes, scopes, from, to, ctx)
 	if err != nil {
 		cclog.Warn("error while loading node data")
 		return nil, err
@@ -825,7 +825,7 @@ func (r *queryResolver) NodeMetricsList(ctx context.Context, cluster string, sub
 		}
 	}
 
-	data, err := metricDataDispatcher.LoadNodeListData(cluster, subCluster, nodes, metrics, scopes, *resolution, from, to, ctx)
+	data, err := metricdispatch.LoadNodeListData(cluster, subCluster, nodes, metrics, scopes, *resolution, from, to, ctx)
 	if err != nil {
 		cclog.Warn("error while loading node data (Resolver.NodeMetricsList")
 		return nil, err
@@ -880,7 +880,7 @@ func (r *queryResolver) ClusterMetrics(ctx context.Context, cluster string, metr
 
 	// 'nodes' == nil -> Defaults to all nodes of cluster for existing query workflow
 	scopes := []schema.MetricScope{"node"}
-	data, err := metricDataDispatcher.LoadNodeData(cluster, metrics, nil, scopes, from, to, ctx)
+	data, err := metricdispatch.LoadNodeData(cluster, metrics, nil, scopes, from, to, ctx)
 	if err != nil {
 		cclog.Warn("error while loading node data")
 		return nil, err
diff --git a/internal/graph/util.go b/internal/graph/util.go
index 42a1d2fb..4135ca72 100644
--- a/internal/graph/util.go
+++ b/internal/graph/util.go
@@ -13,7 +13,7 @@ import (
 
 	"github.com/99designs/gqlgen/graphql"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
+	"github.com/ClusterCockpit/cc-backend/internal/metricdispatch"
 	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
@@ -55,7 +55,7 @@ func (r *queryResolver) rooflineHeatmap(
 		// 	resolution = max(resolution, mc.Timestep)
 		// }
 
-		jobdata, err := metricDataDispatcher.LoadData(job, []string{"flops_any", "mem_bw"}, []schema.MetricScope{schema.MetricScopeNode}, ctx, 0)
+		jobdata, err := metricdispatch.LoadData(job, []string{"flops_any", "mem_bw"}, []schema.MetricScope{schema.MetricScopeNode}, ctx, 0)
 		if err != nil {
 			cclog.Errorf("Error while loading roofline metrics for job %d", job.ID)
 			return nil, err
@@ -128,7 +128,7 @@ func (r *queryResolver) jobsFootprints(ctx context.Context, filter []*model.JobF
 			continue
 		}
 
-		if err := metricDataDispatcher.LoadAverages(job, metrics, avgs, ctx); err != nil {
+		if err := metricdispatch.LoadAverages(job, metrics, avgs, ctx); err != nil {
 			cclog.Error("Error while loading averages for footprint")
 			return nil, err
 		}
diff --git a/internal/metricDataDispatcher/dataLoader.go b/internal/metricDataDispatcher/dataLoader.go
deleted file mode 100644
index 6d1338fa..00000000
--- a/internal/metricDataDispatcher/dataLoader.go
+++ /dev/null
@@ -1,381 +0,0 @@
-// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved. This file is part of cc-backend.
-// Use of this source code is governed by a MIT-style
-// license that can be found in the LICENSE file.
-package metricDataDispatcher
-
-import (
-	"context"
-	"fmt"
-	"math"
-	"time"
-
-	"github.com/ClusterCockpit/cc-backend/internal/config"
-	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
-	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/v2/lrucache"
-	"github.com/ClusterCockpit/cc-lib/v2/resampler"
-	"github.com/ClusterCockpit/cc-lib/v2/schema"
-)
-
-var cache *lrucache.Cache = lrucache.New(128 * 1024 * 1024)
-
-func cacheKey(
-	job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	resolution int,
-) string {
-	// Duration and StartTime do not need to be in the cache key as StartTime is less unique than
-	// job.ID and the TTL of the cache entry makes sure it does not stay there forever.
-	return fmt.Sprintf("%d(%s):[%v],[%v]-%d",
-		job.ID, job.State, metrics, scopes, resolution)
-}
-
-// Fetches the metric data for a job.
-func LoadData(job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	ctx context.Context,
-	resolution int,
-) (schema.JobData, error) {
-	data := cache.Get(cacheKey(job, metrics, scopes, resolution), func() (_ any, ttl time.Duration, size int) {
-		var jd schema.JobData
-		var err error
-
-		if job.State == schema.JobStateRunning ||
-			job.MonitoringStatus == schema.MonitoringStatusRunningOrArchiving ||
-			config.Keys.DisableArchive {
-
-			repo, err := metricdata.GetMetricDataRepo(job.Cluster)
-			if err != nil {
-				return fmt.Errorf("METRICDATA/METRICDATA > no metric data repository configured for '%s'", job.Cluster), 0, 0
-			}
-
-			if scopes == nil {
-				scopes = append(scopes, schema.MetricScopeNode)
-			}
-
-			if metrics == nil {
-				cluster := archive.GetCluster(job.Cluster)
-				for _, mc := range cluster.MetricConfig {
-					metrics = append(metrics, mc.Name)
-				}
-			}
-
-			jd, err = repo.LoadData(job, metrics, scopes, ctx, resolution)
-			if err != nil {
-				if len(jd) != 0 {
-					cclog.Warnf("partial error: %s", err.Error())
-					// return err, 0, 0 // Reactivating will block archiving on one partial error
-				} else {
-					cclog.Error("Error while loading job data from metric repository")
-					return err, 0, 0
-				}
-			}
-			size = jd.Size()
-		} else {
-			var jd_temp schema.JobData
-			jd_temp, err = archive.GetHandle().LoadJobData(job)
-			if err != nil {
-				cclog.Error("Error while loading job data from archive")
-				return err, 0, 0
-			}
-
-			// Deep copy the cached archive hashmap
-			jd = metricdata.DeepCopy(jd_temp)
-
-			// Resampling for archived data.
-			// Pass the resolution from frontend here.
-			for _, v := range jd {
-				for _, v_ := range v {
-					timestep := int64(0)
-					for i := 0; i < len(v_.Series); i += 1 {
-						v_.Series[i].Data, timestep, err = resampler.LargestTriangleThreeBucket(v_.Series[i].Data, int64(v_.Timestep), int64(resolution))
-						if err != nil {
-							return err, 0, 0
-						}
-					}
-					v_.Timestep = int(timestep)
-				}
-			}
-
-			// Avoid sending unrequested data to the client:
-			if metrics != nil || scopes != nil {
-				if metrics == nil {
-					metrics = make([]string, 0, len(jd))
-					for k := range jd {
-						metrics = append(metrics, k)
-					}
-				}
-
-				res := schema.JobData{}
-				for _, metric := range metrics {
-					if perscope, ok := jd[metric]; ok {
-						if len(perscope) > 1 {
-							subset := make(map[schema.MetricScope]*schema.JobMetric)
-							for _, scope := range scopes {
-								if jm, ok := perscope[scope]; ok {
-									subset[scope] = jm
-								}
-							}
-
-							if len(subset) > 0 {
-								perscope = subset
-							}
-						}
-
-						res[metric] = perscope
-					}
-				}
-				jd = res
-			}
-			size = jd.Size()
-		}
-
-		ttl = 5 * time.Hour
-		if job.State == schema.JobStateRunning {
-			ttl = 2 * time.Minute
-		}
-
-		// FIXME: Review: Is this really necessary or correct.
-		// Note: Lines 147-170 formerly known as prepareJobData(jobData, scopes)
-		// For /monitoring/job/<job> and some other places, flops_any and mem_bw need
-		// to be available at the scope 'node'. If a job has a lot of nodes,
-		// statisticsSeries should be available so that a min/median/max Graph can be
-		// used instead of a lot of single lines.
-		// NOTE: New StatsSeries will always be calculated as 'min/median/max'
-		//       Existing (archived) StatsSeries can be 'min/mean/max'!
-		const maxSeriesSize int = 15
-		for _, scopes := range jd {
-			for _, jm := range scopes {
-				if jm.StatisticsSeries != nil || len(jm.Series) <= maxSeriesSize {
-					continue
-				}
-
-				jm.AddStatisticsSeries()
-			}
-		}
-
-		nodeScopeRequested := false
-		for _, scope := range scopes {
-			if scope == schema.MetricScopeNode {
-				nodeScopeRequested = true
-			}
-		}
-
-		if nodeScopeRequested {
-			jd.AddNodeScope("flops_any")
-			jd.AddNodeScope("mem_bw")
-		}
-
-		// Round Resulting Stat Values
-		jd.RoundMetricStats()
-
-		return jd, ttl, size
-	})
-
-	if err, ok := data.(error); ok {
-		cclog.Error("Error in returned dataset")
-		return nil, err
-	}
-
-	return data.(schema.JobData), nil
-}
-
-// Used for the jobsFootprint GraphQL-Query. TODO: Rename/Generalize.
-func LoadAverages(
-	job *schema.Job,
-	metrics []string,
-	data [][]schema.Float,
-	ctx context.Context,
-) error {
-	if job.State != schema.JobStateRunning && !config.Keys.DisableArchive {
-		return archive.LoadAveragesFromArchive(job, metrics, data) // #166 change also here?
-	}
-
-	repo, err := metricdata.GetMetricDataRepo(job.Cluster)
-	if err != nil {
-		return fmt.Errorf("METRICDATA/METRICDATA > no metric data repository configured for '%s'", job.Cluster)
-	}
-
-	stats, err := repo.LoadStats(job, metrics, ctx) // #166 how to handle stats for acc normalizazion?
-	if err != nil {
-		cclog.Errorf("Error while loading statistics for job %v (User %v, Project %v)", job.JobID, job.User, job.Project)
-		return err
-	}
-
-	for i, m := range metrics {
-		nodes, ok := stats[m]
-		if !ok {
-			data[i] = append(data[i], schema.NaN)
-			continue
-		}
-
-		sum := 0.0
-		for _, node := range nodes {
-			sum += node.Avg
-		}
-		data[i] = append(data[i], schema.Float(sum))
-	}
-
-	return nil
-}
-
-// Used for statsTable in frontend: Return scoped statistics by metric.
-func LoadScopedJobStats(
-	job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	ctx context.Context,
-) (schema.ScopedJobStats, error) {
-	if job.State != schema.JobStateRunning && !config.Keys.DisableArchive {
-		return archive.LoadScopedStatsFromArchive(job, metrics, scopes)
-	}
-
-	repo, err := metricdata.GetMetricDataRepo(job.Cluster)
-	if err != nil {
-		return nil, fmt.Errorf("job %d: no metric data repository configured for '%s'", job.JobID, job.Cluster)
-	}
-
-	scopedStats, err := repo.LoadScopedStats(job, metrics, scopes, ctx)
-	if err != nil {
-		cclog.Errorf("error while loading scoped statistics for job %d (User %s, Project %s)", job.JobID, job.User, job.Project)
-		return nil, err
-	}
-
-	return scopedStats, nil
-}
-
-// Used for polar plots in frontend: Aggregates statistics for all nodes to single values for job per metric.
-func LoadJobStats(
-	job *schema.Job,
-	metrics []string,
-	ctx context.Context,
-) (map[string]schema.MetricStatistics, error) {
-	if job.State != schema.JobStateRunning && !config.Keys.DisableArchive {
-		return archive.LoadStatsFromArchive(job, metrics)
-	}
-
-	data := make(map[string]schema.MetricStatistics, len(metrics))
-	repo, err := metricdata.GetMetricDataRepo(job.Cluster)
-	if err != nil {
-		return data, fmt.Errorf("job %d: no metric data repository configured for '%s'", job.JobID, job.Cluster)
-	}
-
-	stats, err := repo.LoadStats(job, metrics, ctx)
-	if err != nil {
-		cclog.Errorf("error while loading statistics for job %d (User %s, Project %s)", job.JobID, job.User, job.Project)
-		return data, err
-	}
-
-	for _, m := range metrics {
-		sum, avg, min, max := 0.0, 0.0, 0.0, 0.0
-		nodes, ok := stats[m]
-		if !ok {
-			data[m] = schema.MetricStatistics{Min: min, Avg: avg, Max: max}
-			continue
-		}
-
-		for _, node := range nodes {
-			sum += node.Avg
-			min = math.Min(min, node.Min)
-			max = math.Max(max, node.Max)
-		}
-
-		data[m] = schema.MetricStatistics{
-			Avg: (math.Round((sum/float64(job.NumNodes))*100) / 100),
-			Min: (math.Round(min*100) / 100),
-			Max: (math.Round(max*100) / 100),
-		}
-	}
-
-	return data, nil
-}
-
-// Used for the classic node/system view. Returns a map of nodes to a map of metrics.
-func LoadNodeData(
-	cluster string,
-	metrics, nodes []string,
-	scopes []schema.MetricScope,
-	from, to time.Time,
-	ctx context.Context,
-) (map[string]map[string][]*schema.JobMetric, error) {
-	repo, err := metricdata.GetMetricDataRepo(cluster)
-	if err != nil {
-		return nil, fmt.Errorf("METRICDATA/METRICDATA > no metric data repository configured for '%s'", cluster)
-	}
-
-	if metrics == nil {
-		for _, m := range archive.GetCluster(cluster).MetricConfig {
-			metrics = append(metrics, m.Name)
-		}
-	}
-
-	data, err := repo.LoadNodeData(cluster, metrics, nodes, scopes, from, to, ctx)
-	if err != nil {
-		if len(data) != 0 {
-			cclog.Warnf("partial error: %s", err.Error())
-		} else {
-			cclog.Error("Error while loading node data from metric repository")
-			return nil, err
-		}
-	}
-
-	if data == nil {
-		return nil, fmt.Errorf("METRICDATA/METRICDATA > the metric data repository for '%s' does not support this query", cluster)
-	}
-
-	return data, nil
-}
-
-func LoadNodeListData(
-	cluster, subCluster string,
-	nodes []string,
-	metrics []string,
-	scopes []schema.MetricScope,
-	resolution int,
-	from, to time.Time,
-	ctx context.Context,
-) (map[string]schema.JobData, error) {
-	repo, err := metricdata.GetMetricDataRepo(cluster)
-	if err != nil {
-		return nil, fmt.Errorf("METRICDATA/METRICDATA > no metric data repository configured for '%s'", cluster)
-	}
-
-	if metrics == nil {
-		for _, m := range archive.GetCluster(cluster).MetricConfig {
-			metrics = append(metrics, m.Name)
-		}
-	}
-
-	data, err := repo.LoadNodeListData(cluster, subCluster, nodes, metrics, scopes, resolution, from, to, ctx)
-	if err != nil {
-		if len(data) != 0 {
-			cclog.Warnf("partial error: %s", err.Error())
-		} else {
-			cclog.Error("Error while loading node data from metric repository")
-			return nil, err
-		}
-	}
-
-	// NOTE: New StatsSeries will always be calculated as 'min/median/max'
-	const maxSeriesSize int = 8
-	for _, jd := range data {
-		for _, scopes := range jd {
-			for _, jm := range scopes {
-				if jm.StatisticsSeries != nil || len(jm.Series) < maxSeriesSize {
-					continue
-				}
-				jm.AddStatisticsSeries()
-			}
-		}
-	}
-
-	if data == nil {
-		return nil, fmt.Errorf("METRICDATA/METRICDATA > the metric data repository for '%s' does not support this query", cluster)
-	}
-
-	return data, nil
-}
diff --git a/internal/metricdata/cc-metric-store.go b/internal/metricdata/cc-metric-store.go
deleted file mode 100644
index 6c146f22..00000000
--- a/internal/metricdata/cc-metric-store.go
+++ /dev/null
@@ -1,1226 +0,0 @@
-// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
-// Use of this source code is governed by a MIT-style
-// license that can be found in the LICENSE file.
-package metricdata
-
-import (
-	"bufio"
-	"bytes"
-	"context"
-	"encoding/json"
-	"fmt"
-	"net/http"
-	"strings"
-	"time"
-
-	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/v2/schema"
-)
-
-type CCMetricStoreConfig struct {
-	Kind  string `json:"kind"`
-	Url   string `json:"url"`
-	Token string `json:"token"`
-
-	// If metrics are known to this MetricDataRepository under a different
-	// name than in the `metricConfig` section of the 'cluster.json',
-	// provide this optional mapping of local to remote name for this metric.
-	Renamings map[string]string `json:"metricRenamings"`
-}
-
-type CCMetricStore struct {
-	here2there    map[string]string
-	there2here    map[string]string
-	client        http.Client
-	jwt           string
-	url           string
-	queryEndpoint string
-}
-
-type ApiQueryRequest struct {
-	Cluster     string     `json:"cluster"`
-	Queries     []ApiQuery `json:"queries"`
-	ForAllNodes []string   `json:"for-all-nodes"`
-	From        int64      `json:"from"`
-	To          int64      `json:"to"`
-	WithStats   bool       `json:"with-stats"`
-	WithData    bool       `json:"with-data"`
-}
-
-type ApiQuery struct {
-	Type       *string  `json:"type,omitempty"`
-	SubType    *string  `json:"subtype,omitempty"`
-	Metric     string   `json:"metric"`
-	Hostname   string   `json:"host"`
-	Resolution int      `json:"resolution"`
-	TypeIds    []string `json:"type-ids,omitempty"`
-	SubTypeIds []string `json:"subtype-ids,omitempty"`
-	Aggregate  bool     `json:"aggreg"`
-}
-
-type ApiQueryResponse struct {
-	Queries []ApiQuery        `json:"queries,omitempty"`
-	Results [][]ApiMetricData `json:"results"`
-}
-
-type ApiMetricData struct {
-	Error      *string        `json:"error"`
-	Data       []schema.Float `json:"data"`
-	From       int64          `json:"from"`
-	To         int64          `json:"to"`
-	Resolution int            `json:"resolution"`
-	Avg        schema.Float   `json:"avg"`
-	Min        schema.Float   `json:"min"`
-	Max        schema.Float   `json:"max"`
-}
-
-func (ccms *CCMetricStore) Init(rawConfig json.RawMessage) error {
-	var config CCMetricStoreConfig
-	if err := json.Unmarshal(rawConfig, &config); err != nil {
-		cclog.Warn("Error while unmarshaling raw json config")
-		return err
-	}
-
-	ccms.url = config.Url
-	ccms.queryEndpoint = fmt.Sprintf("%s/api/query", config.Url)
-	ccms.jwt = config.Token
-	ccms.client = http.Client{
-		Timeout: 10 * time.Second,
-	}
-
-	if config.Renamings != nil {
-		ccms.here2there = config.Renamings
-		ccms.there2here = make(map[string]string, len(config.Renamings))
-		for k, v := range ccms.here2there {
-			ccms.there2here[v] = k
-		}
-	} else {
-		ccms.here2there = make(map[string]string)
-		ccms.there2here = make(map[string]string)
-	}
-
-	return nil
-}
-
-func (ccms *CCMetricStore) toRemoteName(metric string) string {
-	if renamed, ok := ccms.here2there[metric]; ok {
-		return renamed
-	}
-
-	return metric
-}
-
-func (ccms *CCMetricStore) toLocalName(metric string) string {
-	if renamed, ok := ccms.there2here[metric]; ok {
-		return renamed
-	}
-
-	return metric
-}
-
-func (ccms *CCMetricStore) doRequest(
-	ctx context.Context,
-	body *ApiQueryRequest,
-) (*ApiQueryResponse, error) {
-	buf := &bytes.Buffer{}
-	if err := json.NewEncoder(buf).Encode(body); err != nil {
-		cclog.Errorf("Error while encoding request body: %s", err.Error())
-		return nil, err
-	}
-
-	req, err := http.NewRequestWithContext(ctx, http.MethodGet, ccms.queryEndpoint, buf)
-	if err != nil {
-		cclog.Errorf("Error while building request body: %s", err.Error())
-		return nil, err
-	}
-	if ccms.jwt != "" {
-		req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", ccms.jwt))
-	}
-
-	// versioning the cc-metric-store query API.
-	// v2 = data with resampling
-	// v1 = data without resampling
-	q := req.URL.Query()
-	q.Add("version", "v2")
-	req.URL.RawQuery = q.Encode()
-
-	res, err := ccms.client.Do(req)
-	if err != nil {
-		cclog.Errorf("Error while performing request: %s", err.Error())
-		return nil, err
-	}
-
-	if res.StatusCode != http.StatusOK {
-		return nil, fmt.Errorf("'%s': HTTP Status: %s", ccms.queryEndpoint, res.Status)
-	}
-
-	var resBody ApiQueryResponse
-	if err := json.NewDecoder(bufio.NewReader(res.Body)).Decode(&resBody); err != nil {
-		cclog.Errorf("Error while decoding result body: %s", err.Error())
-		return nil, err
-	}
-
-	return &resBody, nil
-}
-
-func (ccms *CCMetricStore) LoadData(
-	job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	ctx context.Context,
-	resolution int,
-) (schema.JobData, error) {
-	queries, assignedScope, err := ccms.buildQueries(job, metrics, scopes, resolution)
-	if err != nil {
-		cclog.Errorf("Error while building queries for jobId %d, Metrics %v, Scopes %v: %s", job.JobID, metrics, scopes, err.Error())
-		return nil, err
-	}
-
-	req := ApiQueryRequest{
-		Cluster:   job.Cluster,
-		From:      job.StartTime,
-		To:        job.StartTime + int64(job.Duration),
-		Queries:   queries,
-		WithStats: true,
-		WithData:  true,
-	}
-
-	resBody, err := ccms.doRequest(ctx, &req)
-	if err != nil {
-		cclog.Errorf("Error while performing request: %s", err.Error())
-		return nil, err
-	}
-
-	var errors []string
-	jobData := make(schema.JobData)
-	for i, row := range resBody.Results {
-		query := req.Queries[i]
-		metric := ccms.toLocalName(query.Metric)
-		scope := assignedScope[i]
-		mc := archive.GetMetricConfig(job.Cluster, metric)
-		if _, ok := jobData[metric]; !ok {
-			jobData[metric] = make(map[schema.MetricScope]*schema.JobMetric)
-		}
-
-		res := mc.Timestep
-		if len(row) > 0 {
-			res = row[0].Resolution
-		}
-
-		jobMetric, ok := jobData[metric][scope]
-		if !ok {
-			jobMetric = &schema.JobMetric{
-				Unit:     mc.Unit,
-				Timestep: res,
-				Series:   make([]schema.Series, 0),
-			}
-			jobData[metric][scope] = jobMetric
-		}
-
-		for ndx, res := range row {
-			if res.Error != nil {
-				/* Build list for "partial errors", if any */
-				errors = append(errors, fmt.Sprintf("failed to fetch '%s' from host '%s': %s", query.Metric, query.Hostname, *res.Error))
-				continue
-			}
-
-			id := (*string)(nil)
-			if query.Type != nil {
-				id = new(string)
-				*id = query.TypeIds[ndx]
-			}
-
-			if res.Avg.IsNaN() || res.Min.IsNaN() || res.Max.IsNaN() {
-				// "schema.Float()" because regular float64 can not be JSONed when NaN.
-				res.Avg = schema.Float(0)
-				res.Min = schema.Float(0)
-				res.Max = schema.Float(0)
-			}
-
-			jobMetric.Series = append(jobMetric.Series, schema.Series{
-				Hostname: query.Hostname,
-				Id:       id,
-				Statistics: schema.MetricStatistics{
-					Avg: float64(res.Avg),
-					Min: float64(res.Min),
-					Max: float64(res.Max),
-				},
-				Data: res.Data,
-			})
-		}
-
-		// So that one can later check len(jobData):
-		if len(jobMetric.Series) == 0 {
-			delete(jobData[metric], scope)
-			if len(jobData[metric]) == 0 {
-				delete(jobData, metric)
-			}
-		}
-	}
-
-	if len(errors) != 0 {
-		/* Returns list for "partial errors" */
-		return jobData, fmt.Errorf("METRICDATA/CCMS > Errors: %s", strings.Join(errors, ", "))
-	}
-	return jobData, nil
-}
-
-func (ccms *CCMetricStore) buildQueries(
-	job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	resolution int,
-) ([]ApiQuery, []schema.MetricScope, error) {
-	queries := make([]ApiQuery, 0, len(metrics)*len(scopes)*len(job.Resources))
-	assignedScope := []schema.MetricScope{}
-
-	subcluster, scerr := archive.GetSubCluster(job.Cluster, job.SubCluster)
-	if scerr != nil {
-		return nil, nil, scerr
-	}
-	topology := subcluster.Topology
-
-	for _, metric := range metrics {
-		remoteName := ccms.toRemoteName(metric)
-		mc := archive.GetMetricConfig(job.Cluster, metric)
-		if mc == nil {
-			// return nil, fmt.Errorf("METRICDATA/CCMS > metric '%s' is not specified for cluster '%s'", metric, job.Cluster)
-			cclog.Infof("metric '%s' is not specified for cluster '%s'", metric, job.Cluster)
-			continue
-		}
-
-		// Skip if metric is removed for subcluster
-		if len(mc.SubClusters) != 0 {
-			isRemoved := false
-			for _, scConfig := range mc.SubClusters {
-				if scConfig.Name == job.SubCluster && scConfig.Remove {
-					isRemoved = true
-					break
-				}
-			}
-			if isRemoved {
-				continue
-			}
-		}
-
-		// Avoid duplicates...
-		handledScopes := make([]schema.MetricScope, 0, 3)
-
-	scopesLoop:
-		for _, requestedScope := range scopes {
-			nativeScope := mc.Scope
-			if nativeScope == schema.MetricScopeAccelerator && job.NumAcc == 0 {
-				continue
-			}
-
-			scope := nativeScope.Max(requestedScope)
-			for _, s := range handledScopes {
-				if scope == s {
-					continue scopesLoop
-				}
-			}
-			handledScopes = append(handledScopes, scope)
-
-			for _, host := range job.Resources {
-				hwthreads := host.HWThreads
-				if hwthreads == nil {
-					hwthreads = topology.Node
-				}
-
-				// Accelerator -> Accelerator (Use "accelerator" scope if requested scope is lower than node)
-				if nativeScope == schema.MetricScopeAccelerator && scope.LT(schema.MetricScopeNode) {
-					if scope != schema.MetricScopeAccelerator {
-						// Skip all other catched cases
-						continue
-					}
-
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Aggregate:  false,
-						Type:       &acceleratorString,
-						TypeIds:    host.Accelerators,
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, schema.MetricScopeAccelerator)
-					continue
-				}
-
-				// Accelerator -> Node
-				if nativeScope == schema.MetricScopeAccelerator && scope == schema.MetricScopeNode {
-					if len(host.Accelerators) == 0 {
-						continue
-					}
-
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Aggregate:  true,
-						Type:       &acceleratorString,
-						TypeIds:    host.Accelerators,
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// HWThread -> HWThead
-				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeHWThread {
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Aggregate:  false,
-						Type:       &hwthreadString,
-						TypeIds:    intToStringSlice(hwthreads),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// HWThread -> Core
-				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeCore {
-					cores, _ := topology.GetCoresFromHWThreads(hwthreads)
-					for _, core := range cores {
-						queries = append(queries, ApiQuery{
-							Metric:     remoteName,
-							Hostname:   host.Hostname,
-							Aggregate:  true,
-							Type:       &hwthreadString,
-							TypeIds:    intToStringSlice(topology.Core[core]),
-							Resolution: resolution,
-						})
-						assignedScope = append(assignedScope, scope)
-					}
-					continue
-				}
-
-				// HWThread -> Socket
-				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeSocket {
-					sockets, _ := topology.GetSocketsFromHWThreads(hwthreads)
-					for _, socket := range sockets {
-						queries = append(queries, ApiQuery{
-							Metric:     remoteName,
-							Hostname:   host.Hostname,
-							Aggregate:  true,
-							Type:       &hwthreadString,
-							TypeIds:    intToStringSlice(topology.Socket[socket]),
-							Resolution: resolution,
-						})
-						assignedScope = append(assignedScope, scope)
-					}
-					continue
-				}
-
-				// HWThread -> Node
-				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeNode {
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Aggregate:  true,
-						Type:       &hwthreadString,
-						TypeIds:    intToStringSlice(hwthreads),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// Core -> Core
-				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeCore {
-					cores, _ := topology.GetCoresFromHWThreads(hwthreads)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Aggregate:  false,
-						Type:       &coreString,
-						TypeIds:    intToStringSlice(cores),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// Core -> Socket
-				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeSocket {
-					sockets, _ := topology.GetSocketsFromCores(hwthreads)
-					for _, socket := range sockets {
-						queries = append(queries, ApiQuery{
-							Metric:     remoteName,
-							Hostname:   host.Hostname,
-							Aggregate:  true,
-							Type:       &coreString,
-							TypeIds:    intToStringSlice(topology.Socket[socket]),
-							Resolution: resolution,
-						})
-						assignedScope = append(assignedScope, scope)
-					}
-					continue
-				}
-
-				// Core -> Node
-				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeNode {
-					cores, _ := topology.GetCoresFromHWThreads(hwthreads)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Aggregate:  true,
-						Type:       &coreString,
-						TypeIds:    intToStringSlice(cores),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// MemoryDomain -> MemoryDomain
-				if nativeScope == schema.MetricScopeMemoryDomain && scope == schema.MetricScopeMemoryDomain {
-					sockets, _ := topology.GetMemoryDomainsFromHWThreads(hwthreads)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Aggregate:  false,
-						Type:       &memoryDomainString,
-						TypeIds:    intToStringSlice(sockets),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// MemoryDoman -> Node
-				if nativeScope == schema.MetricScopeMemoryDomain && scope == schema.MetricScopeNode {
-					sockets, _ := topology.GetMemoryDomainsFromHWThreads(hwthreads)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Aggregate:  true,
-						Type:       &memoryDomainString,
-						TypeIds:    intToStringSlice(sockets),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// Socket -> Socket
-				if nativeScope == schema.MetricScopeSocket && scope == schema.MetricScopeSocket {
-					sockets, _ := topology.GetSocketsFromHWThreads(hwthreads)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Aggregate:  false,
-						Type:       &socketString,
-						TypeIds:    intToStringSlice(sockets),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// Socket -> Node
-				if nativeScope == schema.MetricScopeSocket && scope == schema.MetricScopeNode {
-					sockets, _ := topology.GetSocketsFromHWThreads(hwthreads)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Aggregate:  true,
-						Type:       &socketString,
-						TypeIds:    intToStringSlice(sockets),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// Node -> Node
-				if nativeScope == schema.MetricScopeNode && scope == schema.MetricScopeNode {
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   host.Hostname,
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				return nil, nil, fmt.Errorf("METRICDATA/CCMS > TODO: unhandled case: native-scope=%s, requested-scope=%s", nativeScope, requestedScope)
-			}
-		}
-	}
-
-	return queries, assignedScope, nil
-}
-
-func (ccms *CCMetricStore) LoadStats(
-	job *schema.Job,
-	metrics []string,
-	ctx context.Context,
-) (map[string]map[string]schema.MetricStatistics, error) {
-
-	queries, _, err := ccms.buildQueries(job, metrics, []schema.MetricScope{schema.MetricScopeNode}, 0) // #166 Add scope shere for analysis view accelerator normalization?
-	if err != nil {
-		cclog.Errorf("Error while building queries for jobId %d, Metrics %v: %s", job.JobID, metrics, err.Error())
-		return nil, err
-	}
-
-	req := ApiQueryRequest{
-		Cluster:   job.Cluster,
-		From:      job.StartTime,
-		To:        job.StartTime + int64(job.Duration),
-		Queries:   queries,
-		WithStats: true,
-		WithData:  false,
-	}
-
-	resBody, err := ccms.doRequest(ctx, &req)
-	if err != nil {
-		cclog.Errorf("Error while performing request: %s", err.Error())
-		return nil, err
-	}
-
-	stats := make(map[string]map[string]schema.MetricStatistics, len(metrics))
-	for i, res := range resBody.Results {
-		query := req.Queries[i]
-		metric := ccms.toLocalName(query.Metric)
-		data := res[0]
-		if data.Error != nil {
-			cclog.Errorf("fetching %s for node %s failed: %s", metric, query.Hostname, *data.Error)
-			continue
-		}
-
-		metricdata, ok := stats[metric]
-		if !ok {
-			metricdata = make(map[string]schema.MetricStatistics, job.NumNodes)
-			stats[metric] = metricdata
-		}
-
-		if data.Avg.IsNaN() || data.Min.IsNaN() || data.Max.IsNaN() {
-			cclog.Warnf("fetching %s for node %s failed: one of avg/min/max is NaN", metric, query.Hostname)
-			continue
-		}
-
-		metricdata[query.Hostname] = schema.MetricStatistics{
-			Avg: float64(data.Avg),
-			Min: float64(data.Min),
-			Max: float64(data.Max),
-		}
-	}
-
-	return stats, nil
-}
-
-// Used for Job-View Statistics Table
-func (ccms *CCMetricStore) LoadScopedStats(
-	job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	ctx context.Context,
-) (schema.ScopedJobStats, error) {
-	queries, assignedScope, err := ccms.buildQueries(job, metrics, scopes, 0)
-	if err != nil {
-		cclog.Errorf("Error while building queries for jobId %d, Metrics %v, Scopes %v: %s", job.JobID, metrics, scopes, err.Error())
-		return nil, err
-	}
-
-	req := ApiQueryRequest{
-		Cluster:   job.Cluster,
-		From:      job.StartTime,
-		To:        job.StartTime + int64(job.Duration),
-		Queries:   queries,
-		WithStats: true,
-		WithData:  false,
-	}
-
-	resBody, err := ccms.doRequest(ctx, &req)
-	if err != nil {
-		cclog.Errorf("Error while performing request: %s", err.Error())
-		return nil, err
-	}
-
-	var errors []string
-	scopedJobStats := make(schema.ScopedJobStats)
-
-	for i, row := range resBody.Results {
-		query := req.Queries[i]
-		metric := ccms.toLocalName(query.Metric)
-		scope := assignedScope[i]
-
-		if _, ok := scopedJobStats[metric]; !ok {
-			scopedJobStats[metric] = make(map[schema.MetricScope][]*schema.ScopedStats)
-		}
-
-		if _, ok := scopedJobStats[metric][scope]; !ok {
-			scopedJobStats[metric][scope] = make([]*schema.ScopedStats, 0)
-		}
-
-		for ndx, res := range row {
-			if res.Error != nil {
-				/* Build list for "partial errors", if any */
-				errors = append(errors, fmt.Sprintf("failed to fetch '%s' from host '%s': %s", query.Metric, query.Hostname, *res.Error))
-				continue
-			}
-
-			id := (*string)(nil)
-			if query.Type != nil {
-				id = new(string)
-				*id = query.TypeIds[ndx]
-			}
-
-			if res.Avg.IsNaN() || res.Min.IsNaN() || res.Max.IsNaN() {
-				// "schema.Float()" because regular float64 can not be JSONed when NaN.
-				res.Avg = schema.Float(0)
-				res.Min = schema.Float(0)
-				res.Max = schema.Float(0)
-			}
-
-			scopedJobStats[metric][scope] = append(scopedJobStats[metric][scope], &schema.ScopedStats{
-				Hostname: query.Hostname,
-				Id:       id,
-				Data: &schema.MetricStatistics{
-					Avg: float64(res.Avg),
-					Min: float64(res.Min),
-					Max: float64(res.Max),
-				},
-			})
-		}
-
-		// So that one can later check len(scopedJobStats[metric][scope]): Remove from map if empty
-		if len(scopedJobStats[metric][scope]) == 0 {
-			delete(scopedJobStats[metric], scope)
-			if len(scopedJobStats[metric]) == 0 {
-				delete(scopedJobStats, metric)
-			}
-		}
-	}
-
-	if len(errors) != 0 {
-		/* Returns list for "partial errors" */
-		return scopedJobStats, fmt.Errorf("METRICDATA/CCMS > Errors: %s", strings.Join(errors, ", "))
-	}
-	return scopedJobStats, nil
-}
-
-// Used for Systems-View Node-Overview
-func (ccms *CCMetricStore) LoadNodeData(
-	cluster string,
-	metrics, nodes []string,
-	scopes []schema.MetricScope,
-	from, to time.Time,
-	ctx context.Context,
-) (map[string]map[string][]*schema.JobMetric, error) {
-	req := ApiQueryRequest{
-		Cluster:   cluster,
-		From:      from.Unix(),
-		To:        to.Unix(),
-		WithStats: true,
-		WithData:  true,
-	}
-
-	if nodes == nil {
-		for _, metric := range metrics {
-			req.ForAllNodes = append(req.ForAllNodes, ccms.toRemoteName(metric))
-		}
-	} else {
-		for _, node := range nodes {
-			for _, metric := range metrics {
-				req.Queries = append(req.Queries, ApiQuery{
-					Hostname:   node,
-					Metric:     ccms.toRemoteName(metric),
-					Resolution: 0, // Default for Node Queries: Will return metric $Timestep Resolution
-				})
-			}
-		}
-	}
-
-	resBody, err := ccms.doRequest(ctx, &req)
-	if err != nil {
-		cclog.Errorf("Error while performing request: %s", err.Error())
-		return nil, err
-	}
-
-	var errors []string
-	data := make(map[string]map[string][]*schema.JobMetric)
-	for i, res := range resBody.Results {
-		var query ApiQuery
-		if resBody.Queries != nil {
-			query = resBody.Queries[i]
-		} else {
-			query = req.Queries[i]
-		}
-
-		metric := ccms.toLocalName(query.Metric)
-		qdata := res[0]
-		if qdata.Error != nil {
-			/* Build list for "partial errors", if any */
-			errors = append(errors, fmt.Sprintf("fetching %s for node %s failed: %s", metric, query.Hostname, *qdata.Error))
-		}
-
-		if qdata.Avg.IsNaN() || qdata.Min.IsNaN() || qdata.Max.IsNaN() {
-			// return nil, fmt.Errorf("METRICDATA/CCMS > fetching %s for node %s failed: %s", metric, query.Hostname, "avg/min/max is NaN")
-			qdata.Avg, qdata.Min, qdata.Max = 0., 0., 0.
-		}
-
-		hostdata, ok := data[query.Hostname]
-		if !ok {
-			hostdata = make(map[string][]*schema.JobMetric)
-			data[query.Hostname] = hostdata
-		}
-
-		mc := archive.GetMetricConfig(cluster, metric)
-		if mc != nil {
-			hostdata[metric] = append(hostdata[metric], &schema.JobMetric{
-				Unit:     mc.Unit,
-				Timestep: mc.Timestep,
-				Series: []schema.Series{
-					{
-						Hostname: query.Hostname,
-						Data:     qdata.Data,
-						Statistics: schema.MetricStatistics{
-							Avg: float64(qdata.Avg),
-							Min: float64(qdata.Min),
-							Max: float64(qdata.Max),
-						},
-					},
-				},
-			})
-		} else {
-			cclog.Warnf("Metric '%s' not configured for cluster '%s': Skipped in LoadNodeData() Return!", metric, cluster)
-		}
-	}
-
-	if len(errors) != 0 {
-		/* Returns list of "partial errors" */
-		return data, fmt.Errorf("METRICDATA/CCMS > Errors: %s", strings.Join(errors, ", "))
-	}
-
-	return data, nil
-}
-
-// Used for Systems-View Node-List
-func (ccms *CCMetricStore) LoadNodeListData(
-	cluster, subCluster string,
-	nodes []string,
-	metrics []string,
-	scopes []schema.MetricScope,
-	resolution int,
-	from, to time.Time,
-	ctx context.Context,
-) (map[string]schema.JobData, error) {
-
-	// Note: Order of node data is not guaranteed after this point
-	queries, assignedScope, err := ccms.buildNodeQueries(cluster, subCluster, nodes, metrics, scopes, resolution)
-	if err != nil {
-		cclog.Errorf("Error while building node queries for Cluster %s, SubCLuster %s, Metrics %v, Scopes %v: %s", cluster, subCluster, metrics, scopes, err.Error())
-		return nil, err
-	}
-
-	req := ApiQueryRequest{
-		Cluster:   cluster,
-		Queries:   queries,
-		From:      from.Unix(),
-		To:        to.Unix(),
-		WithStats: true,
-		WithData:  true,
-	}
-
-	resBody, err := ccms.doRequest(ctx, &req)
-	if err != nil {
-		cclog.Errorf("Error while performing request: %s", err.Error())
-		return nil, err
-	}
-
-	var errors []string
-	data := make(map[string]schema.JobData)
-	for i, row := range resBody.Results {
-		var query ApiQuery
-		if resBody.Queries != nil {
-			query = resBody.Queries[i]
-		} else {
-			query = req.Queries[i]
-		}
-		// qdata := res[0]
-		metric := ccms.toLocalName(query.Metric)
-		scope := assignedScope[i]
-		mc := archive.GetMetricConfig(cluster, metric)
-
-		res := mc.Timestep
-		if len(row) > 0 {
-			res = row[0].Resolution
-		}
-
-		// Init Nested Map Data Structures If Not Found
-		hostData, ok := data[query.Hostname]
-		if !ok {
-			hostData = make(schema.JobData)
-			data[query.Hostname] = hostData
-		}
-
-		metricData, ok := hostData[metric]
-		if !ok {
-			metricData = make(map[schema.MetricScope]*schema.JobMetric)
-			data[query.Hostname][metric] = metricData
-		}
-
-		scopeData, ok := metricData[scope]
-		if !ok {
-			scopeData = &schema.JobMetric{
-				Unit:     mc.Unit,
-				Timestep: res,
-				Series:   make([]schema.Series, 0),
-			}
-			data[query.Hostname][metric][scope] = scopeData
-		}
-
-		for ndx, res := range row {
-			if res.Error != nil {
-				/* Build list for "partial errors", if any */
-				errors = append(errors, fmt.Sprintf("failed to fetch '%s' from host '%s': %s", query.Metric, query.Hostname, *res.Error))
-				continue
-			}
-
-			id := (*string)(nil)
-			if query.Type != nil {
-				id = new(string)
-				*id = query.TypeIds[ndx]
-			}
-
-			if res.Avg.IsNaN() || res.Min.IsNaN() || res.Max.IsNaN() {
-				// "schema.Float()" because regular float64 can not be JSONed when NaN.
-				res.Avg = schema.Float(0)
-				res.Min = schema.Float(0)
-				res.Max = schema.Float(0)
-			}
-
-			scopeData.Series = append(scopeData.Series, schema.Series{
-				Hostname: query.Hostname,
-				Id:       id,
-				Statistics: schema.MetricStatistics{
-					Avg: float64(res.Avg),
-					Min: float64(res.Min),
-					Max: float64(res.Max),
-				},
-				Data: res.Data,
-			})
-		}
-	}
-
-	if len(errors) != 0 {
-		/* Returns list of "partial errors" */
-		return data, fmt.Errorf("METRICDATA/CCMS > Errors: %s", strings.Join(errors, ", "))
-	}
-
-	return data, nil
-}
-
-func (ccms *CCMetricStore) buildNodeQueries(
-	cluster string,
-	subCluster string,
-	nodes []string,
-	metrics []string,
-	scopes []schema.MetricScope,
-	resolution int,
-) ([]ApiQuery, []schema.MetricScope, error) {
-
-	queries := make([]ApiQuery, 0, len(metrics)*len(scopes)*len(nodes))
-	assignedScope := []schema.MetricScope{}
-
-	// Get Topol before loop if subCluster given
-	var subClusterTopol *schema.SubCluster
-	var scterr error
-	if subCluster != "" {
-		subClusterTopol, scterr = archive.GetSubCluster(cluster, subCluster)
-		if scterr != nil {
-			cclog.Errorf("could not load cluster %s subCluster %s topology: %s", cluster, subCluster, scterr.Error())
-			return nil, nil, scterr
-		}
-	}
-
-	for _, metric := range metrics {
-		remoteName := ccms.toRemoteName(metric)
-		mc := archive.GetMetricConfig(cluster, metric)
-		if mc == nil {
-			// return nil, fmt.Errorf("METRICDATA/CCMS > metric '%s' is not specified for cluster '%s'", metric, cluster)
-			cclog.Warnf("metric '%s' is not specified for cluster '%s'", metric, cluster)
-			continue
-		}
-
-		// Skip if metric is removed for subcluster
-		if mc.SubClusters != nil {
-			isRemoved := false
-			for _, scConfig := range mc.SubClusters {
-				if scConfig.Name == subCluster && scConfig.Remove {
-					isRemoved = true
-					break
-				}
-			}
-			if isRemoved {
-				continue
-			}
-		}
-
-		// Avoid duplicates...
-		handledScopes := make([]schema.MetricScope, 0, 3)
-
-	scopesLoop:
-		for _, requestedScope := range scopes {
-			nativeScope := mc.Scope
-
-			scope := nativeScope.Max(requestedScope)
-			for _, s := range handledScopes {
-				if scope == s {
-					continue scopesLoop
-				}
-			}
-			handledScopes = append(handledScopes, scope)
-
-			for _, hostname := range nodes {
-
-				// If no subCluster given, get it by node
-				if subCluster == "" {
-					subClusterName, scnerr := archive.GetSubClusterByNode(cluster, hostname)
-					if scnerr != nil {
-						return nil, nil, scnerr
-					}
-					subClusterTopol, scterr = archive.GetSubCluster(cluster, subClusterName)
-					if scterr != nil {
-						return nil, nil, scterr
-					}
-				}
-
-				// Always full node hwthread id list, no partial queries expected -> Use "topology.Node" directly where applicable
-				// Always full accelerator id list, no partial queries expected -> Use "acceleratorIds" directly where applicable
-				topology := subClusterTopol.Topology
-				acceleratorIds := topology.GetAcceleratorIDs()
-
-				// Moved check here if metric matches hardware specs
-				if nativeScope == schema.MetricScopeAccelerator && len(acceleratorIds) == 0 {
-					continue scopesLoop
-				}
-
-				// Accelerator -> Accelerator (Use "accelerator" scope if requested scope is lower than node)
-				if nativeScope == schema.MetricScopeAccelerator && scope.LT(schema.MetricScopeNode) {
-					if scope != schema.MetricScopeAccelerator {
-						// Skip all other catched cases
-						continue
-					}
-
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Aggregate:  false,
-						Type:       &acceleratorString,
-						TypeIds:    acceleratorIds,
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, schema.MetricScopeAccelerator)
-					continue
-				}
-
-				// Accelerator -> Node
-				if nativeScope == schema.MetricScopeAccelerator && scope == schema.MetricScopeNode {
-					if len(acceleratorIds) == 0 {
-						continue
-					}
-
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Aggregate:  true,
-						Type:       &acceleratorString,
-						TypeIds:    acceleratorIds,
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// HWThread -> HWThead
-				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeHWThread {
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Aggregate:  false,
-						Type:       &hwthreadString,
-						TypeIds:    intToStringSlice(topology.Node),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// HWThread -> Core
-				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeCore {
-					cores, _ := topology.GetCoresFromHWThreads(topology.Node)
-					for _, core := range cores {
-						queries = append(queries, ApiQuery{
-							Metric:     remoteName,
-							Hostname:   hostname,
-							Aggregate:  true,
-							Type:       &hwthreadString,
-							TypeIds:    intToStringSlice(topology.Core[core]),
-							Resolution: resolution,
-						})
-						assignedScope = append(assignedScope, scope)
-					}
-					continue
-				}
-
-				// HWThread -> Socket
-				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeSocket {
-					sockets, _ := topology.GetSocketsFromHWThreads(topology.Node)
-					for _, socket := range sockets {
-						queries = append(queries, ApiQuery{
-							Metric:     remoteName,
-							Hostname:   hostname,
-							Aggregate:  true,
-							Type:       &hwthreadString,
-							TypeIds:    intToStringSlice(topology.Socket[socket]),
-							Resolution: resolution,
-						})
-						assignedScope = append(assignedScope, scope)
-					}
-					continue
-				}
-
-				// HWThread -> Node
-				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeNode {
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Aggregate:  true,
-						Type:       &hwthreadString,
-						TypeIds:    intToStringSlice(topology.Node),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// Core -> Core
-				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeCore {
-					cores, _ := topology.GetCoresFromHWThreads(topology.Node)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Aggregate:  false,
-						Type:       &coreString,
-						TypeIds:    intToStringSlice(cores),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// Core -> Socket
-				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeSocket {
-					sockets, _ := topology.GetSocketsFromCores(topology.Node)
-					for _, socket := range sockets {
-						queries = append(queries, ApiQuery{
-							Metric:     remoteName,
-							Hostname:   hostname,
-							Aggregate:  true,
-							Type:       &coreString,
-							TypeIds:    intToStringSlice(topology.Socket[socket]),
-							Resolution: resolution,
-						})
-						assignedScope = append(assignedScope, scope)
-					}
-					continue
-				}
-
-				// Core -> Node
-				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeNode {
-					cores, _ := topology.GetCoresFromHWThreads(topology.Node)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Aggregate:  true,
-						Type:       &coreString,
-						TypeIds:    intToStringSlice(cores),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// MemoryDomain -> MemoryDomain
-				if nativeScope == schema.MetricScopeMemoryDomain && scope == schema.MetricScopeMemoryDomain {
-					sockets, _ := topology.GetMemoryDomainsFromHWThreads(topology.Node)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Aggregate:  false,
-						Type:       &memoryDomainString,
-						TypeIds:    intToStringSlice(sockets),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// MemoryDoman -> Node
-				if nativeScope == schema.MetricScopeMemoryDomain && scope == schema.MetricScopeNode {
-					sockets, _ := topology.GetMemoryDomainsFromHWThreads(topology.Node)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Aggregate:  true,
-						Type:       &memoryDomainString,
-						TypeIds:    intToStringSlice(sockets),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// Socket -> Socket
-				if nativeScope == schema.MetricScopeSocket && scope == schema.MetricScopeSocket {
-					sockets, _ := topology.GetSocketsFromHWThreads(topology.Node)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Aggregate:  false,
-						Type:       &socketString,
-						TypeIds:    intToStringSlice(sockets),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// Socket -> Node
-				if nativeScope == schema.MetricScopeSocket && scope == schema.MetricScopeNode {
-					sockets, _ := topology.GetSocketsFromHWThreads(topology.Node)
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Aggregate:  true,
-						Type:       &socketString,
-						TypeIds:    intToStringSlice(sockets),
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				// Node -> Node
-				if nativeScope == schema.MetricScopeNode && scope == schema.MetricScopeNode {
-					queries = append(queries, ApiQuery{
-						Metric:     remoteName,
-						Hostname:   hostname,
-						Resolution: resolution,
-					})
-					assignedScope = append(assignedScope, scope)
-					continue
-				}
-
-				return nil, nil, fmt.Errorf("METRICDATA/CCMS > TODO: unhandled case: native-scope=%s, requested-scope=%s", nativeScope, requestedScope)
-			}
-		}
-	}
-
-	return queries, assignedScope, nil
-}
diff --git a/internal/metricdata/metricdata.go b/internal/metricdata/metricdata.go
deleted file mode 100644
index ab0e19fb..00000000
--- a/internal/metricdata/metricdata.go
+++ /dev/null
@@ -1,88 +0,0 @@
-// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved. This file is part of cc-backend.
-// Use of this source code is governed by a MIT-style
-// license that can be found in the LICENSE file.
-
-package metricdata
-
-import (
-	"context"
-	"encoding/json"
-	"fmt"
-	"time"
-
-	"github.com/ClusterCockpit/cc-backend/internal/config"
-	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
-	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/v2/schema"
-)
-
-type MetricDataRepository interface {
-	// Initialize this MetricDataRepository. One instance of
-	// this interface will only ever be responsible for one cluster.
-	Init(rawConfig json.RawMessage) error
-
-	// Return the JobData for the given job, only with the requested metrics.
-	LoadData(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error)
-
-	// Return a map of metrics to a map of nodes to the metric statistics of the job. node scope only.
-	LoadStats(job *schema.Job, metrics []string, ctx context.Context) (map[string]map[string]schema.MetricStatistics, error)
-
-	// Return a map of metrics to a map of scopes to the scoped metric statistics of the job.
-	LoadScopedStats(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context) (schema.ScopedJobStats, error)
-
-	// Return a map of hosts to a map of metrics at the requested scopes (currently only node) for that node.
-	LoadNodeData(cluster string, metrics, nodes []string, scopes []schema.MetricScope, from, to time.Time, ctx context.Context) (map[string]map[string][]*schema.JobMetric, error)
-
-	// Return a map of hosts to a map of metrics to a map of scopes for multiple nodes.
-	LoadNodeListData(cluster, subCluster string, nodes, metrics []string, scopes []schema.MetricScope, resolution int, from, to time.Time, ctx context.Context) (map[string]schema.JobData, error)
-}
-
-var metricDataRepos map[string]MetricDataRepository = map[string]MetricDataRepository{}
-
-func Init() error {
-	for _, cluster := range config.Clusters {
-		if cluster.MetricDataRepository != nil {
-			var kind struct {
-				Kind string `json:"kind"`
-			}
-			if err := json.Unmarshal(cluster.MetricDataRepository, &kind); err != nil {
-				cclog.Warn("Error while unmarshaling raw json MetricDataRepository")
-				return err
-			}
-
-			var mdr MetricDataRepository
-			switch kind.Kind {
-			case "cc-metric-store":
-				mdr = &CCMetricStore{}
-			case "cc-metric-store-internal":
-				mdr = &CCMetricStoreInternal{}
-				memorystore.InternalCCMSFlag = true
-			case "prometheus":
-				mdr = &PrometheusDataRepository{}
-			case "test":
-				mdr = &TestMetricDataRepository{}
-			default:
-				return fmt.Errorf("METRICDATA/METRICDATA > Unknown MetricDataRepository %v for cluster %v", kind.Kind, cluster.Name)
-			}
-
-			if err := mdr.Init(cluster.MetricDataRepository); err != nil {
-				cclog.Errorf("Error initializing MetricDataRepository %v for cluster %v", kind.Kind, cluster.Name)
-				return err
-			}
-			metricDataRepos[cluster.Name] = mdr
-		}
-	}
-	return nil
-}
-
-func GetMetricDataRepo(cluster string) (MetricDataRepository, error) {
-	var err error
-	repo, ok := metricDataRepos[cluster]
-
-	if !ok {
-		err = fmt.Errorf("METRICDATA/METRICDATA > no metric data repository configured for '%s'", cluster)
-	}
-
-	return repo, err
-}
diff --git a/internal/metricdata/prometheus.go b/internal/metricdata/prometheus.go
deleted file mode 100644
index 3fb94d51..00000000
--- a/internal/metricdata/prometheus.go
+++ /dev/null
@@ -1,587 +0,0 @@
-// Copyright (C) 2022 DKRZ
-// All rights reserved. This file is part of cc-backend.
-// Use of this source code is governed by a MIT-style
-// license that can be found in the LICENSE file.
-package metricdata
-
-import (
-	"bytes"
-	"context"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"math"
-	"net/http"
-	"os"
-	"regexp"
-	"sort"
-	"strings"
-	"sync"
-	"text/template"
-	"time"
-
-	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/v2/schema"
-	promapi "github.com/prometheus/client_golang/api"
-	promv1 "github.com/prometheus/client_golang/api/prometheus/v1"
-	promcfg "github.com/prometheus/common/config"
-	promm "github.com/prometheus/common/model"
-)
-
-type PrometheusDataRepositoryConfig struct {
-	Url       string            `json:"url"`
-	Username  string            `json:"username,omitempty"`
-	Suffix    string            `json:"suffix,omitempty"`
-	Templates map[string]string `json:"query-templates"`
-}
-
-type PrometheusDataRepository struct {
-	client      promapi.Client
-	queryClient promv1.API
-	suffix      string
-	templates   map[string]*template.Template
-}
-
-type PromQLArgs struct {
-	Nodes string
-}
-
-type Trie map[rune]Trie
-
-var logOnce sync.Once
-
-func contains(s []schema.MetricScope, str schema.MetricScope) bool {
-	for _, v := range s {
-		if v == str {
-			return true
-		}
-	}
-	return false
-}
-
-func MinMaxMean(data []schema.Float) (float64, float64, float64) {
-	if len(data) == 0 {
-		return 0.0, 0.0, 0.0
-	}
-	min := math.MaxFloat64
-	max := -math.MaxFloat64
-	var sum float64
-	var n float64
-	for _, val := range data {
-		if val.IsNaN() {
-			continue
-		}
-		sum += float64(val)
-		n += 1
-		if float64(val) > max {
-			max = float64(val)
-		}
-		if float64(val) < min {
-			min = float64(val)
-		}
-	}
-	return min, max, sum / n
-}
-
-// Rewritten from
-// https://github.com/ermanh/trieregex/blob/master/trieregex/trieregex.py
-func nodeRegex(nodes []string) string {
-	root := Trie{}
-	// add runes of each compute node to trie
-	for _, node := range nodes {
-		_trie := root
-		for _, c := range node {
-			if _, ok := _trie[c]; !ok {
-				_trie[c] = Trie{}
-			}
-			_trie = _trie[c]
-		}
-		_trie['*'] = Trie{}
-	}
-	// recursively build regex from rune trie
-	var trieRegex func(trie Trie, reset bool) string
-	trieRegex = func(trie Trie, reset bool) string {
-		if reset == true {
-			trie = root
-		}
-		if len(trie) == 0 {
-			return ""
-		}
-		if len(trie) == 1 {
-			for key, _trie := range trie {
-				if key == '*' {
-					return ""
-				}
-				return regexp.QuoteMeta(string(key)) + trieRegex(_trie, false)
-			}
-		} else {
-			sequences := []string{}
-			for key, _trie := range trie {
-				if key != '*' {
-					sequences = append(sequences, regexp.QuoteMeta(string(key))+trieRegex(_trie, false))
-				}
-			}
-			sort.Slice(sequences, func(i, j int) bool {
-				return (-len(sequences[i]) < -len(sequences[j])) || (sequences[i] < sequences[j])
-			})
-			var result string
-			// single edge from this tree node
-			if len(sequences) == 1 {
-				result = sequences[0]
-				if len(result) > 1 {
-					result = "(?:" + result + ")"
-				}
-				// multiple edges, each length 1
-			} else if s := strings.Join(sequences, ""); len(s) == len(sequences) {
-				// char or numeric range
-				if len(s)-1 == int(s[len(s)-1])-int(s[0]) {
-					result = fmt.Sprintf("[%c-%c]", s[0], s[len(s)-1])
-					// char or numeric set
-				} else {
-					result = "[" + s + "]"
-				}
-				// multiple edges of different lengths
-			} else {
-				result = "(?:" + strings.Join(sequences, "|") + ")"
-			}
-			if _, ok := trie['*']; ok {
-				result += "?"
-			}
-			return result
-		}
-		return ""
-	}
-	return trieRegex(root, true)
-}
-
-func (pdb *PrometheusDataRepository) Init(rawConfig json.RawMessage) error {
-	var config PrometheusDataRepositoryConfig
-	// parse config
-	if err := json.Unmarshal(rawConfig, &config); err != nil {
-		cclog.Warn("Error while unmarshaling raw json config")
-		return err
-	}
-	// support basic authentication
-	var rt http.RoundTripper = nil
-	if prom_pw := os.Getenv("PROMETHEUS_PASSWORD"); prom_pw != "" && config.Username != "" {
-		prom_pw := promcfg.Secret(prom_pw)
-		rt = promcfg.NewBasicAuthRoundTripper(promcfg.NewInlineSecret(config.Username), promcfg.NewInlineSecret(string(prom_pw)), promapi.DefaultRoundTripper)
-	} else {
-		if config.Username != "" {
-			return errors.New("METRICDATA/PROMETHEUS > Prometheus username provided, but PROMETHEUS_PASSWORD not set")
-		}
-	}
-	// init client
-	client, err := promapi.NewClient(promapi.Config{
-		Address:      config.Url,
-		RoundTripper: rt,
-	})
-	if err != nil {
-		cclog.Error("Error while initializing new prometheus client")
-		return err
-	}
-	// init query client
-	pdb.client = client
-	pdb.queryClient = promv1.NewAPI(pdb.client)
-	// site config
-	pdb.suffix = config.Suffix
-	// init query templates
-	pdb.templates = make(map[string]*template.Template)
-	for metric, templ := range config.Templates {
-		pdb.templates[metric], err = template.New(metric).Parse(templ)
-		if err == nil {
-			cclog.Debugf("Added PromQL template for %s: %s", metric, templ)
-		} else {
-			cclog.Warnf("Failed to parse PromQL template %s for metric %s", templ, metric)
-		}
-	}
-	return nil
-}
-
-// TODO: respect scope argument
-func (pdb *PrometheusDataRepository) FormatQuery(
-	metric string,
-	scope schema.MetricScope,
-	nodes []string,
-	cluster string,
-) (string, error) {
-	args := PromQLArgs{}
-	if len(nodes) > 0 {
-		args.Nodes = fmt.Sprintf("(%s)%s", nodeRegex(nodes), pdb.suffix)
-	} else {
-		args.Nodes = fmt.Sprintf(".*%s", pdb.suffix)
-	}
-
-	buf := &bytes.Buffer{}
-	if templ, ok := pdb.templates[metric]; ok {
-		err := templ.Execute(buf, args)
-		if err != nil {
-			return "", errors.New(fmt.Sprintf("METRICDATA/PROMETHEUS > Error compiling template %v", templ))
-		} else {
-			query := buf.String()
-			cclog.Debugf("PromQL: %s", query)
-			return query, nil
-		}
-	} else {
-		return "", errors.New(fmt.Sprintf("METRICDATA/PROMETHEUS > No PromQL for metric %s configured.", metric))
-	}
-}
-
-// Convert PromAPI row to CC schema.Series
-func (pdb *PrometheusDataRepository) RowToSeries(
-	from time.Time,
-	step int64,
-	steps int64,
-	row *promm.SampleStream,
-) schema.Series {
-	ts := from.Unix()
-	hostname := strings.TrimSuffix(string(row.Metric["exported_instance"]), pdb.suffix)
-	// init array of expected length with NaN
-	values := make([]schema.Float, steps+1)
-	for i := range values {
-		values[i] = schema.NaN
-	}
-	// copy recorded values from prom sample pair
-	for _, v := range row.Values {
-		idx := (v.Timestamp.Unix() - ts) / step
-		values[idx] = schema.Float(v.Value)
-	}
-	min, max, mean := MinMaxMean(values)
-	// output struct
-	return schema.Series{
-		Hostname: hostname,
-		Data:     values,
-		Statistics: schema.MetricStatistics{
-			Avg: mean,
-			Min: min,
-			Max: max,
-		},
-	}
-}
-
-func (pdb *PrometheusDataRepository) LoadData(
-	job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	ctx context.Context,
-	resolution int,
-) (schema.JobData, error) {
-	// TODO respect requested scope
-	if len(scopes) == 0 || !contains(scopes, schema.MetricScopeNode) {
-		scopes = append(scopes, schema.MetricScopeNode)
-	}
-
-	jobData := make(schema.JobData)
-	// parse job specs
-	nodes := make([]string, len(job.Resources))
-	for i, resource := range job.Resources {
-		nodes[i] = resource.Hostname
-	}
-	from := time.Unix(job.StartTime, 0)
-	to := time.Unix(job.StartTime+int64(job.Duration), 0)
-
-	for _, scope := range scopes {
-		if scope != schema.MetricScopeNode {
-			logOnce.Do(func() {
-				cclog.Infof("Scope '%s' requested, but not yet supported: Will return 'node' scope only.", scope)
-			})
-			continue
-		}
-
-		for _, metric := range metrics {
-			metricConfig := archive.GetMetricConfig(job.Cluster, metric)
-			if metricConfig == nil {
-				cclog.Warnf("Error in LoadData: Metric %s for cluster %s not configured", metric, job.Cluster)
-				return nil, errors.New("Prometheus config error")
-			}
-			query, err := pdb.FormatQuery(metric, scope, nodes, job.Cluster)
-			if err != nil {
-				cclog.Warn("Error while formatting prometheus query")
-				return nil, err
-			}
-
-			// ranged query over all job nodes
-			r := promv1.Range{
-				Start: from,
-				End:   to,
-				Step:  time.Duration(metricConfig.Timestep * 1e9),
-			}
-			result, warnings, err := pdb.queryClient.QueryRange(ctx, query, r)
-			if err != nil {
-				cclog.Errorf("Prometheus query error in LoadData: %v\nQuery: %s", err, query)
-				return nil, errors.New("Prometheus query error")
-			}
-			if len(warnings) > 0 {
-				cclog.Warnf("Warnings: %v\n", warnings)
-			}
-
-			// init data structures
-			if _, ok := jobData[metric]; !ok {
-				jobData[metric] = make(map[schema.MetricScope]*schema.JobMetric)
-			}
-			jobMetric, ok := jobData[metric][scope]
-			if !ok {
-				jobMetric = &schema.JobMetric{
-					Unit:     metricConfig.Unit,
-					Timestep: metricConfig.Timestep,
-					Series:   make([]schema.Series, 0),
-				}
-			}
-			step := int64(metricConfig.Timestep)
-			steps := int64(to.Sub(from).Seconds()) / step
-			// iter rows of host, metric, values
-			for _, row := range result.(promm.Matrix) {
-				jobMetric.Series = append(jobMetric.Series,
-					pdb.RowToSeries(from, step, steps, row))
-			}
-			// only add metric if at least one host returned data
-			if !ok && len(jobMetric.Series) > 0 {
-				jobData[metric][scope] = jobMetric
-			}
-			// sort by hostname to get uniform coloring
-			sort.Slice(jobMetric.Series, func(i, j int) bool {
-				return (jobMetric.Series[i].Hostname < jobMetric.Series[j].Hostname)
-			})
-		}
-	}
-	return jobData, nil
-}
-
-// TODO change implementation to precomputed/cached stats
-func (pdb *PrometheusDataRepository) LoadStats(
-	job *schema.Job,
-	metrics []string,
-	ctx context.Context,
-) (map[string]map[string]schema.MetricStatistics, error) {
-	// map of metrics of nodes of stats
-	stats := map[string]map[string]schema.MetricStatistics{}
-
-	data, err := pdb.LoadData(job, metrics, []schema.MetricScope{schema.MetricScopeNode}, ctx, 0 /*resolution here*/)
-	if err != nil {
-		cclog.Warn("Error while loading job for stats")
-		return nil, err
-	}
-	for metric, metricData := range data {
-		stats[metric] = make(map[string]schema.MetricStatistics)
-		for _, series := range metricData[schema.MetricScopeNode].Series {
-			stats[metric][series.Hostname] = series.Statistics
-		}
-	}
-
-	return stats, nil
-}
-
-func (pdb *PrometheusDataRepository) LoadNodeData(
-	cluster string,
-	metrics, nodes []string,
-	scopes []schema.MetricScope,
-	from, to time.Time,
-	ctx context.Context,
-) (map[string]map[string][]*schema.JobMetric, error) {
-	t0 := time.Now()
-	// Map of hosts of metrics of value slices
-	data := make(map[string]map[string][]*schema.JobMetric)
-	// query db for each metric
-	// TODO: scopes seems to be always empty
-	if len(scopes) == 0 || !contains(scopes, schema.MetricScopeNode) {
-		scopes = append(scopes, schema.MetricScopeNode)
-	}
-	for _, scope := range scopes {
-		if scope != schema.MetricScopeNode {
-			logOnce.Do(func() {
-				cclog.Infof("Note: Scope '%s' requested, but not yet supported: Will return 'node' scope only.", scope)
-			})
-			continue
-		}
-		for _, metric := range metrics {
-			metricConfig := archive.GetMetricConfig(cluster, metric)
-			if metricConfig == nil {
-				cclog.Warnf("Error in LoadNodeData: Metric %s for cluster %s not configured", metric, cluster)
-				return nil, errors.New("Prometheus config error")
-			}
-			query, err := pdb.FormatQuery(metric, scope, nodes, cluster)
-			if err != nil {
-				cclog.Warn("Error while formatting prometheus query")
-				return nil, err
-			}
-
-			// ranged query over all nodes
-			r := promv1.Range{
-				Start: from,
-				End:   to,
-				Step:  time.Duration(metricConfig.Timestep * 1e9),
-			}
-			result, warnings, err := pdb.queryClient.QueryRange(ctx, query, r)
-			if err != nil {
-				cclog.Errorf("Prometheus query error in LoadNodeData: %v\n", err)
-				return nil, errors.New("Prometheus query error")
-			}
-			if len(warnings) > 0 {
-				cclog.Warnf("Warnings: %v\n", warnings)
-			}
-
-			step := int64(metricConfig.Timestep)
-			steps := int64(to.Sub(from).Seconds()) / step
-
-			// iter rows of host, metric, values
-			for _, row := range result.(promm.Matrix) {
-				hostname := strings.TrimSuffix(string(row.Metric["exported_instance"]), pdb.suffix)
-				hostdata, ok := data[hostname]
-				if !ok {
-					hostdata = make(map[string][]*schema.JobMetric)
-					data[hostname] = hostdata
-				}
-				// output per host and metric
-				hostdata[metric] = append(hostdata[metric], &schema.JobMetric{
-					Unit:     metricConfig.Unit,
-					Timestep: metricConfig.Timestep,
-					Series:   []schema.Series{pdb.RowToSeries(from, step, steps, row)},
-				},
-				)
-			}
-		}
-	}
-	t1 := time.Since(t0)
-	cclog.Debugf("LoadNodeData of %v nodes took %s", len(data), t1)
-	return data, nil
-}
-
-// Implemented by NHR@FAU; Used in Job-View StatsTable
-func (pdb *PrometheusDataRepository) LoadScopedStats(
-	job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	ctx context.Context,
-) (schema.ScopedJobStats, error) {
-	// Assumption: pdb.loadData() only returns series node-scope - use node scope for statsTable
-	scopedJobStats := make(schema.ScopedJobStats)
-	data, err := pdb.LoadData(job, metrics, []schema.MetricScope{schema.MetricScopeNode}, ctx, 0 /*resolution here*/)
-	if err != nil {
-		cclog.Warn("Error while loading job for scopedJobStats")
-		return nil, err
-	}
-
-	for metric, metricData := range data {
-		for _, scope := range scopes {
-			if scope != schema.MetricScopeNode {
-				logOnce.Do(func() {
-					cclog.Infof("Note: Scope '%s' requested, but not yet supported: Will return 'node' scope only.", scope)
-				})
-				continue
-			}
-
-			if _, ok := scopedJobStats[metric]; !ok {
-				scopedJobStats[metric] = make(map[schema.MetricScope][]*schema.ScopedStats)
-			}
-
-			if _, ok := scopedJobStats[metric][scope]; !ok {
-				scopedJobStats[metric][scope] = make([]*schema.ScopedStats, 0)
-			}
-
-			for _, series := range metricData[scope].Series {
-				scopedJobStats[metric][scope] = append(scopedJobStats[metric][scope], &schema.ScopedStats{
-					Hostname: series.Hostname,
-					Data:     &series.Statistics,
-				})
-			}
-		}
-	}
-
-	return scopedJobStats, nil
-}
-
-// Implemented by NHR@FAU; Used in NodeList-View
-func (pdb *PrometheusDataRepository) LoadNodeListData(
-	cluster, subCluster string,
-	nodes []string,
-	metrics []string,
-	scopes []schema.MetricScope,
-	resolution int,
-	from, to time.Time,
-	ctx context.Context,
-) (map[string]schema.JobData, error) {
-	// Assumption: pdb.loadData() only returns series node-scope - use node scope for NodeList
-
-	// Fetch Data, based on pdb.LoadNodeData()
-	t0 := time.Now()
-	// Map of hosts of jobData
-	data := make(map[string]schema.JobData)
-
-	// query db for each metric
-	// TODO: scopes seems to be always empty
-	if len(scopes) == 0 || !contains(scopes, schema.MetricScopeNode) {
-		scopes = append(scopes, schema.MetricScopeNode)
-	}
-
-	for _, scope := range scopes {
-		if scope != schema.MetricScopeNode {
-			logOnce.Do(func() {
-				cclog.Infof("Note: Scope '%s' requested, but not yet supported: Will return 'node' scope only.", scope)
-			})
-			continue
-		}
-
-		for _, metric := range metrics {
-			metricConfig := archive.GetMetricConfig(cluster, metric)
-			if metricConfig == nil {
-				cclog.Warnf("Error in LoadNodeListData: Metric %s for cluster %s not configured", metric, cluster)
-				return nil, errors.New("Prometheus config error")
-			}
-			query, err := pdb.FormatQuery(metric, scope, nodes, cluster)
-			if err != nil {
-				cclog.Warn("Error while formatting prometheus query")
-				return nil, err
-			}
-
-			// ranged query over all nodes
-			r := promv1.Range{
-				Start: from,
-				End:   to,
-				Step:  time.Duration(metricConfig.Timestep * 1e9),
-			}
-			result, warnings, err := pdb.queryClient.QueryRange(ctx, query, r)
-			if err != nil {
-				cclog.Errorf("Prometheus query error in LoadNodeData: %v\n", err)
-				return nil, errors.New("Prometheus query error")
-			}
-			if len(warnings) > 0 {
-				cclog.Warnf("Warnings: %v\n", warnings)
-			}
-
-			step := int64(metricConfig.Timestep)
-			steps := int64(to.Sub(from).Seconds()) / step
-
-			// iter rows of host, metric, values
-			for _, row := range result.(promm.Matrix) {
-				hostname := strings.TrimSuffix(string(row.Metric["exported_instance"]), pdb.suffix)
-
-				hostdata, ok := data[hostname]
-				if !ok {
-					hostdata = make(schema.JobData)
-					data[hostname] = hostdata
-				}
-
-				metricdata, ok := hostdata[metric]
-				if !ok {
-					metricdata = make(map[schema.MetricScope]*schema.JobMetric)
-					data[hostname][metric] = metricdata
-				}
-
-				// output per host, metric and scope
-				scopeData, ok := metricdata[scope]
-				if !ok {
-					scopeData = &schema.JobMetric{
-						Unit:     metricConfig.Unit,
-						Timestep: metricConfig.Timestep,
-						Series:   []schema.Series{pdb.RowToSeries(from, step, steps, row)},
-					}
-					data[hostname][metric][scope] = scopeData
-				}
-			}
-		}
-	}
-	t1 := time.Since(t0)
-	cclog.Debugf("LoadNodeListData of %v nodes took %s", len(data), t1)
-	return data, nil
-}
diff --git a/internal/metricdata/utils.go b/internal/metricdata/utils.go
deleted file mode 100644
index 21dfbcac..00000000
--- a/internal/metricdata/utils.go
+++ /dev/null
@@ -1,118 +0,0 @@
-// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved. This file is part of cc-backend.
-// Use of this source code is governed by a MIT-style
-// license that can be found in the LICENSE file.
-
-package metricdata
-
-import (
-	"context"
-	"encoding/json"
-	"time"
-
-	"github.com/ClusterCockpit/cc-lib/v2/schema"
-)
-
-var TestLoadDataCallback func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) = func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) {
-	panic("TODO")
-}
-
-// TestMetricDataRepository is only a mock for unit-testing.
-type TestMetricDataRepository struct{}
-
-func (tmdr *TestMetricDataRepository) Init(_ json.RawMessage) error {
-	return nil
-}
-
-func (tmdr *TestMetricDataRepository) LoadData(
-	job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	ctx context.Context,
-	resolution int,
-) (schema.JobData, error) {
-	return TestLoadDataCallback(job, metrics, scopes, ctx, resolution)
-}
-
-func (tmdr *TestMetricDataRepository) LoadStats(
-	job *schema.Job,
-	metrics []string,
-	ctx context.Context,
-) (map[string]map[string]schema.MetricStatistics, error) {
-	panic("TODO")
-}
-
-func (tmdr *TestMetricDataRepository) LoadScopedStats(
-	job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	ctx context.Context,
-) (schema.ScopedJobStats, error) {
-	panic("TODO")
-}
-
-func (tmdr *TestMetricDataRepository) LoadNodeData(
-	cluster string,
-	metrics, nodes []string,
-	scopes []schema.MetricScope,
-	from, to time.Time,
-	ctx context.Context,
-) (map[string]map[string][]*schema.JobMetric, error) {
-	panic("TODO")
-}
-
-func (tmdr *TestMetricDataRepository) LoadNodeListData(
-	cluster, subCluster string,
-	nodes []string,
-	metrics []string,
-	scopes []schema.MetricScope,
-	resolution int,
-	from, to time.Time,
-	ctx context.Context,
-) (map[string]schema.JobData, error) {
-	panic("TODO")
-}
-
-func DeepCopy(jdTemp schema.JobData) schema.JobData {
-	jd := make(schema.JobData, len(jdTemp))
-	for k, v := range jdTemp {
-		jd[k] = make(map[schema.MetricScope]*schema.JobMetric, len(jdTemp[k]))
-		for k_, v_ := range v {
-			jd[k][k_] = new(schema.JobMetric)
-			jd[k][k_].Series = make([]schema.Series, len(v_.Series))
-			for i := 0; i < len(v_.Series); i += 1 {
-				jd[k][k_].Series[i].Data = make([]schema.Float, len(v_.Series[i].Data))
-				copy(jd[k][k_].Series[i].Data, v_.Series[i].Data)
-				jd[k][k_].Series[i].Hostname = v_.Series[i].Hostname
-				jd[k][k_].Series[i].Id = v_.Series[i].Id
-				jd[k][k_].Series[i].Statistics.Avg = v_.Series[i].Statistics.Avg
-				jd[k][k_].Series[i].Statistics.Min = v_.Series[i].Statistics.Min
-				jd[k][k_].Series[i].Statistics.Max = v_.Series[i].Statistics.Max
-			}
-			jd[k][k_].Timestep = v_.Timestep
-			jd[k][k_].Unit.Base = v_.Unit.Base
-			jd[k][k_].Unit.Prefix = v_.Unit.Prefix
-			if v_.StatisticsSeries != nil {
-				// Init Slices
-				jd[k][k_].StatisticsSeries = new(schema.StatsSeries)
-				jd[k][k_].StatisticsSeries.Max = make([]schema.Float, len(v_.StatisticsSeries.Max))
-				jd[k][k_].StatisticsSeries.Min = make([]schema.Float, len(v_.StatisticsSeries.Min))
-				jd[k][k_].StatisticsSeries.Median = make([]schema.Float, len(v_.StatisticsSeries.Median))
-				jd[k][k_].StatisticsSeries.Mean = make([]schema.Float, len(v_.StatisticsSeries.Mean))
-				// Copy Data
-				copy(jd[k][k_].StatisticsSeries.Max, v_.StatisticsSeries.Max)
-				copy(jd[k][k_].StatisticsSeries.Min, v_.StatisticsSeries.Min)
-				copy(jd[k][k_].StatisticsSeries.Median, v_.StatisticsSeries.Median)
-				copy(jd[k][k_].StatisticsSeries.Mean, v_.StatisticsSeries.Mean)
-				// Handle Percentiles
-				for k__, v__ := range v_.StatisticsSeries.Percentiles {
-					jd[k][k_].StatisticsSeries.Percentiles[k__] = make([]schema.Float, len(v__))
-					copy(jd[k][k_].StatisticsSeries.Percentiles[k__], v__)
-				}
-			} else {
-				jd[k][k_].StatisticsSeries = v_.StatisticsSeries
-			}
-		}
-	}
-	return jd
-}
diff --git a/internal/metricdispatch/dataLoader.go b/internal/metricdispatch/dataLoader.go
new file mode 100644
index 00000000..8bfebbd6
--- /dev/null
+++ b/internal/metricdispatch/dataLoader.go
@@ -0,0 +1,490 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+// Package metricdispatch provides a unified interface for loading and caching job metric data.
+//
+// This package serves as a central dispatcher that routes metric data requests to the appropriate
+// backend based on job state. For running jobs, data is fetched from the metric store (e.g., cc-metric-store).
+// For completed jobs, data is retrieved from the file-based job archive.
+//
+// # Key Features
+//
+//   - Automatic backend selection based on job state (running vs. archived)
+//   - LRU cache for performance optimization (128 MB default cache size)
+//   - Data resampling using Largest Triangle Three Bucket algorithm for archived data
+//   - Automatic statistics series generation for jobs with many nodes
+//   - Support for scoped metrics (node, socket, accelerator, core)
+//
+// # Cache Behavior
+//
+// Cached data has different TTL (time-to-live) values depending on job state:
+//   - Running jobs: 2 minutes (data changes frequently)
+//   - Completed jobs: 5 hours (data is static)
+//
+// The cache key is based on job ID, state, requested metrics, scopes, and resolution.
+//
+// # Usage
+//
+// The primary entry point is LoadData, which automatically handles both running and archived jobs:
+//
+//	jobData, err := metricdispatch.LoadData(job, metrics, scopes, ctx, resolution)
+//	if err != nil {
+//	    // Handle error
+//	}
+//
+// For statistics only, use LoadJobStats, LoadScopedJobStats, or LoadAverages depending on the required format.
+package metricdispatch
+
+import (
+	"context"
+	"fmt"
+	"math"
+	"time"
+
+	"github.com/ClusterCockpit/cc-backend/internal/config"
+	"github.com/ClusterCockpit/cc-backend/internal/metricstore"
+	"github.com/ClusterCockpit/cc-backend/pkg/archive"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/lrucache"
+	"github.com/ClusterCockpit/cc-lib/v2/resampler"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+)
+
+// cache is an LRU cache with 128 MB capacity for storing loaded job metric data.
+// The cache reduces load on both the metric store and archive backends.
+var cache *lrucache.Cache = lrucache.New(128 * 1024 * 1024)
+
+// cacheKey generates a unique cache key for a job's metric data based on job ID, state,
+// requested metrics, scopes, and resolution. Duration and StartTime are intentionally excluded
+// because job.ID is more unique and the cache TTL ensures entries don't persist indefinitely.
+func cacheKey(
+	job *schema.Job,
+	metrics []string,
+	scopes []schema.MetricScope,
+	resolution int,
+) string {
+	return fmt.Sprintf("%d(%s):[%v],[%v]-%d",
+		job.ID, job.State, metrics, scopes, resolution)
+}
+
+// LoadData retrieves metric data for a job from the appropriate backend (memory store for running jobs,
+// archive for completed jobs) and applies caching, resampling, and statistics generation as needed.
+//
+// For running jobs or when archive is disabled, data is fetched from the metric store.
+// For completed archived jobs, data is loaded from the job archive and resampled if needed.
+//
+// Parameters:
+//   - job: The job for which to load metric data
+//   - metrics: List of metric names to load (nil loads all metrics for the cluster)
+//   - scopes: Metric scopes to include (nil defaults to node scope)
+//   - ctx: Context for cancellation and timeouts
+//   - resolution: Target number of data points for resampling (only applies to archived data)
+//
+// Returns the loaded job data and any error encountered. For partial errors (some metrics failed),
+// the function returns the successfully loaded data with a warning logged.
+func LoadData(job *schema.Job,
+	metrics []string,
+	scopes []schema.MetricScope,
+	ctx context.Context,
+	resolution int,
+) (schema.JobData, error) {
+	data := cache.Get(cacheKey(job, metrics, scopes, resolution), func() (_ any, ttl time.Duration, size int) {
+		var jd schema.JobData
+		var err error
+
+		if job.State == schema.JobStateRunning ||
+			job.MonitoringStatus == schema.MonitoringStatusRunningOrArchiving ||
+			config.Keys.DisableArchive {
+
+			if scopes == nil {
+				scopes = append(scopes, schema.MetricScopeNode)
+			}
+
+			if metrics == nil {
+				cluster := archive.GetCluster(job.Cluster)
+				for _, mc := range cluster.MetricConfig {
+					metrics = append(metrics, mc.Name)
+				}
+			}
+
+			jd, err = metricstore.LoadData(job, metrics, scopes, ctx, resolution)
+			if err != nil {
+				if len(jd) != 0 {
+					cclog.Warnf("partial error loading metrics from store for job %d (user: %s, project: %s): %s",
+						job.JobID, job.User, job.Project, err.Error())
+				} else {
+					cclog.Errorf("failed to load job data from metric store for job %d (user: %s, project: %s): %s",
+						job.JobID, job.User, job.Project, err.Error())
+					return err, 0, 0
+				}
+			}
+			size = jd.Size()
+		} else {
+			var jdTemp schema.JobData
+			jdTemp, err = archive.GetHandle().LoadJobData(job)
+			if err != nil {
+				cclog.Errorf("failed to load job data from archive for job %d (user: %s, project: %s): %s",
+					job.JobID, job.User, job.Project, err.Error())
+				return err, 0, 0
+			}
+
+			jd = deepCopy(jdTemp)
+
+			// Resample archived data using Largest Triangle Three Bucket algorithm to reduce data points
+			// to the requested resolution, improving transfer performance and client-side rendering.
+			for _, v := range jd {
+				for _, v_ := range v {
+					timestep := int64(0)
+					for i := 0; i < len(v_.Series); i += 1 {
+						v_.Series[i].Data, timestep, err = resampler.LargestTriangleThreeBucket(v_.Series[i].Data, int64(v_.Timestep), int64(resolution))
+						if err != nil {
+							return err, 0, 0
+						}
+					}
+					v_.Timestep = int(timestep)
+				}
+			}
+
+			// Filter job data to only include requested metrics and scopes, avoiding unnecessary data transfer.
+			if metrics != nil || scopes != nil {
+				if metrics == nil {
+					metrics = make([]string, 0, len(jd))
+					for k := range jd {
+						metrics = append(metrics, k)
+					}
+				}
+
+				res := schema.JobData{}
+				for _, metric := range metrics {
+					if perscope, ok := jd[metric]; ok {
+						if len(perscope) > 1 {
+							subset := make(map[schema.MetricScope]*schema.JobMetric)
+							for _, scope := range scopes {
+								if jm, ok := perscope[scope]; ok {
+									subset[scope] = jm
+								}
+							}
+
+							if len(subset) > 0 {
+								perscope = subset
+							}
+						}
+
+						res[metric] = perscope
+					}
+				}
+				jd = res
+			}
+			size = jd.Size()
+		}
+
+		ttl = 5 * time.Hour
+		if job.State == schema.JobStateRunning {
+			ttl = 2 * time.Minute
+		}
+
+		// Generate statistics series for jobs with many nodes to enable min/median/max graphs
+		// instead of overwhelming the UI with individual node lines. Note that newly calculated
+		// statistics use min/median/max, while archived statistics may use min/mean/max.
+		const maxSeriesSize int = 15
+		for _, scopes := range jd {
+			for _, jm := range scopes {
+				if jm.StatisticsSeries != nil || len(jm.Series) <= maxSeriesSize {
+					continue
+				}
+
+				jm.AddStatisticsSeries()
+			}
+		}
+
+		nodeScopeRequested := false
+		for _, scope := range scopes {
+			if scope == schema.MetricScopeNode {
+				nodeScopeRequested = true
+			}
+		}
+
+		if nodeScopeRequested {
+			jd.AddNodeScope("flops_any")
+			jd.AddNodeScope("mem_bw")
+		}
+
+		// Round Resulting Stat Values
+		jd.RoundMetricStats()
+
+		return jd, ttl, size
+	})
+
+	if err, ok := data.(error); ok {
+		cclog.Errorf("error in cached dataset for job %d: %s", job.JobID, err.Error())
+		return nil, err
+	}
+
+	return data.(schema.JobData), nil
+}
+
+// LoadAverages computes average values for the specified metrics across all nodes of a job.
+// For running jobs, it loads statistics from the metric store. For completed jobs, it uses
+// the pre-calculated averages from the job archive. The results are appended to the data slice.
+func LoadAverages(
+	job *schema.Job,
+	metrics []string,
+	data [][]schema.Float,
+	ctx context.Context,
+) error {
+	if job.State != schema.JobStateRunning && !config.Keys.DisableArchive {
+		return archive.LoadAveragesFromArchive(job, metrics, data) // #166 change also here?
+	}
+
+	stats, err := metricstore.LoadStats(job, metrics, ctx)
+	if err != nil {
+		cclog.Errorf("failed to load statistics from metric store for job %d (user: %s, project: %s): %s",
+			job.JobID, job.User, job.Project, err.Error())
+		return err
+	}
+
+	for i, m := range metrics {
+		nodes, ok := stats[m]
+		if !ok {
+			data[i] = append(data[i], schema.NaN)
+			continue
+		}
+
+		sum := 0.0
+		for _, node := range nodes {
+			sum += node.Avg
+		}
+		data[i] = append(data[i], schema.Float(sum))
+	}
+
+	return nil
+}
+
+// LoadScopedJobStats retrieves job statistics organized by metric scope (node, socket, core, accelerator).
+// For running jobs, statistics are computed from the metric store. For completed jobs, pre-calculated
+// statistics are loaded from the job archive.
+func LoadScopedJobStats(
+	job *schema.Job,
+	metrics []string,
+	scopes []schema.MetricScope,
+	ctx context.Context,
+) (schema.ScopedJobStats, error) {
+	if job.State != schema.JobStateRunning && !config.Keys.DisableArchive {
+		return archive.LoadScopedStatsFromArchive(job, metrics, scopes)
+	}
+
+	scopedStats, err := metricstore.LoadScopedStats(job, metrics, scopes, ctx)
+	if err != nil {
+		cclog.Errorf("failed to load scoped statistics from metric store for job %d (user: %s, project: %s): %s",
+			job.JobID, job.User, job.Project, err.Error())
+		return nil, err
+	}
+
+	return scopedStats, nil
+}
+
+// LoadJobStats retrieves aggregated statistics (min/avg/max) for each requested metric across all job nodes.
+// For running jobs, statistics are computed from the metric store. For completed jobs, pre-calculated
+// statistics are loaded from the job archive.
+func LoadJobStats(
+	job *schema.Job,
+	metrics []string,
+	ctx context.Context,
+) (map[string]schema.MetricStatistics, error) {
+	if job.State != schema.JobStateRunning && !config.Keys.DisableArchive {
+		return archive.LoadStatsFromArchive(job, metrics)
+	}
+
+	data := make(map[string]schema.MetricStatistics, len(metrics))
+
+	stats, err := metricstore.LoadStats(job, metrics, ctx)
+	if err != nil {
+		cclog.Errorf("failed to load statistics from metric store for job %d (user: %s, project: %s): %s",
+			job.JobID, job.User, job.Project, err.Error())
+		return data, err
+	}
+
+	for _, m := range metrics {
+		sum, avg, min, max := 0.0, 0.0, 0.0, 0.0
+		nodes, ok := stats[m]
+		if !ok {
+			data[m] = schema.MetricStatistics{Min: min, Avg: avg, Max: max}
+			continue
+		}
+
+		for _, node := range nodes {
+			sum += node.Avg
+			min = math.Min(min, node.Min)
+			max = math.Max(max, node.Max)
+		}
+
+		data[m] = schema.MetricStatistics{
+			Avg: (math.Round((sum/float64(job.NumNodes))*100) / 100),
+			Min: (math.Round(min*100) / 100),
+			Max: (math.Round(max*100) / 100),
+		}
+	}
+
+	return data, nil
+}
+
+// LoadNodeData retrieves metric data for specific nodes in a cluster within a time range.
+// This is used for node monitoring views and system status pages. Data is always fetched from
+// the metric store (not the archive) since it's for current/recent node status monitoring.
+//
+// Returns a nested map structure: node -> metric -> scoped data.
+func LoadNodeData(
+	cluster string,
+	metrics, nodes []string,
+	scopes []schema.MetricScope,
+	from, to time.Time,
+	ctx context.Context,
+) (map[string]map[string][]*schema.JobMetric, error) {
+	if metrics == nil {
+		for _, m := range archive.GetCluster(cluster).MetricConfig {
+			metrics = append(metrics, m.Name)
+		}
+	}
+
+	data, err := metricstore.LoadNodeData(cluster, metrics, nodes, scopes, from, to, ctx)
+	if err != nil {
+		if len(data) != 0 {
+			cclog.Warnf("partial error loading node data from metric store for cluster %s: %s", cluster, err.Error())
+		} else {
+			cclog.Errorf("failed to load node data from metric store for cluster %s: %s", cluster, err.Error())
+			return nil, err
+		}
+	}
+
+	if data == nil {
+		return nil, fmt.Errorf("metric store for cluster '%s' does not support node data queries", cluster)
+	}
+
+	return data, nil
+}
+
+// LoadNodeListData retrieves time-series metric data for multiple nodes within a time range,
+// with optional resampling and automatic statistics generation for large datasets.
+// This is used for comparing multiple nodes or displaying node status over time.
+//
+// Returns a map of node names to their job-like metric data structures.
+func LoadNodeListData(
+	cluster, subCluster string,
+	nodes []string,
+	metrics []string,
+	scopes []schema.MetricScope,
+	resolution int,
+	from, to time.Time,
+	ctx context.Context,
+) (map[string]schema.JobData, error) {
+	if metrics == nil {
+		for _, m := range archive.GetCluster(cluster).MetricConfig {
+			metrics = append(metrics, m.Name)
+		}
+	}
+
+	data, err := metricstore.LoadNodeListData(cluster, subCluster, nodes, metrics, scopes, resolution, from, to, ctx)
+	if err != nil {
+		if len(data) != 0 {
+			cclog.Warnf("partial error loading node list data from metric store for cluster %s, subcluster %s: %s",
+				cluster, subCluster, err.Error())
+		} else {
+			cclog.Errorf("failed to load node list data from metric store for cluster %s, subcluster %s: %s",
+				cluster, subCluster, err.Error())
+			return nil, err
+		}
+	}
+
+	// Generate statistics series for datasets with many series to improve visualization performance.
+	// Statistics are calculated as min/median/max.
+	const maxSeriesSize int = 8
+	for _, jd := range data {
+		for _, scopes := range jd {
+			for _, jm := range scopes {
+				if jm.StatisticsSeries != nil || len(jm.Series) < maxSeriesSize {
+					continue
+				}
+				jm.AddStatisticsSeries()
+			}
+		}
+	}
+
+	if data == nil {
+		return nil, fmt.Errorf("metric store for cluster '%s' does not support node list queries", cluster)
+	}
+
+	return data, nil
+}
+
+// deepCopy creates a deep copy of JobData to prevent cache corruption when modifying
+// archived data (e.g., during resampling). This ensures the cached archive data remains
+// immutable while allowing per-request transformations.
+func deepCopy(source schema.JobData) schema.JobData {
+	result := make(schema.JobData, len(source))
+
+	for metricName, scopeMap := range source {
+		result[metricName] = make(map[schema.MetricScope]*schema.JobMetric, len(scopeMap))
+
+		for scope, jobMetric := range scopeMap {
+			result[metricName][scope] = copyJobMetric(jobMetric)
+		}
+	}
+
+	return result
+}
+
+func copyJobMetric(src *schema.JobMetric) *schema.JobMetric {
+	dst := &schema.JobMetric{
+		Timestep: src.Timestep,
+		Unit:     src.Unit,
+		Series:   make([]schema.Series, len(src.Series)),
+	}
+
+	for i := range src.Series {
+		dst.Series[i] = copySeries(&src.Series[i])
+	}
+
+	if src.StatisticsSeries != nil {
+		dst.StatisticsSeries = copyStatisticsSeries(src.StatisticsSeries)
+	}
+
+	return dst
+}
+
+func copySeries(src *schema.Series) schema.Series {
+	dst := schema.Series{
+		Hostname:   src.Hostname,
+		Id:         src.Id,
+		Statistics: src.Statistics,
+		Data:       make([]schema.Float, len(src.Data)),
+	}
+
+	copy(dst.Data, src.Data)
+	return dst
+}
+
+func copyStatisticsSeries(src *schema.StatsSeries) *schema.StatsSeries {
+	dst := &schema.StatsSeries{
+		Min:    make([]schema.Float, len(src.Min)),
+		Mean:   make([]schema.Float, len(src.Mean)),
+		Median: make([]schema.Float, len(src.Median)),
+		Max:    make([]schema.Float, len(src.Max)),
+	}
+
+	copy(dst.Min, src.Min)
+	copy(dst.Mean, src.Mean)
+	copy(dst.Median, src.Median)
+	copy(dst.Max, src.Max)
+
+	if len(src.Percentiles) > 0 {
+		dst.Percentiles = make(map[int][]schema.Float, len(src.Percentiles))
+		for percentile, values := range src.Percentiles {
+			dst.Percentiles[percentile] = make([]schema.Float, len(values))
+			copy(dst.Percentiles[percentile], values)
+		}
+	}
+
+	return dst
+}
diff --git a/internal/metricdispatch/dataLoader_test.go b/internal/metricdispatch/dataLoader_test.go
new file mode 100644
index 00000000..c4841f8d
--- /dev/null
+++ b/internal/metricdispatch/dataLoader_test.go
@@ -0,0 +1,125 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package metricdispatch
+
+import (
+	"testing"
+
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+)
+
+func TestDeepCopy(t *testing.T) {
+	nodeId := "0"
+	original := schema.JobData{
+		"cpu_load": {
+			schema.MetricScopeNode: &schema.JobMetric{
+				Timestep: 60,
+				Unit:     schema.Unit{Base: "load", Prefix: ""},
+				Series: []schema.Series{
+					{
+						Hostname: "node001",
+						Id:       &nodeId,
+						Data:     []schema.Float{1.0, 2.0, 3.0},
+						Statistics: schema.MetricStatistics{
+							Min: 1.0,
+							Avg: 2.0,
+							Max: 3.0,
+						},
+					},
+				},
+				StatisticsSeries: &schema.StatsSeries{
+					Min:    []schema.Float{1.0, 1.5, 2.0},
+					Mean:   []schema.Float{2.0, 2.5, 3.0},
+					Median: []schema.Float{2.0, 2.5, 3.0},
+					Max:    []schema.Float{3.0, 3.5, 4.0},
+					Percentiles: map[int][]schema.Float{
+						25: {1.5, 2.0, 2.5},
+						75: {2.5, 3.0, 3.5},
+					},
+				},
+			},
+		},
+	}
+
+	copied := deepCopy(original)
+
+	original["cpu_load"][schema.MetricScopeNode].Series[0].Data[0] = 999.0
+	original["cpu_load"][schema.MetricScopeNode].StatisticsSeries.Min[0] = 888.0
+	original["cpu_load"][schema.MetricScopeNode].StatisticsSeries.Percentiles[25][0] = 777.0
+
+	if copied["cpu_load"][schema.MetricScopeNode].Series[0].Data[0] != 1.0 {
+		t.Errorf("Series data was not deeply copied: got %v, want 1.0",
+			copied["cpu_load"][schema.MetricScopeNode].Series[0].Data[0])
+	}
+
+	if copied["cpu_load"][schema.MetricScopeNode].StatisticsSeries.Min[0] != 1.0 {
+		t.Errorf("StatisticsSeries was not deeply copied: got %v, want 1.0",
+			copied["cpu_load"][schema.MetricScopeNode].StatisticsSeries.Min[0])
+	}
+
+	if copied["cpu_load"][schema.MetricScopeNode].StatisticsSeries.Percentiles[25][0] != 1.5 {
+		t.Errorf("Percentiles was not deeply copied: got %v, want 1.5",
+			copied["cpu_load"][schema.MetricScopeNode].StatisticsSeries.Percentiles[25][0])
+	}
+
+	if copied["cpu_load"][schema.MetricScopeNode].Timestep != 60 {
+		t.Errorf("Timestep not copied correctly: got %v, want 60",
+			copied["cpu_load"][schema.MetricScopeNode].Timestep)
+	}
+
+	if copied["cpu_load"][schema.MetricScopeNode].Series[0].Hostname != "node001" {
+		t.Errorf("Hostname not copied correctly: got %v, want node001",
+			copied["cpu_load"][schema.MetricScopeNode].Series[0].Hostname)
+	}
+}
+
+func TestDeepCopyNilStatisticsSeries(t *testing.T) {
+	original := schema.JobData{
+		"mem_used": {
+			schema.MetricScopeNode: &schema.JobMetric{
+				Timestep: 60,
+				Series: []schema.Series{
+					{
+						Hostname: "node001",
+						Data:     []schema.Float{1.0, 2.0},
+					},
+				},
+				StatisticsSeries: nil,
+			},
+		},
+	}
+
+	copied := deepCopy(original)
+
+	if copied["mem_used"][schema.MetricScopeNode].StatisticsSeries != nil {
+		t.Errorf("StatisticsSeries should be nil, got %v",
+			copied["mem_used"][schema.MetricScopeNode].StatisticsSeries)
+	}
+}
+
+func TestDeepCopyEmptyPercentiles(t *testing.T) {
+	original := schema.JobData{
+		"cpu_load": {
+			schema.MetricScopeNode: &schema.JobMetric{
+				Timestep: 60,
+				Series:   []schema.Series{},
+				StatisticsSeries: &schema.StatsSeries{
+					Min:         []schema.Float{1.0},
+					Mean:        []schema.Float{2.0},
+					Median:      []schema.Float{2.0},
+					Max:         []schema.Float{3.0},
+					Percentiles: nil,
+				},
+			},
+		},
+	}
+
+	copied := deepCopy(original)
+
+	if copied["cpu_load"][schema.MetricScopeNode].StatisticsSeries.Percentiles != nil {
+		t.Errorf("Percentiles should be nil when source is nil/empty")
+	}
+}
diff --git a/internal/memorystore/api.go b/internal/metricstore/api.go
similarity index 98%
rename from internal/memorystore/api.go
rename to internal/metricstore/api.go
index 41c53a18..d8a2ea82 100644
--- a/internal/memorystore/api.go
+++ b/internal/metricstore/api.go
@@ -3,10 +3,11 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"errors"
+	"fmt"
 	"math"
 
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
@@ -124,6 +125,9 @@ func FetchData(req APIQueryRequest) (*APIQueryResponse, error) {
 
 	req.WithData = true
 	ms := GetMemoryStore()
+	if ms == nil {
+		return nil, fmt.Errorf("memorystore not initialized")
+	}
 
 	response := APIQueryResponse{
 		Results: make([][]APIMetricData, 0, len(req.Queries)),
diff --git a/internal/memorystore/archive.go b/internal/metricstore/archive.go
similarity index 99%
rename from internal/memorystore/archive.go
rename to internal/metricstore/archive.go
index fc46dac6..972769fd 100644
--- a/internal/memorystore/archive.go
+++ b/internal/metricstore/archive.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"archive/zip"
diff --git a/internal/memorystore/avroCheckpoint.go b/internal/metricstore/avroCheckpoint.go
similarity index 99%
rename from internal/memorystore/avroCheckpoint.go
rename to internal/metricstore/avroCheckpoint.go
index b0b0cf42..275a64bd 100644
--- a/internal/memorystore/avroCheckpoint.go
+++ b/internal/metricstore/avroCheckpoint.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"bufio"
diff --git a/internal/memorystore/avroHelper.go b/internal/metricstore/avroHelper.go
similarity index 99%
rename from internal/memorystore/avroHelper.go
rename to internal/metricstore/avroHelper.go
index 93a293bd..5587a58d 100644
--- a/internal/memorystore/avroHelper.go
+++ b/internal/metricstore/avroHelper.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"context"
diff --git a/internal/memorystore/avroStruct.go b/internal/metricstore/avroStruct.go
similarity index 99%
rename from internal/memorystore/avroStruct.go
rename to internal/metricstore/avroStruct.go
index 2643a9a7..78a8d137 100644
--- a/internal/memorystore/avroStruct.go
+++ b/internal/metricstore/avroStruct.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"sync"
diff --git a/internal/memorystore/buffer.go b/internal/metricstore/buffer.go
similarity index 99%
rename from internal/memorystore/buffer.go
rename to internal/metricstore/buffer.go
index 15e29b3a..94d3ce76 100644
--- a/internal/memorystore/buffer.go
+++ b/internal/metricstore/buffer.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"errors"
diff --git a/internal/memorystore/checkpoint.go b/internal/metricstore/checkpoint.go
similarity index 99%
rename from internal/memorystore/checkpoint.go
rename to internal/metricstore/checkpoint.go
index c48c2fd8..27d611c4 100644
--- a/internal/memorystore/checkpoint.go
+++ b/internal/metricstore/checkpoint.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"bufio"
diff --git a/internal/memorystore/config.go b/internal/metricstore/config.go
similarity index 98%
rename from internal/memorystore/config.go
rename to internal/metricstore/config.go
index fbd62341..97f16c46 100644
--- a/internal/memorystore/config.go
+++ b/internal/metricstore/config.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"fmt"
@@ -19,8 +19,6 @@ const (
 	DefaultAvroCheckpointInterval = time.Minute
 )
 
-var InternalCCMSFlag bool = false
-
 type MetricStoreConfig struct {
 	// Number of concurrent workers for checkpoint and archive operations.
 	// If not set or 0, defaults to min(runtime.NumCPU()/2+1, 10)
diff --git a/internal/memorystore/configSchema.go b/internal/metricstore/configSchema.go
similarity index 99%
rename from internal/memorystore/configSchema.go
rename to internal/metricstore/configSchema.go
index 2616edc6..f1a20a73 100644
--- a/internal/memorystore/configSchema.go
+++ b/internal/metricstore/configSchema.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 const configSchema = `{
     "type": "object",
diff --git a/internal/memorystore/debug.go b/internal/metricstore/debug.go
similarity index 99%
rename from internal/memorystore/debug.go
rename to internal/metricstore/debug.go
index b56cf254..50c91e08 100644
--- a/internal/memorystore/debug.go
+++ b/internal/metricstore/debug.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"bufio"
diff --git a/internal/memorystore/healthcheck.go b/internal/metricstore/healthcheck.go
similarity index 99%
rename from internal/memorystore/healthcheck.go
rename to internal/metricstore/healthcheck.go
index b1052f3b..2a49c47a 100644
--- a/internal/memorystore/healthcheck.go
+++ b/internal/metricstore/healthcheck.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"bufio"
diff --git a/internal/memorystore/level.go b/internal/metricstore/level.go
similarity index 99%
rename from internal/memorystore/level.go
rename to internal/metricstore/level.go
index bce2a7a6..d46f893a 100644
--- a/internal/memorystore/level.go
+++ b/internal/metricstore/level.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"sync"
diff --git a/internal/memorystore/lineprotocol.go b/internal/metricstore/lineprotocol.go
similarity index 99%
rename from internal/memorystore/lineprotocol.go
rename to internal/metricstore/lineprotocol.go
index ca8cc811..cc59e213 100644
--- a/internal/memorystore/lineprotocol.go
+++ b/internal/metricstore/lineprotocol.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"context"
diff --git a/internal/memorystore/memorystore.go b/internal/metricstore/memorystore.go
similarity index 99%
rename from internal/memorystore/memorystore.go
rename to internal/metricstore/memorystore.go
index 7c5ea0eb..14a02fcd 100644
--- a/internal/memorystore/memorystore.go
+++ b/internal/metricstore/memorystore.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-// Package memorystore provides an efficient in-memory time-series metric storage system
+// Package metricstore provides an efficient in-memory time-series metric storage system
 // with support for hierarchical data organization, checkpointing, and archiving.
 //
 // The package organizes metrics in a tree structure (cluster → host → component) and
@@ -17,7 +17,7 @@
 //   - Concurrent checkpoint/archive workers
 //   - Support for sum and average aggregation
 //   - NATS integration for metric ingestion
-package memorystore
+package metricstore
 
 import (
 	"bytes"
diff --git a/internal/memorystore/memorystore_test.go b/internal/metricstore/memorystore_test.go
similarity index 99%
rename from internal/memorystore/memorystore_test.go
rename to internal/metricstore/memorystore_test.go
index 57ea6938..29379d21 100644
--- a/internal/memorystore/memorystore_test.go
+++ b/internal/metricstore/memorystore_test.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"testing"
diff --git a/internal/metricdata/cc-metric-store-internal.go b/internal/metricstore/query.go
similarity index 87%
rename from internal/metricdata/cc-metric-store-internal.go
rename to internal/metricstore/query.go
index 741ce358..78c78dd5 100644
--- a/internal/metricdata/cc-metric-store-internal.go
+++ b/internal/metricstore/query.go
@@ -3,56 +3,41 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package metricdata
+package metricstore
 
 import (
 	"context"
-	"encoding/json"
 	"fmt"
 	"strconv"
 	"strings"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
 	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
-// Bloat Code
-type CCMetricStoreConfigInternal struct {
-	Kind  string `json:"kind"`
-	Url   string `json:"url"`
-	Token string `json:"token"`
+// TestLoadDataCallback allows tests to override LoadData behavior
+var TestLoadDataCallback func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error)
 
-	// If metrics are known to this MetricDataRepository under a different
-	// name than in the `metricConfig` section of the 'cluster.json',
-	// provide this optional mapping of local to remote name for this metric.
-	Renamings map[string]string `json:"metricRenamings"`
-}
-
-// Bloat Code
-type CCMetricStoreInternal struct{}
-
-// Bloat Code
-func (ccms *CCMetricStoreInternal) Init(rawConfig json.RawMessage) error {
-	return nil
-}
-
-func (ccms *CCMetricStoreInternal) LoadData(
+func LoadData(
 	job *schema.Job,
 	metrics []string,
 	scopes []schema.MetricScope,
 	ctx context.Context,
 	resolution int,
 ) (schema.JobData, error) {
-	queries, assignedScope, err := ccms.buildQueries(job, metrics, scopes, int64(resolution))
+	if TestLoadDataCallback != nil {
+		return TestLoadDataCallback(job, metrics, scopes, ctx, resolution)
+	}
+
+	queries, assignedScope, err := buildQueries(job, metrics, scopes, int64(resolution))
 	if err != nil {
 		cclog.Errorf("Error while building queries for jobId %d, Metrics %v, Scopes %v: %s", job.JobID, metrics, scopes, err.Error())
 		return nil, err
 	}
 
-	req := memorystore.APIQueryRequest{
+	req := APIQueryRequest{
 		Cluster:   job.Cluster,
 		From:      job.StartTime,
 		To:        job.StartTime + int64(job.Duration),
@@ -61,7 +46,7 @@ func (ccms *CCMetricStoreInternal) LoadData(
 		WithData:  true,
 	}
 
-	resBody, err := memorystore.FetchData(req)
+	resBody, err := FetchData(req)
 	if err != nil {
 		cclog.Errorf("Error while fetching data : %s", err.Error())
 		return nil, err
@@ -149,13 +134,13 @@ var (
 	acceleratorString  = string(schema.MetricScopeAccelerator)
 )
 
-func (ccms *CCMetricStoreInternal) buildQueries(
+func buildQueries(
 	job *schema.Job,
 	metrics []string,
 	scopes []schema.MetricScope,
 	resolution int64,
-) ([]memorystore.APIQuery, []schema.MetricScope, error) {
-	queries := make([]memorystore.APIQuery, 0, len(metrics)*len(scopes)*len(job.Resources))
+) ([]APIQuery, []schema.MetricScope, error) {
+	queries := make([]APIQuery, 0, len(metrics)*len(scopes)*len(job.Resources))
 	assignedScope := []schema.MetricScope{}
 
 	subcluster, scerr := archive.GetSubCluster(job.Cluster, job.SubCluster)
@@ -217,7 +202,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 						continue
 					}
 
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Aggregate:  false,
@@ -235,7 +220,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 						continue
 					}
 
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Aggregate:  true,
@@ -249,7 +234,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 
 				// HWThread -> HWThead
 				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeHWThread {
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Aggregate:  false,
@@ -265,7 +250,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeCore {
 					cores, _ := topology.GetCoresFromHWThreads(hwthreads)
 					for _, core := range cores {
-						queries = append(queries, memorystore.APIQuery{
+						queries = append(queries, APIQuery{
 							Metric:     metric,
 							Hostname:   host.Hostname,
 							Aggregate:  true,
@@ -282,7 +267,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeSocket {
 					sockets, _ := topology.GetSocketsFromHWThreads(hwthreads)
 					for _, socket := range sockets {
-						queries = append(queries, memorystore.APIQuery{
+						queries = append(queries, APIQuery{
 							Metric:     metric,
 							Hostname:   host.Hostname,
 							Aggregate:  true,
@@ -297,7 +282,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 
 				// HWThread -> Node
 				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeNode {
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Aggregate:  true,
@@ -312,7 +297,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 				// Core -> Core
 				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeCore {
 					cores, _ := topology.GetCoresFromHWThreads(hwthreads)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Aggregate:  false,
@@ -328,7 +313,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeSocket {
 					sockets, _ := topology.GetSocketsFromCores(hwthreads)
 					for _, socket := range sockets {
-						queries = append(queries, memorystore.APIQuery{
+						queries = append(queries, APIQuery{
 							Metric:     metric,
 							Hostname:   host.Hostname,
 							Aggregate:  true,
@@ -344,7 +329,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 				// Core -> Node
 				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeNode {
 					cores, _ := topology.GetCoresFromHWThreads(hwthreads)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Aggregate:  true,
@@ -359,7 +344,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 				// MemoryDomain -> MemoryDomain
 				if nativeScope == schema.MetricScopeMemoryDomain && scope == schema.MetricScopeMemoryDomain {
 					sockets, _ := topology.GetMemoryDomainsFromHWThreads(hwthreads)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Aggregate:  false,
@@ -374,7 +359,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 				// MemoryDoman -> Node
 				if nativeScope == schema.MetricScopeMemoryDomain && scope == schema.MetricScopeNode {
 					sockets, _ := topology.GetMemoryDomainsFromHWThreads(hwthreads)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Aggregate:  true,
@@ -389,7 +374,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 				// Socket -> Socket
 				if nativeScope == schema.MetricScopeSocket && scope == schema.MetricScopeSocket {
 					sockets, _ := topology.GetSocketsFromHWThreads(hwthreads)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Aggregate:  false,
@@ -404,7 +389,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 				// Socket -> Node
 				if nativeScope == schema.MetricScopeSocket && scope == schema.MetricScopeNode {
 					sockets, _ := topology.GetSocketsFromHWThreads(hwthreads)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Aggregate:  true,
@@ -418,7 +403,7 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 
 				// Node -> Node
 				if nativeScope == schema.MetricScopeNode && scope == schema.MetricScopeNode {
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   host.Hostname,
 						Resolution: resolution,
@@ -435,18 +420,18 @@ func (ccms *CCMetricStoreInternal) buildQueries(
 	return queries, assignedScope, nil
 }
 
-func (ccms *CCMetricStoreInternal) LoadStats(
+func LoadStats(
 	job *schema.Job,
 	metrics []string,
 	ctx context.Context,
 ) (map[string]map[string]schema.MetricStatistics, error) {
-	queries, _, err := ccms.buildQueries(job, metrics, []schema.MetricScope{schema.MetricScopeNode}, 0) // #166 Add scope shere for analysis view accelerator normalization?
+	queries, _, err := buildQueries(job, metrics, []schema.MetricScope{schema.MetricScopeNode}, 0) // #166 Add scope shere for analysis view accelerator normalization?
 	if err != nil {
 		cclog.Errorf("Error while building queries for jobId %d, Metrics %v: %s", job.JobID, metrics, err.Error())
 		return nil, err
 	}
 
-	req := memorystore.APIQueryRequest{
+	req := APIQueryRequest{
 		Cluster:   job.Cluster,
 		From:      job.StartTime,
 		To:        job.StartTime + int64(job.Duration),
@@ -455,7 +440,7 @@ func (ccms *CCMetricStoreInternal) LoadStats(
 		WithData:  false,
 	}
 
-	resBody, err := memorystore.FetchData(req)
+	resBody, err := FetchData(req)
 	if err != nil {
 		cclog.Errorf("Error while fetching data : %s", err.Error())
 		return nil, err
@@ -492,20 +477,19 @@ func (ccms *CCMetricStoreInternal) LoadStats(
 	return stats, nil
 }
 
-// Used for Job-View Statistics Table
-func (ccms *CCMetricStoreInternal) LoadScopedStats(
+func LoadScopedStats(
 	job *schema.Job,
 	metrics []string,
 	scopes []schema.MetricScope,
 	ctx context.Context,
 ) (schema.ScopedJobStats, error) {
-	queries, assignedScope, err := ccms.buildQueries(job, metrics, scopes, 0)
+	queries, assignedScope, err := buildQueries(job, metrics, scopes, 0)
 	if err != nil {
 		cclog.Errorf("Error while building queries for jobId %d, Metrics %v, Scopes %v: %s", job.JobID, metrics, scopes, err.Error())
 		return nil, err
 	}
 
-	req := memorystore.APIQueryRequest{
+	req := APIQueryRequest{
 		Cluster:   job.Cluster,
 		From:      job.StartTime,
 		To:        job.StartTime + int64(job.Duration),
@@ -514,7 +498,7 @@ func (ccms *CCMetricStoreInternal) LoadScopedStats(
 		WithData:  false,
 	}
 
-	resBody, err := memorystore.FetchData(req)
+	resBody, err := FetchData(req)
 	if err != nil {
 		cclog.Errorf("Error while fetching data : %s", err.Error())
 		return nil, err
@@ -583,15 +567,14 @@ func (ccms *CCMetricStoreInternal) LoadScopedStats(
 	return scopedJobStats, nil
 }
 
-// Used for Systems-View Node-Overview
-func (ccms *CCMetricStoreInternal) LoadNodeData(
+func LoadNodeData(
 	cluster string,
 	metrics, nodes []string,
 	scopes []schema.MetricScope,
 	from, to time.Time,
 	ctx context.Context,
 ) (map[string]map[string][]*schema.JobMetric, error) {
-	req := memorystore.APIQueryRequest{
+	req := APIQueryRequest{
 		Cluster:   cluster,
 		From:      from.Unix(),
 		To:        to.Unix(),
@@ -604,7 +587,7 @@ func (ccms *CCMetricStoreInternal) LoadNodeData(
 	} else {
 		for _, node := range nodes {
 			for _, metric := range metrics {
-				req.Queries = append(req.Queries, memorystore.APIQuery{
+				req.Queries = append(req.Queries, APIQuery{
 					Hostname:   node,
 					Metric:     metric,
 					Resolution: 0, // Default for Node Queries: Will return metric $Timestep Resolution
@@ -613,7 +596,7 @@ func (ccms *CCMetricStoreInternal) LoadNodeData(
 		}
 	}
 
-	resBody, err := memorystore.FetchData(req)
+	resBody, err := FetchData(req)
 	if err != nil {
 		cclog.Errorf("Error while fetching data : %s", err.Error())
 		return nil, err
@@ -622,7 +605,7 @@ func (ccms *CCMetricStoreInternal) LoadNodeData(
 	var errors []string
 	data := make(map[string]map[string][]*schema.JobMetric)
 	for i, res := range resBody.Results {
-		var query memorystore.APIQuery
+		var query APIQuery
 		if resBody.Queries != nil {
 			query = resBody.Queries[i]
 		} else {
@@ -673,8 +656,7 @@ func (ccms *CCMetricStoreInternal) LoadNodeData(
 	return data, nil
 }
 
-// Used for Systems-View Node-List
-func (ccms *CCMetricStoreInternal) LoadNodeListData(
+func LoadNodeListData(
 	cluster, subCluster string,
 	nodes []string,
 	metrics []string,
@@ -683,15 +665,14 @@ func (ccms *CCMetricStoreInternal) LoadNodeListData(
 	from, to time.Time,
 	ctx context.Context,
 ) (map[string]schema.JobData, error) {
-
 	// Note: Order of node data is not guaranteed after this point
-	queries, assignedScope, err := ccms.buildNodeQueries(cluster, subCluster, nodes, metrics, scopes, int64(resolution))
+	queries, assignedScope, err := buildNodeQueries(cluster, subCluster, nodes, metrics, scopes, int64(resolution))
 	if err != nil {
 		cclog.Errorf("Error while building node queries for Cluster %s, SubCLuster %s, Metrics %v, Scopes %v: %s", cluster, subCluster, metrics, scopes, err.Error())
 		return nil, err
 	}
 
-	req := memorystore.APIQueryRequest{
+	req := APIQueryRequest{
 		Cluster:   cluster,
 		Queries:   queries,
 		From:      from.Unix(),
@@ -700,7 +681,7 @@ func (ccms *CCMetricStoreInternal) LoadNodeListData(
 		WithData:  true,
 	}
 
-	resBody, err := memorystore.FetchData(req)
+	resBody, err := FetchData(req)
 	if err != nil {
 		cclog.Errorf("Error while fetching data : %s", err.Error())
 		return nil, err
@@ -709,7 +690,7 @@ func (ccms *CCMetricStoreInternal) LoadNodeListData(
 	var errors []string
 	data := make(map[string]schema.JobData)
 	for i, row := range resBody.Results {
-		var query memorystore.APIQuery
+		var query APIQuery
 		if resBody.Queries != nil {
 			query = resBody.Queries[i]
 		} else {
@@ -789,15 +770,15 @@ func (ccms *CCMetricStoreInternal) LoadNodeListData(
 	return data, nil
 }
 
-func (ccms *CCMetricStoreInternal) buildNodeQueries(
+func buildNodeQueries(
 	cluster string,
 	subCluster string,
 	nodes []string,
 	metrics []string,
 	scopes []schema.MetricScope,
 	resolution int64,
-) ([]memorystore.APIQuery, []schema.MetricScope, error) {
-	queries := make([]memorystore.APIQuery, 0, len(metrics)*len(scopes)*len(nodes))
+) ([]APIQuery, []schema.MetricScope, error) {
+	queries := make([]APIQuery, 0, len(metrics)*len(scopes)*len(nodes))
 	assignedScope := []schema.MetricScope{}
 
 	// Get Topol before loop if subCluster given
@@ -812,7 +793,6 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 	}
 
 	for _, metric := range metrics {
-		metric := metric
 		mc := archive.GetMetricConfig(cluster, metric)
 		if mc == nil {
 			// return nil, fmt.Errorf("METRICDATA/CCMS > metric '%s' is not specified for cluster '%s'", metric, cluster)
@@ -880,7 +860,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 						continue
 					}
 
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Aggregate:  false,
@@ -898,7 +878,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 						continue
 					}
 
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Aggregate:  true,
@@ -912,7 +892,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 
 				// HWThread -> HWThead
 				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeHWThread {
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Aggregate:  false,
@@ -928,7 +908,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeCore {
 					cores, _ := topology.GetCoresFromHWThreads(topology.Node)
 					for _, core := range cores {
-						queries = append(queries, memorystore.APIQuery{
+						queries = append(queries, APIQuery{
 							Metric:     metric,
 							Hostname:   hostname,
 							Aggregate:  true,
@@ -945,7 +925,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeSocket {
 					sockets, _ := topology.GetSocketsFromHWThreads(topology.Node)
 					for _, socket := range sockets {
-						queries = append(queries, memorystore.APIQuery{
+						queries = append(queries, APIQuery{
 							Metric:     metric,
 							Hostname:   hostname,
 							Aggregate:  true,
@@ -960,7 +940,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 
 				// HWThread -> Node
 				if nativeScope == schema.MetricScopeHWThread && scope == schema.MetricScopeNode {
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Aggregate:  true,
@@ -975,7 +955,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 				// Core -> Core
 				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeCore {
 					cores, _ := topology.GetCoresFromHWThreads(topology.Node)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Aggregate:  false,
@@ -991,7 +971,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeSocket {
 					sockets, _ := topology.GetSocketsFromCores(topology.Node)
 					for _, socket := range sockets {
-						queries = append(queries, memorystore.APIQuery{
+						queries = append(queries, APIQuery{
 							Metric:     metric,
 							Hostname:   hostname,
 							Aggregate:  true,
@@ -1007,7 +987,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 				// Core -> Node
 				if nativeScope == schema.MetricScopeCore && scope == schema.MetricScopeNode {
 					cores, _ := topology.GetCoresFromHWThreads(topology.Node)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Aggregate:  true,
@@ -1022,7 +1002,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 				// MemoryDomain -> MemoryDomain
 				if nativeScope == schema.MetricScopeMemoryDomain && scope == schema.MetricScopeMemoryDomain {
 					sockets, _ := topology.GetMemoryDomainsFromHWThreads(topology.Node)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Aggregate:  false,
@@ -1037,7 +1017,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 				// MemoryDoman -> Node
 				if nativeScope == schema.MetricScopeMemoryDomain && scope == schema.MetricScopeNode {
 					sockets, _ := topology.GetMemoryDomainsFromHWThreads(topology.Node)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Aggregate:  true,
@@ -1052,7 +1032,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 				// Socket -> Socket
 				if nativeScope == schema.MetricScopeSocket && scope == schema.MetricScopeSocket {
 					sockets, _ := topology.GetSocketsFromHWThreads(topology.Node)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Aggregate:  false,
@@ -1067,7 +1047,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 				// Socket -> Node
 				if nativeScope == schema.MetricScopeSocket && scope == schema.MetricScopeNode {
 					sockets, _ := topology.GetSocketsFromHWThreads(topology.Node)
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Aggregate:  true,
@@ -1081,7 +1061,7 @@ func (ccms *CCMetricStoreInternal) buildNodeQueries(
 
 				// Node -> Node
 				if nativeScope == schema.MetricScopeNode && scope == schema.MetricScopeNode {
-					queries = append(queries, memorystore.APIQuery{
+					queries = append(queries, APIQuery{
 						Metric:     metric,
 						Hostname:   hostname,
 						Resolution: resolution,
diff --git a/internal/memorystore/stats.go b/internal/metricstore/stats.go
similarity index 99%
rename from internal/memorystore/stats.go
rename to internal/metricstore/stats.go
index c931ab35..51ffafc1 100644
--- a/internal/memorystore/stats.go
+++ b/internal/metricstore/stats.go
@@ -3,7 +3,7 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
-package memorystore
+package metricstore
 
 import (
 	"errors"
diff --git a/internal/metricsync/metricdata.go b/internal/metricsync/metricdata.go
new file mode 100644
index 00000000..772f16da
--- /dev/null
+++ b/internal/metricsync/metricdata.go
@@ -0,0 +1,60 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package metricsync
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"time"
+
+	"github.com/ClusterCockpit/cc-backend/internal/config"
+	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+)
+
+type MetricDataSource interface {
+	// Initialize this MetricDataRepository. One instance of
+	// this interface will only ever be responsible for one cluster.
+	Init(rawConfig json.RawMessage) error
+
+	// Return a map of hosts to a map of metrics at the requested scopes (currently only node) for that node.
+	Pull(cluster string, metrics, nodes []string, scopes []schema.MetricScope, from, to time.Time, ctx context.Context) (map[string]map[string][]*schema.JobMetric, error)
+}
+
+var metricDataSourceRepos map[string]MetricDataSource = map[string]MetricDataSource{}
+
+func Init() error {
+	for _, cluster := range config.Clusters {
+		if cluster.MetricDataRepository != nil {
+			var kind struct {
+				Kind string `json:"kind"`
+			}
+			if err := json.Unmarshal(cluster.MetricDataRepository, &kind); err != nil {
+				cclog.Warn("Error while unmarshaling raw json MetricDataRepository")
+				return err
+			}
+
+			var mdr MetricDataSource
+			switch kind.Kind {
+			case "cc-metric-store":
+			case "prometheus":
+				// mdr = &PrometheusDataRepository{}
+			case "test":
+				// mdr = &TestMetricDataRepository{}
+			default:
+				return fmt.Errorf("METRICDATA/METRICDATA > Unknown MetricDataRepository %v for cluster %v", kind.Kind, cluster.Name)
+			}
+
+			if err := mdr.Init(cluster.MetricDataRepository); err != nil {
+				cclog.Errorf("Error initializing MetricDataRepository %v for cluster %v", kind.Kind, cluster.Name)
+				return err
+			}
+			metricDataSourceRepos[cluster.Name] = mdr
+		}
+	}
+	return nil
+}
diff --git a/internal/repository/stats.go b/internal/repository/stats.go
index d1e16eb8..989026d1 100644
--- a/internal/repository/stats.go
+++ b/internal/repository/stats.go
@@ -12,7 +12,7 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
+	"github.com/ClusterCockpit/cc-backend/internal/metricdispatch"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
 	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
@@ -766,7 +766,7 @@ func (r *JobRepository) runningJobsMetricStatisticsHistogram(
 			continue
 		}
 
-		if err := metricDataDispatcher.LoadAverages(job, metrics, avgs, ctx); err != nil {
+		if err := metricdispatch.LoadAverages(job, metrics, avgs, ctx); err != nil {
 			cclog.Errorf("Error while loading averages for histogram: %s", err)
 			return nil
 		}
diff --git a/internal/taskmanager/updateFootprintService.go b/internal/taskmanager/updateFootprintService.go
index 979a6137..c8f81e37 100644
--- a/internal/taskmanager/updateFootprintService.go
+++ b/internal/taskmanager/updateFootprintService.go
@@ -10,7 +10,7 @@ import (
 	"math"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
+	"github.com/ClusterCockpit/cc-backend/internal/metricstore"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
 	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
@@ -58,12 +58,6 @@ func RegisterFootprintWorker() {
 						allMetrics = append(allMetrics, mc.Name)
 					}
 
-					repo, err := metricdata.GetMetricDataRepo(cluster.Name)
-					if err != nil {
-						cclog.Errorf("no metric data repository configured for '%s'", cluster.Name)
-						continue
-					}
-
 					pendingStatements := []sq.UpdateBuilder{}
 
 					for _, job := range jobs {
@@ -72,7 +66,7 @@ func RegisterFootprintWorker() {
 
 						sJob := time.Now()
 
-						jobStats, err := repo.LoadStats(job, allMetrics, context.Background())
+						jobStats, err := metricstore.LoadStats(job, allMetrics, context.Background())
 						if err != nil {
 							cclog.Errorf("error wile loading job data stats for footprint update: %v", err)
 							ce++

From ecb5aef7355b498d2f84e1837e536ab5aa69a2d0 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 25 Dec 2025 08:48:03 +0100
Subject: [PATCH 20/59] Fix build error in unit test

---
 internal/api/nats_test.go | 1 -
 1 file changed, 1 deletion(-)

diff --git a/internal/api/nats_test.go b/internal/api/nats_test.go
index 9e1fa2b5..e92ce291 100644
--- a/internal/api/nats_test.go
+++ b/internal/api/nats_test.go
@@ -18,7 +18,6 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/auth"
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph"
-	"github.com/ClusterCockpit/cc-backend/internal/importer"
 	"github.com/ClusterCockpit/cc-backend/internal/metricstore"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"

From 4d6326b8be9bef9d730ea010ae933d43e43ad9a1 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Mon, 12 Jan 2026 08:55:31 +0100
Subject: [PATCH 21/59] Remove metricsync

---
 internal/metricsync/metricdata.go | 60 -------------------------------
 1 file changed, 60 deletions(-)
 delete mode 100644 internal/metricsync/metricdata.go

diff --git a/internal/metricsync/metricdata.go b/internal/metricsync/metricdata.go
deleted file mode 100644
index 772f16da..00000000
--- a/internal/metricsync/metricdata.go
+++ /dev/null
@@ -1,60 +0,0 @@
-// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved. This file is part of cc-backend.
-// Use of this source code is governed by a MIT-style
-// license that can be found in the LICENSE file.
-
-package metricsync
-
-import (
-	"context"
-	"encoding/json"
-	"fmt"
-	"time"
-
-	"github.com/ClusterCockpit/cc-backend/internal/config"
-	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
-	"github.com/ClusterCockpit/cc-lib/v2/schema"
-)
-
-type MetricDataSource interface {
-	// Initialize this MetricDataRepository. One instance of
-	// this interface will only ever be responsible for one cluster.
-	Init(rawConfig json.RawMessage) error
-
-	// Return a map of hosts to a map of metrics at the requested scopes (currently only node) for that node.
-	Pull(cluster string, metrics, nodes []string, scopes []schema.MetricScope, from, to time.Time, ctx context.Context) (map[string]map[string][]*schema.JobMetric, error)
-}
-
-var metricDataSourceRepos map[string]MetricDataSource = map[string]MetricDataSource{}
-
-func Init() error {
-	for _, cluster := range config.Clusters {
-		if cluster.MetricDataRepository != nil {
-			var kind struct {
-				Kind string `json:"kind"`
-			}
-			if err := json.Unmarshal(cluster.MetricDataRepository, &kind); err != nil {
-				cclog.Warn("Error while unmarshaling raw json MetricDataRepository")
-				return err
-			}
-
-			var mdr MetricDataSource
-			switch kind.Kind {
-			case "cc-metric-store":
-			case "prometheus":
-				// mdr = &PrometheusDataRepository{}
-			case "test":
-				// mdr = &TestMetricDataRepository{}
-			default:
-				return fmt.Errorf("METRICDATA/METRICDATA > Unknown MetricDataRepository %v for cluster %v", kind.Kind, cluster.Name)
-			}
-
-			if err := mdr.Init(cluster.MetricDataRepository); err != nil {
-				cclog.Errorf("Error initializing MetricDataRepository %v for cluster %v", kind.Kind, cluster.Name)
-				return err
-			}
-			metricDataSourceRepos[cluster.Name] = mdr
-		}
-	}
-	return nil
-}

From 56399523d7e9582ff7525b4932586415bf48d7ea Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Mon, 12 Jan 2026 09:00:06 +0100
Subject: [PATCH 22/59] Update module deps

---
 go.mod | 17 ++++-------------
 go.sum | 26 ++++++++++++++------------
 2 files changed, 18 insertions(+), 25 deletions(-)

diff --git a/go.mod b/go.mod
index 36ce47b9..c8899162 100644
--- a/go.mod
+++ b/go.mod
@@ -33,8 +33,6 @@ require (
 	github.com/linkedin/goavro/v2 v2.14.1
 	github.com/mattn/go-sqlite3 v1.14.32
 	github.com/nats-io/nats.go v1.47.0
-	github.com/prometheus/client_golang v1.23.2
-	github.com/prometheus/common v0.67.4
 	github.com/qustavo/sqlhooks/v2 v2.1.0
 	github.com/santhosh-tekuri/jsonschema/v5 v5.3.1
 	github.com/stretchr/testify v1.11.1
@@ -65,8 +63,6 @@ require (
 	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.7 // indirect
 	github.com/aws/aws-sdk-go-v2/service/sts v1.40.2 // indirect
 	github.com/aws/smithy-go v1.24.0 // indirect
-	github.com/beorn7/perks v1.0.1 // indirect
-	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/cpuguy83/go-md2man/v2 v2.0.7 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
@@ -86,6 +82,7 @@ require (
 	github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
 	github.com/goccy/go-yaml v1.19.0 // indirect
 	github.com/golang/snappy v0.0.4 // indirect
+	github.com/google/go-cmp v0.7.0 // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/gorilla/securecookie v1.1.2 // indirect
 	github.com/gorilla/websocket v1.5.3 // indirect
@@ -93,24 +90,19 @@ require (
 	github.com/influxdata/influxdb-client-go/v2 v2.14.0 // indirect
 	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf // indirect
 	github.com/jonboulle/clockwork v0.5.0 // indirect
-	github.com/jpillora/backoff v1.0.0 // indirect
-	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/klauspost/compress v1.18.2 // indirect
+	github.com/kr/pretty v0.3.1 // indirect
 	github.com/lann/builder v0.0.0-20180802200727-47ae307949d0 // indirect
 	github.com/lann/ps v0.0.0-20150810152359-62de8c46ede0 // indirect
-	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
-	github.com/modern-go/reflect2 v1.0.2 // indirect
-	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
-	github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f // indirect
 	github.com/nats-io/nkeys v0.4.12 // indirect
 	github.com/nats-io/nuid v1.0.1 // indirect
 	github.com/oapi-codegen/runtime v1.1.1 // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
-	github.com/prometheus/client_model v0.6.2 // indirect
-	github.com/prometheus/procfs v0.16.1 // indirect
+	github.com/prometheus/common v0.67.4 // indirect
 	github.com/robfig/cron/v3 v3.0.1 // indirect
 	github.com/russross/blackfriday/v2 v2.1.0 // indirect
 	github.com/sosodev/duration v1.3.1 // indirect
+	github.com/stmcginnis/gofish v0.20.0 // indirect
 	github.com/stretchr/objx v0.5.2 // indirect
 	github.com/swaggo/files v1.0.1 // indirect
 	github.com/urfave/cli/v2 v2.27.7 // indirect
@@ -125,7 +117,6 @@ require (
 	golang.org/x/sys v0.39.0 // indirect
 	golang.org/x/text v0.32.0 // indirect
 	golang.org/x/tools v0.39.0 // indirect
-	google.golang.org/protobuf v1.36.10 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 	sigs.k8s.io/yaml v1.6.0 // indirect
 )
diff --git a/go.sum b/go.sum
index 9038d960..99c2bdb0 100644
--- a/go.sum
+++ b/go.sum
@@ -23,6 +23,8 @@ github.com/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883 h1:bvNMNQO63//z+xNg
 github.com/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883/go.mod h1:rCTlJbsFo29Kk6CurOXKm700vrz8f0KW0JNfpkRJY/8=
 github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM=
 github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA=
+github.com/antithesishq/antithesis-sdk-go v0.5.0-default-no-op h1:Ucf+QxEKMbPogRO5guBNe5cgd9uZgfoJLOYs8WWhtjM=
+github.com/antithesishq/antithesis-sdk-go v0.5.0-default-no-op/go.mod h1:IUpT2DPAKh6i/YhSbt6Gl3v2yvUZjmKncl7U91fup7E=
 github.com/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ=
 github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP2+08jFMw88y4klk=
 github.com/arbovm/levenshtein v0.0.0-20160628152529-48b4e1c0c4d0 h1:jfIu9sQUG6Ig+0+Ap1h4unLjW6YQJpKZVmUzxsD4E/Q=
@@ -142,7 +144,8 @@ github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
 github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
-github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/google/go-tpm v0.9.7 h1:u89J4tUUeDTlH8xxC3CTW7OHZjbjKoHdQ9W7gCUhtxA=
+github.com/google/go-tpm v0.9.7/go.mod h1:h9jEsEECg7gtLis0upRBQU+GhYVH6jMjrFxI8u6bVUY=
 github.com/google/gofuzz v1.2.0 h1:xRy4A+RhZaiKjJ1bPfwQ8sedCA+YS2YcCHW6ec7JMi0=
 github.com/google/gofuzz v1.2.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/gops v0.3.28 h1:2Xr57tqKAmQYRAfG12E+yLcoa2Y42UJo2lOrUFL9ark=
@@ -192,10 +195,6 @@ github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
 github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
 github.com/jonboulle/clockwork v0.5.0 h1:Hyh9A8u51kptdkR+cqRpT1EebBwTn1oK9YfGYbdFz6I=
 github.com/jonboulle/clockwork v0.5.0/go.mod h1:3mZlmanh0g2NDKO5TWZVJAfofYk64M7XN3SzBPjZF60=
-github.com/jpillora/backoff v1.0.0 h1:uvFg412JmmHBHw7iwprIxkPMI+sGQ4kzOWsMeHnm2EA=
-github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX5e0EB2j4=
-github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
-github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
 github.com/klauspost/compress v1.18.2 h1:iiPHWW0YrcFgpBYhsA6D1+fqHssJscY/Tm/y2Uqnapk=
 github.com/klauspost/compress v1.18.2/go.mod h1:R0h/fSBs8DE4ENlcrlib3PsXS61voFxhIs2DeRhCvJ4=
@@ -219,15 +218,14 @@ github.com/mattn/go-sqlite3 v1.10.0/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsO
 github.com/mattn/go-sqlite3 v1.14.22/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
 github.com/mattn/go-sqlite3 v1.14.32 h1:JD12Ag3oLy1zQA+BNn74xRgaBbdhbNIDYvQUEuuErjs=
 github.com/mattn/go-sqlite3 v1.14.32/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
-github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
-github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
-github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
-github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
-github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
+github.com/minio/highwayhash v1.0.4-0.20251030100505-070ab1a87a76 h1:KGuD/pM2JpL9FAYvBrnBBeENKZNh6eNtjqytV6TYjnk=
+github.com/minio/highwayhash v1.0.4-0.20251030100505-070ab1a87a76/go.mod h1:GGYsuwP/fPD6Y9hMiXuapVvlIUEhFhMTh0rxU3ik1LQ=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
-github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f h1:KUppIJq7/+SVif2QVs3tOP0zanoHgBEVAwHxUSIzRqU=
-github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
+github.com/nats-io/jwt/v2 v2.8.0 h1:K7uzyz50+yGZDO5o772eRE7atlcSEENpL7P+b74JV1g=
+github.com/nats-io/jwt/v2 v2.8.0/go.mod h1:me11pOkwObtcBNR8AiMrUbtVOUGkqYjMQZ6jnSdVUIA=
+github.com/nats-io/nats-server/v2 v2.12.3 h1:KRv+1n7lddMVgkJPQer+pt36TcO0ENxjilBmeWdjcHs=
+github.com/nats-io/nats-server/v2 v2.12.3/go.mod h1:MQXjG9WjyXKz9koWzUc3jYUMKD8x3CLmTNy91IQQz3Y=
 github.com/nats-io/nats.go v1.47.0 h1:YQdADw6J/UfGUd2Oy6tn4Hq6YHxCaJrVKayxxFqYrgM=
 github.com/nats-io/nats.go v1.47.0/go.mod h1:iRWIPokVIFbVijxuMQq4y9ttaBTMe0SFdlZfMDd+33g=
 github.com/nats-io/nkeys v0.4.12 h1:nssm7JKOG9/x4J8II47VWCL1Ds29avyiQDRn0ckMvDc=
@@ -238,6 +236,7 @@ github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLA
 github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmtpMYro=
 github.com/oapi-codegen/runtime v1.1.1/go.mod h1:SK9X900oXmPWilYR5/WKPzt3Kqxn/uS/+lbpREv+eCg=
 github.com/opentracing/opentracing-go v1.1.0/go.mod h1:UkNAQd3GIcIGf0SeVgPpRdFStlNbqXla1AfSYxPUl2o=
+github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
@@ -253,6 +252,7 @@ github.com/qustavo/sqlhooks/v2 v2.1.0 h1:54yBemHnGHp/7xgT+pxwmIlMSDNYKx5JW5dfRAi
 github.com/qustavo/sqlhooks/v2 v2.1.0/go.mod h1:aMREyKo7fOKTwiLuWPsaHRXEmtqG4yREztO0idF83AU=
 github.com/robfig/cron/v3 v3.0.1 h1:WdRxkvbJztn8LMz/QEvLN5sBU+xKpSqwwUO1Pjr4qDs=
 github.com/robfig/cron/v3 v3.0.1/go.mod h1:eQICP3HwyT7UooqI/z+Ov+PtYAWygg1TEWWzGIFLtro=
+github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
 github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=
 github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=
 github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
@@ -264,6 +264,8 @@ github.com/sergi/go-diff v1.3.1/go.mod h1:aMJSSKb2lpPvRNec0+w3fl7LP9IOFzdc9Pa4NF
 github.com/sosodev/duration v1.3.1 h1:qtHBDMQ6lvMQsL15g4aopM4HEfOaYuhWBw3NPTtlqq4=
 github.com/sosodev/duration v1.3.1/go.mod h1:RQIBBX0+fMLc/D9+Jb/fwvVmo0eZvDDEERAikUR6SDg=
 github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
+github.com/stmcginnis/gofish v0.20.0 h1:hH2V2Qe898F2wWT1loApnkDUrXXiLKqbSlMaH3Y1n08=
+github.com/stmcginnis/gofish v0.20.0/go.mod h1:PzF5i8ecRG9A2ol8XT64npKUunyraJ+7t0kYMpQAtqU=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
 github.com/stretchr/objx v0.5.2 h1:xuMeJ0Sdp5ZMRXx/aWO6RZxdr3beISkG5/G/aIRr3pY=

From 4cec93334964c166435e79c99af6e354d661dde7 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 13 Jan 2026 06:28:33 +0100
Subject: [PATCH 23/59] Remove obsolete cluster config section

---
 cmd/cc-backend/main.go                 |  7 +--
 internal/api/api_test.go               |  6 +-
 internal/api/nats_test.go              |  6 +-
 internal/config/config.go              | 21 +------
 internal/config/config_test.go         | 12 +---
 internal/config/schema.go              | 80 --------------------------
 internal/importer/importer_test.go     |  6 +-
 internal/repository/node_test.go       |  6 +-
 internal/repository/userConfig_test.go |  6 +-
 tools/archive-manager/main.go          |  6 +-
 web/web.go                             |  7 ---
 11 files changed, 10 insertions(+), 153 deletions(-)

diff --git a/cmd/cc-backend/main.go b/cmd/cc-backend/main.go
index 331df4f6..8eb3c76f 100644
--- a/cmd/cc-backend/main.go
+++ b/cmd/cc-backend/main.go
@@ -102,12 +102,7 @@ func initConfiguration() error {
 		return fmt.Errorf("main configuration must be present")
 	}
 
-	clustercfg := ccconf.GetPackageConfig("clusters")
-	if clustercfg == nil {
-		return fmt.Errorf("cluster configuration must be present")
-	}
-
-	config.Init(cfg, clustercfg)
+	config.Init(cfg)
 	return nil
 }
 
diff --git a/internal/api/api_test.go b/internal/api/api_test.go
index a2283013..7aa935ff 100644
--- a/internal/api/api_test.go
+++ b/internal/api/api_test.go
@@ -157,11 +157,7 @@ func setup(t *testing.T) *api.RestAPI {
 
 	// Load and check main configuration
 	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
-		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
-			config.Init(cfg, clustercfg)
-		} else {
-			cclog.Abort("Cluster configuration must be present")
-		}
+		config.Init(cfg)
 	} else {
 		cclog.Abort("Main configuration must be present")
 	}
diff --git a/internal/api/nats_test.go b/internal/api/nats_test.go
index e92ce291..319668bb 100644
--- a/internal/api/nats_test.go
+++ b/internal/api/nats_test.go
@@ -151,11 +151,7 @@ func setupNatsTest(t *testing.T) *NatsAPI {
 
 	// Load and check main configuration
 	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
-		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
-			config.Init(cfg, clustercfg)
-		} else {
-			cclog.Abort("Cluster configuration must be present")
-		}
+		config.Init(cfg)
 	} else {
 		cclog.Abort("Main configuration must be present")
 	}
diff --git a/internal/config/config.go b/internal/config/config.go
index af8ec944..b8eea2ca 100644
--- a/internal/config/config.go
+++ b/internal/config/config.go
@@ -111,14 +111,6 @@ type FilterRanges struct {
 	StartTime *TimeRange `json:"startTime"`
 }
 
-type ClusterConfig struct {
-	Name                 string          `json:"name"`
-	FilterRanges         *FilterRanges   `json:"filterRanges"`
-	MetricDataRepository json.RawMessage `json:"metricDataRepository"`
-}
-
-var Clusters []*ClusterConfig
-
 var Keys ProgramConfig = ProgramConfig{
 	Addr:                      "localhost:8080",
 	DisableAuthentication:     false,
@@ -132,7 +124,7 @@ var Keys ProgramConfig = ProgramConfig{
 	ShortRunningJobsDuration:  5 * 60,
 }
 
-func Init(mainConfig json.RawMessage, clusterConfig json.RawMessage) {
+func Init(mainConfig json.RawMessage) {
 	Validate(configSchema, mainConfig)
 	dec := json.NewDecoder(bytes.NewReader(mainConfig))
 	dec.DisallowUnknownFields()
@@ -140,17 +132,6 @@ func Init(mainConfig json.RawMessage, clusterConfig json.RawMessage) {
 		cclog.Abortf("Config Init: Could not decode config file '%s'.\nError: %s\n", mainConfig, err.Error())
 	}
 
-	Validate(clustersSchema, clusterConfig)
-	dec = json.NewDecoder(bytes.NewReader(clusterConfig))
-	dec.DisallowUnknownFields()
-	if err := dec.Decode(&Clusters); err != nil {
-		cclog.Abortf("Config Init: Could not decode config file '%s'.\nError: %s\n", mainConfig, err.Error())
-	}
-
-	if len(Clusters) < 1 {
-		cclog.Abort("Config Init: At least one cluster required in config. Exited with error.")
-	}
-
 	if Keys.EnableResampling != nil && Keys.EnableResampling.MinimumPoints > 0 {
 		resampler.SetMinimumRequiredPoints(Keys.EnableResampling.MinimumPoints)
 	}
diff --git a/internal/config/config_test.go b/internal/config/config_test.go
index 396a80a1..e4a700ff 100644
--- a/internal/config/config_test.go
+++ b/internal/config/config_test.go
@@ -16,11 +16,7 @@ func TestInit(t *testing.T) {
 	fp := "../../configs/config.json"
 	ccconf.Init(fp)
 	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
-		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
-			Init(cfg, clustercfg)
-		} else {
-			cclog.Abort("Cluster configuration must be present")
-		}
+		Init(cfg)
 	} else {
 		cclog.Abort("Main configuration must be present")
 	}
@@ -34,11 +30,7 @@ func TestInitMinimal(t *testing.T) {
 	fp := "../../configs/config-demo.json"
 	ccconf.Init(fp)
 	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
-		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
-			Init(cfg, clustercfg)
-		} else {
-			cclog.Abort("Cluster configuration must be present")
-		}
+		Init(cfg)
 	} else {
 		cclog.Abort("Main configuration must be present")
 	}
diff --git a/internal/config/schema.go b/internal/config/schema.go
index ff8d0c92..2d068140 100644
--- a/internal/config/schema.go
+++ b/internal/config/schema.go
@@ -138,83 +138,3 @@ var configSchema = `
 	},
   "required": ["apiAllowedIPs"]
 	}`
-
-var clustersSchema = `
-  {
-    "type": "array",
-    "items": {
-      "type": "object",
-      "properties": {
-        "name": {
-          "description": "The name of the cluster.",
-          "type": "string"
-        },
-        "metricDataRepository": {
-          "description": "Type of the metric data repository for this cluster",
-          "type": "object",
-          "properties": {
-            "kind": {
-              "type": "string",
-                "enum": ["influxdb", "prometheus", "cc-metric-store", "cc-metric-store-internal", "test"]
-            },
-            "url": {
-              "type": "string"
-            },
-            "token": {
-              "type": "string"
-            }
-          },
-          "required": ["kind"]
-        },
-        "filterRanges": {
-          "description": "This option controls the slider ranges for the UI controls of numNodes, duration, and startTime.",
-          "type": "object",
-          "properties": {
-            "numNodes": {
-              "description": "UI slider range for number of nodes",
-              "type": "object",
-              "properties": {
-                "from": {
-                  "type": "integer"
-                },
-                "to": {
-                  "type": "integer"
-                }
-              },
-              "required": ["from", "to"]
-            },
-            "duration": {
-              "description": "UI slider range for duration",
-              "type": "object",
-              "properties": {
-                "from": {
-                  "type": "integer"
-                },
-                "to": {
-                  "type": "integer"
-                }
-              },
-              "required": ["from", "to"]
-            },
-            "startTime": {
-              "description": "UI slider range for start time",
-              "type": "object",
-              "properties": {
-                "from": {
-                  "type": "string",
-                  "format": "date-time"
-                },
-                "to": {
-                  "type": "null"
-                }
-              },
-              "required": ["from", "to"]
-            }
-          },
-          "required": ["numNodes", "duration", "startTime"]
-        }
-      },
-      "required": ["name", "metricDataRepository", "filterRanges"],
-      "minItems": 1
-    }
-  }`
diff --git a/internal/importer/importer_test.go b/internal/importer/importer_test.go
index bffb8bf6..2d00fc84 100644
--- a/internal/importer/importer_test.go
+++ b/internal/importer/importer_test.go
@@ -121,11 +121,7 @@ func setup(t *testing.T) *repository.JobRepository {
 
 	// Load and check main configuration
 	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
-		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
-			config.Init(cfg, clustercfg)
-		} else {
-			t.Fatal("Cluster configuration must be present")
-		}
+		config.Init(cfg)
 	} else {
 		t.Fatal("Main configuration must be present")
 	}
diff --git a/internal/repository/node_test.go b/internal/repository/node_test.go
index e1d6ca93..fd935b53 100644
--- a/internal/repository/node_test.go
+++ b/internal/repository/node_test.go
@@ -144,11 +144,7 @@ func nodeTestSetup(t *testing.T) {
 
 	// Load and check main configuration
 	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
-		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
-			config.Init(cfg, clustercfg)
-		} else {
-			cclog.Abort("Cluster configuration must be present")
-		}
+		config.Init(cfg)
 	} else {
 		cclog.Abort("Main configuration must be present")
 	}
diff --git a/internal/repository/userConfig_test.go b/internal/repository/userConfig_test.go
index 02c70d0f..ae3adaf2 100644
--- a/internal/repository/userConfig_test.go
+++ b/internal/repository/userConfig_test.go
@@ -58,11 +58,7 @@ func setupUserTest(t *testing.T) *UserCfgRepo {
 
 	// Load and check main configuration
 	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
-		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
-			config.Init(cfg, clustercfg)
-		} else {
-			t.Fatal("Cluster configuration must be present")
-		}
+		config.Init(cfg)
 	} else {
 		t.Fatal("Main configuration must be present")
 	}
diff --git a/tools/archive-manager/main.go b/tools/archive-manager/main.go
index f5f8b836..ffcba793 100644
--- a/tools/archive-manager/main.go
+++ b/tools/archive-manager/main.go
@@ -434,11 +434,7 @@ func main() {
 
 	// Load and check main configuration
 	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
-		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
-			config.Init(cfg, clustercfg)
-		} else {
-			cclog.Abort("Cluster configuration must be present")
-		}
+		config.Init(cfg)
 	} else {
 		cclog.Abort("Main configuration must be present")
 	}
diff --git a/web/web.go b/web/web.go
index d2ae8700..37f1c2b2 100644
--- a/web/web.go
+++ b/web/web.go
@@ -245,7 +245,6 @@ type Page struct {
 	User          schema.User            // Information about the currently logged in user (Full User Info)
 	Roles         map[string]schema.Role // Available roles for frontend render checks
 	Build         Build                  // Latest information about the application
-	Clusters      []config.ClusterConfig // List of all clusters for use in the Header
 	SubClusters   map[string][]string    // Map per cluster of all subClusters for use in the Header
 	FilterPresets map[string]any         // For pages with the Filter component, this can be used to set initial filters.
 	Infos         map[string]any         // For generic use (e.g. username for /monitoring/user/<id>, job id for /monitoring/job/<id>)
@@ -260,12 +259,6 @@ func RenderTemplate(rw http.ResponseWriter, file string, page *Page) {
 		cclog.Errorf("WEB/WEB > template '%s' not found", file)
 	}
 
-	if page.Clusters == nil {
-		for _, c := range config.Clusters {
-			page.Clusters = append(page.Clusters, config.ClusterConfig{Name: c.Name, FilterRanges: c.FilterRanges, MetricDataRepository: nil})
-		}
-	}
-
 	if page.SubClusters == nil {
 		page.SubClusters = make(map[string][]string)
 		for _, cluster := range archive.Clusters {

From 42809e3f75256d282e3f7a5b8bdfd9980c222882 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 13 Jan 2026 07:20:26 +0100
Subject: [PATCH 24/59] Remove embedded tagger rules

---
 configs/tagger/README.md                      |   0
 {internal => configs}/tagger/apps/alf.txt     |   0
 {internal => configs}/tagger/apps/caracal.txt |   0
 {internal => configs}/tagger/apps/chroma.txt  |   0
 {internal => configs}/tagger/apps/cp2k.txt    |   0
 {internal => configs}/tagger/apps/cpmd.txt    |   0
 {internal => configs}/tagger/apps/flame.txt   |   0
 {internal => configs}/tagger/apps/gromacs.txt |   0
 {internal => configs}/tagger/apps/julia.txt   |   0
 {internal => configs}/tagger/apps/lammps.txt  |   0
 {internal => configs}/tagger/apps/matlab.txt  |   0
 .../tagger/apps/openfoam.txt                  |   0
 {internal => configs}/tagger/apps/orca.txt    |   0
 {internal => configs}/tagger/apps/python.txt  |   0
 {internal => configs}/tagger/apps/starccm.txt |   0
 .../tagger/apps/turbomole.txt                 |   0
 {internal => configs}/tagger/apps/vasp.txt    |   0
 .../tagger/jobclasses/highload.json           |   0
 .../tagger/jobclasses/lowUtilization.json     |   0
 .../tagger/jobclasses/lowload.json            |   0
 .../tagger/jobclasses/parameters.json         |   0
 internal/tagger/classifyJob.go                | 105 ++++++++++--------
 internal/tagger/classifyJob_test.go           |   8 +-
 internal/tagger/detectApp.go                  |  61 +++++-----
 internal/tagger/detectApp_test.go             |  70 +++++++++++-
 25 files changed, 166 insertions(+), 78 deletions(-)
 create mode 100644 configs/tagger/README.md
 rename {internal => configs}/tagger/apps/alf.txt (100%)
 rename {internal => configs}/tagger/apps/caracal.txt (100%)
 rename {internal => configs}/tagger/apps/chroma.txt (100%)
 rename {internal => configs}/tagger/apps/cp2k.txt (100%)
 rename {internal => configs}/tagger/apps/cpmd.txt (100%)
 rename {internal => configs}/tagger/apps/flame.txt (100%)
 rename {internal => configs}/tagger/apps/gromacs.txt (100%)
 rename {internal => configs}/tagger/apps/julia.txt (100%)
 rename {internal => configs}/tagger/apps/lammps.txt (100%)
 rename {internal => configs}/tagger/apps/matlab.txt (100%)
 rename {internal => configs}/tagger/apps/openfoam.txt (100%)
 rename {internal => configs}/tagger/apps/orca.txt (100%)
 rename {internal => configs}/tagger/apps/python.txt (100%)
 rename {internal => configs}/tagger/apps/starccm.txt (100%)
 rename {internal => configs}/tagger/apps/turbomole.txt (100%)
 rename {internal => configs}/tagger/apps/vasp.txt (100%)
 rename {internal => configs}/tagger/jobclasses/highload.json (100%)
 rename {internal => configs}/tagger/jobclasses/lowUtilization.json (100%)
 rename {internal => configs}/tagger/jobclasses/lowload.json (100%)
 rename {internal => configs}/tagger/jobclasses/parameters.json (100%)

diff --git a/configs/tagger/README.md b/configs/tagger/README.md
new file mode 100644
index 00000000..e69de29b
diff --git a/internal/tagger/apps/alf.txt b/configs/tagger/apps/alf.txt
similarity index 100%
rename from internal/tagger/apps/alf.txt
rename to configs/tagger/apps/alf.txt
diff --git a/internal/tagger/apps/caracal.txt b/configs/tagger/apps/caracal.txt
similarity index 100%
rename from internal/tagger/apps/caracal.txt
rename to configs/tagger/apps/caracal.txt
diff --git a/internal/tagger/apps/chroma.txt b/configs/tagger/apps/chroma.txt
similarity index 100%
rename from internal/tagger/apps/chroma.txt
rename to configs/tagger/apps/chroma.txt
diff --git a/internal/tagger/apps/cp2k.txt b/configs/tagger/apps/cp2k.txt
similarity index 100%
rename from internal/tagger/apps/cp2k.txt
rename to configs/tagger/apps/cp2k.txt
diff --git a/internal/tagger/apps/cpmd.txt b/configs/tagger/apps/cpmd.txt
similarity index 100%
rename from internal/tagger/apps/cpmd.txt
rename to configs/tagger/apps/cpmd.txt
diff --git a/internal/tagger/apps/flame.txt b/configs/tagger/apps/flame.txt
similarity index 100%
rename from internal/tagger/apps/flame.txt
rename to configs/tagger/apps/flame.txt
diff --git a/internal/tagger/apps/gromacs.txt b/configs/tagger/apps/gromacs.txt
similarity index 100%
rename from internal/tagger/apps/gromacs.txt
rename to configs/tagger/apps/gromacs.txt
diff --git a/internal/tagger/apps/julia.txt b/configs/tagger/apps/julia.txt
similarity index 100%
rename from internal/tagger/apps/julia.txt
rename to configs/tagger/apps/julia.txt
diff --git a/internal/tagger/apps/lammps.txt b/configs/tagger/apps/lammps.txt
similarity index 100%
rename from internal/tagger/apps/lammps.txt
rename to configs/tagger/apps/lammps.txt
diff --git a/internal/tagger/apps/matlab.txt b/configs/tagger/apps/matlab.txt
similarity index 100%
rename from internal/tagger/apps/matlab.txt
rename to configs/tagger/apps/matlab.txt
diff --git a/internal/tagger/apps/openfoam.txt b/configs/tagger/apps/openfoam.txt
similarity index 100%
rename from internal/tagger/apps/openfoam.txt
rename to configs/tagger/apps/openfoam.txt
diff --git a/internal/tagger/apps/orca.txt b/configs/tagger/apps/orca.txt
similarity index 100%
rename from internal/tagger/apps/orca.txt
rename to configs/tagger/apps/orca.txt
diff --git a/internal/tagger/apps/python.txt b/configs/tagger/apps/python.txt
similarity index 100%
rename from internal/tagger/apps/python.txt
rename to configs/tagger/apps/python.txt
diff --git a/internal/tagger/apps/starccm.txt b/configs/tagger/apps/starccm.txt
similarity index 100%
rename from internal/tagger/apps/starccm.txt
rename to configs/tagger/apps/starccm.txt
diff --git a/internal/tagger/apps/turbomole.txt b/configs/tagger/apps/turbomole.txt
similarity index 100%
rename from internal/tagger/apps/turbomole.txt
rename to configs/tagger/apps/turbomole.txt
diff --git a/internal/tagger/apps/vasp.txt b/configs/tagger/apps/vasp.txt
similarity index 100%
rename from internal/tagger/apps/vasp.txt
rename to configs/tagger/apps/vasp.txt
diff --git a/internal/tagger/jobclasses/highload.json b/configs/tagger/jobclasses/highload.json
similarity index 100%
rename from internal/tagger/jobclasses/highload.json
rename to configs/tagger/jobclasses/highload.json
diff --git a/internal/tagger/jobclasses/lowUtilization.json b/configs/tagger/jobclasses/lowUtilization.json
similarity index 100%
rename from internal/tagger/jobclasses/lowUtilization.json
rename to configs/tagger/jobclasses/lowUtilization.json
diff --git a/internal/tagger/jobclasses/lowload.json b/configs/tagger/jobclasses/lowload.json
similarity index 100%
rename from internal/tagger/jobclasses/lowload.json
rename to configs/tagger/jobclasses/lowload.json
diff --git a/internal/tagger/jobclasses/parameters.json b/configs/tagger/jobclasses/parameters.json
similarity index 100%
rename from internal/tagger/jobclasses/parameters.json
rename to configs/tagger/jobclasses/parameters.json
diff --git a/internal/tagger/classifyJob.go b/internal/tagger/classifyJob.go
index 70399218..b5f30949 100644
--- a/internal/tagger/classifyJob.go
+++ b/internal/tagger/classifyJob.go
@@ -2,15 +2,16 @@
 // All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package tagger
 
 import (
 	"bytes"
-	"embed"
 	"encoding/json"
 	"fmt"
 	"maps"
 	"os"
+	"path/filepath"
 	"strings"
 	"text/template"
 
@@ -23,8 +24,16 @@ import (
 	"github.com/expr-lang/expr/vm"
 )
 
-//go:embed jobclasses/*
-var jobClassFiles embed.FS
+const (
+	// defaultJobClassConfigPath is the default path for job classification configuration
+	defaultJobClassConfigPath = "./var/tagger/jobclasses"
+	// tagTypeJobClass is the tag type identifier for job classification tags
+	tagTypeJobClass = "jobClass"
+	// jobClassConfigDirMatch is the directory name used for matching filesystem events
+	jobClassConfigDirMatch = "jobclasses"
+	// parametersFileName is the name of the parameters configuration file
+	parametersFileName = "parameters.json"
+)
 
 // Variable defines a named expression that can be computed and reused in rules.
 // Variables are evaluated before the main rule and their results are added to the environment.
@@ -45,21 +54,21 @@ type ruleVariable struct {
 // and the final rule expression that determines if the job matches the classification.
 type RuleFormat struct {
 	// Name is a human-readable description of the rule
-	Name         string     `json:"name"`
+	Name string `json:"name"`
 	// Tag is the classification tag to apply if the rule matches
-	Tag          string     `json:"tag"`
+	Tag string `json:"tag"`
 	// Parameters are shared values referenced in the rule (e.g., thresholds)
-	Parameters   []string   `json:"parameters"`
+	Parameters []string `json:"parameters"`
 	// Metrics are the job metrics required for this rule (e.g., "cpu_load", "mem_used")
-	Metrics      []string   `json:"metrics"`
+	Metrics []string `json:"metrics"`
 	// Requirements are boolean expressions that must be true for the rule to apply
-	Requirements []string   `json:"requirements"`
+	Requirements []string `json:"requirements"`
 	// Variables are computed values used in the rule expression
-	Variables    []Variable `json:"variables"`
+	Variables []Variable `json:"variables"`
 	// Rule is the boolean expression that determines if the job matches
-	Rule         string     `json:"rule"`
+	Rule string `json:"rule"`
 	// Hint is a template string that generates a message when the rule matches
-	Hint         string     `json:"hint"`
+	Hint string `json:"hint"`
 }
 
 type ruleInfo struct {
@@ -75,29 +84,29 @@ type ruleInfo struct {
 // This interface allows for easier testing and decoupling from the concrete repository implementation.
 type JobRepository interface {
 	// HasTag checks if a job already has a specific tag
-	HasTag(jobId int64, tagType string, tagName string) bool
+	HasTag(jobID int64, tagType string, tagName string) bool
 	// AddTagOrCreateDirect adds a tag to a job or creates it if it doesn't exist
-	AddTagOrCreateDirect(jobId int64, tagType string, tagName string) (tagId int64, err error)
+	AddTagOrCreateDirect(jobID int64, tagType string, tagName string) (tagID int64, err error)
 	// UpdateMetadata updates job metadata with a key-value pair
 	UpdateMetadata(job *schema.Job, key, val string) (err error)
 }
 
 // JobClassTagger classifies jobs based on configurable rules that evaluate job metrics and properties.
-// Rules are loaded from embedded JSON files and can be dynamically reloaded from a watched directory.
+// Rules are loaded from an external configuration directory and can be dynamically reloaded when files change.
 // When a job matches a rule, it is tagged with the corresponding classification and an optional hint message.
 type JobClassTagger struct {
 	// rules maps classification tags to their compiled rule information
-	rules           map[string]ruleInfo
+	rules map[string]ruleInfo
 	// parameters are shared values (e.g., thresholds) used across multiple rules
-	parameters      map[string]any
+	parameters map[string]any
 	// tagType is the type of tag ("jobClass")
-	tagType         string
+	tagType string
 	// cfgPath is the path to watch for configuration changes
-	cfgPath         string
+	cfgPath string
 	// repo provides access to job database operations
-	repo            JobRepository
+	repo JobRepository
 	// getStatistics retrieves job statistics for analysis
-	getStatistics   func(job *schema.Job) (map[string]schema.JobStatistics, error)
+	getStatistics func(job *schema.Job) (map[string]schema.JobStatistics, error)
 	// getMetricConfig retrieves metric configuration (limits) for a cluster
 	getMetricConfig func(cluster, subCluster string) map[string]*schema.Metric
 }
@@ -169,7 +178,7 @@ func (t *JobClassTagger) prepareRule(b []byte, fns string) {
 // EventMatch checks if a filesystem event should trigger configuration reload.
 // It returns true if the event path contains "jobclasses".
 func (t *JobClassTagger) EventMatch(s string) bool {
-	return strings.Contains(s, "jobclasses")
+	return strings.Contains(s, jobClassConfigDirMatch)
 }
 
 // EventCallback is triggered when the configuration directory changes.
@@ -181,9 +190,10 @@ func (t *JobClassTagger) EventCallback() {
 		cclog.Fatal(err)
 	}
 
-	if util.CheckFileExists(t.cfgPath + "/parameters.json") {
+	parametersFile := filepath.Join(t.cfgPath, parametersFileName)
+	if util.CheckFileExists(parametersFile) {
 		cclog.Info("Merge parameters")
-		b, err := os.ReadFile(t.cfgPath + "/parameters.json")
+		b, err := os.ReadFile(parametersFile)
 		if err != nil {
 			cclog.Warnf("prepareRule() > open file error: %v", err)
 		}
@@ -198,13 +208,13 @@ func (t *JobClassTagger) EventCallback() {
 
 	for _, fn := range files {
 		fns := fn.Name()
-		if fns != "parameters.json" {
+		if fns != parametersFileName {
 			cclog.Debugf("Process: %s", fns)
-			filename := fmt.Sprintf("%s/%s", t.cfgPath, fns)
+			filename := filepath.Join(t.cfgPath, fns)
 			b, err := os.ReadFile(filename)
 			if err != nil {
 				cclog.Warnf("prepareRule() > open file error: %v", err)
-				return
+				continue
 			}
 			t.prepareRule(b, fns)
 		}
@@ -213,7 +223,8 @@ func (t *JobClassTagger) EventCallback() {
 
 func (t *JobClassTagger) initParameters() error {
 	cclog.Info("Initialize parameters")
-	b, err := jobClassFiles.ReadFile("jobclasses/parameters.json")
+	parametersFile := filepath.Join(t.cfgPath, parametersFileName)
+	b, err := os.ReadFile(parametersFile)
 	if err != nil {
 		cclog.Warnf("prepareRule() > open file error: %v", err)
 		return err
@@ -227,13 +238,20 @@ func (t *JobClassTagger) initParameters() error {
 	return nil
 }
 
-// Register initializes the JobClassTagger by loading parameters and classification rules.
-// It loads embedded configuration files and sets up a file watch on ./var/tagger/jobclasses
-// if it exists, allowing for dynamic configuration updates without restarting the application.
-// Returns an error if the embedded configuration files cannot be read or parsed.
+// Register initializes the JobClassTagger by loading parameters and classification rules from external folder.
+// It sets up a file watch on ./var/tagger/jobclasses if it exists, allowing for
+// dynamic configuration updates without restarting the application.
+// Returns an error if the configuration path does not exist or cannot be read.
 func (t *JobClassTagger) Register() error {
-	t.cfgPath = "./var/tagger/jobclasses"
-	t.tagType = "jobClass"
+	if t.cfgPath == "" {
+		t.cfgPath = defaultJobClassConfigPath
+	}
+	t.tagType = tagTypeJobClass
+	t.rules = make(map[string]ruleInfo)
+
+	if !util.CheckFileExists(t.cfgPath) {
+		return fmt.Errorf("configuration path does not exist: %s", t.cfgPath)
+	}
 
 	err := t.initParameters()
 	if err != nil {
@@ -241,31 +259,28 @@ func (t *JobClassTagger) Register() error {
 		return err
 	}
 
-	files, err := jobClassFiles.ReadDir("jobclasses")
+	files, err := os.ReadDir(t.cfgPath)
 	if err != nil {
-		return fmt.Errorf("error reading app folder: %#v", err)
+		return fmt.Errorf("error reading jobclasses folder: %#v", err)
 	}
-	t.rules = make(map[string]ruleInfo)
+
 	for _, fn := range files {
 		fns := fn.Name()
-		if fns != "parameters.json" {
-			filename := fmt.Sprintf("jobclasses/%s", fns)
+		if fns != parametersFileName {
 			cclog.Infof("Process: %s", fns)
+			filename := filepath.Join(t.cfgPath, fns)
 
-			b, err := jobClassFiles.ReadFile(filename)
+			b, err := os.ReadFile(filename)
 			if err != nil {
 				cclog.Warnf("prepareRule() > open file error: %v", err)
-				return err
+				continue
 			}
 			t.prepareRule(b, fns)
 		}
 	}
 
-	if util.CheckFileExists(t.cfgPath) {
-		t.EventCallback()
-		cclog.Infof("Setup file watch for %s", t.cfgPath)
-		util.AddListener(t.cfgPath, t)
-	}
+	cclog.Infof("Setup file watch for %s", t.cfgPath)
+	util.AddListener(t.cfgPath, t)
 
 	t.repo = repository.GetJobRepository()
 	t.getStatistics = archive.GetStatistics
diff --git a/internal/tagger/classifyJob_test.go b/internal/tagger/classifyJob_test.go
index bed7a8f0..f82cf807 100644
--- a/internal/tagger/classifyJob_test.go
+++ b/internal/tagger/classifyJob_test.go
@@ -13,13 +13,13 @@ type MockJobRepository struct {
 	mock.Mock
 }
 
-func (m *MockJobRepository) HasTag(jobId int64, tagType string, tagName string) bool {
-	args := m.Called(jobId, tagType, tagName)
+func (m *MockJobRepository) HasTag(jobID int64, tagType string, tagName string) bool {
+	args := m.Called(jobID, tagType, tagName)
 	return args.Bool(0)
 }
 
-func (m *MockJobRepository) AddTagOrCreateDirect(jobId int64, tagType string, tagName string) (tagId int64, err error) {
-	args := m.Called(jobId, tagType, tagName)
+func (m *MockJobRepository) AddTagOrCreateDirect(jobID int64, tagType string, tagName string) (tagID int64, err error) {
+	args := m.Called(jobID, tagType, tagName)
 	return args.Get(0).(int64), args.Error(1)
 }
 
diff --git a/internal/tagger/detectApp.go b/internal/tagger/detectApp.go
index 0b8e3e7e..2a89ea21 100644
--- a/internal/tagger/detectApp.go
+++ b/internal/tagger/detectApp.go
@@ -7,9 +7,7 @@ package tagger
 
 import (
 	"bufio"
-	"embed"
 	"fmt"
-	"io/fs"
 	"os"
 	"path/filepath"
 	"regexp"
@@ -21,8 +19,14 @@ import (
 	"github.com/ClusterCockpit/cc-lib/v2/util"
 )
 
-//go:embed apps/*
-var appFiles embed.FS
+const (
+	// defaultConfigPath is the default path for application tagging configuration
+	defaultConfigPath = "./var/tagger/apps"
+	// tagTypeApp is the tag type identifier for application tags
+	tagTypeApp = "app"
+	// configDirMatch is the directory name used for matching filesystem events
+	configDirMatch = "apps"
+)
 
 type appInfo struct {
 	tag     string
@@ -30,19 +34,19 @@ type appInfo struct {
 }
 
 // AppTagger detects applications by matching patterns in job scripts.
-// It loads application patterns from embedded files and can dynamically reload
-// configuration from a watched directory. When a job script matches a pattern,
+// It loads application patterns from an external configuration directory and can dynamically reload
+// configuration when files change. When a job script matches a pattern,
 // the corresponding application tag is automatically applied.
 type AppTagger struct {
 	// apps maps application tags to their matching patterns
-	apps    map[string]appInfo
+	apps map[string]appInfo
 	// tagType is the type of tag ("app")
 	tagType string
 	// cfgPath is the path to watch for configuration changes
 	cfgPath string
 }
 
-func (t *AppTagger) scanApp(f fs.File, fns string) {
+func (t *AppTagger) scanApp(f *os.File, fns string) {
 	scanner := bufio.NewScanner(f)
 	ai := appInfo{tag: strings.TrimSuffix(fns, filepath.Ext(fns)), strings: make([]string, 0)}
 
@@ -56,7 +60,7 @@ func (t *AppTagger) scanApp(f fs.File, fns string) {
 // EventMatch checks if a filesystem event should trigger configuration reload.
 // It returns true if the event path contains "apps".
 func (t *AppTagger) EventMatch(s string) bool {
-	return strings.Contains(s, "apps")
+	return strings.Contains(s, configDirMatch)
 }
 
 // EventCallback is triggered when the configuration directory changes.
@@ -71,43 +75,50 @@ func (t *AppTagger) EventCallback() {
 	for _, fn := range files {
 		fns := fn.Name()
 		cclog.Debugf("Process: %s", fns)
-		f, err := os.Open(fmt.Sprintf("%s/%s", t.cfgPath, fns))
+		f, err := os.Open(filepath.Join(t.cfgPath, fns))
 		if err != nil {
 			cclog.Errorf("error opening app file %s: %#v", fns, err)
+			continue
 		}
 		t.scanApp(f, fns)
+		f.Close()
 	}
 }
 
-// Register initializes the AppTagger by loading application patterns from embedded files.
-// It also sets up a file watch on ./var/tagger/apps if it exists, allowing for
+// Register initializes the AppTagger by loading application patterns from external folder.
+// It sets up a file watch on ./var/tagger/apps if it exists, allowing for
 // dynamic configuration updates without restarting the application.
-// Returns an error if the embedded application files cannot be read.
+// Returns an error if the configuration path does not exist or cannot be read.
 func (t *AppTagger) Register() error {
-	t.cfgPath = "./var/tagger/apps"
-	t.tagType = "app"
+	if t.cfgPath == "" {
+		t.cfgPath = defaultConfigPath
+	}
+	t.tagType = tagTypeApp
+	t.apps = make(map[string]appInfo, 0)
 
-	files, err := appFiles.ReadDir("apps")
+	if !util.CheckFileExists(t.cfgPath) {
+		return fmt.Errorf("configuration path does not exist: %s", t.cfgPath)
+	}
+
+	files, err := os.ReadDir(t.cfgPath)
 	if err != nil {
 		return fmt.Errorf("error reading app folder: %#v", err)
 	}
-	t.apps = make(map[string]appInfo, 0)
+
 	for _, fn := range files {
 		fns := fn.Name()
 		cclog.Debugf("Process: %s", fns)
-		f, err := appFiles.Open(fmt.Sprintf("apps/%s", fns))
+		f, err := os.Open(filepath.Join(t.cfgPath, fns))
 		if err != nil {
-			return fmt.Errorf("error opening app file %s: %#v", fns, err)
+			cclog.Errorf("error opening app file %s: %#v", fns, err)
+			continue
 		}
-		defer f.Close()
 		t.scanApp(f, fns)
+		f.Close()
 	}
 
-	if util.CheckFileExists(t.cfgPath) {
-		t.EventCallback()
-		cclog.Infof("Setup file watch for %s", t.cfgPath)
-		util.AddListener(t.cfgPath, t)
-	}
+	cclog.Infof("Setup file watch for %s", t.cfgPath)
+	util.AddListener(t.cfgPath, t)
 
 	return nil
 }
diff --git a/internal/tagger/detectApp_test.go b/internal/tagger/detectApp_test.go
index 1c44f670..fe5e7a21 100644
--- a/internal/tagger/detectApp_test.go
+++ b/internal/tagger/detectApp_test.go
@@ -5,6 +5,8 @@
 package tagger
 
 import (
+	"os"
+	"path/filepath"
 	"testing"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
@@ -29,28 +31,88 @@ func noErr(tb testing.TB, err error) {
 	}
 }
 
-func TestRegister(t *testing.T) {
-	var tagger AppTagger
+func setupAppTaggerTestDir(t *testing.T) string {
+	t.Helper()
 
-	err := tagger.Register()
+	testDir := t.TempDir()
+	appsDir := filepath.Join(testDir, "apps")
+	err := os.MkdirAll(appsDir, 0o755)
 	noErr(t, err)
 
+	srcDir := "../../configs/tagger/apps"
+	files, err := os.ReadDir(srcDir)
+	noErr(t, err)
+
+	for _, file := range files {
+		if file.IsDir() {
+			continue
+		}
+		srcPath := filepath.Join(srcDir, file.Name())
+		dstPath := filepath.Join(appsDir, file.Name())
+
+		data, err := os.ReadFile(srcPath)
+		noErr(t, err)
+
+		err = os.WriteFile(dstPath, data, 0o644)
+		noErr(t, err)
+	}
+
+	return appsDir
+}
+
+func TestRegister(t *testing.T) {
+	appsDir := setupAppTaggerTestDir(t)
+
+	var tagger AppTagger
+	tagger.cfgPath = appsDir
+	tagger.tagType = tagTypeApp
+	tagger.apps = make(map[string]appInfo, 0)
+
+	files, err := os.ReadDir(appsDir)
+	noErr(t, err)
+
+	for _, fn := range files {
+		if fn.IsDir() {
+			continue
+		}
+		fns := fn.Name()
+		f, err := os.Open(filepath.Join(appsDir, fns))
+		noErr(t, err)
+		tagger.scanApp(f, fns)
+		f.Close()
+	}
+
 	if len(tagger.apps) != 16 {
 		t.Errorf("wrong summary for diagnostic \ngot: %d \nwant: 16", len(tagger.apps))
 	}
 }
 
 func TestMatch(t *testing.T) {
+	appsDir := setupAppTaggerTestDir(t)
 	r := setup(t)
 
 	job, err := r.FindByIDDirect(317)
 	noErr(t, err)
 
 	var tagger AppTagger
+	tagger.cfgPath = appsDir
+	tagger.tagType = tagTypeApp
+	tagger.apps = make(map[string]appInfo, 0)
 
-	err = tagger.Register()
+	files, err := os.ReadDir(appsDir)
 	noErr(t, err)
 
+	for _, fn := range files {
+		if fn.IsDir() {
+			continue
+		}
+		fns := fn.Name()
+		f, err := os.Open(filepath.Join(appsDir, fns))
+		noErr(t, err)
+		tagger.scanApp(f, fns)
+		f.Close()
+	}
+
 	tagger.Match(job)
 
 	if !r.HasTag(317, "app", "vasp") {

From a9366d14c66aae29e3da4928558bd74b39662990 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 13 Jan 2026 08:32:32 +0100
Subject: [PATCH 25/59] Add README for tagging. Enable tagging by flag without
 configuration option

---
 cmd/cc-backend/main.go   |   2 +
 configs/tagger/README.md | 419 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 421 insertions(+)

diff --git a/cmd/cc-backend/main.go b/cmd/cc-backend/main.go
index 8eb3c76f..9f98ccbf 100644
--- a/cmd/cc-backend/main.go
+++ b/cmd/cc-backend/main.go
@@ -302,6 +302,8 @@ func initSubsystems() error {
 
 	// Apply tags if requested
 	if flagApplyTags {
+		tagger.Init()
+
 		if err := tagger.RunTaggers(); err != nil {
 			return fmt.Errorf("running job taggers: %w", err)
 		}
diff --git a/configs/tagger/README.md b/configs/tagger/README.md
index e69de29b..759cbe97 100644
--- a/configs/tagger/README.md
+++ b/configs/tagger/README.md
@@ -0,0 +1,419 @@
+# Job Tagging Configuration
+
+ClusterCockpit provides automatic job tagging functionality to classify and
+categorize jobs based on configurable rules. The tagging system consists of two
+main components:
+
+1. **Application Detection** - Identifies which application a job is running
+2. **Job Classification** - Analyzes job performance characteristics and applies classification tags
+
+## Directory Structure
+
+```
+configs/tagger/
+├── apps/              # Application detection patterns
+│   ├── vasp.txt
+│   ├── gromacs.txt
+│   └── ...
+└── jobclasses/        # Job classification rules
+    ├── parameters.json
+    ├── lowUtilization.json
+    ├── highload.json
+    └── ...
+```
+
+## Activating Tagger Rules
+
+### Step 1: Copy Configuration Files
+
+To activate tagging, review, adapt, and copy the configuration files from
+`configs/tagger/` to `var/tagger/`:
+
+```bash
+# From the cc-backend root directory
+mkdir -p var/tagger
+cp -r configs/tagger/apps var/tagger/
+cp -r configs/tagger/jobclasses var/tagger/
+```
+
+### Step 2: Enable Tagging in Configuration
+
+Add or set the following configuration key in the `main` section of your `config.json`:
+
+```json
+{
+  "enable-job-taggers": true
+}
+```
+
+**Important**: Automatic tagging is disabled by default. You must explicitly
+enable it by setting `enable-job-taggers: true` in the main configuration file.
+
+### Step 3: Restart cc-backend
+
+The tagger system automatically loads configuration from `./var/tagger/` at
+startup. After copying the files and enabling the feature, restart cc-backend:
+
+```bash
+./cc-backend -server
+```
+
+### Step 4: Verify Configuration Loaded
+
+Check the logs for messages indicating successful configuration loading:
+
+```
+[INFO] Setup file watch for ./var/tagger/apps
+[INFO] Setup file watch for ./var/tagger/jobclasses
+```
+
+## How Tagging Works
+
+### Automatic Tagging
+
+When `enable-job-taggers` is set to `true` in the configuration, tags are
+automatically applied when:
+
+- **Job Start**: Application detection runs immediately when a job starts
+- **Job Stop**: Job classification runs when a job completes
+
+The system analyzes job metadata and metrics to determine appropriate tags.
+
+**Note**: Automatic tagging only works for jobs that start or stop after the
+feature is enabled. Existing jobs are not automatically retagged.
+
+### Manual Tagging (Retroactive)
+
+To apply tags to existing jobs in the database, use the `-apply-tags` command
+line option:
+
+```bash
+./cc-backend -apply-tags
+```
+
+This processes all jobs in the database and applies current tagging rules. This
+is useful when:
+
+- You have existing jobs that were created before tagging was enabled
+- You've added new tagging rules and want to apply them to historical data
+- You've modified existing rules and want to re-evaluate all jobs
+
+### Hot Reload
+
+The tagger system watches the configuration directories for changes. You can
+modify or add rules without restarting `cc-backend`:
+
+- Changes to `var/tagger/apps/*` are detected automatically
+- Changes to `var/tagger/jobclasses/*` are detected automatically
+
+## Application Detection
+
+Application detection identifies which software a job is running by matching
+patterns in the job script.
+
+### Configuration Format
+
+Application patterns are stored in text files under `var/tagger/apps/`. Each
+file contains one or more regular expression patterns (one per line) that match
+against the job script.
+
+**Example: `apps/vasp.txt`**
+
+```
+vasp
+VASP
+```
+
+### How It Works
+
+1. When a job starts, the system retrieves the job script from metadata
+2. Each line in the app files is treated as a regex pattern
+3. Patterns are matched case-insensitively against the lowercased job script
+4. If a match is found, a tag of type `app` with the filename (without extension) is applied
+5. Only the first matching application is tagged
+
+### Adding New Applications
+
+1. Create a new file in `var/tagger/apps/` (e.g., `tensorflow.txt`)
+2. Add regex patterns, one per line:
+
+   ```
+   tensorflow
+   tf\.keras
+   import tensorflow
+   ```
+
+3. The file is automatically detected and loaded
+
+**Note**: The tag name will be the filename without the `.txt` extension (e.g., `tensorflow`).
+
+## Job Classification
+
+Job classification analyzes completed jobs based on their metrics and properties
+to identify performance issues or characteristics.
+
+### Configuration Format
+
+Job classification rules are defined in JSON files under
+`var/tagger/jobclasses/`. Each rule file defines:
+
+- **Metrics required**: Which job metrics to analyze
+- **Requirements**: Pre-conditions that must be met
+- **Variables**: Computed values used in the rule
+- **Rule expression**: Boolean expression that determines if the rule matches
+- **Hint template**: Message displayed when the rule matches
+
+### Parameters File
+
+`jobclasses/parameters.json` defines shared threshold values used across multiple rules:
+
+```json
+{
+  "lowcpuload_threshold_factor": 0.9,
+  "highmemoryusage_threshold_factor": 0.9,
+  "job_min_duration_seconds": 600.0,
+  "sampling_interval_seconds": 30.0
+}
+```
+
+### Rule File Structure
+
+**Example: `jobclasses/lowUtilization.json`**
+
+```json
+{
+  "name": "Low resource utilization",
+  "tag": "lowutilization",
+  "parameters": ["job_min_duration_seconds"],
+  "metrics": ["flops_any", "mem_bw"],
+  "requirements": [
+    "job.shared == \"none\"",
+    "job.duration > job_min_duration_seconds"
+  ],
+  "variables": [
+    {
+      "name": "mem_bw_perc",
+      "expr": "1.0 - (mem_bw.avg / mem_bw.limits.peak)"
+    }
+  ],
+  "rule": "flops_any.avg < flops_any.limits.alert",
+  "hint": "Average flop rate {{.flops_any.avg}} falls below threshold {{.flops_any.limits.alert}}"
+}
+```
+
+#### Field Descriptions
+
+| Field          | Description                                                                   |
+| -------------- | ----------------------------------------------------------------------------- |
+| `name`         | Human-readable description of the rule                                        |
+| `tag`          | Tag identifier applied when the rule matches                                  |
+| `parameters`   | List of parameter names from `parameters.json` to include in rule environment |
+| `metrics`      | List of metrics required for evaluation (must be present in job data)         |
+| `requirements` | Boolean expressions that must all be true for the rule to be evaluated        |
+| `variables`    | Named expressions computed before evaluating the main rule                    |
+| `rule`         | Boolean expression that determines if the job matches this classification     |
+| `hint`         | Go template string for generating a user-visible message                      |
+
+### Expression Environment
+
+Expressions in `requirements`, `variables`, and `rule` have access to:
+
+**Job Properties:**
+
+- `job.shared` - Shared node allocation type
+- `job.duration` - Job runtime in seconds
+- `job.numCores` - Number of CPU cores
+- `job.numNodes` - Number of nodes
+- `job.jobState` - Job completion state
+- `job.numAcc` - Number of accelerators
+- `job.smt` - SMT setting
+
+**Metric Statistics (for each metric in `metrics`):**
+
+- `<metric>.min` - Minimum value
+- `<metric>.max` - Maximum value
+- `<metric>.avg` - Average value
+- `<metric>.limits.peak` - Peak limit from cluster config
+- `<metric>.limits.normal` - Normal threshold
+- `<metric>.limits.caution` - Caution threshold
+- `<metric>.limits.alert` - Alert threshold
+
+**Parameters:**
+
+- All parameters listed in the `parameters` field
+
+**Variables:**
+
+- All variables defined in the `variables` array
+
+### Expression Language
+
+Rules use the [expr](https://github.com/expr-lang/expr) language for expressions. Supported operations:
+
+- **Arithmetic**: `+`, `-`, `*`, `/`, `%`, `^`
+- **Comparison**: `==`, `!=`, `<`, `<=`, `>`, `>=`
+- **Logical**: `&&`, `||`, `!`
+- **Functions**: Standard math functions (see expr documentation)
+
+### Hint Templates
+
+Hints use Go's `text/template` syntax. Variables from the evaluation environment are accessible:
+
+```
+{{.flops_any.avg}}          # Access metric average
+{{.job.duration}}            # Access job property
+{{.my_variable}}             # Access computed variable
+```
+
+### Adding New Classification Rules
+
+1. Create a new JSON file in `var/tagger/jobclasses/` (e.g., `memoryLeak.json`)
+2. Define the rule structure:
+
+   ```json
+   {
+     "name": "Memory Leak Detection",
+     "tag": "memory_leak",
+     "parameters": ["memory_leak_slope_threshold"],
+     "metrics": ["mem_used"],
+     "requirements": ["job.duration > 3600"],
+     "variables": [
+       {
+         "name": "mem_growth",
+         "expr": "(mem_used.max - mem_used.min) / job.duration"
+       }
+     ],
+     "rule": "mem_growth > memory_leak_slope_threshold",
+     "hint": "Memory usage grew by {{.mem_growth}} per second"
+   }
+   ```
+
+3. Add any new parameters to `parameters.json`
+4. The file is automatically detected and loaded
+
+## Configuration Paths
+
+The tagger system reads from these paths (relative to cc-backend working directory):
+
+- **Application patterns**: `./var/tagger/apps/`
+- **Job classification rules**: `./var/tagger/jobclasses/`
+
+These paths are defined as constants in the source code and cannot be changed without recompiling.
+
+## Troubleshooting
+
+### Tags Not Applied
+
+1. **Check tagging is enabled**: Verify `enable-job-taggers: true` is set in `config.json`
+
+2. **Check configuration exists**:
+
+   ```bash
+   ls -la var/tagger/apps
+   ls -la var/tagger/jobclasses
+   ```
+
+3. **Check logs for errors**:
+
+   ```bash
+   ./cc-backend -server -loglevel debug
+   ```
+
+4. **Verify file permissions**: Ensure cc-backend can read the configuration files
+
+5. **For existing jobs**: Use `./cc-backend -apply-tags` to retroactively tag jobs
+
+### Rules Not Matching
+
+1. **Enable debug logging**: Set `loglevel: debug` to see detailed rule evaluation
+2. **Check requirements**: Ensure all requirements in the rule are satisfied
+3. **Verify metrics exist**: Classification rules require job metrics to be available
+4. **Check metric names**: Ensure metric names match those in your cluster configuration
+
+### File Watch Not Working
+
+If changes to configuration files aren't detected:
+
+1. Restart cc-backend to reload all configuration
+2. Check filesystem supports file watching (network filesystems may not)
+3. Check logs for file watch setup messages
+
+## Best Practices
+
+1. **Start Simple**: Begin with basic rules and refine based on results
+2. **Use Requirements**: Filter out irrelevant jobs early with requirements
+3. **Test Incrementally**: Add one rule at a time and verify behavior
+4. **Document Rules**: Use descriptive names and clear hint messages
+5. **Share Parameters**: Define common thresholds in `parameters.json` for consistency
+6. **Version Control**: Keep your `var/tagger/` configuration in version control
+7. **Backup Before Changes**: Test new rules on a copy before deploying to production
+
+## Examples
+
+### Simple Application Detection
+
+**File: `var/tagger/apps/python.txt`**
+
+```
+python
+python3
+\.py
+```
+
+This detects jobs running Python scripts.
+
+### Complex Classification Rule
+
+**File: `var/tagger/jobclasses/cpuImbalance.json`**
+
+```json
+{
+  "name": "CPU Load Imbalance",
+  "tag": "cpu_imbalance",
+  "parameters": ["core_load_imbalance_threshold_factor"],
+  "metrics": ["cpu_load"],
+  "requirements": ["job.numCores > 1", "job.duration > 600"],
+  "variables": [
+    {
+      "name": "load_variance",
+      "expr": "(cpu_load.max - cpu_load.min) / cpu_load.avg"
+    }
+  ],
+  "rule": "load_variance > core_load_imbalance_threshold_factor",
+  "hint": "CPU load varies by {{printf \"%.1f%%\" (load_variance * 100)}} across cores"
+}
+```
+
+This detects jobs where CPU load is unevenly distributed across cores.
+
+## Reference
+
+### Configuration Options
+
+**Main Configuration (`config.json`)**:
+
+- `enable-job-taggers` (boolean, default: `false`) - Enables automatic job tagging system
+  - Must be set to `true` to activate automatic tagging on job start/stop events
+  - Does not affect the `-apply-tags` command line option
+
+**Command Line Options**:
+
+- `-apply-tags` - Apply all tagging rules to existing jobs in the database
+  - Works independently of `enable-job-taggers` configuration
+  - Useful for retroactively tagging jobs or re-evaluating with updated rules
+
+### Default Configuration Location
+
+The example configurations are provided in:
+
+- `configs/tagger/apps/` - Example application patterns (16 applications)
+- `configs/tagger/jobclasses/` - Example classification rules (3 rules)
+
+Copy these to `var/tagger/` and customize for your environment.
+
+### Tag Types
+
+- `app` - Application tags (e.g., "vasp", "gromacs")
+- `jobClass` - Classification tags (e.g., "lowutilization", "highload")
+
+Tags can be queried and filtered in the ClusterCockpit UI and API.

From 2ebab1e2e2579cccebaec7615b3a1e07cf6bfe49 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 13 Jan 2026 09:50:57 +0100
Subject: [PATCH 26/59] Reformat with gofumpt

---
 internal/auth/auth.go             | 10 ++++----
 internal/auth/auth_test.go        | 40 +++++++++++++++----------------
 internal/auth/jwt.go              |  6 ++---
 internal/auth/jwtCookieSession.go |  4 ++--
 internal/auth/jwtHelpers.go       | 24 +++++++++----------
 internal/auth/jwtHelpers_test.go  | 37 ++++++++++++++--------------
 internal/auth/jwtSession.go       |  4 ++--
 internal/auth/oidc.go             |  4 ++--
 8 files changed, 64 insertions(+), 65 deletions(-)

diff --git a/internal/auth/auth.go b/internal/auth/auth.go
index 3be1768e..41691d00 100644
--- a/internal/auth/auth.go
+++ b/internal/auth/auth.go
@@ -40,7 +40,7 @@ type Authenticator interface {
 	// authenticator should attempt the login. This method should not perform
 	// expensive operations or actual authentication.
 	CanLogin(user *schema.User, username string, rw http.ResponseWriter, r *http.Request) (*schema.User, bool)
-	
+
 	// Login performs the actually authentication for the user.
 	// It returns the authenticated user or an error if authentication fails.
 	// The user parameter may be nil if the user doesn't exist in the database yet.
@@ -65,13 +65,13 @@ var ipUserLimiters sync.Map
 func getIPUserLimiter(ip, username string) *rate.Limiter {
 	key := ip + ":" + username
 	now := time.Now()
-	
+
 	if entry, ok := ipUserLimiters.Load(key); ok {
 		rle := entry.(*rateLimiterEntry)
 		rle.lastUsed = now
 		return rle.limiter
 	}
-	
+
 	// More aggressive rate limiting: 5 attempts per 15 minutes
 	newLimiter := rate.NewLimiter(rate.Every(15*time.Minute/5), 5)
 	ipUserLimiters.Store(key, &rateLimiterEntry{
@@ -176,7 +176,7 @@ func (auth *Authentication) AuthViaSession(
 func Init(authCfg *json.RawMessage) {
 	initOnce.Do(func() {
 		authInstance = &Authentication{}
-		
+
 		// Start background cleanup of rate limiters
 		startRateLimiterCleanup()
 
@@ -272,7 +272,7 @@ func handleUserSync(user *schema.User, syncUserOnLogin, updateUserOnLogin bool)
 		cclog.Errorf("Error while loading user '%s': %v", user.Username, err)
 		return
 	}
-	
+
 	if err == sql.ErrNoRows && syncUserOnLogin { // Add new user
 		if err := r.AddUser(user); err != nil {
 			cclog.Errorf("Error while adding user '%s' to DB: %v", user.Username, err)
diff --git a/internal/auth/auth_test.go b/internal/auth/auth_test.go
index 15f153e6..68961354 100644
--- a/internal/auth/auth_test.go
+++ b/internal/auth/auth_test.go
@@ -15,25 +15,25 @@ import (
 func TestGetIPUserLimiter(t *testing.T) {
 	ip := "192.168.1.1"
 	username := "testuser"
-	
+
 	// Get limiter for the first time
 	limiter1 := getIPUserLimiter(ip, username)
 	if limiter1 == nil {
 		t.Fatal("Expected limiter to be created")
 	}
-	
+
 	// Get the same limiter again
 	limiter2 := getIPUserLimiter(ip, username)
 	if limiter1 != limiter2 {
 		t.Error("Expected to get the same limiter instance")
 	}
-	
+
 	// Get a different limiter for different user
 	limiter3 := getIPUserLimiter(ip, "otheruser")
 	if limiter1 == limiter3 {
 		t.Error("Expected different limiter for different user")
 	}
-	
+
 	// Get a different limiter for different IP
 	limiter4 := getIPUserLimiter("192.168.1.2", username)
 	if limiter1 == limiter4 {
@@ -45,16 +45,16 @@ func TestGetIPUserLimiter(t *testing.T) {
 func TestRateLimiterBehavior(t *testing.T) {
 	ip := "10.0.0.1"
 	username := "ratelimituser"
-	
+
 	limiter := getIPUserLimiter(ip, username)
-	
+
 	// Should allow first 5 attempts
 	for i := 0; i < 5; i++ {
 		if !limiter.Allow() {
 			t.Errorf("Request %d should be allowed within rate limit", i+1)
 		}
 	}
-	
+
 	// 6th attempt should be blocked
 	if limiter.Allow() {
 		t.Error("Request 6 should be blocked by rate limiter")
@@ -65,19 +65,19 @@ func TestRateLimiterBehavior(t *testing.T) {
 func TestCleanupOldRateLimiters(t *testing.T) {
 	// Clear all existing limiters first to avoid interference from other tests
 	cleanupOldRateLimiters(time.Now().Add(24 * time.Hour))
-	
+
 	// Create some new rate limiters
 	limiter1 := getIPUserLimiter("1.1.1.1", "user1")
 	limiter2 := getIPUserLimiter("2.2.2.2", "user2")
-	
+
 	if limiter1 == nil || limiter2 == nil {
 		t.Fatal("Failed to create test limiters")
 	}
-	
+
 	// Cleanup limiters older than 1 second from now (should keep both)
 	time.Sleep(10 * time.Millisecond) // Small delay to ensure timestamp difference
 	cleanupOldRateLimiters(time.Now().Add(-1 * time.Second))
-	
+
 	// Verify they still exist (should get same instance)
 	if getIPUserLimiter("1.1.1.1", "user1") != limiter1 {
 		t.Error("Limiter 1 was incorrectly cleaned up")
@@ -85,10 +85,10 @@ func TestCleanupOldRateLimiters(t *testing.T) {
 	if getIPUserLimiter("2.2.2.2", "user2") != limiter2 {
 		t.Error("Limiter 2 was incorrectly cleaned up")
 	}
-	
+
 	// Cleanup limiters older than 1 hour from now (should remove both)
 	cleanupOldRateLimiters(time.Now().Add(2 * time.Hour))
-	
+
 	// Getting them again should create new instances
 	newLimiter1 := getIPUserLimiter("1.1.1.1", "user1")
 	if newLimiter1 == limiter1 {
@@ -107,14 +107,14 @@ func TestIPv4Extraction(t *testing.T) {
 		{"IPv4 without port", "192.168.1.1", "192.168.1.1"},
 		{"Localhost with port", "127.0.0.1:3000", "127.0.0.1"},
 	}
-	
+
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			result := tt.input
 			if host, _, err := net.SplitHostPort(result); err == nil {
 				result = host
 			}
-			
+
 			if result != tt.expected {
 				t.Errorf("Expected %s, got %s", tt.expected, result)
 			}
@@ -122,7 +122,7 @@ func TestIPv4Extraction(t *testing.T) {
 	}
 }
 
-// TestIPv6Extraction tests extracting IPv6 addresses  
+// TestIPv6Extraction tests extracting IPv6 addresses
 func TestIPv6Extraction(t *testing.T) {
 	tests := []struct {
 		name     string
@@ -134,14 +134,14 @@ func TestIPv6Extraction(t *testing.T) {
 		{"IPv6 without port", "2001:db8::1", "2001:db8::1"},
 		{"IPv6 localhost", "::1", "::1"},
 	}
-	
+
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			result := tt.input
 			if host, _, err := net.SplitHostPort(result); err == nil {
 				result = host
 			}
-			
+
 			if result != tt.expected {
 				t.Errorf("Expected %s, got %s", tt.expected, result)
 			}
@@ -160,14 +160,14 @@ func TestIPExtractionEdgeCases(t *testing.T) {
 		{"Empty string", "", ""},
 		{"Just port", ":8080", ""},
 	}
-	
+
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			result := tt.input
 			if host, _, err := net.SplitHostPort(result); err == nil {
 				result = host
 			}
-			
+
 			if result != tt.expected {
 				t.Errorf("Expected %s, got %s", tt.expected, result)
 			}
diff --git a/internal/auth/jwt.go b/internal/auth/jwt.go
index be642219..c0f641b9 100644
--- a/internal/auth/jwt.go
+++ b/internal/auth/jwt.go
@@ -101,20 +101,20 @@ func (ja *JWTAuthenticator) AuthViaJWT(
 
 	// Token is valid, extract payload
 	claims := token.Claims.(jwt.MapClaims)
-	
+
 	// Use shared helper to get user from JWT claims
 	var user *schema.User
 	user, err = getUserFromJWT(claims, Keys.JwtConfig.ValidateUser, schema.AuthToken, -1)
 	if err != nil {
 		return nil, err
 	}
-	
+
 	// If not validating user, we only get roles from JWT (no projects for this auth method)
 	if !Keys.JwtConfig.ValidateUser {
 		user.Roles = extractRolesFromClaims(claims, false)
 		user.Projects = nil // Standard JWT auth doesn't include projects
 	}
-	
+
 	return user, nil
 }
 
diff --git a/internal/auth/jwtCookieSession.go b/internal/auth/jwtCookieSession.go
index 42f7439e..4c4bbeb6 100644
--- a/internal/auth/jwtCookieSession.go
+++ b/internal/auth/jwtCookieSession.go
@@ -146,13 +146,13 @@ func (ja *JWTCookieSessionAuthenticator) Login(
 	}
 
 	claims := token.Claims.(jwt.MapClaims)
-	
+
 	// Use shared helper to get user from JWT claims
 	user, err = getUserFromJWT(claims, jc.ValidateUser, schema.AuthSession, schema.AuthViaToken)
 	if err != nil {
 		return nil, err
 	}
-	
+
 	// Sync or update user if configured
 	if !jc.ValidateUser && (jc.SyncUserOnLogin || jc.UpdateUserOnLogin) {
 		handleTokenUser(user)
diff --git a/internal/auth/jwtHelpers.go b/internal/auth/jwtHelpers.go
index 5bfc91ef..de59145e 100644
--- a/internal/auth/jwtHelpers.go
+++ b/internal/auth/jwtHelpers.go
@@ -28,7 +28,7 @@ func extractStringFromClaims(claims jwt.MapClaims, key string) string {
 // If validateRoles is true, only valid roles are returned
 func extractRolesFromClaims(claims jwt.MapClaims, validateRoles bool) []string {
 	var roles []string
-	
+
 	if rawroles, ok := claims["roles"].([]any); ok {
 		for _, rr := range rawroles {
 			if r, ok := rr.(string); ok {
@@ -42,14 +42,14 @@ func extractRolesFromClaims(claims jwt.MapClaims, validateRoles bool) []string {
 			}
 		}
 	}
-	
+
 	return roles
 }
 
 // extractProjectsFromClaims extracts projects from JWT claims
 func extractProjectsFromClaims(claims jwt.MapClaims) []string {
 	projects := make([]string, 0)
-	
+
 	if rawprojs, ok := claims["projects"].([]any); ok {
 		for _, pp := range rawprojs {
 			if p, ok := pp.(string); ok {
@@ -61,7 +61,7 @@ func extractProjectsFromClaims(claims jwt.MapClaims) []string {
 			projects = append(projects, projSlice...)
 		}
 	}
-	
+
 	return projects
 }
 
@@ -72,14 +72,14 @@ func extractNameFromClaims(claims jwt.MapClaims) string {
 	if name, ok := claims["name"].(string); ok {
 		return name
 	}
-	
+
 	// Try nested structure: {name: {values: [...]}}
 	if wrap, ok := claims["name"].(map[string]any); ok {
 		if vals, ok := wrap["values"].([]any); ok {
 			if len(vals) == 0 {
 				return ""
 			}
-			
+
 			name := fmt.Sprintf("%v", vals[0])
 			for i := 1; i < len(vals); i++ {
 				name += fmt.Sprintf(" %v", vals[i])
@@ -87,7 +87,7 @@ func extractNameFromClaims(claims jwt.MapClaims) string {
 			return name
 		}
 	}
-	
+
 	return ""
 }
 
@@ -100,7 +100,7 @@ func getUserFromJWT(claims jwt.MapClaims, validateUser bool, authType schema.Aut
 	if sub == "" {
 		return nil, errors.New("missing 'sub' claim in JWT")
 	}
-	
+
 	if validateUser {
 		// Validate user against database
 		ur := repository.GetUserRepository()
@@ -109,22 +109,22 @@ func getUserFromJWT(claims jwt.MapClaims, validateUser bool, authType schema.Aut
 			cclog.Errorf("Error while loading user '%v': %v", sub, err)
 			return nil, fmt.Errorf("database error: %w", err)
 		}
-		
+
 		// Deny any logins for unknown usernames
 		if user == nil || err == sql.ErrNoRows {
 			cclog.Warn("Could not find user from JWT in internal database.")
 			return nil, errors.New("unknown user")
 		}
-		
+
 		// Return database user (with database roles)
 		return user, nil
 	}
-	
+
 	// Create user from JWT claims
 	name := extractNameFromClaims(claims)
 	roles := extractRolesFromClaims(claims, true) // Validate roles
 	projects := extractProjectsFromClaims(claims)
-	
+
 	return &schema.User{
 		Username:   sub,
 		Name:       name,
diff --git a/internal/auth/jwtHelpers_test.go b/internal/auth/jwtHelpers_test.go
index 84a1f2e0..4627f7e5 100644
--- a/internal/auth/jwtHelpers_test.go
+++ b/internal/auth/jwtHelpers_test.go
@@ -19,7 +19,7 @@ func TestExtractStringFromClaims(t *testing.T) {
 		"email": "test@example.com",
 		"age":   25, // not a string
 	}
-	
+
 	tests := []struct {
 		name     string
 		key      string
@@ -30,7 +30,7 @@ func TestExtractStringFromClaims(t *testing.T) {
 		{"Non-existent key", "missing", ""},
 		{"Non-string value", "age", ""},
 	}
-	
+
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			result := extractStringFromClaims(claims, tt.key)
@@ -88,16 +88,16 @@ func TestExtractRolesFromClaims(t *testing.T) {
 			expected:      []string{},
 		},
 	}
-	
+
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			result := extractRolesFromClaims(tt.claims, tt.validateRoles)
-			
+
 			if len(result) != len(tt.expected) {
 				t.Errorf("Expected %d roles, got %d", len(tt.expected), len(result))
 				return
 			}
-			
+
 			for i, role := range result {
 				if i >= len(tt.expected) || role != tt.expected[i] {
 					t.Errorf("Expected role %s at position %d, got %s", tt.expected[i], i, role)
@@ -141,16 +141,16 @@ func TestExtractProjectsFromClaims(t *testing.T) {
 			expected: []string{"project1", "project2"}, // Should skip non-strings
 		},
 	}
-	
+
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			result := extractProjectsFromClaims(tt.claims)
-			
+
 			if len(result) != len(tt.expected) {
 				t.Errorf("Expected %d projects, got %d", len(tt.expected), len(result))
 				return
 			}
-			
+
 			for i, project := range result {
 				if i >= len(tt.expected) || project != tt.expected[i] {
 					t.Errorf("Expected project %s at position %d, got %s", tt.expected[i], i, project)
@@ -216,7 +216,7 @@ func TestExtractNameFromClaims(t *testing.T) {
 			expected: "123 Smith", // Should convert to string
 		},
 	}
-	
+
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			result := extractNameFromClaims(tt.claims)
@@ -235,29 +235,28 @@ func TestGetUserFromJWT_NoValidation(t *testing.T) {
 		"roles":    []any{"user", "admin"},
 		"projects": []any{"project1", "project2"},
 	}
-	
+
 	user, err := getUserFromJWT(claims, false, schema.AuthToken, -1)
-	
 	if err != nil {
 		t.Fatalf("Unexpected error: %v", err)
 	}
-	
+
 	if user.Username != "testuser" {
 		t.Errorf("Expected username 'testuser', got '%s'", user.Username)
 	}
-	
+
 	if user.Name != "Test User" {
 		t.Errorf("Expected name 'Test User', got '%s'", user.Name)
 	}
-	
+
 	if len(user.Roles) != 2 {
 		t.Errorf("Expected 2 roles, got %d", len(user.Roles))
 	}
-	
+
 	if len(user.Projects) != 2 {
 		t.Errorf("Expected 2 projects, got %d", len(user.Projects))
 	}
-	
+
 	if user.AuthType != schema.AuthToken {
 		t.Errorf("Expected AuthType %v, got %v", schema.AuthToken, user.AuthType)
 	}
@@ -268,13 +267,13 @@ func TestGetUserFromJWT_MissingSub(t *testing.T) {
 	claims := jwt.MapClaims{
 		"name": "Test User",
 	}
-	
+
 	_, err := getUserFromJWT(claims, false, schema.AuthToken, -1)
-	
+
 	if err == nil {
 		t.Error("Expected error for missing sub claim")
 	}
-	
+
 	if err.Error() != "missing 'sub' claim in JWT" {
 		t.Errorf("Expected specific error message, got: %v", err)
 	}
diff --git a/internal/auth/jwtSession.go b/internal/auth/jwtSession.go
index 107afcb8..de7e985b 100644
--- a/internal/auth/jwtSession.go
+++ b/internal/auth/jwtSession.go
@@ -75,13 +75,13 @@ func (ja *JWTSessionAuthenticator) Login(
 	}
 
 	claims := token.Claims.(jwt.MapClaims)
-	
+
 	// Use shared helper to get user from JWT claims
 	user, err = getUserFromJWT(claims, Keys.JwtConfig.ValidateUser, schema.AuthSession, schema.AuthViaToken)
 	if err != nil {
 		return nil, err
 	}
-	
+
 	// Sync or update user if configured
 	if !Keys.JwtConfig.ValidateUser && (Keys.JwtConfig.SyncUserOnLogin || Keys.JwtConfig.UpdateUserOnLogin) {
 		handleTokenUser(user)
diff --git a/internal/auth/oidc.go b/internal/auth/oidc.go
index a3fc09cc..b90aca4f 100644
--- a/internal/auth/oidc.go
+++ b/internal/auth/oidc.go
@@ -59,7 +59,7 @@ func NewOIDC(a *Authentication) *OIDC {
 	// Use context with timeout for provider initialization
 	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
 	defer cancel()
-	
+
 	provider, err := oidc.NewProvider(ctx, Keys.OpenIDConfig.Provider)
 	if err != nil {
 		cclog.Fatal(err)
@@ -119,7 +119,7 @@ func (oa *OIDC) OAuth2Callback(rw http.ResponseWriter, r *http.Request) {
 	// Exchange authorization code for token with timeout
 	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
 	defer cancel()
-	
+
 	token, err := oa.client.Exchange(ctx, code, oauth2.VerifierOption(codeVerifier))
 	if err != nil {
 		http.Error(rw, "Failed to exchange token: "+err.Error(), http.StatusInternalServerError)

From 04a2e460ae8b1e884795bdf5200e1efb671ac958 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 13 Jan 2026 09:52:00 +0100
Subject: [PATCH 27/59] Refactor metricstore. Initial stub for cluster/
 subcluster specific retention times

---
 internal/metricstore/avroCheckpoint.go        |   6 +-
 internal/metricstore/config.go                |  70 ++++++++++-
 internal/metricstore/configSchema.go          |  38 +++++-
 .../{memorystore.go => metricstore.go}        | 114 ++++++++++++++----
 ...emorystore_test.go => metricstore_test.go} |   2 +-
 5 files changed, 203 insertions(+), 27 deletions(-)
 rename internal/metricstore/{memorystore.go => metricstore.go} (76%)
 rename internal/metricstore/{memorystore_test.go => metricstore_test.go} (99%)

diff --git a/internal/metricstore/avroCheckpoint.go b/internal/metricstore/avroCheckpoint.go
index 275a64bd..aa14ce5a 100644
--- a/internal/metricstore/avroCheckpoint.go
+++ b/internal/metricstore/avroCheckpoint.go
@@ -24,8 +24,10 @@ import (
 	"github.com/linkedin/goavro/v2"
 )
 
-var NumAvroWorkers int = DefaultAvroWorkers
-var startUp bool = true
+var (
+	NumAvroWorkers int  = DefaultAvroWorkers
+	startUp        bool = true
+)
 
 func (as *AvroStore) ToCheckpoint(dir string, dumpAll bool) (int, error) {
 	levels := make([]*AvroLevel, 0)
diff --git a/internal/metricstore/config.go b/internal/metricstore/config.go
index 97f16c46..06ae774d 100644
--- a/internal/metricstore/config.go
+++ b/internal/metricstore/config.go
@@ -33,8 +33,19 @@ type MetricStoreConfig struct {
 		DumpToFile string `json:"dump-to-file"`
 		EnableGops bool   `json:"gops"`
 	} `json:"debug"`
+	// Global default retention duration
 	RetentionInMemory string `json:"retention-in-memory"`
-	Archive           struct {
+	// Per-cluster retention overrides
+	Clusters []struct {
+		Cluster           string `json:"cluster"`
+		RetentionInMemory string `json:"retention-in-memory"`
+		// Per-subcluster retention overrides within this cluster
+		SubClusters []struct {
+			SubCluster        string `json:"subcluster"`
+			RetentionInMemory string `json:"retention-in-memory"`
+		} `json:"subclusters,omitempty"`
+	} `json:"clusters,omitempty"`
+	Archive struct {
 		Interval      string `json:"interval"`
 		RootDir       string `json:"directory"`
 		DeleteInstead bool   `json:"delete-instead"`
@@ -50,6 +61,14 @@ type MetricStoreConfig struct {
 
 var Keys MetricStoreConfig
 
+type retentionConfig struct {
+	global        time.Duration
+	clusterMap    map[string]time.Duration
+	subClusterMap map[string]map[string]time.Duration
+}
+
+var retentionLookup *retentionConfig
+
 // AggregationStrategy for aggregation over multiple values at different cpus/sockets/..., not time!
 type AggregationStrategy int
 
@@ -113,3 +132,52 @@ func AddMetric(name string, metric MetricConfig) error {
 
 	return nil
 }
+
+func GetRetentionDuration(cluster, subCluster string) (time.Duration, error) {
+	if retentionLookup == nil {
+		return 0, fmt.Errorf("[METRICSTORE]> retention configuration not initialized")
+	}
+
+	if subCluster != "" {
+		if subMap, ok := retentionLookup.subClusterMap[cluster]; ok {
+			if retention, ok := subMap[subCluster]; ok {
+				return retention, nil
+			}
+		}
+	}
+
+	if retention, ok := retentionLookup.clusterMap[cluster]; ok {
+		return retention, nil
+	}
+
+	return retentionLookup.global, nil
+}
+
+// GetShortestRetentionDuration returns the shortest configured retention duration
+// across all levels (global, cluster, and subcluster configurations).
+// Returns 0 if retentionLookup is not initialized or global retention is not set.
+func GetShortestRetentionDuration() time.Duration {
+	if retentionLookup == nil || retentionLookup.global <= 0 {
+		return 0
+	}
+
+	shortest := retentionLookup.global
+
+	// Check all cluster-level retention durations
+	for _, clusterRetention := range retentionLookup.clusterMap {
+		if clusterRetention > 0 && clusterRetention < shortest {
+			shortest = clusterRetention
+		}
+	}
+
+	// Check all subcluster-level retention durations
+	for _, subClusterMap := range retentionLookup.subClusterMap {
+		for _, scRetention := range subClusterMap {
+			if scRetention > 0 && scRetention < shortest {
+				shortest = scRetention
+			}
+		}
+	}
+
+	return shortest
+}
diff --git a/internal/metricstore/configSchema.go b/internal/metricstore/configSchema.go
index f1a20a73..868bacc5 100644
--- a/internal/metricstore/configSchema.go
+++ b/internal/metricstore/configSchema.go
@@ -46,9 +46,45 @@ const configSchema = `{
             }
         },
         "retention-in-memory": {
-            "description": "Keep the metrics within memory for given time interval. Retention for X hours, then the metrics would be freed.",
+            "description": "Global default: Keep the metrics within memory for given time interval. Retention for X hours, then the metrics would be freed.",
             "type": "string"
         },
+        "clusters": {
+            "description": "Optional per-cluster retention overrides",
+            "type": "array",
+            "items": {
+                "type": "object",
+                "required": ["cluster"],
+                "properties": {
+                    "cluster": {
+                        "description": "Cluster name",
+                        "type": "string"
+                    },
+                    "retention-in-memory": {
+                        "description": "Cluster-specific retention duration (overrides global default)",
+                        "type": "string"
+                    },
+                    "subclusters": {
+                        "description": "Optional per-subcluster retention overrides",
+                        "type": "array",
+                        "items": {
+                            "type": "object",
+                            "required": ["subcluster"],
+                            "properties": {
+                                "subcluster": {
+                                    "description": "Subcluster name",
+                                    "type": "string"
+                                },
+                                "retention-in-memory": {
+                                    "description": "Subcluster-specific retention duration (overrides cluster and global default)",
+                                    "type": "string"
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+        },
         "nats": {
             "description": "Configuration for accepting published data through NATS.",
             "type": "array",
diff --git a/internal/metricstore/memorystore.go b/internal/metricstore/metricstore.go
similarity index 76%
rename from internal/metricstore/memorystore.go
rename to internal/metricstore/metricstore.go
index 14a02fcd..5a5c3bce 100644
--- a/internal/metricstore/memorystore.go
+++ b/internal/metricstore/metricstore.go
@@ -98,6 +98,49 @@ func Init(rawConfig json.RawMessage, wg *sync.WaitGroup) {
 		}
 	}
 
+	globalRetention, err := time.ParseDuration(Keys.RetentionInMemory)
+	if err != nil {
+		cclog.Fatal(err)
+	}
+
+	retentionLookup = &retentionConfig{
+		global:        globalRetention,
+		clusterMap:    make(map[string]time.Duration),
+		subClusterMap: make(map[string]map[string]time.Duration),
+	}
+
+	for _, clusterCfg := range Keys.Clusters {
+		if clusterCfg.RetentionInMemory != "" {
+			clusterRetention, err := time.ParseDuration(clusterCfg.RetentionInMemory)
+			if err != nil {
+				cclog.Warnf("[METRICSTORE]> Invalid retention duration for cluster '%s': %s\n", clusterCfg.Cluster, err.Error())
+				continue
+			}
+			retentionLookup.clusterMap[clusterCfg.Cluster] = clusterRetention
+			cclog.Debugf("[METRICSTORE]> Cluster '%s' retention: %s\n", clusterCfg.Cluster, clusterRetention)
+		}
+
+		if len(clusterCfg.SubClusters) > 0 {
+			if retentionLookup.subClusterMap[clusterCfg.Cluster] == nil {
+				retentionLookup.subClusterMap[clusterCfg.Cluster] = make(map[string]time.Duration)
+			}
+
+			for _, scCfg := range clusterCfg.SubClusters {
+				if scCfg.RetentionInMemory != "" {
+					scRetention, err := time.ParseDuration(scCfg.RetentionInMemory)
+					if err != nil {
+						cclog.Warnf("[METRICSTORE]> Invalid retention duration for subcluster '%s/%s': %s\n",
+							clusterCfg.Cluster, scCfg.SubCluster, err.Error())
+						continue
+					}
+					retentionLookup.subClusterMap[clusterCfg.Cluster][scCfg.SubCluster] = scRetention
+					cclog.Debugf("[METRICSTORE]> SubCluster '%s/%s' retention: %s\n",
+						clusterCfg.Cluster, scCfg.SubCluster, scRetention)
+				}
+			}
+		}
+	}
+
 	// Pass the config.MetricStoreKeys
 	InitMetrics(Metrics)
 
@@ -208,32 +251,22 @@ func Shutdown() {
 	cclog.Infof("[METRICSTORE]> Done! (%d files written)\n", files)
 }
 
-func getName(m *MemoryStore, i int) string {
-	for key, val := range m.Metrics {
-		if val.offset == i {
-			return key
-		}
-	}
-	return ""
-}
-
 func Retention(wg *sync.WaitGroup, ctx context.Context) {
 	ms := GetMemoryStore()
 
 	go func() {
 		defer wg.Done()
-		d, err := time.ParseDuration(Keys.RetentionInMemory)
-		if err != nil {
-			cclog.Fatal(err)
-		}
-		if d <= 0 {
+		shortestRetention := GetShortestRetentionDuration()
+		if shortestRetention <= 0 {
 			return
 		}
 
-		tickInterval := d / 2
+		tickInterval := shortestRetention / 2
 		if tickInterval <= 0 {
 			return
 		}
+		cclog.Debugf("[METRICSTORE]> Retention ticker interval set to %s (half of shortest retention: %s)\n",
+			tickInterval, shortestRetention)
 		ticker := time.NewTicker(tickInterval)
 		defer ticker.Stop()
 
@@ -242,13 +275,50 @@ func Retention(wg *sync.WaitGroup, ctx context.Context) {
 			case <-ctx.Done():
 				return
 			case <-ticker.C:
-				t := time.Now().Add(-d)
-				cclog.Infof("[METRICSTORE]> start freeing buffers (older than %s)...\n", t.Format(time.RFC3339))
-				freed, err := ms.Free(nil, t.Unix())
-				if err != nil {
-					cclog.Errorf("[METRICSTORE]> freeing up buffers failed: %s\n", err.Error())
-				} else {
-					cclog.Infof("[METRICSTORE]> done: %d buffers freed\n", freed)
+				totalFreed := 0
+
+				clusters := ms.ListChildren(nil)
+				for _, cluster := range clusters {
+					retention, err := GetRetentionDuration(cluster, "")
+					if err != nil {
+						cclog.Warnf("[METRICSTORE]> Could not get retention for cluster '%s': %s\n", cluster, err.Error())
+						continue
+					}
+					if retention <= 0 {
+						continue
+					}
+
+					t := time.Now().Add(-retention)
+					cclog.Debugf("[METRICSTORE]> Freeing buffers for cluster '%s' (older than %s, retention: %s)...\n",
+						cluster, t.Format(time.RFC3339), retention)
+
+					subClusters := ms.ListChildren([]string{cluster})
+					for _, subCluster := range subClusters {
+						scRetention, err := GetRetentionDuration(cluster, subCluster)
+						if err != nil {
+							cclog.Warnf("[METRICSTORE]> Could not get retention for subcluster '%s/%s': %s\n",
+								cluster, subCluster, err.Error())
+							continue
+						}
+						if scRetention <= 0 {
+							continue
+						}
+
+						scTime := time.Now().Add(-scRetention)
+						freed, err := ms.Free([]string{cluster, subCluster}, scTime.Unix())
+						if err != nil {
+							cclog.Errorf("[METRICSTORE]> freeing buffers for '%s/%s' failed: %s\n",
+								cluster, subCluster, err.Error())
+						} else if freed > 0 {
+							cclog.Debugf("[METRICSTORE]> freed %d buffers for '%s/%s' (retention: %s)\n",
+								freed, cluster, subCluster, scRetention)
+							totalFreed += freed
+						}
+					}
+				}
+
+				if totalFreed > 0 {
+					cclog.Infof("[METRICSTORE]> Total buffers freed: %d\n", totalFreed)
 				}
 			}
 		}
diff --git a/internal/metricstore/memorystore_test.go b/internal/metricstore/metricstore_test.go
similarity index 99%
rename from internal/metricstore/memorystore_test.go
rename to internal/metricstore/metricstore_test.go
index 29379d21..fd7c963f 100644
--- a/internal/metricstore/memorystore_test.go
+++ b/internal/metricstore/metricstore_test.go
@@ -131,7 +131,7 @@ func TestBufferWrite(t *testing.T) {
 
 func TestBufferRead(t *testing.T) {
 	b := newBuffer(100, 10)
-	
+
 	// Write some test data
 	b.write(100, schema.Float(1.0))
 	b.write(110, schema.Float(2.0))

From 754f7e16f67e0708a479831c8360064d74147633 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 13 Jan 2026 09:52:31 +0100
Subject: [PATCH 28/59] Reformat with gofumpt

---
 internal/repository/node.go     |  1 -
 pkg/archive/fsBackend.go        |  4 ++--
 pkg/archive/s3Backend_test.go   | 42 ++++++++++++++++-----------------
 tools/archive-manager/main.go   |  1 -
 tools/archive-migration/main.go |  3 +--
 5 files changed, 24 insertions(+), 27 deletions(-)

diff --git a/internal/repository/node.go b/internal/repository/node.go
index 752a36fa..2890cdbc 100644
--- a/internal/repository/node.go
+++ b/internal/repository/node.go
@@ -561,7 +561,6 @@ func (r *NodeRepository) GetNodesForList(
 	nodeFilter string,
 	page *model.PageRequest,
 ) ([]string, map[string]string, int, bool, error) {
-
 	// Init Return Vars
 	nodes := make([]string, 0)
 	stateMap := make(map[string]string)
diff --git a/pkg/archive/fsBackend.go b/pkg/archive/fsBackend.go
index 020f2aa4..61921d70 100644
--- a/pkg/archive/fsBackend.go
+++ b/pkg/archive/fsBackend.go
@@ -188,7 +188,7 @@ func (fsa *FsArchive) Init(rawConfig json.RawMessage) (uint64, error) {
 			if isEmpty {
 				cclog.Infof("fsBackend Init() > Bootstrapping new archive at %s", fsa.path)
 				versionStr := fmt.Sprintf("%d\n", Version)
-				if err := os.WriteFile(filepath.Join(fsa.path, "version.txt"), []byte(versionStr), 0644); err != nil {
+				if err := os.WriteFile(filepath.Join(fsa.path, "version.txt"), []byte(versionStr), 0o644); err != nil {
 					cclog.Errorf("fsBackend Init() > failed to create version.txt: %v", err)
 					return 0, err
 				}
@@ -674,7 +674,7 @@ func (fsa *FsArchive) ImportJob(
 
 func (fsa *FsArchive) StoreClusterCfg(name string, config *schema.Cluster) error {
 	dir := filepath.Join(fsa.path, name)
-	if err := os.MkdirAll(dir, 0777); err != nil {
+	if err := os.MkdirAll(dir, 0o777); err != nil {
 		cclog.Errorf("StoreClusterCfg() > mkdir error: %v", err)
 		return err
 	}
diff --git a/pkg/archive/s3Backend_test.go b/pkg/archive/s3Backend_test.go
index 2b79db7f..0b4e17a2 100644
--- a/pkg/archive/s3Backend_test.go
+++ b/pkg/archive/s3Backend_test.go
@@ -41,7 +41,7 @@ func (m *MockS3Client) GetObject(ctx context.Context, params *s3.GetObjectInput,
 	if !exists {
 		return nil, fmt.Errorf("NoSuchKey: object not found")
 	}
-	
+
 	contentLength := int64(len(data))
 	return &s3.GetObjectOutput{
 		Body:          io.NopCloser(bytes.NewReader(data)),
@@ -65,7 +65,7 @@ func (m *MockS3Client) HeadObject(ctx context.Context, params *s3.HeadObjectInpu
 	if !exists {
 		return nil, fmt.Errorf("NotFound")
 	}
-	
+
 	contentLength := int64(len(data))
 	return &s3.HeadObjectOutput{
 		ContentLength: &contentLength,
@@ -86,12 +86,12 @@ func (m *MockS3Client) CopyObject(ctx context.Context, params *s3.CopyObjectInpu
 		return nil, fmt.Errorf("invalid CopySource")
 	}
 	sourceKey := parts[1]
-	
+
 	data, exists := m.objects[sourceKey]
 	if !exists {
 		return nil, fmt.Errorf("source not found")
 	}
-	
+
 	destKey := aws.ToString(params.Key)
 	m.objects[destKey] = data
 	return &s3.CopyObjectOutput{}, nil
@@ -100,15 +100,15 @@ func (m *MockS3Client) CopyObject(ctx context.Context, params *s3.CopyObjectInpu
 func (m *MockS3Client) ListObjectsV2(ctx context.Context, params *s3.ListObjectsV2Input, optFns ...func(*s3.Options)) (*s3.ListObjectsV2Output, error) {
 	prefix := aws.ToString(params.Prefix)
 	delimiter := aws.ToString(params.Delimiter)
-	
+
 	var contents []types.Object
 	commonPrefixes := make(map[string]bool)
-	
+
 	for key, data := range m.objects {
 		if !strings.HasPrefix(key, prefix) {
 			continue
 		}
-		
+
 		if delimiter != "" {
 			// Check if there's a delimiter after the prefix
 			remainder := strings.TrimPrefix(key, prefix)
@@ -120,21 +120,21 @@ func (m *MockS3Client) ListObjectsV2(ctx context.Context, params *s3.ListObjects
 				continue
 			}
 		}
-		
+
 		size := int64(len(data))
 		contents = append(contents, types.Object{
 			Key:  aws.String(key),
 			Size: &size,
 		})
 	}
-	
+
 	var prefixList []types.CommonPrefix
 	for p := range commonPrefixes {
 		prefixList = append(prefixList, types.CommonPrefix{
 			Prefix: aws.String(p),
 		})
 	}
-	
+
 	return &s3.ListObjectsV2Output{
 		Contents:       contents,
 		CommonPrefixes: prefixList,
@@ -144,10 +144,10 @@ func (m *MockS3Client) ListObjectsV2(ctx context.Context, params *s3.ListObjects
 // Test helper to create a mock S3 archive with test data
 func setupMockS3Archive(t *testing.T) *MockS3Client {
 	mock := NewMockS3Client()
-	
+
 	// Add version.txt
 	mock.objects["version.txt"] = []byte("2\n")
-	
+
 	// Add a test cluster directory
 	mock.objects["emmy/cluster.json"] = []byte(`{
 		"name": "emmy",
@@ -165,7 +165,7 @@ func setupMockS3Archive(t *testing.T) *MockS3Client {
 			}
 		]
 	}`)
-	
+
 	// Add a test job
 	mock.objects["emmy/1403/244/1608923076/meta.json"] = []byte(`{
 		"jobId": 1403244,
@@ -174,7 +174,7 @@ func setupMockS3Archive(t *testing.T) *MockS3Client {
 		"numNodes": 1,
 		"resources": [{"hostname": "node001"}]
 	}`)
-	
+
 	mock.objects["emmy/1403/244/1608923076/data.json"] = []byte(`{
 		"mem_used": {
 			"node": {
@@ -184,7 +184,7 @@ func setupMockS3Archive(t *testing.T) *MockS3Client {
 			}
 		}
 	}`)
-	
+
 	return mock
 }
 
@@ -213,7 +213,7 @@ func TestGetS3Key(t *testing.T) {
 		Cluster:   "emmy",
 		StartTime: 1608923076,
 	}
-	
+
 	key := getS3Key(job, "meta.json")
 	expected := "emmy/1403/244/1608923076/meta.json"
 	if key != expected {
@@ -227,7 +227,7 @@ func TestGetS3Directory(t *testing.T) {
 		Cluster:   "emmy",
 		StartTime: 1608923076,
 	}
-	
+
 	dir := getS3Directory(job)
 	expected := "emmy/1403/244/1608923076/"
 	if dir != expected {
@@ -247,13 +247,13 @@ func TestS3ArchiveConfigParsing(t *testing.T) {
 		"region": "us-east-1",
 		"usePathStyle": true
 	}`)
-	
+
 	var cfg S3ArchiveConfig
 	err := json.Unmarshal(rawConfig, &cfg)
 	if err != nil {
 		t.Fatalf("failed to parse config: %v", err)
 	}
-	
+
 	if cfg.Bucket != "test-bucket" {
 		t.Errorf("expected bucket 'test-bucket', got '%s'", cfg.Bucket)
 	}
@@ -277,14 +277,14 @@ func TestS3KeyGeneration(t *testing.T) {
 		{1404397, "emmy", 1609300556, "data.json.gz", "emmy/1404/397/1609300556/data.json.gz"},
 		{42, "fritz", 1234567890, "meta.json", "fritz/0/042/1234567890/meta.json"},
 	}
-	
+
 	for _, tt := range tests {
 		job := &schema.Job{
 			JobID:     tt.jobID,
 			Cluster:   tt.cluster,
 			StartTime: tt.startTime,
 		}
-		
+
 		key := getS3Key(job, tt.file)
 		if key != tt.expected {
 			t.Errorf("for job %d: expected %s, got %s", tt.jobID, tt.expected, key)
diff --git a/tools/archive-manager/main.go b/tools/archive-manager/main.go
index ffcba793..fff81256 100644
--- a/tools/archive-manager/main.go
+++ b/tools/archive-manager/main.go
@@ -71,7 +71,6 @@ func countJobsNative(archivePath string) (int, error) {
 		}
 		return nil
 	})
-
 	if err != nil {
 		return 0, fmt.Errorf("failed to walk directory: %w", err)
 	}
diff --git a/tools/archive-migration/main.go b/tools/archive-migration/main.go
index 8375ee98..1384e065 100644
--- a/tools/archive-migration/main.go
+++ b/tools/archive-migration/main.go
@@ -70,7 +70,6 @@ func main() {
 
 	// Run migration
 	migrated, failed, err := migrateArchive(archivePath, dryRun, numWorkers)
-
 	if err != nil {
 		cclog.Errorf("Migration completed with errors: %s", err.Error())
 		if failed > 0 {
@@ -104,5 +103,5 @@ func checkVersion(archivePath string) error {
 
 func updateVersion(archivePath string) error {
 	versionFile := filepath.Join(archivePath, "version.txt")
-	return os.WriteFile(versionFile, []byte("3\n"), 0644)
+	return os.WriteFile(versionFile, []byte("3\n"), 0o644)
 }

From 25c8fca56136eb04cbfe14d5f18a67082512bc64 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Tue, 13 Jan 2026 14:42:24 +0100
Subject: [PATCH 29/59] Revert retention config in metricstore

---
 internal/metricstore/config.go       |  68 ------------------
 internal/metricstore/configSchema.go |  38 +---------
 internal/metricstore/metricstore.go  | 103 ++++-----------------------
 3 files changed, 13 insertions(+), 196 deletions(-)

diff --git a/internal/metricstore/config.go b/internal/metricstore/config.go
index 06ae774d..c789f11c 100644
--- a/internal/metricstore/config.go
+++ b/internal/metricstore/config.go
@@ -33,18 +33,7 @@ type MetricStoreConfig struct {
 		DumpToFile string `json:"dump-to-file"`
 		EnableGops bool   `json:"gops"`
 	} `json:"debug"`
-	// Global default retention duration
-	RetentionInMemory string `json:"retention-in-memory"`
-	// Per-cluster retention overrides
-	Clusters []struct {
-		Cluster           string `json:"cluster"`
 		RetentionInMemory string `json:"retention-in-memory"`
-		// Per-subcluster retention overrides within this cluster
-		SubClusters []struct {
-			SubCluster        string `json:"subcluster"`
-			RetentionInMemory string `json:"retention-in-memory"`
-		} `json:"subclusters,omitempty"`
-	} `json:"clusters,omitempty"`
 	Archive struct {
 		Interval      string `json:"interval"`
 		RootDir       string `json:"directory"`
@@ -61,14 +50,6 @@ type MetricStoreConfig struct {
 
 var Keys MetricStoreConfig
 
-type retentionConfig struct {
-	global        time.Duration
-	clusterMap    map[string]time.Duration
-	subClusterMap map[string]map[string]time.Duration
-}
-
-var retentionLookup *retentionConfig
-
 // AggregationStrategy for aggregation over multiple values at different cpus/sockets/..., not time!
 type AggregationStrategy int
 
@@ -132,52 +113,3 @@ func AddMetric(name string, metric MetricConfig) error {
 
 	return nil
 }
-
-func GetRetentionDuration(cluster, subCluster string) (time.Duration, error) {
-	if retentionLookup == nil {
-		return 0, fmt.Errorf("[METRICSTORE]> retention configuration not initialized")
-	}
-
-	if subCluster != "" {
-		if subMap, ok := retentionLookup.subClusterMap[cluster]; ok {
-			if retention, ok := subMap[subCluster]; ok {
-				return retention, nil
-			}
-		}
-	}
-
-	if retention, ok := retentionLookup.clusterMap[cluster]; ok {
-		return retention, nil
-	}
-
-	return retentionLookup.global, nil
-}
-
-// GetShortestRetentionDuration returns the shortest configured retention duration
-// across all levels (global, cluster, and subcluster configurations).
-// Returns 0 if retentionLookup is not initialized or global retention is not set.
-func GetShortestRetentionDuration() time.Duration {
-	if retentionLookup == nil || retentionLookup.global <= 0 {
-		return 0
-	}
-
-	shortest := retentionLookup.global
-
-	// Check all cluster-level retention durations
-	for _, clusterRetention := range retentionLookup.clusterMap {
-		if clusterRetention > 0 && clusterRetention < shortest {
-			shortest = clusterRetention
-		}
-	}
-
-	// Check all subcluster-level retention durations
-	for _, subClusterMap := range retentionLookup.subClusterMap {
-		for _, scRetention := range subClusterMap {
-			if scRetention > 0 && scRetention < shortest {
-				shortest = scRetention
-			}
-		}
-	}
-
-	return shortest
-}
diff --git a/internal/metricstore/configSchema.go b/internal/metricstore/configSchema.go
index 868bacc5..f1a20a73 100644
--- a/internal/metricstore/configSchema.go
+++ b/internal/metricstore/configSchema.go
@@ -46,45 +46,9 @@ const configSchema = `{
             }
         },
         "retention-in-memory": {
-            "description": "Global default: Keep the metrics within memory for given time interval. Retention for X hours, then the metrics would be freed.",
+            "description": "Keep the metrics within memory for given time interval. Retention for X hours, then the metrics would be freed.",
             "type": "string"
         },
-        "clusters": {
-            "description": "Optional per-cluster retention overrides",
-            "type": "array",
-            "items": {
-                "type": "object",
-                "required": ["cluster"],
-                "properties": {
-                    "cluster": {
-                        "description": "Cluster name",
-                        "type": "string"
-                    },
-                    "retention-in-memory": {
-                        "description": "Cluster-specific retention duration (overrides global default)",
-                        "type": "string"
-                    },
-                    "subclusters": {
-                        "description": "Optional per-subcluster retention overrides",
-                        "type": "array",
-                        "items": {
-                            "type": "object",
-                            "required": ["subcluster"],
-                            "properties": {
-                                "subcluster": {
-                                    "description": "Subcluster name",
-                                    "type": "string"
-                                },
-                                "retention-in-memory": {
-                                    "description": "Subcluster-specific retention duration (overrides cluster and global default)",
-                                    "type": "string"
-                                }
-                            }
-                        }
-                    }
-                }
-            }
-        },
         "nats": {
             "description": "Configuration for accepting published data through NATS.",
             "type": "array",
diff --git a/internal/metricstore/metricstore.go b/internal/metricstore/metricstore.go
index 5a5c3bce..ac8948ae 100644
--- a/internal/metricstore/metricstore.go
+++ b/internal/metricstore/metricstore.go
@@ -98,49 +98,6 @@ func Init(rawConfig json.RawMessage, wg *sync.WaitGroup) {
 		}
 	}
 
-	globalRetention, err := time.ParseDuration(Keys.RetentionInMemory)
-	if err != nil {
-		cclog.Fatal(err)
-	}
-
-	retentionLookup = &retentionConfig{
-		global:        globalRetention,
-		clusterMap:    make(map[string]time.Duration),
-		subClusterMap: make(map[string]map[string]time.Duration),
-	}
-
-	for _, clusterCfg := range Keys.Clusters {
-		if clusterCfg.RetentionInMemory != "" {
-			clusterRetention, err := time.ParseDuration(clusterCfg.RetentionInMemory)
-			if err != nil {
-				cclog.Warnf("[METRICSTORE]> Invalid retention duration for cluster '%s': %s\n", clusterCfg.Cluster, err.Error())
-				continue
-			}
-			retentionLookup.clusterMap[clusterCfg.Cluster] = clusterRetention
-			cclog.Debugf("[METRICSTORE]> Cluster '%s' retention: %s\n", clusterCfg.Cluster, clusterRetention)
-		}
-
-		if len(clusterCfg.SubClusters) > 0 {
-			if retentionLookup.subClusterMap[clusterCfg.Cluster] == nil {
-				retentionLookup.subClusterMap[clusterCfg.Cluster] = make(map[string]time.Duration)
-			}
-
-			for _, scCfg := range clusterCfg.SubClusters {
-				if scCfg.RetentionInMemory != "" {
-					scRetention, err := time.ParseDuration(scCfg.RetentionInMemory)
-					if err != nil {
-						cclog.Warnf("[METRICSTORE]> Invalid retention duration for subcluster '%s/%s': %s\n",
-							clusterCfg.Cluster, scCfg.SubCluster, err.Error())
-						continue
-					}
-					retentionLookup.subClusterMap[clusterCfg.Cluster][scCfg.SubCluster] = scRetention
-					cclog.Debugf("[METRICSTORE]> SubCluster '%s/%s' retention: %s\n",
-						clusterCfg.Cluster, scCfg.SubCluster, scRetention)
-				}
-			}
-		}
-	}
-
 	// Pass the config.MetricStoreKeys
 	InitMetrics(Metrics)
 
@@ -256,17 +213,18 @@ func Retention(wg *sync.WaitGroup, ctx context.Context) {
 
 	go func() {
 		defer wg.Done()
-		shortestRetention := GetShortestRetentionDuration()
-		if shortestRetention <= 0 {
+		d, err := time.ParseDuration(Keys.RetentionInMemory)
+		if err != nil {
+			cclog.Fatal(err)
+		}
+		if d <= 0 {
 			return
 		}
 
-		tickInterval := shortestRetention / 2
+		tickInterval := d / 2
 		if tickInterval <= 0 {
 			return
 		}
-		cclog.Debugf("[METRICSTORE]> Retention ticker interval set to %s (half of shortest retention: %s)\n",
-			tickInterval, shortestRetention)
 		ticker := time.NewTicker(tickInterval)
 		defer ticker.Stop()
 
@@ -275,50 +233,13 @@ func Retention(wg *sync.WaitGroup, ctx context.Context) {
 			case <-ctx.Done():
 				return
 			case <-ticker.C:
-				totalFreed := 0
-
-				clusters := ms.ListChildren(nil)
-				for _, cluster := range clusters {
-					retention, err := GetRetentionDuration(cluster, "")
-					if err != nil {
-						cclog.Warnf("[METRICSTORE]> Could not get retention for cluster '%s': %s\n", cluster, err.Error())
-						continue
-					}
-					if retention <= 0 {
-						continue
-					}
-
-					t := time.Now().Add(-retention)
-					cclog.Debugf("[METRICSTORE]> Freeing buffers for cluster '%s' (older than %s, retention: %s)...\n",
-						cluster, t.Format(time.RFC3339), retention)
-
-					subClusters := ms.ListChildren([]string{cluster})
-					for _, subCluster := range subClusters {
-						scRetention, err := GetRetentionDuration(cluster, subCluster)
+				t := time.Now().Add(-d)
+				cclog.Infof("[METRICSTORE]> start freeing buffers (older than %s)...\n", t.Format(time.RFC3339))
+				freed, err := ms.Free(nil, t.Unix())
 						if err != nil {
-							cclog.Warnf("[METRICSTORE]> Could not get retention for subcluster '%s/%s': %s\n",
-								cluster, subCluster, err.Error())
-							continue
-						}
-						if scRetention <= 0 {
-							continue
-						}
-
-						scTime := time.Now().Add(-scRetention)
-						freed, err := ms.Free([]string{cluster, subCluster}, scTime.Unix())
-						if err != nil {
-							cclog.Errorf("[METRICSTORE]> freeing buffers for '%s/%s' failed: %s\n",
-								cluster, subCluster, err.Error())
-						} else if freed > 0 {
-							cclog.Debugf("[METRICSTORE]> freed %d buffers for '%s/%s' (retention: %s)\n",
-								freed, cluster, subCluster, scRetention)
-							totalFreed += freed
-						}
-					}
-				}
-
-				if totalFreed > 0 {
-					cclog.Infof("[METRICSTORE]> Total buffers freed: %d\n", totalFreed)
+					cclog.Errorf("[METRICSTORE]> freeing up buffers failed: %s\n", err.Error())
+				} else {
+					cclog.Infof("[METRICSTORE]> done: %d buffers freed\n", freed)
 				}
 			}
 		}

From 518e9950eac893f54d1d441901860d7e12de71dc Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Tue, 13 Jan 2026 16:59:52 +0100
Subject: [PATCH 30/59] add job exclusivity filter, review db indices

---
 api/schema.graphqls                           |   1 +
 internal/graph/generated/generated.go         | 258 +++++++++---------
 internal/graph/model/models_gen.go            |   1 +
 internal/graph/schema.resolvers.go            |  16 +-
 internal/repository/jobQuery.go               |  88 +++---
 .../sqlite3/09_add-job-cache.up.sql           |  72 ++---
 .../migrations/sqlite3/10_node-table.up.sql   |   2 -
 internal/routerConfig/routes.go               |   6 +
 web/frontend/src/generic/Filters.svelte       |  94 ++++---
 .../src/generic/filters/JobStates.svelte      |  75 ++++-
 10 files changed, 365 insertions(+), 248 deletions(-)

diff --git a/api/schema.graphqls b/api/schema.graphqls
index 1c81e6b6..7be43f73 100644
--- a/api/schema.graphqls
+++ b/api/schema.graphqls
@@ -458,6 +458,7 @@ input JobFilter {
   state: [JobState!]
   metricStats: [MetricStatItem!]
   shared: String
+  schedule: String
   node: StringInput
 }
 
diff --git a/internal/graph/generated/generated.go b/internal/graph/generated/generated.go
index d96ccf1d..2d3aca04 100644
--- a/internal/graph/generated/generated.go
+++ b/internal/graph/generated/generated.go
@@ -2741,6 +2741,7 @@ input JobFilter {
   state: [JobState!]
   metricStats: [MetricStatItem!]
   shared: String
+  schedule: String
   node: StringInput
 }
 
@@ -3002,7 +3003,7 @@ func (ec *executionContext) field_Query_jobMetrics_args(ctx context.Context, raw
 		return nil, err
 	}
 	args["metrics"] = arg1
-	arg2, err := graphql.ProcessArgField(ctx, rawArgs, "scopes", ec.unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScopeᚄ)
+	arg2, err := graphql.ProcessArgField(ctx, rawArgs, "scopes", ec.unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScopeᚄ)
 	if err != nil {
 		return nil, err
 	}
@@ -3159,7 +3160,7 @@ func (ec *executionContext) field_Query_nodeMetricsList_args(ctx context.Context
 		return nil, err
 	}
 	args["nodeFilter"] = arg3
-	arg4, err := graphql.ProcessArgField(ctx, rawArgs, "scopes", ec.unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScopeᚄ)
+	arg4, err := graphql.ProcessArgField(ctx, rawArgs, "scopes", ec.unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScopeᚄ)
 	if err != nil {
 		return nil, err
 	}
@@ -3205,7 +3206,7 @@ func (ec *executionContext) field_Query_nodeMetrics_args(ctx context.Context, ra
 		return nil, err
 	}
 	args["nodes"] = arg1
-	arg2, err := graphql.ProcessArgField(ctx, rawArgs, "scopes", ec.unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScopeᚄ)
+	arg2, err := graphql.ProcessArgField(ctx, rawArgs, "scopes", ec.unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScopeᚄ)
 	if err != nil {
 		return nil, err
 	}
@@ -3336,7 +3337,7 @@ func (ec *executionContext) field_Query_scopedJobStats_args(ctx context.Context,
 		return nil, err
 	}
 	args["metrics"] = arg1
-	arg2, err := graphql.ProcessArgField(ctx, rawArgs, "scopes", ec.unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScopeᚄ)
+	arg2, err := graphql.ProcessArgField(ctx, rawArgs, "scopes", ec.unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScopeᚄ)
 	if err != nil {
 		return nil, err
 	}
@@ -3562,7 +3563,7 @@ func (ec *executionContext) _Cluster_subClusters(ctx context.Context, field grap
 			return obj.SubClusters, nil
 		},
 		nil,
-		ec.marshalNSubCluster2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSubClusterᚄ,
+		ec.marshalNSubCluster2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSubClusterᚄ,
 		true,
 		true,
 	)
@@ -3648,7 +3649,7 @@ func (ec *executionContext) _ClusterMetricWithName_unit(ctx context.Context, fie
 			return obj.Unit, nil
 		},
 		nil,
-		ec.marshalOUnit2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐUnit,
+		ec.marshalOUnit2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐUnit,
 		true,
 		false,
 	)
@@ -3712,7 +3713,7 @@ func (ec *executionContext) _ClusterMetricWithName_data(ctx context.Context, fie
 			return obj.Data, nil
 		},
 		nil,
-		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ,
+		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ,
 		true,
 		true,
 	)
@@ -4200,7 +4201,7 @@ func (ec *executionContext) _GlobalMetricListItem_unit(ctx context.Context, fiel
 			return obj.Unit, nil
 		},
 		nil,
-		ec.marshalNUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐUnit,
+		ec.marshalNUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐUnit,
 		true,
 		true,
 	)
@@ -4235,7 +4236,7 @@ func (ec *executionContext) _GlobalMetricListItem_scope(ctx context.Context, fie
 			return obj.Scope, nil
 		},
 		nil,
-		ec.marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScope,
+		ec.marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScope,
 		true,
 		true,
 	)
@@ -4293,7 +4294,7 @@ func (ec *executionContext) _GlobalMetricListItem_availability(ctx context.Conte
 			return obj.Availability, nil
 		},
 		nil,
-		ec.marshalNClusterSupport2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐClusterSupportᚄ,
+		ec.marshalNClusterSupport2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐClusterSupportᚄ,
 		true,
 		true,
 	)
@@ -4966,7 +4967,7 @@ func (ec *executionContext) _Job_state(ctx context.Context, field graphql.Collec
 			return obj.State, nil
 		},
 		nil,
-		ec.marshalNJobState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobState,
+		ec.marshalNJobState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobState,
 		true,
 		true,
 	)
@@ -4995,7 +4996,7 @@ func (ec *executionContext) _Job_tags(ctx context.Context, field graphql.Collect
 			return ec.resolvers.Job().Tags(ctx, obj)
 		},
 		nil,
-		ec.marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTagᚄ,
+		ec.marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTagᚄ,
 		true,
 		true,
 	)
@@ -5034,7 +5035,7 @@ func (ec *executionContext) _Job_resources(ctx context.Context, field graphql.Co
 			return obj.Resources, nil
 		},
 		nil,
-		ec.marshalNResource2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐResourceᚄ,
+		ec.marshalNResource2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐResourceᚄ,
 		true,
 		true,
 	)
@@ -5401,7 +5402,7 @@ func (ec *executionContext) _JobMetric_unit(ctx context.Context, field graphql.C
 			return obj.Unit, nil
 		},
 		nil,
-		ec.marshalOUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐUnit,
+		ec.marshalOUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐUnit,
 		true,
 		false,
 	)
@@ -5465,7 +5466,7 @@ func (ec *executionContext) _JobMetric_series(ctx context.Context, field graphql
 			return obj.Series, nil
 		},
 		nil,
-		ec.marshalOSeries2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSeriesᚄ,
+		ec.marshalOSeries2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSeriesᚄ,
 		true,
 		false,
 	)
@@ -5504,7 +5505,7 @@ func (ec *executionContext) _JobMetric_statisticsSeries(ctx context.Context, fie
 			return obj.StatisticsSeries, nil
 		},
 		nil,
-		ec.marshalOStatsSeries2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐStatsSeries,
+		ec.marshalOStatsSeries2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐStatsSeries,
 		true,
 		false,
 	)
@@ -5572,7 +5573,7 @@ func (ec *executionContext) _JobMetricWithName_scope(ctx context.Context, field
 			return obj.Scope, nil
 		},
 		nil,
-		ec.marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScope,
+		ec.marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScope,
 		true,
 		true,
 	)
@@ -5601,7 +5602,7 @@ func (ec *executionContext) _JobMetricWithName_metric(ctx context.Context, field
 			return obj.Metric, nil
 		},
 		nil,
-		ec.marshalNJobMetric2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobMetric,
+		ec.marshalNJobMetric2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobMetric,
 		true,
 		true,
 	)
@@ -5640,7 +5641,7 @@ func (ec *executionContext) _JobResultList_items(ctx context.Context, field grap
 			return obj.Items, nil
 		},
 		nil,
-		ec.marshalNJob2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobᚄ,
+		ec.marshalNJob2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobᚄ,
 		true,
 		true,
 	)
@@ -6720,7 +6721,7 @@ func (ec *executionContext) _MetricConfig_unit(ctx context.Context, field graphq
 			return obj.Unit, nil
 		},
 		nil,
-		ec.marshalNUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐUnit,
+		ec.marshalNUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐUnit,
 		true,
 		true,
 	)
@@ -6755,7 +6756,7 @@ func (ec *executionContext) _MetricConfig_scope(ctx context.Context, field graph
 			return obj.Scope, nil
 		},
 		nil,
-		ec.marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScope,
+		ec.marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScope,
 		true,
 		true,
 	)
@@ -6987,7 +6988,7 @@ func (ec *executionContext) _MetricConfig_subClusters(ctx context.Context, field
 			return obj.SubClusters, nil
 		},
 		nil,
-		ec.marshalNSubClusterConfig2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSubClusterConfigᚄ,
+		ec.marshalNSubClusterConfig2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSubClusterConfigᚄ,
 		true,
 		true,
 	)
@@ -7059,7 +7060,7 @@ func (ec *executionContext) _MetricFootprints_data(ctx context.Context, field gr
 			return obj.Data, nil
 		},
 		nil,
-		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ,
+		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ,
 		true,
 		true,
 	)
@@ -7446,7 +7447,7 @@ func (ec *executionContext) _MetricValue_unit(ctx context.Context, field graphql
 			return obj.Unit, nil
 		},
 		nil,
-		ec.marshalNUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐUnit,
+		ec.marshalNUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐUnit,
 		true,
 		true,
 	)
@@ -7511,7 +7512,7 @@ func (ec *executionContext) _Mutation_createTag(ctx context.Context, field graph
 			return ec.resolvers.Mutation().CreateTag(ctx, fc.Args["type"].(string), fc.Args["name"].(string), fc.Args["scope"].(string))
 		},
 		nil,
-		ec.marshalNTag2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTag,
+		ec.marshalNTag2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTag,
 		true,
 		true,
 	)
@@ -7603,7 +7604,7 @@ func (ec *executionContext) _Mutation_addTagsToJob(ctx context.Context, field gr
 			return ec.resolvers.Mutation().AddTagsToJob(ctx, fc.Args["job"].(string), fc.Args["tagIds"].([]string))
 		},
 		nil,
-		ec.marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTagᚄ,
+		ec.marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTagᚄ,
 		true,
 		true,
 	)
@@ -7654,7 +7655,7 @@ func (ec *executionContext) _Mutation_removeTagsFromJob(ctx context.Context, fie
 			return ec.resolvers.Mutation().RemoveTagsFromJob(ctx, fc.Args["job"].(string), fc.Args["tagIds"].([]string))
 		},
 		nil,
-		ec.marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTagᚄ,
+		ec.marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTagᚄ,
 		true,
 		true,
 	)
@@ -7815,7 +7816,7 @@ func (ec *executionContext) _NamedStats_data(ctx context.Context, field graphql.
 			return obj.Data, nil
 		},
 		nil,
-		ec.marshalNMetricStatistics2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricStatistics,
+		ec.marshalNMetricStatistics2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricStatistics,
 		true,
 		true,
 	)
@@ -7881,7 +7882,7 @@ func (ec *executionContext) _NamedStatsWithScope_scope(ctx context.Context, fiel
 			return obj.Scope, nil
 		},
 		nil,
-		ec.marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScope,
+		ec.marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScope,
 		true,
 		true,
 	)
@@ -8179,7 +8180,7 @@ func (ec *executionContext) _Node_schedulerState(ctx context.Context, field grap
 			return ec.resolvers.Node().SchedulerState(ctx, obj)
 		},
 		nil,
-		ec.marshalNSchedulerState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSchedulerState,
+		ec.marshalNSchedulerState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSchedulerState,
 		true,
 		true,
 	)
@@ -8390,7 +8391,7 @@ func (ec *executionContext) _NodeStateResultList_items(ctx context.Context, fiel
 			return obj.Items, nil
 		},
 		nil,
-		ec.marshalNNode2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐNodeᚄ,
+		ec.marshalNNode2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐNodeᚄ,
 		true,
 		true,
 	)
@@ -8801,7 +8802,7 @@ func (ec *executionContext) _Query_clusters(ctx context.Context, field graphql.C
 			return ec.resolvers.Query().Clusters(ctx)
 		},
 		nil,
-		ec.marshalNCluster2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐClusterᚄ,
+		ec.marshalNCluster2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐClusterᚄ,
 		true,
 		true,
 	)
@@ -8838,7 +8839,7 @@ func (ec *executionContext) _Query_tags(ctx context.Context, field graphql.Colle
 			return ec.resolvers.Query().Tags(ctx)
 		},
 		nil,
-		ec.marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTagᚄ,
+		ec.marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTagᚄ,
 		true,
 		true,
 	)
@@ -8877,7 +8878,7 @@ func (ec *executionContext) _Query_globalMetrics(ctx context.Context, field grap
 			return ec.resolvers.Query().GlobalMetrics(ctx)
 		},
 		nil,
-		ec.marshalNGlobalMetricListItem2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐGlobalMetricListItemᚄ,
+		ec.marshalNGlobalMetricListItem2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐGlobalMetricListItemᚄ,
 		true,
 		true,
 	)
@@ -9015,7 +9016,7 @@ func (ec *executionContext) _Query_node(ctx context.Context, field graphql.Colle
 			return ec.resolvers.Query().Node(ctx, fc.Args["id"].(string))
 		},
 		nil,
-		ec.marshalONode2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐNode,
+		ec.marshalONode2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐNode,
 		true,
 		false,
 	)
@@ -9223,7 +9224,7 @@ func (ec *executionContext) _Query_job(ctx context.Context, field graphql.Collec
 			return ec.resolvers.Query().Job(ctx, fc.Args["id"].(string))
 		},
 		nil,
-		ec.marshalOJob2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJob,
+		ec.marshalOJob2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJob,
 		true,
 		false,
 	)
@@ -10180,7 +10181,7 @@ func (ec *executionContext) _ScopedStats_data(ctx context.Context, field graphql
 			return obj.Data, nil
 		},
 		nil,
-		ec.marshalNMetricStatistics2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricStatistics,
+		ec.marshalNMetricStatistics2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricStatistics,
 		true,
 		true,
 	)
@@ -10275,7 +10276,7 @@ func (ec *executionContext) _Series_statistics(ctx context.Context, field graphq
 			return obj.Statistics, nil
 		},
 		nil,
-		ec.marshalOMetricStatistics2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricStatistics,
+		ec.marshalOMetricStatistics2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricStatistics,
 		true,
 		false,
 	)
@@ -10312,7 +10313,7 @@ func (ec *executionContext) _Series_data(ctx context.Context, field graphql.Coll
 			return obj.Data, nil
 		},
 		nil,
-		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ,
+		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ,
 		true,
 		true,
 	)
@@ -10341,7 +10342,7 @@ func (ec *executionContext) _StatsSeries_mean(ctx context.Context, field graphql
 			return obj.Mean, nil
 		},
 		nil,
-		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ,
+		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ,
 		true,
 		true,
 	)
@@ -10370,7 +10371,7 @@ func (ec *executionContext) _StatsSeries_median(ctx context.Context, field graph
 			return obj.Median, nil
 		},
 		nil,
-		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ,
+		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ,
 		true,
 		true,
 	)
@@ -10399,7 +10400,7 @@ func (ec *executionContext) _StatsSeries_min(ctx context.Context, field graphql.
 			return obj.Min, nil
 		},
 		nil,
-		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ,
+		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ,
 		true,
 		true,
 	)
@@ -10428,7 +10429,7 @@ func (ec *executionContext) _StatsSeries_max(ctx context.Context, field graphql.
 			return obj.Max, nil
 		},
 		nil,
-		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ,
+		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ,
 		true,
 		true,
 	)
@@ -10660,7 +10661,7 @@ func (ec *executionContext) _SubCluster_flopRateScalar(ctx context.Context, fiel
 			return obj.FlopRateScalar, nil
 		},
 		nil,
-		ec.marshalNMetricValue2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricValue,
+		ec.marshalNMetricValue2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricValue,
 		true,
 		true,
 	)
@@ -10697,7 +10698,7 @@ func (ec *executionContext) _SubCluster_flopRateSimd(ctx context.Context, field
 			return obj.FlopRateSimd, nil
 		},
 		nil,
-		ec.marshalNMetricValue2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricValue,
+		ec.marshalNMetricValue2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricValue,
 		true,
 		true,
 	)
@@ -10734,7 +10735,7 @@ func (ec *executionContext) _SubCluster_memoryBandwidth(ctx context.Context, fie
 			return obj.MemoryBandwidth, nil
 		},
 		nil,
-		ec.marshalNMetricValue2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricValue,
+		ec.marshalNMetricValue2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricValue,
 		true,
 		true,
 	)
@@ -10771,7 +10772,7 @@ func (ec *executionContext) _SubCluster_topology(ctx context.Context, field grap
 			return obj.Topology, nil
 		},
 		nil,
-		ec.marshalNTopology2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTopology,
+		ec.marshalNTopology2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTopology,
 		true,
 		true,
 	)
@@ -10814,7 +10815,7 @@ func (ec *executionContext) _SubCluster_metricConfig(ctx context.Context, field
 			return obj.MetricConfig, nil
 		},
 		nil,
-		ec.marshalNMetricConfig2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricConfigᚄ,
+		ec.marshalNMetricConfig2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfigᚄ,
 		true,
 		true,
 	)
@@ -11273,7 +11274,7 @@ func (ec *executionContext) _TimeWeights_nodeHours(ctx context.Context, field gr
 			return obj.NodeHours, nil
 		},
 		nil,
-		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ,
+		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ,
 		true,
 		true,
 	)
@@ -11302,7 +11303,7 @@ func (ec *executionContext) _TimeWeights_accHours(ctx context.Context, field gra
 			return obj.AccHours, nil
 		},
 		nil,
-		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ,
+		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ,
 		true,
 		true,
 	)
@@ -11331,7 +11332,7 @@ func (ec *executionContext) _TimeWeights_coreHours(ctx context.Context, field gr
 			return obj.CoreHours, nil
 		},
 		nil,
-		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ,
+		ec.marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ,
 		true,
 		true,
 	)
@@ -11505,7 +11506,7 @@ func (ec *executionContext) _Topology_accelerators(ctx context.Context, field gr
 			return obj.Accelerators, nil
 		},
 		nil,
-		ec.marshalOAccelerator2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐAcceleratorᚄ,
+		ec.marshalOAccelerator2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐAcceleratorᚄ,
 		true,
 		false,
 	)
@@ -13198,7 +13199,7 @@ func (ec *executionContext) unmarshalInputJobFilter(ctx context.Context, obj any
 		asMap[k] = v
 	}
 
-	fieldsInOrder := [...]string{"tags", "dbId", "jobId", "arrayJobId", "user", "project", "jobName", "cluster", "partition", "duration", "energy", "minRunningFor", "numNodes", "numAccelerators", "numHWThreads", "startTime", "state", "metricStats", "shared", "node"}
+	fieldsInOrder := [...]string{"tags", "dbId", "jobId", "arrayJobId", "user", "project", "jobName", "cluster", "partition", "duration", "energy", "minRunningFor", "numNodes", "numAccelerators", "numHWThreads", "startTime", "state", "metricStats", "shared", "schedule", "node"}
 	for _, k := range fieldsInOrder {
 		v, ok := asMap[k]
 		if !ok {
@@ -13319,7 +13320,7 @@ func (ec *executionContext) unmarshalInputJobFilter(ctx context.Context, obj any
 			it.StartTime = data
 		case "state":
 			ctx := graphql.WithPathContext(ctx, graphql.NewPathWithField("state"))
-			data, err := ec.unmarshalOJobState2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobStateᚄ(ctx, v)
+			data, err := ec.unmarshalOJobState2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobStateᚄ(ctx, v)
 			if err != nil {
 				return it, err
 			}
@@ -13338,6 +13339,13 @@ func (ec *executionContext) unmarshalInputJobFilter(ctx context.Context, obj any
 				return it, err
 			}
 			it.Shared = data
+		case "schedule":
+			ctx := graphql.WithPathContext(ctx, graphql.NewPathWithField("schedule"))
+			data, err := ec.unmarshalOString2ᚖstring(ctx, v)
+			if err != nil {
+				return it, err
+			}
+			it.Schedule = data
 		case "node":
 			ctx := graphql.WithPathContext(ctx, graphql.NewPathWithField("node"))
 			data, err := ec.unmarshalOStringInput2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑbackendᚋinternalᚋgraphᚋmodelᚐStringInput(ctx, v)
@@ -13422,7 +13430,7 @@ func (ec *executionContext) unmarshalInputNodeFilter(ctx context.Context, obj an
 			it.Subcluster = data
 		case "schedulerState":
 			ctx := graphql.WithPathContext(ctx, graphql.NewPathWithField("schedulerState"))
-			data, err := ec.unmarshalOSchedulerState2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSchedulerState(ctx, v)
+			data, err := ec.unmarshalOSchedulerState2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSchedulerState(ctx, v)
 			if err != nil {
 				return it, err
 			}
@@ -17481,7 +17489,7 @@ func (ec *executionContext) ___Type(ctx context.Context, sel ast.SelectionSet, o
 
 // region    ***************************** type.gotpl *****************************
 
-func (ec *executionContext) marshalNAccelerator2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐAccelerator(ctx context.Context, sel ast.SelectionSet, v *schema.Accelerator) graphql.Marshaler {
+func (ec *executionContext) marshalNAccelerator2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐAccelerator(ctx context.Context, sel ast.SelectionSet, v *schema.Accelerator) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -17507,7 +17515,7 @@ func (ec *executionContext) marshalNBoolean2bool(ctx context.Context, sel ast.Se
 	return res
 }
 
-func (ec *executionContext) marshalNCluster2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐClusterᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Cluster) graphql.Marshaler {
+func (ec *executionContext) marshalNCluster2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐClusterᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Cluster) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -17531,7 +17539,7 @@ func (ec *executionContext) marshalNCluster2ᚕᚖgithubᚗcomᚋClusterCockpit
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNCluster2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐCluster(ctx, sel, v[i])
+			ret[i] = ec.marshalNCluster2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐCluster(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -17551,7 +17559,7 @@ func (ec *executionContext) marshalNCluster2ᚕᚖgithubᚗcomᚋClusterCockpit
 	return ret
 }
 
-func (ec *executionContext) marshalNCluster2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐCluster(ctx context.Context, sel ast.SelectionSet, v *schema.Cluster) graphql.Marshaler {
+func (ec *executionContext) marshalNCluster2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐCluster(ctx context.Context, sel ast.SelectionSet, v *schema.Cluster) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -17629,11 +17637,11 @@ func (ec *executionContext) marshalNClusterMetrics2ᚖgithubᚗcomᚋClusterCock
 	return ec._ClusterMetrics(ctx, sel, v)
 }
 
-func (ec *executionContext) marshalNClusterSupport2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐClusterSupport(ctx context.Context, sel ast.SelectionSet, v schema.ClusterSupport) graphql.Marshaler {
+func (ec *executionContext) marshalNClusterSupport2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐClusterSupport(ctx context.Context, sel ast.SelectionSet, v schema.ClusterSupport) graphql.Marshaler {
 	return ec._ClusterSupport(ctx, sel, &v)
 }
 
-func (ec *executionContext) marshalNClusterSupport2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐClusterSupportᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.ClusterSupport) graphql.Marshaler {
+func (ec *executionContext) marshalNClusterSupport2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐClusterSupportᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.ClusterSupport) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -17657,7 +17665,7 @@ func (ec *executionContext) marshalNClusterSupport2ᚕgithubᚗcomᚋClusterCock
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNClusterSupport2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐClusterSupport(ctx, sel, v[i])
+			ret[i] = ec.marshalNClusterSupport2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐClusterSupport(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -17812,7 +17820,7 @@ func (ec *executionContext) unmarshalNFloatRange2ᚖgithubᚗcomᚋClusterCockpi
 	return &res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) marshalNGlobalMetricListItem2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐGlobalMetricListItemᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.GlobalMetricListItem) graphql.Marshaler {
+func (ec *executionContext) marshalNGlobalMetricListItem2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐGlobalMetricListItemᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.GlobalMetricListItem) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -17836,7 +17844,7 @@ func (ec *executionContext) marshalNGlobalMetricListItem2ᚕᚖgithubᚗcomᚋCl
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNGlobalMetricListItem2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐGlobalMetricListItem(ctx, sel, v[i])
+			ret[i] = ec.marshalNGlobalMetricListItem2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐGlobalMetricListItem(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -17856,7 +17864,7 @@ func (ec *executionContext) marshalNGlobalMetricListItem2ᚕᚖgithubᚗcomᚋCl
 	return ret
 }
 
-func (ec *executionContext) marshalNGlobalMetricListItem2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐGlobalMetricListItem(ctx context.Context, sel ast.SelectionSet, v *schema.GlobalMetricListItem) graphql.Marshaler {
+func (ec *executionContext) marshalNGlobalMetricListItem2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐGlobalMetricListItem(ctx context.Context, sel ast.SelectionSet, v *schema.GlobalMetricListItem) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -18134,7 +18142,7 @@ func (ec *executionContext) marshalNInt2ᚖint(ctx context.Context, sel ast.Sele
 	return res
 }
 
-func (ec *executionContext) marshalNJob2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Job) graphql.Marshaler {
+func (ec *executionContext) marshalNJob2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Job) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -18158,7 +18166,7 @@ func (ec *executionContext) marshalNJob2ᚕᚖgithubᚗcomᚋClusterCockpitᚋcc
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNJob2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJob(ctx, sel, v[i])
+			ret[i] = ec.marshalNJob2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJob(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -18178,7 +18186,7 @@ func (ec *executionContext) marshalNJob2ᚕᚖgithubᚗcomᚋClusterCockpitᚋcc
 	return ret
 }
 
-func (ec *executionContext) marshalNJob2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJob(ctx context.Context, sel ast.SelectionSet, v *schema.Job) graphql.Marshaler {
+func (ec *executionContext) marshalNJob2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJob(ctx context.Context, sel ast.SelectionSet, v *schema.Job) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -18262,7 +18270,7 @@ func (ec *executionContext) marshalNJobLink2ᚖgithubᚗcomᚋClusterCockpitᚋc
 	return ec._JobLink(ctx, sel, v)
 }
 
-func (ec *executionContext) marshalNJobMetric2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobMetric(ctx context.Context, sel ast.SelectionSet, v *schema.JobMetric) graphql.Marshaler {
+func (ec *executionContext) marshalNJobMetric2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobMetric(ctx context.Context, sel ast.SelectionSet, v *schema.JobMetric) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -18340,13 +18348,13 @@ func (ec *executionContext) marshalNJobResultList2ᚖgithubᚗcomᚋClusterCockp
 	return ec._JobResultList(ctx, sel, v)
 }
 
-func (ec *executionContext) unmarshalNJobState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobState(ctx context.Context, v any) (schema.JobState, error) {
+func (ec *executionContext) unmarshalNJobState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobState(ctx context.Context, v any) (schema.JobState, error) {
 	var res schema.JobState
 	err := res.UnmarshalGQL(v)
 	return res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) marshalNJobState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobState(ctx context.Context, sel ast.SelectionSet, v schema.JobState) graphql.Marshaler {
+func (ec *executionContext) marshalNJobState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobState(ctx context.Context, sel ast.SelectionSet, v schema.JobState) graphql.Marshaler {
 	return v
 }
 
@@ -18458,11 +18466,11 @@ func (ec *executionContext) marshalNJobsStatistics2ᚖgithubᚗcomᚋClusterCock
 	return ec._JobsStatistics(ctx, sel, v)
 }
 
-func (ec *executionContext) marshalNMetricConfig2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricConfig(ctx context.Context, sel ast.SelectionSet, v schema.MetricConfig) graphql.Marshaler {
+func (ec *executionContext) marshalNMetricConfig2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfig(ctx context.Context, sel ast.SelectionSet, v schema.MetricConfig) graphql.Marshaler {
 	return ec._MetricConfig(ctx, sel, &v)
 }
 
-func (ec *executionContext) marshalNMetricConfig2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricConfigᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.MetricConfig) graphql.Marshaler {
+func (ec *executionContext) marshalNMetricConfig2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfigᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.MetricConfig) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -18486,7 +18494,7 @@ func (ec *executionContext) marshalNMetricConfig2ᚕgithubᚗcomᚋClusterCockpi
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNMetricConfig2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricConfig(ctx, sel, v[i])
+			ret[i] = ec.marshalNMetricConfig2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfig(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -18624,13 +18632,13 @@ func (ec *executionContext) marshalNMetricHistoPoints2ᚖgithubᚗcomᚋClusterC
 	return ec._MetricHistoPoints(ctx, sel, v)
 }
 
-func (ec *executionContext) unmarshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScope(ctx context.Context, v any) (schema.MetricScope, error) {
+func (ec *executionContext) unmarshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScope(ctx context.Context, v any) (schema.MetricScope, error) {
 	var res schema.MetricScope
 	err := res.UnmarshalGQL(v)
 	return res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScope(ctx context.Context, sel ast.SelectionSet, v schema.MetricScope) graphql.Marshaler {
+func (ec *executionContext) marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScope(ctx context.Context, sel ast.SelectionSet, v schema.MetricScope) graphql.Marshaler {
 	return v
 }
 
@@ -18639,7 +18647,7 @@ func (ec *executionContext) unmarshalNMetricStatItem2ᚖgithubᚗcomᚋClusterCo
 	return &res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) marshalNMetricStatistics2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricStatistics(ctx context.Context, sel ast.SelectionSet, v *schema.MetricStatistics) graphql.Marshaler {
+func (ec *executionContext) marshalNMetricStatistics2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricStatistics(ctx context.Context, sel ast.SelectionSet, v *schema.MetricStatistics) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -18649,7 +18657,7 @@ func (ec *executionContext) marshalNMetricStatistics2ᚖgithubᚗcomᚋClusterCo
 	return ec._MetricStatistics(ctx, sel, v)
 }
 
-func (ec *executionContext) marshalNMetricValue2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricValue(ctx context.Context, sel ast.SelectionSet, v schema.MetricValue) graphql.Marshaler {
+func (ec *executionContext) marshalNMetricValue2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricValue(ctx context.Context, sel ast.SelectionSet, v schema.MetricValue) graphql.Marshaler {
 	return ec._MetricValue(ctx, sel, &v)
 }
 
@@ -18777,7 +18785,7 @@ func (ec *executionContext) marshalNNamedStatsWithScope2ᚖgithubᚗcomᚋCluste
 	return ec._NamedStatsWithScope(ctx, sel, v)
 }
 
-func (ec *executionContext) marshalNNode2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐNodeᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Node) graphql.Marshaler {
+func (ec *executionContext) marshalNNode2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐNodeᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Node) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -18801,7 +18809,7 @@ func (ec *executionContext) marshalNNode2ᚕᚖgithubᚗcomᚋClusterCockpitᚋc
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNNode2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐNode(ctx, sel, v[i])
+			ret[i] = ec.marshalNNode2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐNode(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -18821,7 +18829,7 @@ func (ec *executionContext) marshalNNode2ᚕᚖgithubᚗcomᚋClusterCockpitᚋc
 	return ret
 }
 
-func (ec *executionContext) marshalNNode2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐNode(ctx context.Context, sel ast.SelectionSet, v *schema.Node) graphql.Marshaler {
+func (ec *executionContext) marshalNNode2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐNode(ctx context.Context, sel ast.SelectionSet, v *schema.Node) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -19026,24 +19034,24 @@ func (ec *executionContext) marshalNNodesResultList2ᚖgithubᚗcomᚋClusterCoc
 	return ec._NodesResultList(ctx, sel, v)
 }
 
-func (ec *executionContext) unmarshalNNullableFloat2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloat(ctx context.Context, v any) (schema.Float, error) {
+func (ec *executionContext) unmarshalNNullableFloat2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloat(ctx context.Context, v any) (schema.Float, error) {
 	var res schema.Float
 	err := res.UnmarshalGQL(v)
 	return res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) marshalNNullableFloat2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloat(ctx context.Context, sel ast.SelectionSet, v schema.Float) graphql.Marshaler {
+func (ec *executionContext) marshalNNullableFloat2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloat(ctx context.Context, sel ast.SelectionSet, v schema.Float) graphql.Marshaler {
 	return v
 }
 
-func (ec *executionContext) unmarshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ(ctx context.Context, v any) ([]schema.Float, error) {
+func (ec *executionContext) unmarshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ(ctx context.Context, v any) ([]schema.Float, error) {
 	var vSlice []any
 	vSlice = graphql.CoerceList(v)
 	var err error
 	res := make([]schema.Float, len(vSlice))
 	for i := range vSlice {
 		ctx := graphql.WithPathContext(ctx, graphql.NewPathWithIndex(i))
-		res[i], err = ec.unmarshalNNullableFloat2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloat(ctx, vSlice[i])
+		res[i], err = ec.unmarshalNNullableFloat2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloat(ctx, vSlice[i])
 		if err != nil {
 			return nil, err
 		}
@@ -19051,10 +19059,10 @@ func (ec *executionContext) unmarshalNNullableFloat2ᚕgithubᚗcomᚋClusterCoc
 	return res, nil
 }
 
-func (ec *executionContext) marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloatᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.Float) graphql.Marshaler {
+func (ec *executionContext) marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloatᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.Float) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	for i := range v {
-		ret[i] = ec.marshalNNullableFloat2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐFloat(ctx, sel, v[i])
+		ret[i] = ec.marshalNNullableFloat2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐFloat(ctx, sel, v[i])
 	}
 
 	for _, e := range ret {
@@ -19066,7 +19074,7 @@ func (ec *executionContext) marshalNNullableFloat2ᚕgithubᚗcomᚋClusterCockp
 	return ret
 }
 
-func (ec *executionContext) marshalNResource2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐResourceᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Resource) graphql.Marshaler {
+func (ec *executionContext) marshalNResource2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐResourceᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Resource) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -19090,7 +19098,7 @@ func (ec *executionContext) marshalNResource2ᚕᚖgithubᚗcomᚋClusterCockpit
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNResource2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐResource(ctx, sel, v[i])
+			ret[i] = ec.marshalNResource2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐResource(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -19110,7 +19118,7 @@ func (ec *executionContext) marshalNResource2ᚕᚖgithubᚗcomᚋClusterCockpit
 	return ret
 }
 
-func (ec *executionContext) marshalNResource2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐResource(ctx context.Context, sel ast.SelectionSet, v *schema.Resource) graphql.Marshaler {
+func (ec *executionContext) marshalNResource2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐResource(ctx context.Context, sel ast.SelectionSet, v *schema.Resource) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -19120,13 +19128,13 @@ func (ec *executionContext) marshalNResource2ᚖgithubᚗcomᚋClusterCockpitᚋ
 	return ec._Resource(ctx, sel, v)
 }
 
-func (ec *executionContext) unmarshalNSchedulerState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSchedulerState(ctx context.Context, v any) (schema.SchedulerState, error) {
+func (ec *executionContext) unmarshalNSchedulerState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSchedulerState(ctx context.Context, v any) (schema.SchedulerState, error) {
 	tmp, err := graphql.UnmarshalString(v)
 	res := schema.SchedulerState(tmp)
 	return res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) marshalNSchedulerState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSchedulerState(ctx context.Context, sel ast.SelectionSet, v schema.SchedulerState) graphql.Marshaler {
+func (ec *executionContext) marshalNSchedulerState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSchedulerState(ctx context.Context, sel ast.SelectionSet, v schema.SchedulerState) graphql.Marshaler {
 	_ = sel
 	res := graphql.MarshalString(string(v))
 	if res == graphql.Null {
@@ -19191,7 +19199,7 @@ func (ec *executionContext) marshalNScopedStats2ᚖgithubᚗcomᚋClusterCockpit
 	return ec._ScopedStats(ctx, sel, v)
 }
 
-func (ec *executionContext) marshalNSeries2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSeries(ctx context.Context, sel ast.SelectionSet, v schema.Series) graphql.Marshaler {
+func (ec *executionContext) marshalNSeries2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSeries(ctx context.Context, sel ast.SelectionSet, v schema.Series) graphql.Marshaler {
 	return ec._Series(ctx, sel, &v)
 }
 
@@ -19251,7 +19259,7 @@ func (ec *executionContext) marshalNString2ᚕstringᚄ(ctx context.Context, sel
 	return ret
 }
 
-func (ec *executionContext) marshalNSubCluster2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSubClusterᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.SubCluster) graphql.Marshaler {
+func (ec *executionContext) marshalNSubCluster2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSubClusterᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.SubCluster) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -19275,7 +19283,7 @@ func (ec *executionContext) marshalNSubCluster2ᚕᚖgithubᚗcomᚋClusterCockp
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNSubCluster2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSubCluster(ctx, sel, v[i])
+			ret[i] = ec.marshalNSubCluster2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSubCluster(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -19295,7 +19303,7 @@ func (ec *executionContext) marshalNSubCluster2ᚕᚖgithubᚗcomᚋClusterCockp
 	return ret
 }
 
-func (ec *executionContext) marshalNSubCluster2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSubCluster(ctx context.Context, sel ast.SelectionSet, v *schema.SubCluster) graphql.Marshaler {
+func (ec *executionContext) marshalNSubCluster2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSubCluster(ctx context.Context, sel ast.SelectionSet, v *schema.SubCluster) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -19305,7 +19313,7 @@ func (ec *executionContext) marshalNSubCluster2ᚖgithubᚗcomᚋClusterCockpit
 	return ec._SubCluster(ctx, sel, v)
 }
 
-func (ec *executionContext) marshalNSubClusterConfig2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSubClusterConfigᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.SubClusterConfig) graphql.Marshaler {
+func (ec *executionContext) marshalNSubClusterConfig2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSubClusterConfigᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.SubClusterConfig) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -19329,7 +19337,7 @@ func (ec *executionContext) marshalNSubClusterConfig2ᚕᚖgithubᚗcomᚋCluste
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNSubClusterConfig2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSubClusterConfig(ctx, sel, v[i])
+			ret[i] = ec.marshalNSubClusterConfig2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSubClusterConfig(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -19349,7 +19357,7 @@ func (ec *executionContext) marshalNSubClusterConfig2ᚕᚖgithubᚗcomᚋCluste
 	return ret
 }
 
-func (ec *executionContext) marshalNSubClusterConfig2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSubClusterConfig(ctx context.Context, sel ast.SelectionSet, v *schema.SubClusterConfig) graphql.Marshaler {
+func (ec *executionContext) marshalNSubClusterConfig2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSubClusterConfig(ctx context.Context, sel ast.SelectionSet, v *schema.SubClusterConfig) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -19359,11 +19367,11 @@ func (ec *executionContext) marshalNSubClusterConfig2ᚖgithubᚗcomᚋClusterCo
 	return ec._SubClusterConfig(ctx, sel, v)
 }
 
-func (ec *executionContext) marshalNTag2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTag(ctx context.Context, sel ast.SelectionSet, v schema.Tag) graphql.Marshaler {
+func (ec *executionContext) marshalNTag2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTag(ctx context.Context, sel ast.SelectionSet, v schema.Tag) graphql.Marshaler {
 	return ec._Tag(ctx, sel, &v)
 }
 
-func (ec *executionContext) marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTagᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Tag) graphql.Marshaler {
+func (ec *executionContext) marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTagᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Tag) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -19387,7 +19395,7 @@ func (ec *executionContext) marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋcc
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNTag2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTag(ctx, sel, v[i])
+			ret[i] = ec.marshalNTag2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTag(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -19407,7 +19415,7 @@ func (ec *executionContext) marshalNTag2ᚕᚖgithubᚗcomᚋClusterCockpitᚋcc
 	return ret
 }
 
-func (ec *executionContext) marshalNTag2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTag(ctx context.Context, sel ast.SelectionSet, v *schema.Tag) graphql.Marshaler {
+func (ec *executionContext) marshalNTag2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTag(ctx context.Context, sel ast.SelectionSet, v *schema.Tag) graphql.Marshaler {
 	if v == nil {
 		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
 			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
@@ -19465,11 +19473,11 @@ func (ec *executionContext) marshalNTimeWeights2ᚖgithubᚗcomᚋClusterCockpit
 	return ec._TimeWeights(ctx, sel, v)
 }
 
-func (ec *executionContext) marshalNTopology2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐTopology(ctx context.Context, sel ast.SelectionSet, v schema.Topology) graphql.Marshaler {
+func (ec *executionContext) marshalNTopology2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐTopology(ctx context.Context, sel ast.SelectionSet, v schema.Topology) graphql.Marshaler {
 	return ec._Topology(ctx, sel, &v)
 }
 
-func (ec *executionContext) marshalNUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐUnit(ctx context.Context, sel ast.SelectionSet, v schema.Unit) graphql.Marshaler {
+func (ec *executionContext) marshalNUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐUnit(ctx context.Context, sel ast.SelectionSet, v schema.Unit) graphql.Marshaler {
 	return ec._Unit(ctx, sel, &v)
 }
 
@@ -19726,7 +19734,7 @@ func (ec *executionContext) marshalN__TypeKind2string(ctx context.Context, sel a
 	return res
 }
 
-func (ec *executionContext) marshalOAccelerator2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐAcceleratorᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Accelerator) graphql.Marshaler {
+func (ec *executionContext) marshalOAccelerator2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐAcceleratorᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.Accelerator) graphql.Marshaler {
 	if v == nil {
 		return graphql.Null
 	}
@@ -19753,7 +19761,7 @@ func (ec *executionContext) marshalOAccelerator2ᚕᚖgithubᚗcomᚋClusterCock
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNAccelerator2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐAccelerator(ctx, sel, v[i])
+			ret[i] = ec.marshalNAccelerator2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐAccelerator(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -20141,7 +20149,7 @@ func (ec *executionContext) unmarshalOIntRange2ᚖgithubᚗcomᚋClusterCockpit
 	return &res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) marshalOJob2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJob(ctx context.Context, sel ast.SelectionSet, v *schema.Job) graphql.Marshaler {
+func (ec *executionContext) marshalOJob2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJob(ctx context.Context, sel ast.SelectionSet, v *schema.Job) graphql.Marshaler {
 	if v == nil {
 		return graphql.Null
 	}
@@ -20173,7 +20181,7 @@ func (ec *executionContext) marshalOJobLinkResultList2ᚖgithubᚗcomᚋClusterC
 	return ec._JobLinkResultList(ctx, sel, v)
 }
 
-func (ec *executionContext) unmarshalOJobState2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobStateᚄ(ctx context.Context, v any) ([]schema.JobState, error) {
+func (ec *executionContext) unmarshalOJobState2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobStateᚄ(ctx context.Context, v any) ([]schema.JobState, error) {
 	if v == nil {
 		return nil, nil
 	}
@@ -20183,7 +20191,7 @@ func (ec *executionContext) unmarshalOJobState2ᚕgithubᚗcomᚋClusterCockpit
 	res := make([]schema.JobState, len(vSlice))
 	for i := range vSlice {
 		ctx := graphql.WithPathContext(ctx, graphql.NewPathWithIndex(i))
-		res[i], err = ec.unmarshalNJobState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobState(ctx, vSlice[i])
+		res[i], err = ec.unmarshalNJobState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobState(ctx, vSlice[i])
 		if err != nil {
 			return nil, err
 		}
@@ -20191,13 +20199,13 @@ func (ec *executionContext) unmarshalOJobState2ᚕgithubᚗcomᚋClusterCockpit
 	return res, nil
 }
 
-func (ec *executionContext) marshalOJobState2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobStateᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.JobState) graphql.Marshaler {
+func (ec *executionContext) marshalOJobState2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobStateᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.JobState) graphql.Marshaler {
 	if v == nil {
 		return graphql.Null
 	}
 	ret := make(graphql.Array, len(v))
 	for i := range v {
-		ret[i] = ec.marshalNJobState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐJobState(ctx, sel, v[i])
+		ret[i] = ec.marshalNJobState2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐJobState(ctx, sel, v[i])
 	}
 
 	for _, e := range ret {
@@ -20256,7 +20264,7 @@ func (ec *executionContext) marshalOMetricHistoPoint2ᚕᚖgithubᚗcomᚋCluste
 	return ret
 }
 
-func (ec *executionContext) unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScopeᚄ(ctx context.Context, v any) ([]schema.MetricScope, error) {
+func (ec *executionContext) unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScopeᚄ(ctx context.Context, v any) ([]schema.MetricScope, error) {
 	if v == nil {
 		return nil, nil
 	}
@@ -20266,7 +20274,7 @@ func (ec *executionContext) unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockp
 	res := make([]schema.MetricScope, len(vSlice))
 	for i := range vSlice {
 		ctx := graphql.WithPathContext(ctx, graphql.NewPathWithIndex(i))
-		res[i], err = ec.unmarshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScope(ctx, vSlice[i])
+		res[i], err = ec.unmarshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScope(ctx, vSlice[i])
 		if err != nil {
 			return nil, err
 		}
@@ -20274,13 +20282,13 @@ func (ec *executionContext) unmarshalOMetricScope2ᚕgithubᚗcomᚋClusterCockp
 	return res, nil
 }
 
-func (ec *executionContext) marshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScopeᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.MetricScope) graphql.Marshaler {
+func (ec *executionContext) marshalOMetricScope2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScopeᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.MetricScope) graphql.Marshaler {
 	if v == nil {
 		return graphql.Null
 	}
 	ret := make(graphql.Array, len(v))
 	for i := range v {
-		ret[i] = ec.marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricScope(ctx, sel, v[i])
+		ret[i] = ec.marshalNMetricScope2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricScope(ctx, sel, v[i])
 	}
 
 	for _, e := range ret {
@@ -20310,7 +20318,7 @@ func (ec *executionContext) unmarshalOMetricStatItem2ᚕᚖgithubᚗcomᚋCluste
 	return res, nil
 }
 
-func (ec *executionContext) marshalOMetricStatistics2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐMetricStatistics(ctx context.Context, sel ast.SelectionSet, v schema.MetricStatistics) graphql.Marshaler {
+func (ec *executionContext) marshalOMetricStatistics2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricStatistics(ctx context.Context, sel ast.SelectionSet, v schema.MetricStatistics) graphql.Marshaler {
 	return ec._MetricStatistics(ctx, sel, &v)
 }
 
@@ -20332,7 +20340,7 @@ func (ec *executionContext) marshalOMonitoringState2ᚖstring(ctx context.Contex
 	return res
 }
 
-func (ec *executionContext) marshalONode2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐNode(ctx context.Context, sel ast.SelectionSet, v *schema.Node) graphql.Marshaler {
+func (ec *executionContext) marshalONode2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐNode(ctx context.Context, sel ast.SelectionSet, v *schema.Node) graphql.Marshaler {
 	if v == nil {
 		return graphql.Null
 	}
@@ -20373,7 +20381,7 @@ func (ec *executionContext) unmarshalOPageRequest2ᚖgithubᚗcomᚋClusterCockp
 	return &res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) unmarshalOSchedulerState2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSchedulerState(ctx context.Context, v any) (*schema.SchedulerState, error) {
+func (ec *executionContext) unmarshalOSchedulerState2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSchedulerState(ctx context.Context, v any) (*schema.SchedulerState, error) {
 	if v == nil {
 		return nil, nil
 	}
@@ -20382,7 +20390,7 @@ func (ec *executionContext) unmarshalOSchedulerState2ᚖgithubᚗcomᚋClusterCo
 	return &res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) marshalOSchedulerState2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSchedulerState(ctx context.Context, sel ast.SelectionSet, v *schema.SchedulerState) graphql.Marshaler {
+func (ec *executionContext) marshalOSchedulerState2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSchedulerState(ctx context.Context, sel ast.SelectionSet, v *schema.SchedulerState) graphql.Marshaler {
 	if v == nil {
 		return graphql.Null
 	}
@@ -20392,7 +20400,7 @@ func (ec *executionContext) marshalOSchedulerState2ᚖgithubᚗcomᚋClusterCock
 	return res
 }
 
-func (ec *executionContext) marshalOSeries2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSeriesᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.Series) graphql.Marshaler {
+func (ec *executionContext) marshalOSeries2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSeriesᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.Series) graphql.Marshaler {
 	if v == nil {
 		return graphql.Null
 	}
@@ -20419,7 +20427,7 @@ func (ec *executionContext) marshalOSeries2ᚕgithubᚗcomᚋClusterCockpitᚋcc
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNSeries2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐSeries(ctx, sel, v[i])
+			ret[i] = ec.marshalNSeries2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐSeries(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -20455,7 +20463,7 @@ func (ec *executionContext) marshalOSortByAggregate2ᚖgithubᚗcomᚋClusterCoc
 	return v
 }
 
-func (ec *executionContext) marshalOStatsSeries2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐStatsSeries(ctx context.Context, sel ast.SelectionSet, v *schema.StatsSeries) graphql.Marshaler {
+func (ec *executionContext) marshalOStatsSeries2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐStatsSeries(ctx context.Context, sel ast.SelectionSet, v *schema.StatsSeries) graphql.Marshaler {
 	if v == nil {
 		return graphql.Null
 	}
@@ -20562,11 +20570,11 @@ func (ec *executionContext) unmarshalOTimeRange2ᚖgithubᚗcomᚋClusterCockpit
 	return &res, graphql.ErrorOnPath(ctx, err)
 }
 
-func (ec *executionContext) marshalOUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐUnit(ctx context.Context, sel ast.SelectionSet, v schema.Unit) graphql.Marshaler {
+func (ec *executionContext) marshalOUnit2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐUnit(ctx context.Context, sel ast.SelectionSet, v schema.Unit) graphql.Marshaler {
 	return ec._Unit(ctx, sel, &v)
 }
 
-func (ec *executionContext) marshalOUnit2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋschemaᚐUnit(ctx context.Context, sel ast.SelectionSet, v *schema.Unit) graphql.Marshaler {
+func (ec *executionContext) marshalOUnit2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐUnit(ctx context.Context, sel ast.SelectionSet, v *schema.Unit) graphql.Marshaler {
 	if v == nil {
 		return graphql.Null
 	}
diff --git a/internal/graph/model/models_gen.go b/internal/graph/model/models_gen.go
index 31ba03ab..06f0ffcf 100644
--- a/internal/graph/model/models_gen.go
+++ b/internal/graph/model/models_gen.go
@@ -82,6 +82,7 @@ type JobFilter struct {
 	State           []schema.JobState `json:"state,omitempty"`
 	MetricStats     []*MetricStatItem `json:"metricStats,omitempty"`
 	Shared          *string           `json:"shared,omitempty"`
+	Schedule        *string           `json:"schedule,omitempty"`
 	Node            *StringInput      `json:"node,omitempty"`
 }
 
diff --git a/internal/graph/schema.resolvers.go b/internal/graph/schema.resolvers.go
index 32499b8c..11168e80 100644
--- a/internal/graph/schema.resolvers.go
+++ b/internal/graph/schema.resolvers.go
@@ -972,12 +972,10 @@ func (r *Resolver) Query() generated.QueryResolver { return &queryResolver{r} }
 // SubCluster returns generated.SubClusterResolver implementation.
 func (r *Resolver) SubCluster() generated.SubClusterResolver { return &subClusterResolver{r} }
 
-type (
-	clusterResolver     struct{ *Resolver }
-	jobResolver         struct{ *Resolver }
-	metricValueResolver struct{ *Resolver }
-	mutationResolver    struct{ *Resolver }
-	nodeResolver        struct{ *Resolver }
-	queryResolver       struct{ *Resolver }
-	subClusterResolver  struct{ *Resolver }
-)
+type clusterResolver struct{ *Resolver }
+type jobResolver struct{ *Resolver }
+type metricValueResolver struct{ *Resolver }
+type mutationResolver struct{ *Resolver }
+type nodeResolver struct{ *Resolver }
+type queryResolver struct{ *Resolver }
+type subClusterResolver struct{ *Resolver }
diff --git a/internal/repository/jobQuery.go b/internal/repository/jobQuery.go
index 8c341afb..4655614f 100644
--- a/internal/repository/jobQuery.go
+++ b/internal/repository/jobQuery.go
@@ -143,57 +143,35 @@ func SecurityCheck(ctx context.Context, query sq.SelectBuilder) (sq.SelectBuilde
 
 // Build a sq.SelectBuilder out of a schema.JobFilter.
 func BuildWhereClause(filter *model.JobFilter, query sq.SelectBuilder) sq.SelectBuilder {
-	if filter.Tags != nil {
-		// This is an OR-Logic query: Returns all distinct jobs with at least one of the requested tags; TODO: AND-Logic query?
-		query = query.Join("jobtag ON jobtag.job_id = job.id").Where(sq.Eq{"jobtag.tag_id": filter.Tags}).Distinct()
-	}
+	// Primary Key
 	if filter.DbID != nil {
 		dbIDs := make([]string, len(filter.DbID))
 		copy(dbIDs, filter.DbID)
 		query = query.Where(sq.Eq{"job.id": dbIDs})
 	}
-	if filter.JobID != nil {
-		query = buildStringCondition("job.job_id", filter.JobID, query)
-	}
-	if filter.ArrayJobID != nil {
-		query = query.Where("job.array_job_id = ?", *filter.ArrayJobID)
-	}
-	if filter.User != nil {
-		query = buildStringCondition("job.hpc_user", filter.User, query)
-	}
-	if filter.Project != nil {
-		query = buildStringCondition("job.project", filter.Project, query)
-	}
-	if filter.JobName != nil {
-		query = buildMetaJsonCondition("jobName", filter.JobName, query)
-	}
+	// Explicit indices
 	if filter.Cluster != nil {
 		query = buildStringCondition("job.cluster", filter.Cluster, query)
 	}
 	if filter.Partition != nil {
 		query = buildStringCondition("job.cluster_partition", filter.Partition, query)
 	}
-	if filter.StartTime != nil {
-		query = buildTimeCondition("job.start_time", filter.StartTime, query)
-	}
-	if filter.Duration != nil {
-		query = buildIntCondition("job.duration", filter.Duration, query)
-	}
-	if filter.MinRunningFor != nil {
-		now := time.Now().Unix() // There does not seam to be a portable way to get the current unix timestamp accross different DBs.
-		query = query.Where("(job.job_state != 'running' OR (? - job.start_time) > ?)", now, *filter.MinRunningFor)
-	}
-	if filter.Shared != nil {
-		query = query.Where("job.shared = ?", *filter.Shared)
-	}
 	if filter.State != nil {
 		states := make([]string, len(filter.State))
 		for i, val := range filter.State {
 			states[i] = string(val)
 		}
-
 		query = query.Where(sq.Eq{"job.job_state": states})
 	}
+	if filter.Shared != nil {
+		query = query.Where("job.shared = ?", *filter.Shared)
+	}
+	if filter.Project != nil {
+		query = buildStringCondition("job.project", filter.Project, query)
+	}
+	if filter.User != nil {
+		query = buildStringCondition("job.hpc_user", filter.User, query)
+	}
 	if filter.NumNodes != nil {
 		query = buildIntCondition("job.num_nodes", filter.NumNodes, query)
 	}
@@ -203,17 +181,57 @@ func BuildWhereClause(filter *model.JobFilter, query sq.SelectBuilder) sq.Select
 	if filter.NumHWThreads != nil {
 		query = buildIntCondition("job.num_hwthreads", filter.NumHWThreads, query)
 	}
-	if filter.Node != nil {
-		query = buildResourceJsonCondition("hostname", filter.Node, query)
+	if filter.ArrayJobID != nil {
+		query = query.Where("job.array_job_id = ?", *filter.ArrayJobID)
+	}
+	if filter.StartTime != nil {
+		query = buildTimeCondition("job.start_time", filter.StartTime, query)
+	}
+	if filter.Duration != nil {
+		query = buildIntCondition("job.duration", filter.Duration, query)
 	}
 	if filter.Energy != nil {
 		query = buildFloatCondition("job.energy", filter.Energy, query)
 	}
+	// Indices on Tag Table
+	if filter.Tags != nil {
+		// This is an OR-Logic query: Returns all distinct jobs with at least one of the requested tags; TODO: AND-Logic query?
+		query = query.Join("jobtag ON jobtag.job_id = job.id").Where(sq.Eq{"jobtag.tag_id": filter.Tags}).Distinct()
+	}
+	// No explicit Indices
+	if filter.JobID != nil {
+		query = buildStringCondition("job.job_id", filter.JobID, query)
+	}
+	// Queries Within JSONs
 	if filter.MetricStats != nil {
 		for _, ms := range filter.MetricStats {
 			query = buildFloatJsonCondition(ms.MetricName, ms.Range, query)
 		}
 	}
+	if filter.Node != nil {
+		query = buildResourceJsonCondition("hostname", filter.Node, query)
+	}
+	if filter.JobName != nil {
+		query = buildMetaJsonCondition("jobName", filter.JobName, query)
+	}
+	if filter.Schedule != nil {
+		interactiveJobname := "interactive"
+		if *filter.Schedule == "interactive" {
+			iFilter := model.StringInput{Eq: &interactiveJobname}
+			query = buildMetaJsonCondition("jobName", &iFilter, query)
+		} else if *filter.Schedule == "batch" {
+			sFilter := model.StringInput{Neq: &interactiveJobname}
+			query = buildMetaJsonCondition("jobName", &sFilter, query)
+		}
+	}
+
+	// Configurable Filter to exclude recently started jobs, see config.go: ShortRunningJobsDuration
+	if filter.MinRunningFor != nil {
+		now := time.Now().Unix()
+		// Only jobs whose start timestamp is more than MinRunningFor seconds in the past
+		// If a job completed within the configured timeframe, it will still show up after the start_time matches the condition!
+		query = query.Where(sq.Lt{"job.start_time": (now - int64(*filter.MinRunningFor))})
+	}
 	return query
 }
 
diff --git a/internal/repository/migrations/sqlite3/09_add-job-cache.up.sql b/internal/repository/migrations/sqlite3/09_add-job-cache.up.sql
index 863b50ea..bd465bcb 100644
--- a/internal/repository/migrations/sqlite3/09_add-job-cache.up.sql
+++ b/internal/repository/migrations/sqlite3/09_add-job-cache.up.sql
@@ -118,15 +118,13 @@ DROP TABLE lookup_exclusive;
 DROP TABLE job; -- Deletes All Existing 'job' Indices; Recreate after Renaming
 ALTER TABLE job_new RENAME TO job;
 
--- Recreate Indices from 08_add-footprint, include new submit_time indices
+-- Recreate Indices from 08_add-footprint; include new 'shared' column
 -- Cluster Filter
-CREATE INDEX IF NOT EXISTS jobs_cluster ON job (cluster);
 CREATE INDEX IF NOT EXISTS jobs_cluster_user ON job (cluster, hpc_user);
 CREATE INDEX IF NOT EXISTS jobs_cluster_project ON job (cluster, project);
 CREATE INDEX IF NOT EXISTS jobs_cluster_subcluster ON job (cluster, subcluster);
 -- Cluster Filter Sorting
 CREATE INDEX IF NOT EXISTS jobs_cluster_starttime ON job (cluster, start_time);
-CREATE INDEX IF NOT EXISTS jobs_cluster_submittime ON job (cluster, submit_time);
 CREATE INDEX IF NOT EXISTS jobs_cluster_duration ON job (cluster, duration);
 CREATE INDEX IF NOT EXISTS jobs_cluster_numnodes ON job (cluster, num_nodes);
 CREATE INDEX IF NOT EXISTS jobs_cluster_numhwthreads ON job (cluster, num_hwthreads);
@@ -134,44 +132,42 @@ CREATE INDEX IF NOT EXISTS jobs_cluster_numacc ON job (cluster, num_acc);
 CREATE INDEX IF NOT EXISTS jobs_cluster_energy ON job (cluster, energy);
 
 -- Cluster+Partition Filter
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition ON job (cluster, cluster_partition);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_user ON job (cluster, cluster_partition, hpc_user);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_project ON job (cluster, cluster_partition, project);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate ON job (cluster, cluster_partition, job_state);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_shared ON job (cluster, cluster_partition, shared);
+
 -- Cluster+Partition Filter Sorting
 CREATE INDEX IF NOT EXISTS jobs_cluster_partition_starttime ON job (cluster, cluster_partition, start_time);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_submittime ON job (cluster, cluster_partition, submit_time);
 CREATE INDEX IF NOT EXISTS jobs_cluster_partition_duration ON job (cluster, cluster_partition, duration);
 CREATE INDEX IF NOT EXISTS jobs_cluster_partition_numnodes ON job (cluster, cluster_partition, num_nodes);
 CREATE INDEX IF NOT EXISTS jobs_cluster_partition_numhwthreads ON job (cluster, cluster_partition, num_hwthreads);
 CREATE INDEX IF NOT EXISTS jobs_cluster_partition_numacc ON job (cluster, cluster_partition, num_acc);
 CREATE INDEX IF NOT EXISTS jobs_cluster_partition_energy ON job (cluster, cluster_partition, energy);
 
--- Cluster+Partition+Jobstate Filter
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate ON job (cluster, cluster_partition, job_state);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_user ON job (cluster, cluster_partition, job_state, hpc_user);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_project ON job (cluster, cluster_partition, job_state, project);
--- Cluster+Partition+Jobstate Filter Sorting
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_starttime ON job (cluster, cluster_partition, job_state, start_time);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_submittime ON job (cluster, cluster_partition, job_state, submit_time);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_duration ON job (cluster, cluster_partition, job_state, duration);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_numnodes ON job (cluster, cluster_partition, job_state, num_nodes);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_numhwthreads ON job (cluster, cluster_partition, job_state, num_hwthreads);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_numacc ON job (cluster, cluster_partition, job_state, num_acc);
-CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_energy ON job (cluster, cluster_partition, job_state, energy);
-
 -- Cluster+JobState Filter
-CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate ON job (cluster, job_state);
 CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_user ON job (cluster, job_state, hpc_user);
 CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_project ON job (cluster, job_state, project);
 -- Cluster+JobState Filter Sorting
 CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_starttime ON job (cluster, job_state, start_time);
-CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_submittime ON job (cluster, job_state, submit_time);
 CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_duration ON job (cluster, job_state, duration);
 CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_numnodes ON job (cluster, job_state, num_nodes);
 CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_numhwthreads ON job (cluster, job_state, num_hwthreads);
 CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_numacc ON job (cluster, job_state, num_acc);
 CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_energy ON job (cluster, job_state, energy);
 
+-- Cluster+Shared Filter
+CREATE INDEX IF NOT EXISTS jobs_cluster_shared_user ON job (cluster, shared, hpc_user);
+CREATE INDEX IF NOT EXISTS jobs_cluster_shared_project ON job (cluster, shared, project);
+-- Cluster+Shared Filter Sorting
+CREATE INDEX IF NOT EXISTS jobs_cluster_shared_starttime ON job (cluster, shared, start_time);
+CREATE INDEX IF NOT EXISTS jobs_cluster_shared_duration ON job (cluster, shared, duration);
+CREATE INDEX IF NOT EXISTS jobs_cluster_shared_numnodes ON job (cluster, shared, num_nodes);
+CREATE INDEX IF NOT EXISTS jobs_cluster_shared_numhwthreads ON job (cluster, shared, num_hwthreads);
+CREATE INDEX IF NOT EXISTS jobs_cluster_shared_numacc ON job (cluster, shared, num_acc);
+CREATE INDEX IF NOT EXISTS jobs_cluster_shared_energy ON job (cluster, shared, energy);
+
 -- User Filter
-CREATE INDEX IF NOT EXISTS jobs_user ON job (hpc_user);
 -- User Filter Sorting
 CREATE INDEX IF NOT EXISTS jobs_user_starttime ON job (hpc_user, start_time);
 CREATE INDEX IF NOT EXISTS jobs_user_duration ON job (hpc_user, duration);
@@ -181,7 +177,6 @@ CREATE INDEX IF NOT EXISTS jobs_user_numacc ON job (hpc_user, num_acc);
 CREATE INDEX IF NOT EXISTS jobs_user_energy ON job (hpc_user, energy);
 
 -- Project Filter
-CREATE INDEX IF NOT EXISTS jobs_project ON job (project);
 CREATE INDEX IF NOT EXISTS jobs_project_user ON job (project, hpc_user);
 -- Project Filter Sorting
 CREATE INDEX IF NOT EXISTS jobs_project_starttime ON job (project, start_time);
@@ -192,10 +187,8 @@ CREATE INDEX IF NOT EXISTS jobs_project_numacc ON job (project, num_acc);
 CREATE INDEX IF NOT EXISTS jobs_project_energy ON job (project, energy);
 
 -- JobState Filter
-CREATE INDEX IF NOT EXISTS jobs_jobstate ON job (job_state);
 CREATE INDEX IF NOT EXISTS jobs_jobstate_user ON job (job_state, hpc_user);
 CREATE INDEX IF NOT EXISTS jobs_jobstate_project ON job (job_state, project);
-CREATE INDEX IF NOT EXISTS jobs_jobstate_cluster ON job (job_state, cluster);
 -- JobState Filter Sorting
 CREATE INDEX IF NOT EXISTS jobs_jobstate_starttime ON job (job_state, start_time);
 CREATE INDEX IF NOT EXISTS jobs_jobstate_duration ON job (job_state, duration);
@@ -204,18 +197,21 @@ CREATE INDEX IF NOT EXISTS jobs_jobstate_numhwthreads ON job (job_state, num_hwt
 CREATE INDEX IF NOT EXISTS jobs_jobstate_numacc ON job (job_state, num_acc);
 CREATE INDEX IF NOT EXISTS jobs_jobstate_energy ON job (job_state, energy);
 
+-- Shared Filter
+CREATE INDEX IF NOT EXISTS jobs_shared_user ON job (shared, hpc_user);
+CREATE INDEX IF NOT EXISTS jobs_shared_project ON job (shared, project);
+-- Shared Filter Sorting
+CREATE INDEX IF NOT EXISTS jobs_shared_starttime ON job (shared, start_time);
+CREATE INDEX IF NOT EXISTS jobs_shared_duration ON job (shared, duration);
+CREATE INDEX IF NOT EXISTS jobs_shared_numnodes ON job (shared, num_nodes);
+CREATE INDEX IF NOT EXISTS jobs_shared_numhwthreads ON job (shared, num_hwthreads);
+CREATE INDEX IF NOT EXISTS jobs_shared_numacc ON job (shared, num_acc);
+CREATE INDEX IF NOT EXISTS jobs_shared_energy ON job (shared, energy);
+
 -- ArrayJob Filter
 CREATE INDEX IF NOT EXISTS jobs_arrayjobid_starttime ON job (array_job_id, start_time);
 CREATE INDEX IF NOT EXISTS jobs_cluster_arrayjobid_starttime ON job (cluster, array_job_id, start_time);
 
--- Sorting without active filters
-CREATE INDEX IF NOT EXISTS jobs_starttime ON job (start_time);
-CREATE INDEX IF NOT EXISTS jobs_duration ON job (duration);
-CREATE INDEX IF NOT EXISTS jobs_numnodes ON job (num_nodes);
-CREATE INDEX IF NOT EXISTS jobs_numhwthreads ON job (num_hwthreads);
-CREATE INDEX IF NOT EXISTS jobs_numacc ON job (num_acc);
-CREATE INDEX IF NOT EXISTS jobs_energy ON job (energy);
-
 -- Single filters with default starttime sorting
 CREATE INDEX IF NOT EXISTS jobs_duration_starttime ON job (duration, start_time);
 CREATE INDEX IF NOT EXISTS jobs_numnodes_starttime ON job (num_nodes, start_time);
@@ -223,6 +219,18 @@ CREATE INDEX IF NOT EXISTS jobs_numhwthreads_starttime ON job (num_hwthreads, st
 CREATE INDEX IF NOT EXISTS jobs_numacc_starttime ON job (num_acc, start_time);
 CREATE INDEX IF NOT EXISTS jobs_energy_starttime ON job (energy, start_time);
 
+-- Single filters with duration sorting
+CREATE INDEX IF NOT EXISTS jobs_starttime_duration ON job (start_time, duration);
+CREATE INDEX IF NOT EXISTS jobs_numnodes_duration ON job (num_nodes, duration);
+CREATE INDEX IF NOT EXISTS jobs_numhwthreads_duration ON job (num_hwthreads, duration);
+CREATE INDEX IF NOT EXISTS jobs_numacc_duration ON job (num_acc, duration);
+CREATE INDEX IF NOT EXISTS jobs_energy_duration ON job (energy, duration);
+
+-- Notes:
+-- Cluster+Partition+Jobstate Filter: Tested -> Full Array Of Combinations non-required
+-- Cluster+JobState+Shared Filter: Tested -> No further timing improvement
+-- JobState+Shared Filter: Tested -> No further timing improvement
+
 -- Optimize DB index usage
 PRAGMA optimize;
 
diff --git a/internal/repository/migrations/sqlite3/10_node-table.up.sql b/internal/repository/migrations/sqlite3/10_node-table.up.sql
index 247bceab..7b5b5ac7 100644
--- a/internal/repository/migrations/sqlite3/10_node-table.up.sql
+++ b/internal/repository/migrations/sqlite3/10_node-table.up.sql
@@ -33,8 +33,6 @@ CREATE INDEX IF NOT EXISTS nodes_cluster_subcluster ON node (cluster, subcluster
 
 -- Add NEW Indices For New Node_State Table Fields
 CREATE INDEX IF NOT EXISTS nodestates_timestamp ON node_state (time_stamp);
-CREATE INDEX IF NOT EXISTS nodestates_state ON node_state (node_state);
-CREATE INDEX IF NOT EXISTS nodestates_health ON node_state (health_state);
 CREATE INDEX IF NOT EXISTS nodestates_state_timestamp ON node_state (node_state, time_stamp);
 CREATE INDEX IF NOT EXISTS nodestates_health_timestamp ON node_state (health_state, time_stamp);
 CREATE INDEX IF NOT EXISTS nodestates_nodeid_state ON node_state (node_id, node_state);
diff --git a/internal/routerConfig/routes.go b/internal/routerConfig/routes.go
index 436031ef..e6a79095 100644
--- a/internal/routerConfig/routes.go
+++ b/internal/routerConfig/routes.go
@@ -257,6 +257,12 @@ func buildFilterPresets(query url.Values) map[string]interface{} {
 	if len(query["state"]) != 0 {
 		filterPresets["state"] = query["state"]
 	}
+	if query.Get("shared") != "" {
+		filterPresets["shared"] = query.Get("shared")
+	}
+	if query.Get("schedule") != "" {
+		filterPresets["schedule"] = query.Get("schedule")
+	}
 	if rawtags, ok := query["tag"]; ok {
 		tags := make([]int, len(rawtags))
 		for i, tid := range rawtags {
diff --git a/web/frontend/src/generic/Filters.svelte b/web/frontend/src/generic/Filters.svelte
index 7bc877f0..74417015 100644
--- a/web/frontend/src/generic/Filters.svelte
+++ b/web/frontend/src/generic/Filters.svelte
@@ -28,7 +28,7 @@
   } from "@sveltestrap/sveltestrap";
   import Info from "./filters/InfoBox.svelte";
   import Cluster from "./filters/Cluster.svelte";
-  import JobStates, { allJobStates } from "./filters/JobStates.svelte";
+  import JobStates, { allJobStates, mapSharedStates } from "./filters/JobStates.svelte";
   import StartTime, { startTimeSelectOptions } from "./filters/StartTime.svelte";
   import Duration from "./filters/Duration.svelte";
   import Tags from "./filters/Tags.svelte";
@@ -69,6 +69,8 @@
     cluster: null,
     partition: null,
     states: allJobStates,
+    shared: "",
+    schedule: "",
     startTime: { from: null, to: null, range: ""},
     duration: {
       lessThan: null,
@@ -103,6 +105,8 @@
       filterPresets.states || filterPresets.state
         ? [filterPresets.state].flat()
         : allJobStates,
+    shared: filterPresets.shared || "",
+    schedule: filterPresets.schedule || "",
     startTime: filterPresets.startTime || { from: null, to: null, range: ""},
     duration: filterPresets.duration || {
       lessThan: null,
@@ -146,19 +150,39 @@
     let items = [];
     if (filters.dbId.length != 0)
       items.push({ dbId: filters.dbId });
-    if (filters.jobId)
-      items.push({ jobId: { [filters.jobIdMatch]: filters.jobId } });
-    if (filters.arrayJobId != null)
-      items.push({ arrayJobId: filters.arrayJobId });
-    if (filters.jobName) items.push({ jobName: { contains: filters.jobName } });
-    if (filters.project)
-      items.push({ project: { [filters.projectMatch]: filters.project } });
-    if (filters.user)
-      items.push({ user: { [filters.userMatch]: filters.user } });
     if (filters.cluster) items.push({ cluster: { eq: filters.cluster } });
     if (filters.partition) items.push({ partition: { eq: filters.partition } });
     if (filters.states.length != allJobStates?.length)
       items.push({ state: filters.states });
+    if (filters.shared) items.push({ shared: filters.shared });
+    if (filters.project)
+      items.push({ project: { [filters.projectMatch]: filters.project } });
+    if (filters.user)
+      items.push({ user: { [filters.userMatch]: filters.user } });
+    if (filters.numNodes.from != null || filters.numNodes.to != null) {
+      items.push({
+        numNodes: { from: filters.numNodes.from, to: filters.numNodes.to },
+      });
+    }
+    if (filters.numAccelerators.from != null || filters.numAccelerators.to != null) {
+      items.push({
+        numAccelerators: {
+          from: filters.numAccelerators.from,
+          to: filters.numAccelerators.to,
+        },
+      });
+    }
+    if (filters.numHWThreads.from != null || filters.numHWThreads.to != null) {
+      items.push({
+        numHWThreads: {
+          from: filters.numHWThreads.from,
+          to: filters.numHWThreads.to,
+        },
+      });
+    }
+    if (filters.arrayJobId != null)
+      items.push({ arrayJobId: filters.arrayJobId });
+    if (filters.tags.length != 0) items.push({ tags: filters.tags });
     if (filters.startTime.from || filters.startTime.to)
       items.push({
         startTime: { from: filters.startTime.from, to: filters.startTime.to },
@@ -175,36 +199,17 @@
       items.push({ duration: { from: 0, to: filters.duration.lessThan } });
     if (filters.duration.moreThan)
       items.push({ duration: { from: filters.duration.moreThan, to: 604800 } }); // 7 days to include special jobs with long runtimes
-    if (filters.tags.length != 0) items.push({ tags: filters.tags });
-    if (filters.numNodes.from != null || filters.numNodes.to != null) {
-      items.push({
-        numNodes: { from: filters.numNodes.from, to: filters.numNodes.to },
-      });
-    }
-    if (filters.numHWThreads.from != null || filters.numHWThreads.to != null) {
-      items.push({
-        numHWThreads: {
-          from: filters.numHWThreads.from,
-          to: filters.numHWThreads.to,
-        },
-      });
-    }
-    if (filters.numAccelerators.from != null || filters.numAccelerators.to != null) {
-      items.push({
-        numAccelerators: {
-          from: filters.numAccelerators.from,
-          to: filters.numAccelerators.to,
-        },
-      });
-    }
-    if (filters.node) items.push({ node: { [filters.nodeMatch]: filters.node } });
     if (filters.energy.from || filters.energy.to)
       items.push({
         energy: { from: filters.energy.from, to: filters.energy.to },
       });
+    if (filters.jobId)
+      items.push({ jobId: { [filters.jobIdMatch]: filters.jobId } });
     if (filters.stats.length != 0)
       items.push({ metricStats: filters.stats.map((st) => { return { metricName: st.field, range: { from: st.from, to: st.to }} }) });
-
+    if (filters.node) items.push({ node: { [filters.nodeMatch]: filters.node } });
+    if (filters.jobName) items.push({ jobName: { contains: filters.jobName } });
+    if (filters.schedule) items.push({ schedule: filters.schedule });
     applyFilters({ filters: items });
     changeURL();
     return items;
@@ -248,6 +253,8 @@
     if (filters.partition) opts.push(`partition=${filters.partition}`);
     if (filters.states.length != allJobStates?.length)
       for (let state of filters.states) opts.push(`state=${state}`);
+    if (filters.shared) opts.push(`shared=${filters.shared}`);
+    if (filters.schedule) opts.push(`schedule=${filters.schedule}`);
     if (filters.startTime.from && filters.startTime.to)
       opts.push(
         `startTime=${dateToUnixEpoch(filters.startTime.from)}-${dateToUnixEpoch(filters.startTime.to)}`,
@@ -366,6 +373,23 @@
   {#if filters.states.length != allJobStates?.length}
     <Info icon="gear-fill" onclick={() => (isJobStatesOpen = true)}>
       {filters.states.join(", ")}
+      {#if filters.shared && !filters.schedule}
+        ({mapSharedStates[filters.shared]})
+      {:else if filters.schedule && !filters.shared}
+        ({filters.schedule.charAt(0).toUpperCase() + filters.schedule?.slice(1)})
+      {:else if (filters.shared && filters.schedule)}
+        ({[mapSharedStates[filters.shared], (filters.schedule.charAt(0).toUpperCase() + filters.schedule.slice(1))].join(", ")})
+      {/if}
+    </Info>
+  {:else if (filters.shared || filters.schedule)}
+    <Info icon="gear-fill" onclick={() => (isJobStatesOpen = true)}>
+      {#if filters.shared && !filters.schedule}
+        {mapSharedStates[filters.shared]}
+      {:else if filters.schedule && !filters.shared}
+        {filters.schedule.charAt(0).toUpperCase() + filters.schedule?.slice(1)}
+      {:else if (filters.shared && filters.schedule)}
+        {[mapSharedStates[filters.shared], (filters.schedule.charAt(0).toUpperCase() + filters.schedule.slice(1))].join(", ")}
+      {/if}
     </Info>
   {/if}
 
@@ -468,6 +492,8 @@
 <JobStates
   bind:isOpen={isJobStatesOpen}
   presetStates={filters.states}
+  presetShared={filters.shared}
+  presetSchedule={filters.schedule}
   setFilter={(filter) => updateFilters(filter)}
 />
 
diff --git a/web/frontend/src/generic/filters/JobStates.svelte b/web/frontend/src/generic/filters/JobStates.svelte
index ba4168f7..dc622a20 100644
--- a/web/frontend/src/generic/filters/JobStates.svelte
+++ b/web/frontend/src/generic/filters/JobStates.svelte
@@ -4,23 +4,35 @@
   Properties:
   - `isOpen Bool?`: Is this filter component opened [Bindable, Default: false]
   - `presetStates [String]?`: The latest selected filter state [Default: [...allJobStates]]
+  - `presetShared String?`: The latest selected filter shared [Default: ""]
+  - `presetShedule String?`: The latest selected filter schedule [Default: ""]
   - `setFilter Func`: The callback function to apply current filter selection
 
   Exported:
   - `const allJobStates [String]`: List of all available job states used in cc-backend
+  - `const mapSharedStates {String:String}`: Object of all available shared states used in cc-backend with label
 -->
 
 <script module>
   export const allJobStates = [
+    "pending",
     "running",
     "completed",
     "failed",
-    "cancelled",
-    "stopped",
     "timeout",
+    "deadline",
     "preempted",
+    "suspended",
+    "cancelled",
     "out_of_memory",
+    "boot_fail",
+    "node_fail"
   ];
+  export const mapSharedStates = {
+    none: "Exclusive",
+    multi_user: "Shared",
+    single_user: "Multitask",
+  };
 </script>
 
 <script>
@@ -34,17 +46,31 @@
     ModalBody,
     ModalHeader,
     ModalFooter,
+    Input,
+    Row,
+    Col
   } from "@sveltestrap/sveltestrap";
 
   /* Svelte 5 Props */
   let {
     isOpen = $bindable(false),
     presetStates = [...allJobStates],
+    presetShared = "",
+    presetSchedule = "",
     setFilter
   } = $props();
 
+  /* Const Init */
+  const allSharedStates = [
+    "none",
+    "multi_user",
+    "single_user",
+  ];
+
   /* State Init */
   let pendingStates = $state([...presetStates]);
+  let pendingShared = $state(presetShared);
+  let pendingSchedule = $state(presetSchedule);
 
 </script>
 
@@ -60,10 +86,26 @@
             name="flavours"
             value={state}
           />
-          {state}
+          {state.charAt(0).toUpperCase() + state.slice(1)}
         </ListGroupItem>
       {/each}
     </ListGroup>
+    <hr/>
+    <Row>
+      <Col>
+        <h5>Resource Sharing</h5>
+        <Input type="radio" bind:group={pendingShared} value="" label="All" />
+        {#each allSharedStates as shared}
+          <Input type="radio" bind:group={pendingShared} value={shared} label={mapSharedStates[shared]} />
+        {/each}
+      </Col>
+      <Col>
+        <h5>Processing Type</h5>
+        <Input type="radio" bind:group={pendingSchedule} value="" label="All" />
+        <Input type="radio" bind:group={pendingSchedule} value="interactive" label="Interactive" />
+        <Input type="radio" bind:group={pendingSchedule} value="batch" label="Batch Process" />
+      </Col>
+    </Row>
   </ModalBody>
   <ModalFooter>
     <Button
@@ -71,21 +113,32 @@
       disabled={pendingStates.length == 0}
       onclick={() => {
         isOpen = false;
-        setFilter({ states: [...pendingStates] });
+        setFilter({ states: [...pendingStates], shared: pendingShared, schedule: pendingSchedule });
       }}>Close & Apply</Button
     >
-    <Button
-      color="warning"
-      onclick={() => {
-        pendingStates = [];
-      }}>Deselect All</Button
-    >
+    {#if pendingStates.length != 0}
+      <Button
+        color="warning"
+        onclick={() => {
+          pendingStates = [];
+        }}>Deselect All</Button
+      >
+    {:else}
+      <Button
+        color="success"
+        onclick={() => {
+          pendingStates = [...allJobStates];
+        }}>Select All</Button
+      >
+    {/if}
     <Button
       color="danger"
       onclick={() => {
         isOpen = false;
         pendingStates = [...allJobStates];
-        setFilter({ states: [...pendingStates] });
+        pendingShared = "";
+        pendingSchedule = "";
+        setFilter({ states: [...pendingStates], shared: pendingShared, schedule: pendingSchedule });
       }}>Reset</Button
     >
     <Button onclick={() => (isOpen = false)}>Close</Button>

From fb8db3c3aed9527e01c526f3943b5d5abdafed01 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 07:37:31 +0100
Subject: [PATCH 31/59] Add query which node metric data needs to be retained

---
 go.mod                     |  1 +
 go.sum                     |  2 ++
 internal/repository/job.go | 61 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 64 insertions(+)

diff --git a/go.mod b/go.mod
index 9cb82fbc..808b2e7a 100644
--- a/go.mod
+++ b/go.mod
@@ -109,6 +109,7 @@ require (
 	github.com/urfave/cli/v2 v2.27.7 // indirect
 	github.com/urfave/cli/v3 v3.6.1 // indirect
 	github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342 // indirect
+	github.com/xtgo/set v1.0.0 // indirect
 	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect
diff --git a/go.sum b/go.sum
index 8d3904ae..39571309 100644
--- a/go.sum
+++ b/go.sum
@@ -318,6 +318,8 @@ github.com/vektah/gqlparser/v2 v2.5.31 h1:YhWGA1mfTjID7qJhd1+Vxhpk5HTgydrGU9IgkW
 github.com/vektah/gqlparser/v2 v2.5.31/go.mod h1:c1I28gSOVNzlfc4WuDlqU7voQnsqI6OG2amkBAFmgts=
 github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342 h1:FnBeRrxr7OU4VvAzt5X7s6266i6cSVkkFPS0TuXWbIg=
 github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342/go.mod h1:Ohn+xnUBiLI6FVj/9LpzZWtj1/D6lUovWYBkxHVV3aM=
+github.com/xtgo/set v1.0.0 h1:6BCNBRv3ORNDQ7fyoJXRv+tstJz3m1JVFQErfeZz2pY=
+github.com/xtgo/set v1.0.0/go.mod h1:d3NHzGzSa0NmB2NhFyECA+QdRp29oEn2xbT+TpeFoM8=
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
diff --git a/internal/repository/job.go b/internal/repository/job.go
index 99970ce1..1ff8047e 100644
--- a/internal/repository/job.go
+++ b/internal/repository/job.go
@@ -76,6 +76,7 @@ import (
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 	"github.com/jmoiron/sqlx"
+	"github.com/xtgo/set"
 )
 
 var (
@@ -772,3 +773,63 @@ func (r *JobRepository) UpdateFootprint(
 
 	return stmt.Set("footprint", string(rawFootprint)), nil
 }
+
+func (r *JobRepository) GetUsedNodes(ts uint64) map[string][]string {
+	q := sq.Select("job.cluster", "job.resources").From("job").
+		Where("job.start_time < ?", ts).
+		Where(sq.Eq{"job.job_state": "running"})
+
+	rows, err := q.RunWith(r.stmtCache).Query()
+	if err != nil {
+		queryString, queryVars, _ := q.ToSql()
+		cclog.Errorf("Error while running query '%s' %v: %v", queryString, queryVars, err)
+		return nil
+	}
+	defer rows.Close()
+
+	// Use a map of sets for efficient deduplication
+	nodeSet := make(map[string]map[string]struct{})
+
+	var (
+		cluster      string
+		rawResources []byte
+		resources    []*schema.Resource
+	)
+
+	for rows.Next() {
+		if err := rows.Scan(&cluster, &rawResources); err != nil {
+			cclog.Warnf("Error scanning job row in GetUsedNodes: %v", err)
+			continue
+		}
+
+		if err := json.Unmarshal(rawResources, &resources); err != nil {
+			cclog.Warnf("Error unmarshaling resources for cluster %s: %v", cluster, err)
+			continue
+		}
+
+		if _, ok := nodeSet[cluster]; !ok {
+			nodeSet[cluster] = make(map[string]struct{})
+		}
+
+		for _, res := range resources {
+			nodeSet[cluster][res.Hostname] = struct{}{}
+		}
+	}
+
+	if err := rows.Err(); err != nil {
+		cclog.Errorf("Error iterating rows in GetUsedNodes: %v", err)
+	}
+
+	nodeList := make(map[string][]string)
+	for cluster, nodes := range nodeSet {
+		// Convert map keys to slice
+		list := make([]string, 0, len(nodes))
+		for node := range nodes {
+			list = append(list, node)
+		}
+		// set.Strings sorts the slice and ensures uniqueness
+		nodeList[cluster] = set.Strings(list)
+	}
+
+	return nodeList
+}

From 71b75eea0e53b99b27b18ed78f5600ce4e199b6f Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 08:49:55 +0100
Subject: [PATCH 32/59] Improve GetUsedNodes function

---
 internal/repository/job.go | 41 ++++++++++++++++++++++++++++----------
 1 file changed, 31 insertions(+), 10 deletions(-)

diff --git a/internal/repository/job.go b/internal/repository/job.go
index 1ff8047e..78e1f3fe 100644
--- a/internal/repository/job.go
+++ b/internal/repository/job.go
@@ -66,6 +66,7 @@ import (
 	"fmt"
 	"maps"
 	"math"
+	"sort"
 	"strconv"
 	"sync"
 	"time"
@@ -76,7 +77,6 @@ import (
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
 	sq "github.com/Masterminds/squirrel"
 	"github.com/jmoiron/sqlx"
-	"github.com/xtgo/set"
 )
 
 var (
@@ -774,7 +774,16 @@ func (r *JobRepository) UpdateFootprint(
 	return stmt.Set("footprint", string(rawFootprint)), nil
 }
 
-func (r *JobRepository) GetUsedNodes(ts uint64) map[string][]string {
+// GetUsedNodes returns a map of cluster names to sorted lists of unique hostnames
+// that are currently in use by jobs that started before the given timestamp and
+// are still in running state.
+//
+// The timestamp parameter (ts) is compared against job.start_time to find
+// relevant jobs. Returns an error if the database query fails or row iteration
+// encounters errors. Individual row parsing errors are logged but don't fail
+// the entire operation.
+func (r *JobRepository) GetUsedNodes(ts uint64) (map[string][]string, error) {
+	// Note: Query expects index on (job_state, start_time) for optimal performance
 	q := sq.Select("job.cluster", "job.resources").From("job").
 		Where("job.start_time < ?", ts).
 		Where(sq.Eq{"job.job_state": "running"})
@@ -782,8 +791,7 @@ func (r *JobRepository) GetUsedNodes(ts uint64) map[string][]string {
 	rows, err := q.RunWith(r.stmtCache).Query()
 	if err != nil {
 		queryString, queryVars, _ := q.ToSql()
-		cclog.Errorf("Error while running query '%s' %v: %v", queryString, queryVars, err)
-		return nil
+		return nil, fmt.Errorf("query failed [%s] %v: %w", queryString, queryVars, err)
 	}
 	defer rows.Close()
 
@@ -794,16 +802,25 @@ func (r *JobRepository) GetUsedNodes(ts uint64) map[string][]string {
 		cluster      string
 		rawResources []byte
 		resources    []*schema.Resource
+		skippedRows  int
 	)
 
 	for rows.Next() {
 		if err := rows.Scan(&cluster, &rawResources); err != nil {
 			cclog.Warnf("Error scanning job row in GetUsedNodes: %v", err)
+			skippedRows++
 			continue
 		}
 
+		resources = resources[:0] // Clear slice, keep capacity
 		if err := json.Unmarshal(rawResources, &resources); err != nil {
 			cclog.Warnf("Error unmarshaling resources for cluster %s: %v", cluster, err)
+			skippedRows++
+			continue
+		}
+
+		if len(resources) == 0 {
+			cclog.Debugf("Job in cluster %s has no resources", cluster)
 			continue
 		}
 
@@ -817,19 +834,23 @@ func (r *JobRepository) GetUsedNodes(ts uint64) map[string][]string {
 	}
 
 	if err := rows.Err(); err != nil {
-		cclog.Errorf("Error iterating rows in GetUsedNodes: %v", err)
+		return nil, fmt.Errorf("error iterating rows: %w", err)
 	}
 
-	nodeList := make(map[string][]string)
+	if skippedRows > 0 {
+		cclog.Warnf("GetUsedNodes: Skipped %d rows due to parsing errors", skippedRows)
+	}
+
+	// Convert sets to sorted slices
+	nodeList := make(map[string][]string, len(nodeSet))
 	for cluster, nodes := range nodeSet {
-		// Convert map keys to slice
 		list := make([]string, 0, len(nodes))
 		for node := range nodes {
 			list = append(list, node)
 		}
-		// set.Strings sorts the slice and ensures uniqueness
-		nodeList[cluster] = set.Strings(list)
+		sort.Strings(list)
+		nodeList[cluster] = list
 	}
 
-	return nodeList
+	return nodeList, nil
 }

From 6cf59043a38ce70963e5a8b24046cd0c9820708c Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 08:59:27 +0100
Subject: [PATCH 33/59] Review and improve, add documentation

---
 internal/repository/jobQuery.go | 128 +++++++++++++++++++++-----------
 1 file changed, 86 insertions(+), 42 deletions(-)

diff --git a/internal/repository/jobQuery.go b/internal/repository/jobQuery.go
index 4655614f..745fa32d 100644
--- a/internal/repository/jobQuery.go
+++ b/internal/repository/jobQuery.go
@@ -2,6 +2,10 @@
 // All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
+// Package repository provides job query functionality with filtering, pagination,
+// and security controls. This file contains the main query builders and security
+// checks for job retrieval operations.
 package repository
 
 import (
@@ -19,6 +23,22 @@ import (
 	sq "github.com/Masterminds/squirrel"
 )
 
+const (
+	// Default initial capacity for job result slices
+	defaultJobsCapacity = 50
+)
+
+// QueryJobs retrieves jobs from the database with optional filtering, pagination,
+// and sorting. Security controls are automatically applied based on the user context.
+//
+// Parameters:
+//   - ctx: Context containing user authentication information
+//   - filters: Optional job filters (cluster, state, user, time ranges, etc.)
+//   - page: Optional pagination parameters (page number and items per page)
+//   - order: Optional sorting specification (column or footprint field)
+//
+// Returns a slice of jobs matching the criteria, or an error if the query fails.
+// The function enforces role-based access control through SecurityCheck.
 func (r *JobRepository) QueryJobs(
 	ctx context.Context,
 	filters []*model.JobFilter,
@@ -33,18 +53,16 @@ func (r *JobRepository) QueryJobs(
 	if order != nil {
 		field := toSnakeCase(order.Field)
 		if order.Type == "col" {
-			// "col": Fixed column name query
 			switch order.Order {
 			case model.SortDirectionEnumAsc:
 				query = query.OrderBy(fmt.Sprintf("job.%s ASC", field))
 			case model.SortDirectionEnumDesc:
 				query = query.OrderBy(fmt.Sprintf("job.%s DESC", field))
 			default:
-				return nil, errors.New("REPOSITORY/QUERY > invalid sorting order for column")
+				return nil, errors.New("invalid sorting order for column")
 			}
 		} else {
-			// "foot": Order by footprint JSON field values
-			// Verify and Search Only in Valid Jsons
+			// Order by footprint JSON field values
 			query = query.Where("JSON_VALID(meta_data)")
 			switch order.Order {
 			case model.SortDirectionEnumAsc:
@@ -52,7 +70,7 @@ func (r *JobRepository) QueryJobs(
 			case model.SortDirectionEnumDesc:
 				query = query.OrderBy(fmt.Sprintf("JSON_EXTRACT(footprint, \"$.%s\") DESC", field))
 			default:
-				return nil, errors.New("REPOSITORY/QUERY > invalid sorting order for footprint")
+				return nil, errors.New("invalid sorting order for footprint")
 			}
 		}
 	}
@@ -69,29 +87,35 @@ func (r *JobRepository) QueryJobs(
 	rows, err := query.RunWith(r.stmtCache).Query()
 	if err != nil {
 		queryString, queryVars, _ := query.ToSql()
-		cclog.Errorf("Error while running query '%s' %v: %v", queryString, queryVars, err)
-		return nil, err
+		return nil, fmt.Errorf("query failed [%s] %v: %w", queryString, queryVars, err)
 	}
+	defer rows.Close()
 
-	jobs := make([]*schema.Job, 0, 50)
+	jobs := make([]*schema.Job, 0, defaultJobsCapacity)
 	for rows.Next() {
 		job, err := scanJob(rows)
 		if err != nil {
-			rows.Close()
-			cclog.Warn("Error while scanning rows (Jobs)")
-			return nil, err
+			cclog.Warnf("Error scanning job row: %v", err)
+			return nil, fmt.Errorf("failed to scan job row: %w", err)
 		}
 		jobs = append(jobs, job)
 	}
 
+	if err := rows.Err(); err != nil {
+		return nil, fmt.Errorf("error iterating job rows: %w", err)
+	}
+
 	return jobs, nil
 }
 
+// CountJobs returns the total number of jobs matching the given filters.
+// Security controls are automatically applied based on the user context.
+// Uses DISTINCT count to handle tag filters correctly (jobs may appear multiple
+// times when joined with the tag table).
 func (r *JobRepository) CountJobs(
 	ctx context.Context,
 	filters []*model.JobFilter,
 ) (int, error) {
-	// DISTICT count for tags filters, does not affect other queries
 	query, qerr := SecurityCheck(ctx, sq.Select("count(DISTINCT job.id)").From("job"))
 	if qerr != nil {
 		return 0, qerr
@@ -103,12 +127,22 @@ func (r *JobRepository) CountJobs(
 
 	var count int
 	if err := query.RunWith(r.DB).Scan(&count); err != nil {
-		return 0, err
+		return 0, fmt.Errorf("failed to count jobs: %w", err)
 	}
 
 	return count, nil
 }
 
+// SecurityCheckWithUser applies role-based access control filters to a job query
+// based on the provided user's roles and permissions.
+//
+// Access rules by role:
+//   - API role (exclusive): Full access to all jobs
+//   - Admin/Support roles: Full access to all jobs
+//   - Manager role: Access to jobs in managed projects plus own jobs
+//   - User role: Access only to own jobs
+//
+// Returns an error if the user is nil or has no recognized roles.
 func SecurityCheckWithUser(user *schema.User, query sq.SelectBuilder) (sq.SelectBuilder, error) {
 	if user == nil {
 		var qnil sq.SelectBuilder
@@ -116,32 +150,35 @@ func SecurityCheckWithUser(user *schema.User, query sq.SelectBuilder) (sq.Select
 	}
 
 	switch {
-	case len(user.Roles) == 1 && user.HasRole(schema.RoleApi): // API-User : All jobs
+	case len(user.Roles) == 1 && user.HasRole(schema.RoleApi):
 		return query, nil
-	case user.HasAnyRole([]schema.Role{schema.RoleAdmin, schema.RoleSupport}): // Admin & Support : All jobs
+	case user.HasAnyRole([]schema.Role{schema.RoleAdmin, schema.RoleSupport}):
 		return query, nil
-	case user.HasRole(schema.RoleManager): // Manager : Add filter for managed projects' jobs only + personal jobs
+	case user.HasRole(schema.RoleManager):
 		if len(user.Projects) != 0 {
 			return query.Where(sq.Or{sq.Eq{"job.project": user.Projects}, sq.Eq{"job.hpc_user": user.Username}}), nil
-		} else {
-			cclog.Debugf("Manager-User '%s' has no defined projects to lookup! Query only personal jobs ...", user.Username)
-			return query.Where("job.hpc_user = ?", user.Username), nil
 		}
-	case user.HasRole(schema.RoleUser): // User : Only personal jobs
+		cclog.Debugf("Manager '%s' has no assigned projects, restricting to personal jobs", user.Username)
 		return query.Where("job.hpc_user = ?", user.Username), nil
-	default: // No known Role, return error
+	case user.HasRole(schema.RoleUser):
+		return query.Where("job.hpc_user = ?", user.Username), nil
+	default:
 		var qnil sq.SelectBuilder
 		return qnil, fmt.Errorf("user has no or unknown roles")
 	}
 }
 
+// SecurityCheck extracts the user from the context and applies role-based access
+// control filters to the query. This is a convenience wrapper around SecurityCheckWithUser.
 func SecurityCheck(ctx context.Context, query sq.SelectBuilder) (sq.SelectBuilder, error) {
 	user := GetUserFromContext(ctx)
-
 	return SecurityCheckWithUser(user, query)
 }
 
-// Build a sq.SelectBuilder out of a schema.JobFilter.
+// BuildWhereClause constructs SQL WHERE conditions from a JobFilter and applies
+// them to the query. Supports filtering by job properties (cluster, state, user),
+// time ranges, resource usage, tags, and JSON field searches in meta_data,
+// footprint, and resources columns.
 func BuildWhereClause(filter *model.JobFilter, query sq.SelectBuilder) sq.SelectBuilder {
 	// Primary Key
 	if filter.DbID != nil {
@@ -205,23 +242,24 @@ func BuildWhereClause(filter *model.JobFilter, query sq.SelectBuilder) sq.Select
 	// Queries Within JSONs
 	if filter.MetricStats != nil {
 		for _, ms := range filter.MetricStats {
-			query = buildFloatJsonCondition(ms.MetricName, ms.Range, query)
+			query = buildFloatJSONCondition(ms.MetricName, ms.Range, query)
 		}
 	}
 	if filter.Node != nil {
-		query = buildResourceJsonCondition("hostname", filter.Node, query)
+		query = buildResourceJSONCondition("hostname", filter.Node, query)
 	}
 	if filter.JobName != nil {
-		query = buildMetaJsonCondition("jobName", filter.JobName, query)
+		query = buildMetaJSONCondition("jobName", filter.JobName, query)
 	}
 	if filter.Schedule != nil {
 		interactiveJobname := "interactive"
-		if *filter.Schedule == "interactive" {
+		switch *filter.Schedule {
+		case "interactive":
 			iFilter := model.StringInput{Eq: &interactiveJobname}
-			query = buildMetaJsonCondition("jobName", &iFilter, query)
-		} else if *filter.Schedule == "batch" {
+			query = buildMetaJSONCondition("jobName", &iFilter, query)
+		case "batch":
 			sFilter := model.StringInput{Neq: &interactiveJobname}
-			query = buildMetaJsonCondition("jobName", &sFilter, query)
+			query = buildMetaJSONCondition("jobName", &sFilter, query)
 		}
 	}
 
@@ -235,14 +273,18 @@ func BuildWhereClause(filter *model.JobFilter, query sq.SelectBuilder) sq.Select
 	return query
 }
 
+// buildIntCondition creates a BETWEEN clause for integer range filters.
 func buildIntCondition(field string, cond *config.IntRange, query sq.SelectBuilder) sq.SelectBuilder {
 	return query.Where(field+" BETWEEN ? AND ?", cond.From, cond.To)
 }
 
+// buildFloatCondition creates a BETWEEN clause for float range filters.
 func buildFloatCondition(field string, cond *model.FloatRange, query sq.SelectBuilder) sq.SelectBuilder {
 	return query.Where(field+" BETWEEN ? AND ?", cond.From, cond.To)
 }
 
+// buildTimeCondition creates time range filters supporting absolute timestamps,
+// relative time ranges (last6h, last24h, last7d, last30d), or open-ended ranges.
 func buildTimeCondition(field string, cond *config.TimeRange, query sq.SelectBuilder) sq.SelectBuilder {
 	if cond.From != nil && cond.To != nil {
 		return query.Where(field+" BETWEEN ? AND ?", cond.From.Unix(), cond.To.Unix())
@@ -272,12 +314,14 @@ func buildTimeCondition(field string, cond *config.TimeRange, query sq.SelectBui
 	}
 }
 
-func buildFloatJsonCondition(condName string, condRange *model.FloatRange, query sq.SelectBuilder) sq.SelectBuilder {
-	// Verify and Search Only in Valid Jsons
+// buildFloatJSONCondition creates a filter on a numeric field within the footprint JSON column.
+func buildFloatJSONCondition(condName string, condRange *model.FloatRange, query sq.SelectBuilder) sq.SelectBuilder {
 	query = query.Where("JSON_VALID(footprint)")
 	return query.Where("JSON_EXTRACT(footprint, \"$."+condName+"\") BETWEEN ? AND ?", condRange.From, condRange.To)
 }
 
+// buildStringCondition creates filters for string fields supporting equality,
+// inequality, prefix, suffix, substring, and IN list matching.
 func buildStringCondition(field string, cond *model.StringInput, query sq.SelectBuilder) sq.SelectBuilder {
 	if cond.Eq != nil {
 		return query.Where(field+" = ?", *cond.Eq)
@@ -302,10 +346,9 @@ func buildStringCondition(field string, cond *model.StringInput, query sq.Select
 	return query
 }
 
-func buildMetaJsonCondition(jsonField string, cond *model.StringInput, query sq.SelectBuilder) sq.SelectBuilder {
-	// Verify and Search Only in Valid Jsons
+// buildMetaJSONCondition creates filters on fields within the meta_data JSON column.
+func buildMetaJSONCondition(jsonField string, cond *model.StringInput, query sq.SelectBuilder) sq.SelectBuilder {
 	query = query.Where("JSON_VALID(meta_data)")
-	// add "AND" Sql query Block for field match
 	if cond.Eq != nil {
 		return query.Where("JSON_EXTRACT(meta_data, \"$."+jsonField+"\") = ?", *cond.Eq)
 	}
@@ -324,10 +367,10 @@ func buildMetaJsonCondition(jsonField string, cond *model.StringInput, query sq.
 	return query
 }
 
-func buildResourceJsonCondition(jsonField string, cond *model.StringInput, query sq.SelectBuilder) sq.SelectBuilder {
-	// Verify and Search Only in Valid Jsons
+// buildResourceJSONCondition creates filters on fields within the resources JSON array column.
+// Uses json_each to search within array elements.
+func buildResourceJSONCondition(jsonField string, cond *model.StringInput, query sq.SelectBuilder) sq.SelectBuilder {
 	query = query.Where("JSON_VALID(resources)")
-	// add "AND" Sql query Block for field match
 	if cond.Eq != nil {
 		return query.Where("EXISTS (SELECT 1 FROM json_each(job.resources) WHERE json_extract(value, \"$."+jsonField+"\") = ?)", *cond.Eq)
 	}
@@ -351,15 +394,16 @@ var (
 	matchAllCap   = regexp.MustCompile("([a-z0-9])([A-Z])")
 )
 
+// toSnakeCase converts camelCase strings to snake_case for SQL column names.
+// Includes security checks to prevent SQL injection attempts.
+// Panics if potentially dangerous characters are detected.
 func toSnakeCase(str string) string {
 	for _, c := range str {
-		if c == '\'' || c == '\\' {
-			cclog.Panic("toSnakeCase() attack vector!")
+		if c == '\'' || c == '\\' || c == '"' || c == ';' || c == '-' || c == ' ' {
+			cclog.Panicf("toSnakeCase: potentially dangerous character detected in input: %q", str)
 		}
 	}
 
-	str = strings.ReplaceAll(str, "'", "")
-	str = strings.ReplaceAll(str, "\\", "")
 	snake := matchFirstCap.ReplaceAllString(str, "${1}_${2}")
 	snake = matchAllCap.ReplaceAllString(snake, "${1}_${2}")
 	return strings.ToLower(snake)

From 9e542dc2006c2dbe3fc4c7206254d2590affdfd8 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 09:26:03 +0100
Subject: [PATCH 34/59] Review and improve, add documentation

---
 internal/repository/jobFind.go | 83 +++++++++++++++++++++++-----------
 1 file changed, 57 insertions(+), 26 deletions(-)

diff --git a/internal/repository/jobFind.go b/internal/repository/jobFind.go
index ff2c27aa..8f6daeb4 100644
--- a/internal/repository/jobFind.go
+++ b/internal/repository/jobFind.go
@@ -27,6 +27,10 @@ func (r *JobRepository) Find(
 	cluster *string,
 	startTime *int64,
 ) (*schema.Job, error) {
+	if jobID == nil {
+		return nil, fmt.Errorf("jobID cannot be nil")
+	}
+
 	start := time.Now()
 	q := sq.Select(jobColumns...).From("job").
 		Where("job.job_id = ?", *jobID)
@@ -38,17 +42,27 @@ func (r *JobRepository) Find(
 		q = q.Where("job.start_time = ?", *startTime)
 	}
 
-	q = q.OrderBy("job.id DESC") // always use newest matching job by db id if more than one match
+	q = q.OrderBy("job.id DESC").Limit(1) // always use newest matching job by db id if more than one match
 
 	cclog.Debugf("Timer Find %s", time.Since(start))
 	return scanJob(q.RunWith(r.stmtCache).QueryRow())
 }
 
+// FindCached executes a SQL query to find a specific batch job from the job_cache table.
+// The job is queried using the batch job id, and optionally filtered by cluster name
+// and start time (UNIX epoch time seconds). This method uses cached job data which
+// may be stale but provides faster access than Find().
+// It returns a pointer to a schema.Job data structure and an error variable.
+// To check if no job was found test err == sql.ErrNoRows
 func (r *JobRepository) FindCached(
 	jobID *int64,
 	cluster *string,
 	startTime *int64,
 ) (*schema.Job, error) {
+	if jobID == nil {
+		return nil, fmt.Errorf("jobID cannot be nil")
+	}
+
 	q := sq.Select(jobCacheColumns...).From("job_cache").
 		Where("job_cache.job_id = ?", *jobID)
 
@@ -59,7 +73,7 @@ func (r *JobRepository) FindCached(
 		q = q.Where("job_cache.start_time = ?", *startTime)
 	}
 
-	q = q.OrderBy("job_cache.id DESC") // always use newest matching job by db id if more than one match
+	q = q.OrderBy("job_cache.id DESC").Limit(1) // always use newest matching job by db id if more than one match
 
 	return scanJob(q.RunWith(r.stmtCache).QueryRow())
 }
@@ -74,6 +88,10 @@ func (r *JobRepository) FindAll(
 	cluster *string,
 	startTime *int64,
 ) ([]*schema.Job, error) {
+	if jobID == nil {
+		return nil, fmt.Errorf("jobID cannot be nil")
+	}
+
 	start := time.Now()
 	q := sq.Select(jobColumns...).From("job").
 		Where("job.job_id = ?", *jobID)
@@ -87,8 +105,8 @@ func (r *JobRepository) FindAll(
 
 	rows, err := q.RunWith(r.stmtCache).Query()
 	if err != nil {
-		cclog.Error("Error while running query")
-		return nil, err
+		cclog.Errorf("Error while running FindAll query for jobID=%d: %v", *jobID, err)
+		return nil, fmt.Errorf("failed to execute FindAll query: %w", err)
 	}
 	defer rows.Close()
 
@@ -96,8 +114,8 @@ func (r *JobRepository) FindAll(
 	for rows.Next() {
 		job, err := scanJob(rows)
 		if err != nil {
-			cclog.Warn("Error while scanning rows")
-			return nil, err
+			cclog.Warnf("Error while scanning rows in FindAll: %v", err)
+			return nil, fmt.Errorf("failed to scan job row: %w", err)
 		}
 		jobs = append(jobs, job)
 	}
@@ -120,8 +138,8 @@ func (r *JobRepository) GetJobList(limit int, offset int) ([]int64, error) {
 
 	rows, err := query.RunWith(r.stmtCache).Query()
 	if err != nil {
-		cclog.Error("Error while running query")
-		return nil, err
+		cclog.Errorf("Error while running GetJobList query (limit=%d, offset=%d): %v", limit, offset, err)
+		return nil, fmt.Errorf("failed to execute GetJobList query: %w", err)
 	}
 	defer rows.Close()
 
@@ -130,8 +148,8 @@ func (r *JobRepository) GetJobList(limit int, offset int) ([]int64, error) {
 		var id int64
 		err := rows.Scan(&id)
 		if err != nil {
-			cclog.Warn("Error while scanning rows")
-			return nil, err
+			cclog.Warnf("Error while scanning rows in GetJobList: %v", err)
+			return nil, fmt.Errorf("failed to scan job ID: %w", err)
 		}
 		jl = append(jl, id)
 	}
@@ -202,10 +220,10 @@ func (r *JobRepository) FindByJobID(ctx context.Context, jobID int64, startTime
 	return scanJob(q.RunWith(r.stmtCache).QueryRow())
 }
 
-// IsJobOwner executes a SQL query to find a specific batch job.
-// The job is queried using the slurm id,a username and the cluster.
-// It returns a bool.
-// If job was found, user is owner: test err != sql.ErrNoRows
+// IsJobOwner checks if the specified user owns the batch job identified by jobID,
+// startTime, and cluster. Returns true if the user is the owner, false otherwise.
+// This method does not return errors; it returns false for both non-existent jobs
+// and jobs owned by other users.
 func (r *JobRepository) IsJobOwner(jobID int64, startTime int64, user string, cluster string) bool {
 	q := sq.Select("id").
 		From("job").
@@ -215,6 +233,9 @@ func (r *JobRepository) IsJobOwner(jobID int64, startTime int64, user string, cl
 		Where("job.start_time = ?", startTime)
 
 	_, err := scanJob(q.RunWith(r.stmtCache).QueryRow())
+	if err != nil && err != sql.ErrNoRows {
+		cclog.Warnf("IsJobOwner: unexpected error for jobID=%d, user=%s, cluster=%s: %v", jobID, user, cluster, err)
+	}
 	return err != sql.ErrNoRows
 }
 
@@ -232,6 +253,11 @@ func (r *JobRepository) FindConcurrentJobs(
 	}
 
 	query = query.Where("cluster = ?", job.Cluster)
+
+	if len(job.Resources) == 0 {
+		return nil, fmt.Errorf("job has no resources defined")
+	}
+
 	var startTime int64
 	var stopTime int64
 
@@ -244,10 +270,15 @@ func (r *JobRepository) FindConcurrentJobs(
 		stopTime = startTime + int64(job.Duration)
 	}
 
-	// Add 200s overlap for jobs start time at the end
-	startTimeTail := startTime + 10
-	stopTimeTail := stopTime - 200
-	startTimeFront := startTime + 200
+	// Time buffer constants for finding overlapping jobs
+	// overlapBufferStart: 10s grace period at job start to catch jobs starting just after
+	// overlapBufferEnd: 200s buffer at job end to account for scheduling/cleanup overlap
+	const overlapBufferStart = 10
+	const overlapBufferEnd = 200
+
+	startTimeTail := startTime + overlapBufferStart
+	stopTimeTail := stopTime - overlapBufferEnd
+	startTimeFront := startTime + overlapBufferEnd
 
 	queryRunning := query.Where("job.job_state = ?").Where("(job.start_time BETWEEN ? AND ? OR job.start_time < ?)",
 		"running", startTimeTail, stopTimeTail, startTime)
@@ -261,8 +292,8 @@ func (r *JobRepository) FindConcurrentJobs(
 
 	rows, err := query.RunWith(r.stmtCache).Query()
 	if err != nil {
-		cclog.Errorf("Error while running query: %v", err)
-		return nil, err
+		cclog.Errorf("Error while running concurrent jobs query: %v", err)
+		return nil, fmt.Errorf("failed to execute concurrent jobs query: %w", err)
 	}
 	defer rows.Close()
 
@@ -273,8 +304,8 @@ func (r *JobRepository) FindConcurrentJobs(
 		var id, jobID, startTime sql.NullInt64
 
 		if err = rows.Scan(&id, &jobID, &startTime); err != nil {
-			cclog.Warn("Error while scanning rows")
-			return nil, err
+			cclog.Warnf("Error while scanning concurrent job rows: %v", err)
+			return nil, fmt.Errorf("failed to scan concurrent job row: %w", err)
 		}
 
 		if id.Valid {
@@ -289,8 +320,8 @@ func (r *JobRepository) FindConcurrentJobs(
 
 	rows, err = queryRunning.RunWith(r.stmtCache).Query()
 	if err != nil {
-		cclog.Errorf("Error while running query: %v", err)
-		return nil, err
+		cclog.Errorf("Error while running concurrent running jobs query: %v", err)
+		return nil, fmt.Errorf("failed to execute concurrent running jobs query: %w", err)
 	}
 	defer rows.Close()
 
@@ -298,8 +329,8 @@ func (r *JobRepository) FindConcurrentJobs(
 		var id, jobID, startTime sql.NullInt64
 
 		if err := rows.Scan(&id, &jobID, &startTime); err != nil {
-			cclog.Warn("Error while scanning rows")
-			return nil, err
+			cclog.Warnf("Error while scanning running concurrent job rows: %v", err)
+			return nil, fmt.Errorf("failed to scan running concurrent job row: %w", err)
 		}
 
 		if id.Valid {

From b2f870e3c04a41b4fcca658afa59677d36a23146 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 10:08:06 +0100
Subject: [PATCH 35/59] Convert nodestate nats API to influx line protocol
 payload. Review and add doc comments.

Improve and extend tests
---
 internal/api/nats.go      | 143 +++++++++++++++++++++++++++-----
 internal/api/nats_test.go | 170 +++++++++++++++++++++++++++-----------
 2 files changed, 243 insertions(+), 70 deletions(-)

diff --git a/internal/api/nats.go b/internal/api/nats.go
index efd04406..48c6449b 100644
--- a/internal/api/nats.go
+++ b/internal/api/nats.go
@@ -6,7 +6,6 @@
 package api
 
 import (
-	"bytes"
 	"database/sql"
 	"encoding/json"
 	"strings"
@@ -26,7 +25,40 @@ import (
 )
 
 // NatsAPI provides NATS subscription-based handlers for Job and Node operations.
-// It mirrors the functionality of the REST API but uses NATS messaging.
+// It mirrors the functionality of the REST API but uses NATS messaging with
+// InfluxDB line protocol as the message format.
+//
+// # Message Format
+//
+// All NATS messages use InfluxDB line protocol format (https://docs.influxdata.com/influxdb/v2.0/reference/syntax/line-protocol/)
+// with the following structure:
+//
+//	measurement,tag1=value1,tag2=value2 field1=value1,field2=value2 timestamp
+//
+// # Job Events
+//
+// Job start/stop events use the "job" measurement with a "function" tag to distinguish operations:
+//
+//	job,function=start_job event="{...JSON payload...}" <timestamp>
+//	job,function=stop_job event="{...JSON payload...}" <timestamp>
+//
+// The JSON payload in the "event" field follows the schema.Job or StopJobAPIRequest structure.
+//
+// Example job start message:
+//
+//	job,function=start_job event="{\"jobId\":1001,\"user\":\"testuser\",\"cluster\":\"testcluster\",...}" 1234567890000000000
+//
+// # Node State Events
+//
+// Node state updates use the "nodestate" measurement with cluster information:
+//
+//	nodestate event="{...JSON payload...}" <timestamp>
+//
+// The JSON payload follows the UpdateNodeStatesRequest structure.
+//
+// Example node state message:
+//
+//	nodestate event="{\"cluster\":\"testcluster\",\"nodes\":[{\"hostname\":\"node01\",\"states\":[\"idle\"]}]}" 1234567890000000000
 type NatsAPI struct {
 	JobRepository *repository.JobRepository
 	// RepositoryMutex protects job creation operations from race conditions
@@ -67,10 +99,12 @@ func (api *NatsAPI) StartSubscriptions() error {
 	return nil
 }
 
+// processJobEvent routes job event messages to the appropriate handler based on the "function" tag.
+// Validates that required tags and fields are present before processing.
 func (api *NatsAPI) processJobEvent(msg lp.CCMessage) {
 	function, ok := msg.GetTag("function")
 	if !ok {
-		cclog.Errorf("Job event is missing tag 'function': %+v", msg)
+		cclog.Errorf("Job event is missing required tag 'function': measurement=%s", msg.Name())
 		return
 	}
 
@@ -78,43 +112,66 @@ func (api *NatsAPI) processJobEvent(msg lp.CCMessage) {
 	case "start_job":
 		v, ok := msg.GetEventValue()
 		if !ok {
-			cclog.Errorf("Job event is missing event value: %+v", msg)
+			cclog.Errorf("Job start event is missing event field with JSON payload")
+			return
 		}
 		api.handleStartJob(v)
 
 	case "stop_job":
 		v, ok := msg.GetEventValue()
 		if !ok {
-			cclog.Errorf("Job event is missing event value: %+v", msg)
+			cclog.Errorf("Job stop event is missing event field with JSON payload")
+			return
 		}
 		api.handleStopJob(v)
+
 	default:
-		cclog.Warnf("Unimplemented job event: %+v", msg)
+		cclog.Warnf("Unknown job event function '%s', expected 'start_job' or 'stop_job'", function)
 	}
 }
 
+// handleJobEvent processes job-related messages received via NATS using InfluxDB line protocol.
+// The message must be in line protocol format with measurement="job" and include:
+//   - tag "function" with value "start_job" or "stop_job"
+//   - field "event" containing JSON payload (schema.Job or StopJobAPIRequest)
+//
+// Example: job,function=start_job event="{\"jobId\":1001,...}" 1234567890000000000
 func (api *NatsAPI) handleJobEvent(subject string, data []byte) {
+	if len(data) == 0 {
+		cclog.Warnf("NATS %s: received empty message", subject)
+		return
+	}
+
 	d := influx.NewDecoderWithBytes(data)
 
 	for d.Next() {
 		m, err := receivers.DecodeInfluxMessage(d)
 		if err != nil {
-			cclog.Errorf("NATS %s:  Failed to decode message: %v", subject, err)
+			cclog.Errorf("NATS %s: failed to decode InfluxDB line protocol message: %v", subject, err)
 			return
 		}
 
-		if m.IsEvent() {
-			if m.Name() == "job" {
-				api.processJobEvent(m)
-			}
+		if !m.IsEvent() {
+			cclog.Warnf("NATS %s: received non-event message, skipping", subject)
+			continue
 		}
 
+		if m.Name() == "job" {
+			api.processJobEvent(m)
+		} else {
+			cclog.Warnf("NATS %s: unexpected measurement name '%s', expected 'job'", subject, m.Name())
+		}
 	}
 }
 
 // handleStartJob processes job start messages received via NATS.
-// Expected JSON payload follows the schema.Job structure.
+// The payload parameter contains JSON following the schema.Job structure.
+// Jobs are validated, checked for duplicates, and inserted into the database.
 func (api *NatsAPI) handleStartJob(payload string) {
+	if payload == "" {
+		cclog.Error("NATS start job: payload is empty")
+		return
+	}
 	req := schema.Job{
 		Shared:           "none",
 		MonitoringStatus: schema.MonitoringStatusRunningOrArchiving,
@@ -173,8 +230,13 @@ func (api *NatsAPI) handleStartJob(payload string) {
 }
 
 // handleStopJob processes job stop messages received via NATS.
-// Expected JSON payload follows the StopJobAPIRequest structure.
+// The payload parameter contains JSON following the StopJobAPIRequest structure.
+// The job is marked as stopped in the database and archiving is triggered if monitoring is enabled.
 func (api *NatsAPI) handleStopJob(payload string) {
+	if payload == "" {
+		cclog.Error("NATS stop job: payload is empty")
+		return
+	}
 	var req StopJobAPIRequest
 
 	dec := json.NewDecoder(strings.NewReader(payload))
@@ -243,15 +305,21 @@ func (api *NatsAPI) handleStopJob(payload string) {
 	archiver.TriggerArchiving(job)
 }
 
-// handleNodeState processes node state update messages received via NATS.
-// Expected JSON payload follows the UpdateNodeStatesRequest structure.
-func (api *NatsAPI) handleNodeState(subject string, data []byte) {
+// processNodestateEvent extracts and processes node state data from the InfluxDB message.
+// Updates node states in the repository for all nodes in the payload.
+func (api *NatsAPI) processNodestateEvent(msg lp.CCMessage) {
+	v, ok := msg.GetEventValue()
+	if !ok {
+		cclog.Errorf("Nodestate event is missing event field with JSON payload")
+		return
+	}
+
 	var req UpdateNodeStatesRequest
 
-	dec := json.NewDecoder(bytes.NewReader(data))
+	dec := json.NewDecoder(strings.NewReader(v))
 	dec.DisallowUnknownFields()
 	if err := dec.Decode(&req); err != nil {
-		cclog.Errorf("NATS %s: parsing request failed: %v", subject, err)
+		cclog.Errorf("NATS nodestate: parsing request failed: %v", err)
 		return
 	}
 
@@ -270,10 +338,43 @@ func (api *NatsAPI) handleNodeState(subject string, data []byte) {
 		}
 
 		if err := repo.UpdateNodeState(node.Hostname, req.Cluster, &nodeState); err != nil {
-			cclog.Errorf("NATS %s: updating node state for %s on %s failed: %v",
-				subject, node.Hostname, req.Cluster, err)
+			cclog.Errorf("NATS nodestate: updating node state for %s on %s failed: %v",
+				node.Hostname, req.Cluster, err)
 		}
 	}
 
-	cclog.Debugf("NATS %s: updated %d node states for cluster %s", subject, len(req.Nodes), req.Cluster)
+	cclog.Debugf("NATS nodestate: updated %d node states for cluster %s", len(req.Nodes), req.Cluster)
+}
+
+// handleNodeState processes node state update messages received via NATS using InfluxDB line protocol.
+// The message must be in line protocol format with measurement="nodestate" and include:
+//   - field "event" containing JSON payload (UpdateNodeStatesRequest)
+//
+// Example: nodestate event="{\"cluster\":\"testcluster\",\"nodes\":[...]}" 1234567890000000000
+func (api *NatsAPI) handleNodeState(subject string, data []byte) {
+	if len(data) == 0 {
+		cclog.Warnf("NATS %s: received empty message", subject)
+		return
+	}
+
+	d := influx.NewDecoderWithBytes(data)
+
+	for d.Next() {
+		m, err := receivers.DecodeInfluxMessage(d)
+		if err != nil {
+			cclog.Errorf("NATS %s: failed to decode InfluxDB line protocol message: %v", subject, err)
+			return
+		}
+
+		if !m.IsEvent() {
+			cclog.Warnf("NATS %s: received non-event message, skipping", subject)
+			continue
+		}
+
+		if m.Name() == "nodestate" {
+			api.processNodestateEvent(m)
+		} else {
+			cclog.Warnf("NATS %s: unexpected measurement name '%s', expected 'nodestate'", subject, m.Name())
+		}
+	}
 }
diff --git a/internal/api/nats_test.go b/internal/api/nats_test.go
index 319668bb..4b1431cb 100644
--- a/internal/api/nats_test.go
+++ b/internal/api/nats_test.go
@@ -603,25 +603,13 @@ func TestNatsHandleNodeState(t *testing.T) {
 
 	tests := []struct {
 		name        string
-		payload     string
+		data        []byte
 		expectError bool
 		validateFn  func(t *testing.T)
 	}{
 		{
-			name: "valid node state update",
-			payload: `{
-				"cluster": "testcluster",
-				"nodes": [
-					{
-						"hostname": "host123",
-						"states": ["allocated"],
-						"cpusAllocated": 8,
-						"memoryAllocated": 16384,
-						"gpusAllocated": 0,
-						"jobsRunning": 1
-					}
-				]
-			}`,
+			name:        "valid node state update",
+			data:        []byte(`nodestate event="{\"cluster\":\"testcluster\",\"nodes\":[{\"hostname\":\"host123\",\"states\":[\"allocated\"],\"cpusAllocated\":8,\"memoryAllocated\":16384,\"gpusAllocated\":0,\"jobsRunning\":1}]}" 1234567890000000000`),
 			expectError: false,
 			validateFn: func(t *testing.T) {
 				// In a full test, we would verify the node state was updated in the database
@@ -629,51 +617,35 @@ func TestNatsHandleNodeState(t *testing.T) {
 			},
 		},
 		{
-			name: "multiple nodes",
-			payload: `{
-				"cluster": "testcluster",
-				"nodes": [
-					{
-						"hostname": "host123",
-						"states": ["idle"],
-						"cpusAllocated": 0,
-						"memoryAllocated": 0,
-						"gpusAllocated": 0,
-						"jobsRunning": 0
-					},
-					{
-						"hostname": "host124",
-						"states": ["allocated"],
-						"cpusAllocated": 4,
-						"memoryAllocated": 8192,
-						"gpusAllocated": 1,
-						"jobsRunning": 1
-					}
-				]
-			}`,
+			name:        "multiple nodes",
+			data:        []byte(`nodestate event="{\"cluster\":\"testcluster\",\"nodes\":[{\"hostname\":\"host123\",\"states\":[\"idle\"],\"cpusAllocated\":0,\"memoryAllocated\":0,\"gpusAllocated\":0,\"jobsRunning\":0},{\"hostname\":\"host124\",\"states\":[\"allocated\"],\"cpusAllocated\":4,\"memoryAllocated\":8192,\"gpusAllocated\":1,\"jobsRunning\":1}]}" 1234567890000000000`),
 			expectError: false,
 		},
 		{
-			name: "invalid JSON",
-			payload: `{
-				"cluster": "testcluster",
-				"nodes": "not an array"
-			}`,
+			name:        "invalid JSON in event field",
+			data:        []byte(`nodestate event="{\"cluster\":\"testcluster\",\"nodes\":\"not an array\"}" 1234567890000000000`),
 			expectError: true,
 		},
 		{
-			name: "empty nodes array",
-			payload: `{
-				"cluster": "testcluster",
-				"nodes": []
-			}`,
+			name:        "empty nodes array",
+			data:        []byte(`nodestate event="{\"cluster\":\"testcluster\",\"nodes\":[]}" 1234567890000000000`),
 			expectError: false, // Empty array should not cause error
 		},
+		{
+			name:        "invalid line protocol format",
+			data:        []byte(`invalid line protocol format`),
+			expectError: true,
+		},
+		{
+			name:        "empty data",
+			data:        []byte(``),
+			expectError: false, // Should be handled gracefully with warning
+		},
 	}
 
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			natsAPI.handleNodeState("test.subject", []byte(tt.payload))
+			natsAPI.handleNodeState("test.subject", tt.data)
 
 			// Allow some time for async operations
 			time.Sleep(50 * time.Millisecond)
@@ -789,7 +761,7 @@ func TestNatsHandleJobEvent(t *testing.T) {
 	}{
 		{
 			name:        "valid influx line protocol",
-			data:        []byte(`job,function=start_job event="{\"jobId\":4001,\"user\":\"testuser\",\"project\":\"testproj\",\"cluster\":\"testcluster\",\"partition\":\"main\",\"walltime\":3600,\"numNodes\":1,\"numHwthreads\":8,\"numAcc\":0,\"shared\":\"none\",\"monitoringStatus\":1,\"smt\":1,\"resources\":[{\"hostname\":\"host123\",\"hwthreads\":[0,1,2,3]}],\"startTime\":1234567890}"`),
+			data:        []byte(`job,function=start_job event="{\"jobId\":4001,\"user\":\"testuser\",\"project\":\"testproj\",\"cluster\":\"testcluster\",\"partition\":\"main\",\"walltime\":3600,\"numNodes\":1,\"numHwthreads\":8,\"numAcc\":0,\"shared\":\"none\",\"monitoringStatus\":1,\"smt\":1,\"resources\":[{\"hostname\":\"host123\",\"hwthreads\":[0,1,2,3]}],\"startTime\":1234567890}" 1234567890000000000`),
 			expectError: false,
 		},
 		{
@@ -814,6 +786,106 @@ func TestNatsHandleJobEvent(t *testing.T) {
 	}
 }
 
+func TestNatsHandleJobEventEdgeCases(t *testing.T) {
+	natsAPI := setupNatsTest(t)
+	t.Cleanup(cleanupNatsTest)
+
+	tests := []struct {
+		name        string
+		data        []byte
+		expectError bool
+		description string
+	}{
+		{
+			name:        "non-event message (metric data)",
+			data:        []byte(`job,function=start_job value=123.45 1234567890000000000`),
+			expectError: false,
+			description: "Should skip non-event messages gracefully",
+		},
+		{
+			name:        "wrong measurement name",
+			data:        []byte(`wrongmeasurement,function=start_job event="{}" 1234567890000000000`),
+			expectError: false,
+			description: "Should warn about unexpected measurement but not fail",
+		},
+		{
+			name:        "missing event field",
+			data:        []byte(`job,function=start_job other_field="value" 1234567890000000000`),
+			expectError: true,
+			description: "Should error when event field is missing",
+		},
+		{
+			name:        "multiple measurements in one message",
+			data:        []byte("job,function=start_job event=\"{}\" 1234567890000000000\njob,function=stop_job event=\"{}\" 1234567890000000000"),
+			expectError: false,
+			description: "Should process multiple lines",
+		},
+		{
+			name:        "escaped quotes in JSON payload",
+			data:        []byte(`job,function=start_job event="{\"jobId\":6001,\"user\":\"test\\\"user\",\"cluster\":\"test\"}" 1234567890000000000`),
+			expectError: true,
+			description: "Should handle escaped quotes (though JSON parsing may fail)",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			natsAPI.handleJobEvent("test.subject", tt.data)
+			time.Sleep(50 * time.Millisecond)
+		})
+	}
+}
+
+func TestNatsHandleNodeStateEdgeCases(t *testing.T) {
+	natsAPI := setupNatsTest(t)
+	t.Cleanup(cleanupNatsTest)
+
+	tests := []struct {
+		name        string
+		data        []byte
+		expectError bool
+		description string
+	}{
+		{
+			name:        "missing cluster field in JSON",
+			data:        []byte(`nodestate event="{\"nodes\":[]}" 1234567890000000000`),
+			expectError: true,
+			description: "Should fail when cluster is missing",
+		},
+		{
+			name:        "malformed JSON with unescaped quotes",
+			data:        []byte(`nodestate event="{\"cluster\":\"test"cluster\",\"nodes\":[]}" 1234567890000000000`),
+			expectError: true,
+			description: "Should fail on malformed JSON",
+		},
+		{
+			name:        "unicode characters in hostname",
+			data:        []byte(`nodestate event="{\"cluster\":\"testcluster\",\"nodes\":[{\"hostname\":\"host-ñ123\",\"states\":[\"idle\"],\"cpusAllocated\":0,\"memoryAllocated\":0,\"gpusAllocated\":0,\"jobsRunning\":0}]}" 1234567890000000000`),
+			expectError: false,
+			description: "Should handle unicode characters",
+		},
+		{
+			name:        "very large node count",
+			data:        []byte(`nodestate event="{\"cluster\":\"testcluster\",\"nodes\":[{\"hostname\":\"node1\",\"states\":[\"idle\"],\"cpusAllocated\":0,\"memoryAllocated\":0,\"gpusAllocated\":0,\"jobsRunning\":0},{\"hostname\":\"node2\",\"states\":[\"idle\"],\"cpusAllocated\":0,\"memoryAllocated\":0,\"gpusAllocated\":0,\"jobsRunning\":0},{\"hostname\":\"node3\",\"states\":[\"idle\"],\"cpusAllocated\":0,\"memoryAllocated\":0,\"gpusAllocated\":0,\"jobsRunning\":0}]}" 1234567890000000000`),
+			expectError: false,
+			description: "Should handle multiple nodes efficiently",
+		},
+		{
+			name:        "timestamp in past",
+			data:        []byte(`nodestate event="{\"cluster\":\"testcluster\",\"nodes\":[]}" 1000000000000000000`),
+			expectError: false,
+			description: "Should accept any valid timestamp",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			natsAPI.handleNodeState("test.subject", tt.data)
+			time.Sleep(50 * time.Millisecond)
+		})
+	}
+}
+
 func TestNatsHandleStartJobDuplicatePrevention(t *testing.T) {
 	natsAPI := setupNatsTest(t)
 	t.Cleanup(cleanupNatsTest)

From 19402d30af2c984e335099933206ecb7c8b6e8bc Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 10:09:19 +0100
Subject: [PATCH 36/59] Review and improve error messages and doc comments

---
 internal/repository/job.go | 149 +++++++++++++++++++++++--------------
 1 file changed, 94 insertions(+), 55 deletions(-)

diff --git a/internal/repository/job.go b/internal/repository/job.go
index 78e1f3fe..293c28d4 100644
--- a/internal/repository/job.go
+++ b/internal/repository/job.go
@@ -156,27 +156,41 @@ func scanJob(row interface{ Scan(...any) error }) (*schema.Job, error) {
 	return job, nil
 }
 
+// Optimize performs database optimization by running VACUUM command.
+// This reclaims unused space and defragments the database file.
+// Should be run periodically during maintenance windows.
 func (r *JobRepository) Optimize() error {
 	if _, err := r.DB.Exec(`VACUUM`); err != nil {
-		return err
+		cclog.Errorf("Error while executing VACUUM: %v", err)
+		return fmt.Errorf("failed to optimize database: %w", err)
 	}
 	return nil
 }
 
+// Flush removes all data from job-related tables (jobtag, tag, job).
+// WARNING: This is a destructive operation that deletes all job data.
+// Use with extreme caution, typically only for testing or complete resets.
 func (r *JobRepository) Flush() error {
 	if _, err := r.DB.Exec(`DELETE FROM jobtag`); err != nil {
-		return err
+		cclog.Errorf("Error while deleting from jobtag table: %v", err)
+		return fmt.Errorf("failed to flush jobtag table: %w", err)
 	}
 	if _, err := r.DB.Exec(`DELETE FROM tag`); err != nil {
-		return err
+		cclog.Errorf("Error while deleting from tag table: %v", err)
+		return fmt.Errorf("failed to flush tag table: %w", err)
 	}
 	if _, err := r.DB.Exec(`DELETE FROM job`); err != nil {
-		return err
+		cclog.Errorf("Error while deleting from job table: %v", err)
+		return fmt.Errorf("failed to flush job table: %w", err)
 	}
 	return nil
 }
 
 func (r *JobRepository) FetchMetadata(job *schema.Job) (map[string]string, error) {
+	if job == nil {
+		return nil, fmt.Errorf("job cannot be nil")
+	}
+
 	start := time.Now()
 	cachekey := fmt.Sprintf("metadata:%d", job.ID)
 	if cached := r.cache.Get(cachekey, nil); cached != nil {
@@ -186,8 +200,8 @@ func (r *JobRepository) FetchMetadata(job *schema.Job) (map[string]string, error
 
 	if err := sq.Select("job.meta_data").From("job").Where("job.id = ?", job.ID).
 		RunWith(r.stmtCache).QueryRow().Scan(&job.RawMetaData); err != nil {
-		cclog.Warn("Error while scanning for job metadata")
-		return nil, err
+		cclog.Warnf("Error while scanning for job metadata (ID=%d): %v", job.ID, err)
+		return nil, fmt.Errorf("failed to fetch metadata for job %d: %w", job.ID, err)
 	}
 
 	if len(job.RawMetaData) == 0 {
@@ -195,8 +209,8 @@ func (r *JobRepository) FetchMetadata(job *schema.Job) (map[string]string, error
 	}
 
 	if err := json.Unmarshal(job.RawMetaData, &job.MetaData); err != nil {
-		cclog.Warn("Error while unmarshaling raw metadata json")
-		return nil, err
+		cclog.Warnf("Error while unmarshaling raw metadata json (ID=%d): %v", job.ID, err)
+		return nil, fmt.Errorf("failed to unmarshal metadata for job %d: %w", job.ID, err)
 	}
 
 	r.cache.Put(cachekey, job.MetaData, len(job.RawMetaData), 24*time.Hour)
@@ -205,6 +219,10 @@ func (r *JobRepository) FetchMetadata(job *schema.Job) (map[string]string, error
 }
 
 func (r *JobRepository) UpdateMetadata(job *schema.Job, key, val string) (err error) {
+	if job == nil {
+		return fmt.Errorf("job cannot be nil")
+	}
+
 	cachekey := fmt.Sprintf("metadata:%d", job.ID)
 	r.cache.Del(cachekey)
 	if job.MetaData == nil {
@@ -241,12 +259,16 @@ func (r *JobRepository) UpdateMetadata(job *schema.Job, key, val string) (err er
 }
 
 func (r *JobRepository) FetchFootprint(job *schema.Job) (map[string]float64, error) {
+	if job == nil {
+		return nil, fmt.Errorf("job cannot be nil")
+	}
+
 	start := time.Now()
 
 	if err := sq.Select("job.footprint").From("job").Where("job.id = ?", job.ID).
 		RunWith(r.stmtCache).QueryRow().Scan(&job.RawFootprint); err != nil {
-		cclog.Warn("Error while scanning for job footprint")
-		return nil, err
+		cclog.Warnf("Error while scanning for job footprint (ID=%d): %v", job.ID, err)
+		return nil, fmt.Errorf("failed to fetch footprint for job %d: %w", job.ID, err)
 	}
 
 	if len(job.RawFootprint) == 0 {
@@ -254,8 +276,8 @@ func (r *JobRepository) FetchFootprint(job *schema.Job) (map[string]float64, err
 	}
 
 	if err := json.Unmarshal(job.RawFootprint, &job.Footprint); err != nil {
-		cclog.Warn("Error while unmarshaling raw footprint json")
-		return nil, err
+		cclog.Warnf("Error while unmarshaling raw footprint json (ID=%d): %v", job.ID, err)
+		return nil, fmt.Errorf("failed to unmarshal footprint for job %d: %w", job.ID, err)
 	}
 
 	cclog.Debugf("Timer FetchFootprint %s", time.Since(start))
@@ -263,6 +285,10 @@ func (r *JobRepository) FetchFootprint(job *schema.Job) (map[string]float64, err
 }
 
 func (r *JobRepository) FetchEnergyFootprint(job *schema.Job) (map[string]float64, error) {
+	if job == nil {
+		return nil, fmt.Errorf("job cannot be nil")
+	}
+
 	start := time.Now()
 	cachekey := fmt.Sprintf("energyFootprint:%d", job.ID)
 	if cached := r.cache.Get(cachekey, nil); cached != nil {
@@ -272,8 +298,8 @@ func (r *JobRepository) FetchEnergyFootprint(job *schema.Job) (map[string]float6
 
 	if err := sq.Select("job.energy_footprint").From("job").Where("job.id = ?", job.ID).
 		RunWith(r.stmtCache).QueryRow().Scan(&job.RawEnergyFootprint); err != nil {
-		cclog.Warn("Error while scanning for job energy_footprint")
-		return nil, err
+		cclog.Warnf("Error while scanning for job energy_footprint (ID=%d): %v", job.ID, err)
+		return nil, fmt.Errorf("failed to fetch energy footprint for job %d: %w", job.ID, err)
 	}
 
 	if len(job.RawEnergyFootprint) == 0 {
@@ -281,8 +307,8 @@ func (r *JobRepository) FetchEnergyFootprint(job *schema.Job) (map[string]float6
 	}
 
 	if err := json.Unmarshal(job.RawEnergyFootprint, &job.EnergyFootprint); err != nil {
-		cclog.Warn("Error while unmarshaling raw energy footprint json")
-		return nil, err
+		cclog.Warnf("Error while unmarshaling raw energy footprint json (ID=%d): %v", job.ID, err)
+		return nil, fmt.Errorf("failed to unmarshal energy footprint for job %d: %w", job.ID, err)
 	}
 
 	r.cache.Put(cachekey, job.EnergyFootprint, len(job.EnergyFootprint), 24*time.Hour)
@@ -363,6 +389,10 @@ func (r *JobRepository) DeleteJobByID(id int64) error {
 }
 
 func (r *JobRepository) FindUserOrProjectOrJobname(user *schema.User, searchterm string) (jobid string, username string, project string, jobname string) {
+	if searchterm == "" {
+		return "", "", "", ""
+	}
+
 	if _, err := strconv.Atoi(searchterm); err == nil { // Return empty on successful conversion: parent method will redirect for integer jobId
 		return searchterm, "", "", ""
 	} else { // Has to have letters and logged-in user for other guesses
@@ -394,6 +424,10 @@ var (
 )
 
 func (r *JobRepository) FindColumnValue(user *schema.User, searchterm string, table string, selectColumn string, whereColumn string, isLike bool) (result string, err error) {
+	if user == nil {
+		return "", fmt.Errorf("user cannot be nil")
+	}
+
 	compareStr := " = ?"
 	query := searchterm
 	if isLike {
@@ -404,17 +438,11 @@ func (r *JobRepository) FindColumnValue(user *schema.User, searchterm string, ta
 		theQuery := sq.Select(table+"."+selectColumn).Distinct().From(table).
 			Where(table+"."+whereColumn+compareStr, query)
 
-		// theSql, args, theErr := theQuery.ToSql()
-		// if theErr != nil {
-		// 	cclog.Warn("Error while converting query to sql")
-		// 	return "", err
-		// }
-		// cclog.Debugf("SQL query (FindColumnValue): `%s`, args: %#v", theSql, args)
-
 		err := theQuery.RunWith(r.stmtCache).QueryRow().Scan(&result)
 
 		if err != nil && err != sql.ErrNoRows {
-			return "", err
+			cclog.Warnf("Error while querying FindColumnValue (table=%s, column=%s): %v", table, selectColumn, err)
+			return "", fmt.Errorf("failed to find column value: %w", err)
 		} else if err == nil {
 			return result, nil
 		}
@@ -426,21 +454,26 @@ func (r *JobRepository) FindColumnValue(user *schema.User, searchterm string, ta
 }
 
 func (r *JobRepository) FindColumnValues(user *schema.User, query string, table string, selectColumn string, whereColumn string) (results []string, err error) {
+	if user == nil {
+		return nil, fmt.Errorf("user cannot be nil")
+	}
+
 	emptyResult := make([]string, 0)
 	if user.HasAnyRole([]schema.Role{schema.RoleAdmin, schema.RoleSupport, schema.RoleManager}) {
 		rows, err := sq.Select(table+"."+selectColumn).Distinct().From(table).
 			Where(table+"."+whereColumn+" LIKE ?", fmt.Sprint("%", query, "%")).
 			RunWith(r.stmtCache).Query()
 		if err != nil && err != sql.ErrNoRows {
-			return emptyResult, err
+			cclog.Errorf("Error while querying FindColumnValues (table=%s, column=%s): %v", table, selectColumn, err)
+			return emptyResult, fmt.Errorf("failed to find column values: %w", err)
 		} else if err == nil {
+			defer rows.Close()
 			for rows.Next() {
 				var result string
 				err := rows.Scan(&result)
 				if err != nil {
-					rows.Close()
-					cclog.Warnf("Error while scanning rows: %v", err)
-					return emptyResult, err
+					cclog.Warnf("Error while scanning rows in FindColumnValues: %v", err)
+					return emptyResult, fmt.Errorf("failed to scan column value: %w", err)
 				}
 				results = append(results, result)
 			}
@@ -482,8 +515,8 @@ func (r *JobRepository) AllocatedNodes(cluster string) (map[string]map[string]in
 		Where("job.cluster = ?", cluster).
 		RunWith(r.stmtCache).Query()
 	if err != nil {
-		cclog.Error("Error while running query")
-		return nil, err
+		cclog.Errorf("Error while running AllocatedNodes query for cluster=%s: %v", cluster, err)
+		return nil, fmt.Errorf("failed to query allocated nodes for cluster %s: %w", cluster, err)
 	}
 
 	var raw []byte
@@ -493,12 +526,12 @@ func (r *JobRepository) AllocatedNodes(cluster string) (map[string]map[string]in
 		var resources []*schema.Resource
 		var subcluster string
 		if err := rows.Scan(&raw, &subcluster); err != nil {
-			cclog.Warn("Error while scanning rows")
-			return nil, err
+			cclog.Warnf("Error while scanning rows in AllocatedNodes: %v", err)
+			return nil, fmt.Errorf("failed to scan allocated nodes row: %w", err)
 		}
 		if err := json.Unmarshal(raw, &resources); err != nil {
-			cclog.Warn("Error while unmarshaling raw resources json")
-			return nil, err
+			cclog.Warnf("Error while unmarshaling raw resources json in AllocatedNodes: %v", err)
+			return nil, fmt.Errorf("failed to unmarshal resources in AllocatedNodes: %w", err)
 		}
 
 		hosts, ok := subclusters[subcluster]
@@ -529,14 +562,14 @@ func (r *JobRepository) StopJobsExceedingWalltimeBy(seconds int) error {
 		Where("(? - job.start_time) > (job.walltime + ?)", currentTime, seconds).
 		RunWith(r.DB).Exec()
 	if err != nil {
-		cclog.Warn("Error while stopping jobs exceeding walltime")
-		return err
+		cclog.Warnf("Error while stopping jobs exceeding walltime: %v", err)
+		return fmt.Errorf("failed to stop jobs exceeding walltime: %w", err)
 	}
 
 	rowsAffected, err := res.RowsAffected()
 	if err != nil {
-		cclog.Warn("Error while fetching affected rows after stopping due to exceeded walltime")
-		return err
+		cclog.Warnf("Error while fetching affected rows after stopping due to exceeded walltime: %v", err)
+		return fmt.Errorf("failed to get rows affected count: %w", err)
 	}
 
 	if rowsAffected > 0 {
@@ -552,18 +585,19 @@ func (r *JobRepository) FindJobIdsByTag(tagID int64) ([]int64, error) {
 		Where(sq.Eq{"jobtag.tag_id": tagID}).Distinct()
 	rows, err := query.RunWith(r.stmtCache).Query()
 	if err != nil {
-		cclog.Error("Error while running query")
-		return nil, err
+		cclog.Errorf("Error while running FindJobIdsByTag query for tagID=%d: %v", tagID, err)
+		return nil, fmt.Errorf("failed to find job IDs by tag %d: %w", tagID, err)
 	}
+	defer rows.Close()
+
 	jobIds := make([]int64, 0, 100)
 
 	for rows.Next() {
 		var jobID int64
 
 		if err := rows.Scan(&jobID); err != nil {
-			rows.Close()
-			cclog.Warn("Error while scanning rows")
-			return nil, err
+			cclog.Warnf("Error while scanning rows in FindJobIdsByTag: %v", err)
+			return nil, fmt.Errorf("failed to scan job ID in FindJobIdsByTag: %w", err)
 		}
 
 		jobIds = append(jobIds, jobID)
@@ -581,8 +615,8 @@ func (r *JobRepository) FindRunningJobs(cluster string) ([]*schema.Job, error) {
 
 	rows, err := query.RunWith(r.stmtCache).Query()
 	if err != nil {
-		cclog.Error("Error while running query")
-		return nil, err
+		cclog.Errorf("Error while running FindRunningJobs query for cluster=%s: %v", cluster, err)
+		return nil, fmt.Errorf("failed to find running jobs for cluster %s: %w", cluster, err)
 	}
 	defer rows.Close()
 
@@ -590,8 +624,8 @@ func (r *JobRepository) FindRunningJobs(cluster string) ([]*schema.Job, error) {
 	for rows.Next() {
 		job, err := scanJob(rows)
 		if err != nil {
-			cclog.Warn("Error while scanning rows")
-			return nil, err
+			cclog.Warnf("Error while scanning rows in FindRunningJobs: %v", err)
+			return nil, fmt.Errorf("failed to scan job in FindRunningJobs: %w", err)
 		}
 		jobs = append(jobs, job)
 	}
@@ -607,7 +641,8 @@ func (r *JobRepository) UpdateDuration() error {
 
 	_, err := stmnt.RunWith(r.stmtCache).Exec()
 	if err != nil {
-		return err
+		cclog.Errorf("Error while updating duration for running jobs: %v", err)
+		return fmt.Errorf("failed to update duration for running jobs: %w", err)
 	}
 
 	return nil
@@ -634,8 +669,8 @@ func (r *JobRepository) FindJobsBetween(startTimeBegin int64, startTimeEnd int64
 
 	rows, err := query.RunWith(r.stmtCache).Query()
 	if err != nil {
-		cclog.Error("Error while running query")
-		return nil, err
+		cclog.Errorf("Error while running FindJobsBetween query: %v", err)
+		return nil, fmt.Errorf("failed to find jobs between %d and %d: %w", startTimeBegin, startTimeEnd, err)
 	}
 	defer rows.Close()
 
@@ -643,8 +678,8 @@ func (r *JobRepository) FindJobsBetween(startTimeBegin int64, startTimeEnd int64
 	for rows.Next() {
 		job, err := scanJob(rows)
 		if err != nil {
-			cclog.Warn("Error while scanning rows")
-			return nil, err
+			cclog.Warnf("Error while scanning rows in FindJobsBetween: %v", err)
+			return nil, fmt.Errorf("failed to scan job in FindJobsBetween: %w", err)
 		}
 		jobs = append(jobs, job)
 	}
@@ -662,13 +697,17 @@ func (r *JobRepository) UpdateMonitoringStatus(job int64, monitoringStatus int32
 		Set("monitoring_status", monitoringStatus).
 		Where("job.id = ?", job)
 
-	_, err = stmt.RunWith(r.stmtCache).Exec()
-	return err
+	if _, err = stmt.RunWith(r.stmtCache).Exec(); err != nil {
+		cclog.Errorf("Error while updating monitoring status for job %d: %v", job, err)
+		return fmt.Errorf("failed to update monitoring status for job %d: %w", job, err)
+	}
+	return nil
 }
 
 func (r *JobRepository) Execute(stmt sq.UpdateBuilder) error {
 	if _, err := stmt.RunWith(r.stmtCache).Exec(); err != nil {
-		return err
+		cclog.Errorf("Error while executing statement: %v", err)
+		return fmt.Errorf("failed to execute update statement: %w", err)
 	}
 
 	return nil

From 0ea0270fe17ceca3156a2f563df7987d6ab50063 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 10:37:07 +0100
Subject: [PATCH 37/59] Reintroduce Clusters as string list of cluster names

---
 web/web.go | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/web/web.go b/web/web.go
index 37f1c2b2..6ff01403 100644
--- a/web/web.go
+++ b/web/web.go
@@ -245,6 +245,7 @@ type Page struct {
 	User          schema.User            // Information about the currently logged in user (Full User Info)
 	Roles         map[string]schema.Role // Available roles for frontend render checks
 	Build         Build                  // Latest information about the application
+	Clusters      []string               // List of all cluster names
 	SubClusters   map[string][]string    // Map per cluster of all subClusters for use in the Header
 	FilterPresets map[string]any         // For pages with the Filter component, this can be used to set initial filters.
 	Infos         map[string]any         // For generic use (e.g. username for /monitoring/user/<id>, job id for /monitoring/job/<id>)
@@ -259,9 +260,15 @@ func RenderTemplate(rw http.ResponseWriter, file string, page *Page) {
 		cclog.Errorf("WEB/WEB > template '%s' not found", file)
 	}
 
+	if page.Clusters == nil {
+		page.Clusters = make([]string, 2)
+	}
+
 	if page.SubClusters == nil {
 		page.SubClusters = make(map[string][]string)
 		for _, cluster := range archive.Clusters {
+			page.Clusters = append(page.Clusters, cluster.Name)
+
 			for _, sc := range cluster.SubClusters {
 				page.SubClusters[cluster.Name] = append(page.SubClusters[cluster.Name], sc.Name)
 			}

From c8627a13f40011cd07d43772760c09a73078c0c4 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 11:17:49 +0100
Subject: [PATCH 38/59] Remove obsolete slusters config section

---
 cmd/cc-backend/init.go                 | 28 ++-------------
 configs/config-demo.json               | 47 --------------------------
 configs/config.json                    | 34 ++-----------------
 internal/api/api_test.go               | 35 +++++++------------
 internal/api/nats_test.go              | 11 ------
 internal/importer/importer_test.go     | 32 ++----------------
 internal/repository/node_test.go       | 11 ------
 internal/repository/userConfig_test.go | 10 ------
 8 files changed, 19 insertions(+), 189 deletions(-)

diff --git a/cmd/cc-backend/init.go b/cmd/cc-backend/init.go
index 025396be..e30ae2e1 100644
--- a/cmd/cc-backend/init.go
+++ b/cmd/cc-backend/init.go
@@ -48,7 +48,7 @@ const configString = `
     "emission-constant": 317
   },
   "cron": {
-    "commit-job-worker": "2m",
+    "commit-job-worker": "1m",
     "duration-worker": "5m",
     "footprint-worker": "10m"
   },
@@ -60,31 +60,7 @@ const configString = `
     "jwts": {
       "max-age": "2000h"
     }
-  },
- "clusters": [
-     {
-         "name": "name",
-         "metricDataRepository": {
-             "kind": "cc-metric-store",
-             "url": "http://localhost:8082",
-             "token": ""
-         },
-         "filterRanges": {
-             "numNodes": {
-                 "from": 1,
-                 "to": 64
-             },
-             "duration": {
-                 "from": 0,
-                 "to": 86400
-             },
-             "startTime": {
-                 "from": "2023-01-01T00:00:00Z",
-                 "to": null
-             }
-         }
-     }
- ]
+  }
 }
 `
 
diff --git a/configs/config-demo.json b/configs/config-demo.json
index aa388316..bd492e31 100644
--- a/configs/config-demo.json
+++ b/configs/config-demo.json
@@ -29,52 +29,6 @@
     "username": "root",
     "password": "root"
   },
-  "clusters": [
-    {
-      "name": "fritz",
-      "metricDataRepository": {
-        "kind": "cc-metric-store-internal",
-        "url": "http://localhost:8082",
-        "token": "eyJ0eXAiOiJKV1QiLCJhbGciOiJFZERTQSJ9.eyJ1c2VyIjoiYWRtaW4iLCJyb2xlcyI6WyJST0xFX0FETUlOIiwiUk9MRV9BTkFMWVNUIiwiUk9MRV9VU0VSIl19.d-3_3FZTsadPjDEdsWrrQ7nS0edMAR4zjl-eK7rJU3HziNBfI9PDHDIpJVHTNN5E5SlLGLFXctWyKAkwhXL-Dw"
-      },
-      "filterRanges": {
-        "numNodes": {
-          "from": 1,
-          "to": 64
-        },
-        "duration": {
-          "from": 0,
-          "to": 86400
-        },
-        "startTime": {
-          "from": "2022-01-01T00:00:00Z",
-          "to": null
-        }
-      }
-    },
-    {
-      "name": "alex",
-      "metricDataRepository": {
-        "kind": "cc-metric-store-internal",
-        "url": "http://localhost:8082",
-        "token": "eyJ0eXAiOiJKV1QiLCJhbGciOiJFZERTQSJ9.eyJ1c2VyIjoiYWRtaW4iLCJyb2xlcyI6WyJST0xFX0FETUlOIiwiUk9MRV9BTkFMWVNUIiwiUk9MRV9VU0VSIl19.d-3_3FZTsadPjDEdsWrrQ7nS0edMAR4zjl-eK7rJU3HziNBfI9PDHDIpJVHTNN5E5SlLGLFXctWyKAkwhXL-Dw"
-      },
-      "filterRanges": {
-        "numNodes": {
-          "from": 1,
-          "to": 64
-        },
-        "duration": {
-          "from": 0,
-          "to": 86400
-        },
-        "startTime": {
-          "from": "2022-01-01T00:00:00Z",
-          "to": null
-        }
-      }
-    }
-  ],
   "metric-store": {
     "checkpoints": {
       "file-format": "avro",
@@ -99,4 +53,3 @@
     ]
   }
 }
-
diff --git a/configs/config.json b/configs/config.json
index 41d8ecac..44961c85 100644
--- a/configs/config.json
+++ b/configs/config.json
@@ -11,10 +11,7 @@
     "resampling": {
       "minimumPoints": 600,
       "trigger": 180,
-      "resolutions": [
-        240,
-        60
-      ]
+      "resolutions": [240, 60]
     },
     "apiSubjects": {
       "subjectJobEvent": "cc.job.event",
@@ -22,37 +19,12 @@
     }
   },
   "cron": {
-    "commit-job-worker": "2m",
+    "commit-job-worker": "1m",
     "duration-worker": "5m",
     "footprint-worker": "10m"
   },
   "archive": {
     "kind": "file",
     "path": "./var/job-archive"
-  },
-  "clusters": [
-    {
-      "name": "test",
-      "metricDataRepository": {
-        "kind": "cc-metric-store",
-        "url": "http://localhost:8082",
-        "token": "eyJhbGciOiJF-E-pQBQ"
-      },
-      "filterRanges": {
-        "numNodes": {
-          "from": 1,
-          "to": 64
-        },
-        "duration": {
-          "from": 0,
-          "to": 86400
-        },
-        "startTime": {
-          "from": "2022-01-01T00:00:00Z",
-          "to": null
-        }
-      }
-    }
-  ]
+  }
 }
-
diff --git a/internal/api/api_test.go b/internal/api/api_test.go
index 7aa935ff..025983c1 100644
--- a/internal/api/api_test.go
+++ b/internal/api/api_test.go
@@ -39,33 +39,22 @@ func setup(t *testing.T) *api.RestAPI {
 	repository.ResetConnection()
 
 	const testconfig = `{
-		"main": {
-	"addr":            "0.0.0.0:8080",
-	"validate": false,
-  "apiAllowedIPs": [
-    "*"
-  ]
-	},
+	"main": {
+	   "addr":            "0.0.0.0:8080",
+	   "validate": false,
+     "apiAllowedIPs": [
+       "*"
+      ]
+  },
 	"archive": {
-		"kind": "file",
-		"path": "./var/job-archive"
+		 "kind": "file",
+		 "path": "./var/job-archive"
 	},
 	"auth": {
-  "jwts": {
-      "max-age": "2m"
+     "jwts": {
+     "max-age": "2m"
+  }
   }
-	},
-	"clusters": [
-	{
-	   "name": "testcluster",
-	   "metricDataRepository": {"kind": "test", "url": "bla:8081"},
-	   "filterRanges": {
-		"numNodes": { "from": 1, "to": 64 },
-		"duration": { "from": 0, "to": 86400 },
-		"startTime": { "from": "2022-01-01T00:00:00Z", "to": null }
-	   }
-	}
-	]
 }`
 	const testclusterJSON = `{
         "name": "testcluster",
diff --git a/internal/api/nats_test.go b/internal/api/nats_test.go
index 4b1431cb..c6a9bcd9 100644
--- a/internal/api/nats_test.go
+++ b/internal/api/nats_test.go
@@ -48,18 +48,7 @@ func setupNatsTest(t *testing.T) *NatsAPI {
   "jwts": {
       "max-age": "2m"
   }
-	},
-	"clusters": [
-	{
-	   "name": "testcluster",
-	   "metricDataRepository": {"kind": "test", "url": "bla:8081"},
-	   "filterRanges": {
-		"numNodes": { "from": 1, "to": 64 },
-		"duration": { "from": 0, "to": 86400 },
-		"startTime": { "from": "2022-01-01T00:00:00Z", "to": null }
-	   }
 	}
-	]
 }`
 	const testclusterJSON = `{
         "name": "testcluster",
diff --git a/internal/importer/importer_test.go b/internal/importer/importer_test.go
index 2d00fc84..ebc500b7 100644
--- a/internal/importer/importer_test.go
+++ b/internal/importer/importer_test.go
@@ -56,36 +56,8 @@ func setup(t *testing.T) *repository.JobRepository {
 	"archive": {
 		"kind": "file",
 		"path": "./var/job-archive"
-	},
-	"clusters": [
-	{
-	   "name": "testcluster",
-	   "metricDataRepository": {"kind": "test", "url": "bla:8081"},
-	   "filterRanges": {
-		"numNodes": { "from": 1, "to": 64 },
-		"duration": { "from": 0, "to": 86400 },
-		"startTime": { "from": "2022-01-01T00:00:00Z", "to": null }
-	   }
-	},
-    {
-	   "name": "fritz",
-	   "metricDataRepository": {"kind": "test", "url": "bla:8081"},
-	   "filterRanges": {
-		"numNodes": { "from": 1, "to": 944 },
-		"duration": { "from": 0, "to": 86400 },
-		"startTime": { "from": "2022-01-01T00:00:00Z", "to": null }
-	   }
-	},
-    {
-		"name": "taurus",
-		"metricDataRepository": {"kind": "test", "url": "bla:8081"},
-		 "filterRanges": {
-		   "numNodes": { "from": 1, "to": 4000 },
-		   "duration": { "from": 0, "to": 604800 },
-		   "startTime": { "from": "2010-01-01T00:00:00Z", "to": null }
-		 }
-	 }
-	]}`
+	}
+	}`
 
 	cclog.Init("info", true)
 	tmpdir := t.TempDir()
diff --git a/internal/repository/node_test.go b/internal/repository/node_test.go
index fd935b53..990de924 100644
--- a/internal/repository/node_test.go
+++ b/internal/repository/node_test.go
@@ -38,18 +38,7 @@ func nodeTestSetup(t *testing.T) {
   "jwts": {
       "max-age": "2m"
   }
-	},
-	"clusters": [
-	{
-	   "name": "testcluster",
-	   "metricDataRepository": {"kind": "test", "url": "bla:8081"},
-	   "filterRanges": {
-		"numNodes": { "from": 1, "to": 64 },
-		"duration": { "from": 0, "to": 86400 },
-		"startTime": { "from": "2022-01-01T00:00:00Z", "to": null }
-	   }
 	}
-	]
 }`
 	const testclusterJSON = `{
         "name": "testcluster",
diff --git a/internal/repository/userConfig_test.go b/internal/repository/userConfig_test.go
index ae3adaf2..f66fccfb 100644
--- a/internal/repository/userConfig_test.go
+++ b/internal/repository/userConfig_test.go
@@ -27,17 +27,7 @@ func setupUserTest(t *testing.T) *UserCfgRepo {
 	"archive": {
 		"kind": "file",
 		"path": "./var/job-archive"
-	},
-	"clusters": [
-	{
-	   "name": "testcluster",
-	   "metricDataRepository": {"kind": "test", "url": "bla:8081"},
-	   "filterRanges": {
-		"numNodes": { "from": 1, "to": 64 },
-		"duration": { "from": 0, "to": 86400 },
-		"startTime": { "from": "2022-01-01T00:00:00Z", "to": null }
 	}
-	}]
 }`
 
 	cclog.Init("info", true)

From 4cb8d648cbb5bd40e40462d6f0d2d4d8fa78178c Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Wed, 14 Jan 2026 11:25:40 +0100
Subject: [PATCH 39/59] adapt frontend to backend config changes, clarify
 variable names

---
 web/frontend/src/Config.root.svelte           |  6 +--
 web/frontend/src/Header.svelte                | 36 +++++++--------
 web/frontend/src/config.entrypoint.js         |  2 +-
 web/frontend/src/config/AdminSettings.svelte  |  6 +--
 web/frontend/src/config/admin/Options.svelte  | 12 ++---
 .../src/generic/filters/Resources.svelte      | 20 +--------
 web/frontend/src/header.entrypoint.js         |  4 +-
 web/frontend/src/header/NavbarLinks.svelte    | 44 +++++++++----------
 web/templates/base.tmpl                       |  4 +-
 9 files changed, 58 insertions(+), 76 deletions(-)

diff --git a/web/frontend/src/Config.root.svelte b/web/frontend/src/Config.root.svelte
index 171b2a08..0e1daec3 100644
--- a/web/frontend/src/Config.root.svelte
+++ b/web/frontend/src/Config.root.svelte
@@ -7,7 +7,7 @@
   - `isApi Bool!`: Is currently logged in user api authority
   - `username String!`: Empty string if auth. is disabled, otherwise the username as string
   - `ncontent String!`: The currently displayed message on the homescreen
-  - `clusters [String]`: The available clusternames
+  - `clusterNames [String]`: The available clusternames
 -->
 
 <script>
@@ -23,7 +23,7 @@
     isApi,
     username,
     ncontent,
-    clusters
+    clusterNames
   } = $props();
 </script>
 
@@ -32,7 +32,7 @@
     <CardHeader>
       <CardTitle class="mb-1">Admin Options</CardTitle>
     </CardHeader>
-    <AdminSettings {ncontent} {clusters}/>
+    <AdminSettings {ncontent} {clusterNames}/>
   </Card>
 {/if}
 
diff --git a/web/frontend/src/Header.svelte b/web/frontend/src/Header.svelte
index f7ceac2e..ea818c62 100644
--- a/web/frontend/src/Header.svelte
+++ b/web/frontend/src/Header.svelte
@@ -4,8 +4,8 @@
   Properties:
   - `username String`: Empty string if auth. is disabled, otherwise the username as string
   - `authlevel Number`: The current users authentication level
-  - `clusters [String]`: List of cluster names
-  - `subClusters [String]`: List of subCluster names
+  - `clusterNames [String]`: List of cluster names
+  - `subclusterMap map[String][]string`: Map of subclusters by cluster names
   - `roles [Number]`: Enum containing available roles
 -->
 
@@ -28,8 +28,8 @@
   let { 
     username,
     authlevel,
-    clusters,
-    subClusters,
+    clusterNames,
+    subclusterMap,
     roles
   } = $props();
 
@@ -152,15 +152,15 @@
     <Nav navbar>
       {#if showMax || showBrg}
         <NavbarLinks
-          {clusters}
-          {subClusters}
+          {clusterNames}
+          {subclusterMap}
           links={views.filter((item) => item.requiredRole <= authlevel)}
         />
 
       {:else if showMid}
         <NavbarLinks
-          {clusters}
-          {subClusters}
+          {clusterNames}
+          {subclusterMap}
           links={views.filter(
             (item) => item.requiredRole <= authlevel && item.menu != "Info",
           )}
@@ -173,8 +173,8 @@
             </DropdownToggle>
             <DropdownMenu class="dropdown-menu-lg-end">
               <NavbarLinks
-                {clusters}
-                {subClusters}
+                {clusterNames}
+                {subclusterMap}
                 direction="right"
                 links={views.filter(
                   (item) =>
@@ -187,8 +187,8 @@
 
       {:else if showSml}
         <NavbarLinks
-          {clusters}
-          {subClusters}
+          {clusterNames}
+          {subclusterMap}
           links={views.filter(
             (item) => item.requiredRole <= authlevel && item.menu == "none",
           )}
@@ -200,8 +200,8 @@
             </DropdownToggle>
             <DropdownMenu class="dropdown-menu-lg-end">
               <NavbarLinks
-                {clusters}
-                {subClusters}
+                {clusterNames}
+                {subclusterMap}
                 direction="right"
                 links={views.filter(
                   (item) => item.requiredRole <= authlevel && item.menu == 'Jobs',
@@ -217,8 +217,8 @@
             </DropdownToggle>
             <DropdownMenu class="dropdown-menu-lg-end">
               <NavbarLinks
-                {clusters}
-                {subClusters}
+                {clustersNames}
+                {subclusterMap}
                 direction="right"
                 links={views.filter(
                   (item) => item.requiredRole <= authlevel && item.menu == 'Groups',
@@ -234,8 +234,8 @@
             </DropdownToggle>
             <DropdownMenu class="dropdown-menu-lg-end">
               <NavbarLinks
-                {clusters}
-                {subClusters}
+                {clusterNames}
+                {subclusterMap}
                 direction="right"
                 links={views.filter(
                   (item) => item.requiredRole <= authlevel && item.menu == 'Info',
diff --git a/web/frontend/src/config.entrypoint.js b/web/frontend/src/config.entrypoint.js
index 5d11eedd..a5878b86 100644
--- a/web/frontend/src/config.entrypoint.js
+++ b/web/frontend/src/config.entrypoint.js
@@ -10,7 +10,7 @@ mount(Config, {
         isApi: isApi,
         username: username,
         ncontent: ncontent,
-        clusters: hClusters.map((c) => c.name) // Defined in Header Template
+        clusterNames: hClusterNames
     },
     context: new Map([
             ['cc-config', clusterCockpitConfig],
diff --git a/web/frontend/src/config/AdminSettings.svelte b/web/frontend/src/config/AdminSettings.svelte
index 79072e30..46958963 100644
--- a/web/frontend/src/config/AdminSettings.svelte
+++ b/web/frontend/src/config/AdminSettings.svelte
@@ -3,7 +3,7 @@
 
   Properties:
   - `ncontent String`: The homepage notice content
-  - `clusters [String]`: The available clusternames
+  - `clusterNames [String]`: The available clusternames
 -->
 
 <script>
@@ -19,7 +19,7 @@
   /* Svelte 5 Props */
   let {
     ncontent,
-    clusters
+    clusterNames
   } = $props();
 
   /* Const Init*/
@@ -68,6 +68,6 @@
   <Col>
     <EditProject reloadUser={() => getUserList()} />
   </Col>
-  <Options config={ccconfig} {clusters}/>
+  <Options config={ccconfig} {clusterNames}/>
   <NoticeEdit {ncontent}/>
 </Row>
diff --git a/web/frontend/src/config/admin/Options.svelte b/web/frontend/src/config/admin/Options.svelte
index d61d2202..ea6809f3 100644
--- a/web/frontend/src/config/admin/Options.svelte
+++ b/web/frontend/src/config/admin/Options.svelte
@@ -2,7 +2,7 @@
   @component Admin option select card
 
     Properties:
-  - `clusters [String]`: The available clusternames
+  - `clusterNames [String]`: The available clusternames
 -->
 
 <script>
@@ -11,7 +11,7 @@
 
   /* Svelte 5 Props */
   let {
-    clusters,
+    clusterNames,
   } = $props();
 
   /*Const Init */
@@ -52,17 +52,17 @@
   </Card>
 </Col>
 
-{#if clusters?.length > 0}
+{#if clusterNames?.length > 0}
   <Col> 
     <Card class="h-100">
       <CardBody>
         <CardTitle class="mb-3">Public Dashboard Links</CardTitle>
         <Row>
-        {#each clusters as cluster}
+        {#each clusterNames as cn}
           <Col>
-            <Button color="info" class="mb-2 mb-xl-0" href={`/monitoring/dashboard/${cluster}`} target="_blank">
+            <Button color="info" class="mb-2 mb-xl-0" href={`/monitoring/dashboard/${cn}`} target="_blank">
               <Icon name="clipboard-pulse" class="mr-2"/>
-              {cluster.charAt(0).toUpperCase() + cluster.slice(1)} Public Dashboard
+              {cn.charAt(0).toUpperCase() + cn.slice(1)} Public Dashboard
             </Button>
           </Col>
         {/each}
diff --git a/web/frontend/src/generic/filters/Resources.svelte b/web/frontend/src/generic/filters/Resources.svelte
index 340998f9..49a28f8c 100644
--- a/web/frontend/src/generic/filters/Resources.svelte
+++ b/web/frontend/src/generic/filters/Resources.svelte
@@ -76,7 +76,7 @@
   /* State Init*/
   // Counts
   let minNumNodes = $state(1);
-  let maxNumNodes = $state(0);
+  let maxNumNodes = $state(128);
   let maxNumHWThreads = $state(0);
   let maxNumAccelerators = $state(0);
   // Pending
@@ -107,24 +107,6 @@
   /* Reactive Effects | Svelte 5 onMount */
   $effect(() => {
     if ($initialized) {
-      // 'hClusters' defined in templates/base.tmpl
-      if (activeCluster != null) {
-        const { filterRanges } = hClusters.find((c) => c.name == activeCluster);
-        minNumNodes = filterRanges.numNodes.from;
-        maxNumNodes = filterRanges.numNodes.to;
-      } else if (clusters.length > 0) {
-        for (let hc of hClusters) {
-          const { filterRanges } = hc;
-          minNumNodes = Math.min(minNumNodes, filterRanges.numNodes.from);
-          maxNumNodes = Math.max(maxNumNodes, filterRanges.numNodes.to);
-        };
-      };
-    };
-  });
-  
-  $effect(() => {
-    if ($initialized) {
-      // 'hClusters' defined in templates/base.tmpl
       if (activeCluster != null) {
         const { subClusters } = clusters.find((c) => c.name == activeCluster);
         maxNumAccelerators = findMaxNumAccels([{ subClusters }]);
diff --git a/web/frontend/src/header.entrypoint.js b/web/frontend/src/header.entrypoint.js
index 37fe6f84..5e6e0bf9 100644
--- a/web/frontend/src/header.entrypoint.js
+++ b/web/frontend/src/header.entrypoint.js
@@ -9,8 +9,8 @@ if (headerDomTarget != null) {
         props: {
             username: hUsername, 
             authlevel: hAuthlevel,
-            clusters: hClusters, 
-            subClusters: hSubClusters,
+            clusterNames: hClusterNames, 
+            subclusterMap: hSubclusterMap,
             roles: hRoles,
         },
     });
diff --git a/web/frontend/src/header/NavbarLinks.svelte b/web/frontend/src/header/NavbarLinks.svelte
index 04fec0ea..a607c8a4 100644
--- a/web/frontend/src/header/NavbarLinks.svelte
+++ b/web/frontend/src/header/NavbarLinks.svelte
@@ -2,8 +2,8 @@
   @component Navbar component; renders in app navigation links as received from upstream
 
   Properties:
-  - `clusters [String]`: List of cluster names
-  - `subClusters map[String][]string`: Map of subclusters by cluster names
+  - `clusterNames [String]`: List of cluster names
+  - `subclusterMap map[String][]string`: Map of subclusters by cluster names
   - `links [Object]`: Pre-filtered link objects based on user auth
   - `direction String?`: The direcion of the drop-down menue [default: down]
 -->
@@ -20,8 +20,8 @@
 
   /* Svelte 5 Props */
   let {
-    clusters,
-    subClusters,
+    clusterNames,
+    subclusterMap,
     links,
     direction = "down"
   } = $props();
@@ -36,25 +36,25 @@
           {item.title}
         </DropdownToggle>
         <DropdownMenu class="dropdown-menu-lg-end">
-          {#each clusters as cluster}
+          {#each clusterNames as cn}
             <Dropdown nav direction="right">
               <DropdownToggle nav caret class="dropdown-item py-1 px-2">
-                {cluster.name}
+                {cn}
               </DropdownToggle>
               <DropdownMenu>
                 <DropdownItem class="py-1 px-2"
-                  href={item.href + cluster.name}
+                  href={item.href + cn}
                 >
                   Node Overview
                 </DropdownItem>
                 <DropdownItem class="py-1 px-2"
-                  href={item.href + 'list/' + cluster.name}
+                  href={`${item.href}list/${cn}`}
                 >
                   Node List
                 </DropdownItem>
-                {#each subClusters[cluster.name] as subCluster}
+                {#each subclusterMap[cn] as scn}
                   <DropdownItem class="py-1 px-2"
-                    href={item.href + 'list/' + cluster.name + '/' + subCluster}
+                    href={`${item.href}list/${cn}/${scn}`}
                   >
                   {subCluster} Node List
                   </DropdownItem>
@@ -71,19 +71,19 @@
           {item.title}
         </DropdownToggle>
         <DropdownMenu class="dropdown-menu-lg-end">
-          {#each clusters as cluster}
+          {#each clusterNames as cn}
             <Dropdown nav direction="right">
               <DropdownToggle nav caret class="dropdown-item py-1 px-2">
-                {cluster.name}
+                {cn}
               </DropdownToggle>
               <DropdownMenu>
                 <DropdownItem class="py-1 px-2"
-                  href={item.href + cluster.name}
+                  href={item.href + cn}
                 >
                   Status Dashboard
                 </DropdownItem>
                 <DropdownItem class="py-1 px-2"
-                  href={item.href + 'detail/' + cluster.name}
+                  href={`${item.href}detail/${cn}`}
                 >
                   Status Details
                 </DropdownItem>
@@ -105,19 +105,19 @@
             All Clusters
           </DropdownItem>
           <DropdownItem divider />
-          {#each clusters as cluster}
+          {#each clusterNames as cn}
             <Dropdown nav direction="right">
               <DropdownToggle nav caret class="dropdown-item py-1 px-2">
-                {cluster.name}
+                {cn}
               </DropdownToggle>
               <DropdownMenu>
                 <DropdownItem class="py-1 px-2"
-                  href={item.href + '?cluster=' + cluster.name}
+                  href={`${item.href}?cluster=${cn}`}
                 >
                   All Jobs
                 </DropdownItem>
                 <DropdownItem class="py-1 px-2"
-                  href={item.href + '?cluster=' + cluster.name + '&state=running'}
+                  href={`${item.href}?cluster=${cn}&state=running`}
                 >
                   Running Jobs
                 </DropdownItem>
@@ -138,12 +138,12 @@
         {item.title}
       </DropdownToggle>
       <DropdownMenu class="dropdown-menu-lg-end">
-        {#each clusters as cluster}
+        {#each clusterNames as cn}
           <DropdownItem
-            href={item.href + cluster.name}
-            active={window.location.pathname == item.href + cluster.name}
+            href={item.href + cn}
+            active={window.location.pathname == item.href + cn}
           >
-            {cluster.name}
+            {cn}
           </DropdownItem>
         {/each}
       </DropdownMenu>
diff --git a/web/templates/base.tmpl b/web/templates/base.tmpl
index a1bd4134..fd94668c 100644
--- a/web/templates/base.tmpl
+++ b/web/templates/base.tmpl
@@ -17,8 +17,8 @@
             // Used for header.entrypoint.js mount and filters/Resources.svelte
             const hUsername = {{ .User.Username }};
             const hAuthlevel = {{ .User.GetAuthLevel }};
-            const hClusters = {{ .Clusters }};
-            const hSubClusters = {{ .SubClusters }};
+            const hClusterNames = {{ .Clusters }};
+            const hSubclusterMap = {{ .SubClusters }};
             const hRoles = {{ .Roles }};
         </script>
     </head>

From 77b7548ef3fcb69f679c462c5ddb701cbf81682c Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Wed, 14 Jan 2026 13:00:36 +0100
Subject: [PATCH 40/59] fix wrong varname

---
 web/frontend/src/header/NavbarLinks.svelte | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/web/frontend/src/header/NavbarLinks.svelte b/web/frontend/src/header/NavbarLinks.svelte
index a607c8a4..ad0eb77e 100644
--- a/web/frontend/src/header/NavbarLinks.svelte
+++ b/web/frontend/src/header/NavbarLinks.svelte
@@ -56,7 +56,7 @@
                   <DropdownItem class="py-1 px-2"
                     href={`${item.href}list/${cn}/${scn}`}
                   >
-                  {subCluster} Node List
+                  {scn} Node List
                   </DropdownItem>
                 {/each}
               </DropdownMenu>

From 3276ed7785a19709b866745551a220cc7808bbb6 Mon Sep 17 00:00:00 2001
From: Aditya Ujeniya <adityauj@gmail.com>
Date: Wed, 14 Jan 2026 14:56:36 +0100
Subject: [PATCH 41/59] Half-baked commit for new dynamic retention logic

---
 cmd/cc-backend/init.go              |   2 +-
 configs/config-demo.json            |   2 +-
 internal/metricstore/level.go       |  23 +++++++
 internal/metricstore/metricstore.go | 102 +++++++++++++++++++++++++++-
 internal/repository/job.go          |   2 +-
 web/frontend/package-lock.json      |   5 --
 6 files changed, 126 insertions(+), 10 deletions(-)

diff --git a/cmd/cc-backend/init.go b/cmd/cc-backend/init.go
index e30ae2e1..19c8dd29 100644
--- a/cmd/cc-backend/init.go
+++ b/cmd/cc-backend/init.go
@@ -36,7 +36,7 @@ const configString = `
     "short-running-jobs-duration": 300,
     "resampling": {
       "minimumPoints": 600,
-      "trigger": 180,
+      "trigger": 300,
       "resolutions": [
         240,
         60
diff --git a/configs/config-demo.json b/configs/config-demo.json
index bd492e31..e512c9de 100644
--- a/configs/config-demo.json
+++ b/configs/config-demo.json
@@ -4,7 +4,7 @@
     "short-running-jobs-duration": 300,
     "resampling": {
       "minimumPoints": 600,
-      "trigger": 180,
+      "trigger": 300,
       "resolutions": [240, 60]
     },
     "apiAllowedIPs": ["*"],
diff --git a/internal/metricstore/level.go b/internal/metricstore/level.go
index d46f893a..87aeefc9 100644
--- a/internal/metricstore/level.go
+++ b/internal/metricstore/level.go
@@ -72,6 +72,29 @@ func (l *Level) findLevelOrCreate(selector []string, nMetrics int) *Level {
 	return child.findLevelOrCreate(selector[1:], nMetrics)
 }
 
+func (l *Level) collectPaths(currentDepth, targetDepth int, currentPath []string, results *[][]string) {
+	l.lock.RLock()
+	defer l.lock.RUnlock()
+
+	for key, child := range l.children {
+		if child == nil {
+			continue
+		}
+
+		// We explicitly make a new slice and copy data to avoid sharing underlying arrays between siblings
+		newPath := make([]string, len(currentPath))
+		copy(newPath, currentPath)
+		newPath = append(newPath, key)
+
+		// Check depth, and just return if depth reached
+		if currentDepth+1 == targetDepth {
+			*results = append(*results, newPath)
+		} else {
+			child.collectPaths(currentDepth+1, targetDepth, newPath, results)
+		}
+	}
+}
+
 func (l *Level) free(t int64) (int, error) {
 	l.lock.Lock()
 	defer l.lock.Unlock()
diff --git a/internal/metricstore/metricstore.go b/internal/metricstore/metricstore.go
index ac8948ae..e35b4d58 100644
--- a/internal/metricstore/metricstore.go
+++ b/internal/metricstore/metricstore.go
@@ -235,8 +235,9 @@ func Retention(wg *sync.WaitGroup, ctx context.Context) {
 			case <-ticker.C:
 				t := time.Now().Add(-d)
 				cclog.Infof("[METRICSTORE]> start freeing buffers (older than %s)...\n", t.Format(time.RFC3339))
-				freed, err := ms.Free(nil, t.Unix())
-						if err != nil {
+
+				freed, err := Free(ms, t)
+				if err != nil {
 					cclog.Errorf("[METRICSTORE]> freeing up buffers failed: %s\n", err.Error())
 				} else {
 					cclog.Infof("[METRICSTORE]> done: %d buffers freed\n", freed)
@@ -246,6 +247,103 @@ func Retention(wg *sync.WaitGroup, ctx context.Context) {
 	}()
 }
 
+func Free(ms *MemoryStore, t time.Time) (int, error) {
+	// jobRepo := repository.GetJobRepository()
+	// excludeSelectors, err := jobRepo.GetUsedNodes(t.Unix())
+	// if err != nil {
+	// 	return 0, err
+	// }
+
+	excludeSelectors := make(map[string][]string, 0)
+
+	// excludeSelectors := map[string][]string{
+	// 	"alex":  {"a0122", "a0123", "a0225"},
+	// 	"fritz": {"f0201", "f0202"},
+	// }
+
+	switch lenMap := len(excludeSelectors); lenMap {
+
+	// If the length of the map returned by GetUsedNodes() is 0,
+	// then use default Free method with nil selector
+	case 0:
+		return ms.Free(nil, t.Unix())
+
+	// Else formulate selectors, exclude those from the map
+	// and free the rest of the selectors
+	default:
+		selectors := GetSelectors(ms, excludeSelectors)
+		return FreeSelected(ms, selectors, t)
+	}
+}
+
+// A function to free specific selectors. Used when we want to retain some specific nodes
+// beyond the retention time.
+func FreeSelected(ms *MemoryStore, selectors [][]string, t time.Time) (int, error) {
+	freed := 0
+
+	for _, selector := range selectors {
+
+		freedBuffers, err := ms.Free(selector, t.Unix())
+		if err != nil {
+			cclog.Errorf("error while freeing selected buffers: %#v", err)
+		}
+		freed += freedBuffers
+
+	}
+
+	return freed, nil
+}
+
+// This function will populate all the second last levels - meaning nodes
+// From that we can exclude the specific selectosr/node we want to retain.
+func GetSelectors(ms *MemoryStore, excludeSelectors map[string][]string) [][]string {
+	allSelectors := ms.GetPaths(2)
+
+	filteredSelectors := make([][]string, 0, len(allSelectors))
+
+	for _, path := range allSelectors {
+		if len(path) < 2 {
+			continue
+		}
+
+		key := path[0]   // The "Key" (Level 1)
+		value := path[1] // The "Value" (Level 2)
+
+		exclude := false
+
+		// Check if the key exists in our exclusion map
+		if excludedValues, exists := excludeSelectors[key]; exists {
+			// The key exists, now check if the specific value is in the exclusion list
+			for _, ev := range excludedValues {
+				if ev == value {
+					exclude = true
+					break
+				}
+			}
+		}
+
+		if !exclude {
+			filteredSelectors = append(filteredSelectors, path)
+		}
+	}
+
+	// fmt.Printf("All selectors: %#v\n\n", allSelectors)
+	// fmt.Printf("filteredSelectors: %#v\n\n", filteredSelectors)
+
+	return filteredSelectors
+}
+
+// GetPaths returns a list of lists (paths) to the specified depth.
+func (ms *MemoryStore) GetPaths(targetDepth int) [][]string {
+	var results [][]string
+
+	// Start recursion. Initial path is empty.
+	// We treat Root as depth 0.
+	ms.root.collectPaths(0, targetDepth, []string{}, &results)
+
+	return results
+}
+
 // Write all values in `metrics` to the level specified by `selector` for time `ts`.
 // Look at `findLevelOrCreate` for how selectors work.
 func (m *MemoryStore) Write(selector []string, ts int64, metrics []Metric) error {
diff --git a/internal/repository/job.go b/internal/repository/job.go
index 293c28d4..b1e92424 100644
--- a/internal/repository/job.go
+++ b/internal/repository/job.go
@@ -821,7 +821,7 @@ func (r *JobRepository) UpdateFootprint(
 // relevant jobs. Returns an error if the database query fails or row iteration
 // encounters errors. Individual row parsing errors are logged but don't fail
 // the entire operation.
-func (r *JobRepository) GetUsedNodes(ts uint64) (map[string][]string, error) {
+func (r *JobRepository) GetUsedNodes(ts int64) (map[string][]string, error) {
 	// Note: Query expects index on (job_state, start_time) for optimal performance
 	q := sq.Select("job.cluster", "job.resources").From("job").
 		Where("job.start_time < ?", ts).
diff --git a/web/frontend/package-lock.json b/web/frontend/package-lock.json
index 8db152f8..2820b72b 100644
--- a/web/frontend/package-lock.json
+++ b/web/frontend/package-lock.json
@@ -621,7 +621,6 @@
       "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
       "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
       "license": "MIT",
-      "peer": true,
       "bin": {
         "acorn": "bin/acorn"
       },
@@ -822,7 +821,6 @@
       "resolved": "https://registry.npmjs.org/graphql/-/graphql-16.12.0.tgz",
       "integrity": "sha512-DKKrynuQRne0PNpEbzuEdHlYOMksHSUI8Zc9Unei5gTsMNA2/vMpoMz/yKba50pejK56qj98qM0SjYxAKi13gQ==",
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": "^12.22.0 || ^14.16.0 || ^16.0.0 || >=17.0.0"
       }
@@ -929,7 +927,6 @@
       "resolved": "https://registry.npmjs.org/picomatch/-/picomatch-4.0.3.tgz",
       "integrity": "sha512-5gTmgEY/sqK6gFXLIsQNH19lWb4ebPDLA4SdLP7dsWkIXHWlG66oPuVvXSGFPppYZz8ZDZq0dYYrbHfBCVUb1Q==",
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=12"
       },
@@ -984,7 +981,6 @@
       "integrity": "sha512-3nk8Y3a9Ea8szgKhinMlGMhGMw89mqule3KWczxhIzqudyHdCIOHw8WJlj/r329fACjKLEh13ZSk7oE22kyeIw==",
       "devOptional": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@types/estree": "1.0.8"
       },
@@ -1165,7 +1161,6 @@
       "resolved": "https://registry.npmjs.org/svelte/-/svelte-5.46.1.tgz",
       "integrity": "sha512-ynjfCHD3nP2el70kN5Pmg37sSi0EjOm9FgHYQdC4giWG/hzO3AatzXXJJgP305uIhGQxSufJLuYWtkY8uK/8RA==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@jridgewell/remapping": "^2.3.4",
         "@jridgewell/sourcemap-codec": "^1.5.0",

From 211d4fae5434a9653dc3207913b099f30eaeb58f Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 15:10:20 +0100
Subject: [PATCH 42/59] Refactor s3 backend and suppress checksum warning

---
 pkg/archive/s3Backend.go | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/pkg/archive/s3Backend.go b/pkg/archive/s3Backend.go
index a9933a9f..85df5c27 100644
--- a/pkg/archive/s3Backend.go
+++ b/pkg/archive/s3Backend.go
@@ -15,6 +15,7 @@ import (
 	"io"
 	"math"
 	"os"
+	"slices"
 	"strconv"
 	"strings"
 	"sync"
@@ -115,6 +116,7 @@ func (s3a *S3Archive) Init(rawConfig json.RawMessage) (uint64, error) {
 
 	// Create S3 client with path-style option and custom endpoint if specified
 	s3a.client = s3.NewFromConfig(awsCfg, func(o *s3.Options) {
+		o.DisableLogOutputChecksumValidationSkipped = true
 		o.UsePathStyle = cfg.UsePathStyle
 		if cfg.Endpoint != "" {
 			o.BaseEndpoint = aws.String(cfg.Endpoint)
@@ -911,13 +913,7 @@ func (s3a *S3Archive) StoreClusterCfg(name string, config *schema.Cluster) error
 	}
 
 	// Update clusters list if new
-	found := false
-	for _, c := range s3a.clusters {
-		if c == name {
-			found = true
-			break
-		}
-	}
+	found := slices.Contains(s3a.clusters, name)
 	if !found {
 		s3a.clusters = append(s3a.clusters, name)
 	}

From c6465ad9e5ec3ca1faa5886f46c8bd092d62aa19 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 15:28:34 +0100
Subject: [PATCH 43/59] Add s3 configuration options

---
 pkg/archive/archive.go | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/pkg/archive/archive.go b/pkg/archive/archive.go
index f9ce4314..c3032faa 100644
--- a/pkg/archive/archive.go
+++ b/pkg/archive/archive.go
@@ -31,13 +31,15 @@
 //	  }
 //	}
 //
-// For S3 backend:
+// For S3 backend (endpoint, region, and usePathStyle are optional):
 //
 //	{
 //	  "archive": {
 //	    "kind": "s3",
+//	    "endpoint": "http://192.168.178.10",
 //	    "bucket": "my-job-archive",
 //	    "region": "us-east-1",
+//	    "usePathStyle": true,
 //	    "accessKey": "...",
 //	    "secretKey": "..."
 //	  }

From 9c3beddf5454622c0df2507c84b609e38c6b015e Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Wed, 14 Jan 2026 15:39:38 +0100
Subject: [PATCH 44/59] Improve documentation

---
 internal/api/rest.go | 147 ++++++++++++++++++++++++++++++++++++-------
 1 file changed, 125 insertions(+), 22 deletions(-)

diff --git a/internal/api/rest.go b/internal/api/rest.go
index 195de826..27374f6e 100644
--- a/internal/api/rest.go
+++ b/internal/api/rest.go
@@ -48,6 +48,7 @@ import (
 const (
 	noticeFilePath  = "./var/notice.txt"
 	noticeFilePerms = 0o644
+	maxNoticeLength = 10000 // Maximum allowed notice content length in characters
 )
 
 type RestAPI struct {
@@ -61,6 +62,7 @@ type RestAPI struct {
 	RepositoryMutex sync.Mutex
 }
 
+// New creates and initializes a new RestAPI instance with configured dependencies.
 func New() *RestAPI {
 	return &RestAPI{
 		JobRepository:   repository.GetJobRepository(),
@@ -69,6 +71,8 @@ func New() *RestAPI {
 	}
 }
 
+// MountAPIRoutes registers REST API endpoints for job and cluster management.
+// These routes use JWT token authentication via the X-Auth-Token header.
 func (api *RestAPI) MountAPIRoutes(r *mux.Router) {
 	r.StrictSlash(true)
 	// REST API Uses TokenAuth
@@ -103,6 +107,8 @@ func (api *RestAPI) MountAPIRoutes(r *mux.Router) {
 	}
 }
 
+// MountUserAPIRoutes registers user-accessible REST API endpoints.
+// These are limited endpoints for regular users with JWT token authentication.
 func (api *RestAPI) MountUserAPIRoutes(r *mux.Router) {
 	r.StrictSlash(true)
 	// REST API Uses TokenAuth
@@ -112,6 +118,8 @@ func (api *RestAPI) MountUserAPIRoutes(r *mux.Router) {
 	r.HandleFunc("/jobs/metrics/{id}", api.getJobMetrics).Methods(http.MethodGet)
 }
 
+// MountMetricStoreAPIRoutes registers metric storage API endpoints.
+// These endpoints handle metric data ingestion and health checks with JWT token authentication.
 func (api *RestAPI) MountMetricStoreAPIRoutes(r *mux.Router) {
 	// REST API Uses TokenAuth
 	// Note: StrictSlash handles trailing slash variations automatically
@@ -126,6 +134,8 @@ func (api *RestAPI) MountMetricStoreAPIRoutes(r *mux.Router) {
 	r.HandleFunc("/api/healthcheck/", metricsHealth).Methods(http.MethodGet)
 }
 
+// MountConfigAPIRoutes registers configuration and user management endpoints.
+// These routes use session-based authentication and require admin privileges.
 func (api *RestAPI) MountConfigAPIRoutes(r *mux.Router) {
 	r.StrictSlash(true)
 	// Settings Frontend Uses SessionAuth
@@ -139,6 +149,8 @@ func (api *RestAPI) MountConfigAPIRoutes(r *mux.Router) {
 	}
 }
 
+// MountFrontendAPIRoutes registers frontend-specific API endpoints.
+// These routes support JWT generation and user configuration updates with session authentication.
 func (api *RestAPI) MountFrontendAPIRoutes(r *mux.Router) {
 	r.StrictSlash(true)
 	// Settings Frontend Uses SessionAuth
@@ -160,6 +172,8 @@ type DefaultAPIResponse struct {
 	Message string `json:"msg"`
 }
 
+// handleError writes a standardized JSON error response with the given status code.
+// It logs the error at WARN level and ensures proper Content-Type headers are set.
 func handleError(err error, statusCode int, rw http.ResponseWriter) {
 	cclog.Warnf("REST ERROR : %s", err.Error())
 	rw.Header().Add("Content-Type", "application/json")
@@ -172,15 +186,38 @@ func handleError(err error, statusCode int, rw http.ResponseWriter) {
 	}
 }
 
+// decode reads JSON from r into val with strict validation that rejects unknown fields.
 func decode(r io.Reader, val any) error {
 	dec := json.NewDecoder(r)
 	dec.DisallowUnknownFields()
 	return dec.Decode(val)
 }
 
-func (api *RestAPI) editNotice(rw http.ResponseWriter, r *http.Request) {
-	// SecuredCheck() only worked with TokenAuth: Removed
+// validatePathComponent checks if a path component contains potentially malicious patterns
+// that could be used for path traversal attacks. Returns an error if validation fails.
+func validatePathComponent(component, componentName string) error {
+	if strings.Contains(component, "..") ||
+		strings.Contains(component, "/") ||
+		strings.Contains(component, "\\") {
+		return fmt.Errorf("invalid %s", componentName)
+	}
+	return nil
+}
 
+// editNotice godoc
+// @summary     Update system notice
+// @tags        Config
+// @description Updates the notice.txt file content. Only admins are allowed. Content is limited to 10000 characters.
+// @accept      mpfd
+// @produce     plain
+// @param       new-content formData string true "New notice content (max 10000 characters)"
+// @success     200 {string} string "Update Notice Content Success"
+// @failure     400 {object} ErrorResponse "Bad Request"
+// @failure     403 {object} ErrorResponse "Forbidden"
+// @failure     500 {object} ErrorResponse "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /notice/ [post]
+func (api *RestAPI) editNotice(rw http.ResponseWriter, r *http.Request) {
 	if user := repository.GetUserFromContext(r.Context()); !user.HasRole(schema.RoleAdmin) {
 		handleError(fmt.Errorf("only admins are allowed to update the notice.txt file"), http.StatusForbidden, rw)
 		return
@@ -189,9 +226,8 @@ func (api *RestAPI) editNotice(rw http.ResponseWriter, r *http.Request) {
 	// Get Value
 	newContent := r.FormValue("new-content")
 
-	// Validate content length to prevent DoS
-	if len(newContent) > 10000 {
-		handleError(fmt.Errorf("notice content exceeds maximum length of 10000 characters"), http.StatusBadRequest, rw)
+	if len(newContent) > maxNoticeLength {
+		handleError(fmt.Errorf("notice content exceeds maximum length of %d characters", maxNoticeLength), http.StatusBadRequest, rw)
 		return
 	}
 
@@ -203,7 +239,9 @@ func (api *RestAPI) editNotice(rw http.ResponseWriter, r *http.Request) {
 			handleError(fmt.Errorf("creating notice file failed: %w", err), http.StatusInternalServerError, rw)
 			return
 		}
-		ntxt.Close()
+		if err := ntxt.Close(); err != nil {
+			cclog.Warnf("Failed to close notice file: %v", err)
+		}
 	}
 
 	if err := os.WriteFile(noticeFilePath, []byte(newContent), noticeFilePerms); err != nil {
@@ -213,13 +251,30 @@ func (api *RestAPI) editNotice(rw http.ResponseWriter, r *http.Request) {
 
 	rw.Header().Set("Content-Type", "text/plain")
 	rw.WriteHeader(http.StatusOK)
+	var msg []byte
 	if newContent != "" {
-		rw.Write([]byte("Update Notice Content Success"))
+		msg = []byte("Update Notice Content Success")
 	} else {
-		rw.Write([]byte("Empty Notice Content Success"))
+		msg = []byte("Empty Notice Content Success")
+	}
+	if _, err := rw.Write(msg); err != nil {
+		cclog.Errorf("Failed to write response: %v", err)
 	}
 }
 
+// getJWT godoc
+// @summary     Generate JWT token
+// @tags        Frontend
+// @description Generates a JWT token for a user. Admins can generate tokens for any user, regular users only for themselves.
+// @accept      mpfd
+// @produce     plain
+// @param       username formData string true "Username to generate JWT for"
+// @success     200 {string} string "JWT token"
+// @failure     403 {object} ErrorResponse "Forbidden"
+// @failure     404 {object} ErrorResponse "User Not Found"
+// @failure     500 {object} ErrorResponse "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /jwt/ [get]
 func (api *RestAPI) getJWT(rw http.ResponseWriter, r *http.Request) {
 	rw.Header().Set("Content-Type", "text/plain")
 	username := r.FormValue("username")
@@ -244,12 +299,22 @@ func (api *RestAPI) getJWT(rw http.ResponseWriter, r *http.Request) {
 	}
 
 	rw.WriteHeader(http.StatusOK)
-	rw.Write([]byte(jwt))
+	if _, err := rw.Write([]byte(jwt)); err != nil {
+		cclog.Errorf("Failed to write JWT response: %v", err)
+	}
 }
 
+// getRoles godoc
+// @summary     Get available roles
+// @tags        Config
+// @description Returns a list of valid user roles. Only admins are allowed.
+// @produce     json
+// @success     200 {array} string "List of role names"
+// @failure     403 {object} ErrorResponse "Forbidden"
+// @failure     500 {object} ErrorResponse "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /roles/ [get]
 func (api *RestAPI) getRoles(rw http.ResponseWriter, r *http.Request) {
-	// SecuredCheck() only worked with TokenAuth: Removed
-
 	user := repository.GetUserFromContext(r.Context())
 	if !user.HasRole(schema.RoleAdmin) {
 		handleError(fmt.Errorf("only admins are allowed to fetch a list of roles"), http.StatusForbidden, rw)
@@ -268,6 +333,18 @@ func (api *RestAPI) getRoles(rw http.ResponseWriter, r *http.Request) {
 	}
 }
 
+// updateConfiguration godoc
+// @summary     Update user configuration
+// @tags        Frontend
+// @description Updates a user's configuration key-value pair.
+// @accept      mpfd
+// @produce     plain
+// @param       key formData string true "Configuration key"
+// @param       value formData string true "Configuration value"
+// @success     200 {string} string "success"
+// @failure     500 {object} ErrorResponse "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /configuration/ [post]
 func (api *RestAPI) updateConfiguration(rw http.ResponseWriter, r *http.Request) {
 	rw.Header().Set("Content-Type", "text/plain")
 	key, value := r.FormValue("key"), r.FormValue("value")
@@ -278,9 +355,25 @@ func (api *RestAPI) updateConfiguration(rw http.ResponseWriter, r *http.Request)
 	}
 
 	rw.WriteHeader(http.StatusOK)
-	rw.Write([]byte("success"))
+	if _, err := rw.Write([]byte("success")); err != nil {
+		cclog.Errorf("Failed to write response: %v", err)
+	}
 }
 
+// putMachineState godoc
+// @summary     Store machine state
+// @tags        Machine State
+// @description Stores machine state data for a specific cluster node. Validates cluster and host names to prevent path traversal.
+// @accept      json
+// @produce     plain
+// @param       cluster path string true "Cluster name"
+// @param       host path string true "Host name"
+// @success     201 "Created"
+// @failure     400 {object} ErrorResponse "Bad Request"
+// @failure     404 {object} ErrorResponse "Machine state not enabled"
+// @failure     500 {object} ErrorResponse "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /machine_state/{cluster}/{host} [put]
 func (api *RestAPI) putMachineState(rw http.ResponseWriter, r *http.Request) {
 	if api.MachineStateDir == "" {
 		handleError(fmt.Errorf("machine state not enabled"), http.StatusNotFound, rw)
@@ -291,13 +384,12 @@ func (api *RestAPI) putMachineState(rw http.ResponseWriter, r *http.Request) {
 	cluster := vars["cluster"]
 	host := vars["host"]
 
-	// Validate cluster and host to prevent path traversal attacks
-	if strings.Contains(cluster, "..") || strings.Contains(cluster, "/") || strings.Contains(cluster, "\\") {
-		handleError(fmt.Errorf("invalid cluster name"), http.StatusBadRequest, rw)
+	if err := validatePathComponent(cluster, "cluster name"); err != nil {
+		handleError(err, http.StatusBadRequest, rw)
 		return
 	}
-	if strings.Contains(host, "..") || strings.Contains(host, "/") || strings.Contains(host, "\\") {
-		handleError(fmt.Errorf("invalid host name"), http.StatusBadRequest, rw)
+	if err := validatePathComponent(host, "host name"); err != nil {
+		handleError(err, http.StatusBadRequest, rw)
 		return
 	}
 
@@ -323,6 +415,18 @@ func (api *RestAPI) putMachineState(rw http.ResponseWriter, r *http.Request) {
 	rw.WriteHeader(http.StatusCreated)
 }
 
+// getMachineState godoc
+// @summary     Retrieve machine state
+// @tags        Machine State
+// @description Retrieves stored machine state data for a specific cluster node. Validates cluster and host names to prevent path traversal.
+// @produce     json
+// @param       cluster path string true "Cluster name"
+// @param       host path string true "Host name"
+// @success     200 {object} object "Machine state JSON data"
+// @failure     400 {object} ErrorResponse "Bad Request"
+// @failure     404 {object} ErrorResponse "Machine state not enabled or file not found"
+// @security    ApiKeyAuth
+// @router      /machine_state/{cluster}/{host} [get]
 func (api *RestAPI) getMachineState(rw http.ResponseWriter, r *http.Request) {
 	if api.MachineStateDir == "" {
 		handleError(fmt.Errorf("machine state not enabled"), http.StatusNotFound, rw)
@@ -333,13 +437,12 @@ func (api *RestAPI) getMachineState(rw http.ResponseWriter, r *http.Request) {
 	cluster := vars["cluster"]
 	host := vars["host"]
 
-	// Validate cluster and host to prevent path traversal attacks
-	if strings.Contains(cluster, "..") || strings.Contains(cluster, "/") || strings.Contains(cluster, "\\") {
-		handleError(fmt.Errorf("invalid cluster name"), http.StatusBadRequest, rw)
+	if err := validatePathComponent(cluster, "cluster name"); err != nil {
+		handleError(err, http.StatusBadRequest, rw)
 		return
 	}
-	if strings.Contains(host, "..") || strings.Contains(host, "/") || strings.Contains(host, "\\") {
-		handleError(fmt.Errorf("invalid host name"), http.StatusBadRequest, rw)
+	if err := validatePathComponent(host, "host name"); err != nil {
+		handleError(err, http.StatusBadRequest, rw)
 		return
 	}
 

From 5d376e6865a1c48469c129075f7c72839a7c577e Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Wed, 14 Jan 2026 16:03:34 +0100
Subject: [PATCH 45/59] fix clustername array init size

---
 web/web.go | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/web/web.go b/web/web.go
index 6ff01403..b4c3749a 100644
--- a/web/web.go
+++ b/web/web.go
@@ -261,7 +261,7 @@ func RenderTemplate(rw http.ResponseWriter, file string, page *Page) {
 	}
 
 	if page.Clusters == nil {
-		page.Clusters = make([]string, 2)
+		page.Clusters = make([]string, 0)
 	}
 
 	if page.SubClusters == nil {

From 94b86ef11acf8844ae7037b44ba67a6c56c37d23 Mon Sep 17 00:00:00 2001
From: Michael Panzlaff <michael.panzlaff@fau.de>
Date: Wed, 14 Jan 2026 16:06:35 +0100
Subject: [PATCH 46/59] Mismatched event types are not something to be
 concerned about

If a different CCMessage type was sent over the same subject as
requested, that shouldn't raise a warning. This may happen in production
instances, but in order to ease debugging, lower it to 'debug' level.
---
 internal/api/nats.go | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/internal/api/nats.go b/internal/api/nats.go
index 48c6449b..9fdfbbb2 100644
--- a/internal/api/nats.go
+++ b/internal/api/nats.go
@@ -152,14 +152,14 @@ func (api *NatsAPI) handleJobEvent(subject string, data []byte) {
 		}
 
 		if !m.IsEvent() {
-			cclog.Warnf("NATS %s: received non-event message, skipping", subject)
+			cclog.Debugf("NATS %s: received non-event message, skipping", subject)
 			continue
 		}
 
 		if m.Name() == "job" {
 			api.processJobEvent(m)
 		} else {
-			cclog.Warnf("NATS %s: unexpected measurement name '%s', expected 'job'", subject, m.Name())
+			cclog.Debugf("NATS %s: unexpected measurement name '%s', expected 'job'", subject, m.Name())
 		}
 	}
 }

From 9deee54e41566fd4ab930a1382ae38951f0952eb Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Wed, 14 Jan 2026 17:18:21 +0100
Subject: [PATCH 47/59] make nextPage query conditional if no return limit is
 requested

---
 internal/graph/schema.resolvers.go | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/internal/graph/schema.resolvers.go b/internal/graph/schema.resolvers.go
index 2cb4f992..920dfe57 100644
--- a/internal/graph/schema.resolvers.go
+++ b/internal/graph/schema.resolvers.go
@@ -590,21 +590,24 @@ func (r *queryResolver) Jobs(ctx context.Context, filter []*model.JobFilter, pag
 
 	// Note: Even if App-Default 'config.Keys.UiDefaults["job_list_usePaging"]' is set, always return hasNextPage boolean.
 	// Users can decide in frontend to use continuous scroll, even if app-default is paging!
+	// Skip if page.ItemsPerPage == -1 ("Load All" -> No Next Page required, Status Dashboards)
 	/*
 	  Example Page 4 @ 10 IpP : Does item 41 exist?
 	  Minimal Page 41 @ 1 IpP : If len(result) is 1, Page 5 @ 10 IpP exists.
 	*/
-	nextPage := &model.PageRequest{
-		ItemsPerPage: 1,
-		Page:         ((page.Page * page.ItemsPerPage) + 1),
+	hasNextPage := false
+	if page.ItemsPerPage != -1 {
+		nextPage := &model.PageRequest{
+			ItemsPerPage: 1,
+			Page:         ((page.Page * page.ItemsPerPage) + 1),
+		}
+		nextJobs, err := r.Repo.QueryJobs(ctx, filter, nextPage, order)
+		if err != nil {
+			cclog.Warn("Error while querying next jobs")
+			return nil, err
+		}
+		hasNextPage = len(nextJobs) == 1
 	}
-	nextJobs, err := r.Repo.QueryJobs(ctx, filter, nextPage, order)
-	if err != nil {
-		cclog.Warn("Error while querying next jobs")
-		return nil, err
-	}
-
-	hasNextPage := len(nextJobs) == 1
 
 	return &model.JobResultList{Items: jobs, Count: &count, HasNextPage: &hasNextPage}, nil
 }

From e5c620ca2050c4098c87d8691d76f6d2256b7c3b Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Wed, 14 Jan 2026 19:22:31 +0100
Subject: [PATCH 48/59] filter metrics for NodeMetrics query

---
 internal/graph/schema.resolvers.go | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/internal/graph/schema.resolvers.go b/internal/graph/schema.resolvers.go
index 920dfe57..881d07e9 100644
--- a/internal/graph/schema.resolvers.go
+++ b/internal/graph/schema.resolvers.go
@@ -756,10 +756,16 @@ func (r *queryResolver) NodeMetrics(ctx context.Context, cluster string, nodes [
 		return nil, errors.New("you need to be administrator or support staff for this query")
 	}
 
+	defaultMetrics := make([]string, 0)
+	for _, mc := range archive.GetCluster(cluster).MetricConfig {
+		defaultMetrics = append(defaultMetrics, mc.Name)
+	}
 	if metrics == nil {
-		for _, mc := range archive.GetCluster(cluster).MetricConfig {
-			metrics = append(metrics, mc.Name)
-		}
+		metrics = defaultMetrics
+	} else {
+		metrics = slices.DeleteFunc(metrics, func(metric string) bool {
+			return !slices.Contains(defaultMetrics, metric) // Remove undefined metrics.
+		})
 	}
 
 	data, err := metricdispatch.LoadNodeData(cluster, metrics, nodes, scopes, from, to, ctx)

From 8f0bb907ff2bf75bcd576acad1f363ec280fb70d Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 15 Jan 2026 06:41:23 +0100
Subject: [PATCH 49/59] Improve documentation and add more tests

---
 internal/repository/hooks_test.go       | 274 +++++++++++
 internal/repository/job.go              | 277 ++++++++++-
 internal/repository/jobCreate_test.go   | 500 ++++++++++++++++++++
 internal/repository/jobHooks.go         |  48 +-
 internal/repository/migration.go        |  63 +++
 internal/repository/stats.go            |  54 ++-
 internal/repository/stats_test.go       |  13 +-
 internal/repository/tags.go             |  42 +-
 internal/repository/transaction_test.go | 311 +++++++++++++
 internal/repository/user.go             |  47 ++
 internal/repository/user_test.go        | 596 ++++++++++++++++++++++++
 internal/tagger/tagger.go               |   2 +-
 12 files changed, 2185 insertions(+), 42 deletions(-)
 create mode 100644 internal/repository/hooks_test.go
 create mode 100644 internal/repository/jobCreate_test.go
 create mode 100644 internal/repository/transaction_test.go
 create mode 100644 internal/repository/user_test.go

diff --git a/internal/repository/hooks_test.go b/internal/repository/hooks_test.go
new file mode 100644
index 00000000..52f954b5
--- /dev/null
+++ b/internal/repository/hooks_test.go
@@ -0,0 +1,274 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+package repository
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	_ "github.com/mattn/go-sqlite3"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+type MockJobHook struct {
+	startCalled bool
+	stopCalled  bool
+	startJobs   []*schema.Job
+	stopJobs    []*schema.Job
+}
+
+func (m *MockJobHook) JobStartCallback(job *schema.Job) {
+	m.startCalled = true
+	m.startJobs = append(m.startJobs, job)
+}
+
+func (m *MockJobHook) JobStopCallback(job *schema.Job) {
+	m.stopCalled = true
+	m.stopJobs = append(m.stopJobs, job)
+}
+
+func TestRegisterJobHook(t *testing.T) {
+	t.Run("register single hook", func(t *testing.T) {
+		hooks = nil
+		mock := &MockJobHook{}
+
+		RegisterJobHook(mock)
+
+		assert.NotNil(t, hooks)
+		assert.Len(t, hooks, 1)
+		assert.Equal(t, mock, hooks[0])
+
+		hooks = nil
+	})
+
+	t.Run("register multiple hooks", func(t *testing.T) {
+		hooks = nil
+		mock1 := &MockJobHook{}
+		mock2 := &MockJobHook{}
+
+		RegisterJobHook(mock1)
+		RegisterJobHook(mock2)
+
+		assert.Len(t, hooks, 2)
+		assert.Equal(t, mock1, hooks[0])
+		assert.Equal(t, mock2, hooks[1])
+
+		hooks = nil
+	})
+
+	t.Run("register nil hook does not add to hooks", func(t *testing.T) {
+		hooks = nil
+		RegisterJobHook(nil)
+
+		if hooks != nil {
+			assert.Len(t, hooks, 0, "Nil hook should not be added")
+		}
+
+		hooks = nil
+	})
+}
+
+func TestCallJobStartHooks(t *testing.T) {
+	t.Run("call start hooks with single job", func(t *testing.T) {
+		hooks = nil
+		mock := &MockJobHook{}
+		RegisterJobHook(mock)
+
+		job := &schema.Job{
+			JobID:   123,
+			User:    "testuser",
+			Cluster: "testcluster",
+		}
+
+		CallJobStartHooks([]*schema.Job{job})
+
+		assert.True(t, mock.startCalled)
+		assert.False(t, mock.stopCalled)
+		assert.Len(t, mock.startJobs, 1)
+		assert.Equal(t, int64(123), mock.startJobs[0].JobID)
+
+		hooks = nil
+	})
+
+	t.Run("call start hooks with multiple jobs", func(t *testing.T) {
+		hooks = nil
+		mock := &MockJobHook{}
+		RegisterJobHook(mock)
+
+		jobs := []*schema.Job{
+			{JobID: 1, User: "user1", Cluster: "cluster1"},
+			{JobID: 2, User: "user2", Cluster: "cluster2"},
+			{JobID: 3, User: "user3", Cluster: "cluster3"},
+		}
+
+		CallJobStartHooks(jobs)
+
+		assert.True(t, mock.startCalled)
+		assert.Len(t, mock.startJobs, 3)
+		assert.Equal(t, int64(1), mock.startJobs[0].JobID)
+		assert.Equal(t, int64(2), mock.startJobs[1].JobID)
+		assert.Equal(t, int64(3), mock.startJobs[2].JobID)
+
+		hooks = nil
+	})
+
+	t.Run("call start hooks with multiple registered hooks", func(t *testing.T) {
+		hooks = nil
+		mock1 := &MockJobHook{}
+		mock2 := &MockJobHook{}
+		RegisterJobHook(mock1)
+		RegisterJobHook(mock2)
+
+		job := &schema.Job{
+			JobID: 456, User: "testuser", Cluster: "testcluster",
+		}
+
+		CallJobStartHooks([]*schema.Job{job})
+
+		assert.True(t, mock1.startCalled)
+		assert.True(t, mock2.startCalled)
+		assert.Len(t, mock1.startJobs, 1)
+		assert.Len(t, mock2.startJobs, 1)
+
+		hooks = nil
+	})
+
+	t.Run("call start hooks with nil hooks", func(t *testing.T) {
+		hooks = nil
+
+		job := &schema.Job{
+			JobID: 789, User: "testuser", Cluster: "testcluster",
+		}
+
+		CallJobStartHooks([]*schema.Job{job})
+
+		hooks = nil
+	})
+
+	t.Run("call start hooks with empty job list", func(t *testing.T) {
+		hooks = nil
+		mock := &MockJobHook{}
+		RegisterJobHook(mock)
+
+		CallJobStartHooks([]*schema.Job{})
+
+		assert.False(t, mock.startCalled)
+		assert.Len(t, mock.startJobs, 0)
+
+		hooks = nil
+	})
+}
+
+func TestCallJobStopHooks(t *testing.T) {
+	t.Run("call stop hooks with single job", func(t *testing.T) {
+		hooks = nil
+		mock := &MockJobHook{}
+		RegisterJobHook(mock)
+
+		job := &schema.Job{
+			JobID:   123,
+			User:    "testuser",
+			Cluster: "testcluster",
+		}
+
+		CallJobStopHooks(job)
+
+		assert.True(t, mock.stopCalled)
+		assert.False(t, mock.startCalled)
+		assert.Len(t, mock.stopJobs, 1)
+		assert.Equal(t, int64(123), mock.stopJobs[0].JobID)
+
+		hooks = nil
+	})
+
+	t.Run("call stop hooks with multiple registered hooks", func(t *testing.T) {
+		hooks = nil
+		mock1 := &MockJobHook{}
+		mock2 := &MockJobHook{}
+		RegisterJobHook(mock1)
+		RegisterJobHook(mock2)
+
+		job := &schema.Job{
+			JobID: 456, User: "testuser", Cluster: "testcluster",
+		}
+
+		CallJobStopHooks(job)
+
+		assert.True(t, mock1.stopCalled)
+		assert.True(t, mock2.stopCalled)
+		assert.Len(t, mock1.stopJobs, 1)
+		assert.Len(t, mock2.stopJobs, 1)
+
+		hooks = nil
+	})
+
+	t.Run("call stop hooks with nil hooks", func(t *testing.T) {
+		hooks = nil
+
+		job := &schema.Job{
+			JobID: 789, User: "testuser", Cluster: "testcluster",
+		}
+
+		CallJobStopHooks(job)
+
+		hooks = nil
+	})
+}
+
+func TestSQLHooks(t *testing.T) {
+	_ = setup(t)
+
+	t.Run("hooks log queries in debug mode", func(t *testing.T) {
+		h := &Hooks{}
+
+		ctx := context.Background()
+		query := "SELECT * FROM job WHERE job_id = ?"
+		args := []any{123}
+
+		ctxWithTime, err := h.Before(ctx, query, args...)
+		require.NoError(t, err)
+		assert.NotNil(t, ctxWithTime)
+
+		beginTime := ctxWithTime.Value("begin")
+		require.NotNil(t, beginTime)
+		_, ok := beginTime.(time.Time)
+		assert.True(t, ok, "Begin time should be time.Time")
+
+		time.Sleep(10 * time.Millisecond)
+
+		ctxAfter, err := h.After(ctxWithTime, query, args...)
+		require.NoError(t, err)
+		assert.NotNil(t, ctxAfter)
+	})
+}
+
+func TestHookIntegration(t *testing.T) {
+	t.Run("hooks are called during job lifecycle", func(t *testing.T) {
+		hooks = nil
+		mock := &MockJobHook{}
+		RegisterJobHook(mock)
+
+		job := &schema.Job{
+			JobID:   999,
+			User:    "integrationuser",
+			Cluster: "integrationcluster",
+		}
+
+		CallJobStartHooks([]*schema.Job{job})
+		assert.True(t, mock.startCalled)
+		assert.Equal(t, 1, len(mock.startJobs))
+
+		CallJobStopHooks(job)
+		assert.True(t, mock.stopCalled)
+		assert.Equal(t, 1, len(mock.stopJobs))
+
+		assert.Equal(t, mock.startJobs[0].JobID, mock.stopJobs[0].JobID)
+
+		hooks = nil
+	})
+}
diff --git a/internal/repository/job.go b/internal/repository/job.go
index b1e92424..bd33774c 100644
--- a/internal/repository/job.go
+++ b/internal/repository/job.go
@@ -80,18 +80,33 @@ import (
 )
 
 var (
-	jobRepoOnce     sync.Once
+	// jobRepoOnce ensures singleton initialization of the JobRepository
+	jobRepoOnce sync.Once
+	// jobRepoInstance holds the single instance of JobRepository
 	jobRepoInstance *JobRepository
 )
 
+// JobRepository provides database access for job-related operations.
+// It implements the repository pattern to abstract database interactions
+// and provides caching for improved performance.
+//
+// The repository is a singleton initialized via GetJobRepository().
+// All database queries use prepared statements via stmtCache for efficiency.
+// Frequently accessed data (metadata, energy footprints) is cached in an LRU cache.
 type JobRepository struct {
-	DB        *sqlx.DB
-	stmtCache *sq.StmtCache
-	cache     *lrucache.Cache
-	driver    string
-	Mutex     sync.Mutex
+	DB        *sqlx.DB        // Database connection pool
+	stmtCache *sq.StmtCache   // Prepared statement cache for query optimization
+	cache     *lrucache.Cache // LRU cache for metadata and footprint data
+	driver    string          // Database driver name (e.g., "sqlite3")
+	Mutex     sync.Mutex      // Mutex for thread-safe operations
 }
 
+// GetJobRepository returns the singleton instance of JobRepository.
+// The repository is initialized lazily on first access with database connection,
+// prepared statement cache, and LRU cache configured from repoConfig.
+//
+// This function is thread-safe and ensures only one instance is created.
+// It must be called after Connect() has established a database connection.
 func GetJobRepository() *JobRepository {
 	jobRepoOnce.Do(func() {
 		db := GetConnection()
@@ -107,6 +122,8 @@ func GetJobRepository() *JobRepository {
 	return jobRepoInstance
 }
 
+// jobColumns defines the standard set of columns selected from the job table.
+// Used consistently across all job queries to ensure uniform data retrieval.
 var jobColumns []string = []string{
 	"job.id", "job.job_id", "job.hpc_user", "job.project", "job.cluster", "job.subcluster",
 	"job.start_time", "job.cluster_partition", "job.array_job_id", "job.num_nodes",
@@ -115,6 +132,8 @@ var jobColumns []string = []string{
 	"job.footprint", "job.energy",
 }
 
+// jobCacheColumns defines columns from the job_cache table, mirroring jobColumns.
+// Used for queries against cached job data for performance optimization.
 var jobCacheColumns []string = []string{
 	"job_cache.id", "job_cache.job_id", "job_cache.hpc_user", "job_cache.project", "job_cache.cluster",
 	"job_cache.subcluster", "job_cache.start_time", "job_cache.cluster_partition",
@@ -124,6 +143,14 @@ var jobCacheColumns []string = []string{
 	"job_cache.footprint", "job_cache.energy",
 }
 
+// scanJob converts a database row into a schema.Job struct.
+// It handles JSON unmarshaling of resources and footprint fields,
+// and calculates accurate duration for running jobs.
+//
+// Parameters:
+//   - row: Database row implementing Scan() interface (sql.Row or sql.Rows)
+//
+// Returns the populated Job struct or an error if scanning or unmarshaling fails.
 func scanJob(row interface{ Scan(...any) error }) (*schema.Job, error) {
 	job := &schema.Job{}
 
@@ -186,6 +213,16 @@ func (r *JobRepository) Flush() error {
 	return nil
 }
 
+// FetchMetadata retrieves and unmarshals the metadata JSON for a job.
+// Metadata is cached with a 24-hour TTL to improve performance.
+//
+// The metadata field stores arbitrary key-value pairs associated with a job,
+// such as tags, labels, or custom attributes added by external systems.
+//
+// Parameters:
+//   - job: Job struct with valid ID field, metadata will be populated in job.MetaData
+//
+// Returns the metadata map or an error if the job is nil or database query fails.
 func (r *JobRepository) FetchMetadata(job *schema.Job) (map[string]string, error) {
 	if job == nil {
 		return nil, fmt.Errorf("job cannot be nil")
@@ -218,6 +255,16 @@ func (r *JobRepository) FetchMetadata(job *schema.Job) (map[string]string, error
 	return job.MetaData, nil
 }
 
+// UpdateMetadata adds or updates a single metadata key-value pair for a job.
+// The entire metadata map is re-marshaled and stored, and the cache is invalidated.
+// Also triggers archive metadata update via archive.UpdateMetadata.
+//
+// Parameters:
+//   - job: Job struct with valid ID, existing metadata will be fetched if not present
+//   - key: Metadata key to set
+//   - val: Metadata value to set
+//
+// Returns an error if the job is nil, metadata fetch fails, or database update fails.
 func (r *JobRepository) UpdateMetadata(job *schema.Job, key, val string) (err error) {
 	if job == nil {
 		return fmt.Errorf("job cannot be nil")
@@ -228,7 +275,7 @@ func (r *JobRepository) UpdateMetadata(job *schema.Job, key, val string) (err er
 	if job.MetaData == nil {
 		if _, err = r.FetchMetadata(job); err != nil {
 			cclog.Warnf("Error while fetching metadata for job, DB ID '%v'", job.ID)
-			return err
+			return fmt.Errorf("failed to fetch metadata for job %d: %w", job.ID, err)
 		}
 	}
 
@@ -243,7 +290,7 @@ func (r *JobRepository) UpdateMetadata(job *schema.Job, key, val string) (err er
 
 	if job.RawMetaData, err = json.Marshal(job.MetaData); err != nil {
 		cclog.Warnf("Error while marshaling metadata for job, DB ID '%v'", job.ID)
-		return err
+		return fmt.Errorf("failed to marshal metadata for job %d: %w", job.ID, err)
 	}
 
 	if _, err = sq.Update("job").
@@ -251,13 +298,23 @@ func (r *JobRepository) UpdateMetadata(job *schema.Job, key, val string) (err er
 		Where("job.id = ?", job.ID).
 		RunWith(r.stmtCache).Exec(); err != nil {
 		cclog.Warnf("Error while updating metadata for job, DB ID '%v'", job.ID)
-		return err
+		return fmt.Errorf("failed to update metadata in database for job %d: %w", job.ID, err)
 	}
 
 	r.cache.Put(cachekey, job.MetaData, len(job.RawMetaData), 24*time.Hour)
 	return archive.UpdateMetadata(job, job.MetaData)
 }
 
+// FetchFootprint retrieves and unmarshals the performance footprint JSON for a job.
+// Unlike FetchMetadata, footprints are NOT cached as they can be large and change frequently.
+//
+// The footprint contains summary statistics (avg/min/max) for monitored metrics,
+// stored as JSON with keys like "cpu_load_avg", "mem_used_max", etc.
+//
+// Parameters:
+//   - job: Job struct with valid ID, footprint will be populated in job.Footprint
+//
+// Returns the footprint map or an error if the job is nil or database query fails.
 func (r *JobRepository) FetchFootprint(job *schema.Job) (map[string]float64, error) {
 	if job == nil {
 		return nil, fmt.Errorf("job cannot be nil")
@@ -284,6 +341,16 @@ func (r *JobRepository) FetchFootprint(job *schema.Job) (map[string]float64, err
 	return job.Footprint, nil
 }
 
+// FetchEnergyFootprint retrieves and unmarshals the energy footprint JSON for a job.
+// Energy footprints are cached with a 24-hour TTL as they are frequently accessed but rarely change.
+//
+// The energy footprint contains calculated energy consumption (in kWh) per metric,
+// stored as JSON with keys like "power_avg", "acc_power_avg", etc.
+//
+// Parameters:
+//   - job: Job struct with valid ID, energy footprint will be populated in job.EnergyFootprint
+//
+// Returns the energy footprint map or an error if the job is nil or database query fails.
 func (r *JobRepository) FetchEnergyFootprint(job *schema.Job) (map[string]float64, error) {
 	if job == nil {
 		return nil, fmt.Errorf("job cannot be nil")
@@ -316,6 +383,18 @@ func (r *JobRepository) FetchEnergyFootprint(job *schema.Job) (map[string]float6
 	return job.EnergyFootprint, nil
 }
 
+// DeleteJobsBefore removes jobs older than the specified start time.
+// Optionally preserves tagged jobs to protect important data from deletion.
+// Cache entries for deleted jobs are automatically invalidated.
+//
+// This is typically used for data retention policies and cleanup operations.
+// WARNING: This is a destructive operation that permanently deletes job records.
+//
+// Parameters:
+//   - startTime: Unix timestamp, jobs with start_time < this value will be deleted
+//   - omitTagged: If true, skip jobs that have associated tags (jobtag entries)
+//
+// Returns the count of deleted jobs or an error if the operation fails.
 func (r *JobRepository) DeleteJobsBefore(startTime int64, omitTagged bool) (int, error) {
 	var cnt int
 	q := sq.Select("count(*)").From("job").Where("job.start_time < ?", startTime)
@@ -371,6 +450,13 @@ func (r *JobRepository) DeleteJobsBefore(startTime int64, omitTagged bool) (int,
 	return cnt, err
 }
 
+// DeleteJobByID permanently removes a single job by its database ID.
+// Cache entries for the deleted job are automatically invalidated.
+//
+// Parameters:
+//   - id: Database ID (primary key) of the job to delete
+//
+// Returns an error if the deletion fails.
 func (r *JobRepository) DeleteJobByID(id int64) error {
 	// Invalidate cache entries before deletion
 	r.cache.Del(fmt.Sprintf("metadata:%d", id))
@@ -388,6 +474,24 @@ func (r *JobRepository) DeleteJobByID(id int64) error {
 	return err
 }
 
+// FindUserOrProjectOrJobname attempts to interpret a search term as a job ID,
+// username, project ID, or job name by querying the database.
+//
+// Search logic (in priority order):
+//  1. If searchterm is numeric, treat as job ID (returned immediately)
+//  2. Try exact match in job.hpc_user column (username)
+//  3. Try LIKE match in hpc_user.name column (real name)
+//  4. Try exact match in job.project column (project ID)
+//  5. If no matches, return searchterm as jobname for GraphQL query
+//
+// This powers the searchbar functionality for flexible job searching.
+// Requires authenticated user for database lookups (returns empty if user is nil).
+//
+// Parameters:
+//   - user: Authenticated user context, required for database access
+//   - searchterm: Search string to interpret
+//
+// Returns up to one non-empty value among (jobid, username, project, jobname).
 func (r *JobRepository) FindUserOrProjectOrJobname(user *schema.User, searchterm string) (jobid string, username string, project string, jobname string) {
 	if searchterm == "" {
 		return "", "", "", ""
@@ -423,6 +527,19 @@ var (
 	ErrForbidden = errors.New("not authorized")
 )
 
+// FindColumnValue performs a generic column lookup in a database table with role-based access control.
+// Only users with admin, support, or manager roles can execute this query.
+//
+// Parameters:
+//   - user: User context for authorization check
+//   - searchterm: Value to search for (exact match or LIKE pattern)
+//   - table: Database table name to query
+//   - selectColumn: Column name to return in results
+//   - whereColumn: Column name to filter on
+//   - isLike: If true, use LIKE with wildcards; if false, use exact equality
+//
+// Returns the first matching value, ErrForbidden if user lacks permission,
+// or ErrNotFound if no matches are found.
 func (r *JobRepository) FindColumnValue(user *schema.User, searchterm string, table string, selectColumn string, whereColumn string, isLike bool) (result string, err error) {
 	if user == nil {
 		return "", fmt.Errorf("user cannot be nil")
@@ -453,6 +570,19 @@ func (r *JobRepository) FindColumnValue(user *schema.User, searchterm string, ta
 	}
 }
 
+// FindColumnValues performs a generic column lookup returning multiple matches with role-based access control.
+// Similar to FindColumnValue but returns all matching values instead of just the first.
+// Only users with admin, support, or manager roles can execute this query.
+//
+// Parameters:
+//   - user: User context for authorization check
+//   - query: Search pattern (always uses LIKE with wildcards)
+//   - table: Database table name to query
+//   - selectColumn: Column name to return in results
+//   - whereColumn: Column name to filter on
+//
+// Returns a slice of matching values, ErrForbidden if user lacks permission,
+// or ErrNotFound if no matches are found.
 func (r *JobRepository) FindColumnValues(user *schema.User, query string, table string, selectColumn string, whereColumn string) (results []string, err error) {
 	if user == nil {
 		return nil, fmt.Errorf("user cannot be nil")
@@ -487,6 +617,13 @@ func (r *JobRepository) FindColumnValues(user *schema.User, query string, table
 	}
 }
 
+// Partitions returns a list of distinct cluster partitions for a given cluster.
+// Results are cached with a 1-hour TTL to improve performance.
+//
+// Parameters:
+//   - cluster: Cluster name to query partitions for
+//
+// Returns a slice of partition names or an error if the database query fails.
 func (r *JobRepository) Partitions(cluster string) ([]string, error) {
 	var err error
 	start := time.Now()
@@ -550,6 +687,19 @@ func (r *JobRepository) AllocatedNodes(cluster string) (map[string]map[string]in
 }
 
 // FIXME: Set duration to requested walltime?
+// StopJobsExceedingWalltimeBy marks running jobs as failed if they exceed their walltime limit.
+// This is typically called periodically to clean up stuck or orphaned jobs.
+//
+// Jobs are marked with:
+//   - monitoring_status: MonitoringStatusArchivingFailed
+//   - duration: 0
+//   - job_state: JobStateFailed
+//
+// Parameters:
+//   - seconds: Grace period beyond walltime before marking as failed
+//
+// Returns an error if the database update fails.
+// Logs the number of jobs marked as failed if any were affected.
 func (r *JobRepository) StopJobsExceedingWalltimeBy(seconds int) error {
 	start := time.Now()
 	currentTime := time.Now().Unix()
@@ -579,6 +729,12 @@ func (r *JobRepository) StopJobsExceedingWalltimeBy(seconds int) error {
 	return nil
 }
 
+// FindJobIdsByTag returns all job database IDs associated with a specific tag.
+//
+// Parameters:
+//   - tagID: Database ID of the tag to search for
+//
+// Returns a slice of job IDs or an error if the query fails.
 func (r *JobRepository) FindJobIdsByTag(tagID int64) ([]int64, error) {
 	query := sq.Select("job.id").From("job").
 		Join("jobtag ON jobtag.job_id = job.id").
@@ -607,6 +763,13 @@ func (r *JobRepository) FindJobIdsByTag(tagID int64) ([]int64, error) {
 }
 
 // FIXME: Reconsider filtering short jobs with harcoded threshold
+// FindRunningJobs returns all currently running jobs for a specific cluster.
+// Filters out short-running jobs based on repoConfig.MinRunningJobDuration threshold.
+//
+// Parameters:
+//   - cluster: Cluster name to filter jobs
+//
+// Returns a slice of running job objects or an error if the query fails.
 func (r *JobRepository) FindRunningJobs(cluster string) ([]*schema.Job, error) {
 	query := sq.Select(jobColumns...).From("job").
 		Where("job.cluster = ?", cluster).
@@ -634,6 +797,12 @@ func (r *JobRepository) FindRunningJobs(cluster string) ([]*schema.Job, error) {
 	return jobs, nil
 }
 
+// UpdateDuration recalculates and updates the duration field for all running jobs.
+// Called periodically to keep job durations current without querying individual jobs.
+//
+// Duration is calculated as: current_time - job.start_time
+//
+// Returns an error if the database update fails.
 func (r *JobRepository) UpdateDuration() error {
 	stmnt := sq.Update("job").
 		Set("duration", sq.Expr("? - job.start_time", time.Now().Unix())).
@@ -648,6 +817,16 @@ func (r *JobRepository) UpdateDuration() error {
 	return nil
 }
 
+// FindJobsBetween returns jobs within a specified time range.
+// If startTimeBegin is 0, returns all jobs before startTimeEnd.
+// Optionally excludes tagged jobs from results.
+//
+// Parameters:
+//   - startTimeBegin: Unix timestamp for range start (use 0 for unbounded start)
+//   - startTimeEnd: Unix timestamp for range end
+//   - omitTagged: If true, exclude jobs with associated tags
+//
+// Returns a slice of jobs or an error if the time range is invalid or query fails.
 func (r *JobRepository) FindJobsBetween(startTimeBegin int64, startTimeEnd int64, omitTagged bool) ([]*schema.Job, error) {
 	var query sq.SelectBuilder
 
@@ -688,6 +867,14 @@ func (r *JobRepository) FindJobsBetween(startTimeBegin int64, startTimeEnd int64
 	return jobs, nil
 }
 
+// UpdateMonitoringStatus updates the monitoring status for a job and invalidates its cache entries.
+// Cache invalidation affects both metadata and energy footprint to ensure consistency.
+//
+// Parameters:
+//   - job: Database ID of the job to update
+//   - monitoringStatus: New monitoring status value (see schema.MonitoringStatus constants)
+//
+// Returns an error if the database update fails.
 func (r *JobRepository) UpdateMonitoringStatus(job int64, monitoringStatus int32) (err error) {
 	// Invalidate cache entries as monitoring status affects job state
 	r.cache.Del(fmt.Sprintf("metadata:%d", job))
@@ -704,6 +891,13 @@ func (r *JobRepository) UpdateMonitoringStatus(job int64, monitoringStatus int32
 	return nil
 }
 
+// Execute runs a Squirrel UpdateBuilder statement against the database.
+// This is a generic helper for executing pre-built update queries.
+//
+// Parameters:
+//   - stmt: Squirrel UpdateBuilder with prepared update query
+//
+// Returns an error if the execution fails.
 func (r *JobRepository) Execute(stmt sq.UpdateBuilder) error {
 	if _, err := stmt.RunWith(r.stmtCache).Exec(); err != nil {
 		cclog.Errorf("Error while executing statement: %v", err)
@@ -713,6 +907,14 @@ func (r *JobRepository) Execute(stmt sq.UpdateBuilder) error {
 	return nil
 }
 
+// MarkArchived adds monitoring status update to an existing UpdateBuilder statement.
+// This is a builder helper used when constructing multi-field update queries.
+//
+// Parameters:
+//   - stmt: Existing UpdateBuilder to modify
+//   - monitoringStatus: Monitoring status value to set
+//
+// Returns the modified UpdateBuilder for method chaining.
 func (r *JobRepository) MarkArchived(
 	stmt sq.UpdateBuilder,
 	monitoringStatus int32,
@@ -720,11 +922,22 @@ func (r *JobRepository) MarkArchived(
 	return stmt.Set("monitoring_status", monitoringStatus)
 }
 
+// UpdateEnergy calculates and updates the energy consumption for a job.
+// This is called for running jobs during intermediate updates or when archiving.
+//
+// Energy calculation formula:
+//   - For "power" metrics: Energy (kWh) = (Power_avg * NumNodes * Duration_hours) / 1000
+//   - For "energy" metrics: Currently not implemented (would need sum statistics)
+//
+// The calculation accounts for:
+//   - Multi-node jobs: Multiplies by NumNodes to get total cluster energy
+//   - Shared jobs: Node average is already based on partial resources, so NumNodes=1
+//   - Unit conversion: Watts * hours / 1000 = kilowatt-hours (kWh)
+//   - Rounding: Results rounded to 2 decimal places
 func (r *JobRepository) UpdateEnergy(
 	stmt sq.UpdateBuilder,
 	jobMeta *schema.Job,
 ) (sq.UpdateBuilder, error) {
-	/* Note: Only Called for Running Jobs during Intermediate Update or on Archiving */
 	sc, err := archive.GetSubCluster(jobMeta.Cluster, jobMeta.SubCluster)
 	if err != nil {
 		cclog.Errorf("cannot get subcluster: %s", err.Error())
@@ -732,25 +945,27 @@ func (r *JobRepository) UpdateEnergy(
 	}
 	energyFootprint := make(map[string]float64)
 
-	// Total Job Energy Outside Loop
+	// Accumulate total energy across all energy-related metrics
 	totalEnergy := 0.0
 	for _, fp := range sc.EnergyFootprint {
-		// Always Init Metric Energy Inside Loop
+		// Calculate energy for this specific metric
 		metricEnergy := 0.0
 		if i, err := archive.MetricIndex(sc.MetricConfig, fp); err == nil {
-			// Note: For DB data, calculate and save as kWh
 			switch sc.MetricConfig[i].Energy {
-			case "energy": // this metric has energy as unit (Joules or Wh)
+			case "energy": // Metric already in energy units (Joules or Wh)
 				cclog.Warnf("Update EnergyFootprint for Job %d and Metric %s on cluster %s: Set to 'energy' in cluster.json: Not implemented, will return 0.0", jobMeta.JobID, jobMeta.Cluster, fp)
-				// FIXME: Needs sum as stats type
-			case "power": // this metric has power as unit (Watt)
-				// Energy: Power (in Watts) * Time (in Seconds)
-				// Unit: (W * (s / 3600)) / 1000 = kWh
-				// Round 2 Digits: round(Energy * 100) / 100
-				// Here: (All-Node Metric Average * Number of Nodes) * (Job Duration in Seconds / 3600) / 1000
-				// Note: Shared Jobs handled correctly since "Node Average" is based on partial resources, while "numNodes" factor is 1
+				// FIXME: Needs sum as stats type to accumulate energy values over time
+			case "power": // Metric in power units (Watts)
+				// Energy (kWh) = Power (W) × Time (h) / 1000
+				// Formula: (avg_power_per_node * num_nodes) * (duration_sec / 3600) / 1000
+				//
+				// Breakdown:
+				//   LoadJobStat(jobMeta, fp, "avg") = average power per node (W)
+				//   jobMeta.NumNodes = number of nodes (1 for shared jobs)
+				//   jobMeta.Duration / 3600.0 = duration in hours
+				//   / 1000.0 = convert Wh to kWh
 				rawEnergy := ((LoadJobStat(jobMeta, fp, "avg") * float64(jobMeta.NumNodes)) * (float64(jobMeta.Duration) / 3600.0)) / 1000.0
-				metricEnergy = math.Round(rawEnergy*100.0) / 100.0
+				metricEnergy = math.Round(rawEnergy*100.0) / 100.0 // Round to 2 decimal places
 			}
 		} else {
 			cclog.Warnf("Error while collecting energy metric %s for job, DB ID '%v', return '0.0'", fp, jobMeta.ID)
@@ -758,8 +973,6 @@ func (r *JobRepository) UpdateEnergy(
 
 		energyFootprint[fp] = metricEnergy
 		totalEnergy += metricEnergy
-
-		// cclog.Infof("Metric %s Average %f -> %f kWh | Job %d Total -> %f kWh", fp, LoadJobStat(jobMeta, fp, "avg"), energy, jobMeta.JobID, totalEnergy)
 	}
 
 	var rawFootprint []byte
@@ -771,11 +984,19 @@ func (r *JobRepository) UpdateEnergy(
 	return stmt.Set("energy_footprint", string(rawFootprint)).Set("energy", (math.Round(totalEnergy*100.0) / 100.0)), nil
 }
 
+// UpdateFootprint calculates and updates the performance footprint for a job.
+// This is called for running jobs during intermediate updates or when archiving.
+//
+// A footprint is a summary statistic (avg/min/max) for each monitored metric.
+// The specific statistic type is defined in the cluster config's Footprint field.
+// Results are stored as JSON with keys like "metric_avg", "metric_max", etc.
+//
+// Example: For a "cpu_load" metric with Footprint="avg", this stores
+// the average CPU load across all nodes as "cpu_load_avg": 85.3
 func (r *JobRepository) UpdateFootprint(
 	stmt sq.UpdateBuilder,
 	jobMeta *schema.Job,
 ) (sq.UpdateBuilder, error) {
-	/* Note: Only Called for Running Jobs during Intermediate Update or on Archiving */
 	sc, err := archive.GetSubCluster(jobMeta.Cluster, jobMeta.SubCluster)
 	if err != nil {
 		cclog.Errorf("cannot get subcluster: %s", err.Error())
@@ -783,7 +1004,10 @@ func (r *JobRepository) UpdateFootprint(
 	}
 	footprint := make(map[string]float64)
 
+	// Build footprint map with metric_stattype as keys
 	for _, fp := range sc.Footprint {
+		// Determine which statistic to use: avg, min, or max
+		// First check global metric config, then cluster-specific config
 		var statType string
 		for _, gm := range archive.GlobalMetricList {
 			if gm.Name == fp {
@@ -791,15 +1015,18 @@ func (r *JobRepository) UpdateFootprint(
 			}
 		}
 
+		// Validate statistic type
 		if statType != "avg" && statType != "min" && statType != "max" {
 			cclog.Warnf("unknown statType for footprint update: %s", statType)
 			return stmt, fmt.Errorf("unknown statType for footprint update: %s", statType)
 		}
 
+		// Override with cluster-specific config if available
 		if i, err := archive.MetricIndex(sc.MetricConfig, fp); err != nil {
 			statType = sc.MetricConfig[i].Footprint
 		}
 
+		// Store as "metric_stattype": value (e.g., "cpu_load_avg": 85.3)
 		name := fmt.Sprintf("%s_%s", fp, statType)
 		footprint[name] = LoadJobStat(jobMeta, fp, statType)
 	}
diff --git a/internal/repository/jobCreate_test.go b/internal/repository/jobCreate_test.go
new file mode 100644
index 00000000..3a586482
--- /dev/null
+++ b/internal/repository/jobCreate_test.go
@@ -0,0 +1,500 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+package repository
+
+import (
+	"encoding/json"
+	"testing"
+
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	_ "github.com/mattn/go-sqlite3"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// createTestJob creates a minimal valid job for testing
+func createTestJob(jobID int64, cluster string) *schema.Job {
+	return &schema.Job{
+		JobID:            jobID,
+		User:             "testuser",
+		Project:          "testproject",
+		Cluster:          cluster,
+		SubCluster:       "main",
+		Partition:        "batch",
+		NumNodes:         1,
+		NumHWThreads:     4,
+		NumAcc:           0,
+		Shared:           "none",
+		MonitoringStatus: schema.MonitoringStatusRunningOrArchiving,
+		SMT:              1,
+		State:            schema.JobStateRunning,
+		StartTime:        1234567890,
+		Duration:         0,
+		Walltime:         3600,
+		Resources: []*schema.Resource{
+			{
+				Hostname:  "node01",
+				HWThreads: []int{0, 1, 2, 3},
+			},
+		},
+		Footprint: map[string]float64{
+			"cpu_load":      50.0,
+			"mem_used":      8000.0,
+			"flops_any":     0.5,
+			"mem_bw":        10.0,
+			"net_bw":        2.0,
+			"file_bw":       1.0,
+			"cpu_used":      2.0,
+			"cpu_load_core": 12.5,
+		},
+		MetaData: map[string]string{
+			"jobName":     "test_job",
+			"queue":       "normal",
+			"qosName":     "default",
+			"accountName": "testaccount",
+		},
+	}
+}
+
+func TestInsertJob(t *testing.T) {
+	r := setup(t)
+
+	t.Run("successful insertion", func(t *testing.T) {
+		job := createTestJob(999001, "testcluster")
+		job.RawResources, _ = json.Marshal(job.Resources)
+		job.RawFootprint, _ = json.Marshal(job.Footprint)
+		job.RawMetaData, _ = json.Marshal(job.MetaData)
+
+		id, err := r.InsertJob(job)
+		require.NoError(t, err, "InsertJob should succeed")
+		assert.Greater(t, id, int64(0), "Should return valid insert ID")
+
+		// Verify job was inserted into job_cache
+		var count int
+		err = r.DB.QueryRow("SELECT COUNT(*) FROM job_cache WHERE job_id = ? AND cluster = ?",
+			job.JobID, job.Cluster).Scan(&count)
+		require.NoError(t, err)
+		assert.Equal(t, 1, count, "Job should be in job_cache table")
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job_cache WHERE job_id = ? AND cluster = ?", job.JobID, job.Cluster)
+		require.NoError(t, err)
+	})
+
+	t.Run("insertion with all fields", func(t *testing.T) {
+		job := createTestJob(999002, "testcluster")
+		job.ArrayJobID = 5000
+		job.Energy = 1500.5
+		job.RawResources, _ = json.Marshal(job.Resources)
+		job.RawFootprint, _ = json.Marshal(job.Footprint)
+		job.RawMetaData, _ = json.Marshal(job.MetaData)
+
+		id, err := r.InsertJob(job)
+		require.NoError(t, err)
+		assert.Greater(t, id, int64(0))
+
+		// Verify all fields were stored correctly
+		var retrievedJob schema.Job
+		err = r.DB.QueryRow(`SELECT job_id, hpc_user, project, cluster, array_job_id, energy 
+			FROM job_cache WHERE id = ?`, id).Scan(
+			&retrievedJob.JobID, &retrievedJob.User, &retrievedJob.Project,
+			&retrievedJob.Cluster, &retrievedJob.ArrayJobID, &retrievedJob.Energy)
+		require.NoError(t, err)
+		assert.Equal(t, job.JobID, retrievedJob.JobID)
+		assert.Equal(t, job.User, retrievedJob.User)
+		assert.Equal(t, job.Project, retrievedJob.Project)
+		assert.Equal(t, job.Cluster, retrievedJob.Cluster)
+		assert.Equal(t, job.ArrayJobID, retrievedJob.ArrayJobID)
+		assert.Equal(t, job.Energy, retrievedJob.Energy)
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job_cache WHERE id = ?", id)
+		require.NoError(t, err)
+	})
+}
+
+func TestStart(t *testing.T) {
+	r := setup(t)
+
+	t.Run("successful job start with JSON encoding", func(t *testing.T) {
+		job := createTestJob(999003, "testcluster")
+
+		id, err := r.Start(job)
+		require.NoError(t, err, "Start should succeed")
+		assert.Greater(t, id, int64(0), "Should return valid insert ID")
+
+		// Verify job was inserted and JSON fields were encoded
+		var rawResources, rawFootprint, rawMetaData []byte
+		err = r.DB.QueryRow(`SELECT resources, footprint, meta_data FROM job_cache WHERE id = ?`, id).Scan(
+			&rawResources, &rawFootprint, &rawMetaData)
+		require.NoError(t, err)
+
+		// Verify resources JSON
+		var resources []*schema.Resource
+		err = json.Unmarshal(rawResources, &resources)
+		require.NoError(t, err, "Resources should be valid JSON")
+		assert.Equal(t, 1, len(resources))
+		assert.Equal(t, "node01", resources[0].Hostname)
+
+		// Verify footprint JSON
+		var footprint map[string]float64
+		err = json.Unmarshal(rawFootprint, &footprint)
+		require.NoError(t, err, "Footprint should be valid JSON")
+		assert.Equal(t, 50.0, footprint["cpu_load"])
+		assert.Equal(t, 8000.0, footprint["mem_used"])
+
+		// Verify metadata JSON
+		var metaData map[string]string
+		err = json.Unmarshal(rawMetaData, &metaData)
+		require.NoError(t, err, "MetaData should be valid JSON")
+		assert.Equal(t, "test_job", metaData["jobName"])
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job_cache WHERE id = ?", id)
+		require.NoError(t, err)
+	})
+
+	t.Run("job start with empty footprint", func(t *testing.T) {
+		job := createTestJob(999004, "testcluster")
+		job.Footprint = map[string]float64{}
+
+		id, err := r.Start(job)
+		require.NoError(t, err)
+		assert.Greater(t, id, int64(0))
+
+		// Verify empty footprint was encoded as empty JSON object
+		var rawFootprint []byte
+		err = r.DB.QueryRow(`SELECT footprint FROM job_cache WHERE id = ?`, id).Scan(&rawFootprint)
+		require.NoError(t, err)
+		assert.Equal(t, []byte("{}"), rawFootprint)
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job_cache WHERE id = ?", id)
+		require.NoError(t, err)
+	})
+
+	t.Run("job start with nil metadata", func(t *testing.T) {
+		job := createTestJob(999005, "testcluster")
+		job.MetaData = nil
+
+		id, err := r.Start(job)
+		require.NoError(t, err)
+		assert.Greater(t, id, int64(0))
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job_cache WHERE id = ?", id)
+		require.NoError(t, err)
+	})
+}
+
+func TestStop(t *testing.T) {
+	r := setup(t)
+
+	t.Run("successful job stop", func(t *testing.T) {
+		// First insert a job using Start
+		job := createTestJob(999106, "testcluster")
+		id, err := r.Start(job)
+		require.NoError(t, err)
+
+		// Move from job_cache to job table (simulate SyncJobs) - exclude id to let it auto-increment
+		_, err = r.DB.Exec(`INSERT INTO job (job_id, cluster, subcluster, submit_time, start_time, hpc_user, project, 
+			cluster_partition, array_job_id, duration, walltime, job_state, meta_data, resources, num_nodes, 
+			num_hwthreads, num_acc, smt, shared, monitoring_status, energy, energy_footprint, footprint) 
+			SELECT job_id, cluster, subcluster, submit_time, start_time, hpc_user, project, 
+			cluster_partition, array_job_id, duration, walltime, job_state, meta_data, resources, num_nodes, 
+			num_hwthreads, num_acc, smt, shared, monitoring_status, energy, energy_footprint, footprint 
+			FROM job_cache WHERE id = ?`, id)
+		require.NoError(t, err)
+		_, err = r.DB.Exec("DELETE FROM job_cache WHERE id = ?", id)
+		require.NoError(t, err)
+
+		// Get the new job id in the job table
+		err = r.DB.QueryRow("SELECT id FROM job WHERE job_id = ? AND cluster = ? AND start_time = ?",
+			job.JobID, job.Cluster, job.StartTime).Scan(&id)
+		require.NoError(t, err)
+
+		// Stop the job
+		duration := int32(3600)
+		state := schema.JobStateCompleted
+		monitoringStatus := int32(schema.MonitoringStatusArchivingSuccessful)
+
+		err = r.Stop(id, duration, state, monitoringStatus)
+		require.NoError(t, err, "Stop should succeed")
+
+		// Verify job was updated
+		var retrievedDuration int32
+		var retrievedState string
+		var retrievedMonStatus int32
+		err = r.DB.QueryRow(`SELECT duration, job_state, monitoring_status FROM job WHERE id = ?`, id).Scan(
+			&retrievedDuration, &retrievedState, &retrievedMonStatus)
+		require.NoError(t, err)
+		assert.Equal(t, duration, retrievedDuration)
+		assert.Equal(t, string(state), retrievedState)
+		assert.Equal(t, monitoringStatus, retrievedMonStatus)
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job WHERE id = ?", id)
+		require.NoError(t, err)
+	})
+
+	t.Run("stop updates job state transitions", func(t *testing.T) {
+		// Insert a job
+		job := createTestJob(999107, "testcluster")
+		id, err := r.Start(job)
+		require.NoError(t, err)
+
+		// Move to job table
+		_, err = r.DB.Exec(`INSERT INTO job (job_id, cluster, subcluster, submit_time, start_time, hpc_user, project, 
+			cluster_partition, array_job_id, duration, walltime, job_state, meta_data, resources, num_nodes, 
+			num_hwthreads, num_acc, smt, shared, monitoring_status, energy, energy_footprint, footprint) 
+			SELECT job_id, cluster, subcluster, submit_time, start_time, hpc_user, project, 
+			cluster_partition, array_job_id, duration, walltime, job_state, meta_data, resources, num_nodes, 
+			num_hwthreads, num_acc, smt, shared, monitoring_status, energy, energy_footprint, footprint 
+			FROM job_cache WHERE id = ?`, id)
+		require.NoError(t, err)
+		_, err = r.DB.Exec("DELETE FROM job_cache WHERE id = ?", id)
+		require.NoError(t, err)
+
+		// Get the new job id in the job table
+		err = r.DB.QueryRow("SELECT id FROM job WHERE job_id = ? AND cluster = ? AND start_time = ?",
+			job.JobID, job.Cluster, job.StartTime).Scan(&id)
+		require.NoError(t, err)
+
+		// Stop the job with different duration
+		err = r.Stop(id, 7200, schema.JobStateCompleted, int32(schema.MonitoringStatusArchivingSuccessful))
+		require.NoError(t, err)
+
+		// Verify the duration was updated correctly
+		var duration int32
+		err = r.DB.QueryRow(`SELECT duration FROM job WHERE id = ?`, id).Scan(&duration)
+		require.NoError(t, err)
+		assert.Equal(t, int32(7200), duration, "Duration should be updated to 7200")
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job WHERE id = ?", id)
+		require.NoError(t, err)
+	})
+
+	t.Run("stop with different states", func(t *testing.T) {
+		testCases := []struct {
+			name             string
+			jobID            int64
+			state            schema.JobState
+			monitoringStatus int32
+		}{
+			{"completed", 999108, schema.JobStateCompleted, int32(schema.MonitoringStatusArchivingSuccessful)},
+			{"failed", 999118, schema.JobStateFailed, int32(schema.MonitoringStatusArchivingSuccessful)},
+			{"cancelled", 999119, schema.JobStateCancelled, int32(schema.MonitoringStatusArchivingSuccessful)},
+			{"timeout", 999120, schema.JobStateTimeout, int32(schema.MonitoringStatusArchivingSuccessful)},
+		}
+
+		for _, tc := range testCases {
+			t.Run(tc.name, func(t *testing.T) {
+				job := createTestJob(tc.jobID, "testcluster")
+				id, err := r.Start(job)
+				require.NoError(t, err)
+
+				// Move to job table
+				_, err = r.DB.Exec(`INSERT INTO job (job_id, cluster, subcluster, submit_time, start_time, hpc_user, project, 
+					cluster_partition, array_job_id, duration, walltime, job_state, meta_data, resources, num_nodes, 
+					num_hwthreads, num_acc, smt, shared, monitoring_status, energy, energy_footprint, footprint) 
+					SELECT job_id, cluster, subcluster, submit_time, start_time, hpc_user, project, 
+					cluster_partition, array_job_id, duration, walltime, job_state, meta_data, resources, num_nodes, 
+					num_hwthreads, num_acc, smt, shared, monitoring_status, energy, energy_footprint, footprint 
+					FROM job_cache WHERE id = ?`, id)
+				require.NoError(t, err)
+				_, err = r.DB.Exec("DELETE FROM job_cache WHERE id = ?", id)
+				require.NoError(t, err)
+
+				// Get the new job id in the job table
+				err = r.DB.QueryRow("SELECT id FROM job WHERE job_id = ? AND cluster = ? AND start_time = ?",
+					job.JobID, job.Cluster, job.StartTime).Scan(&id)
+				require.NoError(t, err)
+
+				// Stop with specific state
+				err = r.Stop(id, 1800, tc.state, tc.monitoringStatus)
+				require.NoError(t, err)
+
+				// Verify state was set correctly
+				var retrievedState string
+				err = r.DB.QueryRow(`SELECT job_state FROM job WHERE id = ?`, id).Scan(&retrievedState)
+				require.NoError(t, err)
+				assert.Equal(t, string(tc.state), retrievedState)
+
+				// Clean up
+				_, err = r.DB.Exec("DELETE FROM job WHERE id = ?", id)
+				require.NoError(t, err)
+			})
+		}
+	})
+}
+
+func TestStopCached(t *testing.T) {
+	r := setup(t)
+
+	t.Run("successful stop cached job", func(t *testing.T) {
+		// Insert a job in job_cache
+		job := createTestJob(999009, "testcluster")
+		id, err := r.Start(job)
+		require.NoError(t, err)
+
+		// Stop the cached job
+		duration := int32(3600)
+		state := schema.JobStateCompleted
+		monitoringStatus := int32(schema.MonitoringStatusArchivingSuccessful)
+
+		err = r.StopCached(id, duration, state, monitoringStatus)
+		require.NoError(t, err, "StopCached should succeed")
+
+		// Verify job was updated in job_cache table
+		var retrievedDuration int32
+		var retrievedState string
+		var retrievedMonStatus int32
+		err = r.DB.QueryRow(`SELECT duration, job_state, monitoring_status FROM job_cache WHERE id = ?`, id).Scan(
+			&retrievedDuration, &retrievedState, &retrievedMonStatus)
+		require.NoError(t, err)
+		assert.Equal(t, duration, retrievedDuration)
+		assert.Equal(t, string(state), retrievedState)
+		assert.Equal(t, monitoringStatus, retrievedMonStatus)
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job_cache WHERE id = ?", id)
+		require.NoError(t, err)
+	})
+
+	t.Run("stop cached job does not affect job table", func(t *testing.T) {
+		// Insert a job in job_cache
+		job := createTestJob(999010, "testcluster")
+		id, err := r.Start(job)
+		require.NoError(t, err)
+
+		// Stop the cached job
+		err = r.StopCached(id, 3600, schema.JobStateCompleted, int32(schema.MonitoringStatusArchivingSuccessful))
+		require.NoError(t, err)
+
+		// Verify job table was not affected
+		var count int
+		err = r.DB.QueryRow(`SELECT COUNT(*) FROM job WHERE job_id = ? AND cluster = ?`,
+			job.JobID, job.Cluster).Scan(&count)
+		require.NoError(t, err)
+		assert.Equal(t, 0, count, "Job table should not be affected by StopCached")
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job_cache WHERE id = ?", id)
+		require.NoError(t, err)
+	})
+}
+
+func TestSyncJobs(t *testing.T) {
+	r := setup(t)
+
+	t.Run("sync jobs from cache to main table", func(t *testing.T) {
+		// Ensure cache is empty first
+		_, err := r.DB.Exec("DELETE FROM job_cache")
+		require.NoError(t, err)
+
+		// Insert multiple jobs in job_cache
+		job1 := createTestJob(999011, "testcluster")
+		job2 := createTestJob(999012, "testcluster")
+		job3 := createTestJob(999013, "testcluster")
+
+		_, err = r.Start(job1)
+		require.NoError(t, err)
+		_, err = r.Start(job2)
+		require.NoError(t, err)
+		_, err = r.Start(job3)
+		require.NoError(t, err)
+
+		// Verify jobs are in job_cache
+		var cacheCount int
+		err = r.DB.QueryRow("SELECT COUNT(*) FROM job_cache WHERE job_id IN (?, ?, ?)",
+			job1.JobID, job2.JobID, job3.JobID).Scan(&cacheCount)
+		require.NoError(t, err)
+		assert.Equal(t, 3, cacheCount, "All jobs should be in job_cache")
+
+		// Sync jobs
+		jobs, err := r.SyncJobs()
+		require.NoError(t, err, "SyncJobs should succeed")
+		assert.Equal(t, 3, len(jobs), "Should return 3 synced jobs")
+
+		// Verify jobs were moved to job table
+		var jobCount int
+		err = r.DB.QueryRow("SELECT COUNT(*) FROM job WHERE job_id IN (?, ?, ?)",
+			job1.JobID, job2.JobID, job3.JobID).Scan(&jobCount)
+		require.NoError(t, err)
+		assert.Equal(t, 3, jobCount, "All jobs should be in job table")
+
+		// Verify job_cache was cleared
+		err = r.DB.QueryRow("SELECT COUNT(*) FROM job_cache WHERE job_id IN (?, ?, ?)",
+			job1.JobID, job2.JobID, job3.JobID).Scan(&cacheCount)
+		require.NoError(t, err)
+		assert.Equal(t, 0, cacheCount, "job_cache should be empty after sync")
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job WHERE job_id IN (?, ?, ?)", job1.JobID, job2.JobID, job3.JobID)
+		require.NoError(t, err)
+	})
+
+	t.Run("sync preserves job data", func(t *testing.T) {
+		// Ensure cache is empty first
+		_, err := r.DB.Exec("DELETE FROM job_cache")
+		require.NoError(t, err)
+
+		// Insert a job with specific data
+		job := createTestJob(999014, "testcluster")
+		job.ArrayJobID = 7777
+		job.Energy = 2500.75
+		job.Duration = 1800
+
+		id, err := r.Start(job)
+		require.NoError(t, err)
+
+		// Update some fields to simulate job progress
+		result, err := r.DB.Exec(`UPDATE job_cache SET duration = ?, energy = ? WHERE id = ?`,
+			3600, 3000.5, id)
+		require.NoError(t, err)
+		rowsAffected, _ := result.RowsAffected()
+		require.Equal(t, int64(1), rowsAffected, "UPDATE should affect exactly 1 row")
+
+		// Verify the update worked
+		var checkDuration int32
+		var checkEnergy float64
+		err = r.DB.QueryRow(`SELECT duration, energy FROM job_cache WHERE id = ?`, id).Scan(&checkDuration, &checkEnergy)
+		require.NoError(t, err)
+		require.Equal(t, int32(3600), checkDuration, "Duration should be updated to 3600 before sync")
+		require.Equal(t, 3000.5, checkEnergy, "Energy should be updated to 3000.5 before sync")
+
+		// Sync jobs
+		jobs, err := r.SyncJobs()
+		require.NoError(t, err)
+		require.Equal(t, 1, len(jobs), "Should return exactly 1 synced job")
+
+		// Verify in database
+		var dbJob schema.Job
+		err = r.DB.QueryRow(`SELECT job_id, hpc_user, project, cluster, array_job_id, duration, energy 
+			FROM job WHERE job_id = ? AND cluster = ?`, job.JobID, job.Cluster).Scan(
+			&dbJob.JobID, &dbJob.User, &dbJob.Project, &dbJob.Cluster,
+			&dbJob.ArrayJobID, &dbJob.Duration, &dbJob.Energy)
+		require.NoError(t, err)
+		assert.Equal(t, job.JobID, dbJob.JobID)
+		assert.Equal(t, int32(3600), dbJob.Duration)
+		assert.Equal(t, 3000.5, dbJob.Energy)
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM job WHERE job_id = ? AND cluster = ?", job.JobID, job.Cluster)
+		require.NoError(t, err)
+	})
+
+	t.Run("sync with empty cache returns empty list", func(t *testing.T) {
+		// Ensure cache is empty
+		_, err := r.DB.Exec("DELETE FROM job_cache")
+		require.NoError(t, err)
+
+		// Sync should return empty list
+		jobs, err := r.SyncJobs()
+		require.NoError(t, err)
+		assert.Equal(t, 0, len(jobs), "Should return empty list when cache is empty")
+	})
+}
diff --git a/internal/repository/jobHooks.go b/internal/repository/jobHooks.go
index c449d308..41684d5c 100644
--- a/internal/repository/jobHooks.go
+++ b/internal/repository/jobHooks.go
@@ -10,8 +10,36 @@ import (
 	"github.com/ClusterCockpit/cc-lib/v2/schema"
 )
 
+// JobHook interface allows external components to hook into job lifecycle events.
+// Implementations can perform actions when jobs start or stop, such as tagging,
+// logging, notifications, or triggering external workflows.
+//
+// Example implementation:
+//
+//	type MyJobTagger struct{}
+//
+//	func (t *MyJobTagger) JobStartCallback(job *schema.Job) {
+//	    if job.NumNodes > 100 {
+//	        // Tag large jobs automatically
+//	    }
+//	}
+//
+//	func (t *MyJobTagger) JobStopCallback(job *schema.Job) {
+//	    if job.State == schema.JobStateFailed {
+//	        // Log or alert on failed jobs
+//	    }
+//	}
+//
+// Register hooks during application initialization:
+//
+//	repository.RegisterJobHook(&MyJobTagger{})
 type JobHook interface {
+	// JobStartCallback is invoked when one or more jobs start.
+	// This is called synchronously, so implementations should be fast.
 	JobStartCallback(job *schema.Job)
+
+	// JobStopCallback is invoked when a job completes.
+	// This is called synchronously, so implementations should be fast.
 	JobStopCallback(job *schema.Job)
 }
 
@@ -20,7 +48,13 @@ var (
 	hooks    []JobHook
 )
 
-func RegisterJobJook(hook JobHook) {
+// RegisterJobHook registers a JobHook to receive job lifecycle callbacks.
+// Multiple hooks can be registered and will be called in registration order.
+// This function is safe to call multiple times and is typically called during
+// application initialization.
+//
+// Nil hooks are silently ignored to simplify conditional registration.
+func RegisterJobHook(hook JobHook) {
 	initOnce.Do(func() {
 		hooks = make([]JobHook, 0)
 	})
@@ -30,6 +64,12 @@ func RegisterJobJook(hook JobHook) {
 	}
 }
 
+// CallJobStartHooks invokes all registered JobHook.JobStartCallback methods
+// for each job in the provided slice. This is called internally by the repository
+// when jobs are started (e.g., via StartJob or batch job imports).
+//
+// Hooks are called synchronously in registration order. If a hook panics,
+// the panic will propagate to the caller.
 func CallJobStartHooks(jobs []*schema.Job) {
 	if hooks == nil {
 		return
@@ -44,6 +84,12 @@ func CallJobStartHooks(jobs []*schema.Job) {
 	}
 }
 
+// CallJobStopHooks invokes all registered JobHook.JobStopCallback methods
+// for the provided job. This is called internally by the repository when a
+// job completes (e.g., via StopJob or job state updates).
+//
+// Hooks are called synchronously in registration order. If a hook panics,
+// the panic will propagate to the caller.
 func CallJobStopHooks(job *schema.Job) {
 	if hooks == nil {
 		return
diff --git a/internal/repository/migration.go b/internal/repository/migration.go
index a47f9fcd..0f99889e 100644
--- a/internal/repository/migration.go
+++ b/internal/repository/migration.go
@@ -16,11 +16,29 @@ import (
 	"github.com/golang-migrate/migrate/v4/source/iofs"
 )
 
+// Version is the current database schema version required by this version of cc-backend.
+// When the database schema changes, this version is incremented and a new migration file
+// is added to internal/repository/migrations/sqlite3/.
+//
+// Version history:
+//   - Version 10: Current version
+//
+// Migration files are embedded at build time from the migrations directory.
 const Version uint = 10
 
 //go:embed migrations/*
 var migrationFiles embed.FS
 
+// checkDBVersion verifies that the database schema version matches the expected version.
+// This is called automatically during Connect() to ensure schema compatibility.
+//
+// Returns an error if:
+//   - Database version is older than expected (needs migration)
+//   - Database version is newer than expected (needs app upgrade)
+//   - Database is in a dirty state (failed migration)
+//
+// A "dirty" database indicates a migration was started but not completed successfully.
+// This requires manual intervention to fix the database and force the version.
 func checkDBVersion(db *sql.DB) error {
 	driver, err := sqlite3.WithInstance(db, &sqlite3.Config{})
 	if err != nil {
@@ -58,6 +76,8 @@ func checkDBVersion(db *sql.DB) error {
 	return nil
 }
 
+// getMigrateInstance creates a new migration instance for the given database file.
+// This is used internally by MigrateDB, RevertDB, and ForceDB.
 func getMigrateInstance(db string) (m *migrate.Migrate, err error) {
 	d, err := iofs.New(migrationFiles, "migrations/sqlite3")
 	if err != nil {
@@ -72,6 +92,23 @@ func getMigrateInstance(db string) (m *migrate.Migrate, err error) {
 	return m, nil
 }
 
+// MigrateDB applies all pending database migrations to bring the schema up to date.
+// This should be run with the -migrate-db flag before starting the application
+// after upgrading to a new version that requires schema changes.
+//
+// Process:
+//  1. Checks current database version
+//  2. Applies all migrations from current version to target Version
+//  3. Updates schema_migrations table to track applied migrations
+//
+// Important:
+//   - Always backup your database before running migrations
+//   - Migrations are irreversible without manual intervention
+//   - If a migration fails, the database is marked "dirty" and requires manual fix
+//
+// Usage:
+//
+//	cc-backend -migrate-db
 func MigrateDB(db string) error {
 	m, err := getMigrateInstance(db)
 	if err != nil {
@@ -107,6 +144,17 @@ func MigrateDB(db string) error {
 	return nil
 }
 
+// RevertDB rolls back the database schema to the previous version (Version - 1).
+// This is primarily used for testing or emergency rollback scenarios.
+//
+// Warning:
+//   - This may cause data loss if newer schema added columns/tables
+//   - Always backup before reverting
+//   - Not all migrations are safely reversible
+//
+// Usage:
+//
+//	cc-backend -revert-db
 func RevertDB(db string) error {
 	m, err := getMigrateInstance(db)
 	if err != nil {
@@ -125,6 +173,21 @@ func RevertDB(db string) error {
 	return nil
 }
 
+// ForceDB forces the database schema version to the current Version without running migrations.
+// This is only used to recover from failed migrations that left the database in a "dirty" state.
+//
+// When to use:
+//   - After manually fixing a failed migration
+//   - When you've manually applied schema changes and need to update the version marker
+//
+// Warning:
+//   - This does NOT apply any schema changes
+//   - Only use after manually verifying the schema is correct
+//   - Improper use can cause schema/version mismatch
+//
+// Usage:
+//
+//	cc-backend -force-db
 func ForceDB(db string) error {
 	m, err := getMigrateInstance(db)
 	if err != nil {
diff --git a/internal/repository/stats.go b/internal/repository/stats.go
index 989026d1..cd175c23 100644
--- a/internal/repository/stats.go
+++ b/internal/repository/stats.go
@@ -277,6 +277,15 @@ func (r *JobRepository) JobsStats(
 	return stats, nil
 }
 
+// LoadJobStat retrieves a specific statistic for a metric from a job's statistics.
+// Returns 0.0 if the metric is not found or statType is invalid.
+//
+// Parameters:
+//   - job: Job struct with populated Statistics field
+//   - metric: Name of the metric to query (e.g., "cpu_load", "mem_used")
+//   - statType: Type of statistic: "avg", "min", or "max"
+//
+// Returns the requested statistic value or 0.0 if not found.
 func LoadJobStat(job *schema.Job, metric string, statType string) float64 {
 	if stats, ok := job.Statistics[metric]; ok {
 		switch statType {
@@ -579,7 +588,9 @@ func (r *JobRepository) jobsDurationStatisticsHistogram(
 		return nil, qerr
 	}
 
-	// Setup Array
+	// Initialize histogram bins with zero counts
+	// Each bin represents a duration range: bin N = [N*binSizeSeconds, (N+1)*binSizeSeconds)
+	// Example: binSizeSeconds=3600 (1 hour), bin 1 = 0-1h, bin 2 = 1-2h, etc.
 	points := make([]*model.HistoPoint, 0)
 	for i := 1; i <= *targetBinCount; i++ {
 		point := model.HistoPoint{Value: i * binSizeSeconds, Count: 0}
@@ -596,7 +607,8 @@ func (r *JobRepository) jobsDurationStatisticsHistogram(
 		return nil, err
 	}
 
-	// Fill Array at matching $Value
+	// Match query results to pre-initialized bins and fill counts
+	// Query returns raw duration values that need to be mapped to correct bins
 	for rows.Next() {
 		point := model.HistoPoint{}
 		if err := rows.Scan(&point.Value, &point.Count); err != nil {
@@ -604,11 +616,13 @@ func (r *JobRepository) jobsDurationStatisticsHistogram(
 			return nil, err
 		}
 
+		// Find matching bin and update count
+		// point.Value is multiplied by binSizeSeconds to match pre-calculated bin.Value
 		for _, e := range points {
 			if e.Value == (point.Value * binSizeSeconds) {
-				// Note:
-				//  Matching on unmodified integer value (and multiplying point.Value by binSizeSeconds after match)
-				//  causes frontend to loop into highest targetBinCount, due to zoom condition instantly being fullfilled (cause unknown)
+				// Note: Matching on unmodified integer value (and multiplying point.Value
+				// by binSizeSeconds after match) causes frontend to loop into highest
+				// targetBinCount, due to zoom condition instantly being fulfilled (cause unknown)
 				e.Count = point.Count
 				break
 			}
@@ -625,12 +639,16 @@ func (r *JobRepository) jobsMetricStatisticsHistogram(
 	filters []*model.JobFilter,
 	bins *int,
 ) (*model.MetricHistoPoints, error) {
-	// Get specific Peak or largest Peak
+	// Determine the metric's peak value for histogram normalization
+	// Peak value defines the upper bound for binning: values are distributed across
+	// bins from 0 to peak. First try to get peak from filtered cluster, otherwise
+	// scan all clusters to find the maximum peak value.
 	var metricConfig *schema.MetricConfig
 	var peak float64
 	var unit string
 	var footprintStat string
 
+	// Try to get metric config from filtered cluster
 	for _, f := range filters {
 		if f.Cluster != nil {
 			metricConfig = archive.GetMetricConfig(*f.Cluster.Eq, metric)
@@ -641,6 +659,8 @@ func (r *JobRepository) jobsMetricStatisticsHistogram(
 		}
 	}
 
+	// If no cluster filter or peak not found, find largest peak across all clusters
+	// This ensures histogram can accommodate all possible values
 	if peak == 0.0 {
 		for _, c := range archive.Clusters {
 			for _, m := range c.MetricConfig {
@@ -659,11 +679,18 @@ func (r *JobRepository) jobsMetricStatisticsHistogram(
 		}
 	}
 
-	// cclog.Debugf("Metric %s, Peak %f, Unit %s", metric, peak, unit)
-	// Make bins, see https://jereze.com/code/sql-histogram/ (Modified here)
+	// Construct SQL histogram bins using normalized values
+	// Algorithm based on: https://jereze.com/code/sql-histogram/ (modified)
 	start := time.Now()
 
-	// Find Jobs' Value Bin Number: Divide Value by Peak, Multiply by RequestedBins, then CAST to INT: Gets Bin-Number of Job
+	// Calculate bin number for each job's metric value:
+	// 1. Extract metric value from JSON footprint
+	// 2. Normalize to [0,1] by dividing by peak
+	// 3. Multiply by number of bins to get bin number
+	// 4. Cast to integer for bin assignment
+	//
+	// Special case: Values exactly equal to peak would fall into bin N+1,
+	// so we multiply peak by 0.999999999 to force it into the last bin (bin N)
 	binQuery := fmt.Sprintf(`CAST(
 		((case when json_extract(footprint, "$.%s") = %f then %f*0.999999999 else json_extract(footprint, "$.%s") end) / %f)
 		* %v as INTEGER )`,
@@ -698,7 +725,9 @@ func (r *JobRepository) jobsMetricStatisticsHistogram(
 		return nil, err
 	}
 
-	// Setup Return Array With Bin-Numbers for Match and Min/Max based on Peak
+	// Initialize histogram bins with calculated min/max ranges
+	// Each bin represents a range of metric values
+	// Example: peak=1000, bins=10 -> bin 1=[0,100), bin 2=[100,200), ..., bin 10=[900,1000]
 	points := make([]*model.MetricHistoPoint, 0)
 	binStep := int(peak) / *bins
 	for i := 1; i <= *bins; i++ {
@@ -708,13 +737,16 @@ func (r *JobRepository) jobsMetricStatisticsHistogram(
 		points = append(points, &epoint)
 	}
 
-	for rows.Next() { // Fill Count if Bin-No. Matches (Not every Bin exists in DB!)
+	// Fill counts from query results
+	// Query only returns bins that have jobs, so we match against pre-initialized bins
+	for rows.Next() {
 		rpoint := model.MetricHistoPoint{}
 		if err := rows.Scan(&rpoint.Bin, &rpoint.Count); err != nil { // Required for Debug: &rpoint.Min, &rpoint.Max
 			cclog.Warnf("Error while scanning rows for %s", metric)
 			return nil, err // FIXME: Totally bricks cc-backend if returned and if all metrics requested?
 		}
 
+		// Match query result to pre-initialized bin and update count
 		for _, e := range points {
 			if e.Bin != nil && rpoint.Bin != nil {
 				if *e.Bin == *rpoint.Bin {
diff --git a/internal/repository/stats_test.go b/internal/repository/stats_test.go
index e10c9685..a8dfc818 100644
--- a/internal/repository/stats_test.go
+++ b/internal/repository/stats_test.go
@@ -25,11 +25,20 @@ func TestBuildJobStatsQuery(t *testing.T) {
 func TestJobStats(t *testing.T) {
 	r := setup(t)
 
+	// First, count the actual jobs in the database (excluding test jobs)
+	var expectedCount int
+	err := r.DB.QueryRow(`SELECT COUNT(*) FROM job WHERE cluster != 'testcluster'`).Scan(&expectedCount)
+	noErr(t, err)
+
 	filter := &model.JobFilter{}
+	// Exclude test jobs created by other tests
+	testCluster := "testcluster"
+	filter.Cluster = &model.StringInput{Neq: &testCluster}
+
 	stats, err := r.JobsStats(getContext(t), []*model.JobFilter{filter})
 	noErr(t, err)
 
-	if stats[0].TotalJobs != 544 {
-		t.Fatalf("Want 544, Got %d", stats[0].TotalJobs)
+	if stats[0].TotalJobs != expectedCount {
+		t.Fatalf("Want %d, Got %d", expectedCount, stats[0].TotalJobs)
 	}
 }
diff --git a/internal/repository/tags.go b/internal/repository/tags.go
index 9bc9abae..f6cccfe2 100644
--- a/internal/repository/tags.go
+++ b/internal/repository/tags.go
@@ -16,8 +16,32 @@ import (
 	sq "github.com/Masterminds/squirrel"
 )
 
+// Tag Scope Rules:
+//
+// Tags in ClusterCockpit have three visibility scopes that control who can see and use them:
+//
+//  1. "global" - Visible to all users, can be used by anyone
+//     Example: System-generated tags like "energy-efficient", "failed", "short"
+//
+//  2. "private" - Only visible to the creating user
+//     Example: Personal notes like "needs-review", "interesting-case"
+//
+//  3. "admin" - Only visible to users with admin or support roles
+//     Example: Internal notes like "hardware-issue", "billing-problem"
+//
+// Authorization Rules:
+//   - Regular users can only create/see "global" and their own "private" tags
+//   - Admin/Support can create/see all scopes including "admin" tags
+//   - Users can only add tags to jobs they have permission to view
+//   - Tag scope is enforced at query time in GetTags() and CountTags()
+
 // AddTag adds the tag with id `tagId` to the job with the database id `jobId`.
 // Requires user authentication for security checks.
+//
+// The user must have permission to view the job. Tag visibility is determined by scope:
+//   - "global" tags: visible to all users
+//   - "private" tags: only visible to the tag creator
+//   - "admin" tags: only visible to admin/support users
 func (r *JobRepository) AddTag(user *schema.User, job int64, tag int64) ([]*schema.Tag, error) {
 	j, err := r.FindByIDWithUser(user, job)
 	if err != nil {
@@ -180,7 +204,15 @@ func (r *JobRepository) RemoveTagById(tagID int64) error {
 	return nil
 }
 
-// CreateTag creates a new tag with the specified type and name and returns its database id.
+// CreateTag creates a new tag with the specified type, name, and scope.
+// Returns the database ID of the newly created tag.
+//
+// Scope defaults to "global" if empty string is provided.
+// Valid scopes: "global", "private", "admin"
+//
+// Example:
+//
+//	tagID, err := repo.CreateTag("performance", "high-memory", "global")
 func (r *JobRepository) CreateTag(tagType string, tagName string, tagScope string) (tagId int64, err error) {
 	// Default to "Global" scope if none defined
 	if tagScope == "" {
@@ -199,8 +231,14 @@ func (r *JobRepository) CreateTag(tagType string, tagName string, tagScope strin
 	return res.LastInsertId()
 }
 
+// CountTags returns all tags visible to the user and the count of jobs for each tag.
+// Applies scope-based filtering to respect tag visibility rules.
+//
+// Returns:
+//   - tags: slice of tags the user can see
+//   - counts: map of tag name to job count
+//   - err: any error encountered
 func (r *JobRepository) CountTags(user *schema.User) (tags []schema.Tag, counts map[string]int, err error) {
-	// Fetch all Tags in DB for Display in Frontend Tag-View
 	tags = make([]schema.Tag, 0, 100)
 	xrows, err := r.DB.Queryx("SELECT id, tag_type, tag_name, tag_scope FROM tag")
 	if err != nil {
diff --git a/internal/repository/transaction_test.go b/internal/repository/transaction_test.go
new file mode 100644
index 00000000..1832bea0
--- /dev/null
+++ b/internal/repository/transaction_test.go
@@ -0,0 +1,311 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+package repository
+
+import (
+	"testing"
+
+	_ "github.com/mattn/go-sqlite3"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestTransactionInit(t *testing.T) {
+	r := setup(t)
+
+	t.Run("successful transaction init", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err, "TransactionInit should succeed")
+		require.NotNil(t, tx, "Transaction should not be nil")
+		require.NotNil(t, tx.tx, "Transaction.tx should not be nil")
+
+		// Clean up
+		err = tx.Rollback()
+		require.NoError(t, err, "Rollback should succeed")
+	})
+}
+
+func TestTransactionCommit(t *testing.T) {
+	r := setup(t)
+
+	t.Run("commit after successful operations", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+
+		// Insert a test tag
+		_, err = r.TransactionAdd(tx, "INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (?, ?, ?)",
+			"test_type", "test_tag_commit", "global")
+		require.NoError(t, err, "TransactionAdd should succeed")
+
+		// Commit the transaction
+		err = tx.Commit()
+		require.NoError(t, err, "Commit should succeed")
+
+		// Verify the tag was inserted
+		var count int
+		err = r.DB.QueryRow("SELECT COUNT(*) FROM tag WHERE tag_name = ?", "test_tag_commit").Scan(&count)
+		require.NoError(t, err)
+		assert.Equal(t, 1, count, "Tag should be committed to database")
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM tag WHERE tag_name = ?", "test_tag_commit")
+		require.NoError(t, err)
+	})
+
+	t.Run("commit on already committed transaction", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+
+		err = tx.Commit()
+		require.NoError(t, err, "First commit should succeed")
+
+		err = tx.Commit()
+		assert.Error(t, err, "Second commit should fail")
+		assert.Contains(t, err.Error(), "transaction already committed or rolled back")
+	})
+}
+
+func TestTransactionRollback(t *testing.T) {
+	r := setup(t)
+
+	t.Run("rollback after operations", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+
+		// Insert a test tag
+		_, err = r.TransactionAdd(tx, "INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (?, ?, ?)",
+			"test_type", "test_tag_rollback", "global")
+		require.NoError(t, err, "TransactionAdd should succeed")
+
+		// Rollback the transaction
+		err = tx.Rollback()
+		require.NoError(t, err, "Rollback should succeed")
+
+		// Verify the tag was NOT inserted
+		var count int
+		err = r.DB.QueryRow("SELECT COUNT(*) FROM tag WHERE tag_name = ?", "test_tag_rollback").Scan(&count)
+		require.NoError(t, err)
+		assert.Equal(t, 0, count, "Tag should not be in database after rollback")
+	})
+
+	t.Run("rollback on already rolled back transaction", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+
+		err = tx.Rollback()
+		require.NoError(t, err, "First rollback should succeed")
+
+		err = tx.Rollback()
+		assert.NoError(t, err, "Second rollback should be safe (no-op)")
+	})
+
+	t.Run("rollback on committed transaction", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+
+		err = tx.Commit()
+		require.NoError(t, err)
+
+		err = tx.Rollback()
+		assert.NoError(t, err, "Rollback after commit should be safe (no-op)")
+	})
+}
+
+func TestTransactionAdd(t *testing.T) {
+	r := setup(t)
+
+	t.Run("insert with TransactionAdd", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+		defer tx.Rollback()
+
+		id, err := r.TransactionAdd(tx, "INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (?, ?, ?)",
+			"test_type", "test_add", "global")
+		require.NoError(t, err, "TransactionAdd should succeed")
+		assert.Greater(t, id, int64(0), "Should return valid insert ID")
+	})
+
+	t.Run("error on nil transaction", func(t *testing.T) {
+		tx := &Transaction{tx: nil}
+
+		_, err := r.TransactionAdd(tx, "INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (?, ?, ?)",
+			"test_type", "test_nil", "global")
+		assert.Error(t, err, "Should error on nil transaction")
+		assert.Contains(t, err.Error(), "transaction is nil or already completed")
+	})
+
+	t.Run("error on invalid SQL", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+		defer tx.Rollback()
+
+		_, err = r.TransactionAdd(tx, "INVALID SQL STATEMENT")
+		assert.Error(t, err, "Should error on invalid SQL")
+	})
+
+	t.Run("error after transaction committed", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+
+		err = tx.Commit()
+		require.NoError(t, err)
+
+		_, err = r.TransactionAdd(tx, "INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (?, ?, ?)",
+			"test_type", "test_after_commit", "global")
+		assert.Error(t, err, "Should error when transaction is already committed")
+	})
+}
+
+func TestTransactionAddNamed(t *testing.T) {
+	r := setup(t)
+
+	t.Run("insert with TransactionAddNamed", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+		defer tx.Rollback()
+
+		type TagArgs struct {
+			Type  string `db:"type"`
+			Name  string `db:"name"`
+			Scope string `db:"scope"`
+		}
+
+		args := TagArgs{
+			Type:  "test_type",
+			Name:  "test_named",
+			Scope: "global",
+		}
+
+		id, err := r.TransactionAddNamed(tx,
+			"INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (:type, :name, :scope)",
+			args)
+		require.NoError(t, err, "TransactionAddNamed should succeed")
+		assert.Greater(t, id, int64(0), "Should return valid insert ID")
+	})
+
+	t.Run("error on nil transaction", func(t *testing.T) {
+		tx := &Transaction{tx: nil}
+
+		_, err := r.TransactionAddNamed(tx, "INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (:type, :name, :scope)",
+			map[string]interface{}{"type": "test", "name": "test", "scope": "global"})
+		assert.Error(t, err, "Should error on nil transaction")
+		assert.Contains(t, err.Error(), "transaction is nil or already completed")
+	})
+}
+
+func TestTransactionMultipleOperations(t *testing.T) {
+	r := setup(t)
+
+	t.Run("multiple inserts in single transaction", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+		defer tx.Rollback()
+
+		// Insert multiple tags
+		for i := 0; i < 5; i++ {
+			_, err = r.TransactionAdd(tx,
+				"INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (?, ?, ?)",
+				"test_type", "test_multi_"+string(rune('a'+i)), "global")
+			require.NoError(t, err, "Insert %d should succeed", i)
+		}
+
+		err = tx.Commit()
+		require.NoError(t, err, "Commit should succeed")
+
+		// Verify all tags were inserted
+		var count int
+		err = r.DB.QueryRow("SELECT COUNT(*) FROM tag WHERE tag_name LIKE 'test_multi_%'").Scan(&count)
+		require.NoError(t, err)
+		assert.Equal(t, 5, count, "All 5 tags should be committed")
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM tag WHERE tag_name LIKE 'test_multi_%'")
+		require.NoError(t, err)
+	})
+
+	t.Run("rollback undoes all operations", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+
+		// Insert multiple tags
+		for i := 0; i < 3; i++ {
+			_, err = r.TransactionAdd(tx,
+				"INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (?, ?, ?)",
+				"test_type", "test_rollback_"+string(rune('a'+i)), "global")
+			require.NoError(t, err)
+		}
+
+		err = tx.Rollback()
+		require.NoError(t, err, "Rollback should succeed")
+
+		// Verify no tags were inserted
+		var count int
+		err = r.DB.QueryRow("SELECT COUNT(*) FROM tag WHERE tag_name LIKE 'test_rollback_%'").Scan(&count)
+		require.NoError(t, err)
+		assert.Equal(t, 0, count, "No tags should be in database after rollback")
+	})
+}
+
+func TestTransactionEnd(t *testing.T) {
+	r := setup(t)
+
+	t.Run("deprecated TransactionEnd calls Commit", func(t *testing.T) {
+		tx, err := r.TransactionInit()
+		require.NoError(t, err)
+
+		_, err = r.TransactionAdd(tx, "INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (?, ?, ?)",
+			"test_type", "test_end", "global")
+		require.NoError(t, err)
+
+		// Use deprecated method
+		err = r.TransactionEnd(tx)
+		require.NoError(t, err, "TransactionEnd should succeed")
+
+		// Verify the tag was committed
+		var count int
+		err = r.DB.QueryRow("SELECT COUNT(*) FROM tag WHERE tag_name = ?", "test_end").Scan(&count)
+		require.NoError(t, err)
+		assert.Equal(t, 1, count, "Tag should be committed")
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM tag WHERE tag_name = ?", "test_end")
+		require.NoError(t, err)
+	})
+}
+
+func TestTransactionDeferPattern(t *testing.T) {
+	r := setup(t)
+
+	t.Run("defer rollback pattern", func(t *testing.T) {
+		insertTag := func() error {
+			tx, err := r.TransactionInit()
+			if err != nil {
+				return err
+			}
+			defer tx.Rollback() // Safe to call even after commit
+
+			_, err = r.TransactionAdd(tx, "INSERT INTO tag (tag_type, tag_name, tag_scope) VALUES (?, ?, ?)",
+				"test_type", "test_defer", "global")
+			if err != nil {
+				return err
+			}
+
+			return tx.Commit()
+		}
+
+		err := insertTag()
+		require.NoError(t, err, "Function should succeed")
+
+		// Verify the tag was committed
+		var count int
+		err = r.DB.QueryRow("SELECT COUNT(*) FROM tag WHERE tag_name = ?", "test_defer").Scan(&count)
+		require.NoError(t, err)
+		assert.Equal(t, 1, count, "Tag should be committed despite defer rollback")
+
+		// Clean up
+		_, err = r.DB.Exec("DELETE FROM tag WHERE tag_name = ?", "test_defer")
+		require.NoError(t, err)
+	})
+}
diff --git a/internal/repository/user.go b/internal/repository/user.go
index 770915b6..42a22384 100644
--- a/internal/repository/user.go
+++ b/internal/repository/user.go
@@ -22,6 +22,25 @@ import (
 	"golang.org/x/crypto/bcrypt"
 )
 
+// Authentication and Role System:
+//
+// ClusterCockpit supports multiple authentication sources:
+//   - Local: Username/password stored in database (password hashed with bcrypt)
+//   - LDAP: External LDAP/Active Directory authentication
+//   - JWT: Token-based authentication for API access
+//
+// Role Hierarchy (from highest to lowest privilege):
+//   1. "admin" - Full system access, can manage all users and jobs
+//   2. "support" - Can view all jobs but limited management capabilities
+//   3. "manager" - Can manage specific projects and their users
+//   4. "api" - Programmatic access for job submission/management
+//   5. "user" - Default role, can only view own jobs
+//
+// Project Association:
+//   - Managers have a list of projects they oversee
+//   - Regular users' project membership is determined by job data
+//   - Managers can view/manage all jobs within their projects
+
 var (
 	userRepoOnce     sync.Once
 	userRepoInstance *UserRepository
@@ -44,6 +63,9 @@ func GetUserRepository() *UserRepository {
 	return userRepoInstance
 }
 
+// GetUser retrieves a user by username from the database.
+// Returns the complete user record including hashed password, roles, and projects.
+// Password field contains bcrypt hash for local auth users, empty for LDAP users.
 func (r *UserRepository) GetUser(username string) (*schema.User, error) {
 	user := &schema.User{Username: username}
 	var hashedPassword, name, rawRoles, email, rawProjects sql.NullString
@@ -93,6 +115,12 @@ func (r *UserRepository) GetLdapUsernames() ([]string, error) {
 	return users, nil
 }
 
+// AddUser creates a new user in the database.
+// Passwords are automatically hashed with bcrypt before storage.
+// Auth source determines authentication method (local, LDAP, etc.).
+//
+// Required fields: Username, Roles
+// Optional fields: Name, Email, Password, Projects, AuthSource
 func (r *UserRepository) AddUser(user *schema.User) error {
 	rolesJson, _ := json.Marshal(user.Roles)
 	projectsJson, _ := json.Marshal(user.Projects)
@@ -229,6 +257,14 @@ func (r *UserRepository) ListUsers(specialsOnly bool) ([]*schema.User, error) {
 	return users, nil
 }
 
+// AddRole adds a role to a user's role list.
+// Role string is automatically lowercased.
+// Valid roles: admin, support, manager, api, user
+//
+// Returns error if:
+//   - User doesn't exist
+//   - Role is invalid
+//   - User already has the role
 func (r *UserRepository) AddRole(
 	ctx context.Context,
 	username string,
@@ -258,6 +294,11 @@ func (r *UserRepository) AddRole(
 	return nil
 }
 
+// RemoveRole removes a role from a user's role list.
+//
+// Special rules:
+//   - Cannot remove "manager" role while user has assigned projects
+//   - Must remove all projects first before removing manager role
 func (r *UserRepository) RemoveRole(ctx context.Context, username string, queryrole string) error {
 	oldRole := strings.ToLower(queryrole)
 	user, err := r.GetUser(username)
@@ -294,6 +335,12 @@ func (r *UserRepository) RemoveRole(ctx context.Context, username string, queryr
 	return nil
 }
 
+// AddProject assigns a project to a manager user.
+// Only users with the "manager" role can have assigned projects.
+//
+// Returns error if:
+//   - User doesn't have manager role
+//   - User already manages the project
 func (r *UserRepository) AddProject(
 	ctx context.Context,
 	username string,
diff --git a/internal/repository/user_test.go b/internal/repository/user_test.go
new file mode 100644
index 00000000..370d261d
--- /dev/null
+++ b/internal/repository/user_test.go
@@ -0,0 +1,596 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+package repository
+
+import (
+	"context"
+	"testing"
+
+	"github.com/ClusterCockpit/cc-lib/v2/schema"
+	_ "github.com/mattn/go-sqlite3"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"golang.org/x/crypto/bcrypt"
+)
+
+func TestAddUser(t *testing.T) {
+	_ = setup(t)
+	r := GetUserRepository()
+
+	t.Run("add user with all fields", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "testuser1",
+			Name:       "Test User One",
+			Email:      "test1@example.com",
+			Password:   "testpassword123",
+			Roles:      []string{"user"},
+			Projects:   []string{"project1", "project2"},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		retrievedUser, err := r.GetUser("testuser1")
+		require.NoError(t, err)
+		assert.Equal(t, user.Username, retrievedUser.Username)
+		assert.Equal(t, user.Name, retrievedUser.Name)
+		assert.Equal(t, user.Email, retrievedUser.Email)
+		assert.Equal(t, user.Roles, retrievedUser.Roles)
+		assert.Equal(t, user.Projects, retrievedUser.Projects)
+		assert.NotEmpty(t, retrievedUser.Password)
+		err = bcrypt.CompareHashAndPassword([]byte(retrievedUser.Password), []byte("testpassword123"))
+		assert.NoError(t, err, "Password should be hashed correctly")
+
+		err = r.DelUser("testuser1")
+		require.NoError(t, err)
+	})
+
+	t.Run("add user with minimal fields", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "testuser2",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLDAP,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		retrievedUser, err := r.GetUser("testuser2")
+		require.NoError(t, err)
+		assert.Equal(t, user.Username, retrievedUser.Username)
+		assert.Equal(t, "", retrievedUser.Name)
+		assert.Equal(t, "", retrievedUser.Email)
+		assert.Equal(t, "", retrievedUser.Password)
+
+		err = r.DelUser("testuser2")
+		require.NoError(t, err)
+	})
+
+	t.Run("add duplicate user fails", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "testuser3",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.AddUser(user)
+		assert.Error(t, err, "Adding duplicate user should fail")
+
+		err = r.DelUser("testuser3")
+		require.NoError(t, err)
+	})
+}
+
+func TestGetUser(t *testing.T) {
+	_ = setup(t)
+	r := GetUserRepository()
+
+	t.Run("get existing user", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "getuser1",
+			Name:       "Get User",
+			Email:      "getuser@example.com",
+			Roles:      []string{"user", "admin"},
+			Projects:   []string{"proj1"},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		retrieved, err := r.GetUser("getuser1")
+		require.NoError(t, err)
+		assert.Equal(t, user.Username, retrieved.Username)
+		assert.Equal(t, user.Name, retrieved.Name)
+		assert.Equal(t, user.Email, retrieved.Email)
+		assert.ElementsMatch(t, user.Roles, retrieved.Roles)
+		assert.ElementsMatch(t, user.Projects, retrieved.Projects)
+
+		err = r.DelUser("getuser1")
+		require.NoError(t, err)
+	})
+
+	t.Run("get non-existent user", func(t *testing.T) {
+		_, err := r.GetUser("nonexistent")
+		assert.Error(t, err)
+	})
+}
+
+func TestUpdateUser(t *testing.T) {
+	_ = setup(t)
+	r := GetUserRepository()
+
+	t.Run("update user name", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "updateuser1",
+			Name:       "Original Name",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		dbUser, err := r.GetUser("updateuser1")
+		require.NoError(t, err)
+
+		updatedUser := &schema.User{
+			Username: "updateuser1",
+			Name:     "Updated Name",
+		}
+
+		err = r.UpdateUser(dbUser, updatedUser)
+		require.NoError(t, err)
+
+		retrieved, err := r.GetUser("updateuser1")
+		require.NoError(t, err)
+		assert.Equal(t, "Updated Name", retrieved.Name)
+
+		err = r.DelUser("updateuser1")
+		require.NoError(t, err)
+	})
+
+	t.Run("update with no changes", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "updateuser2",
+			Name:       "Same Name",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		dbUser, err := r.GetUser("updateuser2")
+		require.NoError(t, err)
+
+		err = r.UpdateUser(dbUser, dbUser)
+		assert.NoError(t, err)
+
+		err = r.DelUser("updateuser2")
+		require.NoError(t, err)
+	})
+}
+
+func TestDelUser(t *testing.T) {
+	_ = setup(t)
+	r := GetUserRepository()
+
+	t.Run("delete existing user", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "deluser1",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.DelUser("deluser1")
+		require.NoError(t, err)
+
+		_, err = r.GetUser("deluser1")
+		assert.Error(t, err, "User should not exist after deletion")
+	})
+
+	t.Run("delete non-existent user", func(t *testing.T) {
+		err := r.DelUser("nonexistent")
+		assert.NoError(t, err, "Deleting non-existent user should not error")
+	})
+}
+
+func TestListUsers(t *testing.T) {
+	_ = setup(t)
+	r := GetUserRepository()
+
+	user1 := &schema.User{
+		Username:   "listuser1",
+		Roles:      []string{"user"},
+		Projects:   []string{},
+		AuthSource: schema.AuthViaLocalPassword,
+	}
+	user2 := &schema.User{
+		Username:   "listuser2",
+		Roles:      []string{"admin"},
+		Projects:   []string{},
+		AuthSource: schema.AuthViaLocalPassword,
+	}
+	user3 := &schema.User{
+		Username:   "listuser3",
+		Roles:      []string{"manager"},
+		Projects:   []string{"proj1"},
+		AuthSource: schema.AuthViaLocalPassword,
+	}
+
+	err := r.AddUser(user1)
+	require.NoError(t, err)
+	err = r.AddUser(user2)
+	require.NoError(t, err)
+	err = r.AddUser(user3)
+	require.NoError(t, err)
+
+	t.Run("list all users", func(t *testing.T) {
+		users, err := r.ListUsers(false)
+		require.NoError(t, err)
+		assert.GreaterOrEqual(t, len(users), 3)
+
+		usernames := make([]string, len(users))
+		for i, u := range users {
+			usernames[i] = u.Username
+		}
+		assert.Contains(t, usernames, "listuser1")
+		assert.Contains(t, usernames, "listuser2")
+		assert.Contains(t, usernames, "listuser3")
+	})
+
+	t.Run("list special users only", func(t *testing.T) {
+		users, err := r.ListUsers(true)
+		require.NoError(t, err)
+
+		usernames := make([]string, len(users))
+		for i, u := range users {
+			usernames[i] = u.Username
+		}
+		assert.Contains(t, usernames, "listuser2")
+		assert.Contains(t, usernames, "listuser3")
+	})
+
+	err = r.DelUser("listuser1")
+	require.NoError(t, err)
+	err = r.DelUser("listuser2")
+	require.NoError(t, err)
+	err = r.DelUser("listuser3")
+	require.NoError(t, err)
+}
+
+func TestGetLdapUsernames(t *testing.T) {
+	_ = setup(t)
+	r := GetUserRepository()
+
+	ldapUser := &schema.User{
+		Username:   "ldapuser1",
+		Roles:      []string{"user"},
+		Projects:   []string{},
+		AuthSource: schema.AuthViaLDAP,
+	}
+	localUser := &schema.User{
+		Username:   "localuser1",
+		Roles:      []string{"user"},
+		Projects:   []string{},
+		AuthSource: schema.AuthViaLocalPassword,
+	}
+
+	err := r.AddUser(ldapUser)
+	require.NoError(t, err)
+	err = r.AddUser(localUser)
+	require.NoError(t, err)
+
+	usernames, err := r.GetLdapUsernames()
+	require.NoError(t, err)
+	assert.Contains(t, usernames, "ldapuser1")
+	assert.NotContains(t, usernames, "localuser1")
+
+	err = r.DelUser("ldapuser1")
+	require.NoError(t, err)
+	err = r.DelUser("localuser1")
+	require.NoError(t, err)
+}
+
+func TestAddRole(t *testing.T) {
+	_ = setup(t)
+	r := GetUserRepository()
+	ctx := context.Background()
+
+	t.Run("add valid role", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "roleuser1",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.AddRole(ctx, "roleuser1", "admin")
+		require.NoError(t, err)
+
+		retrieved, err := r.GetUser("roleuser1")
+		require.NoError(t, err)
+		assert.Contains(t, retrieved.Roles, "admin")
+		assert.Contains(t, retrieved.Roles, "user")
+
+		err = r.DelUser("roleuser1")
+		require.NoError(t, err)
+	})
+
+	t.Run("add duplicate role", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "roleuser2",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.AddRole(ctx, "roleuser2", "user")
+		assert.Error(t, err, "Adding duplicate role should fail")
+		assert.Contains(t, err.Error(), "already has role")
+
+		err = r.DelUser("roleuser2")
+		require.NoError(t, err)
+	})
+
+	t.Run("add invalid role", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "roleuser3",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.AddRole(ctx, "roleuser3", "invalidrole")
+		assert.Error(t, err, "Adding invalid role should fail")
+		assert.Contains(t, err.Error(), "no valid option")
+
+		err = r.DelUser("roleuser3")
+		require.NoError(t, err)
+	})
+}
+
+func TestRemoveRole(t *testing.T) {
+	_ = setup(t)
+	r := GetUserRepository()
+	ctx := context.Background()
+
+	t.Run("remove existing role", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "rmroleuser1",
+			Roles:      []string{"user", "admin"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.RemoveRole(ctx, "rmroleuser1", "admin")
+		require.NoError(t, err)
+
+		retrieved, err := r.GetUser("rmroleuser1")
+		require.NoError(t, err)
+		assert.NotContains(t, retrieved.Roles, "admin")
+		assert.Contains(t, retrieved.Roles, "user")
+
+		err = r.DelUser("rmroleuser1")
+		require.NoError(t, err)
+	})
+
+	t.Run("remove non-existent role", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "rmroleuser2",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.RemoveRole(ctx, "rmroleuser2", "admin")
+		assert.Error(t, err, "Removing non-existent role should fail")
+		assert.Contains(t, err.Error(), "already deleted")
+
+		err = r.DelUser("rmroleuser2")
+		require.NoError(t, err)
+	})
+
+	t.Run("remove manager role with projects", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "rmroleuser3",
+			Roles:      []string{"manager"},
+			Projects:   []string{"proj1", "proj2"},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.RemoveRole(ctx, "rmroleuser3", "manager")
+		assert.Error(t, err, "Removing manager role with projects should fail")
+		assert.Contains(t, err.Error(), "still has assigned project")
+
+		err = r.DelUser("rmroleuser3")
+		require.NoError(t, err)
+	})
+}
+
+func TestAddProject(t *testing.T) {
+	_ = setup(t)
+	r := GetUserRepository()
+	ctx := context.Background()
+
+	t.Run("add project to manager", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "projuser1",
+			Roles:      []string{"manager"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.AddProject(ctx, "projuser1", "newproject")
+		require.NoError(t, err)
+
+		retrieved, err := r.GetUser("projuser1")
+		require.NoError(t, err)
+		assert.Contains(t, retrieved.Projects, "newproject")
+
+		err = r.DelUser("projuser1")
+		require.NoError(t, err)
+	})
+
+	t.Run("add project to non-manager", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "projuser2",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.AddProject(ctx, "projuser2", "newproject")
+		assert.Error(t, err, "Adding project to non-manager should fail")
+		assert.Contains(t, err.Error(), "not a manager")
+
+		err = r.DelUser("projuser2")
+		require.NoError(t, err)
+	})
+
+	t.Run("add duplicate project", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "projuser3",
+			Roles:      []string{"manager"},
+			Projects:   []string{"existingproject"},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.AddProject(ctx, "projuser3", "existingproject")
+		assert.Error(t, err, "Adding duplicate project should fail")
+		assert.Contains(t, err.Error(), "already manages")
+
+		err = r.DelUser("projuser3")
+		require.NoError(t, err)
+	})
+}
+
+func TestRemoveProject(t *testing.T) {
+	_ = setup(t)
+	r := GetUserRepository()
+	ctx := context.Background()
+
+	t.Run("remove existing project", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "rmprojuser1",
+			Roles:      []string{"manager"},
+			Projects:   []string{"proj1", "proj2"},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.RemoveProject(ctx, "rmprojuser1", "proj1")
+		require.NoError(t, err)
+
+		retrieved, err := r.GetUser("rmprojuser1")
+		require.NoError(t, err)
+		assert.NotContains(t, retrieved.Projects, "proj1")
+		assert.Contains(t, retrieved.Projects, "proj2")
+
+		err = r.DelUser("rmprojuser1")
+		require.NoError(t, err)
+	})
+
+	t.Run("remove non-existent project", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "rmprojuser2",
+			Roles:      []string{"manager"},
+			Projects:   []string{"proj1"},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.RemoveProject(ctx, "rmprojuser2", "nonexistent")
+		assert.Error(t, err, "Removing non-existent project should fail")
+
+		err = r.DelUser("rmprojuser2")
+		require.NoError(t, err)
+	})
+
+	t.Run("remove project from non-manager", func(t *testing.T) {
+		user := &schema.User{
+			Username:   "rmprojuser3",
+			Roles:      []string{"user"},
+			Projects:   []string{},
+			AuthSource: schema.AuthViaLocalPassword,
+		}
+
+		err := r.AddUser(user)
+		require.NoError(t, err)
+
+		err = r.RemoveProject(ctx, "rmprojuser3", "proj1")
+		assert.Error(t, err, "Removing project from non-manager should fail")
+		assert.Contains(t, err.Error(), "not a manager")
+
+		err = r.DelUser("rmprojuser3")
+		require.NoError(t, err)
+	})
+}
+
+func TestGetUserFromContext(t *testing.T) {
+	t.Run("get user from context", func(t *testing.T) {
+		user := &schema.User{
+			Username: "contextuser",
+			Roles:    []string{"user"},
+		}
+
+		ctx := context.WithValue(context.Background(), ContextUserKey, user)
+		retrieved := GetUserFromContext(ctx)
+
+		require.NotNil(t, retrieved)
+		assert.Equal(t, user.Username, retrieved.Username)
+	})
+
+	t.Run("get user from empty context", func(t *testing.T) {
+		ctx := context.Background()
+		retrieved := GetUserFromContext(ctx)
+
+		assert.Nil(t, retrieved)
+	})
+}
diff --git a/internal/tagger/tagger.go b/internal/tagger/tagger.go
index 0839603d..2a5a0a7d 100644
--- a/internal/tagger/tagger.go
+++ b/internal/tagger/tagger.go
@@ -64,7 +64,7 @@ func newTagger() {
 func Init() {
 	initOnce.Do(func() {
 		newTagger()
-		repository.RegisterJobJook(jobTagger)
+		repository.RegisterJobHook(jobTagger)
 	})
 }
 

From e1efc684763cff3cf379a9ce8704f37706833e1d Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 15 Jan 2026 08:32:06 +0100
Subject: [PATCH 50/59] Update dependencies. Rebuild graphql and swagger

---
 api/swagger.json                       | 1178 +++++++++++++++++++++---
 api/swagger.yaml                       |  690 ++++++++++++--
 go.mod                                 |    4 +-
 go.sum                                 |   35 +-
 internal/api/cluster.go                |    2 +-
 internal/api/docs.go                   | 1178 +++++++++++++++++++++---
 internal/api/job.go                    |   27 +-
 internal/api/node.go                   |    2 +-
 internal/api/user.go                   |    2 +-
 internal/graph/generated/generated.go  |   20 +-
 internal/graph/schema.resolvers.go     |    4 +-
 internal/importer/handleImport.go      |    1 +
 internal/importer/normalize.go         |    1 +
 internal/metricstore/metricstore.go    |    4 +-
 internal/repository/hooks.go           |    1 +
 internal/repository/job.go             |    2 -
 internal/repository/jobHooks.go        |    1 +
 internal/repository/job_test.go        |    4 +-
 internal/repository/node.go            |    2 +-
 internal/repository/repository_test.go |    8 +-
 internal/repository/stats.go           |  356 +++++--
 internal/repository/tags.go            |  197 +++-
 pkg/archive/clusterConfig.go           |    4 +-
 pkg/archive/nodelist.go                |  153 ++-
 24 files changed, 3321 insertions(+), 555 deletions(-)

diff --git a/api/swagger.json b/api/swagger.json
index 0327a91d..42ed7bb6 100644
--- a/api/swagger.json
+++ b/api/swagger.json
@@ -18,11 +18,6 @@
     "paths": {
         "/api/clusters/": {
             "get": {
-                "security": [
-                    {
-                        "ApiKeyAuth": []
-                    }
-                ],
                 "description": "Get a list of all cluster configs. Specific cluster can be requested using query parameter.",
                 "produces": [
                     "application/json"
@@ -43,7 +38,7 @@
                     "200": {
                         "description": "Array of clusters",
                         "schema": {
-                            "$ref": "#/definitions/api.GetClustersApiResponse"
+                            "$ref": "#/definitions/api.GetClustersAPIResponse"
                         }
                     },
                     "400": {
@@ -70,16 +65,16 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/": {
-            "get": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/": {
+            "get": {
                 "description": "Get a list of all jobs. Filters can be applied using query parameters.\nNumber of results can be limited by page. Results are sorted by descending startTime.",
                 "produces": [
                     "application/json"
@@ -138,7 +133,7 @@
                     "200": {
                         "description": "Job array and page info",
                         "schema": {
-                            "$ref": "#/definitions/api.GetJobsApiResponse"
+                            "$ref": "#/definitions/api.GetJobsAPIResponse"
                         }
                     },
                     "400": {
@@ -165,16 +160,16 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/delete_job/": {
-            "delete": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/delete_job/": {
+            "delete": {
                 "description": "Job to delete is specified by request body. All fields are required in this case.",
                 "consumes": [
                     "application/json"
@@ -193,7 +188,7 @@
                         "in": "body",
                         "required": true,
                         "schema": {
-                            "$ref": "#/definitions/api.DeleteJobApiRequest"
+                            "$ref": "#/definitions/api.DeleteJobAPIRequest"
                         }
                     }
                 ],
@@ -201,7 +196,7 @@
                     "200": {
                         "description": "Success message",
                         "schema": {
-                            "$ref": "#/definitions/api.DefaultApiResponse"
+                            "$ref": "#/definitions/api.DefaultAPIResponse"
                         }
                     },
                     "400": {
@@ -240,16 +235,16 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/delete_job/{id}": {
-            "delete": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/delete_job/{id}": {
+            "delete": {
                 "description": "Job to remove is specified by database ID. This will not remove the job from the job archive.",
                 "produces": [
                     "application/json"
@@ -271,7 +266,7 @@
                     "200": {
                         "description": "Success message",
                         "schema": {
-                            "$ref": "#/definitions/api.DefaultApiResponse"
+                            "$ref": "#/definitions/api.DefaultAPIResponse"
                         }
                     },
                     "400": {
@@ -310,16 +305,16 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/delete_job_before/{ts}": {
-            "delete": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/delete_job_before/{ts}": {
+            "delete": {
                 "description": "Remove all jobs with start time before timestamp. The jobs will not be removed from the job archive.",
                 "produces": [
                     "application/json"
@@ -335,13 +330,19 @@
                         "name": "ts",
                         "in": "path",
                         "required": true
+                    },
+                    {
+                        "type": "boolean",
+                        "description": "Omit jobs with tags from deletion",
+                        "name": "omit-tagged",
+                        "in": "query"
                     }
                 ],
                 "responses": {
                     "200": {
                         "description": "Success message",
                         "schema": {
-                            "$ref": "#/definitions/api.DefaultApiResponse"
+                            "$ref": "#/definitions/api.DefaultAPIResponse"
                         }
                     },
                     "400": {
@@ -380,16 +381,16 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/edit_meta/{id}": {
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/edit_meta/{id}": {
+            "post": {
                 "description": "Edit key value pairs in job metadata json\nIf a key already exists its content will be overwritten",
                 "consumes": [
                     "application/json"
@@ -450,16 +451,16 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/start_job/": {
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/start_job/": {
+            "post": {
                 "description": "Job specified in request body will be saved to database as \"running\" with new DB ID.\nJob specifications follow the 'Job' scheme, API will fail to execute if requirements are not met.",
                 "consumes": [
                     "application/json"
@@ -486,7 +487,7 @@
                     "201": {
                         "description": "Job added successfully",
                         "schema": {
-                            "$ref": "#/definitions/api.DefaultApiResponse"
+                            "$ref": "#/definitions/api.DefaultAPIResponse"
                         }
                     },
                     "400": {
@@ -519,16 +520,16 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/stop_job/": {
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/stop_job/": {
+            "post": {
                 "description": "Job to stop is specified by request body. All fields are required in this case.\nReturns full job resource information according to 'Job' scheme.",
                 "produces": [
                     "application/json"
@@ -544,7 +545,7 @@
                         "in": "body",
                         "required": true,
                         "schema": {
-                            "$ref": "#/definitions/api.StopJobApiRequest"
+                            "$ref": "#/definitions/api.StopJobAPIRequest"
                         }
                     }
                 ],
@@ -591,16 +592,16 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/tag_job/{id}": {
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/tag_job/{id}": {
+            "post": {
                 "description": "Adds tag(s) to a job specified by DB ID. Name and Type of Tag(s) can be chosen freely.\nTag Scope for frontend visibility will default to \"global\" if none entered, other options: \"admin\" or specific username.\nIf tagged job is already finished: Tag will be written directly to respective archive files.",
                 "consumes": [
                     "application/json"
@@ -628,7 +629,7 @@
                         "schema": {
                             "type": "array",
                             "items": {
-                                "$ref": "#/definitions/api.ApiTag"
+                                "$ref": "#/definitions/api.APITag"
                             }
                         }
                     }
@@ -664,16 +665,16 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/{id}": {
-            "get": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/{id}": {
+            "get": {
                 "description": "Job to get is specified by database ID\nReturns full job resource information according to 'Job' scheme and all metrics according to 'JobData'.",
                 "produces": [
                     "application/json"
@@ -701,7 +702,7 @@
                     "200": {
                         "description": "Job resource",
                         "schema": {
-                            "$ref": "#/definitions/api.GetJobApiResponse"
+                            "$ref": "#/definitions/api.GetJobAPIResponse"
                         }
                     },
                     "400": {
@@ -740,14 +741,14 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            },
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            },
+            "post": {
                 "description": "Job to get is specified by database ID\nReturns full job resource information according to 'Job' scheme and all metrics according to 'JobData'.",
                 "consumes": [
                     "application/json"
@@ -784,7 +785,7 @@
                     "200": {
                         "description": "Job resource",
                         "schema": {
-                            "$ref": "#/definitions/api.GetJobApiResponse"
+                            "$ref": "#/definitions/api.GetJobAPIResponse"
                         }
                     },
                     "400": {
@@ -823,16 +824,16 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/nodestats/": {
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/nodestats/": {
+            "post": {
                 "description": "Returns a JSON-encoded list of users.\nRequired query-parameter defines if all users or only users with additional special roles are returned.",
                 "produces": [
                     "application/json"
@@ -856,7 +857,7 @@
                     "200": {
                         "description": "Success message",
                         "schema": {
-                            "$ref": "#/definitions/api.DefaultApiResponse"
+                            "$ref": "#/definitions/api.DefaultAPIResponse"
                         }
                     },
                     "400": {
@@ -883,16 +884,86 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/users/": {
-            "get": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
+                ]
+            }
+        },
+        "/api/user/{id}": {
+            "post": {
+                "description": "Allows admins to add/remove roles and projects for a user",
+                "produces": [
+                    "text/plain"
                 ],
+                "tags": [
+                    "User"
+                ],
+                "summary": "Update user roles and projects",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Username",
+                        "name": "id",
+                        "in": "path",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Role to add",
+                        "name": "add-role",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "Role to remove",
+                        "name": "remove-role",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "Project to add",
+                        "name": "add-project",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "Project to remove",
+                        "name": "remove-project",
+                        "in": "formData"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Success message",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "422": {
+                        "description": "Unprocessable Entity",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/api/users/": {
+            "get": {
                 "description": "Returns a JSON-encoded list of users.\nRequired query-parameter defines if all users or only users with additional special roles are returned.",
                 "produces": [
                     "application/json"
@@ -916,7 +987,7 @@
                         "schema": {
                             "type": "array",
                             "items": {
-                                "$ref": "#/definitions/api.ApiReturnedUser"
+                                "$ref": "#/definitions/api.APIReturnedUser"
                             }
                         }
                     },
@@ -944,16 +1015,361 @@
                             "type": "string"
                         }
                     }
-                }
-            }
-        },
-        "/jobs/tag_job/{id}": {
-            "delete": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
+                ]
+            },
+            "post": {
+                "description": "Creates a new user with specified credentials and role",
+                "produces": [
+                    "text/plain"
                 ],
+                "tags": [
+                    "User"
+                ],
+                "summary": "Create a new user",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Username",
+                        "name": "username",
+                        "in": "formData",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Password (not required for API users)",
+                        "name": "password",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "User role",
+                        "name": "role",
+                        "in": "formData",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Full name",
+                        "name": "name",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "Email address",
+                        "name": "email",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "Project (required for managers)",
+                        "name": "project",
+                        "in": "formData"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Success message",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "422": {
+                        "description": "Unprocessable Entity",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            },
+            "delete": {
+                "description": "Deletes a user from the system",
+                "produces": [
+                    "text/plain"
+                ],
+                "tags": [
+                    "User"
+                ],
+                "summary": "Delete a user",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Username to delete",
+                        "name": "username",
+                        "in": "formData",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Success",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "422": {
+                        "description": "Unprocessable Entity",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/configuration/": {
+            "post": {
+                "description": "Updates a user's configuration key-value pair.",
+                "consumes": [
+                    "multipart/form-data"
+                ],
+                "produces": [
+                    "text/plain"
+                ],
+                "tags": [
+                    "Frontend"
+                ],
+                "summary": "Update user configuration",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Configuration key",
+                        "name": "key",
+                        "in": "formData",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Configuration value",
+                        "name": "value",
+                        "in": "formData",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "success",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/debug/": {
+            "post": {
+                "description": "This endpoint allows the users to print the content of",
+                "produces": [
+                    "application/json"
+                ],
+                "tags": [
+                    "debug"
+                ],
+                "summary": "Debug endpoint",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Selector",
+                        "name": "selector",
+                        "in": "query"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Debug dump",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "401": {
+                        "description": "Unauthorized",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/free/": {
+            "post": {
+                "description": "This endpoint allows the users to free the Buffers from the",
+                "produces": [
+                    "application/json"
+                ],
+                "tags": [
+                    "free"
+                ],
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "up to timestamp",
+                        "name": "to",
+                        "in": "query"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "ok",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "401": {
+                        "description": "Unauthorized",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/healthcheck/": {
+            "get": {
+                "description": "This endpoint allows the users to check if a node is healthy",
+                "produces": [
+                    "application/json"
+                ],
+                "tags": [
+                    "healthcheck"
+                ],
+                "summary": "HealthCheck endpoint",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Selector",
+                        "name": "selector",
+                        "in": "query"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Debug dump",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "401": {
+                        "description": "Unauthorized",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/jobs/tag_job/{id}": {
+            "delete": {
                 "description": "Removes tag(s) from a job specified by DB ID. Name and Type of Tag(s) must match.\nTag Scope is required for matching, options: \"global\", \"admin\". Private tags can not be deleted via API.\nIf tagged job is already finished: Tag will be removed from respective archive files.",
                 "consumes": [
                     "application/json"
@@ -981,7 +1397,7 @@
                         "schema": {
                             "type": "array",
                             "items": {
-                                "$ref": "#/definitions/api.ApiTag"
+                                "$ref": "#/definitions/api.APITag"
                             }
                         }
                     }
@@ -1017,16 +1433,276 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/tags/": {
-            "delete": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
+                ]
+            }
+        },
+        "/jwt/": {
+            "get": {
+                "description": "Generates a JWT token for a user. Admins can generate tokens for any user, regular users only for themselves.",
+                "consumes": [
+                    "multipart/form-data"
                 ],
+                "produces": [
+                    "text/plain"
+                ],
+                "tags": [
+                    "Frontend"
+                ],
+                "summary": "Generate JWT token",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Username to generate JWT for",
+                        "name": "username",
+                        "in": "formData",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "JWT token",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "404": {
+                        "description": "User Not Found",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/machine_state/{cluster}/{host}": {
+            "get": {
+                "description": "Retrieves stored machine state data for a specific cluster node. Validates cluster and host names to prevent path traversal.",
+                "produces": [
+                    "application/json"
+                ],
+                "tags": [
+                    "Machine State"
+                ],
+                "summary": "Retrieve machine state",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Cluster name",
+                        "name": "cluster",
+                        "in": "path",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Host name",
+                        "name": "host",
+                        "in": "path",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Machine state JSON data",
+                        "schema": {
+                            "type": "object"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "404": {
+                        "description": "Machine state not enabled or file not found",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            },
+            "put": {
+                "description": "Stores machine state data for a specific cluster node. Validates cluster and host names to prevent path traversal.",
+                "consumes": [
+                    "application/json"
+                ],
+                "produces": [
+                    "text/plain"
+                ],
+                "tags": [
+                    "Machine State"
+                ],
+                "summary": "Store machine state",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Cluster name",
+                        "name": "cluster",
+                        "in": "path",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Host name",
+                        "name": "host",
+                        "in": "path",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "201": {
+                        "description": "Created"
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "404": {
+                        "description": "Machine state not enabled",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/notice/": {
+            "post": {
+                "description": "Updates the notice.txt file content. Only admins are allowed. Content is limited to 10000 characters.",
+                "consumes": [
+                    "multipart/form-data"
+                ],
+                "produces": [
+                    "text/plain"
+                ],
+                "tags": [
+                    "Config"
+                ],
+                "summary": "Update system notice",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "New notice content (max 10000 characters)",
+                        "name": "new-content",
+                        "in": "formData",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Update Notice Content Success",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/roles/": {
+            "get": {
+                "description": "Returns a list of valid user roles. Only admins are allowed.",
+                "produces": [
+                    "application/json"
+                ],
+                "tags": [
+                    "Config"
+                ],
+                "summary": "Get available roles",
+                "responses": {
+                    "200": {
+                        "description": "List of role names",
+                        "schema": {
+                            "type": "array",
+                            "items": {
+                                "type": "string"
+                            }
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/tags/": {
+            "delete": {
                 "description": "Removes tags by type and name. Name and Type of Tag(s) must match.\nTag Scope is required for matching, options: \"global\", \"admin\". Private tags can not be deleted via API.\nTag wills be removed from respective archive files.",
                 "consumes": [
                     "application/json"
@@ -1047,7 +1723,7 @@
                         "schema": {
                             "type": "array",
                             "items": {
-                                "$ref": "#/definitions/api.ApiTag"
+                                "$ref": "#/definitions/api.APITag"
                             }
                         }
                     }
@@ -1083,12 +1759,72 @@
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/write/": {
+            "post": {
+                "consumes": [
+                    "text/plain"
+                ],
+                "produces": [
+                    "application/json"
+                ],
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "If the lines in the body do not have a cluster tag, use this value instead.",
+                        "name": "cluster",
+                        "in": "query"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "ok",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "401": {
+                        "description": "Unauthorized",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
             }
         }
     },
     "definitions": {
-        "api.ApiReturnedUser": {
+        "api.APIReturnedUser": {
             "type": "object",
             "properties": {
                 "email": {
@@ -1114,7 +1850,7 @@
                 }
             }
         },
-        "api.ApiTag": {
+        "api.APITag": {
             "type": "object",
             "properties": {
                 "name": {
@@ -1134,7 +1870,7 @@
                 }
             }
         },
-        "api.DefaultApiResponse": {
+        "api.DefaultAPIResponse": {
             "type": "object",
             "properties": {
                 "msg": {
@@ -1142,7 +1878,7 @@
                 }
             }
         },
-        "api.DeleteJobApiRequest": {
+        "api.DeleteJobAPIRequest": {
             "type": "object",
             "required": [
                 "jobId"
@@ -1191,7 +1927,7 @@
                 }
             }
         },
-        "api.GetClustersApiResponse": {
+        "api.GetClustersAPIResponse": {
             "type": "object",
             "properties": {
                 "clusters": {
@@ -1203,7 +1939,7 @@
                 }
             }
         },
-        "api.GetJobApiResponse": {
+        "api.GetJobAPIResponse": {
             "type": "object",
             "properties": {
                 "data": {
@@ -1217,7 +1953,7 @@
                 }
             }
         },
-        "api.GetJobsApiResponse": {
+        "api.GetJobsAPIResponse": {
             "type": "object",
             "properties": {
                 "items": {
@@ -1251,39 +1987,7 @@
                 }
             }
         },
-        "api.Node": {
-            "type": "object",
-            "properties": {
-                "cpusAllocated": {
-                    "type": "integer"
-                },
-                "cpusTotal": {
-                    "type": "integer"
-                },
-                "gpusAllocated": {
-                    "type": "integer"
-                },
-                "gpusTotal": {
-                    "type": "integer"
-                },
-                "hostname": {
-                    "type": "string"
-                },
-                "memoryAllocated": {
-                    "type": "integer"
-                },
-                "memoryTotal": {
-                    "type": "integer"
-                },
-                "states": {
-                    "type": "array",
-                    "items": {
-                        "type": "string"
-                    }
-                }
-            }
-        },
-        "api.StopJobApiRequest": {
+        "api.StopJobAPIRequest": {
             "type": "object",
             "required": [
                 "jobState",
@@ -1326,7 +2030,7 @@
                 "nodes": {
                     "type": "array",
                     "items": {
-                        "$ref": "#/definitions/api.Node"
+                        "$ref": "#/definitions/schema.NodePayload"
                     }
                 }
             }
@@ -1335,12 +2039,15 @@
             "type": "object",
             "properties": {
                 "id": {
+                    "description": "Unique identifier for the accelerator (e.g., \"0\", \"1\", \"GPU-0\")",
                     "type": "string"
                 },
                 "model": {
+                    "description": "Specific model name (e.g., \"A100\", \"MI100\")",
                     "type": "string"
                 },
                 "type": {
+                    "description": "Type of accelerator (e.g., \"Nvidia GPU\", \"AMD GPU\")",
                     "type": "string"
                 }
             }
@@ -1349,15 +2056,18 @@
             "type": "object",
             "properties": {
                 "metricConfig": {
+                    "description": "Cluster-wide metric configurations",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.MetricConfig"
                     }
                 },
                 "name": {
+                    "description": "Unique cluster name (e.g., \"fritz\", \"alex\")",
                     "type": "string"
                 },
                 "subClusters": {
+                    "description": "Homogeneous partitions within the cluster",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.SubCluster"
@@ -1366,6 +2076,7 @@
             }
         },
         "schema.Job": {
+            "description": "Information of a HPC job.",
             "type": "object",
             "properties": {
                 "arrayJobId": {
@@ -1394,6 +2105,13 @@
                         "format": "float64"
                     }
                 },
+                "exclusive": {
+                    "description": "for backwards compatibility",
+                    "type": "integer",
+                    "maximum": 2,
+                    "minimum": 0,
+                    "example": 1
+                },
                 "footprint": {
                     "type": "object",
                     "additionalProperties": {
@@ -1416,7 +2134,7 @@
                         "deadline",
                         "failed",
                         "node_fail",
-                        "out_of_memory",
+                        "out-of-memory",
                         "pending",
                         "preempted",
                         "running",
@@ -1528,9 +2246,11 @@
             "type": "object",
             "properties": {
                 "id": {
+                    "description": "Internal database ID",
                     "type": "integer"
                 },
                 "jobId": {
+                    "description": "The job's external job ID",
                     "type": "integer"
                 }
             }
@@ -1539,9 +2259,11 @@
             "type": "object",
             "properties": {
                 "count": {
+                    "description": "Total count of available items",
                     "type": "integer"
                 },
                 "items": {
+                    "description": "List of job links",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.JobLink"
@@ -1553,19 +2275,31 @@
             "type": "object",
             "properties": {
                 "series": {
+                    "description": "Individual time series data",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.Series"
                     }
                 },
                 "statisticsSeries": {
-                    "$ref": "#/definitions/schema.StatsSeries"
+                    "description": "Aggregated statistics over time",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.StatsSeries"
+                        }
+                    ]
                 },
                 "timestep": {
+                    "description": "Sampling interval in seconds",
                     "type": "integer"
                 },
                 "unit": {
-                    "$ref": "#/definitions/schema.Unit"
+                    "description": "Unit of measurement",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.Unit"
+                        }
+                    ]
                 }
             }
         },
@@ -1631,46 +2365,71 @@
             "type": "object",
             "properties": {
                 "aggregation": {
+                    "description": "Aggregation function (avg, sum, min, max)",
                     "type": "string"
                 },
                 "alert": {
+                    "description": "Alert threshold (requires attention)",
                     "type": "number"
                 },
                 "caution": {
+                    "description": "Caution threshold (concerning but not critical)",
                     "type": "number"
                 },
                 "energy": {
+                    "description": "Energy measurement method",
                     "type": "string"
                 },
                 "footprint": {
+                    "description": "Footprint category",
                     "type": "string"
                 },
                 "lowerIsBetter": {
+                    "description": "Whether lower values are better",
                     "type": "boolean"
                 },
                 "name": {
+                    "description": "Metric name (e.g., \"cpu_load\", \"mem_used\")",
                     "type": "string"
                 },
                 "normal": {
+                    "description": "Normal/typical value (good performance)",
                     "type": "number"
                 },
                 "peak": {
+                    "description": "Peak/maximum expected value (best performance)",
                     "type": "number"
                 },
+                "restrict": {
+                    "description": "Restrict visibility to non user roles",
+                    "type": "boolean"
+                },
                 "scope": {
-                    "$ref": "#/definitions/schema.MetricScope"
+                    "description": "Metric scope (node, socket, core, etc.)",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.MetricScope"
+                        }
+                    ]
                 },
                 "subClusters": {
+                    "description": "Subcluster-specific overrides",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.SubClusterConfig"
                     }
                 },
                 "timestep": {
+                    "description": "Measurement interval in seconds",
                     "type": "integer"
                 },
                 "unit": {
-                    "$ref": "#/definitions/schema.Unit"
+                    "description": "Unit of measurement",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.Unit"
+                        }
+                    ]
                 }
             }
         },
@@ -1699,12 +2458,15 @@
             "type": "object",
             "properties": {
                 "avg": {
+                    "description": "Average/mean value",
                     "type": "number"
                 },
                 "max": {
+                    "description": "Maximum value",
                     "type": "number"
                 },
                 "min": {
+                    "description": "Minimum value",
                     "type": "number"
                 }
             }
@@ -1713,30 +2475,72 @@
             "type": "object",
             "properties": {
                 "unit": {
-                    "$ref": "#/definitions/schema.Unit"
+                    "description": "Unit of measurement (e.g., FLOP/s, GB/s)",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.Unit"
+                        }
+                    ]
                 },
                 "value": {
+                    "description": "Numeric value of the measurement",
                     "type": "number"
                 }
             }
         },
+        "schema.NodePayload": {
+            "type": "object",
+            "properties": {
+                "cpusAllocated": {
+                    "description": "Number of allocated CPUs",
+                    "type": "integer"
+                },
+                "gpusAllocated": {
+                    "description": "Number of allocated GPUs",
+                    "type": "integer"
+                },
+                "hostname": {
+                    "description": "Node hostname",
+                    "type": "string"
+                },
+                "jobsRunning": {
+                    "description": "Number of running jobs",
+                    "type": "integer"
+                },
+                "memoryAllocated": {
+                    "description": "Allocated memory in MB",
+                    "type": "integer"
+                },
+                "states": {
+                    "description": "State strings (flexible format)",
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                }
+            }
+        },
         "schema.Resource": {
             "description": "A resource used by a job",
             "type": "object",
             "properties": {
                 "accelerators": {
+                    "description": "Allocated accelerator IDs (e.g., GPU IDs)",
                     "type": "array",
                     "items": {
                         "type": "string"
                     }
                 },
                 "configuration": {
+                    "description": "Optional configuration identifier",
                     "type": "string"
                 },
                 "hostname": {
+                    "description": "Node hostname",
                     "type": "string"
                 },
                 "hwthreads": {
+                    "description": "Allocated hardware thread IDs",
                     "type": "array",
                     "items": {
                         "type": "integer"
@@ -1748,19 +2552,27 @@
             "type": "object",
             "properties": {
                 "data": {
+                    "description": "Time series measurements",
                     "type": "array",
                     "items": {
                         "type": "number"
                     }
                 },
                 "hostname": {
+                    "description": "Source hostname",
                     "type": "string"
                 },
                 "id": {
+                    "description": "Optional ID (e.g., core ID, GPU ID)",
                     "type": "string"
                 },
                 "statistics": {
-                    "$ref": "#/definitions/schema.MetricStatistics"
+                    "description": "Statistical summary (min/avg/max)",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.MetricStatistics"
+                        }
+                    ]
                 }
             }
         },
@@ -1768,30 +2580,35 @@
             "type": "object",
             "properties": {
                 "max": {
+                    "description": "Maximum values over time",
                     "type": "array",
                     "items": {
                         "type": "number"
                     }
                 },
                 "mean": {
+                    "description": "Mean values over time",
                     "type": "array",
                     "items": {
                         "type": "number"
                     }
                 },
                 "median": {
+                    "description": "Median values over time",
                     "type": "array",
                     "items": {
                         "type": "number"
                     }
                 },
                 "min": {
+                    "description": "Minimum values over time",
                     "type": "array",
                     "items": {
                         "type": "number"
                     }
                 },
                 "percentiles": {
+                    "description": "Percentile values over time (e.g., 10th, 50th, 90th)",
                     "type": "object",
                     "additionalProperties": {
                         "type": "array",
@@ -1807,52 +2624,81 @@
             "type": "object",
             "properties": {
                 "coresPerSocket": {
+                    "description": "Number of cores per CPU socket",
                     "type": "integer"
                 },
                 "energyFootprint": {
+                    "description": "Energy-related footprint metrics",
                     "type": "array",
                     "items": {
                         "type": "string"
                     }
                 },
                 "flopRateScalar": {
-                    "$ref": "#/definitions/schema.MetricValue"
+                    "description": "Theoretical scalar FLOP rate per node",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.MetricValue"
+                        }
+                    ]
                 },
                 "flopRateSimd": {
-                    "$ref": "#/definitions/schema.MetricValue"
+                    "description": "Theoretical SIMD FLOP rate per node",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.MetricValue"
+                        }
+                    ]
                 },
                 "footprint": {
+                    "description": "Default footprint metrics for jobs",
                     "type": "array",
                     "items": {
                         "type": "string"
                     }
                 },
                 "memoryBandwidth": {
-                    "$ref": "#/definitions/schema.MetricValue"
+                    "description": "Theoretical memory bandwidth per node",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.MetricValue"
+                        }
+                    ]
                 },
                 "metricConfig": {
+                    "description": "Subcluster-specific metric configurations",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.MetricConfig"
                     }
                 },
                 "name": {
+                    "description": "Name of the subcluster (e.g., \"main\", \"gpu\", \"bigmem\")",
                     "type": "string"
                 },
                 "nodes": {
+                    "description": "Node list in condensed format (e.g., \"node[001-100]\")",
                     "type": "string"
                 },
                 "processorType": {
+                    "description": "CPU model (e.g., \"Intel Xeon Gold 6148\")",
                     "type": "string"
                 },
                 "socketsPerNode": {
+                    "description": "Number of CPU sockets per node",
                     "type": "integer"
                 },
                 "threadsPerCore": {
+                    "description": "Number of hardware threads per core (SMT level)",
                     "type": "integer"
                 },
                 "topology": {
-                    "$ref": "#/definitions/schema.Topology"
+                    "description": "Hardware topology of nodes in this subcluster",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.Topology"
+                        }
+                    ]
                 }
             }
         },
@@ -1860,34 +2706,52 @@
             "type": "object",
             "properties": {
                 "alert": {
+                    "description": "Alert threshold (requires attention)",
                     "type": "number"
                 },
                 "caution": {
+                    "description": "Caution threshold (concerning but not critical)",
                     "type": "number"
                 },
                 "energy": {
+                    "description": "Energy measurement configuration",
                     "type": "string"
                 },
                 "footprint": {
+                    "description": "Footprint category for this metric",
                     "type": "string"
                 },
                 "lowerIsBetter": {
+                    "description": "Whether lower values indicate better performance",
                     "type": "boolean"
                 },
                 "name": {
+                    "description": "Metric name (e.g., \"cpu_load\", \"mem_used\")",
                     "type": "string"
                 },
                 "normal": {
+                    "description": "Normal/typical value (good performance)",
                     "type": "number"
                 },
                 "peak": {
+                    "description": "Peak/maximum expected value (best performance)",
                     "type": "number"
                 },
                 "remove": {
+                    "description": "Whether to exclude this metric for this subcluster",
+                    "type": "boolean"
+                },
+                "restrict": {
+                    "description": "Restrict visibility to non user roles",
                     "type": "boolean"
                 },
                 "unit": {
-                    "$ref": "#/definitions/schema.Unit"
+                    "description": "Unit of measurement",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.Unit"
+                        }
+                    ]
                 }
             }
         },
@@ -1916,12 +2780,14 @@
             "type": "object",
             "properties": {
                 "accelerators": {
+                    "description": "Attached accelerators (GPUs, etc.)",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.Accelerator"
                     }
                 },
                 "core": {
+                    "description": "Hardware threads grouped by core",
                     "type": "array",
                     "items": {
                         "type": "array",
@@ -1931,6 +2797,7 @@
                     }
                 },
                 "die": {
+                    "description": "Hardware threads grouped by die (optional)",
                     "type": "array",
                     "items": {
                         "type": "array",
@@ -1940,6 +2807,7 @@
                     }
                 },
                 "memoryDomain": {
+                    "description": "Hardware threads grouped by NUMA domain",
                     "type": "array",
                     "items": {
                         "type": "array",
@@ -1949,12 +2817,14 @@
                     }
                 },
                 "node": {
+                    "description": "All hardware thread IDs on this node",
                     "type": "array",
                     "items": {
                         "type": "integer"
                     }
                 },
                 "socket": {
+                    "description": "Hardware threads grouped by socket",
                     "type": "array",
                     "items": {
                         "type": "array",
@@ -1969,9 +2839,11 @@
             "type": "object",
             "properties": {
                 "base": {
+                    "description": "Base unit (e.g., \"B/s\", \"F/s\", \"W\")",
                     "type": "string"
                 },
                 "prefix": {
+                    "description": "SI prefix (e.g., \"G\", \"M\", \"K\", \"T\")",
                     "type": "string"
                 }
             }
diff --git a/api/swagger.yaml b/api/swagger.yaml
index 119e9529..0bf60082 100644
--- a/api/swagger.yaml
+++ b/api/swagger.yaml
@@ -1,5 +1,5 @@
 definitions:
-  api.ApiReturnedUser:
+  api.APIReturnedUser:
     properties:
       email:
         type: string
@@ -16,7 +16,7 @@ definitions:
       username:
         type: string
     type: object
-  api.ApiTag:
+  api.APITag:
     properties:
       name:
         description: Tag Name
@@ -31,12 +31,12 @@ definitions:
         example: Debug
         type: string
     type: object
-  api.DefaultApiResponse:
+  api.DefaultAPIResponse:
     properties:
       msg:
         type: string
     type: object
-  api.DeleteJobApiRequest:
+  api.DeleteJobAPIRequest:
     properties:
       cluster:
         description: Cluster of job
@@ -71,7 +71,7 @@ definitions:
         description: Statustext of Errorcode
         type: string
     type: object
-  api.GetClustersApiResponse:
+  api.GetClustersAPIResponse:
     properties:
       clusters:
         description: Array of clusters
@@ -79,7 +79,7 @@ definitions:
           $ref: '#/definitions/schema.Cluster'
         type: array
     type: object
-  api.GetJobApiResponse:
+  api.GetJobAPIResponse:
     properties:
       data:
         items:
@@ -88,7 +88,7 @@ definitions:
       meta:
         $ref: '#/definitions/schema.Job'
     type: object
-  api.GetJobsApiResponse:
+  api.GetJobsAPIResponse:
     properties:
       items:
         description: Number of jobs returned
@@ -111,28 +111,7 @@ definitions:
       scope:
         $ref: '#/definitions/schema.MetricScope'
     type: object
-  api.Node:
-    properties:
-      cpusAllocated:
-        type: integer
-      cpusTotal:
-        type: integer
-      gpusAllocated:
-        type: integer
-      gpusTotal:
-        type: integer
-      hostname:
-        type: string
-      memoryAllocated:
-        type: integer
-      memoryTotal:
-        type: integer
-      states:
-        items:
-          type: string
-        type: array
-    type: object
-  api.StopJobApiRequest:
+  api.StopJobAPIRequest:
     properties:
       cluster:
         example: fritz
@@ -161,32 +140,39 @@ definitions:
         type: string
       nodes:
         items:
-          $ref: '#/definitions/api.Node'
+          $ref: '#/definitions/schema.NodePayload'
         type: array
     type: object
   schema.Accelerator:
     properties:
       id:
+        description: Unique identifier for the accelerator (e.g., "0", "1", "GPU-0")
         type: string
       model:
+        description: Specific model name (e.g., "A100", "MI100")
         type: string
       type:
+        description: Type of accelerator (e.g., "Nvidia GPU", "AMD GPU")
         type: string
     type: object
   schema.Cluster:
     properties:
       metricConfig:
+        description: Cluster-wide metric configurations
         items:
           $ref: '#/definitions/schema.MetricConfig'
         type: array
       name:
+        description: Unique cluster name (e.g., "fritz", "alex")
         type: string
       subClusters:
+        description: Homogeneous partitions within the cluster
         items:
           $ref: '#/definitions/schema.SubCluster'
         type: array
     type: object
   schema.Job:
+    description: Information of a HPC job.
     properties:
       arrayJobId:
         example: 123000
@@ -207,6 +193,12 @@ definitions:
           format: float64
           type: number
         type: object
+      exclusive:
+        description: for backwards compatibility
+        example: 1
+        maximum: 2
+        minimum: 0
+        type: integer
       footprint:
         additionalProperties:
           format: float64
@@ -227,7 +219,7 @@ definitions:
         - deadline
         - failed
         - node_fail
-        - out_of_memory
+        - out-of-memory
         - pending
         - preempted
         - running
@@ -307,15 +299,19 @@ definitions:
   schema.JobLink:
     properties:
       id:
+        description: Internal database ID
         type: integer
       jobId:
+        description: The job's external job ID
         type: integer
     type: object
   schema.JobLinkResultList:
     properties:
       count:
+        description: Total count of available items
         type: integer
       items:
+        description: List of job links
         items:
           $ref: '#/definitions/schema.JobLink'
         type: array
@@ -323,15 +319,21 @@ definitions:
   schema.JobMetric:
     properties:
       series:
+        description: Individual time series data
         items:
           $ref: '#/definitions/schema.Series'
         type: array
       statisticsSeries:
-        $ref: '#/definitions/schema.StatsSeries'
+        allOf:
+        - $ref: '#/definitions/schema.StatsSeries'
+        description: Aggregated statistics over time
       timestep:
+        description: Sampling interval in seconds
         type: integer
       unit:
-        $ref: '#/definitions/schema.Unit'
+        allOf:
+        - $ref: '#/definitions/schema.Unit'
+        description: Unit of measurement
     type: object
   schema.JobState:
     enum:
@@ -385,33 +387,51 @@ definitions:
   schema.MetricConfig:
     properties:
       aggregation:
+        description: Aggregation function (avg, sum, min, max)
         type: string
       alert:
+        description: Alert threshold (requires attention)
         type: number
       caution:
+        description: Caution threshold (concerning but not critical)
         type: number
       energy:
+        description: Energy measurement method
         type: string
       footprint:
+        description: Footprint category
         type: string
       lowerIsBetter:
+        description: Whether lower values are better
         type: boolean
       name:
+        description: Metric name (e.g., "cpu_load", "mem_used")
         type: string
       normal:
+        description: Normal/typical value (good performance)
         type: number
       peak:
+        description: Peak/maximum expected value (best performance)
         type: number
+      restrict:
+        description: Restrict visibility to non user roles
+        type: boolean
       scope:
-        $ref: '#/definitions/schema.MetricScope'
+        allOf:
+        - $ref: '#/definitions/schema.MetricScope'
+        description: Metric scope (node, socket, core, etc.)
       subClusters:
+        description: Subcluster-specific overrides
         items:
           $ref: '#/definitions/schema.SubClusterConfig'
         type: array
       timestep:
+        description: Measurement interval in seconds
         type: integer
       unit:
-        $ref: '#/definitions/schema.Unit'
+        allOf:
+        - $ref: '#/definitions/schema.Unit'
+        description: Unit of measurement
     type: object
   schema.MetricScope:
     enum:
@@ -434,31 +454,64 @@ definitions:
   schema.MetricStatistics:
     properties:
       avg:
+        description: Average/mean value
         type: number
       max:
+        description: Maximum value
         type: number
       min:
+        description: Minimum value
         type: number
     type: object
   schema.MetricValue:
     properties:
       unit:
-        $ref: '#/definitions/schema.Unit'
+        allOf:
+        - $ref: '#/definitions/schema.Unit'
+        description: Unit of measurement (e.g., FLOP/s, GB/s)
       value:
+        description: Numeric value of the measurement
         type: number
     type: object
+  schema.NodePayload:
+    properties:
+      cpusAllocated:
+        description: Number of allocated CPUs
+        type: integer
+      gpusAllocated:
+        description: Number of allocated GPUs
+        type: integer
+      hostname:
+        description: Node hostname
+        type: string
+      jobsRunning:
+        description: Number of running jobs
+        type: integer
+      memoryAllocated:
+        description: Allocated memory in MB
+        type: integer
+      states:
+        description: State strings (flexible format)
+        items:
+          type: string
+        type: array
+    type: object
   schema.Resource:
     description: A resource used by a job
     properties:
       accelerators:
+        description: Allocated accelerator IDs (e.g., GPU IDs)
         items:
           type: string
         type: array
       configuration:
+        description: Optional configuration identifier
         type: string
       hostname:
+        description: Node hostname
         type: string
       hwthreads:
+        description: Allocated hardware thread IDs
         items:
           type: integer
         type: array
@@ -466,31 +519,40 @@ definitions:
   schema.Series:
     properties:
       data:
+        description: Time series measurements
         items:
           type: number
         type: array
       hostname:
+        description: Source hostname
         type: string
       id:
+        description: Optional ID (e.g., core ID, GPU ID)
         type: string
       statistics:
-        $ref: '#/definitions/schema.MetricStatistics'
+        allOf:
+        - $ref: '#/definitions/schema.MetricStatistics'
+        description: Statistical summary (min/avg/max)
     type: object
   schema.StatsSeries:
     properties:
       max:
+        description: Maximum values over time
         items:
           type: number
         type: array
       mean:
+        description: Mean values over time
         items:
           type: number
         type: array
       median:
+        description: Median values over time
         items:
           type: number
         type: array
       min:
+        description: Minimum values over time
         items:
           type: number
         type: array
@@ -500,65 +562,97 @@ definitions:
             format: float64
             type: number
           type: array
+        description: Percentile values over time (e.g., 10th, 50th, 90th)
         type: object
     type: object
   schema.SubCluster:
     properties:
       coresPerSocket:
+        description: Number of cores per CPU socket
         type: integer
       energyFootprint:
+        description: Energy-related footprint metrics
         items:
           type: string
         type: array
       flopRateScalar:
-        $ref: '#/definitions/schema.MetricValue'
+        allOf:
+        - $ref: '#/definitions/schema.MetricValue'
+        description: Theoretical scalar FLOP rate per node
       flopRateSimd:
-        $ref: '#/definitions/schema.MetricValue'
+        allOf:
+        - $ref: '#/definitions/schema.MetricValue'
+        description: Theoretical SIMD FLOP rate per node
       footprint:
+        description: Default footprint metrics for jobs
         items:
           type: string
         type: array
       memoryBandwidth:
-        $ref: '#/definitions/schema.MetricValue'
+        allOf:
+        - $ref: '#/definitions/schema.MetricValue'
+        description: Theoretical memory bandwidth per node
       metricConfig:
+        description: Subcluster-specific metric configurations
         items:
           $ref: '#/definitions/schema.MetricConfig'
         type: array
       name:
+        description: Name of the subcluster (e.g., "main", "gpu", "bigmem")
         type: string
       nodes:
+        description: Node list in condensed format (e.g., "node[001-100]")
         type: string
       processorType:
+        description: CPU model (e.g., "Intel Xeon Gold 6148")
         type: string
       socketsPerNode:
+        description: Number of CPU sockets per node
         type: integer
       threadsPerCore:
+        description: Number of hardware threads per core (SMT level)
         type: integer
       topology:
-        $ref: '#/definitions/schema.Topology'
+        allOf:
+        - $ref: '#/definitions/schema.Topology'
+        description: Hardware topology of nodes in this subcluster
     type: object
   schema.SubClusterConfig:
     properties:
       alert:
+        description: Alert threshold (requires attention)
         type: number
       caution:
+        description: Caution threshold (concerning but not critical)
         type: number
       energy:
+        description: Energy measurement configuration
         type: string
       footprint:
+        description: Footprint category for this metric
         type: string
       lowerIsBetter:
+        description: Whether lower values indicate better performance
         type: boolean
       name:
+        description: Metric name (e.g., "cpu_load", "mem_used")
         type: string
       normal:
+        description: Normal/typical value (good performance)
         type: number
       peak:
+        description: Peak/maximum expected value (best performance)
         type: number
       remove:
+        description: Whether to exclude this metric for this subcluster
+        type: boolean
+      restrict:
+        description: Restrict visibility to non user roles
         type: boolean
       unit:
-        $ref: '#/definitions/schema.Unit'
+        allOf:
+        - $ref: '#/definitions/schema.Unit'
+        description: Unit of measurement
     type: object
   schema.Tag:
     description: Defines a tag using name and type.
@@ -578,32 +672,38 @@ definitions:
   schema.Topology:
     properties:
       accelerators:
+        description: Attached accelerators (GPUs, etc.)
         items:
           $ref: '#/definitions/schema.Accelerator'
         type: array
       core:
+        description: Hardware threads grouped by core
         items:
           items:
             type: integer
           type: array
         type: array
       die:
+        description: Hardware threads grouped by die (optional)
         items:
           items:
             type: integer
           type: array
         type: array
       memoryDomain:
+        description: Hardware threads grouped by NUMA domain
         items:
           items:
             type: integer
           type: array
         type: array
       node:
+        description: All hardware thread IDs on this node
         items:
           type: integer
         type: array
       socket:
+        description: Hardware threads grouped by socket
         items:
           items:
             type: integer
@@ -613,8 +713,10 @@ definitions:
   schema.Unit:
     properties:
       base:
+        description: Base unit (e.g., "B/s", "F/s", "W")
         type: string
       prefix:
+        description: SI prefix (e.g., "G", "M", "K", "T")
         type: string
     type: object
 host: localhost:8080
@@ -645,7 +747,7 @@ paths:
         "200":
           description: Array of clusters
           schema:
-            $ref: '#/definitions/api.GetClustersApiResponse'
+            $ref: '#/definitions/api.GetClustersAPIResponse'
         "400":
           description: Bad Request
           schema:
@@ -710,7 +812,7 @@ paths:
         "200":
           description: Job array and page info
           schema:
-            $ref: '#/definitions/api.GetJobsApiResponse'
+            $ref: '#/definitions/api.GetJobsAPIResponse'
         "400":
           description: Bad Request
           schema:
@@ -753,7 +855,7 @@ paths:
         "200":
           description: Job resource
           schema:
-            $ref: '#/definitions/api.GetJobApiResponse'
+            $ref: '#/definitions/api.GetJobAPIResponse'
         "400":
           description: Bad Request
           schema:
@@ -810,7 +912,7 @@ paths:
         "200":
           description: Job resource
           schema:
-            $ref: '#/definitions/api.GetJobApiResponse'
+            $ref: '#/definitions/api.GetJobAPIResponse'
         "400":
           description: Bad Request
           schema:
@@ -853,14 +955,14 @@ paths:
         name: request
         required: true
         schema:
-          $ref: '#/definitions/api.DeleteJobApiRequest'
+          $ref: '#/definitions/api.DeleteJobAPIRequest'
       produces:
       - application/json
       responses:
         "200":
           description: Success message
           schema:
-            $ref: '#/definitions/api.DefaultApiResponse'
+            $ref: '#/definitions/api.DefaultAPIResponse'
         "400":
           description: Bad Request
           schema:
@@ -907,7 +1009,7 @@ paths:
         "200":
           description: Success message
           schema:
-            $ref: '#/definitions/api.DefaultApiResponse'
+            $ref: '#/definitions/api.DefaultAPIResponse'
         "400":
           description: Bad Request
           schema:
@@ -948,13 +1050,17 @@ paths:
         name: ts
         required: true
         type: integer
+      - description: Omit jobs with tags from deletion
+        in: query
+        name: omit-tagged
+        type: boolean
       produces:
       - application/json
       responses:
         "200":
           description: Success message
           schema:
-            $ref: '#/definitions/api.DefaultApiResponse'
+            $ref: '#/definitions/api.DefaultAPIResponse'
         "400":
           description: Bad Request
           schema:
@@ -1052,7 +1158,7 @@ paths:
         "201":
           description: Job added successfully
           schema:
-            $ref: '#/definitions/api.DefaultApiResponse'
+            $ref: '#/definitions/api.DefaultAPIResponse'
         "400":
           description: Bad Request
           schema:
@@ -1090,7 +1196,7 @@ paths:
         name: request
         required: true
         schema:
-          $ref: '#/definitions/api.StopJobApiRequest'
+          $ref: '#/definitions/api.StopJobAPIRequest'
       produces:
       - application/json
       responses:
@@ -1147,7 +1253,7 @@ paths:
         required: true
         schema:
           items:
-            $ref: '#/definitions/api.ApiTag'
+            $ref: '#/definitions/api.APITag'
           type: array
       produces:
       - application/json
@@ -1195,7 +1301,7 @@ paths:
         "200":
           description: Success message
           schema:
-            $ref: '#/definitions/api.DefaultApiResponse'
+            $ref: '#/definitions/api.DefaultAPIResponse'
         "400":
           description: Bad Request
           schema:
@@ -1217,7 +1323,80 @@ paths:
       summary: Deliver updated Slurm node states
       tags:
       - Nodestates
+  /api/user/{id}:
+    post:
+      description: Allows admins to add/remove roles and projects for a user
+      parameters:
+      - description: Username
+        in: path
+        name: id
+        required: true
+        type: string
+      - description: Role to add
+        in: formData
+        name: add-role
+        type: string
+      - description: Role to remove
+        in: formData
+        name: remove-role
+        type: string
+      - description: Project to add
+        in: formData
+        name: add-project
+        type: string
+      - description: Project to remove
+        in: formData
+        name: remove-project
+        type: string
+      produces:
+      - text/plain
+      responses:
+        "200":
+          description: Success message
+          schema:
+            type: string
+        "403":
+          description: Forbidden
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "422":
+          description: Unprocessable Entity
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Update user roles and projects
+      tags:
+      - User
   /api/users/:
+    delete:
+      description: Deletes a user from the system
+      parameters:
+      - description: Username to delete
+        in: formData
+        name: username
+        required: true
+        type: string
+      produces:
+      - text/plain
+      responses:
+        "200":
+          description: Success
+          schema:
+            type: string
+        "403":
+          description: Forbidden
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "422":
+          description: Unprocessable Entity
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Delete a user
+      tags:
+      - User
     get:
       description: |-
         Returns a JSON-encoded list of users.
@@ -1236,7 +1415,7 @@ paths:
           description: List of users returned successfully
           schema:
             items:
-              $ref: '#/definitions/api.ApiReturnedUser'
+              $ref: '#/definitions/api.APIReturnedUser'
             type: array
         "400":
           description: Bad Request
@@ -1259,6 +1438,198 @@ paths:
       summary: Returns a list of users
       tags:
       - User
+    post:
+      description: Creates a new user with specified credentials and role
+      parameters:
+      - description: Username
+        in: formData
+        name: username
+        required: true
+        type: string
+      - description: Password (not required for API users)
+        in: formData
+        name: password
+        type: string
+      - description: User role
+        in: formData
+        name: role
+        required: true
+        type: string
+      - description: Full name
+        in: formData
+        name: name
+        type: string
+      - description: Email address
+        in: formData
+        name: email
+        type: string
+      - description: Project (required for managers)
+        in: formData
+        name: project
+        type: string
+      produces:
+      - text/plain
+      responses:
+        "200":
+          description: Success message
+          schema:
+            type: string
+        "400":
+          description: Bad Request
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "403":
+          description: Forbidden
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "422":
+          description: Unprocessable Entity
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Create a new user
+      tags:
+      - User
+  /configuration/:
+    post:
+      consumes:
+      - multipart/form-data
+      description: Updates a user's configuration key-value pair.
+      parameters:
+      - description: Configuration key
+        in: formData
+        name: key
+        required: true
+        type: string
+      - description: Configuration value
+        in: formData
+        name: value
+        required: true
+        type: string
+      produces:
+      - text/plain
+      responses:
+        "200":
+          description: success
+          schema:
+            type: string
+        "500":
+          description: Internal Server Error
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Update user configuration
+      tags:
+      - Frontend
+  /debug/:
+    post:
+      description: This endpoint allows the users to print the content of
+      parameters:
+      - description: Selector
+        in: query
+        name: selector
+        type: string
+      produces:
+      - application/json
+      responses:
+        "200":
+          description: Debug dump
+          schema:
+            type: string
+        "400":
+          description: Bad Request
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "401":
+          description: Unauthorized
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "403":
+          description: Forbidden
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "500":
+          description: Internal Server Error
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Debug endpoint
+      tags:
+      - debug
+  /free/:
+    post:
+      description: This endpoint allows the users to free the Buffers from the
+      parameters:
+      - description: up to timestamp
+        in: query
+        name: to
+        type: string
+      produces:
+      - application/json
+      responses:
+        "200":
+          description: ok
+          schema:
+            type: string
+        "400":
+          description: Bad Request
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "401":
+          description: Unauthorized
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "403":
+          description: Forbidden
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "500":
+          description: Internal Server Error
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      tags:
+      - free
+  /healthcheck/:
+    get:
+      description: This endpoint allows the users to check if a node is healthy
+      parameters:
+      - description: Selector
+        in: query
+        name: selector
+        type: string
+      produces:
+      - application/json
+      responses:
+        "200":
+          description: Debug dump
+          schema:
+            type: string
+        "400":
+          description: Bad Request
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "401":
+          description: Unauthorized
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "403":
+          description: Forbidden
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "500":
+          description: Internal Server Error
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: HealthCheck endpoint
+      tags:
+      - healthcheck
   /jobs/tag_job/{id}:
     delete:
       consumes:
@@ -1279,7 +1650,7 @@ paths:
         required: true
         schema:
           items:
-            $ref: '#/definitions/api.ApiTag'
+            $ref: '#/definitions/api.APITag'
           type: array
       produces:
       - application/json
@@ -1309,6 +1680,176 @@ paths:
       summary: Removes one or more tags from a job
       tags:
       - Job add and modify
+  /jwt/:
+    get:
+      consumes:
+      - multipart/form-data
+      description: Generates a JWT token for a user. Admins can generate tokens for
+        any user, regular users only for themselves.
+      parameters:
+      - description: Username to generate JWT for
+        in: formData
+        name: username
+        required: true
+        type: string
+      produces:
+      - text/plain
+      responses:
+        "200":
+          description: JWT token
+          schema:
+            type: string
+        "403":
+          description: Forbidden
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "404":
+          description: User Not Found
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "500":
+          description: Internal Server Error
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Generate JWT token
+      tags:
+      - Frontend
+  /machine_state/{cluster}/{host}:
+    get:
+      description: Retrieves stored machine state data for a specific cluster node.
+        Validates cluster and host names to prevent path traversal.
+      parameters:
+      - description: Cluster name
+        in: path
+        name: cluster
+        required: true
+        type: string
+      - description: Host name
+        in: path
+        name: host
+        required: true
+        type: string
+      produces:
+      - application/json
+      responses:
+        "200":
+          description: Machine state JSON data
+          schema:
+            type: object
+        "400":
+          description: Bad Request
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "404":
+          description: Machine state not enabled or file not found
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Retrieve machine state
+      tags:
+      - Machine State
+    put:
+      consumes:
+      - application/json
+      description: Stores machine state data for a specific cluster node. Validates
+        cluster and host names to prevent path traversal.
+      parameters:
+      - description: Cluster name
+        in: path
+        name: cluster
+        required: true
+        type: string
+      - description: Host name
+        in: path
+        name: host
+        required: true
+        type: string
+      produces:
+      - text/plain
+      responses:
+        "201":
+          description: Created
+        "400":
+          description: Bad Request
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "404":
+          description: Machine state not enabled
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "500":
+          description: Internal Server Error
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Store machine state
+      tags:
+      - Machine State
+  /notice/:
+    post:
+      consumes:
+      - multipart/form-data
+      description: Updates the notice.txt file content. Only admins are allowed. Content
+        is limited to 10000 characters.
+      parameters:
+      - description: New notice content (max 10000 characters)
+        in: formData
+        name: new-content
+        required: true
+        type: string
+      produces:
+      - text/plain
+      responses:
+        "200":
+          description: Update Notice Content Success
+          schema:
+            type: string
+        "400":
+          description: Bad Request
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "403":
+          description: Forbidden
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "500":
+          description: Internal Server Error
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Update system notice
+      tags:
+      - Config
+  /roles/:
+    get:
+      description: Returns a list of valid user roles. Only admins are allowed.
+      produces:
+      - application/json
+      responses:
+        "200":
+          description: List of role names
+          schema:
+            items:
+              type: string
+            type: array
+        "403":
+          description: Forbidden
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "500":
+          description: Internal Server Error
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Get available roles
+      tags:
+      - Config
   /tags/:
     delete:
       consumes:
@@ -1324,7 +1865,7 @@ paths:
         required: true
         schema:
           items:
-            $ref: '#/definitions/api.ApiTag'
+            $ref: '#/definitions/api.APITag'
           type: array
       produces:
       - text/plain
@@ -1354,6 +1895,41 @@ paths:
       summary: Removes all tags and job-relations for type:name tuple
       tags:
       - Tag remove
+  /write/:
+    post:
+      consumes:
+      - text/plain
+      parameters:
+      - description: If the lines in the body do not have a cluster tag, use this
+          value instead.
+        in: query
+        name: cluster
+        type: string
+      produces:
+      - application/json
+      responses:
+        "200":
+          description: ok
+          schema:
+            type: string
+        "400":
+          description: Bad Request
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "401":
+          description: Unauthorized
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "403":
+          description: Forbidden
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "500":
+          description: Internal Server Error
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
 securityDefinitions:
   ApiKeyAuth:
     in: header
diff --git a/go.mod b/go.mod
index 808b2e7a..479f1644 100644
--- a/go.mod
+++ b/go.mod
@@ -11,7 +11,7 @@ tool (
 
 require (
 	github.com/99designs/gqlgen v0.17.85
-	github.com/ClusterCockpit/cc-lib/v2 v2.0.0
+	github.com/ClusterCockpit/cc-lib/v2 v2.1.0
 	github.com/Masterminds/squirrel v1.5.4
 	github.com/aws/aws-sdk-go-v2 v1.41.1
 	github.com/aws/aws-sdk-go-v2/config v1.32.6
@@ -109,7 +109,6 @@ require (
 	github.com/urfave/cli/v2 v2.27.7 // indirect
 	github.com/urfave/cli/v3 v3.6.1 // indirect
 	github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342 // indirect
-	github.com/xtgo/set v1.0.0 // indirect
 	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
 	golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b // indirect
@@ -119,7 +118,6 @@ require (
 	golang.org/x/sys v0.39.0 // indirect
 	golang.org/x/text v0.32.0 // indirect
 	golang.org/x/tools v0.40.0 // indirect
-	google.golang.org/protobuf v1.36.11 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 	sigs.k8s.io/yaml v1.6.0 // indirect
 )
diff --git a/go.sum b/go.sum
index 39571309..ef89e2d2 100644
--- a/go.sum
+++ b/go.sum
@@ -2,12 +2,10 @@ filippo.io/edwards25519 v1.1.0 h1:FNf4tywRC1HmFuKW5xopWpigGjJKiJSV0Cqo0cJWDaA=
 filippo.io/edwards25519 v1.1.0/go.mod h1:BxyFTGdWcka3PhytdK4V28tE5sGfRvvvRV7EaN4VDT4=
 github.com/99designs/gqlgen v0.17.85 h1:EkGx3U2FDcxQm8YDLQSpXIAVmpDyZ3IcBMOJi2nH1S0=
 github.com/99designs/gqlgen v0.17.85/go.mod h1:yvs8s0bkQlRfqg03YXr3eR4OQUowVhODT/tHzCXnbOU=
-github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161 h1:L/gRVlceqvL25UVaW/CKtUDjefjrs0SPonmDGUVOYP0=
-github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161/go.mod h1:xomTg63KZ2rFqZQzSB4Vz2SUXa1BpHTVz9L5PTmPC4E=
 github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358 h1:mFRzDkZVAjdal+s7s0MwaRv9igoPqLRdzOLzw/8Xvq8=
 github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358/go.mod h1:chxPXzSsl7ZWRAuOIE23GDNzjWuZquvFlgA8xmpunjU=
-github.com/ClusterCockpit/cc-lib/v2 v2.0.0 h1:OjDADx8mf9SflqeeKUuhy5pamu4YDucae6wUX6vvNNA=
-github.com/ClusterCockpit/cc-lib/v2 v2.0.0/go.mod h1:JuxMAuEOaLLNEnnL9U3ejha8kMvsSatLdKPZEgJw6iw=
+github.com/ClusterCockpit/cc-lib/v2 v2.1.0 h1:B6l6h0IjfEuY9DU6aVM3fSsj24lQ1eudXK9QTKmJjqg=
+github.com/ClusterCockpit/cc-lib/v2 v2.1.0/go.mod h1:JuxMAuEOaLLNEnnL9U3ejha8kMvsSatLdKPZEgJw6iw=
 github.com/KyleBanks/depth v1.2.1 h1:5h8fQADFrWtarTdtDudMmGsC7GPbOAu6RVB3ffsVFHc=
 github.com/KyleBanks/depth v1.2.1/go.mod h1:jzSb9d0L43HxTQfT+oSA1EEp2q+ne2uh6XgeJcm8brE=
 github.com/Masterminds/squirrel v1.5.4 h1:uUcX/aBc8O7Fg9kaISIUsHXdKuqehiXAMQTYX8afzqM=
@@ -74,10 +72,6 @@ github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6r
 github.com/bmatcuk/doublestar v1.1.1/go.mod h1:UD6OnuiIn0yFxxA2le/rnRU1G4RaI4UvFv1sNto9p6w=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/containerd/errdefs v1.0.0 h1:tg5yIfIlQIrxYtu9ajqY42W3lpS19XqdxRQeEwYG8PI=
-github.com/containerd/errdefs v1.0.0/go.mod h1:+YBYIdtsnF4Iw6nWZhJcqGSg/dwvV7tyJ/kCkyJ2k+M=
-github.com/containerd/errdefs/pkg v0.3.0 h1:9IKJ06FvyNlexW690DXuQNx2KA2cUJXx151Xdx3ZPPE=
-github.com/containerd/errdefs/pkg v0.3.0/go.mod h1:NJw6s9HwNuRhnjJhM7pylWwMyAkmCQvQ4GpJHEqRLVk=
 github.com/coreos/go-oidc/v3 v3.17.0 h1:hWBGaQfbi0iVviX4ibC7bk8OKT5qNr4klBaCHVNvehc=
 github.com/coreos/go-oidc/v3 v3.17.0/go.mod h1:wqPbKFrVnE90vty060SB40FCJ8fTHTxSwyXJqZH+sI8=
 github.com/cpuguy83/go-md2man/v2 v2.0.7 h1:zbFlGlXEAKlwXpmvle3d8Oe3YnkKIK4xSRTd3sHPnBo=
@@ -89,16 +83,6 @@ github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dgryski/trifles v0.0.0-20230903005119-f50d829f2e54 h1:SG7nF6SRlWhcT7cNTs5R6Hk4V2lcmLz2NsG2VnInyNo=
 github.com/dgryski/trifles v0.0.0-20230903005119-f50d829f2e54/go.mod h1:if7Fbed8SFyPtHLHbg49SI7NAdJiC5WIA09pe59rfAA=
-github.com/dhui/dktest v0.4.6 h1:+DPKyScKSEp3VLtbMDHcUq6V5Lm5zfZZVb0Sk7Ahom4=
-github.com/dhui/dktest v0.4.6/go.mod h1:JHTSYDtKkvFNFHJKqCzVzqXecyv+tKt8EzceOmQOgbU=
-github.com/distribution/reference v0.6.0 h1:0IXCQ5g4/QMHHkarYzh5l+u8T3t73zM5QvfrDyIgxBk=
-github.com/distribution/reference v0.6.0/go.mod h1:BbU0aIcezP1/5jX/8MP0YiH4SdvB5Y4f/wlDRiLyi3E=
-github.com/docker/docker v28.3.3+incompatible h1:Dypm25kh4rmk49v1eiVbsAtpAsYURjYkaKubwuBdxEI=
-github.com/docker/docker v28.3.3+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk=
-github.com/docker/go-connections v0.5.0 h1:USnMq7hx7gwdVZq1L49hLXaFtUdTADjXGp+uj1Br63c=
-github.com/docker/go-connections v0.5.0/go.mod h1:ov60Kzw0kKElRwhNs9UlUHAE/F9Fe6GLaXnqyDdmEXc=
-github.com/docker/go-units v0.5.0 h1:69rxXcBk27SvSaaxTtLh/8llcHD8vYHT7WSdRZ/jvr4=
-github.com/docker/go-units v0.5.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
 github.com/expr-lang/expr v1.17.7 h1:Q0xY/e/2aCIp8g9s/LGvMDCC5PxYlvHgDZRQ4y16JX8=
 github.com/expr-lang/expr v1.17.7/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
 github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
@@ -236,17 +220,8 @@ github.com/mattn/go-sqlite3 v1.10.0/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsO
 github.com/mattn/go-sqlite3 v1.14.22/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
 github.com/mattn/go-sqlite3 v1.14.33 h1:A5blZ5ulQo2AtayQ9/limgHEkFreKj1Dv226a1K73s0=
 github.com/mattn/go-sqlite3 v1.14.33/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
-github.com/moby/docker-image-spec v1.3.1 h1:jMKff3w6PgbfSa69GfNg+zN/XLhfXJGnEx3Nl2EsFP0=
-github.com/moby/docker-image-spec v1.3.1/go.mod h1:eKmb5VW8vQEh/BAr2yvVNvuiJuY6UIocYsFu/DxxRpo=
-github.com/moby/term v0.5.0 h1:xt8Q1nalod/v7BqbG21f8mQPqH+xAaC9C3N3wfWbVP0=
-github.com/moby/term v0.5.0/go.mod h1:8FzsFHVUBGZdbDsJw/ot+X+d5HLUbvklYLJ9uGfcI3Y=
-github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
-github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
-github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
-github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
-github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
-github.com/morikuni/aec v1.0.0 h1:nP9CBfwrvYnBRgY6qfDQkygYDmYwOilePFkwzv4dU8A=
-github.com/morikuni/aec v1.0.0/go.mod h1:BbKIizmSmc5MMPqRYbxO4ZU0S0+P200+tUnFx7PXmsc=
+github.com/minio/highwayhash v1.0.4-0.20251030100505-070ab1a87a76 h1:KGuD/pM2JpL9FAYvBrnBBeENKZNh6eNtjqytV6TYjnk=
+github.com/minio/highwayhash v1.0.4-0.20251030100505-070ab1a87a76/go.mod h1:GGYsuwP/fPD6Y9hMiXuapVvlIUEhFhMTh0rxU3ik1LQ=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
 github.com/nats-io/jwt/v2 v2.8.0 h1:K7uzyz50+yGZDO5o772eRE7atlcSEENpL7P+b74JV1g=
@@ -318,8 +293,6 @@ github.com/vektah/gqlparser/v2 v2.5.31 h1:YhWGA1mfTjID7qJhd1+Vxhpk5HTgydrGU9IgkW
 github.com/vektah/gqlparser/v2 v2.5.31/go.mod h1:c1I28gSOVNzlfc4WuDlqU7voQnsqI6OG2amkBAFmgts=
 github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342 h1:FnBeRrxr7OU4VvAzt5X7s6266i6cSVkkFPS0TuXWbIg=
 github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342/go.mod h1:Ohn+xnUBiLI6FVj/9LpzZWtj1/D6lUovWYBkxHVV3aM=
-github.com/xtgo/set v1.0.0 h1:6BCNBRv3ORNDQ7fyoJXRv+tstJz3m1JVFQErfeZz2pY=
-github.com/xtgo/set v1.0.0/go.mod h1:d3NHzGzSa0NmB2NhFyECA+QdRp29oEn2xbT+TpeFoM8=
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
diff --git a/internal/api/cluster.go b/internal/api/cluster.go
index b6f41244..d1c3c898 100644
--- a/internal/api/cluster.go
+++ b/internal/api/cluster.go
@@ -27,7 +27,7 @@ type GetClustersAPIResponse struct {
 // @description Get a list of all cluster configs. Specific cluster can be requested using query parameter.
 // @produce     json
 // @param       cluster        query    string            false "Job Cluster"
-// @success     200            {object} api.GetClustersApiResponse  "Array of clusters"
+// @success     200            {object} api.GetClustersAPIResponse  "Array of clusters"
 // @failure     400            {object} api.ErrorResponse       "Bad Request"
 // @failure     401            {object} api.ErrorResponse       "Unauthorized"
 // @failure     403            {object} api.ErrorResponse       "Forbidden"
diff --git a/internal/api/docs.go b/internal/api/docs.go
index d0b5c6fb..78eecfa3 100644
--- a/internal/api/docs.go
+++ b/internal/api/docs.go
@@ -25,11 +25,6 @@ const docTemplate = `{
     "paths": {
         "/api/clusters/": {
             "get": {
-                "security": [
-                    {
-                        "ApiKeyAuth": []
-                    }
-                ],
                 "description": "Get a list of all cluster configs. Specific cluster can be requested using query parameter.",
                 "produces": [
                     "application/json"
@@ -50,7 +45,7 @@ const docTemplate = `{
                     "200": {
                         "description": "Array of clusters",
                         "schema": {
-                            "$ref": "#/definitions/api.GetClustersApiResponse"
+                            "$ref": "#/definitions/api.GetClustersAPIResponse"
                         }
                     },
                     "400": {
@@ -77,16 +72,16 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/": {
-            "get": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/": {
+            "get": {
                 "description": "Get a list of all jobs. Filters can be applied using query parameters.\nNumber of results can be limited by page. Results are sorted by descending startTime.",
                 "produces": [
                     "application/json"
@@ -145,7 +140,7 @@ const docTemplate = `{
                     "200": {
                         "description": "Job array and page info",
                         "schema": {
-                            "$ref": "#/definitions/api.GetJobsApiResponse"
+                            "$ref": "#/definitions/api.GetJobsAPIResponse"
                         }
                     },
                     "400": {
@@ -172,16 +167,16 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/delete_job/": {
-            "delete": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/delete_job/": {
+            "delete": {
                 "description": "Job to delete is specified by request body. All fields are required in this case.",
                 "consumes": [
                     "application/json"
@@ -200,7 +195,7 @@ const docTemplate = `{
                         "in": "body",
                         "required": true,
                         "schema": {
-                            "$ref": "#/definitions/api.DeleteJobApiRequest"
+                            "$ref": "#/definitions/api.DeleteJobAPIRequest"
                         }
                     }
                 ],
@@ -208,7 +203,7 @@ const docTemplate = `{
                     "200": {
                         "description": "Success message",
                         "schema": {
-                            "$ref": "#/definitions/api.DefaultApiResponse"
+                            "$ref": "#/definitions/api.DefaultAPIResponse"
                         }
                     },
                     "400": {
@@ -247,16 +242,16 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/delete_job/{id}": {
-            "delete": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/delete_job/{id}": {
+            "delete": {
                 "description": "Job to remove is specified by database ID. This will not remove the job from the job archive.",
                 "produces": [
                     "application/json"
@@ -278,7 +273,7 @@ const docTemplate = `{
                     "200": {
                         "description": "Success message",
                         "schema": {
-                            "$ref": "#/definitions/api.DefaultApiResponse"
+                            "$ref": "#/definitions/api.DefaultAPIResponse"
                         }
                     },
                     "400": {
@@ -317,16 +312,16 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/delete_job_before/{ts}": {
-            "delete": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/delete_job_before/{ts}": {
+            "delete": {
                 "description": "Remove all jobs with start time before timestamp. The jobs will not be removed from the job archive.",
                 "produces": [
                     "application/json"
@@ -342,13 +337,19 @@ const docTemplate = `{
                         "name": "ts",
                         "in": "path",
                         "required": true
+                    },
+                    {
+                        "type": "boolean",
+                        "description": "Omit jobs with tags from deletion",
+                        "name": "omit-tagged",
+                        "in": "query"
                     }
                 ],
                 "responses": {
                     "200": {
                         "description": "Success message",
                         "schema": {
-                            "$ref": "#/definitions/api.DefaultApiResponse"
+                            "$ref": "#/definitions/api.DefaultAPIResponse"
                         }
                     },
                     "400": {
@@ -387,16 +388,16 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/edit_meta/{id}": {
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/edit_meta/{id}": {
+            "post": {
                 "description": "Edit key value pairs in job metadata json\nIf a key already exists its content will be overwritten",
                 "consumes": [
                     "application/json"
@@ -457,16 +458,16 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/start_job/": {
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/start_job/": {
+            "post": {
                 "description": "Job specified in request body will be saved to database as \"running\" with new DB ID.\nJob specifications follow the 'Job' scheme, API will fail to execute if requirements are not met.",
                 "consumes": [
                     "application/json"
@@ -493,7 +494,7 @@ const docTemplate = `{
                     "201": {
                         "description": "Job added successfully",
                         "schema": {
-                            "$ref": "#/definitions/api.DefaultApiResponse"
+                            "$ref": "#/definitions/api.DefaultAPIResponse"
                         }
                     },
                     "400": {
@@ -526,16 +527,16 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/stop_job/": {
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/stop_job/": {
+            "post": {
                 "description": "Job to stop is specified by request body. All fields are required in this case.\nReturns full job resource information according to 'Job' scheme.",
                 "produces": [
                     "application/json"
@@ -551,7 +552,7 @@ const docTemplate = `{
                         "in": "body",
                         "required": true,
                         "schema": {
-                            "$ref": "#/definitions/api.StopJobApiRequest"
+                            "$ref": "#/definitions/api.StopJobAPIRequest"
                         }
                     }
                 ],
@@ -598,16 +599,16 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/tag_job/{id}": {
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/tag_job/{id}": {
+            "post": {
                 "description": "Adds tag(s) to a job specified by DB ID. Name and Type of Tag(s) can be chosen freely.\nTag Scope for frontend visibility will default to \"global\" if none entered, other options: \"admin\" or specific username.\nIf tagged job is already finished: Tag will be written directly to respective archive files.",
                 "consumes": [
                     "application/json"
@@ -635,7 +636,7 @@ const docTemplate = `{
                         "schema": {
                             "type": "array",
                             "items": {
-                                "$ref": "#/definitions/api.ApiTag"
+                                "$ref": "#/definitions/api.APITag"
                             }
                         }
                     }
@@ -671,16 +672,16 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/jobs/{id}": {
-            "get": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/jobs/{id}": {
+            "get": {
                 "description": "Job to get is specified by database ID\nReturns full job resource information according to 'Job' scheme and all metrics according to 'JobData'.",
                 "produces": [
                     "application/json"
@@ -708,7 +709,7 @@ const docTemplate = `{
                     "200": {
                         "description": "Job resource",
                         "schema": {
-                            "$ref": "#/definitions/api.GetJobApiResponse"
+                            "$ref": "#/definitions/api.GetJobAPIResponse"
                         }
                     },
                     "400": {
@@ -747,14 +748,14 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            },
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            },
+            "post": {
                 "description": "Job to get is specified by database ID\nReturns full job resource information according to 'Job' scheme and all metrics according to 'JobData'.",
                 "consumes": [
                     "application/json"
@@ -791,7 +792,7 @@ const docTemplate = `{
                     "200": {
                         "description": "Job resource",
                         "schema": {
-                            "$ref": "#/definitions/api.GetJobApiResponse"
+                            "$ref": "#/definitions/api.GetJobAPIResponse"
                         }
                     },
                     "400": {
@@ -830,16 +831,16 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/nodestats/": {
-            "post": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
-                ],
+                ]
+            }
+        },
+        "/api/nodestats/": {
+            "post": {
                 "description": "Returns a JSON-encoded list of users.\nRequired query-parameter defines if all users or only users with additional special roles are returned.",
                 "produces": [
                     "application/json"
@@ -863,7 +864,7 @@ const docTemplate = `{
                     "200": {
                         "description": "Success message",
                         "schema": {
-                            "$ref": "#/definitions/api.DefaultApiResponse"
+                            "$ref": "#/definitions/api.DefaultAPIResponse"
                         }
                     },
                     "400": {
@@ -890,16 +891,86 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/api/users/": {
-            "get": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
+                ]
+            }
+        },
+        "/api/user/{id}": {
+            "post": {
+                "description": "Allows admins to add/remove roles and projects for a user",
+                "produces": [
+                    "text/plain"
                 ],
+                "tags": [
+                    "User"
+                ],
+                "summary": "Update user roles and projects",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Username",
+                        "name": "id",
+                        "in": "path",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Role to add",
+                        "name": "add-role",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "Role to remove",
+                        "name": "remove-role",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "Project to add",
+                        "name": "add-project",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "Project to remove",
+                        "name": "remove-project",
+                        "in": "formData"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Success message",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "422": {
+                        "description": "Unprocessable Entity",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/api/users/": {
+            "get": {
                 "description": "Returns a JSON-encoded list of users.\nRequired query-parameter defines if all users or only users with additional special roles are returned.",
                 "produces": [
                     "application/json"
@@ -923,7 +994,7 @@ const docTemplate = `{
                         "schema": {
                             "type": "array",
                             "items": {
-                                "$ref": "#/definitions/api.ApiReturnedUser"
+                                "$ref": "#/definitions/api.APIReturnedUser"
                             }
                         }
                     },
@@ -951,16 +1022,361 @@ const docTemplate = `{
                             "type": "string"
                         }
                     }
-                }
-            }
-        },
-        "/jobs/tag_job/{id}": {
-            "delete": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
+                ]
+            },
+            "post": {
+                "description": "Creates a new user with specified credentials and role",
+                "produces": [
+                    "text/plain"
                 ],
+                "tags": [
+                    "User"
+                ],
+                "summary": "Create a new user",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Username",
+                        "name": "username",
+                        "in": "formData",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Password (not required for API users)",
+                        "name": "password",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "User role",
+                        "name": "role",
+                        "in": "formData",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Full name",
+                        "name": "name",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "Email address",
+                        "name": "email",
+                        "in": "formData"
+                    },
+                    {
+                        "type": "string",
+                        "description": "Project (required for managers)",
+                        "name": "project",
+                        "in": "formData"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Success message",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "422": {
+                        "description": "Unprocessable Entity",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            },
+            "delete": {
+                "description": "Deletes a user from the system",
+                "produces": [
+                    "text/plain"
+                ],
+                "tags": [
+                    "User"
+                ],
+                "summary": "Delete a user",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Username to delete",
+                        "name": "username",
+                        "in": "formData",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Success",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "422": {
+                        "description": "Unprocessable Entity",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/configuration/": {
+            "post": {
+                "description": "Updates a user's configuration key-value pair.",
+                "consumes": [
+                    "multipart/form-data"
+                ],
+                "produces": [
+                    "text/plain"
+                ],
+                "tags": [
+                    "Frontend"
+                ],
+                "summary": "Update user configuration",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Configuration key",
+                        "name": "key",
+                        "in": "formData",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Configuration value",
+                        "name": "value",
+                        "in": "formData",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "success",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/debug/": {
+            "post": {
+                "description": "This endpoint allows the users to print the content of",
+                "produces": [
+                    "application/json"
+                ],
+                "tags": [
+                    "debug"
+                ],
+                "summary": "Debug endpoint",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Selector",
+                        "name": "selector",
+                        "in": "query"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Debug dump",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "401": {
+                        "description": "Unauthorized",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/free/": {
+            "post": {
+                "description": "This endpoint allows the users to free the Buffers from the",
+                "produces": [
+                    "application/json"
+                ],
+                "tags": [
+                    "free"
+                ],
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "up to timestamp",
+                        "name": "to",
+                        "in": "query"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "ok",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "401": {
+                        "description": "Unauthorized",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/healthcheck/": {
+            "get": {
+                "description": "This endpoint allows the users to check if a node is healthy",
+                "produces": [
+                    "application/json"
+                ],
+                "tags": [
+                    "healthcheck"
+                ],
+                "summary": "HealthCheck endpoint",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Selector",
+                        "name": "selector",
+                        "in": "query"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Debug dump",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "401": {
+                        "description": "Unauthorized",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/jobs/tag_job/{id}": {
+            "delete": {
                 "description": "Removes tag(s) from a job specified by DB ID. Name and Type of Tag(s) must match.\nTag Scope is required for matching, options: \"global\", \"admin\". Private tags can not be deleted via API.\nIf tagged job is already finished: Tag will be removed from respective archive files.",
                 "consumes": [
                     "application/json"
@@ -988,7 +1404,7 @@ const docTemplate = `{
                         "schema": {
                             "type": "array",
                             "items": {
-                                "$ref": "#/definitions/api.ApiTag"
+                                "$ref": "#/definitions/api.APITag"
                             }
                         }
                     }
@@ -1024,16 +1440,276 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
-            }
-        },
-        "/tags/": {
-            "delete": {
+                },
                 "security": [
                     {
                         "ApiKeyAuth": []
                     }
+                ]
+            }
+        },
+        "/jwt/": {
+            "get": {
+                "description": "Generates a JWT token for a user. Admins can generate tokens for any user, regular users only for themselves.",
+                "consumes": [
+                    "multipart/form-data"
                 ],
+                "produces": [
+                    "text/plain"
+                ],
+                "tags": [
+                    "Frontend"
+                ],
+                "summary": "Generate JWT token",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Username to generate JWT for",
+                        "name": "username",
+                        "in": "formData",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "JWT token",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "404": {
+                        "description": "User Not Found",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/machine_state/{cluster}/{host}": {
+            "get": {
+                "description": "Retrieves stored machine state data for a specific cluster node. Validates cluster and host names to prevent path traversal.",
+                "produces": [
+                    "application/json"
+                ],
+                "tags": [
+                    "Machine State"
+                ],
+                "summary": "Retrieve machine state",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Cluster name",
+                        "name": "cluster",
+                        "in": "path",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Host name",
+                        "name": "host",
+                        "in": "path",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Machine state JSON data",
+                        "schema": {
+                            "type": "object"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "404": {
+                        "description": "Machine state not enabled or file not found",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            },
+            "put": {
+                "description": "Stores machine state data for a specific cluster node. Validates cluster and host names to prevent path traversal.",
+                "consumes": [
+                    "application/json"
+                ],
+                "produces": [
+                    "text/plain"
+                ],
+                "tags": [
+                    "Machine State"
+                ],
+                "summary": "Store machine state",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "Cluster name",
+                        "name": "cluster",
+                        "in": "path",
+                        "required": true
+                    },
+                    {
+                        "type": "string",
+                        "description": "Host name",
+                        "name": "host",
+                        "in": "path",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "201": {
+                        "description": "Created"
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "404": {
+                        "description": "Machine state not enabled",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/notice/": {
+            "post": {
+                "description": "Updates the notice.txt file content. Only admins are allowed. Content is limited to 10000 characters.",
+                "consumes": [
+                    "multipart/form-data"
+                ],
+                "produces": [
+                    "text/plain"
+                ],
+                "tags": [
+                    "Config"
+                ],
+                "summary": "Update system notice",
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "New notice content (max 10000 characters)",
+                        "name": "new-content",
+                        "in": "formData",
+                        "required": true
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "Update Notice Content Success",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/roles/": {
+            "get": {
+                "description": "Returns a list of valid user roles. Only admins are allowed.",
+                "produces": [
+                    "application/json"
+                ],
+                "tags": [
+                    "Config"
+                ],
+                "summary": "Get available roles",
+                "responses": {
+                    "200": {
+                        "description": "List of role names",
+                        "schema": {
+                            "type": "array",
+                            "items": {
+                                "type": "string"
+                            }
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/tags/": {
+            "delete": {
                 "description": "Removes tags by type and name. Name and Type of Tag(s) must match.\nTag Scope is required for matching, options: \"global\", \"admin\". Private tags can not be deleted via API.\nTag wills be removed from respective archive files.",
                 "consumes": [
                     "application/json"
@@ -1054,7 +1730,7 @@ const docTemplate = `{
                         "schema": {
                             "type": "array",
                             "items": {
-                                "$ref": "#/definitions/api.ApiTag"
+                                "$ref": "#/definitions/api.APITag"
                             }
                         }
                     }
@@ -1090,12 +1766,72 @@ const docTemplate = `{
                             "$ref": "#/definitions/api.ErrorResponse"
                         }
                     }
-                }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
+            }
+        },
+        "/write/": {
+            "post": {
+                "consumes": [
+                    "text/plain"
+                ],
+                "produces": [
+                    "application/json"
+                ],
+                "parameters": [
+                    {
+                        "type": "string",
+                        "description": "If the lines in the body do not have a cluster tag, use this value instead.",
+                        "name": "cluster",
+                        "in": "query"
+                    }
+                ],
+                "responses": {
+                    "200": {
+                        "description": "ok",
+                        "schema": {
+                            "type": "string"
+                        }
+                    },
+                    "400": {
+                        "description": "Bad Request",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "401": {
+                        "description": "Unauthorized",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "403": {
+                        "description": "Forbidden",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    },
+                    "500": {
+                        "description": "Internal Server Error",
+                        "schema": {
+                            "$ref": "#/definitions/api.ErrorResponse"
+                        }
+                    }
+                },
+                "security": [
+                    {
+                        "ApiKeyAuth": []
+                    }
+                ]
             }
         }
     },
     "definitions": {
-        "api.ApiReturnedUser": {
+        "api.APIReturnedUser": {
             "type": "object",
             "properties": {
                 "email": {
@@ -1121,7 +1857,7 @@ const docTemplate = `{
                 }
             }
         },
-        "api.ApiTag": {
+        "api.APITag": {
             "type": "object",
             "properties": {
                 "name": {
@@ -1141,7 +1877,7 @@ const docTemplate = `{
                 }
             }
         },
-        "api.DefaultApiResponse": {
+        "api.DefaultAPIResponse": {
             "type": "object",
             "properties": {
                 "msg": {
@@ -1149,7 +1885,7 @@ const docTemplate = `{
                 }
             }
         },
-        "api.DeleteJobApiRequest": {
+        "api.DeleteJobAPIRequest": {
             "type": "object",
             "required": [
                 "jobId"
@@ -1198,7 +1934,7 @@ const docTemplate = `{
                 }
             }
         },
-        "api.GetClustersApiResponse": {
+        "api.GetClustersAPIResponse": {
             "type": "object",
             "properties": {
                 "clusters": {
@@ -1210,7 +1946,7 @@ const docTemplate = `{
                 }
             }
         },
-        "api.GetJobApiResponse": {
+        "api.GetJobAPIResponse": {
             "type": "object",
             "properties": {
                 "data": {
@@ -1224,7 +1960,7 @@ const docTemplate = `{
                 }
             }
         },
-        "api.GetJobsApiResponse": {
+        "api.GetJobsAPIResponse": {
             "type": "object",
             "properties": {
                 "items": {
@@ -1258,39 +1994,7 @@ const docTemplate = `{
                 }
             }
         },
-        "api.Node": {
-            "type": "object",
-            "properties": {
-                "cpusAllocated": {
-                    "type": "integer"
-                },
-                "cpusTotal": {
-                    "type": "integer"
-                },
-                "gpusAllocated": {
-                    "type": "integer"
-                },
-                "gpusTotal": {
-                    "type": "integer"
-                },
-                "hostname": {
-                    "type": "string"
-                },
-                "memoryAllocated": {
-                    "type": "integer"
-                },
-                "memoryTotal": {
-                    "type": "integer"
-                },
-                "states": {
-                    "type": "array",
-                    "items": {
-                        "type": "string"
-                    }
-                }
-            }
-        },
-        "api.StopJobApiRequest": {
+        "api.StopJobAPIRequest": {
             "type": "object",
             "required": [
                 "jobState",
@@ -1333,7 +2037,7 @@ const docTemplate = `{
                 "nodes": {
                     "type": "array",
                     "items": {
-                        "$ref": "#/definitions/api.Node"
+                        "$ref": "#/definitions/schema.NodePayload"
                     }
                 }
             }
@@ -1342,12 +2046,15 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "id": {
+                    "description": "Unique identifier for the accelerator (e.g., \"0\", \"1\", \"GPU-0\")",
                     "type": "string"
                 },
                 "model": {
+                    "description": "Specific model name (e.g., \"A100\", \"MI100\")",
                     "type": "string"
                 },
                 "type": {
+                    "description": "Type of accelerator (e.g., \"Nvidia GPU\", \"AMD GPU\")",
                     "type": "string"
                 }
             }
@@ -1356,15 +2063,18 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "metricConfig": {
+                    "description": "Cluster-wide metric configurations",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.MetricConfig"
                     }
                 },
                 "name": {
+                    "description": "Unique cluster name (e.g., \"fritz\", \"alex\")",
                     "type": "string"
                 },
                 "subClusters": {
+                    "description": "Homogeneous partitions within the cluster",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.SubCluster"
@@ -1373,6 +2083,7 @@ const docTemplate = `{
             }
         },
         "schema.Job": {
+            "description": "Information of a HPC job.",
             "type": "object",
             "properties": {
                 "arrayJobId": {
@@ -1401,6 +2112,13 @@ const docTemplate = `{
                         "format": "float64"
                     }
                 },
+                "exclusive": {
+                    "description": "for backwards compatibility",
+                    "type": "integer",
+                    "maximum": 2,
+                    "minimum": 0,
+                    "example": 1
+                },
                 "footprint": {
                     "type": "object",
                     "additionalProperties": {
@@ -1423,7 +2141,7 @@ const docTemplate = `{
                         "deadline",
                         "failed",
                         "node_fail",
-                        "out_of_memory",
+                        "out-of-memory",
                         "pending",
                         "preempted",
                         "running",
@@ -1535,9 +2253,11 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "id": {
+                    "description": "Internal database ID",
                     "type": "integer"
                 },
                 "jobId": {
+                    "description": "The job's external job ID",
                     "type": "integer"
                 }
             }
@@ -1546,9 +2266,11 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "count": {
+                    "description": "Total count of available items",
                     "type": "integer"
                 },
                 "items": {
+                    "description": "List of job links",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.JobLink"
@@ -1560,19 +2282,31 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "series": {
+                    "description": "Individual time series data",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.Series"
                     }
                 },
                 "statisticsSeries": {
-                    "$ref": "#/definitions/schema.StatsSeries"
+                    "description": "Aggregated statistics over time",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.StatsSeries"
+                        }
+                    ]
                 },
                 "timestep": {
+                    "description": "Sampling interval in seconds",
                     "type": "integer"
                 },
                 "unit": {
-                    "$ref": "#/definitions/schema.Unit"
+                    "description": "Unit of measurement",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.Unit"
+                        }
+                    ]
                 }
             }
         },
@@ -1638,46 +2372,71 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "aggregation": {
+                    "description": "Aggregation function (avg, sum, min, max)",
                     "type": "string"
                 },
                 "alert": {
+                    "description": "Alert threshold (requires attention)",
                     "type": "number"
                 },
                 "caution": {
+                    "description": "Caution threshold (concerning but not critical)",
                     "type": "number"
                 },
                 "energy": {
+                    "description": "Energy measurement method",
                     "type": "string"
                 },
                 "footprint": {
+                    "description": "Footprint category",
                     "type": "string"
                 },
                 "lowerIsBetter": {
+                    "description": "Whether lower values are better",
                     "type": "boolean"
                 },
                 "name": {
+                    "description": "Metric name (e.g., \"cpu_load\", \"mem_used\")",
                     "type": "string"
                 },
                 "normal": {
+                    "description": "Normal/typical value (good performance)",
                     "type": "number"
                 },
                 "peak": {
+                    "description": "Peak/maximum expected value (best performance)",
                     "type": "number"
                 },
+                "restrict": {
+                    "description": "Restrict visibility to non user roles",
+                    "type": "boolean"
+                },
                 "scope": {
-                    "$ref": "#/definitions/schema.MetricScope"
+                    "description": "Metric scope (node, socket, core, etc.)",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.MetricScope"
+                        }
+                    ]
                 },
                 "subClusters": {
+                    "description": "Subcluster-specific overrides",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.SubClusterConfig"
                     }
                 },
                 "timestep": {
+                    "description": "Measurement interval in seconds",
                     "type": "integer"
                 },
                 "unit": {
-                    "$ref": "#/definitions/schema.Unit"
+                    "description": "Unit of measurement",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.Unit"
+                        }
+                    ]
                 }
             }
         },
@@ -1706,12 +2465,15 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "avg": {
+                    "description": "Average/mean value",
                     "type": "number"
                 },
                 "max": {
+                    "description": "Maximum value",
                     "type": "number"
                 },
                 "min": {
+                    "description": "Minimum value",
                     "type": "number"
                 }
             }
@@ -1720,30 +2482,72 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "unit": {
-                    "$ref": "#/definitions/schema.Unit"
+                    "description": "Unit of measurement (e.g., FLOP/s, GB/s)",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.Unit"
+                        }
+                    ]
                 },
                 "value": {
+                    "description": "Numeric value of the measurement",
                     "type": "number"
                 }
             }
         },
+        "schema.NodePayload": {
+            "type": "object",
+            "properties": {
+                "cpusAllocated": {
+                    "description": "Number of allocated CPUs",
+                    "type": "integer"
+                },
+                "gpusAllocated": {
+                    "description": "Number of allocated GPUs",
+                    "type": "integer"
+                },
+                "hostname": {
+                    "description": "Node hostname",
+                    "type": "string"
+                },
+                "jobsRunning": {
+                    "description": "Number of running jobs",
+                    "type": "integer"
+                },
+                "memoryAllocated": {
+                    "description": "Allocated memory in MB",
+                    "type": "integer"
+                },
+                "states": {
+                    "description": "State strings (flexible format)",
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    }
+                }
+            }
+        },
         "schema.Resource": {
             "description": "A resource used by a job",
             "type": "object",
             "properties": {
                 "accelerators": {
+                    "description": "Allocated accelerator IDs (e.g., GPU IDs)",
                     "type": "array",
                     "items": {
                         "type": "string"
                     }
                 },
                 "configuration": {
+                    "description": "Optional configuration identifier",
                     "type": "string"
                 },
                 "hostname": {
+                    "description": "Node hostname",
                     "type": "string"
                 },
                 "hwthreads": {
+                    "description": "Allocated hardware thread IDs",
                     "type": "array",
                     "items": {
                         "type": "integer"
@@ -1755,19 +2559,27 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "data": {
+                    "description": "Time series measurements",
                     "type": "array",
                     "items": {
                         "type": "number"
                     }
                 },
                 "hostname": {
+                    "description": "Source hostname",
                     "type": "string"
                 },
                 "id": {
+                    "description": "Optional ID (e.g., core ID, GPU ID)",
                     "type": "string"
                 },
                 "statistics": {
-                    "$ref": "#/definitions/schema.MetricStatistics"
+                    "description": "Statistical summary (min/avg/max)",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.MetricStatistics"
+                        }
+                    ]
                 }
             }
         },
@@ -1775,30 +2587,35 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "max": {
+                    "description": "Maximum values over time",
                     "type": "array",
                     "items": {
                         "type": "number"
                     }
                 },
                 "mean": {
+                    "description": "Mean values over time",
                     "type": "array",
                     "items": {
                         "type": "number"
                     }
                 },
                 "median": {
+                    "description": "Median values over time",
                     "type": "array",
                     "items": {
                         "type": "number"
                     }
                 },
                 "min": {
+                    "description": "Minimum values over time",
                     "type": "array",
                     "items": {
                         "type": "number"
                     }
                 },
                 "percentiles": {
+                    "description": "Percentile values over time (e.g., 10th, 50th, 90th)",
                     "type": "object",
                     "additionalProperties": {
                         "type": "array",
@@ -1814,52 +2631,81 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "coresPerSocket": {
+                    "description": "Number of cores per CPU socket",
                     "type": "integer"
                 },
                 "energyFootprint": {
+                    "description": "Energy-related footprint metrics",
                     "type": "array",
                     "items": {
                         "type": "string"
                     }
                 },
                 "flopRateScalar": {
-                    "$ref": "#/definitions/schema.MetricValue"
+                    "description": "Theoretical scalar FLOP rate per node",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.MetricValue"
+                        }
+                    ]
                 },
                 "flopRateSimd": {
-                    "$ref": "#/definitions/schema.MetricValue"
+                    "description": "Theoretical SIMD FLOP rate per node",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.MetricValue"
+                        }
+                    ]
                 },
                 "footprint": {
+                    "description": "Default footprint metrics for jobs",
                     "type": "array",
                     "items": {
                         "type": "string"
                     }
                 },
                 "memoryBandwidth": {
-                    "$ref": "#/definitions/schema.MetricValue"
+                    "description": "Theoretical memory bandwidth per node",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.MetricValue"
+                        }
+                    ]
                 },
                 "metricConfig": {
+                    "description": "Subcluster-specific metric configurations",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.MetricConfig"
                     }
                 },
                 "name": {
+                    "description": "Name of the subcluster (e.g., \"main\", \"gpu\", \"bigmem\")",
                     "type": "string"
                 },
                 "nodes": {
+                    "description": "Node list in condensed format (e.g., \"node[001-100]\")",
                     "type": "string"
                 },
                 "processorType": {
+                    "description": "CPU model (e.g., \"Intel Xeon Gold 6148\")",
                     "type": "string"
                 },
                 "socketsPerNode": {
+                    "description": "Number of CPU sockets per node",
                     "type": "integer"
                 },
                 "threadsPerCore": {
+                    "description": "Number of hardware threads per core (SMT level)",
                     "type": "integer"
                 },
                 "topology": {
-                    "$ref": "#/definitions/schema.Topology"
+                    "description": "Hardware topology of nodes in this subcluster",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.Topology"
+                        }
+                    ]
                 }
             }
         },
@@ -1867,34 +2713,52 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "alert": {
+                    "description": "Alert threshold (requires attention)",
                     "type": "number"
                 },
                 "caution": {
+                    "description": "Caution threshold (concerning but not critical)",
                     "type": "number"
                 },
                 "energy": {
+                    "description": "Energy measurement configuration",
                     "type": "string"
                 },
                 "footprint": {
+                    "description": "Footprint category for this metric",
                     "type": "string"
                 },
                 "lowerIsBetter": {
+                    "description": "Whether lower values indicate better performance",
                     "type": "boolean"
                 },
                 "name": {
+                    "description": "Metric name (e.g., \"cpu_load\", \"mem_used\")",
                     "type": "string"
                 },
                 "normal": {
+                    "description": "Normal/typical value (good performance)",
                     "type": "number"
                 },
                 "peak": {
+                    "description": "Peak/maximum expected value (best performance)",
                     "type": "number"
                 },
                 "remove": {
+                    "description": "Whether to exclude this metric for this subcluster",
+                    "type": "boolean"
+                },
+                "restrict": {
+                    "description": "Restrict visibility to non user roles",
                     "type": "boolean"
                 },
                 "unit": {
-                    "$ref": "#/definitions/schema.Unit"
+                    "description": "Unit of measurement",
+                    "allOf": [
+                        {
+                            "$ref": "#/definitions/schema.Unit"
+                        }
+                    ]
                 }
             }
         },
@@ -1923,12 +2787,14 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "accelerators": {
+                    "description": "Attached accelerators (GPUs, etc.)",
                     "type": "array",
                     "items": {
                         "$ref": "#/definitions/schema.Accelerator"
                     }
                 },
                 "core": {
+                    "description": "Hardware threads grouped by core",
                     "type": "array",
                     "items": {
                         "type": "array",
@@ -1938,6 +2804,7 @@ const docTemplate = `{
                     }
                 },
                 "die": {
+                    "description": "Hardware threads grouped by die (optional)",
                     "type": "array",
                     "items": {
                         "type": "array",
@@ -1947,6 +2814,7 @@ const docTemplate = `{
                     }
                 },
                 "memoryDomain": {
+                    "description": "Hardware threads grouped by NUMA domain",
                     "type": "array",
                     "items": {
                         "type": "array",
@@ -1956,12 +2824,14 @@ const docTemplate = `{
                     }
                 },
                 "node": {
+                    "description": "All hardware thread IDs on this node",
                     "type": "array",
                     "items": {
                         "type": "integer"
                     }
                 },
                 "socket": {
+                    "description": "Hardware threads grouped by socket",
                     "type": "array",
                     "items": {
                         "type": "array",
@@ -1976,9 +2846,11 @@ const docTemplate = `{
             "type": "object",
             "properties": {
                 "base": {
+                    "description": "Base unit (e.g., \"B/s\", \"F/s\", \"W\")",
                     "type": "string"
                 },
                 "prefix": {
+                    "description": "SI prefix (e.g., \"G\", \"M\", \"K\", \"T\")",
                     "type": "string"
                 }
             }
diff --git a/internal/api/job.go b/internal/api/job.go
index 09f7b22c..1b1e05d6 100644
--- a/internal/api/job.go
+++ b/internal/api/job.go
@@ -104,7 +104,7 @@ type JobMetricWithName struct {
 // @param       items-per-page query    int               false "Items per page (Default: 25)"
 // @param       page           query    int               false "Page Number (Default: 1)"
 // @param       with-metadata  query    bool              false "Include metadata (e.g. jobScript) in response"
-// @success     200            {object} api.GetJobsApiResponse  "Job array and page info"
+// @success     200            {object} api.GetJobsAPIResponse  "Job array and page info"
 // @failure     400            {object} api.ErrorResponse       "Bad Request"
 // @failure     401   		   {object} api.ErrorResponse       "Unauthorized"
 // @failure     403            {object} api.ErrorResponse       "Forbidden"
@@ -232,7 +232,7 @@ func (api *RestAPI) getJobs(rw http.ResponseWriter, r *http.Request) {
 // @produce     json
 // @param       id          path     int                  true "Database ID of Job"
 // @param       all-metrics query    bool                 false "Include all available metrics"
-// @success     200     {object} api.GetJobApiResponse      "Job resource"
+// @success     200     {object} api.GetJobAPIResponse      "Job resource"
 // @failure     400     {object} api.ErrorResponse          "Bad Request"
 // @failure     401     {object} api.ErrorResponse          "Unauthorized"
 // @failure     403     {object} api.ErrorResponse          "Forbidden"
@@ -324,8 +324,8 @@ func (api *RestAPI) getCompleteJobByID(rw http.ResponseWriter, r *http.Request)
 // @accept      json
 // @produce     json
 // @param       id          path     int                  true "Database ID of Job"
-// @param       request     body     api.GetJobApiRequest true  "Array of metric names"
-// @success     200     {object} api.GetJobApiResponse      "Job resource"
+// @param       request     body     api.GetJobAPIRequest true  "Array of metric names"
+// @success     200     {object} api.GetJobAPIResponse      "Job resource"
 // @failure     400     {object} api.ErrorResponse          "Bad Request"
 // @failure     401     {object} api.ErrorResponse          "Unauthorized"
 // @failure     403     {object} api.ErrorResponse          "Forbidden"
@@ -478,7 +478,7 @@ func (api *RestAPI) editMeta(rw http.ResponseWriter, r *http.Request) {
 // @accept      json
 // @produce     json
 // @param       id      path     int                  true "Job Database ID"
-// @param       request body     api.TagJobApiRequest true "Array of tag-objects to add"
+// @param       request body     api.TagJobAPIRequest true "Array of tag-objects to add"
 // @success     200     {object} schema.Job                "Updated job resource"
 // @failure     400     {object} api.ErrorResponse         "Bad Request"
 // @failure     401     {object} api.ErrorResponse         "Unauthorized"
@@ -542,7 +542,7 @@ func (api *RestAPI) tagJob(rw http.ResponseWriter, r *http.Request) {
 // @accept      json
 // @produce     json
 // @param       id      path     int                  true "Job Database ID"
-// @param       request body     api.TagJobApiRequest true "Array of tag-objects to remove"
+// @param       request body     api.TagJobAPIRequest true "Array of tag-objects to remove"
 // @success     200     {object} schema.Job                "Updated job resource"
 // @failure     400     {object} api.ErrorResponse         "Bad Request"
 // @failure     401     {object} api.ErrorResponse         "Unauthorized"
@@ -606,7 +606,7 @@ func (api *RestAPI) removeTagJob(rw http.ResponseWriter, r *http.Request) {
 // @description Tag wills be removed from respective archive files.
 // @accept      json
 // @produce     plain
-// @param       request body     api.TagJobApiRequest true "Array of tag-objects to remove"
+// @param       request body     api.TagJobAPIRequest true "Array of tag-objects to remove"
 // @success     200     {string} string                    "Success Response"
 // @failure     400     {object} api.ErrorResponse         "Bad Request"
 // @failure     401     {object} api.ErrorResponse         "Unauthorized"
@@ -650,7 +650,7 @@ func (api *RestAPI) removeTags(rw http.ResponseWriter, r *http.Request) {
 // @accept      json
 // @produce     json
 // @param       request body     schema.Job true "Job to add"
-// @success     201     {object} api.DefaultApiResponse    "Job added successfully"
+// @success     201     {object} api.DefaultAPIResponse    "Job added successfully"
 // @failure     400     {object} api.ErrorResponse            "Bad Request"
 // @failure     401     {object} api.ErrorResponse            "Unauthorized"
 // @failure     403     {object} api.ErrorResponse            "Forbidden"
@@ -728,7 +728,7 @@ func (api *RestAPI) startJob(rw http.ResponseWriter, r *http.Request) {
 // @description Job to stop is specified by request body. All fields are required in this case.
 // @description Returns full job resource information according to 'Job' scheme.
 // @produce     json
-// @param       request body     api.StopJobApiRequest true "All fields required"
+// @param       request body     api.StopJobAPIRequest true "All fields required"
 // @success     200     {object} schema.Job                 "Success message"
 // @failure     400     {object} api.ErrorResponse          "Bad Request"
 // @failure     401     {object} api.ErrorResponse          "Unauthorized"
@@ -754,7 +754,6 @@ func (api *RestAPI) stopJobByRequest(rw http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	// cclog.Printf("loading db job for stopJobByRequest... : stopJobApiRequest=%v", req)
 	job, err = api.JobRepository.Find(req.JobID, req.Cluster, req.StartTime)
 	if err != nil {
 		// Try cached jobs if not found in main repository
@@ -776,7 +775,7 @@ func (api *RestAPI) stopJobByRequest(rw http.ResponseWriter, r *http.Request) {
 // @description Job to remove is specified by database ID. This will not remove the job from the job archive.
 // @produce     json
 // @param       id      path     int                   true "Database ID of Job"
-// @success     200     {object} api.DefaultApiResponse  "Success message"
+// @success     200     {object} api.DefaultAPIResponse  "Success message"
 // @failure     400     {object} api.ErrorResponse          "Bad Request"
 // @failure     401     {object} api.ErrorResponse          "Unauthorized"
 // @failure     403     {object} api.ErrorResponse          "Forbidden"
@@ -820,8 +819,8 @@ func (api *RestAPI) deleteJobByID(rw http.ResponseWriter, r *http.Request) {
 // @description Job to delete is specified by request body. All fields are required in this case.
 // @accept      json
 // @produce     json
-// @param       request body     api.DeleteJobApiRequest true "All fields required"
-// @success     200     {object} api.DefaultApiResponse  "Success message"
+// @param       request body     api.DeleteJobAPIRequest true "All fields required"
+// @success     200     {object} api.DefaultAPIResponse  "Success message"
 // @failure     400     {object} api.ErrorResponse          "Bad Request"
 // @failure     401     {object} api.ErrorResponse          "Unauthorized"
 // @failure     403     {object} api.ErrorResponse          "Forbidden"
@@ -873,7 +872,7 @@ func (api *RestAPI) deleteJobByRequest(rw http.ResponseWriter, r *http.Request)
 // @description Remove all jobs with start time before timestamp. The jobs will not be removed from the job archive.
 // @produce     json
 // @param       ts      path     int                   true "Unix epoch timestamp"
-// @success     200     {object} api.DefaultApiResponse  "Success message"
+// @success     200     {object} api.DefaultAPIResponse  "Success message"
 // @failure     400     {object} api.ErrorResponse          "Bad Request"
 // @failure     401     {object} api.ErrorResponse          "Unauthorized"
 // @failure     403     {object} api.ErrorResponse          "Forbidden"
diff --git a/internal/api/node.go b/internal/api/node.go
index 350f097d..4ad5337a 100644
--- a/internal/api/node.go
+++ b/internal/api/node.go
@@ -47,7 +47,7 @@ func determineState(states []string) schema.SchedulerState {
 // @description Required query-parameter defines if all users or only users with additional special roles are returned.
 // @produce     json
 // @param       request body UpdateNodeStatesRequest true "Request body containing nodes and their states"
-// @success     200     {object} api.DefaultApiResponse "Success message"
+// @success     200     {object} api.DefaultAPIResponse "Success message"
 // @failure     400     {object} api.ErrorResponse      "Bad Request"
 // @failure     401     {object} api.ErrorResponse      "Unauthorized"
 // @failure     403     {object} api.ErrorResponse      "Forbidden"
diff --git a/internal/api/user.go b/internal/api/user.go
index 1821b69b..5564fd61 100644
--- a/internal/api/user.go
+++ b/internal/api/user.go
@@ -31,7 +31,7 @@ type APIReturnedUser struct {
 // @description Required query-parameter defines if all users or only users with additional special roles are returned.
 // @produce     json
 // @param       not-just-user query bool true "If returned list should contain all users or only users with additional special roles"
-// @success     200     {array} api.ApiReturnedUser "List of users returned successfully"
+// @success     200     {array} api.APIReturnedUser "List of users returned successfully"
 // @failure     400     {string} string             "Bad Request"
 // @failure     401     {string} string             "Unauthorized"
 // @failure     403     {string} string             "Forbidden"
diff --git a/internal/graph/generated/generated.go b/internal/graph/generated/generated.go
index 2d3aca04..c218c0af 100644
--- a/internal/graph/generated/generated.go
+++ b/internal/graph/generated/generated.go
@@ -10815,7 +10815,7 @@ func (ec *executionContext) _SubCluster_metricConfig(ctx context.Context, field
 			return obj.MetricConfig, nil
 		},
 		nil,
-		ec.marshalNMetricConfig2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfigᚄ,
+		ec.marshalNMetricConfig2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfigᚄ,
 		true,
 		true,
 	)
@@ -18466,11 +18466,7 @@ func (ec *executionContext) marshalNJobsStatistics2ᚖgithubᚗcomᚋClusterCock
 	return ec._JobsStatistics(ctx, sel, v)
 }
 
-func (ec *executionContext) marshalNMetricConfig2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfig(ctx context.Context, sel ast.SelectionSet, v schema.MetricConfig) graphql.Marshaler {
-	return ec._MetricConfig(ctx, sel, &v)
-}
-
-func (ec *executionContext) marshalNMetricConfig2ᚕgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfigᚄ(ctx context.Context, sel ast.SelectionSet, v []schema.MetricConfig) graphql.Marshaler {
+func (ec *executionContext) marshalNMetricConfig2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfigᚄ(ctx context.Context, sel ast.SelectionSet, v []*schema.MetricConfig) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
 	isLen1 := len(v) == 1
@@ -18494,7 +18490,7 @@ func (ec *executionContext) marshalNMetricConfig2ᚕgithubᚗcomᚋClusterCockpi
 			if !isLen1 {
 				defer wg.Done()
 			}
-			ret[i] = ec.marshalNMetricConfig2githubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfig(ctx, sel, v[i])
+			ret[i] = ec.marshalNMetricConfig2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfig(ctx, sel, v[i])
 		}
 		if isLen1 {
 			f(i)
@@ -18514,6 +18510,16 @@ func (ec *executionContext) marshalNMetricConfig2ᚕgithubᚗcomᚋClusterCockpi
 	return ret
 }
 
+func (ec *executionContext) marshalNMetricConfig2ᚖgithubᚗcomᚋClusterCockpitᚋccᚑlibᚋv2ᚋschemaᚐMetricConfig(ctx context.Context, sel ast.SelectionSet, v *schema.MetricConfig) graphql.Marshaler {
+	if v == nil {
+		if !graphql.HasFieldError(ctx, graphql.GetFieldContext(ctx)) {
+			graphql.AddErrorf(ctx, "the requested element is null which the schema does not allow")
+		}
+		return graphql.Null
+	}
+	return ec._MetricConfig(ctx, sel, v)
+}
+
 func (ec *executionContext) marshalNMetricFootprints2ᚕᚖgithubᚗcomᚋClusterCockpitᚋccᚑbackendᚋinternalᚋgraphᚋmodelᚐMetricFootprintsᚄ(ctx context.Context, sel ast.SelectionSet, v []*model.MetricFootprints) graphql.Marshaler {
 	ret := make(graphql.Array, len(v))
 	var wg sync.WaitGroup
diff --git a/internal/graph/schema.resolvers.go b/internal/graph/schema.resolvers.go
index 2cb4f992..21ccaf92 100644
--- a/internal/graph/schema.resolvers.go
+++ b/internal/graph/schema.resolvers.go
@@ -3,7 +3,7 @@ package graph
 // This file will be automatically regenerated based on the schema, any resolver
 // implementations
 // will be copied through when generating and any unknown code will be moved to the end.
-// Code generated by github.com/99designs/gqlgen version v0.17.84
+// Code generated by github.com/99designs/gqlgen version v0.17.85
 
 import (
 	"context"
@@ -283,7 +283,7 @@ func (r *mutationResolver) RemoveTagFromList(ctx context.Context, tagIds []strin
 		// Test Access: Admins && Admin Tag OR Everyone && Private Tag
 		if user.HasRole(schema.RoleAdmin) && (tscope == "global" || tscope == "admin") || user.Username == tscope {
 			// Remove from DB
-			if err = r.Repo.RemoveTagById(tid); err != nil {
+			if err = r.Repo.RemoveTagByID(tid); err != nil {
 				cclog.Warn("Error while removing tag")
 				return nil, err
 			} else {
diff --git a/internal/importer/handleImport.go b/internal/importer/handleImport.go
index 4b217475..2ac35ea9 100644
--- a/internal/importer/handleImport.go
+++ b/internal/importer/handleImport.go
@@ -2,6 +2,7 @@
 // All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package importer
 
 import (
diff --git a/internal/importer/normalize.go b/internal/importer/normalize.go
index c6e84d4b..cc6fb545 100644
--- a/internal/importer/normalize.go
+++ b/internal/importer/normalize.go
@@ -2,6 +2,7 @@
 // All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package importer
 
 import (
diff --git a/internal/metricstore/metricstore.go b/internal/metricstore/metricstore.go
index e35b4d58..d75c9ef8 100644
--- a/internal/metricstore/metricstore.go
+++ b/internal/metricstore/metricstore.go
@@ -74,7 +74,7 @@ func Init(rawConfig json.RawMessage, wg *sync.WaitGroup) {
 	cclog.Debugf("[METRICSTORE]> Using %d workers for checkpoint/archive operations\n", Keys.NumWorkers)
 
 	// Helper function to add metric configuration
-	addMetricConfig := func(mc schema.MetricConfig) {
+	addMetricConfig := func(mc *schema.MetricConfig) {
 		agg, err := AssignAggregationStrategy(mc.Aggregation)
 		if err != nil {
 			cclog.Warnf("Could not find aggregation strategy for metric config '%s': %s", mc.Name, err.Error())
@@ -88,7 +88,7 @@ func Init(rawConfig json.RawMessage, wg *sync.WaitGroup) {
 
 	for _, c := range archive.Clusters {
 		for _, mc := range c.MetricConfig {
-			addMetricConfig(*mc)
+			addMetricConfig(mc)
 		}
 
 		for _, sc := range c.SubClusters {
diff --git a/internal/repository/hooks.go b/internal/repository/hooks.go
index c916b57e..824beb7c 100644
--- a/internal/repository/hooks.go
+++ b/internal/repository/hooks.go
@@ -2,6 +2,7 @@
 // All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package repository
 
 import (
diff --git a/internal/repository/job.go b/internal/repository/job.go
index bd33774c..9ee51735 100644
--- a/internal/repository/job.go
+++ b/internal/repository/job.go
@@ -686,7 +686,6 @@ func (r *JobRepository) AllocatedNodes(cluster string) (map[string]map[string]in
 	return subclusters, nil
 }
 
-// FIXME: Set duration to requested walltime?
 // StopJobsExceedingWalltimeBy marks running jobs as failed if they exceed their walltime limit.
 // This is typically called periodically to clean up stuck or orphaned jobs.
 //
@@ -762,7 +761,6 @@ func (r *JobRepository) FindJobIdsByTag(tagID int64) ([]int64, error) {
 	return jobIds, nil
 }
 
-// FIXME: Reconsider filtering short jobs with harcoded threshold
 // FindRunningJobs returns all currently running jobs for a specific cluster.
 // Filters out short-running jobs based on repoConfig.MinRunningJobDuration threshold.
 //
diff --git a/internal/repository/jobHooks.go b/internal/repository/jobHooks.go
index 41684d5c..66d29eea 100644
--- a/internal/repository/jobHooks.go
+++ b/internal/repository/jobHooks.go
@@ -2,6 +2,7 @@
 // All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package repository
 
 import (
diff --git a/internal/repository/job_test.go b/internal/repository/job_test.go
index 17766c69..9f4871fd 100644
--- a/internal/repository/job_test.go
+++ b/internal/repository/job_test.go
@@ -90,13 +90,13 @@ func TestFindJobsBetween(t *testing.T) {
 
 	// 2. Create a tag
 	tagName := fmt.Sprintf("testtag_%d", time.Now().UnixNano())
-	tagId, err := r.CreateTag("testtype", tagName, "global")
+	tagID, err := r.CreateTag("testtype", tagName, "global")
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	// 3. Link Tag (Manually to avoid archive dependency side-effects in unit test)
-	_, err = r.DB.Exec("INSERT INTO jobtag (job_id, tag_id) VALUES (?, ?)", *targetJob.ID, tagId)
+	_, err = r.DB.Exec("INSERT INTO jobtag (job_id, tag_id) VALUES (?, ?)", *targetJob.ID, tagID)
 	if err != nil {
 		t.Fatal(err)
 	}
diff --git a/internal/repository/node.go b/internal/repository/node.go
index 2890cdbc..a81fc58d 100644
--- a/internal/repository/node.go
+++ b/internal/repository/node.go
@@ -579,7 +579,7 @@ func (r *NodeRepository) GetNodesForList(
 		queryFilters = append(queryFilters, &model.NodeFilter{Hostname: &model.StringInput{Contains: &nodeFilter}})
 	}
 	if stateFilter != "all" && stateFilter != "notindb" {
-		var queryState schema.SchedulerState = schema.SchedulerState(stateFilter)
+		queryState := schema.SchedulerState(stateFilter)
 		queryFilters = append(queryFilters, &model.NodeFilter{SchedulerState: &queryState})
 	}
 	// if healthFilter != "all" {
diff --git a/internal/repository/repository_test.go b/internal/repository/repository_test.go
index 9d07b026..475e7bca 100644
--- a/internal/repository/repository_test.go
+++ b/internal/repository/repository_test.go
@@ -46,7 +46,7 @@ func BenchmarkSelect1(b *testing.B) {
 }
 
 func BenchmarkDB_FindJobById(b *testing.B) {
-	var jobId int64 = 1677322
+	var jobID int64 = 1677322
 
 	b.Run("FindJobById", func(b *testing.B) {
 		db := setup(b)
@@ -55,7 +55,7 @@ func BenchmarkDB_FindJobById(b *testing.B) {
 
 		b.RunParallel(func(pb *testing.PB) {
 			for pb.Next() {
-				_, err := db.FindByID(getContext(b), jobId)
+				_, err := db.FindByID(getContext(b), jobID)
 				noErr(b, err)
 			}
 		})
@@ -63,7 +63,7 @@ func BenchmarkDB_FindJobById(b *testing.B) {
 }
 
 func BenchmarkDB_FindJob(b *testing.B) {
-	var jobId int64 = 107266
+	var jobID int64 = 107266
 	var startTime int64 = 1657557241
 	cluster := "fritz"
 
@@ -74,7 +74,7 @@ func BenchmarkDB_FindJob(b *testing.B) {
 
 		b.RunParallel(func(pb *testing.PB) {
 			for pb.Next() {
-				_, err := db.Find(&jobId, &cluster, &startTime)
+				_, err := db.Find(&jobID, &cluster, &startTime)
 				noErr(b, err)
 			}
 		})
diff --git a/internal/repository/stats.go b/internal/repository/stats.go
index cd175c23..851a4ca1 100644
--- a/internal/repository/stats.go
+++ b/internal/repository/stats.go
@@ -2,6 +2,44 @@
 // All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
+// This file contains job statistics and histogram generation functionality for the JobRepository.
+//
+// # Job Statistics
+//
+// The statistics methods provide aggregated metrics about jobs including total jobs, users,
+// walltime, and resource usage (nodes, cores, accelerators). Statistics can be computed:
+//   - Overall (JobsStats): Single aggregate across all matching jobs
+//   - Grouped (JobsStatsGrouped): Aggregated by user, project, cluster, or subcluster
+//   - Counts (JobCountGrouped, AddJobCount): Simple job counts with optional filtering
+//
+// All statistics methods support filtering via JobFilter and respect security contexts.
+//
+// # Histograms
+//
+// Histogram methods generate distribution data for visualization:
+//   - Duration, nodes, cores, accelerators (AddHistograms)
+//   - Job metrics like CPU load, memory usage (AddMetricHistograms)
+//
+// Histograms use intelligent binning:
+//   - Duration: Variable bin sizes (1m, 10m, 1h, 6h, 12h, 24h) with zero-padding
+//   - Resources: Natural value-based bins
+//   - Metrics: Normalized to peak values with configurable bin counts
+//
+// # Running vs. Completed Jobs
+//
+// Statistics handle running jobs specially:
+//   - Duration calculated as (now - start_time) for running jobs
+//   - Metric histograms for running jobs load data from metric backend instead of footprint
+//   - Job state filtering distinguishes running/completed jobs
+//
+// # Performance Considerations
+//
+// - All queries use prepared statements via stmtCache
+// - Complex aggregations use SQL for efficiency
+// - Histogram pre-initialization ensures consistent bin ranges
+// - Metric histogram queries limited to 500 jobs for running job analysis
+
 package repository
 
 import (
@@ -19,7 +57,9 @@ import (
 	sq "github.com/Masterminds/squirrel"
 )
 
-// GraphQL validation should make sure that no unkown values can be specified.
+// groupBy2column maps GraphQL Aggregate enum values to their corresponding database column names.
+// Used by JobsStatsGrouped and JobCountGrouped to translate user-facing grouping dimensions
+// into SQL GROUP BY clauses. GraphQL validation ensures only valid enum values are accepted.
 var groupBy2column = map[model.Aggregate]string{
 	model.AggregateUser:       "job.hpc_user",
 	model.AggregateProject:    "job.project",
@@ -27,6 +67,9 @@ var groupBy2column = map[model.Aggregate]string{
 	model.AggregateSubcluster: "job.subcluster",
 }
 
+// sortBy2column maps GraphQL SortByAggregate enum values to their corresponding computed column names.
+// Used by JobsStatsGrouped to translate sort preferences into SQL ORDER BY clauses.
+// Column names match the AS aliases used in buildStatsQuery.
 var sortBy2column = map[model.SortByAggregate]string{
 	model.SortByAggregateTotaljobs:      "totalJobs",
 	model.SortByAggregateTotalusers:     "totalUsers",
@@ -39,6 +82,21 @@ var sortBy2column = map[model.SortByAggregate]string{
 	model.SortByAggregateTotalacchours:  "totalAccHours",
 }
 
+// buildCountQuery constructs a SQL query to count jobs with optional grouping and filtering.
+//
+// Parameters:
+//   - filter: Job filters to apply (cluster, user, time range, etc.)
+//   - kind: Special filter - "running" for running jobs only, "short" for jobs under threshold
+//   - col: Column name to GROUP BY; empty string for total count without grouping
+//
+// Returns a SelectBuilder that produces either:
+//   - Single count: COUNT(job.id) when col is empty
+//   - Grouped counts: col, COUNT(job.id) when col is specified
+//
+// The kind parameter enables counting specific job categories:
+//   - "running": Only jobs with job_state = 'running'
+//   - "short": Only jobs with duration < ShortRunningJobsDuration config value
+//   - empty: All jobs matching filters
 func (r *JobRepository) buildCountQuery(
 	filter []*model.JobFilter,
 	kind string,
@@ -47,10 +105,8 @@ func (r *JobRepository) buildCountQuery(
 	var query sq.SelectBuilder
 
 	if col != "" {
-		// Scan columns: id, cnt
 		query = sq.Select(col, "COUNT(job.id)").From("job").GroupBy(col)
 	} else {
-		// Scan columns:  cnt
 		query = sq.Select("COUNT(job.id)").From("job")
 	}
 
@@ -68,6 +124,27 @@ func (r *JobRepository) buildCountQuery(
 	return query
 }
 
+// buildStatsQuery constructs a SQL query to compute comprehensive job statistics with optional grouping.
+//
+// Parameters:
+//   - filter: Job filters to apply (cluster, user, time range, etc.)
+//   - col: Column name to GROUP BY; empty string for overall statistics without grouping
+//
+// Returns a SelectBuilder that produces comprehensive statistics:
+//   - totalJobs: Count of jobs
+//   - totalUsers: Count of distinct users (always 0 when grouping by user)
+//   - totalWalltime: Sum of job durations in hours
+//   - totalNodes: Sum of nodes used across all jobs
+//   - totalNodeHours: Sum of (duration × num_nodes) in hours
+//   - totalCores: Sum of hardware threads used across all jobs
+//   - totalCoreHours: Sum of (duration × num_hwthreads) in hours
+//   - totalAccs: Sum of accelerators used across all jobs
+//   - totalAccHours: Sum of (duration × num_acc) in hours
+//
+// Special handling:
+//   - Running jobs: Duration calculated as (now - start_time) instead of stored duration
+//   - Grouped queries: Also select grouping column and user's display name from hpc_user table
+//   - All time values converted from seconds to hours (÷ 3600) and rounded
 func (r *JobRepository) buildStatsQuery(
 	filter []*model.JobFilter,
 	col string,
@@ -75,31 +152,29 @@ func (r *JobRepository) buildStatsQuery(
 	var query sq.SelectBuilder
 
 	if col != "" {
-		// Scan columns: id, name, totalJobs, totalUsers, totalWalltime, totalNodes, totalNodeHours, totalCores, totalCoreHours, totalAccs, totalAccHours
 		query = sq.Select(
 			col,
 			"name",
 			"COUNT(job.id) as totalJobs",
 			"COUNT(DISTINCT job.hpc_user) AS totalUsers",
 			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END)) / 3600) as int) as totalWalltime`, time.Now().Unix()),
-			fmt.Sprintf(`CAST(SUM(job.num_nodes) as int) as totalNodes`),
+			`CAST(SUM(job.num_nodes) as int) as totalNodes`,
 			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_nodes) / 3600) as int) as totalNodeHours`, time.Now().Unix()),
-			fmt.Sprintf(`CAST(SUM(job.num_hwthreads) as int) as totalCores`),
+			`CAST(SUM(job.num_hwthreads) as int) as totalCores`,
 			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_hwthreads) / 3600) as int) as totalCoreHours`, time.Now().Unix()),
-			fmt.Sprintf(`CAST(SUM(job.num_acc) as int) as totalAccs`),
+			`CAST(SUM(job.num_acc) as int) as totalAccs`,
 			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_acc) / 3600) as int) as totalAccHours`, time.Now().Unix()),
 		).From("job").LeftJoin("hpc_user ON hpc_user.username = job.hpc_user").GroupBy(col)
 	} else {
-		// Scan columns: totalJobs, totalUsers, totalWalltime, totalNodes, totalNodeHours, totalCores, totalCoreHours, totalAccs, totalAccHours
 		query = sq.Select(
 			"COUNT(job.id) as totalJobs",
 			"COUNT(DISTINCT job.hpc_user) AS totalUsers",
 			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END)) / 3600) as int)`, time.Now().Unix()),
-			fmt.Sprintf(`CAST(SUM(job.num_nodes) as int)`),
+			`CAST(SUM(job.num_nodes) as int)`,
 			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_nodes) / 3600) as int)`, time.Now().Unix()),
-			fmt.Sprintf(`CAST(SUM(job.num_hwthreads) as int)`),
+			`CAST(SUM(job.num_hwthreads) as int)`,
 			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_hwthreads) / 3600) as int)`, time.Now().Unix()),
-			fmt.Sprintf(`CAST(SUM(job.num_acc) as int)`),
+			`CAST(SUM(job.num_acc) as int)`,
 			fmt.Sprintf(`CAST(ROUND(SUM((CASE WHEN job.job_state = "running" THEN %d - job.start_time ELSE job.duration END) * job.num_acc) / 3600) as int)`, time.Now().Unix()),
 		).From("job")
 	}
@@ -111,6 +186,25 @@ func (r *JobRepository) buildStatsQuery(
 	return query
 }
 
+// JobsStatsGrouped computes comprehensive job statistics grouped by a dimension (user, project, cluster, or subcluster).
+//
+// This is the primary method for generating aggregated statistics views in the UI, providing
+// metrics like total jobs, walltime, and resource usage broken down by the specified grouping.
+//
+// Parameters:
+//   - ctx: Context for security checks and cancellation
+//   - filter: Filters to apply (time range, cluster, job state, etc.)
+//   - page: Optional pagination (ItemsPerPage: -1 disables pagination)
+//   - sortBy: Optional sort column (totalJobs, totalWalltime, totalCoreHours, etc.)
+//   - groupBy: Required grouping dimension (User, Project, Cluster, or Subcluster)
+//
+// Returns a slice of JobsStatistics, one per group, with:
+//   - ID: The group identifier (username, project name, cluster name, etc.)
+//   - Name: Display name (for users, from hpc_user.name; empty for other groups)
+//   - Statistics: totalJobs, totalUsers, totalWalltime, resource usage metrics
+//
+// Security: Respects user roles via SecurityCheck - users see only their own data unless admin/support.
+// Performance: Results are sorted in SQL and pagination applied before scanning rows.
 func (r *JobRepository) JobsStatsGrouped(
 	ctx context.Context,
 	filter []*model.JobFilter,
@@ -230,6 +324,21 @@ func (r *JobRepository) JobsStatsGrouped(
 	return stats, nil
 }
 
+// JobsStats computes overall job statistics across all matching jobs without grouping.
+//
+// This method provides a single aggregate view of job metrics, useful for dashboard
+// summaries and overall system utilization reports.
+//
+// Parameters:
+//   - ctx: Context for security checks and cancellation
+//   - filter: Filters to apply (time range, cluster, job state, etc.)
+//
+// Returns a single-element slice containing aggregate statistics:
+//   - totalJobs, totalUsers, totalWalltime
+//   - totalNodeHours, totalCoreHours, totalAccHours
+//
+// Unlike JobsStatsGrouped, this returns overall totals without breaking down by dimension.
+// Security checks are applied via SecurityCheck to respect user access levels.
 func (r *JobRepository) JobsStats(
 	ctx context.Context,
 	filter []*model.JobFilter,
@@ -303,6 +412,17 @@ func LoadJobStat(job *schema.Job, metric string, statType string) float64 {
 	return 0.0
 }
 
+// JobCountGrouped counts jobs grouped by a dimension without computing detailed statistics.
+//
+// This is a lightweight alternative to JobsStatsGrouped when only job counts are needed,
+// avoiding the overhead of calculating walltime and resource usage metrics.
+//
+// Parameters:
+//   - ctx: Context for security checks
+//   - filter: Filters to apply
+//   - groupBy: Grouping dimension (User, Project, Cluster, or Subcluster)
+//
+// Returns JobsStatistics with only ID and TotalJobs populated for each group.
 func (r *JobRepository) JobCountGrouped(
 	ctx context.Context,
 	filter []*model.JobFilter,
@@ -343,6 +463,20 @@ func (r *JobRepository) JobCountGrouped(
 	return stats, nil
 }
 
+// AddJobCountGrouped augments existing statistics with additional job counts by category.
+//
+// This method enriches JobsStatistics returned by JobsStatsGrouped or JobCountGrouped
+// with counts of running or short-running jobs, matched by group ID.
+//
+// Parameters:
+//   - ctx: Context for security checks
+//   - filter: Filters to apply
+//   - groupBy: Grouping dimension (must match the dimension used for stats parameter)
+//   - stats: Existing statistics to augment (modified in-place by ID matching)
+//   - kind: "running" to add RunningJobs count, "short" to add ShortJobs count
+//
+// Returns the same stats slice with RunningJobs or ShortJobs fields populated per group.
+// Groups without matching jobs will have 0 for the added field.
 func (r *JobRepository) AddJobCountGrouped(
 	ctx context.Context,
 	filter []*model.JobFilter,
@@ -392,6 +526,18 @@ func (r *JobRepository) AddJobCountGrouped(
 	return stats, nil
 }
 
+// AddJobCount augments existing overall statistics with additional job counts by category.
+//
+// Similar to AddJobCountGrouped but for ungrouped statistics. Applies the same count
+// to all statistics entries (typically just one).
+//
+// Parameters:
+//   - ctx: Context for security checks
+//   - filter: Filters to apply
+//   - stats: Existing statistics to augment (modified in-place)
+//   - kind: "running" to add RunningJobs count, "short" to add ShortJobs count
+//
+// Returns the same stats slice with RunningJobs or ShortJobs fields set to the total count.
 func (r *JobRepository) AddJobCount(
 	ctx context.Context,
 	filter []*model.JobFilter,
@@ -437,6 +583,26 @@ func (r *JobRepository) AddJobCount(
 	return stats, nil
 }
 
+// AddHistograms augments statistics with distribution histograms for job properties.
+//
+// Generates histogram data for visualization of job duration, node count, core count,
+// and accelerator count distributions. Duration histogram uses intelligent binning based
+// on the requested resolution.
+//
+// Parameters:
+//   - ctx: Context for security checks
+//   - filter: Filters to apply to jobs included in histograms
+//   - stat: Statistics struct to augment (modified in-place)
+//   - durationBins: Bin size - "1m", "10m", "1h", "6h", "12h", or "24h" (default)
+//
+// Populates these fields in stat:
+//   - HistDuration: Job duration distribution (zero-padded bins)
+//   - HistNumNodes: Node count distribution
+//   - HistNumCores: Core (hwthread) count distribution
+//   - HistNumAccs: Accelerator count distribution
+//
+// Duration bins are pre-initialized with zeros to ensure consistent ranges for visualization.
+// Bin size determines both the width and maximum duration displayed (e.g., "1h" = 48 bins × 1h = 48h max).
 func (r *JobRepository) AddHistograms(
 	ctx context.Context,
 	filter []*model.JobFilter,
@@ -447,20 +613,20 @@ func (r *JobRepository) AddHistograms(
 
 	var targetBinCount int
 	var targetBinSize int
-	switch {
-	case *durationBins == "1m": // 1 Minute Bins + Max 60 Bins -> Max 60 Minutes
+	switch *durationBins {
+	case "1m": // 1 Minute Bins + Max 60 Bins -> Max 60 Minutes
 		targetBinCount = 60
 		targetBinSize = 60
-	case *durationBins == "10m": // 10 Minute Bins + Max 72 Bins -> Max 12 Hours
+	case "10m": // 10 Minute Bins + Max 72 Bins -> Max 12 Hours
 		targetBinCount = 72
 		targetBinSize = 600
-	case *durationBins == "1h": // 1 Hour Bins + Max 48 Bins -> Max 48 Hours
+	case "1h": // 1 Hour Bins + Max 48 Bins -> Max 48 Hours
 		targetBinCount = 48
 		targetBinSize = 3600
-	case *durationBins == "6h": // 6 Hour Bins + Max 12 Bins -> Max 3 Days
+	case "6h": // 6 Hour Bins + Max 12 Bins -> Max 3 Days
 		targetBinCount = 12
 		targetBinSize = 21600
-	case *durationBins == "12h": // 12 hour Bins + Max 14 Bins -> Max 7 Days
+	case "12h": // 12 hour Bins + Max 14 Bins -> Max 7 Days
 		targetBinCount = 14
 		targetBinSize = 43200
 	default: // 24h
@@ -499,7 +665,30 @@ func (r *JobRepository) AddHistograms(
 	return stat, nil
 }
 
-// Requires thresholds for metric from config for cluster? Of all clusters and use largest? split to 10 + 1 for artifacts?
+// AddMetricHistograms augments statistics with distribution histograms for job metrics.
+//
+// Generates histogram data for metrics like CPU load, memory usage, etc. Handles running
+// and completed jobs differently: running jobs load data from metric backend, completed jobs
+// use footprint data from database.
+//
+// Parameters:
+//   - ctx: Context for security checks
+//   - filter: Filters to apply (MUST contain State filter for running jobs)
+//   - metrics: List of metric names to histogram (e.g., ["cpu_load", "mem_used"])
+//   - stat: Statistics struct to augment (modified in-place)
+//   - targetBinCount: Number of histogram bins (default: 10)
+//
+// Populates HistMetrics field in stat with MetricHistoPoints for each metric.
+//
+// Binning algorithm:
+//   - Values normalized to metric's peak value from cluster configuration
+//   - Bins evenly distributed from 0 to peak
+//   - Pre-initialized with zeros for consistent visualization
+//
+// Limitations:
+//   - Running jobs: Limited to 500 jobs for performance
+//   - Requires valid cluster configuration with metric peak values
+//   - Uses footprint statistic (avg/max/min) configured per metric
 func (r *JobRepository) AddMetricHistograms(
 	ctx context.Context,
 	filter []*model.JobFilter,
@@ -534,7 +723,16 @@ func (r *JobRepository) AddMetricHistograms(
 	return stat, nil
 }
 
-// `value` must be the column grouped by, but renamed to "value"
+// jobsStatisticsHistogram generates a simple histogram by grouping on a column value.
+//
+// Used for histograms where the column value directly represents the bin (e.g., node count, core count).
+// Unlike duration/metric histograms, this doesn't pre-initialize bins with zeros.
+//
+// Parameters:
+//   - value: SQL expression that produces the histogram value, aliased as "value"
+//   - filters: Job filters to apply
+//
+// Returns histogram points with Value (from column) and Count (number of jobs).
 func (r *JobRepository) jobsStatisticsHistogram(
 	ctx context.Context,
 	value string,
@@ -573,6 +771,26 @@ func (r *JobRepository) jobsStatisticsHistogram(
 	return points, nil
 }
 
+// jobsDurationStatisticsHistogram generates a duration histogram with pre-initialized bins.
+//
+// Bins are zero-padded to provide consistent ranges for visualization, unlike simple
+// histograms which only return bins with data. The value parameter should compute
+// the bin number from job duration.
+//
+// Parameters:
+//   - value: SQL expression computing bin number from duration, aliased as "value"
+//   - filters: Job filters to apply
+//   - binSizeSeconds: Width of each bin in seconds
+//   - targetBinCount: Number of bins to pre-initialize
+//
+// Returns histogram points with Value (bin_number × binSizeSeconds) and Count.
+// All bins from 1 to targetBinCount are returned, with Count=0 for empty bins.
+//
+// Algorithm:
+//  1. Pre-initialize targetBinCount bins with zero counts
+//  2. Query database for actual counts per bin
+//  3. Match query results to pre-initialized bins by value
+//  4. Bins without matches remain at zero
 func (r *JobRepository) jobsDurationStatisticsHistogram(
 	ctx context.Context,
 	value string,
@@ -588,7 +806,6 @@ func (r *JobRepository) jobsDurationStatisticsHistogram(
 		return nil, qerr
 	}
 
-	// Initialize histogram bins with zero counts
 	// Each bin represents a duration range: bin N = [N*binSizeSeconds, (N+1)*binSizeSeconds)
 	// Example: binSizeSeconds=3600 (1 hour), bin 1 = 0-1h, bin 2 = 1-2h, etc.
 	points := make([]*model.HistoPoint, 0)
@@ -607,8 +824,8 @@ func (r *JobRepository) jobsDurationStatisticsHistogram(
 		return nil, err
 	}
 
-	// Match query results to pre-initialized bins and fill counts
-	// Query returns raw duration values that need to be mapped to correct bins
+	// Match query results to pre-initialized bins.
+	// point.Value from query is the bin number; multiply by binSizeSeconds to match bin.Value.
 	for rows.Next() {
 		point := model.HistoPoint{}
 		if err := rows.Scan(&point.Value, &point.Count); err != nil {
@@ -616,13 +833,8 @@ func (r *JobRepository) jobsDurationStatisticsHistogram(
 			return nil, err
 		}
 
-		// Find matching bin and update count
-		// point.Value is multiplied by binSizeSeconds to match pre-calculated bin.Value
 		for _, e := range points {
 			if e.Value == (point.Value * binSizeSeconds) {
-				// Note: Matching on unmodified integer value (and multiplying point.Value
-				// by binSizeSeconds after match) causes frontend to loop into highest
-				// targetBinCount, due to zoom condition instantly being fulfilled (cause unknown)
 				e.Count = point.Count
 				break
 			}
@@ -633,13 +845,34 @@ func (r *JobRepository) jobsDurationStatisticsHistogram(
 	return points, nil
 }
 
+// jobsMetricStatisticsHistogram generates a metric histogram using footprint data from completed jobs.
+//
+// Values are normalized to the metric's peak value and distributed into bins. The algorithm
+// is based on SQL histogram generation techniques, extracting metric values from JSON footprint
+// and computing bin assignments in SQL.
+//
+// Parameters:
+//   - metric: Metric name (e.g., "cpu_load", "mem_used")
+//   - filters: Job filters to apply
+//   - bins: Number of bins to generate
+//
+// Returns MetricHistoPoints with metric name, unit, footprint stat type, and binned data.
+//
+// Algorithm:
+//  1. Determine peak value from cluster configuration (filtered cluster or max across all)
+//  2. Generate SQL that extracts footprint value, normalizes to [0,1], multiplies by bin count
+//  3. Pre-initialize bins with min/max ranges based on peak value
+//  4. Query database for counts per bin
+//  5. Match results to pre-initialized bins
+//
+// Special handling: Values exactly equal to peak are forced into the last bin by multiplying
+// peak by 0.999999999 to avoid creating an extra bin.
 func (r *JobRepository) jobsMetricStatisticsHistogram(
 	ctx context.Context,
 	metric string,
 	filters []*model.JobFilter,
 	bins *int,
 ) (*model.MetricHistoPoints, error) {
-	// Determine the metric's peak value for histogram normalization
 	// Peak value defines the upper bound for binning: values are distributed across
 	// bins from 0 to peak. First try to get peak from filtered cluster, otherwise
 	// scan all clusters to find the maximum peak value.
@@ -679,18 +912,14 @@ func (r *JobRepository) jobsMetricStatisticsHistogram(
 		}
 	}
 
-	// Construct SQL histogram bins using normalized values
+	// Construct SQL histogram bins using normalized values.
 	// Algorithm based on: https://jereze.com/code/sql-histogram/ (modified)
 	start := time.Now()
 
-	// Calculate bin number for each job's metric value:
-	// 1. Extract metric value from JSON footprint
-	// 2. Normalize to [0,1] by dividing by peak
-	// 3. Multiply by number of bins to get bin number
-	// 4. Cast to integer for bin assignment
-	//
-	// Special case: Values exactly equal to peak would fall into bin N+1,
-	// so we multiply peak by 0.999999999 to force it into the last bin (bin N)
+	// Bin calculation formula:
+	//   bin_number = CAST( (value / peak) * num_bins AS INTEGER ) + 1
+	// Special case: value == peak would create bin N+1, so we test for equality
+	// and multiply peak by 0.999999999 to force it into bin N.
 	binQuery := fmt.Sprintf(`CAST(
 		((case when json_extract(footprint, "$.%s") = %f then %f*0.999999999 else json_extract(footprint, "$.%s") end) / %f)
 		* %v as INTEGER )`,
@@ -699,24 +928,19 @@ func (r *JobRepository) jobsMetricStatisticsHistogram(
 	mainQuery := sq.Select(
 		fmt.Sprintf(`%s + 1 as bin`, binQuery),
 		`count(*) as count`,
-		// For Debug: // fmt.Sprintf(`CAST((%f / %d) as INTEGER ) * %s as min`, peak, *bins, binQuery),
-		// For Debug: // fmt.Sprintf(`CAST((%f / %d) as INTEGER ) * (%s + 1) as max`, peak, *bins, binQuery),
 	).From("job").Where(
 		"JSON_VALID(footprint)",
 	).Where(fmt.Sprintf(`json_extract(footprint, "$.%s") is not null and json_extract(footprint, "$.%s") <= %f`, (metric + "_" + footprintStat), (metric + "_" + footprintStat), peak))
 
-	// Only accessible Jobs...
 	mainQuery, qerr := SecurityCheck(ctx, mainQuery)
 	if qerr != nil {
 		return nil, qerr
 	}
 
-	// Filters...
 	for _, f := range filters {
 		mainQuery = BuildWhereClause(f, mainQuery)
 	}
 
-	// Finalize query with Grouping and Ordering
 	mainQuery = mainQuery.GroupBy("bin").OrderBy("bin")
 
 	rows, err := mainQuery.RunWith(r.DB).Query()
@@ -725,8 +949,7 @@ func (r *JobRepository) jobsMetricStatisticsHistogram(
 		return nil, err
 	}
 
-	// Initialize histogram bins with calculated min/max ranges
-	// Each bin represents a range of metric values
+	// Pre-initialize bins with calculated min/max ranges.
 	// Example: peak=1000, bins=10 -> bin 1=[0,100), bin 2=[100,200), ..., bin 10=[900,1000]
 	points := make([]*model.MetricHistoPoint, 0)
 	binStep := int(peak) / *bins
@@ -737,29 +960,18 @@ func (r *JobRepository) jobsMetricStatisticsHistogram(
 		points = append(points, &epoint)
 	}
 
-	// Fill counts from query results
-	// Query only returns bins that have jobs, so we match against pre-initialized bins
+	// Match query results to pre-initialized bins.
 	for rows.Next() {
 		rpoint := model.MetricHistoPoint{}
-		if err := rows.Scan(&rpoint.Bin, &rpoint.Count); err != nil { // Required for Debug: &rpoint.Min, &rpoint.Max
+		if err := rows.Scan(&rpoint.Bin, &rpoint.Count); err != nil {
 			cclog.Warnf("Error while scanning rows for %s", metric)
-			return nil, err // FIXME: Totally bricks cc-backend if returned and if all metrics requested?
+			return nil, err
 		}
 
-		// Match query result to pre-initialized bin and update count
 		for _, e := range points {
-			if e.Bin != nil && rpoint.Bin != nil {
-				if *e.Bin == *rpoint.Bin {
-					e.Count = rpoint.Count
-					// Only Required For Debug: Check DB returned Min/Max against Backend Init above
-					// if rpoint.Min != nil {
-					// 	cclog.Warnf(">>>> Bin %d Min Set For %s to %d (Init'd with: %d)", *e.Bin, metric, *rpoint.Min, *e.Min)
-					// }
-					// if rpoint.Max != nil {
-					// 	cclog.Warnf(">>>> Bin %d Max Set For %s to %d (Init'd with: %d)", *e.Bin, metric, *rpoint.Max, *e.Max)
-					// }
-					break
-				}
+			if e.Bin != nil && rpoint.Bin != nil && *e.Bin == *rpoint.Bin {
+				e.Count = rpoint.Count
+				break
 			}
 		}
 	}
@@ -770,6 +982,28 @@ func (r *JobRepository) jobsMetricStatisticsHistogram(
 	return &result, nil
 }
 
+// runningJobsMetricStatisticsHistogram generates metric histograms for running jobs using live data.
+//
+// Unlike completed jobs which use footprint data from the database, running jobs require
+// fetching current metric averages from the metric backend (via metricdispatch).
+//
+// Parameters:
+//   - metrics: List of metric names
+//   - filters: Job filters (should filter to running jobs only)
+//   - bins: Number of histogram bins
+//
+// Returns slice of MetricHistoPoints, one per metric.
+//
+// Limitations:
+//   - Maximum 500 jobs (returns nil if more jobs match)
+//   - Requires metric backend availability
+//   - Bins based on metric peak values from cluster configuration
+//
+// Algorithm:
+//  1. Query first 501 jobs to check count limit
+//  2. Load metric averages for all jobs via metricdispatch
+//  3. For each metric, create bins based on peak value
+//  4. Iterate averages and count jobs per bin
 func (r *JobRepository) runningJobsMetricStatisticsHistogram(
 	ctx context.Context,
 	metrics []string,
diff --git a/internal/repository/tags.go b/internal/repository/tags.go
index f6cccfe2..861cbb76 100644
--- a/internal/repository/tags.go
+++ b/internal/repository/tags.go
@@ -3,6 +3,34 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
+// Package repository provides data access and persistence layer for ClusterCockpit.
+//
+// This file implements tag management functionality for job categorization and classification.
+// Tags support both manual assignment (via REST/GraphQL APIs) and automatic detection
+// (via tagger plugins). The implementation includes role-based access control through
+// tag scopes and maintains bidirectional consistency between the SQL database and
+// the file-based job archive.
+//
+// Database Schema:
+//
+//	CREATE TABLE tag (
+//	    id INTEGER PRIMARY KEY AUTOINCREMENT,
+//	    tag_type VARCHAR(255) NOT NULL,
+//	    tag_name VARCHAR(255) NOT NULL,
+//	    tag_scope VARCHAR(255) NOT NULL DEFAULT "global",
+//	    CONSTRAINT tag_unique UNIQUE (tag_type, tag_name, tag_scope)
+//	);
+//
+//	CREATE TABLE jobtag (
+//	    job_id INTEGER,
+//	    tag_id INTEGER,
+//	    PRIMARY KEY (job_id, tag_id),
+//	    FOREIGN KEY (job_id) REFERENCES job(id) ON DELETE CASCADE,
+//	    FOREIGN KEY (tag_id) REFERENCES tag(id) ON DELETE CASCADE
+//	);
+//
+// The jobtag junction table enables many-to-many relationships between jobs and tags.
+// CASCADE deletion ensures referential integrity when jobs or tags are removed.
 package repository
 
 import (
@@ -73,7 +101,7 @@ func (r *JobRepository) AddTagDirect(job int64, tag int64) ([]*schema.Tag, error
 func (r *JobRepository) RemoveTag(user *schema.User, job, tag int64) ([]*schema.Tag, error) {
 	j, err := r.FindByIDWithUser(user, job)
 	if err != nil {
-		cclog.Warn("Error while finding job by id")
+		cclog.Warnf("Error while finding job %d for user %s during tag removal: %v", job, user.Username, err)
 		return nil, err
 	}
 
@@ -93,7 +121,7 @@ func (r *JobRepository) RemoveTag(user *schema.User, job, tag int64) ([]*schema.
 
 	archiveTags, err := r.getArchiveTags(&job)
 	if err != nil {
-		cclog.Warn("Error while getting tags for job")
+		cclog.Warnf("Error while getting archive tags for job %d in RemoveTag: %v", job, err)
 		return nil, err
 	}
 
@@ -104,7 +132,7 @@ func (r *JobRepository) RemoveTag(user *schema.User, job, tag int64) ([]*schema.
 // Requires user authentication for security checks. Used by REST API.
 func (r *JobRepository) RemoveJobTagByRequest(user *schema.User, job int64, tagType string, tagName string, tagScope string) ([]*schema.Tag, error) {
 	// Get Tag ID to delete
-	tagID, exists := r.TagId(tagType, tagName, tagScope)
+	tagID, exists := r.TagID(tagType, tagName, tagScope)
 	if !exists {
 		cclog.Warnf("Tag does not exist (name, type, scope): %s, %s, %s", tagName, tagType, tagScope)
 		return nil, fmt.Errorf("tag does not exist (name, type, scope): %s, %s, %s", tagName, tagType, tagScope)
@@ -113,7 +141,7 @@ func (r *JobRepository) RemoveJobTagByRequest(user *schema.User, job int64, tagT
 	// Get Job
 	j, err := r.FindByIDWithUser(user, job)
 	if err != nil {
-		cclog.Warn("Error while finding job by id")
+		cclog.Warnf("Error while finding job %d for user %s during tag removal by request: %v", job, user.Username, err)
 		return nil, err
 	}
 
@@ -128,19 +156,30 @@ func (r *JobRepository) RemoveJobTagByRequest(user *schema.User, job int64, tagT
 
 	tags, err := r.GetTags(user, &job)
 	if err != nil {
-		cclog.Warn("Error while getting tags for job")
+		cclog.Warnf("Error while getting tags for job %d in RemoveJobTagByRequest: %v", job, err)
 		return nil, err
 	}
 
 	archiveTags, err := r.getArchiveTags(&job)
 	if err != nil {
-		cclog.Warn("Error while getting tags for job")
+		cclog.Warnf("Error while getting archive tags for job %d in RemoveJobTagByRequest: %v", job, err)
 		return nil, err
 	}
 
 	return tags, archive.UpdateTags(j, archiveTags)
 }
 
+// removeTagFromArchiveJobs updates the job archive for all affected jobs after a tag deletion.
+//
+// This function is called asynchronously (via goroutine) after removing a tag from the database
+// to synchronize the file-based job archive with the database state. Errors are logged but not
+// returned since this runs in the background.
+//
+// Parameters:
+//   - jobIds: Database IDs of all jobs that had the deleted tag
+//
+// Implementation note: Each job is processed individually to handle partial failures gracefully.
+// If one job fails to update, others will still be processed.
 func (r *JobRepository) removeTagFromArchiveJobs(jobIds []int64) {
 	for _, j := range jobIds {
 		tags, err := r.getArchiveTags(&j)
@@ -163,18 +202,18 @@ func (r *JobRepository) removeTagFromArchiveJobs(jobIds []int64) {
 // Used by REST API. Does not update tagged jobs in Job archive.
 func (r *JobRepository) RemoveTagByRequest(tagType string, tagName string, tagScope string) error {
 	// Get Tag ID to delete
-	tagID, exists := r.TagId(tagType, tagName, tagScope)
+	tagID, exists := r.TagID(tagType, tagName, tagScope)
 	if !exists {
 		cclog.Warnf("Tag does not exist (name, type, scope): %s, %s, %s", tagName, tagType, tagScope)
 		return fmt.Errorf("tag does not exist (name, type, scope): %s, %s, %s", tagName, tagType, tagScope)
 	}
 
-	return r.RemoveTagById(tagID)
+	return r.RemoveTagByID(tagID)
 }
 
 // Removes a tag from db by tag id
 // Used by GraphQL API.
-func (r *JobRepository) RemoveTagById(tagID int64) error {
+func (r *JobRepository) RemoveTagByID(tagID int64) error {
 	jobIds, err := r.FindJobIdsByTag(tagID)
 	if err != nil {
 		return err
@@ -213,7 +252,7 @@ func (r *JobRepository) RemoveTagById(tagID int64) error {
 // Example:
 //
 //	tagID, err := repo.CreateTag("performance", "high-memory", "global")
-func (r *JobRepository) CreateTag(tagType string, tagName string, tagScope string) (tagId int64, err error) {
+func (r *JobRepository) CreateTag(tagType string, tagName string, tagScope string) (tagID int64, err error) {
 	// Default to "Global" scope if none defined
 	if tagScope == "" {
 		tagScope = "global"
@@ -300,13 +339,13 @@ func (r *JobRepository) CountTags(user *schema.User) (tags []schema.Tag, counts
 	for rows.Next() {
 		var tagType string
 		var tagName string
-		var tagId int
+		var tagID int
 		var count int
-		if err = rows.Scan(&tagType, &tagName, &tagId, &count); err != nil {
+		if err = rows.Scan(&tagType, &tagName, &tagID, &count); err != nil {
 			return nil, nil, err
 		}
 		// Use tagId as second Map-Key component to differentiate tags with identical names
-		counts[fmt.Sprint(tagType, tagName, tagId)] = count
+		counts[fmt.Sprint(tagType, tagName, tagID)] = count
 	}
 	err = rows.Err()
 
@@ -314,18 +353,44 @@ func (r *JobRepository) CountTags(user *schema.User) (tags []schema.Tag, counts
 }
 
 var (
-	ErrTagNotFound        = errors.New("the tag does not exist")
-	ErrJobNotOwned        = errors.New("user is not owner of job")
-	ErrTagNoAccess        = errors.New("user not permitted to use that tag")
-	ErrTagPrivateScope    = errors.New("tag is private to another user")
-	ErrTagAdminScope      = errors.New("tag requires admin privileges")
+	// ErrTagNotFound is returned when a tag ID or tag identifier (type, name, scope) does not exist in the database.
+	ErrTagNotFound = errors.New("the tag does not exist")
+
+	// ErrJobNotOwned is returned when a user attempts to tag a job they do not have permission to access.
+	ErrJobNotOwned = errors.New("user is not owner of job")
+
+	// ErrTagNoAccess is returned when a user attempts to use a tag they cannot access due to scope restrictions.
+	ErrTagNoAccess = errors.New("user not permitted to use that tag")
+
+	// ErrTagPrivateScope is returned when a user attempts to access another user's private tag.
+	ErrTagPrivateScope = errors.New("tag is private to another user")
+
+	// ErrTagAdminScope is returned when a non-admin user attempts to use an admin-scoped tag.
+	ErrTagAdminScope = errors.New("tag requires admin privileges")
+
+	// ErrTagsIncompatScopes is returned when attempting to combine admin and non-admin scoped tags in a single operation.
 	ErrTagsIncompatScopes = errors.New("combining admin and non-admin scoped tags not allowed")
 )
 
 // addJobTag is a helper function that inserts a job-tag association and updates the archive.
-// Returns the updated tag list for the job.
-func (r *JobRepository) addJobTag(jobId int64, tagId int64, job *schema.Job, getTags func() ([]*schema.Tag, error)) ([]*schema.Tag, error) {
-	q := sq.Insert("jobtag").Columns("job_id", "tag_id").Values(jobId, tagId)
+//
+// This function performs three operations atomically:
+//  1. Inserts the job-tag association into the jobtag junction table
+//  2. Retrieves the updated tag list for the job (using the provided getTags callback)
+//  3. Updates the job archive with the new tags to maintain database-archive consistency
+//
+// Parameters:
+//   - jobId: Database ID of the job
+//   - tagId: Database ID of the tag to associate
+//   - job: Full job object needed for archive update
+//   - getTags: Callback function to retrieve updated tags (allows different security contexts)
+//
+// Returns the complete updated tag list for the job or an error.
+//
+// Note: This function does NOT validate tag scope permissions - callers must perform
+// authorization checks before invoking this helper.
+func (r *JobRepository) addJobTag(jobID int64, tagID int64, job *schema.Job, getTags func() ([]*schema.Tag, error)) ([]*schema.Tag, error) {
+	q := sq.Insert("jobtag").Columns("job_id", "tag_id").Values(jobID, tagID)
 
 	if _, err := q.RunWith(r.stmtCache).Exec(); err != nil {
 		s, _, _ := q.ToSql()
@@ -335,13 +400,13 @@ func (r *JobRepository) addJobTag(jobId int64, tagId int64, job *schema.Job, get
 
 	tags, err := getTags()
 	if err != nil {
-		cclog.Warnf("Error getting tags for job %d: %v", jobId, err)
+		cclog.Warnf("Error getting tags for job %d: %v", jobID, err)
 		return nil, err
 	}
 
-	archiveTags, err := r.getArchiveTags(&jobId)
+	archiveTags, err := r.getArchiveTags(&jobID)
 	if err != nil {
-		cclog.Warnf("Error getting archive tags for job %d: %v", jobId, err)
+		cclog.Warnf("Error getting archive tags for job %d: %v", jobID, err)
 		return nil, err
 	}
 
@@ -350,7 +415,7 @@ func (r *JobRepository) addJobTag(jobId int64, tagId int64, job *schema.Job, get
 
 // AddTagOrCreate adds the tag with the specified type and name to the job with the database id `jobId`.
 // If such a tag does not yet exist, it is created.
-func (r *JobRepository) AddTagOrCreate(user *schema.User, jobId int64, tagType string, tagName string, tagScope string) (tagId int64, err error) {
+func (r *JobRepository) AddTagOrCreate(user *schema.User, jobID int64, tagType string, tagName string, tagScope string) (tagID int64, err error) {
 	// Default to "Global" scope if none defined
 	if tagScope == "" {
 		tagScope = "global"
@@ -364,44 +429,43 @@ func (r *JobRepository) AddTagOrCreate(user *schema.User, jobId int64, tagType s
 		return 0, fmt.Errorf("cannot write tag scope with current authorization")
 	}
 
-	tagId, exists := r.TagId(tagType, tagName, tagScope)
+	tagID, exists := r.TagID(tagType, tagName, tagScope)
 	if !exists {
-		tagId, err = r.CreateTag(tagType, tagName, tagScope)
+		tagID, err = r.CreateTag(tagType, tagName, tagScope)
 		if err != nil {
 			return 0, err
 		}
 	}
 
-	if _, err := r.AddTag(user, jobId, tagId); err != nil {
+	if _, err := r.AddTag(user, jobID, tagID); err != nil {
 		return 0, err
 	}
 
-	return tagId, nil
+	return tagID, nil
 }
 
-// used in auto tagger plugins
-func (r *JobRepository) AddTagOrCreateDirect(jobId int64, tagType string, tagName string) (tagId int64, err error) {
+func (r *JobRepository) AddTagOrCreateDirect(jobID int64, tagType string, tagName string) (tagID int64, err error) {
 	tagScope := "global"
 
-	tagId, exists := r.TagId(tagType, tagName, tagScope)
+	tagID, exists := r.TagID(tagType, tagName, tagScope)
 	if !exists {
-		tagId, err = r.CreateTag(tagType, tagName, tagScope)
+		tagID, err = r.CreateTag(tagType, tagName, tagScope)
 		if err != nil {
 			return 0, err
 		}
 	}
 
-	if _, err := r.AddTagDirect(jobId, tagId); err != nil {
+	if _, err := r.AddTagDirect(jobID, tagID); err != nil {
 		return 0, err
 	}
 
-	return tagId, nil
+	return tagID, nil
 }
 
-func (r *JobRepository) HasTag(jobId int64, tagType string, tagName string) bool {
+func (r *JobRepository) HasTag(jobID int64, tagType string, tagName string) bool {
 	var id int64
 	q := sq.Select("id").From("tag").Join("jobtag ON jobtag.tag_id = tag.id").
-		Where("jobtag.job_id = ?", jobId).Where("tag.tag_type = ?", tagType).
+		Where("jobtag.job_id = ?", jobID).Where("tag.tag_type = ?", tagType).
 		Where("tag.tag_name = ?", tagName)
 	err := q.RunWith(r.stmtCache).QueryRow().Scan(&id)
 	if err != nil {
@@ -411,21 +475,21 @@ func (r *JobRepository) HasTag(jobId int64, tagType string, tagName string) bool
 	}
 }
 
-// TagId returns the database id of the tag with the specified type and name.
-func (r *JobRepository) TagId(tagType string, tagName string, tagScope string) (tagId int64, exists bool) {
+// TagID returns the database id of the tag with the specified type and name.
+func (r *JobRepository) TagID(tagType string, tagName string, tagScope string) (tagID int64, exists bool) {
 	exists = true
 	if err := sq.Select("id").From("tag").
 		Where("tag.tag_type = ?", tagType).Where("tag.tag_name = ?", tagName).Where("tag.tag_scope = ?", tagScope).
-		RunWith(r.stmtCache).QueryRow().Scan(&tagId); err != nil {
+		RunWith(r.stmtCache).QueryRow().Scan(&tagID); err != nil {
 		exists = false
 	}
 	return
 }
 
 // TagInfo returns the database infos of the tag with the specified id.
-func (r *JobRepository) TagInfo(tagId int64) (tagType string, tagName string, tagScope string, exists bool) {
+func (r *JobRepository) TagInfo(tagID int64) (tagType string, tagName string, tagScope string, exists bool) {
 	exists = true
-	if err := sq.Select("tag.tag_type", "tag.tag_name", "tag.tag_scope").From("tag").Where("tag.id = ?", tagId).
+	if err := sq.Select("tag.tag_type", "tag.tag_name", "tag.tag_scope").From("tag").Where("tag.id = ?", tagID).
 		RunWith(r.stmtCache).QueryRow().Scan(&tagType, &tagName, &tagScope); err != nil {
 		exists = false
 	}
@@ -450,7 +514,7 @@ func (r *JobRepository) GetTags(user *schema.User, job *int64) ([]*schema.Tag, e
 	for rows.Next() {
 		tag := &schema.Tag{}
 		if err := rows.Scan(&tag.ID, &tag.Type, &tag.Name, &tag.Scope); err != nil {
-			cclog.Warn("Error while scanning rows")
+			cclog.Warnf("Error while scanning tag rows in GetTags: %v", err)
 			return nil, err
 		}
 		// Handle Scope Filtering: Tag Scope is Global, Private (== Username) or User is auth'd to view Admin Tags
@@ -483,7 +547,7 @@ func (r *JobRepository) GetTagsDirect(job *int64) ([]*schema.Tag, error) {
 	for rows.Next() {
 		tag := &schema.Tag{}
 		if err := rows.Scan(&tag.ID, &tag.Type, &tag.Name, &tag.Scope); err != nil {
-			cclog.Warn("Error while scanning rows")
+			cclog.Warnf("Error while scanning tag rows in GetTagsDirect: %v", err)
 			return nil, err
 		}
 		tags = append(tags, tag)
@@ -492,7 +556,18 @@ func (r *JobRepository) GetTagsDirect(job *int64) ([]*schema.Tag, error) {
 	return tags, nil
 }
 
-// GetArchiveTags returns a list of all tags *regardless of scope* for archiving if job is nil or of the tags that the job with that database ID has.
+// getArchiveTags returns all tags for a job WITHOUT applying scope-based filtering.
+//
+// This internal function is used exclusively for job archive synchronization where we need
+// to store all tags regardless of the current user's permissions. Unlike GetTags() which
+// filters by scope, this returns the complete unfiltered tag list.
+//
+// Parameters:
+//   - job: Pointer to job database ID, or nil to return all tags in the system
+//
+// Returns all tags without scope filtering, used only for archive operations.
+//
+// WARNING: Do NOT expose this function to user-facing APIs as it bypasses authorization.
 func (r *JobRepository) getArchiveTags(job *int64) ([]*schema.Tag, error) {
 	q := sq.Select("id", "tag_type", "tag_name", "tag_scope").From("tag")
 	if job != nil {
@@ -510,7 +585,7 @@ func (r *JobRepository) getArchiveTags(job *int64) ([]*schema.Tag, error) {
 	for rows.Next() {
 		tag := &schema.Tag{}
 		if err := rows.Scan(&tag.ID, &tag.Type, &tag.Name, &tag.Scope); err != nil {
-			cclog.Warn("Error while scanning rows")
+			cclog.Warnf("Error while scanning tag rows in getArchiveTags: %v", err)
 			return nil, err
 		}
 		tags = append(tags, tag)
@@ -519,18 +594,18 @@ func (r *JobRepository) getArchiveTags(job *int64) ([]*schema.Tag, error) {
 	return tags, nil
 }
 
-func (r *JobRepository) ImportTag(jobId int64, tagType string, tagName string, tagScope string) (err error) {
+func (r *JobRepository) ImportTag(jobID int64, tagType string, tagName string, tagScope string) (err error) {
 	// Import has no scope ctx, only import from metafile to DB (No recursive archive update required), only returns err
 
-	tagId, exists := r.TagId(tagType, tagName, tagScope)
+	tagID, exists := r.TagID(tagType, tagName, tagScope)
 	if !exists {
-		tagId, err = r.CreateTag(tagType, tagName, tagScope)
+		tagID, err = r.CreateTag(tagType, tagName, tagScope)
 		if err != nil {
 			return err
 		}
 	}
 
-	q := sq.Insert("jobtag").Columns("job_id", "tag_id").Values(jobId, tagId)
+	q := sq.Insert("jobtag").Columns("job_id", "tag_id").Values(jobID, tagID)
 
 	if _, err := q.RunWith(r.stmtCache).Exec(); err != nil {
 		s, _, _ := q.ToSql()
@@ -541,6 +616,28 @@ func (r *JobRepository) ImportTag(jobId int64, tagType string, tagName string, t
 	return nil
 }
 
+// checkScopeAuth validates whether a user is authorized to perform an operation on a tag with the given scope.
+//
+// This function implements the tag scope authorization matrix:
+//
+//	Scope        | Read Access                      | Write Access
+//	-------------|----------------------------------|----------------------------------
+//	"global"     | All users                        | Admin, Support, API-only
+//	"admin"      | Admin, Support                   | Admin, API-only
+//	<username>   | Owner only                       | Owner only (private tags)
+//
+// Parameters:
+//   - user: User attempting the operation (must not be nil)
+//   - operation: Either "read" or "write"
+//   - scope: Tag scope value ("global", "admin", or username for private tags)
+//
+// Returns:
+//   - pass: true if authorized, false if denied
+//   - err: error only if operation is invalid or user is nil
+//
+// Special cases:
+//   - API-only users (single role: RoleApi) can write to admin and global scopes for automation
+//   - Private tags use the username as scope, granting exclusive access to that user
 func (r *JobRepository) checkScopeAuth(user *schema.User, operation string, scope string) (pass bool, err error) {
 	if user != nil {
 		switch {
diff --git a/pkg/archive/clusterConfig.go b/pkg/archive/clusterConfig.go
index 6e4866eb..272eeb35 100644
--- a/pkg/archive/clusterConfig.go
+++ b/pkg/archive/clusterConfig.go
@@ -108,7 +108,7 @@ func initClusterConfig() error {
 				}
 
 				availability.SubClusters = append(availability.SubClusters, sc.Name)
-				sc.MetricConfig = append(sc.MetricConfig, *newMetric)
+				sc.MetricConfig = append(sc.MetricConfig, newMetric)
 
 				if newMetric.Footprint != "" {
 					sc.Footprint = append(sc.Footprint, newMetric.Name)
@@ -282,7 +282,7 @@ func GetSubClusterByNode(cluster, hostname string) (string, error) {
 	return "", fmt.Errorf("ARCHIVE/CLUSTERCONFIG > no subcluster found for cluster %v and host %v", cluster, hostname)
 }
 
-func MetricIndex(mc []schema.MetricConfig, name string) (int, error) {
+func MetricIndex(mc []*schema.MetricConfig, name string) (int, error) {
 	for i, m := range mc {
 		if m.Name == name {
 			return i, nil
diff --git a/pkg/archive/nodelist.go b/pkg/archive/nodelist.go
index 7a3784c3..42d8492a 100644
--- a/pkg/archive/nodelist.go
+++ b/pkg/archive/nodelist.go
@@ -3,6 +3,70 @@
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 
+// Package archive provides nodelist parsing functionality for HPC cluster node specifications.
+//
+// # Overview
+//
+// The nodelist package implements parsing and querying of compact node list representations
+// commonly used in HPC job schedulers and cluster management systems. It converts compressed
+// node specifications (e.g., "node[01-10]") into queryable structures that can efficiently
+// test node membership and expand to full node lists.
+//
+// # Node List Format
+//
+// Node lists use a compact syntax with the following rules:
+//
+//  1. Comma-separated terms represent alternative node patterns (OR logic)
+//  2. Each term consists of a string prefix followed by optional numeric ranges
+//  3. Numeric ranges are specified in square brackets with zero-padded start-end format
+//  4. Multiple ranges within brackets are comma-separated
+//  5. Range digits must be zero-padded and of equal length (e.g., "01-99" not "1-99")
+//
+// # Examples
+//
+//	"node01"                    // Single node
+//	"node01,node02"             // Multiple individual nodes
+//	"node[01-10]"               // Range: node01 through node10 (zero-padded)
+//	"node[01-10,20-30]"         // Multiple ranges: node01-10 and node20-30
+//	"cn-00[10-20],cn-00[50-60]" // Different prefixes with ranges
+//	"login,compute[001-100]"    // Mixed individual and range terms
+//
+// # Usage
+//
+// Parse a node list specification:
+//
+//	nl, err := ParseNodeList("node[01-10],login")
+//	if err != nil {
+//	    log.Fatal(err)
+//	}
+//
+// Check if a node name matches the list:
+//
+//	if nl.Contains("node05") {
+//	    // node05 is in the list
+//	}
+//
+// Expand to full list of node names:
+//
+//	nodes := nl.PrintList()  // ["node01", "node02", ..., "node10", "login"]
+//
+// Count total nodes in the list:
+//
+//	count := nl.NodeCount()  // 11 (10 from range + 1 individual)
+//
+// # Integration
+//
+// This package is used by:
+//   - clusterConfig.go: Parses SubCluster.Nodes field from cluster configuration
+//   - schema.resolvers.go: GraphQL resolver for computing numberOfNodes in subclusters
+//   - Job archive: Validates node assignments against configured cluster topology
+//
+// # Constraints
+//
+//   - Only zero-padded numeric ranges are supported
+//   - Range start and end must have identical digit counts
+//   - No whitespace allowed in node list specifications
+//   - Ranges must be specified as start-end (not individual numbers)
 package archive
 
 import (
@@ -13,12 +77,36 @@ import (
 	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
 )
 
+// NodeList represents a parsed node list specification as a collection of node pattern terms.
+// Each term is a sequence of expressions that must match consecutively for a node name to match.
+// Terms are evaluated with OR logic - a node matches if ANY term matches completely.
+//
+// Internal structure:
+//   - Outer slice: OR terms (comma-separated in input)
+//   - Inner slice: AND expressions (must all match sequentially)
+//   - Each expression implements: consume (pattern matching), limits (range info), prefix (string part)
+//
+// Example: "node[01-10],login" becomes:
+//   - Term 1: [NLExprString("node"), NLExprIntRanges(01-10)]
+//   - Term 2: [NLExprString("login")]
 type NodeList [][]interface {
 	consume(input string) (next string, ok bool)
 	limits() []map[string]int
 	prefix() string
 }
 
+// Contains tests whether the given node name matches any pattern in the NodeList.
+// Returns true if the name matches at least one term completely, false otherwise.
+//
+// Matching logic:
+//   - Evaluates each term sequentially (OR logic across terms)
+//   - Within a term, all expressions must match in order (AND logic)
+//   - A match is complete only if the entire input is consumed (str == "")
+//
+// Examples:
+//   - NodeList("node[01-10]").Contains("node05") → true
+//   - NodeList("node[01-10]").Contains("node11") → false
+//   - NodeList("node[01-10]").Contains("node5")  → false (missing zero-padding)
 func (nl *NodeList) Contains(name string) bool {
 	var ok bool
 	for _, term := range *nl {
@@ -38,14 +126,22 @@ func (nl *NodeList) Contains(name string) bool {
 	return false
 }
 
+// PrintList expands the NodeList into a full slice of individual node names.
+// This performs the inverse operation of ParseNodeList, expanding all ranges
+// into their constituent node names with proper zero-padding.
+//
+// Returns a slice of node names in the order they appear in the NodeList.
+// For range terms, nodes are expanded in ascending numeric order.
+//
+// Example:
+//   - ParseNodeList("node[01-03],login").PrintList() → ["node01", "node02", "node03", "login"]
 func (nl *NodeList) PrintList() []string {
 	var out []string
 	for _, term := range *nl {
-		// Get String-Part first
 		prefix := term[0].prefix()
-		if len(term) == 1 { // If only String-Part in Term: Single Node Name -> Use as provided
+		if len(term) == 1 {
 			out = append(out, prefix)
-		} else { // Else: Numeric start-end definition with x digits zeroPadded
+		} else {
 			limitArr := term[1].limits()
 			for _, inner := range limitArr {
 				for i := inner["start"]; i < inner["end"]+1; i++ {
@@ -61,12 +157,22 @@ func (nl *NodeList) PrintList() []string {
 	return out
 }
 
+// NodeCount returns the total number of individual nodes represented by the NodeList.
+// This efficiently counts nodes without expanding the full list, making it suitable
+// for large node ranges.
+//
+// Calculation:
+//   - Individual node terms contribute 1
+//   - Range terms contribute (end - start + 1) for each range
+//
+// Example:
+//   - ParseNodeList("node[01-10],login").NodeCount() → 11 (10 from range + 1 individual)
 func (nl *NodeList) NodeCount() int {
 	out := 0
 	for _, term := range *nl {
-		if len(term) == 1 { // If only String-Part in Term: Single Node Name -> add one
+		if len(term) == 1 {
 			out += 1
-		} else { // Else: Numeric start-end definition -> add difference + 1
+		} else {
 			limitArr := term[1].limits()
 			for _, inner := range limitArr {
 				out += (inner["end"] - inner["start"]) + 1
@@ -76,6 +182,8 @@ func (nl *NodeList) NodeCount() int {
 	return out
 }
 
+// NLExprString represents a literal string prefix in a node name pattern.
+// It matches by checking if the input starts with this exact string.
 type NLExprString string
 
 func (nle NLExprString) consume(input string) (next string, ok bool) {
@@ -96,6 +204,8 @@ func (nle NLExprString) prefix() string {
 	return string(nle)
 }
 
+// NLExprIntRanges represents multiple alternative integer ranges (comma-separated within brackets).
+// A node name matches if it matches ANY of the contained ranges (OR logic).
 type NLExprIntRanges []NLExprIntRange
 
 func (nles NLExprIntRanges) consume(input string) (next string, ok bool) {
@@ -122,6 +232,11 @@ func (nles NLExprIntRanges) prefix() string {
 	return s
 }
 
+// NLExprIntRange represents a single zero-padded integer range (e.g., "01-99").
+// Fields:
+//   - start, end: Numeric range boundaries (inclusive)
+//   - zeroPadded: Must be true (non-padded ranges not supported)
+//   - digits: Required digit count for zero-padding
 type NLExprIntRange struct {
 	start, end int64
 	zeroPadded bool
@@ -176,6 +291,28 @@ func (nles NLExprIntRange) prefix() string {
 	return s
 }
 
+// ParseNodeList parses a compact node list specification into a queryable NodeList structure.
+//
+// Input format rules:
+//   - Comma-separated terms (OR logic): "node01,node02" matches either node
+//   - Range syntax: "node[01-10]" expands to node01 through node10
+//   - Multiple ranges: "node[01-05,10-15]" creates two ranges
+//   - Zero-padding required: digits in ranges must be zero-padded and equal length
+//   - Mixed formats: "login,compute[001-100]" combines individual and range terms
+//
+// Validation:
+//   - Returns error if brackets are unclosed
+//   - Returns error if ranges lack '-' separator
+//   - Returns error if range digits have unequal length
+//   - Returns error if range numbers fail to parse
+//   - Returns error on invalid characters
+//
+// Examples:
+//   - "node[01-10]" → NodeList with one term (10 nodes)
+//   - "node01,node02" → NodeList with two terms (2 nodes)
+//   - "cn[01-05,10-15]" → NodeList with ranges 01-05 and 10-15 (11 nodes total)
+//   - "a[1-9]" → Error (not zero-padded)
+//   - "a[01-9]" → Error (unequal digit counts)
 func ParseNodeList(raw string) (NodeList, error) {
 	isLetter := func(r byte) bool { return ('a' <= r && r <= 'z') || ('A' <= r && r <= 'Z') }
 	isDigit := func(r byte) bool { return '0' <= r && r <= '9' }
@@ -232,12 +369,12 @@ func ParseNodeList(raw string) (NodeList, error) {
 				nles := NLExprIntRanges{}
 
 				for _, part := range parts {
-					minus := strings.Index(part, "-")
-					if minus == -1 {
+					before, after, ok := strings.Cut(part, "-")
+					if !ok {
 						return nil, fmt.Errorf("ARCHIVE/NODELIST > no '-' found inside '[...]'")
 					}
 
-					s1, s2 := part[0:minus], part[minus+1:]
+					s1, s2 := before, after
 					if len(s1) != len(s2) || len(s1) == 0 {
 						return nil, fmt.Errorf("ARCHIVE/NODELIST > %v and %v are not of equal length or of length zero", s1, s2)
 					}

From 3b7fc44ce944072a9349669df28f15e8ede3671e Mon Sep 17 00:00:00 2001
From: Christoph Kluge <christoph.kluge@fau.de>
Date: Thu, 15 Jan 2026 10:11:31 +0100
Subject: [PATCH 51/59] specify job count return logs, move to debug level

---
 internal/repository/job.go     | 4 ++--
 internal/repository/jobFind.go | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/internal/repository/job.go b/internal/repository/job.go
index b1e92424..80082315 100644
--- a/internal/repository/job.go
+++ b/internal/repository/job.go
@@ -630,7 +630,7 @@ func (r *JobRepository) FindRunningJobs(cluster string) ([]*schema.Job, error) {
 		jobs = append(jobs, job)
 	}
 
-	cclog.Infof("Return job count %d", len(jobs))
+	cclog.Debugf("JobRepository.FindRunningJobs(): Return job count %d (cluster: %s)", len(jobs), cluster)
 	return jobs, nil
 }
 
@@ -684,7 +684,7 @@ func (r *JobRepository) FindJobsBetween(startTimeBegin int64, startTimeEnd int64
 		jobs = append(jobs, job)
 	}
 
-	cclog.Infof("Return job count %d", len(jobs))
+	cclog.Debugf("JobRepository.FindJobsBetween(): Return job count %d (omitTagged: %v)", len(jobs), omitTagged)
 	return jobs, nil
 }
 
diff --git a/internal/repository/jobFind.go b/internal/repository/jobFind.go
index 8f6daeb4..4386be2d 100644
--- a/internal/repository/jobFind.go
+++ b/internal/repository/jobFind.go
@@ -154,7 +154,7 @@ func (r *JobRepository) GetJobList(limit int, offset int) ([]int64, error) {
 		jl = append(jl, id)
 	}
 
-	cclog.Infof("Return job count %d", len(jl))
+	cclog.Debugf("JobRepository.GetJobList(): Return job count %d", len(jl))
 	return jl, nil
 }
 

From d59aa2e855716ea172c8933f4d4632b8185a0494 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 15 Jan 2026 11:33:01 +0100
Subject: [PATCH 52/59] Restructure configuration with sensible defaults. Fix
 shutdown hangs

---
 internal/metricstore/archive.go      |   2 +-
 internal/metricstore/avroHelper.go   |  51 +++++++++-
 internal/metricstore/checkpoint.go   |   2 +-
 internal/metricstore/config.go       |  63 +++++++-----
 internal/metricstore/configSchema.go | 146 ++++++++++++---------------
 internal/metricstore/lineprotocol.go |  17 ++--
 internal/metricstore/metricstore.go  |  40 +++++---
 7 files changed, 189 insertions(+), 132 deletions(-)

diff --git a/internal/metricstore/archive.go b/internal/metricstore/archive.go
index 972769fd..78efadfe 100644
--- a/internal/metricstore/archive.go
+++ b/internal/metricstore/archive.go
@@ -24,7 +24,7 @@ import (
 func Archiving(wg *sync.WaitGroup, ctx context.Context) {
 	go func() {
 		defer wg.Done()
-		d, err := time.ParseDuration(Keys.Archive.Interval)
+		d, err := time.ParseDuration(Keys.Archive.ArchiveInterval)
 		if err != nil {
 			cclog.Fatalf("[METRICSTORE]> error parsing archive interval duration: %v\n", err)
 		}
diff --git a/internal/metricstore/avroHelper.go b/internal/metricstore/avroHelper.go
index 5587a58d..985fdd78 100644
--- a/internal/metricstore/avroHelper.go
+++ b/internal/metricstore/avroHelper.go
@@ -30,8 +30,51 @@ func DataStaging(wg *sync.WaitGroup, ctx context.Context) {
 		for {
 			select {
 			case <-ctx.Done():
-				return
-			case val := <-LineProtocolMessages:
+				// Drain any remaining messages in channel before exiting
+				for {
+					select {
+					case val, ok := <-LineProtocolMessages:
+						if !ok {
+							// Channel closed
+							return
+						}
+						// Process remaining message
+						freq, err := GetMetricFrequency(val.MetricName)
+						if err != nil {
+							continue
+						}
+
+						metricName := ""
+						for _, selectorName := range val.Selector {
+							metricName += selectorName + SelectorDelimiter
+						}
+						metricName += val.MetricName
+
+						var selector []string
+						selector = append(selector, val.Cluster, val.Node, strconv.FormatInt(freq, 10))
+
+						if !stringSlicesEqual(oldSelector, selector) {
+							avroLevel = avroStore.root.findAvroLevelOrCreate(selector)
+							if avroLevel == nil {
+								cclog.Errorf("Error creating or finding the level with cluster : %s, node : %s, metric : %s\n", val.Cluster, val.Node, val.MetricName)
+							}
+							oldSelector = slices.Clone(selector)
+						}
+
+						if avroLevel != nil {
+							avroLevel.addMetric(metricName, val.Value, val.Timestamp, int(freq))
+						}
+					default:
+						// No more messages, exit
+						return
+					}
+				}
+			case val, ok := <-LineProtocolMessages:
+				if !ok {
+					// Channel closed, exit gracefully
+					return
+				}
+
 				// Fetch the frequency of the metric from the global configuration
 				freq, err := GetMetricFrequency(val.MetricName)
 				if err != nil {
@@ -65,7 +108,9 @@ func DataStaging(wg *sync.WaitGroup, ctx context.Context) {
 					oldSelector = slices.Clone(selector)
 				}
 
-				avroLevel.addMetric(metricName, val.Value, val.Timestamp, int(freq))
+				if avroLevel != nil {
+					avroLevel.addMetric(metricName, val.Value, val.Timestamp, int(freq))
+				}
 			}
 		}
 	}()
diff --git a/internal/metricstore/checkpoint.go b/internal/metricstore/checkpoint.go
index 27d611c4..fb72fc6e 100644
--- a/internal/metricstore/checkpoint.go
+++ b/internal/metricstore/checkpoint.go
@@ -408,7 +408,7 @@ func (m *MemoryStore) FromCheckpointFiles(dir string, from int64) (int, error) {
 		return m.FromCheckpoint(dir, from, altFormat)
 	}
 
-	cclog.Print("[METRICSTORE]> No valid checkpoint files found in the directory")
+	cclog.Info("[METRICSTORE]> No valid checkpoint files found")
 	return 0, nil
 }
 
diff --git a/internal/metricstore/config.go b/internal/metricstore/config.go
index c789f11c..9657453d 100644
--- a/internal/metricstore/config.go
+++ b/internal/metricstore/config.go
@@ -19,36 +19,49 @@ const (
 	DefaultAvroCheckpointInterval = time.Minute
 )
 
+type Checkpoints struct {
+	FileFormat string `json:"file-format"`
+	Interval   string `json:"interval"`
+	RootDir    string `json:"directory"`
+}
+
+type Debug struct {
+	DumpToFile string `json:"dump-to-file"`
+	EnableGops bool   `json:"gops"`
+}
+
+type Archive struct {
+	ArchiveInterval string `json:"interval"`
+	RootDir         string `json:"directory"`
+	DeleteInstead   bool   `json:"delete-instead"`
+}
+
+type Subscriptions []struct {
+	// Channel name
+	SubscribeTo string `json:"subscribe-to"`
+
+	// Allow lines without a cluster tag, use this as default, optional
+	ClusterTag string `json:"cluster-tag"`
+}
+
 type MetricStoreConfig struct {
 	// Number of concurrent workers for checkpoint and archive operations.
 	// If not set or 0, defaults to min(runtime.NumCPU()/2+1, 10)
-	NumWorkers  int `json:"num-workers"`
-	Checkpoints struct {
-		FileFormat string `json:"file-format"`
-		Interval   string `json:"interval"`
-		RootDir    string `json:"directory"`
-		Restore    string `json:"restore"`
-	} `json:"checkpoints"`
-	Debug struct {
-		DumpToFile string `json:"dump-to-file"`
-		EnableGops bool   `json:"gops"`
-	} `json:"debug"`
-		RetentionInMemory string `json:"retention-in-memory"`
-	Archive struct {
-		Interval      string `json:"interval"`
-		RootDir       string `json:"directory"`
-		DeleteInstead bool   `json:"delete-instead"`
-	} `json:"archive"`
-	Subscriptions []struct {
-		// Channel name
-		SubscribeTo string `json:"subscribe-to"`
-
-		// Allow lines without a cluster tag, use this as default, optional
-		ClusterTag string `json:"cluster-tag"`
-	} `json:"subscriptions"`
+	NumWorkers        int            `json:"num-workers"`
+	RetentionInMemory string         `json:"retention-in-memory"`
+	MemoryCap         int            `json:"memory-cap"`
+	Checkpoints       Checkpoints    `json:"checkpoints"`
+	Debug             *Debug         `json:"debug"`
+	Archive           *Archive       `json:"archive"`
+	Subscriptions     *Subscriptions `json:"nats-subscriptions"`
 }
 
-var Keys MetricStoreConfig
+var Keys MetricStoreConfig = MetricStoreConfig{
+	Checkpoints: Checkpoints{
+		FileFormat: "avro",
+		RootDir:    "./var/checkpoints",
+	},
+}
 
 // AggregationStrategy for aggregation over multiple values at different cpus/sockets/..., not time!
 type AggregationStrategy int
diff --git a/internal/metricstore/configSchema.go b/internal/metricstore/configSchema.go
index f1a20a73..c06bc6d9 100644
--- a/internal/metricstore/configSchema.go
+++ b/internal/metricstore/configSchema.go
@@ -6,90 +6,72 @@
 package metricstore
 
 const configSchema = `{
-    "type": "object",
-    "description": "Configuration specific to built-in metric-store.",
-    "properties": {
-        "checkpoints": {
-            "description": "Configuration for checkpointing the metrics within metric-store",
-            "type": "object",
-            "properties": {
-                "file-format": {
-                    "description": "Specify the type of checkpoint file. There are 2 variants: 'avro' and 'json'. If nothing is specified, 'avro' is default.",
-                    "type": "string"
-                },
-                "interval": {
-                    "description": "Interval at which the metrics should be checkpointed.",
-                    "type": "string"
-                },
-                "directory": {
-                    "description": "Specify the parent directy in which the checkpointed files should be placed.",
-                    "type": "string"
-                },
-                "restore": {
-                    "description": "When cc-backend starts up, look for checkpointed files that are less than X hours old and load metrics from these selected checkpoint files.",
-                    "type": "string"
-                }
-            }
+  "type": "object",
+  "description": "Configuration specific to built-in metric-store.",
+  "properties": {
+    "num-workers": {
+      "description": "Number of concurrent workers for checkpoint and archive operations",
+      "type": "integer"
+    },
+    "checkpoints": {
+      "description": "Configuration for checkpointing the metrics within metric-store",
+      "type": "object",
+      "properties": {
+        "file-format": {
+          "description": "Specify the type of checkpoint file. There are 2 variants: 'avro' and 'json'. If nothing is specified, 'avro' is default.",
+          "type": "string"
         },
-        "archive": {
-            "description": "Configuration for archiving the already checkpointed files.",
-            "type": "object",
-            "properties": {
-                "interval": {
-                    "description": "Interval at which the checkpointed files should be archived.",
-                    "type": "string"
-                },
-                "directory": {
-                    "description": "Specify the parent directy in which the archived files should be placed.",
-                    "type": "string"
-                }
-            }
+        "interval": {
+          "description": "Interval at which the metrics should be checkpointed.",
+          "type": "string"
         },
-        "retention-in-memory": {
-            "description": "Keep the metrics within memory for given time interval. Retention for X hours, then the metrics would be freed.",
-            "type": "string"
-        },
-        "nats": {
-            "description": "Configuration for accepting published data through NATS.",
-            "type": "array",
-            "items": {
-                "type": "object",
-                "properties": {
-                    "address": {
-                        "description": "Address of the NATS server.",
-                        "type": "string"
-                    },
-                    "username": {
-                        "description": "Optional: If configured with username/password method.",
-                        "type": "string"
-                    },
-                    "password": {
-                        "description": "Optional: If configured with username/password method.",
-                        "type": "string"
-                    },
-                    "creds-file-path": {
-                        "description": "Optional: If configured with Credential File method. Path to your NATS cred file.",
-                        "type": "string"
-                    },
-                    "subscriptions": {
-                        "description": "Array of various subscriptions. Allows to subscibe to different subjects and publishers.",
-                        "type": "array",
-                        "items": {
-                            "type": "object",
-                            "properties": {
-                                "subscribe-to": {
-                                    "description": "Channel name",
-                                    "type": "string"
-                                },
-                                "cluster-tag": {
-                                    "description": "Optional: Allow lines without a cluster tag, use this as default",
-                                    "type": "string"
-                                }
-                            }
-                        }
-                    }
-                }
-            }
+        "directory": {
+          "description": "Specify the parent directy in which the checkpointed files should be placed.",
+          "type": "string"
         }
+      },
+      "required": ["interval"]
+    },
+    "archive": {
+      "description": "Configuration for archiving the already checkpointed files.",
+      "type": "object",
+      "properties": {
+        "interval": {
+          "description": "Interval at which the checkpointed files should be archived.",
+          "type": "string"
+        },
+        "directory": {
+          "description": "Specify the directy in which the archived files should be placed.",
+          "type": "string"
+        }
+      },
+      "required": ["interval", "directory"]
+    },
+    "retention-in-memory": {
+      "description": "Keep the metrics within memory for given time interval. Retention for X hours, then the metrics would be freed.",
+      "type": "string"
+    },
+    "memory-cap": {
+      "description": "Upper memory capacity limit used by metricstore in GB",
+      "type": "integer"
+    },
+    "nats-subscriptions": {
+      "description": "Array of various subscriptions. Allows to subscibe to different subjects and publishers.",
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "subscribe-to": {
+            "description": "Channel name",
+            "type": "string"
+          },
+          "cluster-tag": {
+            "description": "Optional: Allow lines without a cluster tag, use this as default",
+            "type": "string"
+          }
+        }
+      }
     }
+  },
+  "required": ["checkpoints", "retention-in-memory"]
 }`
diff --git a/internal/metricstore/lineprotocol.go b/internal/metricstore/lineprotocol.go
index cc59e213..ca8ea138 100644
--- a/internal/metricstore/lineprotocol.go
+++ b/internal/metricstore/lineprotocol.go
@@ -29,29 +29,30 @@ func ReceiveNats(ms *MemoryStore,
 	}
 
 	var wg sync.WaitGroup
-
 	msgs := make(chan []byte, workers*2)
 
-	for _, sc := range Keys.Subscriptions {
+	for _, sc := range *Keys.Subscriptions {
 		clusterTag := sc.ClusterTag
 		if workers > 1 {
 			wg.Add(workers)
 
 			for range workers {
 				go func() {
+					defer wg.Done()
 					for m := range msgs {
 						dec := lineprotocol.NewDecoderWithBytes(m)
 						if err := DecodeLine(dec, ms, clusterTag); err != nil {
 							cclog.Errorf("error: %s", err.Error())
 						}
 					}
-
-					wg.Done()
 				}()
 			}
 
 			nc.Subscribe(sc.SubscribeTo, func(subject string, data []byte) {
-				msgs <- data
+				select {
+				case msgs <- data:
+				case <-ctx.Done():
+				}
 			})
 		} else {
 			nc.Subscribe(sc.SubscribeTo, func(subject string, data []byte) {
@@ -64,7 +65,11 @@ func ReceiveNats(ms *MemoryStore,
 		cclog.Infof("NATS subscription to '%s' established", sc.SubscribeTo)
 	}
 
-	close(msgs)
+	go func() {
+		<-ctx.Done()
+		close(msgs)
+	}()
+
 	wg.Wait()
 
 	return nil
diff --git a/internal/metricstore/metricstore.go b/internal/metricstore/metricstore.go
index d75c9ef8..7c17cd88 100644
--- a/internal/metricstore/metricstore.go
+++ b/internal/metricstore/metricstore.go
@@ -25,6 +25,7 @@ import (
 	"encoding/json"
 	"errors"
 	"runtime"
+	"slices"
 	"sync"
 	"time"
 
@@ -61,7 +62,7 @@ func Init(rawConfig json.RawMessage, wg *sync.WaitGroup) {
 	if rawConfig != nil {
 		config.Validate(configSchema, rawConfig)
 		dec := json.NewDecoder(bytes.NewReader(rawConfig))
-		// dec.DisallowUnknownFields()
+		dec.DisallowUnknownFields()
 		if err := dec.Decode(&Keys); err != nil {
 			cclog.Abortf("[METRICSTORE]> Metric Store Config Init: Could not decode config file '%s'.\nError: %s\n", rawConfig, err.Error())
 		}
@@ -103,7 +104,7 @@ func Init(rawConfig json.RawMessage, wg *sync.WaitGroup) {
 
 	ms := GetMemoryStore()
 
-	d, err := time.ParseDuration(Keys.Checkpoints.Restore)
+	d, err := time.ParseDuration(Keys.RetentionInMemory)
 	if err != nil {
 		cclog.Fatal(err)
 	}
@@ -128,11 +129,21 @@ func Init(rawConfig json.RawMessage, wg *sync.WaitGroup) {
 
 	ctx, shutdown := context.WithCancel(context.Background())
 
-	wg.Add(4)
+	retentionGoroutines := 1
+	checkpointingGoroutines := 1
+	dataStagingGoroutines := 1
+	archivingGoroutines := 0
+	if Keys.Archive != nil {
+		archivingGoroutines = 1
+	}
+	totalGoroutines := retentionGoroutines + checkpointingGoroutines + dataStagingGoroutines + archivingGoroutines
+	wg.Add(totalGoroutines)
 
 	Retention(wg, ctx)
 	Checkpointing(wg, ctx)
-	Archiving(wg, ctx)
+	if Keys.Archive != nil {
+		Archiving(wg, ctx)
+	}
 	DataStaging(wg, ctx)
 
 	// Note: Signal handling has been removed from this function.
@@ -141,9 +152,11 @@ func Init(rawConfig json.RawMessage, wg *sync.WaitGroup) {
 	// Store the shutdown function for later use by Shutdown()
 	shutdownFunc = shutdown
 
-	err = ReceiveNats(ms, 1, ctx)
-	if err != nil {
-		cclog.Fatal(err)
+	if Keys.Subscriptions != nil {
+		err = ReceiveNats(ms, 1, ctx)
+		if err != nil {
+			cclog.Fatal(err)
+		}
 	}
 }
 
@@ -184,11 +197,14 @@ func GetMemoryStore() *MemoryStore {
 }
 
 func Shutdown() {
-	// Cancel the context to signal all background goroutines to stop
 	if shutdownFunc != nil {
 		shutdownFunc()
 	}
 
+	if Keys.Checkpoints.FileFormat != "json" {
+		close(LineProtocolMessages)
+	}
+
 	cclog.Infof("[METRICSTORE]> Writing to '%s'...\n", Keys.Checkpoints.RootDir)
 	var files int
 	var err error
@@ -199,7 +215,6 @@ func Shutdown() {
 		files, err = ms.ToCheckpoint(Keys.Checkpoints.RootDir, lastCheckpoint.Unix(), time.Now().Unix())
 	} else {
 		files, err = GetAvroStore().ToCheckpoint(Keys.Checkpoints.RootDir, true)
-		close(LineProtocolMessages)
 	}
 
 	if err != nil {
@@ -314,11 +329,8 @@ func GetSelectors(ms *MemoryStore, excludeSelectors map[string][]string) [][]str
 		// Check if the key exists in our exclusion map
 		if excludedValues, exists := excludeSelectors[key]; exists {
 			// The key exists, now check if the specific value is in the exclusion list
-			for _, ev := range excludedValues {
-				if ev == value {
-					exclude = true
-					break
-				}
+			if slices.Contains(excludedValues, value) {
+				exclude = true
 			}
 		}
 

From cb219b3c748d569e32d4b657f79885eba5bd8def Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 15 Jan 2026 11:34:06 +0100
Subject: [PATCH 53/59] Fix configuration issues. Fix shutdown hangs

Always turn on compression
---
 cmd/cc-backend/main.go              | 21 +++++++---
 internal/taskmanager/taskManager.go | 64 +++++++++++++++++------------
 pkg/nats/client.go                  |  2 +-
 3 files changed, 55 insertions(+), 32 deletions(-)

diff --git a/cmd/cc-backend/main.go b/cmd/cc-backend/main.go
index 9f98ccbf..12aa9104 100644
--- a/cmd/cc-backend/main.go
+++ b/cmd/cc-backend/main.go
@@ -271,6 +271,7 @@ func initSubsystems() error {
 	// Initialize job archive
 	archiveCfg := ccconf.GetPackageConfig("archive")
 	if archiveCfg == nil {
+		cclog.Debug("Archive configuration not found, using default archive configuration")
 		archiveCfg = json.RawMessage(defaultArchiveConfig)
 	}
 	if err := archive.Init(archiveCfg, config.Keys.DisableArchive); err != nil {
@@ -375,22 +376,32 @@ func runServer(ctx context.Context) error {
 	}
 	runtime.SystemdNotify(true, "running")
 
-	// Wait for completion or error
+	waitDone := make(chan struct{})
 	go func() {
 		wg.Wait()
+		close(waitDone)
+	}()
+
+	go func() {
+		<-waitDone
 		close(errChan)
 	}()
 
-	// Check for server startup errors
 	select {
 	case err := <-errChan:
 		if err != nil {
 			return err
 		}
 	case <-time.After(100 * time.Millisecond):
-		// Server started successfully, wait for completion
-		if err := <-errChan; err != nil {
-			return err
+		select {
+		case err := <-errChan:
+			if err != nil {
+				return err
+			}
+		case <-waitDone:
+		case <-time.After(45 * time.Second):
+			cclog.Error("Shutdown timeout after 45 seconds - forcing exit")
+			return fmt.Errorf("shutdown timeout exceeded")
 		}
 	}
 
diff --git a/internal/taskmanager/taskManager.go b/internal/taskmanager/taskManager.go
index 06e4f28f..e1388c86 100644
--- a/internal/taskmanager/taskManager.go
+++ b/internal/taskmanager/taskManager.go
@@ -17,6 +17,10 @@ import (
 	"github.com/go-co-op/gocron/v2"
 )
 
+const (
+	DefaultCompressOlderThen = 7
+)
+
 // Retention defines the configuration for job retention policies.
 type Retention struct {
 	Policy     string `json:"policy"`
@@ -60,6 +64,38 @@ func parseDuration(s string) (time.Duration, error) {
 	return interval, nil
 }
 
+func initArchiveServices(config json.RawMessage) {
+	var cfg struct {
+		Retention   Retention `json:"retention"`
+		Compression int       `json:"compression"`
+	}
+	cfg.Retention.IncludeDB = true
+
+	if err := json.Unmarshal(config, &cfg); err != nil {
+		cclog.Errorf("error while unmarshaling raw config json: %v", err)
+	}
+
+	switch cfg.Retention.Policy {
+	case "delete":
+		RegisterRetentionDeleteService(
+			cfg.Retention.Age,
+			cfg.Retention.IncludeDB,
+			cfg.Retention.OmitTagged)
+	case "move":
+		RegisterRetentionMoveService(
+			cfg.Retention.Age,
+			cfg.Retention.IncludeDB,
+			cfg.Retention.Location,
+			cfg.Retention.OmitTagged)
+	}
+
+	if cfg.Compression > 0 {
+		RegisterCompressionService(cfg.Compression)
+	} else {
+		RegisterCompressionService(DefaultCompressOlderThen)
+	}
+}
+
 // Start initializes the task manager, parses configurations, and registers background tasks.
 // It starts the gocron scheduler.
 func Start(cronCfg, archiveConfig json.RawMessage) {
@@ -80,32 +116,8 @@ func Start(cronCfg, archiveConfig json.RawMessage) {
 		cclog.Errorf("error while decoding cron config: %v", err)
 	}
 
-	var cfg struct {
-		Retention   Retention `json:"retention"`
-		Compression int       `json:"compression"`
-	}
-	cfg.Retention.IncludeDB = true
-
-	if err := json.Unmarshal(archiveConfig, &cfg); err != nil {
-		cclog.Warn("Error while unmarshaling raw config json")
-	}
-
-	switch cfg.Retention.Policy {
-	case "delete":
-		RegisterRetentionDeleteService(
-			cfg.Retention.Age,
-			cfg.Retention.IncludeDB,
-			cfg.Retention.OmitTagged)
-	case "move":
-		RegisterRetentionMoveService(
-			cfg.Retention.Age,
-			cfg.Retention.IncludeDB,
-			cfg.Retention.Location,
-			cfg.Retention.OmitTagged)
-	}
-
-	if cfg.Compression > 0 {
-		RegisterCompressionService(cfg.Compression)
+	if archiveConfig != nil {
+		initArchiveServices(archiveConfig)
 	}
 
 	lc := auth.Keys.LdapConfig
diff --git a/pkg/nats/client.go b/pkg/nats/client.go
index a32ebdca..3222a525 100644
--- a/pkg/nats/client.go
+++ b/pkg/nats/client.go
@@ -77,7 +77,7 @@ type MessageHandler func(subject string, data []byte)
 func Connect() {
 	clientOnce.Do(func() {
 		if Keys.Address == "" {
-			cclog.Warn("NATS: no address configured, skipping connection")
+			cclog.Info("NATS: no address configured, skipping connection")
 			return
 		}
 

From 9c92a7796bff7989b760867329a3dd74363b8308 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 15 Jan 2026 12:20:11 +0100
Subject: [PATCH 54/59] Introduce nodeprovider interface to break import cycle

---
 cmd/cc-backend/main.go              |  7 +++++-
 internal/metricstore/metricstore.go | 38 +++++++++++++++++++++++------
 2 files changed, 36 insertions(+), 9 deletions(-)

diff --git a/cmd/cc-backend/main.go b/cmd/cc-backend/main.go
index 12aa9104..9b8cd1b0 100644
--- a/cmd/cc-backend/main.go
+++ b/cmd/cc-backend/main.go
@@ -320,8 +320,13 @@ func runServer(ctx context.Context) error {
 	mscfg := ccconf.GetPackageConfig("metric-store")
 	if mscfg != nil {
 		metricstore.Init(mscfg, &wg)
+
+		// Inject repository as NodeProvider to break import cycle
+		ms := metricstore.GetMemoryStore()
+		jobRepo := repository.GetJobRepository()
+		ms.SetNodeProvider(jobRepo)
 	} else {
-		cclog.Debug("Metric store configuration not found, skipping metricstore initialization")
+		return fmt.Errorf("missing metricstore configuration")
 	}
 
 	// Start archiver and task manager
diff --git a/internal/metricstore/metricstore.go b/internal/metricstore/metricstore.go
index 7c17cd88..37028654 100644
--- a/internal/metricstore/metricstore.go
+++ b/internal/metricstore/metricstore.go
@@ -45,6 +45,15 @@ var (
 	shutdownFunc context.CancelFunc
 )
 
+// NodeProvider provides information about nodes currently in use by running jobs.
+// This interface allows metricstore to query job information without directly
+// depending on the repository package, breaking the import cycle.
+type NodeProvider interface {
+	// GetUsedNodes returns a map of cluster names to sorted lists of unique hostnames
+	// that are currently in use by jobs that started before the given timestamp.
+	GetUsedNodes(ts int64) (map[string][]string, error)
+}
+
 type Metric struct {
 	Name         string
 	Value        schema.Float
@@ -52,8 +61,9 @@ type Metric struct {
 }
 
 type MemoryStore struct {
-	Metrics map[string]MetricConfig
-	root    Level
+	Metrics      map[string]MetricConfig
+	root         Level
+	nodeProvider NodeProvider // Injected dependency for querying running jobs
 }
 
 func Init(rawConfig json.RawMessage, wg *sync.WaitGroup) {
@@ -196,6 +206,14 @@ func GetMemoryStore() *MemoryStore {
 	return msInstance
 }
 
+// SetNodeProvider sets the NodeProvider implementation for the MemoryStore.
+// This must be called during initialization to provide job state information
+// for selective buffer retention during Free operations.
+// If not set, the Free function will fall back to freeing all buffers.
+func (ms *MemoryStore) SetNodeProvider(provider NodeProvider) {
+	ms.nodeProvider = provider
+}
+
 func Shutdown() {
 	if shutdownFunc != nil {
 		shutdownFunc()
@@ -263,13 +281,17 @@ func Retention(wg *sync.WaitGroup, ctx context.Context) {
 }
 
 func Free(ms *MemoryStore, t time.Time) (int, error) {
-	// jobRepo := repository.GetJobRepository()
-	// excludeSelectors, err := jobRepo.GetUsedNodes(t.Unix())
-	// if err != nil {
-	// 	return 0, err
-	// }
+	// If no NodeProvider is configured, free all buffers older than t
+	if ms.nodeProvider == nil {
+		return ms.Free(nil, t.Unix())
+	}
 
-	excludeSelectors := make(map[string][]string, 0)
+	excludeSelectors, err := ms.nodeProvider.GetUsedNodes(t.Unix())
+	if err != nil {
+		return 0, err
+	}
+
+	// excludeSelectors := make(map[string][]string, 0)
 
 	// excludeSelectors := map[string][]string{
 	// 	"alex":  {"a0122", "a0123", "a0225"},

From 155e05495e3f0f91d0fa6bef5a202cfa709c8f8d Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 15 Jan 2026 13:29:19 +0100
Subject: [PATCH 55/59] Fix shutdown timout bug

---
 cmd/cc-backend/main.go | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/cmd/cc-backend/main.go b/cmd/cc-backend/main.go
index 9b8cd1b0..1cc4c8cd 100644
--- a/cmd/cc-backend/main.go
+++ b/cmd/cc-backend/main.go
@@ -392,21 +392,26 @@ func runServer(ctx context.Context) error {
 		close(errChan)
 	}()
 
+	// Wait for either:
+	// 1. An error from server startup
+	// 2. Completion of all goroutines (normal shutdown or crash)
 	select {
 	case err := <-errChan:
+		// errChan will be closed when waitDone is closed, which happens
+		// when all goroutines complete (either from normal shutdown or error)
 		if err != nil {
 			return err
 		}
 	case <-time.After(100 * time.Millisecond):
+		// Give the server 100ms to start and report any immediate startup errors
+		// After that, just wait for normal shutdown completion
 		select {
 		case err := <-errChan:
 			if err != nil {
 				return err
 			}
 		case <-waitDone:
-		case <-time.After(45 * time.Second):
-			cclog.Error("Shutdown timeout after 45 seconds - forcing exit")
-			return fmt.Errorf("shutdown timeout exceeded")
+			// Normal shutdown completed
 		}
 	}
 

From 72248defbfa2da4dec7a54ba2fed992c4df01332 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 15 Jan 2026 13:39:22 +0100
Subject: [PATCH 56/59] Cleanup print statements. Always enable Compression

---
 internal/metricstore/checkpoint.go      | 1 -
 internal/taskmanager/ldapSyncService.go | 4 ++--
 internal/taskmanager/taskManager.go     | 7 +++++--
 3 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/internal/metricstore/checkpoint.go b/internal/metricstore/checkpoint.go
index fb72fc6e..b5511221 100644
--- a/internal/metricstore/checkpoint.go
+++ b/internal/metricstore/checkpoint.go
@@ -408,7 +408,6 @@ func (m *MemoryStore) FromCheckpointFiles(dir string, from int64) (int, error) {
 		return m.FromCheckpoint(dir, from, altFormat)
 	}
 
-	cclog.Info("[METRICSTORE]> No valid checkpoint files found")
 	return 0, nil
 }
 
diff --git a/internal/taskmanager/ldapSyncService.go b/internal/taskmanager/ldapSyncService.go
index 9e99a261..55a99bab 100644
--- a/internal/taskmanager/ldapSyncService.go
+++ b/internal/taskmanager/ldapSyncService.go
@@ -23,7 +23,8 @@ func RegisterLdapSyncService(ds string) {
 
 	auth := auth.GetAuthInstance()
 
-	cclog.Info("Register LDAP sync service")
+	cclog.Infof("register ldap sync service with %s interval", ds)
+
 	s.NewJob(gocron.DurationJob(interval),
 		gocron.NewTask(
 			func() {
@@ -32,6 +33,5 @@ func RegisterLdapSyncService(ds string) {
 				if err := auth.LdapAuth.Sync(); err != nil {
 					cclog.Errorf("ldap sync failed: %s", err.Error())
 				}
-				cclog.Print("ldap sync done")
 			}))
 }
diff --git a/internal/taskmanager/taskManager.go b/internal/taskmanager/taskManager.go
index e1388c86..cbc4120f 100644
--- a/internal/taskmanager/taskManager.go
+++ b/internal/taskmanager/taskManager.go
@@ -18,7 +18,7 @@ import (
 )
 
 const (
-	DefaultCompressOlderThen = 7
+	DefaultCompressOlderThan = 7
 )
 
 // Retention defines the configuration for job retention policies.
@@ -92,7 +92,7 @@ func initArchiveServices(config json.RawMessage) {
 	if cfg.Compression > 0 {
 		RegisterCompressionService(cfg.Compression)
 	} else {
-		RegisterCompressionService(DefaultCompressOlderThen)
+		RegisterCompressionService(DefaultCompressOlderThan)
 	}
 }
 
@@ -118,6 +118,9 @@ func Start(cronCfg, archiveConfig json.RawMessage) {
 
 	if archiveConfig != nil {
 		initArchiveServices(archiveConfig)
+	} else {
+		// Always enable compression
+		RegisterCompressionService(DefaultCompressOlderThan)
 	}
 
 	lc := auth.Keys.LdapConfig

From a3fffa8e8b17a28ed66badcae5f7c3ab3d5bdcaa Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 15 Jan 2026 13:57:15 +0100
Subject: [PATCH 57/59] Update example and demo config

---
 configs/config-demo.json | 45 ++++++----------------------------------
 configs/config.json      | 42 +++++++++++++++++++++++++++++++++----
 2 files changed, 44 insertions(+), 43 deletions(-)

diff --git a/configs/config-demo.json b/configs/config-demo.json
index e512c9de..79670f91 100644
--- a/configs/config-demo.json
+++ b/configs/config-demo.json
@@ -1,55 +1,22 @@
 {
   "main": {
     "addr": "127.0.0.1:8080",
-    "short-running-jobs-duration": 300,
-    "resampling": {
-      "minimumPoints": 600,
-      "trigger": 300,
-      "resolutions": [240, 60]
-    },
-    "apiAllowedIPs": ["*"],
-    "emission-constant": 317
+    "apiAllowedIPs": ["*"]
   },
   "cron": {
-    "commit-job-worker": "2m",
-    "duration-worker": "5m",
-    "footprint-worker": "10m"
-  },
-  "archive": {
-    "kind": "file",
-    "path": "./var/job-archive"
+    "commit-job-worker": "1m",
+    "duration-worker": "3m",
+    "footprint-worker": "5m"
   },
   "auth": {
     "jwts": {
       "max-age": "2000h"
     }
   },
-  "nats": {
-    "address": "nats://0.0.0.0:4222",
-    "username": "root",
-    "password": "root"
-  },
   "metric-store": {
     "checkpoints": {
-      "file-format": "avro",
-      "interval": "1h",
-      "directory": "./var/checkpoints",
-      "restore": "48h"
+      "interval": "1h"
     },
-    "archive": {
-      "interval": "1h",
-      "directory": "./var/archive"
-    },
-    "retention-in-memory": "48h",
-    "subscriptions": [
-      {
-        "subscribe-to": "hpc-nats",
-        "cluster-tag": "fritz"
-      },
-      {
-        "subscribe-to": "hpc-nats",
-        "cluster-tag": "alex"
-      }
-    ]
+    "retention-in-memory": "12h"
   }
 }
diff --git a/configs/config.json b/configs/config.json
index 44961c85..291df813 100644
--- a/configs/config.json
+++ b/configs/config.json
@@ -5,7 +5,6 @@
     "https-key-file": "/etc/letsencrypt/live/url/privkey.pem",
     "user": "clustercockpit",
     "group": "clustercockpit",
-    "validate": false,
     "apiAllowedIPs": ["*"],
     "short-running-jobs-duration": 300,
     "resampling": {
@@ -18,13 +17,48 @@
       "subjectNodeState": "cc.node.state"
     }
   },
+  "nats": {
+    "address": "nats://0.0.0.0:4222",
+    "username": "root",
+    "password": "root"
+  },
+  "auth": {
+    "jwts": {
+      "max-age": "2000h"
+    }
+  },
   "cron": {
     "commit-job-worker": "1m",
     "duration-worker": "5m",
     "footprint-worker": "10m"
   },
   "archive": {
-    "kind": "file",
-    "path": "./var/job-archive"
-  }
+    "kind": "s3",
+    "endpoint": "http://x.x.x.x",
+    "bucket": "jobarchive",
+    "accessKey": "xx",
+    "secretKey": "xx",
+    "retention": {
+      "policy": "move",
+      "age": 365,
+      "location": "./var/archive"
+    }
+  },
+  "metric-store": {
+    "checkpoints": {
+      "interval": "1h"
+    },
+    "retention-in-memory": "12h",
+    "subscriptions": [
+      {
+        "subscribe-to": "hpc-nats",
+        "cluster-tag": "fritz"
+      },
+      {
+        "subscribe-to": "hpc-nats",
+        "cluster-tag": "alex"
+      }
+    ]
+  },
+  "ui-file": "ui-config.json"
 }

From b6f0faa97fdd1073c5f143d7ea5407d699c3077f Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 15 Jan 2026 15:47:40 +0100
Subject: [PATCH 58/59] Make polarplot default in Jobview

---
 web/web.go | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/web/web.go b/web/web.go
index b4c3749a..66df18b5 100644
--- a/web/web.go
+++ b/web/web.go
@@ -77,14 +77,14 @@ type PlotConfiguration struct {
 var UIDefaults = WebConfig{
 	JobList: JobListConfig{
 		UsePaging:     false,
-		ShowFootprint: true,
+		ShowFootprint: false,
 	},
 	NodeList: NodeListConfig{
 		UsePaging: true,
 	},
 	JobView: JobViewConfig{
 		ShowPolarPlot: true,
-		ShowFootprint: true,
+		ShowFootprint: false,
 		ShowRoofline:  true,
 		ShowStatTable: true,
 	},

From 7db2bbe6b0bc1688baa6f6cf828a485e4e1fe4c4 Mon Sep 17 00:00:00 2001
From: Jan Eitzinger <jan@moebiusband.org>
Date: Thu, 15 Jan 2026 15:53:54 +0100
Subject: [PATCH 59/59] Add job tagger option to example config

---
 configs/config.json | 1 +
 1 file changed, 1 insertion(+)

diff --git a/configs/config.json b/configs/config.json
index 291df813..f91d9661 100644
--- a/configs/config.json
+++ b/configs/config.json
@@ -7,6 +7,7 @@
     "group": "clustercockpit",
     "apiAllowedIPs": ["*"],
     "short-running-jobs-duration": 300,
+    "enable-job-taggers": true,
     "resampling": {
       "minimumPoints": 600,
       "trigger": 180,