refactor(inframonitoring): drop required-metrics test, add test hosts_warnings

* chore: send warning instead of error for unseen metrics and missing (metric, key)

* chore: update integration test

* chore: fix integration test

* chore: fix test

* chore: add unit test for missing key

deploy/docker-swarm/docker-compose.ha.yaml

@@ -190,7 +190,7 @@ services:
       # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
   signoz:
     !!merge <<: *db-depend
-    image: signoz/signoz:v0.128.0
+    image: signoz/signoz:v0.129.0
     ports:
       - "8080:8080" # signoz port
     #   - "6060:6060"     # pprof port

deploy/docker-swarm/docker-compose.yaml

@@ -117,7 +117,7 @@ services:
       # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
   signoz:
     !!merge <<: *db-depend
-    image: signoz/signoz:v0.128.0
+    image: signoz/signoz:v0.129.0
     ports:
       - "8080:8080" # signoz port
     volumes:

deploy/docker/docker-compose.ha.yaml

@@ -181,7 +181,7 @@ services:
       # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
   signoz:
     !!merge <<: *db-depend
-    image: signoz/signoz:${VERSION:-v0.128.0}
+    image: signoz/signoz:${VERSION:-v0.129.0}
     container_name: signoz
     ports:
       - "8080:8080" # signoz port

deploy/docker/docker-compose.yaml

@@ -109,7 +109,7 @@ services:
       # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
   signoz:
     !!merge <<: *db-depend
-    image: signoz/signoz:${VERSION:-v0.128.0}
+    image: signoz/signoz:${VERSION:-v0.129.0}
     container_name: signoz
     ports:
       - "8080:8080" # signoz port

docs/api/openapi.yml

@@ -3938,8 +3938,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesClusterRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -3950,7 +3948,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesDaemonSetRecord:
@@ -4007,8 +4004,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesDaemonSetRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4019,7 +4014,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesDeploymentRecord:
@@ -4076,8 +4070,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesDeploymentRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4088,7 +4080,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesHostFilter:
@@ -4154,8 +4145,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesHostRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4166,7 +4155,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesJobRecord:
@@ -4229,8 +4217,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesJobRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4241,7 +4227,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesNamespaceRecord:
@@ -4276,8 +4261,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesNamespaceRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4288,7 +4271,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesNodeCondition:
@@ -4353,8 +4335,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesNodeRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4365,7 +4345,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesPodCountsByPhase:
@@ -4451,8 +4430,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesPodRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4463,7 +4440,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesPostableClusters:
@@ -4726,16 +4702,6 @@ components:
       - end
       - limit
       type: object
-    InframonitoringtypesRequiredMetricsCheck:
-      properties:
-        missingMetrics:
-          items:
-            type: string
-          nullable: true
-          type: array
-      required:
-      - missingMetrics
-      type: object
     InframonitoringtypesResponseType:
       enum:
       - list
@@ -4795,8 +4761,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesStatefulSetRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4807,7 +4771,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesVolumeRecord:
@@ -4855,8 +4818,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesVolumeRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4867,7 +4828,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     LlmpricingruletypesGettablePricingRules:
@@ -14695,10 +14655,10 @@ paths:
         for custom groupBy keys; in both modes every row aggregates nodes and pods
         in the group. Supports filtering via a filter expression, custom groupBy,
         ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination
-        via offset/limit. Also reports missing required metrics and whether the requested
-        time range falls before the data retention boundary. Numeric metric fields
-        (clusterCPU, clusterCPUAllocatable, clusterMemory, clusterMemoryAllocatable)
-        return -1 as a sentinel when no data is available for that field.'
+        via offset/limit. Also reports whether the requested time range falls before
+        the data retention boundary. Numeric metric fields (clusterCPU, clusterCPUAllocatable,
+        clusterMemory, clusterMemoryAllocatable) return -1 as a sentinel when no data
+        is available for that field.'
       operationId: ListClusters
       requestBody:
         content:
@@ -14771,11 +14731,11 @@ paths:
         row aggregates pods owned by daemonsets in the group. Supports filtering via
         a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit
         / memory / memory_request / memory_limit / desired_nodes / current_nodes,
-        and pagination via offset/limit. Also reports missing required metrics and
-        whether the requested time range falls before the data retention boundary.
-        Numeric metric fields (daemonSetCPU, daemonSetCPURequest, daemonSetCPULimit,
-        daemonSetMemory, daemonSetMemoryRequest, daemonSetMemoryLimit, desiredNodes,
-        currentNodes) return -1 as a sentinel when no data is available for that field.'
+        and pagination via offset/limit. Also reports whether the requested time range
+        falls before the data retention boundary. Numeric metric fields (daemonSetCPU,
+        daemonSetCPURequest, daemonSetCPULimit, daemonSetMemory, daemonSetMemoryRequest,
+        daemonSetMemoryLimit, desiredNodes, currentNodes) return -1 as a sentinel
+        when no data is available for that field.'
       operationId: ListDaemonSets
       requestBody:
         content:
@@ -14846,11 +14806,11 @@ paths:
         group. Supports filtering via a filter expression, custom groupBy, ordering
         by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit
         / desired_pods / available_pods, and pagination via offset/limit. Also reports
-        missing required metrics and whether the requested time range falls before
-        the data retention boundary. Numeric metric fields (deploymentCPU, deploymentCPURequest,
-        deploymentCPULimit, deploymentMemory, deploymentMemoryRequest, deploymentMemoryLimit,
-        desiredPods, availablePods) return -1 as a sentinel when no data is available
-        for that field.'
+        whether the requested time range falls before the data retention boundary.
+        Numeric metric fields (deploymentCPU, deploymentCPURequest, deploymentCPULimit,
+        deploymentMemory, deploymentMemoryRequest, deploymentMemoryLimit, desiredPods,
+        availablePods) return -1 as a sentinel when no data is available for that
+        field.'
       operationId: ListDeployments
       requestBody:
         content:
@@ -14915,10 +14875,9 @@ paths:
         custom groupBy to aggregate hosts by any attribute, ordering by any of the
         five metrics, and pagination via offset/limit. The response type is ''list''
         for the default host.name grouping or ''grouped_list'' for custom groupBy
-        keys. Also reports missing required metrics and whether the requested time
-        range falls before the data retention boundary. Numeric metric fields (cpu,
-        memory, wait, load15, diskUsage) return -1 as a sentinel when no data is available
-        for that field.'
+        keys. Also reports whether the requested time range falls before the data
+        retention boundary. Numeric metric fields (cpu, memory, wait, load15, diskUsage)
+        return -1 as a sentinel when no data is available for that field.'
       operationId: ListHosts
       requestBody:
         content:
@@ -14992,11 +14951,11 @@ paths:
         jobs in the group. Supports filtering via a filter expression, custom groupBy,
         ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit
         / desired_successful_pods / active_pods / failed_pods / successful_pods, and
-        pagination via offset/limit. Also reports missing required metrics and whether
-        the requested time range falls before the data retention boundary. Numeric
-        metric fields (jobCPU, jobCPURequest, jobCPULimit, jobMemory, jobMemoryRequest,
-        jobMemoryLimit, desiredSuccessfulPods, activePods, failedPods, successfulPods)
-        return -1 as a sentinel when no data is available for that field.'
+        pagination via offset/limit. Also reports whether the requested time range
+        falls before the data retention boundary. Numeric metric fields (jobCPU, jobCPURequest,
+        jobCPULimit, jobMemory, jobMemoryRequest, jobMemoryLimit, desiredSuccessfulPods,
+        activePods, failedPods, successfulPods) return -1 as a sentinel when no data
+        is available for that field.'
       operationId: ListJobs
       requestBody:
         content:
@@ -15061,10 +15020,10 @@ paths:
         type is ''list'' for the default k8s.namespace.name grouping or ''grouped_list''
         for custom groupBy keys; in both modes every row aggregates pods in the group.
         Supports filtering via a filter expression, custom groupBy, ordering by cpu
-        / memory, and pagination via offset/limit. Also reports missing required metrics
-        and whether the requested time range falls before the data retention boundary.
-        Numeric metric fields (namespaceCPU, namespaceMemory) return -1 as a sentinel
-        when no data is available for that field.'
+        / memory, and pagination via offset/limit. Also reports whether the requested
+        time range falls before the data retention boundary. Numeric metric fields
+        (namespaceCPU, namespaceMemory) return -1 as a sentinel when no data is available
+        for that field.'
       operationId: ListNamespaces
       requestBody:
         content:
@@ -15132,10 +15091,10 @@ paths:
         for custom groupBy keys (each row aggregates nodes in the group; condition
         stays no_data). Supports filtering via a filter expression, custom groupBy,
         ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination
-        via offset/limit. Also reports missing required metrics and whether the requested
-        time range falls before the data retention boundary. Numeric metric fields
-        (nodeCPU, nodeCPUAllocatable, nodeMemory, nodeMemoryAllocatable) return -1
-        as a sentinel when no data is available for that field.'
+        via offset/limit. Also reports whether the requested time range falls before
+        the data retention boundary. Numeric metric fields (nodeCPU, nodeCPUAllocatable,
+        nodeMemory, nodeMemoryAllocatable) return -1 as a sentinel when no data is
+        available for that field.'
       operationId: ListNodes
       requestBody:
         content:
@@ -15204,11 +15163,10 @@ paths:
         is one pod with its current phase) or ''grouped_list'' for custom groupBy
         keys (each row aggregates pods in the group with per-phase counts under podCountsByPhase:
         { pending, running, succeeded, failed, unknown } derived from each pod''s
-        latest phase in the window). Also reports missing required metrics and whether
-        the requested time range falls before the data retention boundary. Numeric
-        metric fields (podCPU, podCPURequest, podCPULimit, podMemory, podMemoryRequest,
-        podMemoryLimit, podAge) return -1 as a sentinel when no data is available
-        for that field.'
+        latest phase in the window). Also reports whether the requested time range
+        falls before the data retention boundary. Numeric metric fields (podCPU, podCPURequest,
+        podCPULimit, podMemory, podMemoryRequest, podMemoryLimit, podAge) return -1
+        as a sentinel when no data is available for that field.'
       operationId: ListPods
       requestBody:
         content:
@@ -15275,11 +15233,10 @@ paths:
         usage, inodes, inodes_free, inodes_used), and pagination via offset/limit.
         The response type is ''list'' for the default k8s.persistentvolumeclaim.name
         grouping or ''grouped_list'' for custom groupBy keys; in both modes every
-        row aggregates volumes in the group. Also reports missing required metrics
-        and whether the requested time range falls before the data retention boundary.
-        Numeric metric fields (volumeAvailable, volumeCapacity, volumeUsage, volumeInodes,
-        volumeInodesFree, volumeInodesUsed) return -1 as a sentinel when no data is
-        available for that field.'
+        row aggregates volumes in the group. Also reports whether the requested time
+        range falls before the data retention boundary. Numeric metric fields (volumeAvailable,
+        volumeCapacity, volumeUsage, volumeInodes, volumeInodesFree, volumeInodesUsed)
+        return -1 as a sentinel when no data is available for that field.'
       operationId: ListVolumes
       requestBody:
         content:
@@ -15350,11 +15307,10 @@ paths:
         statefulsets in the group. Supports filtering via a filter expression, custom
         groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request
         / memory_limit / desired_pods / current_pods, and pagination via offset/limit.
-        Also reports missing required metrics and whether the requested time range
-        falls before the data retention boundary. Numeric metric fields (statefulSetCPU,
-        statefulSetCPURequest, statefulSetCPULimit, statefulSetMemory, statefulSetMemoryRequest,
-        statefulSetMemoryLimit, desiredPods, currentPods) return -1 as a sentinel
-        when no data is available for that field.'
+        Also reports whether the requested time range falls before the data retention
+        boundary. Numeric metric fields (statefulSetCPU, statefulSetCPURequest, statefulSetCPULimit,
+        statefulSetMemory, statefulSetMemoryRequest, statefulSetMemoryLimit, desiredPods,
+        currentPods) return -1 as a sentinel when no data is available for that field.'
       operationId: ListStatefulSets
       requestBody:
         content:

frontend/src/api/generated/services/inframonitoring/index.ts

@@ -39,7 +39,7 @@ import { GeneratedAPIInstance } from '../../../generatedAPIInstance';
 import type { ErrorType, BodyType } from '../../../generatedAPIInstance';
 
 /**
- * Returns a paginated list of Kubernetes clusters with key aggregated metrics derived by summing per-node values within the group: CPU usage, CPU allocatable, memory working set, memory allocatable. Each row also reports per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready value) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each cluster includes metadata attributes (k8s.cluster.name). The response type is 'list' for the default k8s.cluster.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates nodes and pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (clusterCPU, clusterCPUAllocatable, clusterMemory, clusterMemoryAllocatable) return -1 as a sentinel when no data is available for that field.
+ * Returns a paginated list of Kubernetes clusters with key aggregated metrics derived by summing per-node values within the group: CPU usage, CPU allocatable, memory working set, memory allocatable. Each row also reports per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready value) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each cluster includes metadata attributes (k8s.cluster.name). The response type is 'list' for the default k8s.cluster.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates nodes and pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (clusterCPU, clusterCPUAllocatable, clusterMemory, clusterMemoryAllocatable) return -1 as a sentinel when no data is available for that field.
  * @summary List Clusters for Infra Monitoring
  */
 export const listClusters = (
@@ -122,7 +122,7 @@ export const useListClusters = <
 	return useMutation(getListClustersMutationOptions(options));
 };
 /**
- * Returns a paginated list of Kubernetes DaemonSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the daemonset, plus average CPU/memory request and limit utilization (daemonSetCPURequest, daemonSetCPULimit, daemonSetMemoryRequest, daemonSetMemoryLimit). Each row also reports the latest known node-level counters from kube-state-metrics: desiredNodes (k8s.daemonset.desired_scheduled_nodes, the number of nodes the daemonset wants to run on) and currentNodes (k8s.daemonset.current_scheduled_nodes, the number of nodes the daemonset currently runs on) — note these are node counts, not pod counts. It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each daemonset includes metadata attributes (k8s.daemonset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.daemonset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by daemonsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_nodes / current_nodes, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (daemonSetCPU, daemonSetCPURequest, daemonSetCPULimit, daemonSetMemory, daemonSetMemoryRequest, daemonSetMemoryLimit, desiredNodes, currentNodes) return -1 as a sentinel when no data is available for that field.
+ * Returns a paginated list of Kubernetes DaemonSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the daemonset, plus average CPU/memory request and limit utilization (daemonSetCPURequest, daemonSetCPULimit, daemonSetMemoryRequest, daemonSetMemoryLimit). Each row also reports the latest known node-level counters from kube-state-metrics: desiredNodes (k8s.daemonset.desired_scheduled_nodes, the number of nodes the daemonset wants to run on) and currentNodes (k8s.daemonset.current_scheduled_nodes, the number of nodes the daemonset currently runs on) — note these are node counts, not pod counts. It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each daemonset includes metadata attributes (k8s.daemonset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.daemonset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by daemonsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_nodes / current_nodes, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (daemonSetCPU, daemonSetCPURequest, daemonSetCPULimit, daemonSetMemory, daemonSetMemoryRequest, daemonSetMemoryLimit, desiredNodes, currentNodes) return -1 as a sentinel when no data is available for that field.
  * @summary List DaemonSets for Infra Monitoring
  */
 export const listDaemonSets = (
@@ -205,7 +205,7 @@ export const useListDaemonSets = <
 	return useMutation(getListDaemonSetsMutationOptions(options));
 };
 /**
- * Returns a paginated list of Kubernetes Deployments with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the deployment, plus average CPU/memory request and limit utilization (deploymentCPURequest, deploymentCPULimit, deploymentMemoryRequest, deploymentMemoryLimit). Each row also reports the latest known desiredPods (k8s.deployment.desired) and availablePods (k8s.deployment.available) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each deployment includes metadata attributes (k8s.deployment.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.deployment.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by deployments in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / available_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (deploymentCPU, deploymentCPURequest, deploymentCPULimit, deploymentMemory, deploymentMemoryRequest, deploymentMemoryLimit, desiredPods, availablePods) return -1 as a sentinel when no data is available for that field.
+ * Returns a paginated list of Kubernetes Deployments with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the deployment, plus average CPU/memory request and limit utilization (deploymentCPURequest, deploymentCPULimit, deploymentMemoryRequest, deploymentMemoryLimit). Each row also reports the latest known desiredPods (k8s.deployment.desired) and availablePods (k8s.deployment.available) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each deployment includes metadata attributes (k8s.deployment.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.deployment.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by deployments in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / available_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (deploymentCPU, deploymentCPURequest, deploymentCPULimit, deploymentMemory, deploymentMemoryRequest, deploymentMemoryLimit, desiredPods, availablePods) return -1 as a sentinel when no data is available for that field.
  * @summary List Deployments for Infra Monitoring
  */
 export const listDeployments = (
@@ -288,7 +288,7 @@ export const useListDeployments = <
 	return useMutation(getListDeploymentsMutationOptions(options));
 };
 /**
- * Returns a paginated list of hosts with key infrastructure metrics: CPU usage (%), memory usage (%), I/O wait (%), disk usage (%), and 15-minute load average. Each host includes its current status (active/inactive based on metrics reported in the last 10 minutes) and metadata attributes (e.g., os.type). Supports filtering via a filter expression, filtering by host status, custom groupBy to aggregate hosts by any attribute, ordering by any of the five metrics, and pagination via offset/limit. The response type is 'list' for the default host.name grouping or 'grouped_list' for custom groupBy keys. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (cpu, memory, wait, load15, diskUsage) return -1 as a sentinel when no data is available for that field.
+ * Returns a paginated list of hosts with key infrastructure metrics: CPU usage (%), memory usage (%), I/O wait (%), disk usage (%), and 15-minute load average. Each host includes its current status (active/inactive based on metrics reported in the last 10 minutes) and metadata attributes (e.g., os.type). Supports filtering via a filter expression, filtering by host status, custom groupBy to aggregate hosts by any attribute, ordering by any of the five metrics, and pagination via offset/limit. The response type is 'list' for the default host.name grouping or 'grouped_list' for custom groupBy keys. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (cpu, memory, wait, load15, diskUsage) return -1 as a sentinel when no data is available for that field.
  * @summary List Hosts for Infra Monitoring
  */
 export const listHosts = (
@@ -371,7 +371,7 @@ export const useListHosts = <
 	return useMutation(getListHostsMutationOptions(options));
 };
 /**
- * Returns a paginated list of Kubernetes Jobs with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the job, plus average CPU/memory request and limit utilization (jobCPURequest, jobCPULimit, jobMemoryRequest, jobMemoryLimit). Each row also reports the latest known job-level counters from kube-state-metrics: desiredSuccessfulPods (k8s.job.desired_successful_pods, the target completion count), activePods (k8s.job.active_pods), failedPods (k8s.job.failed_pods, cumulative across the lifetime of the job), and successfulPods (k8s.job.successful_pods, cumulative). It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value); note podCountsByPhase.failed (current pod-phase) is distinct from failedPods (cumulative job kube-state-metric). Each job includes metadata attributes (k8s.job.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.job.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by jobs in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_successful_pods / active_pods / failed_pods / successful_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (jobCPU, jobCPURequest, jobCPULimit, jobMemory, jobMemoryRequest, jobMemoryLimit, desiredSuccessfulPods, activePods, failedPods, successfulPods) return -1 as a sentinel when no data is available for that field.
+ * Returns a paginated list of Kubernetes Jobs with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the job, plus average CPU/memory request and limit utilization (jobCPURequest, jobCPULimit, jobMemoryRequest, jobMemoryLimit). Each row also reports the latest known job-level counters from kube-state-metrics: desiredSuccessfulPods (k8s.job.desired_successful_pods, the target completion count), activePods (k8s.job.active_pods), failedPods (k8s.job.failed_pods, cumulative across the lifetime of the job), and successfulPods (k8s.job.successful_pods, cumulative). It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value); note podCountsByPhase.failed (current pod-phase) is distinct from failedPods (cumulative job kube-state-metric). Each job includes metadata attributes (k8s.job.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.job.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by jobs in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_successful_pods / active_pods / failed_pods / successful_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (jobCPU, jobCPURequest, jobCPULimit, jobMemory, jobMemoryRequest, jobMemoryLimit, desiredSuccessfulPods, activePods, failedPods, successfulPods) return -1 as a sentinel when no data is available for that field.
  * @summary List Jobs for Infra Monitoring
  */
 export const listJobs = (
@@ -454,7 +454,7 @@ export const useListJobs = <
 	return useMutation(getListJobsMutationOptions(options));
 };
 /**
- * Returns a paginated list of Kubernetes namespaces with key aggregated pod metrics: CPU usage and memory working set (summed across pods in the group), plus per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value in the window). Each namespace includes metadata attributes (k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.namespace.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / memory, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (namespaceCPU, namespaceMemory) return -1 as a sentinel when no data is available for that field.
+ * Returns a paginated list of Kubernetes namespaces with key aggregated pod metrics: CPU usage and memory working set (summed across pods in the group), plus per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value in the window). Each namespace includes metadata attributes (k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.namespace.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / memory, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (namespaceCPU, namespaceMemory) return -1 as a sentinel when no data is available for that field.
  * @summary List Namespaces for Infra Monitoring
  */
 export const listNamespaces = (
@@ -537,7 +537,7 @@ export const useListNamespaces = <
 	return useMutation(getListNamespacesMutationOptions(options));
 };
 /**
- * Returns a paginated list of Kubernetes nodes with key metrics: CPU usage, CPU allocatable, memory working set, memory allocatable, per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready in the window) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } for pods scheduled on the listed nodes). Each node includes metadata attributes (k8s.node.uid, k8s.cluster.name). The response type is 'list' for the default k8s.node.name grouping (each row is one node with its current condition string: ready / not_ready / no_data) or 'grouped_list' for custom groupBy keys (each row aggregates nodes in the group; condition stays no_data). Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (nodeCPU, nodeCPUAllocatable, nodeMemory, nodeMemoryAllocatable) return -1 as a sentinel when no data is available for that field.
+ * Returns a paginated list of Kubernetes nodes with key metrics: CPU usage, CPU allocatable, memory working set, memory allocatable, per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready in the window) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } for pods scheduled on the listed nodes). Each node includes metadata attributes (k8s.node.uid, k8s.cluster.name). The response type is 'list' for the default k8s.node.name grouping (each row is one node with its current condition string: ready / not_ready / no_data) or 'grouped_list' for custom groupBy keys (each row aggregates nodes in the group; condition stays no_data). Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (nodeCPU, nodeCPUAllocatable, nodeMemory, nodeMemoryAllocatable) return -1 as a sentinel when no data is available for that field.
  * @summary List Nodes for Infra Monitoring
  */
 export const listNodes = (
@@ -620,7 +620,7 @@ export const useListNodes = <
 	return useMutation(getListNodesMutationOptions(options));
 };
 /**
- * Returns a paginated list of Kubernetes pods with key metrics: CPU usage, CPU request/limit utilization, memory working set, memory request/limit utilization, current pod phase (pending/running/succeeded/failed/unknown/no_data), and pod age (ms since start time). Each pod includes metadata attributes (namespace, node, workload owner such as deployment/statefulset/daemonset/job/cronjob, cluster). Supports filtering via a filter expression, custom groupBy to aggregate pods by any attribute, ordering by any of the six metrics (cpu, cpu_request, cpu_limit, memory, memory_request, memory_limit), and pagination via offset/limit. The response type is 'list' for the default k8s.pod.uid grouping (each row is one pod with its current phase) or 'grouped_list' for custom groupBy keys (each row aggregates pods in the group with per-phase counts under podCountsByPhase: { pending, running, succeeded, failed, unknown } derived from each pod's latest phase in the window). Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (podCPU, podCPURequest, podCPULimit, podMemory, podMemoryRequest, podMemoryLimit, podAge) return -1 as a sentinel when no data is available for that field.
+ * Returns a paginated list of Kubernetes pods with key metrics: CPU usage, CPU request/limit utilization, memory working set, memory request/limit utilization, current pod phase (pending/running/succeeded/failed/unknown/no_data), and pod age (ms since start time). Each pod includes metadata attributes (namespace, node, workload owner such as deployment/statefulset/daemonset/job/cronjob, cluster). Supports filtering via a filter expression, custom groupBy to aggregate pods by any attribute, ordering by any of the six metrics (cpu, cpu_request, cpu_limit, memory, memory_request, memory_limit), and pagination via offset/limit. The response type is 'list' for the default k8s.pod.uid grouping (each row is one pod with its current phase) or 'grouped_list' for custom groupBy keys (each row aggregates pods in the group with per-phase counts under podCountsByPhase: { pending, running, succeeded, failed, unknown } derived from each pod's latest phase in the window). Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (podCPU, podCPURequest, podCPULimit, podMemory, podMemoryRequest, podMemoryLimit, podAge) return -1 as a sentinel when no data is available for that field.
  * @summary List Pods for Infra Monitoring
  */
 export const listPods = (
@@ -703,7 +703,7 @@ export const useListPods = <
 	return useMutation(getListPodsMutationOptions(options));
 };
 /**
- * Returns a paginated list of Kubernetes persistent volume claims (PVCs) with key volume metrics: available bytes, capacity bytes, usage (capacity - available), inodes, free inodes, and used inodes. Each row also includes metadata attributes (k8s.persistentvolumeclaim.name, k8s.pod.uid, k8s.pod.name, k8s.namespace.name, k8s.node.name, k8s.statefulset.name, k8s.cluster.name). Supports filtering via a filter expression, custom groupBy to aggregate volumes by any attribute, ordering by any of the six metrics (available, capacity, usage, inodes, inodes_free, inodes_used), and pagination via offset/limit. The response type is 'list' for the default k8s.persistentvolumeclaim.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates volumes in the group. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (volumeAvailable, volumeCapacity, volumeUsage, volumeInodes, volumeInodesFree, volumeInodesUsed) return -1 as a sentinel when no data is available for that field.
+ * Returns a paginated list of Kubernetes persistent volume claims (PVCs) with key volume metrics: available bytes, capacity bytes, usage (capacity - available), inodes, free inodes, and used inodes. Each row also includes metadata attributes (k8s.persistentvolumeclaim.name, k8s.pod.uid, k8s.pod.name, k8s.namespace.name, k8s.node.name, k8s.statefulset.name, k8s.cluster.name). Supports filtering via a filter expression, custom groupBy to aggregate volumes by any attribute, ordering by any of the six metrics (available, capacity, usage, inodes, inodes_free, inodes_used), and pagination via offset/limit. The response type is 'list' for the default k8s.persistentvolumeclaim.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates volumes in the group. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (volumeAvailable, volumeCapacity, volumeUsage, volumeInodes, volumeInodesFree, volumeInodesUsed) return -1 as a sentinel when no data is available for that field.
  * @summary List Volumes for Infra Monitoring
  */
 export const listVolumes = (
@@ -786,7 +786,7 @@ export const useListVolumes = <
 	return useMutation(getListVolumesMutationOptions(options));
 };
 /**
- * Returns a paginated list of Kubernetes StatefulSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the statefulset, plus average CPU/memory request and limit utilization (statefulSetCPURequest, statefulSetCPULimit, statefulSetMemoryRequest, statefulSetMemoryLimit). Each row also reports the latest known desiredPods (k8s.statefulset.desired_pods) and currentPods (k8s.statefulset.current_pods) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each statefulset includes metadata attributes (k8s.statefulset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.statefulset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by statefulsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / current_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (statefulSetCPU, statefulSetCPURequest, statefulSetCPULimit, statefulSetMemory, statefulSetMemoryRequest, statefulSetMemoryLimit, desiredPods, currentPods) return -1 as a sentinel when no data is available for that field.
+ * Returns a paginated list of Kubernetes StatefulSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the statefulset, plus average CPU/memory request and limit utilization (statefulSetCPURequest, statefulSetCPULimit, statefulSetMemoryRequest, statefulSetMemoryLimit). Each row also reports the latest known desiredPods (k8s.statefulset.desired_pods) and currentPods (k8s.statefulset.current_pods) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each statefulset includes metadata attributes (k8s.statefulset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.statefulset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by statefulsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / current_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (statefulSetCPU, statefulSetCPURequest, statefulSetCPULimit, statefulSetMemory, statefulSetMemoryRequest, statefulSetMemoryLimit, desiredPods, currentPods) return -1 as a sentinel when no data is available for that field.
  * @summary List StatefulSets for Infra Monitoring
  */
 export const listStatefulSets = (

frontend/src/api/generated/services/sigNoz.schemas.ts

@@ -5423,13 +5423,6 @@ export interface InframonitoringtypesClusterRecordDTO {
 	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
 }
 
-export interface InframonitoringtypesRequiredMetricsCheckDTO {
-	/**
-	 * @type array,null
-	 */
-	missingMetrics: string[] | null;
-}
-
 export enum InframonitoringtypesResponseTypeDTO {
 	list = 'list',
 	grouped_list = 'grouped_list',
@@ -5465,7 +5458,6 @@ export interface InframonitoringtypesClustersDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesClusterRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5543,7 +5535,6 @@ export interface InframonitoringtypesDaemonSetsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesDaemonSetRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5621,7 +5612,6 @@ export interface InframonitoringtypesDeploymentsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesDeploymentRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5707,7 +5697,6 @@ export interface InframonitoringtypesHostsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesHostRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5793,7 +5782,6 @@ export interface InframonitoringtypesJobsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesJobRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5843,7 +5831,6 @@ export interface InframonitoringtypesNamespacesDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesNamespaceRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5910,7 +5897,6 @@ export interface InframonitoringtypesNodesDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesNodeRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5994,7 +5980,6 @@ export interface InframonitoringtypesPodsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesPodRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -6342,7 +6327,6 @@ export interface InframonitoringtypesStatefulSetsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesStatefulSetRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -6411,7 +6395,6 @@ export interface InframonitoringtypesVolumesDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesVolumeRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */

frontend/src/container/MetricsApplication/Tabs/Overview/ServiceOverview.tsx

@@ -1,6 +1,5 @@
 import { useMemo } from 'react';
 import { useParams } from 'react-router-dom';
-import { Skeleton } from 'antd';
 import { ENTITY_VERSION_V4 } from 'constants/app';
 import { FeatureKeys } from 'constants/features';
 import { PANEL_TYPES } from 'constants/queryBuilder';
@@ -124,24 +123,14 @@ function ServiceOverview({
 			/>
 			<Card data-testid="service_latency">
 				<GraphContainer>
-					{topLevelOperationsIsLoading && (
-						<Skeleton
-							style={{
-								height: '100%',
-								padding: '16px',
-							}}
-						/>
-					)}
-					{!topLevelOperationsIsLoading && (
-						<Graph
-							onDragSelect={onDragSelect}
-							widget={latencyWidget}
-							onClickHandler={handleGraphClick('Service')}
-							isQueryEnabled={isQueryEnabled}
-							version={ENTITY_VERSION_V4}
-							enableDrillDown={SERVICE_DETAIL_DRILLDOWN_ENABLED}
-						/>
-					)}
+					<Graph
+						onDragSelect={onDragSelect}
+						widget={latencyWidget}
+						onClickHandler={handleGraphClick('Service')}
+						isQueryEnabled={isQueryEnabled}
+						version={ENTITY_VERSION_V4}
+						enableDrillDown={SERVICE_DETAIL_DRILLDOWN_ENABLED}
+					/>
 				</GraphContainer>
 			</Card>
 		</>

frontend/src/container/MetricsApplication/Tabs/Overview/TopLevelOperations.tsx

@@ -1,4 +1,3 @@
-import { Skeleton } from 'antd';
 import { Typography } from '@signozhq/ui/typography';
 import axios from 'axios';
 import { SOMETHING_WENT_WRONG } from 'constants/api';
@@ -29,24 +28,14 @@ function TopLevelOperation({
 				</Typography>
 			) : (
 				<GraphContainer>
-					{topLevelOperationsIsLoading && (
-						<Skeleton
-							style={{
-								height: '100%',
-								padding: '16px',
-							}}
-						/>
-					)}
-					{!topLevelOperationsIsLoading && (
-						<Graph
-							widget={widget}
-							onClickHandler={handleGraphClick(opName)}
-							onDragSelect={onDragSelect}
-							isQueryEnabled={!topLevelOperationsIsLoading}
-							version={ENTITY_VERSION_V4}
-							enableDrillDown={SERVICE_DETAIL_DRILLDOWN_ENABLED}
-						/>
-					)}
+					<Graph
+						widget={widget}
+						onClickHandler={handleGraphClick(opName)}
+						onDragSelect={onDragSelect}
+						isQueryEnabled={!topLevelOperationsIsLoading}
+						version={ENTITY_VERSION_V4}
+						enableDrillDown={SERVICE_DETAIL_DRILLDOWN_ENABLED}
+					/>
 				</GraphContainer>
 			)}
 		</Card>

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardPageToolbar/index.tsx

@@ -20,6 +20,7 @@ import APIError from 'types/api/error';
 import DashboardActions from './DashboardActions/DashboardActions';
 import DashboardInfo from './DashboardInfo/DashboardInfo';
 import { useEditableTitle } from './DashboardInfo/useEditableTitle';
+import { usePublicDashboardMeta } from '../DashboardSettings/PublicDashboard/usePublicDashboardMeta';
 
 import styles from './DashboardPageToolbar.module.scss';
 
@@ -52,6 +53,10 @@ function DashboardPageToolbar(props: DashboardPageToolbarProps): JSX.Element {
 		(s) => s.setIsPanelTypeSelectionModalOpen,
 	);
 
+	// Single global fetch of the public-sharing meta (the drawer reuses this cache);
+	// drives the public-access badge.
+	const { isPublic: isPublicDashboard } = usePublicDashboardMeta(id);
+
 	const isAuthor =
 		!!user?.email && !!dashboard.createdBy && dashboard.createdBy === user.email;
 
@@ -117,7 +122,7 @@ function DashboardPageToolbar(props: DashboardPageToolbarProps): JSX.Element {
 					image={image}
 					tags={tags}
 					description={description}
-					isPublicDashboard={false}
+					isPublicDashboard={isPublicDashboard}
 					isDashboardLocked={isDashboardLocked}
 					isEditing={isEditing}
 					draft={draft}

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboard.module.scss

@@ -1,106 +1,15 @@
-// settings card wrapper — mirrors the V1 public dashboard treatment
-.publicDashboardCard {
+// Publish tab — "status strip" direction (Claude Design: Publish Drawer Final).
+// Fills the drawer height so the actions anchor a footer instead of floating.
+.publishTab {
 	display: flex;
 	flex-direction: column;
-	gap: 8px;
-	padding: 16px;
-	border-radius: 3px;
-	border: 1px solid var(--l2-border);
+	height: 100%;
+	min-height: 100%;
 }
 
-.statusTitle {
-	margin-bottom: 16px;
-	color: var(--l1-foreground);
-	font-family: Inter;
-	font-size: 14px;
-	font-weight: 500;
-	line-height: 20px;
-}
-
-.checkbox {
-	margin-bottom: 8px;
-}
-
-.timeRangeSelectGroup {
-	display: flex;
-	flex-direction: column;
-	gap: 4px;
-	margin-bottom: 8px;
-}
-
-.timeRangeSelectLabel {
-	color: var(--l2-foreground);
-	font-family: Inter;
-	font-size: 12px;
-	font-weight: 500;
-	line-height: 18px;
-}
-
-.timeRangeSelect {
-	width: 200px;
-}
-
-.urlGroup {
-	display: flex;
-	flex-direction: column;
-	gap: 4px;
-}
-
-.urlLabel {
-	color: var(--l2-foreground);
-	font-family: Inter;
-	font-size: 12px;
-	font-weight: 500;
-	line-height: 18px;
-}
-
-.urlContainer {
-	display: flex;
-	align-items: center;
-	gap: 8px;
-	padding: 0 4px;
-	border-radius: 4px;
-	border: 1px solid var(--l1-border);
-	background: var(--l3-background);
-}
-
-.urlText {
+.content {
 	flex: 1;
-	overflow: hidden;
-	text-overflow: ellipsis;
-	white-space: nowrap;
-	color: var(--l2-foreground);
-	font-family: Inter;
-	font-size: 13px;
-	line-height: 32px;
-}
-
-.callout {
 	display: flex;
-	align-items: center;
-	gap: 8px;
-	margin-top: 12px;
-	padding: 12px 8px;
-	border-radius: 3px;
-	background: color-mix(in srgb, var(--primary-background) 10%, transparent);
-}
-
-.calloutIcon {
-	flex-shrink: 0;
-	color: var(--text-robin-300);
-}
-
-.calloutText {
-	color: var(--text-robin-300);
-	font-family: Inter;
-	font-size: 11px;
-	font-weight: 400;
-	line-height: 16px;
-}
-
-.actions {
-	display: flex;
-	justify-content: flex-end;
-	gap: 8px;
-	margin-top: 32px;
+	flex-direction: column;
+	gap: 20px;
 }

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardActions/PublicDashboardActions.module.scss

@@ -0,0 +1,12 @@
+.footer {
+	position: sticky;
+	z-index: 1;
+	flex: none;
+	display: flex;
+	align-items: center;
+	justify-content: flex-end;
+	gap: 12px;
+	margin-top: 10px;
+	padding-top: 14px;
+	border-top: 1px solid var(--l2-border);
+}

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardActions/PublicDashboardActions.tsx

@@ -1,7 +1,7 @@
-import { Globe, Trash } from '@signozhq/icons';
+import { Globe, RefreshCw, Trash } from '@signozhq/icons';
 import { Button } from '@signozhq/ui/button';
 
-import styles from './PublicDashboard.module.scss';
+import styles from './PublicDashboardActions.module.scss';
 
 interface PublicDashboardActionsProps {
 	isPublic: boolean;
@@ -25,7 +25,7 @@ function PublicDashboardActions({
 	onUnpublish,
 }: PublicDashboardActionsProps): JSX.Element {
 	return (
-		<div className={styles.actions}>
+		<div className={styles.footer}>
 			{isPublic ? (
 				<>
 					<Button
@@ -33,22 +33,22 @@ function PublicDashboardActions({
 						color="destructive"
 						disabled={disabled}
 						loading={isUnpublishing}
-						prefix={<Trash size={14} />}
+						prefix={<Trash size={15} />}
 						testId="public-dashboard-unpublish"
 						onClick={onUnpublish}
 					>
-						Unpublish dashboard
+						Unpublish Dashboard
 					</Button>
 					<Button
 						variant="solid"
 						color="primary"
 						disabled={disabled}
 						loading={isUpdating}
-						prefix={<Globe size={14} />}
+						prefix={<RefreshCw size={15} />}
 						testId="public-dashboard-update"
 						onClick={onUpdate}
 					>
-						Update published dashboard
+						Update Dashboard
 					</Button>
 				</>
 			) : (
@@ -57,11 +57,11 @@ function PublicDashboardActions({
 					color="primary"
 					disabled={disabled}
 					loading={isPublishing}
-					prefix={<Globe size={14} />}
+					prefix={<Globe size={15} />}
 					testId="public-dashboard-publish"
 					onClick={onPublish}
 				>
-					Publish dashboard
+					Publish Dashboard
 				</Button>
 			)}
 		</div>

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardCallout.tsx

@@ -1,17 +0,0 @@
-import { Info } from '@signozhq/icons';
-import { Typography } from '@signozhq/ui/typography';
-
-import styles from './PublicDashboard.module.scss';
-
-function PublicDashboardCallout(): JSX.Element {
-	return (
-		<div className={styles.callout}>
-			<Info size={12} className={styles.calloutIcon} />
-			<Typography.Text className={styles.calloutText}>
-				Dashboard variables won&apos;t work in public dashboards
-			</Typography.Text>
-		</div>
-	);
-}
-
-export default PublicDashboardCallout;

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardHint/PublicDashboardHint.module.scss

@@ -0,0 +1,19 @@
+.hint {
+	display: flex;
+	align-items: flex-start;
+	gap: 8px;
+	padding-top: 2px;
+	color: var(--l3-foreground);
+}
+
+.hintIcon {
+	flex: none;
+	margin-top: 1px;
+	color: var(--l3-foreground);
+}
+
+.hintText {
+	color: var(--l3-foreground);
+	font-size: 12px;
+	line-height: 1.5;
+}

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardHint/PublicDashboardHint.tsx

@@ -0,0 +1,17 @@
+import { Info } from '@signozhq/icons';
+import { Typography } from '@signozhq/ui/typography';
+
+import styles from './PublicDashboardHint.module.scss';
+
+function PublicDashboardHint(): JSX.Element {
+	return (
+		<div className={styles.hint}>
+			<Info size={14} className={styles.hintIcon} />
+			<Typography.Text className={styles.hintText}>
+				Dashboard variables aren&apos;t supported on public links.
+			</Typography.Text>
+		</div>
+	);
+}
+
+export default PublicDashboardHint;

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardSettingsForm/PublicDashboardSettingsForm.module.scss

@@ -0,0 +1,34 @@
+.switchRow {
+	display: flex;
+	align-items: center;
+}
+
+.fieldGroup {
+	display: flex;
+	flex-direction: column;
+	gap: 8px;
+
+	// Render the (non-portaled) dropdown above the drawer.
+	[data-radix-popper-content-wrapper] {
+		z-index: 1100 !important;
+	}
+
+	// Radix sets --radix-select-trigger-width on the content element (the wrapper's
+	// child), so match it there to make the dropdown take the input's width.
+	// SelectSimple exposes no content className, hence the descendant selector.
+	[data-radix-popper-content-wrapper] > * {
+		width: var(--radix-select-trigger-width);
+		min-width: var(--radix-select-trigger-width);
+	}
+}
+
+.fieldLabel {
+	color: var(--l2-foreground);
+	font-size: 12px;
+	font-weight: 500;
+	line-height: 1;
+}
+
+.timeRangeSelect {
+	width: 100%;
+}

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardSettingsForm/PublicDashboardSettingsForm.tsx

@@ -1,9 +1,9 @@
-import { Checkbox } from '@signozhq/ui/checkbox';
 import { SelectSimple } from '@signozhq/ui/select';
+import { Switch } from '@signozhq/ui/switch';
 import { Typography } from '@signozhq/ui/typography';
+import { RelativeDurationOptions } from 'container/TopNav/DateTimeSelectionV2/constants';
 
-import { TIME_RANGE_PRESETS_OPTIONS } from './constants';
-import styles from './PublicDashboard.module.scss';
+import styles from './PublicDashboardSettingsForm.module.scss';
 
 interface PublicDashboardSettingsFormProps {
 	timeRangeEnabled: boolean;
@@ -22,28 +22,29 @@ function PublicDashboardSettingsForm({
 }: PublicDashboardSettingsFormProps): JSX.Element {
 	return (
 		<>
-			<Checkbox
-				id="public-dashboard-enable-time-range"
-				className={styles.checkbox}
-				testId="public-dashboard-time-range-toggle"
-				value={timeRangeEnabled}
-				disabled={disabled}
-				onChange={(checked): void => onTimeRangeEnabledChange(checked === true)}
-			>
-				Enable time range
-			</Checkbox>
+			<div className={styles.switchRow}>
+				<Switch
+					testId="public-dashboard-time-range-toggle"
+					value={timeRangeEnabled}
+					disabled={disabled}
+					onChange={onTimeRangeEnabledChange}
+				>
+					Enable time range
+				</Switch>
+			</div>
 
-			<div className={styles.timeRangeSelectGroup}>
-				<Typography.Text className={styles.timeRangeSelectLabel}>
+			<div className={styles.fieldGroup}>
+				<Typography.Text className={styles.fieldLabel}>
 					Default time range
 				</Typography.Text>
 				<SelectSimple
 					className={styles.timeRangeSelect}
 					testId="public-dashboard-default-time-range"
 					placeholder="Select default time range"
-					items={TIME_RANGE_PRESETS_OPTIONS}
+					items={RelativeDurationOptions}
 					value={defaultTimeRange}
 					disabled={disabled}
+					withPortal={false}
 					onChange={(value): void => onDefaultTimeRangeChange(value as string)}
 				/>
 			</div>

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardStatus.tsx

@@ -1,21 +0,0 @@
-import { Typography } from '@signozhq/ui/typography';
-
-import styles from './PublicDashboard.module.scss';
-
-interface PublicDashboardStatusProps {
-	isPublic: boolean;
-}
-
-function PublicDashboardStatus({
-	isPublic,
-}: PublicDashboardStatusProps): JSX.Element {
-	return (
-		<Typography.Text className={styles.statusTitle}>
-			{isPublic
-				? 'This dashboard is publicly accessible. Anyone with the link can view it.'
-				: 'This dashboard is private. Publish it to make it accessible to anyone with the link.'}
-		</Typography.Text>
-	);
-}
-
-export default PublicDashboardStatus;

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardStatus/PublicDashboardStatus.module.scss

@@ -0,0 +1,67 @@
+.statusStrip {
+	display: flex;
+	align-items: center;
+	gap: 13px;
+	padding: 14px 16px;
+	border-radius: 8px;
+	border: 1px solid var(--l2-border);
+	background: var(--l1-background);
+}
+
+.statusStripLive {
+	border-color: var(--callout-primary-border);
+	background: var(--callout-primary-background);
+}
+
+.statusMedallion {
+	display: flex;
+	align-items: center;
+	justify-content: center;
+	flex: none;
+	width: 38px;
+	height: 38px;
+	border-radius: 6px;
+	border: 1px solid var(--l2-border);
+	background: var(--l3-background);
+	color: var(--l2-foreground);
+}
+
+.statusMedallionLive {
+	border-color: var(--callout-primary-border);
+	background: var(--callout-primary-background);
+	color: var(--callout-primary-icon);
+}
+
+.statusBody {
+	flex: 1;
+	min-width: 0;
+	display: flex;
+	flex-direction: column;
+}
+
+.statusTitle {
+	color: var(--l1-foreground);
+	font-size: 14px;
+	font-weight: 600;
+	line-height: 1.2;
+}
+
+.statusSubtitle {
+	margin-top: 2px;
+	color: var(--l3-foreground);
+	font-size: 13px;
+	line-height: 1.35;
+}
+
+.statusSubtitleLive {
+	color: var(--l2-foreground);
+}
+
+.statusBadgeDot {
+	display: inline-block;
+	width: 6px;
+	height: 6px;
+	border-radius: 50%;
+	margin-right: 6px;
+	background: currentColor;
+}

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardStatus/PublicDashboardStatus.tsx

@@ -0,0 +1,50 @@
+import { Globe, LockKeyhole } from '@signozhq/icons';
+import { Badge } from '@signozhq/ui/badge';
+import { Typography } from '@signozhq/ui/typography';
+import cx from 'classnames';
+
+import styles from './PublicDashboardStatus.module.scss';
+
+interface PublicDashboardStatusProps {
+	isPublic: boolean;
+}
+
+function PublicDashboardStatus({
+	isPublic,
+}: PublicDashboardStatusProps): JSX.Element {
+	return (
+		<div
+			className={cx(styles.statusStrip, { [styles.statusStripLive]: isPublic })}
+		>
+			<span
+				className={cx(styles.statusMedallion, {
+					[styles.statusMedallionLive]: isPublic,
+				})}
+			>
+				{isPublic ? <Globe size={18} /> : <LockKeyhole size={18} />}
+			</span>
+
+			<div className={styles.statusBody}>
+				<Typography.Text className={styles.statusTitle}>
+					{isPublic ? 'This dashboard is live' : 'This dashboard is private'}
+				</Typography.Text>
+				<Typography.Text
+					className={cx(styles.statusSubtitle, {
+						[styles.statusSubtitleLive]: isPublic,
+					})}
+				>
+					{isPublic
+						? 'Anyone with the link can view it — no account needed.'
+						: 'Publish it to share a read-only view with anyone who has the link.'}
+				</Typography.Text>
+			</div>
+
+			<Badge variant="outline" color={isPublic ? 'robin' : 'secondary'}>
+				<span className={styles.statusBadgeDot} />
+				{isPublic ? 'Public' : 'Private'}
+			</Badge>
+		</div>
+	);
+}
+
+export default PublicDashboardStatus;

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardUrl.tsx

@@ -1,49 +0,0 @@
-import { Copy, ExternalLink } from '@signozhq/icons';
-import { Button } from '@signozhq/ui/button';
-import { Typography } from '@signozhq/ui/typography';
-
-import styles from './PublicDashboard.module.scss';
-
-interface PublicDashboardUrlProps {
-	url: string;
-	onCopy: () => void;
-	onOpen: () => void;
-}
-
-function PublicDashboardUrl({
-	url,
-	onCopy,
-	onOpen,
-}: PublicDashboardUrlProps): JSX.Element {
-	return (
-		<div className={styles.urlGroup}>
-			<Typography.Text className={styles.urlLabel}>
-				Public dashboard URL
-			</Typography.Text>
-
-			<div className={styles.urlContainer}>
-				<Typography.Text className={styles.urlText}>{url}</Typography.Text>
-				<Button
-					variant="ghost"
-					size="icon"
-					aria-label="Copy public dashboard URL"
-					testId="public-dashboard-copy-url"
-					onClick={onCopy}
-				>
-					<Copy size={14} />
-				</Button>
-				<Button
-					variant="ghost"
-					size="icon"
-					aria-label="Open public dashboard in new tab"
-					testId="public-dashboard-open-url"
-					onClick={onOpen}
-				>
-					<ExternalLink size={14} />
-				</Button>
-			</div>
-		</div>
-	);
-}
-
-export default PublicDashboardUrl;

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardUrl/PublicDashboardUrl.module.scss

@@ -0,0 +1,69 @@
+.fieldGroup {
+	display: flex;
+	flex-direction: column;
+	gap: 8px;
+}
+
+.fieldLabel {
+	color: var(--l2-foreground);
+	font-size: 12px;
+	font-weight: 500;
+	line-height: 1;
+}
+
+.linkPlaceholder {
+	display: flex;
+	align-items: center;
+	gap: 9px;
+	height: 40px;
+	padding: 0 12px;
+	border-radius: 6px;
+	border: 1px dashed var(--l2-border);
+	background: var(--l1-background);
+	color: var(--l3-foreground);
+}
+
+.linkPlaceholderIcon {
+	flex: none;
+	color: var(--l3-foreground);
+}
+
+.linkPlaceholderText {
+	color: var(--l3-foreground);
+	font-size: 13px;
+	line-height: 1;
+}
+
+.linkField {
+	display: flex;
+	align-items: center;
+	gap: 2px;
+	height: 40px;
+	padding: 0 5px 0 12px;
+	border-radius: 6px;
+	border: 1px solid var(--l2-border);
+	background: var(--l1-background);
+
+	&:hover {
+		border-color: var(--l3-border);
+	}
+}
+
+.linkUrl {
+	flex: 1;
+	min-width: 0;
+	overflow: hidden;
+	text-overflow: ellipsis;
+	white-space: nowrap;
+	color: var(--l2-foreground);
+	font-family: var(--font-mono, 'Geist Mono'), monospace;
+	font-size: 13px;
+	line-height: 1;
+}
+
+.linkDivider {
+	width: 1px;
+	height: 20px;
+	margin: 0 4px;
+	background: var(--l2-border);
+}

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/PublicDashboardUrl/PublicDashboardUrl.tsx

@@ -0,0 +1,59 @@
+import { Copy, ExternalLink, Link2 } from '@signozhq/icons';
+import { Button } from '@signozhq/ui/button';
+import { Typography } from '@signozhq/ui/typography';
+
+import styles from './PublicDashboardUrl.module.scss';
+
+interface PublicDashboardUrlProps {
+	isPublic: boolean;
+	url: string;
+	onCopy: () => void;
+	onOpen: () => void;
+}
+
+function PublicDashboardUrl({
+	isPublic,
+	url,
+	onCopy,
+	onOpen,
+}: PublicDashboardUrlProps): JSX.Element {
+	return (
+		<div className={styles.fieldGroup}>
+			<Typography.Text className={styles.fieldLabel}>Public link</Typography.Text>
+
+			{isPublic ? (
+				<div className={styles.linkField}>
+					<Typography.Text className={styles.linkUrl}>{url}</Typography.Text>
+					<span className={styles.linkDivider} />
+					<Button
+						variant="ghost"
+						size="icon"
+						aria-label="Copy link"
+						testId="public-dashboard-copy-url"
+						onClick={onCopy}
+					>
+						<Copy size={15} />
+					</Button>
+					<Button
+						variant="ghost"
+						size="icon"
+						aria-label="Open link"
+						testId="public-dashboard-open-url"
+						onClick={onOpen}
+					>
+						<ExternalLink size={15} />
+					</Button>
+				</div>
+			) : (
+				<div className={styles.linkPlaceholder}>
+					<Link2 size={15} className={styles.linkPlaceholderIcon} />
+					<Typography.Text className={styles.linkPlaceholderText}>
+						Your shareable link will appear here once published
+					</Typography.Text>
+				</div>
+			)}
+		</div>
+	);
+}
+
+export default PublicDashboardUrl;

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/constants.ts

@@ -1,14 +0,0 @@
-export interface TimeRangePresetOption {
-	label: string;
-	value: string;
-}
-
-// Default time-range presets offered for the public dashboard viewer.
-export const TIME_RANGE_PRESETS_OPTIONS: TimeRangePresetOption[] = [
-	{ label: 'Last 5 minutes', value: '5m' },
-	{ label: 'Last 15 minutes', value: '15m' },
-	{ label: 'Last 30 minutes', value: '30m' },
-	{ label: 'Last 1 hour', value: '1h' },
-	{ label: 'Last 6 hours', value: '6h' },
-	{ label: 'Last 1 day', value: '24h' },
-];

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/index.tsx

@@ -1,10 +1,10 @@
 import type { DashboardtypesGettableDashboardV2DTO } from 'api/generated/services/sigNoz.schemas';
 
-import PublicDashboardActions from './PublicDashboardActions';
-import PublicDashboardCallout from './PublicDashboardCallout';
-import PublicDashboardSettingsForm from './PublicDashboardSettingsForm';
-import PublicDashboardStatus from './PublicDashboardStatus';
-import PublicDashboardUrl from './PublicDashboardUrl';
+import PublicDashboardActions from './PublicDashboardActions/PublicDashboardActions';
+import PublicDashboardHint from './PublicDashboardHint/PublicDashboardHint';
+import PublicDashboardSettingsForm from './PublicDashboardSettingsForm/PublicDashboardSettingsForm';
+import PublicDashboardStatus from './PublicDashboardStatus/PublicDashboardStatus';
+import PublicDashboardUrl from './PublicDashboardUrl/PublicDashboardUrl';
 import { usePublicDashboard } from './usePublicDashboard';
 import styles from './PublicDashboard.module.scss';
 
@@ -37,22 +37,27 @@ function PublicDashboardSettings({
 	const controlsDisabled = isLoading || !isAdmin;
 
 	return (
-		<div className={styles.publicDashboardCard}>
-			<PublicDashboardStatus isPublic={isPublic} />
+		<div className={styles.publishTab}>
+			<div className={styles.content}>
+				<PublicDashboardStatus isPublic={isPublic} />
 
-			<PublicDashboardSettingsForm
-				timeRangeEnabled={timeRangeEnabled}
-				defaultTimeRange={defaultTimeRange}
-				disabled={controlsDisabled}
-				onTimeRangeEnabledChange={setTimeRangeEnabled}
-				onDefaultTimeRangeChange={setDefaultTimeRange}
-			/>
+				<PublicDashboardUrl
+					isPublic={isPublic}
+					url={publicUrl}
+					onCopy={onCopyUrl}
+					onOpen={onOpenUrl}
+				/>
 
-			{isPublic && (
-				<PublicDashboardUrl url={publicUrl} onCopy={onCopyUrl} onOpen={onOpenUrl} />
-			)}
+				<PublicDashboardSettingsForm
+					timeRangeEnabled={timeRangeEnabled}
+					defaultTimeRange={defaultTimeRange}
+					disabled={controlsDisabled}
+					onTimeRangeEnabledChange={setTimeRangeEnabled}
+					onDefaultTimeRangeChange={setDefaultTimeRange}
+				/>
+			</div>
 
-			<PublicDashboardCallout />
+			<PublicDashboardHint />
 
 			<PublicDashboardActions
 				isPublic={isPublic}

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/usePublicDashboard.ts

@@ -6,7 +6,6 @@ import {
 	invalidateGetPublicDashboard,
 	useCreatePublicDashboard,
 	useDeletePublicDashboard,
-	useGetPublicDashboard,
 	useUpdatePublicDashboard,
 } from 'api/generated/services/dashboard';
 import { DEFAULT_TIME_RANGE } from 'container/TopNav/DateTimeSelectionV2/constants';
@@ -17,6 +16,8 @@ import { USER_ROLES } from 'types/roles';
 import { getAbsoluteUrl } from 'utils/basePath';
 import { openInNewTab } from 'utils/navigation';
 
+import { usePublicDashboardMeta } from './usePublicDashboardMeta';
+
 export interface UsePublicDashboardReturn {
 	isPublic: boolean;
 	isAdmin: boolean;
@@ -54,22 +55,16 @@ export function usePublicDashboard(
 	const [defaultTimeRange, setDefaultTimeRange] =
 		useState<string>(DEFAULT_TIME_RANGE);
 
+	// Read the shared public-meta cache — the GET is owned globally (toolbar), so the
+	// drawer reuses it rather than issuing its own request.
 	const {
-		data,
+		publicMeta,
+		isPublic,
 		isLoading: isLoadingMeta,
 		isFetching,
 		error,
 		refetch,
-	} = useGetPublicDashboard(
-		{ id: dashboardId },
-		{ query: { enabled: !!dashboardId, retry: false } },
-	);
-
-	// react-query retains the last successful `data` even after a refetch errors, so
-	// after unpublishing (the refetch 404s) `data` still holds the old publicPath.
-	// Gate on `!error` so the UI flips back to the private state.
-	const publicMeta = error ? undefined : data?.data;
-	const isPublic = !!publicMeta?.publicPath;
+	} = usePublicDashboardMeta(dashboardId);
 
 	// Seed form state from the server config when published.
 	useEffect(() => {
@@ -103,7 +98,7 @@ export function usePublicDashboard(
 		(message: string): void => {
 			toast.success(message);
 			void invalidateGetPublicDashboard(queryClient, { id: dashboardId });
-			void refetch();
+			refetch();
 		},
 		[queryClient, dashboardId, refetch],
 	);

frontend/src/pages/DashboardPageV2/DashboardContainer/DashboardSettings/PublicDashboard/usePublicDashboardMeta.ts

@@ -0,0 +1,65 @@
+import { useMemo } from 'react';
+import { useGetPublicDashboard } from 'api/generated/services/dashboard';
+import type { DashboardtypesGettablePublicDasbhboardDTO } from 'api/generated/services/sigNoz.schemas';
+import { useGetTenantLicense } from 'hooks/useGetTenantLicense';
+
+export interface UsePublicDashboardMetaReturn {
+	publicMeta: DashboardtypesGettablePublicDasbhboardDTO | undefined;
+	isPublic: boolean;
+	isLoading: boolean;
+	isFetching: boolean;
+	error: unknown;
+	refetch: () => void;
+}
+
+// How long a fetched result stays fresh before a natural trigger may refresh it.
+const PUBLIC_META_STALE_TIME = 5 * 60 * 1000;
+
+/**
+ * Single source of truth for a dashboard's public-sharing meta. Keyed by dashboard
+ * id via the generated query, so the GET happens once globally (the toolbar mounts it
+ * with the dashboard) and every other caller — the publish settings drawer — reads the
+ * same cache instead of issuing its own request. A mutation that invalidates
+ * getGetPublicDashboardQueryKey refreshes all consumers at once.
+ *
+ * Only fetched on cloud / enterprise tenants, where public dashboards are available.
+ */
+export function usePublicDashboardMeta(
+	dashboardId: string,
+): UsePublicDashboardMetaReturn {
+	const { isCloudUser, isEnterpriseSelfHostedUser } = useGetTenantLicense();
+	const enabled = !!dashboardId && (isCloudUser || isEnterpriseSelfHostedUser);
+
+	const { data, isLoading, isFetching, error, refetch } = useGetPublicDashboard(
+		{ id: dashboardId },
+		{
+			query: {
+				enabled,
+				retry: false,
+				// refetchOnMount: false stops opening the drawer / switching to the Publish
+				// tab from refiring the GET — it reuses the toolbar's cached result. A finite
+				// staleTime still lets it refresh naturally once the data ages, and mutations
+				// invalidate the key to refresh the published state immediately.
+				staleTime: PUBLIC_META_STALE_TIME,
+				refetchOnMount: false,
+			},
+		},
+	);
+
+	// react-query retains the last successful `data` after a refetch errors (e.g. the
+	// 404 once a dashboard is unpublished), so gate on the error to reflect the
+	// private state.
+	const publicMeta = error ? undefined : data?.data;
+
+	return useMemo(
+		() => ({
+			publicMeta,
+			isPublic: !!publicMeta?.publicPath,
+			isLoading,
+			isFetching,
+			error,
+			refetch,
+		}),
+		[publicMeta, isLoading, isFetching, error, refetch],
+	);
+}

pkg/apiserver/signozapiserver/inframonitoring.go

@@ -16,7 +16,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 			ID:                  "ListHosts",
 			Tags:                []string{"inframonitoring"},
 			Summary:             "List Hosts for Infra Monitoring",
-			Description:         "Returns a paginated list of hosts with key infrastructure metrics: CPU usage (%), memory usage (%), I/O wait (%), disk usage (%), and 15-minute load average. Each host includes its current status (active/inactive based on metrics reported in the last 10 minutes) and metadata attributes (e.g., os.type). Supports filtering via a filter expression, filtering by host status, custom groupBy to aggregate hosts by any attribute, ordering by any of the five metrics, and pagination via offset/limit. The response type is 'list' for the default host.name grouping or 'grouped_list' for custom groupBy keys. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (cpu, memory, wait, load15, diskUsage) return -1 as a sentinel when no data is available for that field.",
+			Description:         "Returns a paginated list of hosts with key infrastructure metrics: CPU usage (%), memory usage (%), I/O wait (%), disk usage (%), and 15-minute load average. Each host includes its current status (active/inactive based on metrics reported in the last 10 minutes) and metadata attributes (e.g., os.type). Supports filtering via a filter expression, filtering by host status, custom groupBy to aggregate hosts by any attribute, ordering by any of the five metrics, and pagination via offset/limit. The response type is 'list' for the default host.name grouping or 'grouped_list' for custom groupBy keys. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (cpu, memory, wait, load15, diskUsage) return -1 as a sentinel when no data is available for that field.",
 			Request:             new(inframonitoringtypes.PostableHosts),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.Hosts),
@@ -35,7 +35,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 			ID:                  "ListPods",
 			Tags:                []string{"inframonitoring"},
 			Summary:             "List Pods for Infra Monitoring",
-			Description:         "Returns a paginated list of Kubernetes pods with key metrics: CPU usage, CPU request/limit utilization, memory working set, memory request/limit utilization, current pod phase (pending/running/succeeded/failed/unknown/no_data), and pod age (ms since start time). Each pod includes metadata attributes (namespace, node, workload owner such as deployment/statefulset/daemonset/job/cronjob, cluster). Supports filtering via a filter expression, custom groupBy to aggregate pods by any attribute, ordering by any of the six metrics (cpu, cpu_request, cpu_limit, memory, memory_request, memory_limit), and pagination via offset/limit. The response type is 'list' for the default k8s.pod.uid grouping (each row is one pod with its current phase) or 'grouped_list' for custom groupBy keys (each row aggregates pods in the group with per-phase counts under podCountsByPhase: { pending, running, succeeded, failed, unknown } derived from each pod's latest phase in the window). Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (podCPU, podCPURequest, podCPULimit, podMemory, podMemoryRequest, podMemoryLimit, podAge) return -1 as a sentinel when no data is available for that field.",
+			Description:         "Returns a paginated list of Kubernetes pods with key metrics: CPU usage, CPU request/limit utilization, memory working set, memory request/limit utilization, current pod phase (pending/running/succeeded/failed/unknown/no_data), and pod age (ms since start time). Each pod includes metadata attributes (namespace, node, workload owner such as deployment/statefulset/daemonset/job/cronjob, cluster). Supports filtering via a filter expression, custom groupBy to aggregate pods by any attribute, ordering by any of the six metrics (cpu, cpu_request, cpu_limit, memory, memory_request, memory_limit), and pagination via offset/limit. The response type is 'list' for the default k8s.pod.uid grouping (each row is one pod with its current phase) or 'grouped_list' for custom groupBy keys (each row aggregates pods in the group with per-phase counts under podCountsByPhase: { pending, running, succeeded, failed, unknown } derived from each pod's latest phase in the window). Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (podCPU, podCPURequest, podCPULimit, podMemory, podMemoryRequest, podMemoryLimit, podAge) return -1 as a sentinel when no data is available for that field.",
 			Request:             new(inframonitoringtypes.PostablePods),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.Pods),
@@ -54,7 +54,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 			ID:                  "ListNodes",
 			Tags:                []string{"inframonitoring"},
 			Summary:             "List Nodes for Infra Monitoring",
-			Description:         "Returns a paginated list of Kubernetes nodes with key metrics: CPU usage, CPU allocatable, memory working set, memory allocatable, per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready in the window) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } for pods scheduled on the listed nodes). Each node includes metadata attributes (k8s.node.uid, k8s.cluster.name). The response type is 'list' for the default k8s.node.name grouping (each row is one node with its current condition string: ready / not_ready / no_data) or 'grouped_list' for custom groupBy keys (each row aggregates nodes in the group; condition stays no_data). Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (nodeCPU, nodeCPUAllocatable, nodeMemory, nodeMemoryAllocatable) return -1 as a sentinel when no data is available for that field.",
+			Description:         "Returns a paginated list of Kubernetes nodes with key metrics: CPU usage, CPU allocatable, memory working set, memory allocatable, per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready in the window) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } for pods scheduled on the listed nodes). Each node includes metadata attributes (k8s.node.uid, k8s.cluster.name). The response type is 'list' for the default k8s.node.name grouping (each row is one node with its current condition string: ready / not_ready / no_data) or 'grouped_list' for custom groupBy keys (each row aggregates nodes in the group; condition stays no_data). Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (nodeCPU, nodeCPUAllocatable, nodeMemory, nodeMemoryAllocatable) return -1 as a sentinel when no data is available for that field.",
 			Request:             new(inframonitoringtypes.PostableNodes),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.Nodes),
@@ -73,7 +73,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 			ID:                  "ListNamespaces",
 			Tags:                []string{"inframonitoring"},
 			Summary:             "List Namespaces for Infra Monitoring",
-			Description:         "Returns a paginated list of Kubernetes namespaces with key aggregated pod metrics: CPU usage and memory working set (summed across pods in the group), plus per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value in the window). Each namespace includes metadata attributes (k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.namespace.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / memory, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (namespaceCPU, namespaceMemory) return -1 as a sentinel when no data is available for that field.",
+			Description:         "Returns a paginated list of Kubernetes namespaces with key aggregated pod metrics: CPU usage and memory working set (summed across pods in the group), plus per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value in the window). Each namespace includes metadata attributes (k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.namespace.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / memory, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (namespaceCPU, namespaceMemory) return -1 as a sentinel when no data is available for that field.",
 			Request:             new(inframonitoringtypes.PostableNamespaces),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.Namespaces),
@@ -92,7 +92,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 			ID:                  "ListClusters",
 			Tags:                []string{"inframonitoring"},
 			Summary:             "List Clusters for Infra Monitoring",
-			Description:         "Returns a paginated list of Kubernetes clusters with key aggregated metrics derived by summing per-node values within the group: CPU usage, CPU allocatable, memory working set, memory allocatable. Each row also reports per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready value) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each cluster includes metadata attributes (k8s.cluster.name). The response type is 'list' for the default k8s.cluster.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates nodes and pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (clusterCPU, clusterCPUAllocatable, clusterMemory, clusterMemoryAllocatable) return -1 as a sentinel when no data is available for that field.",
+			Description:         "Returns a paginated list of Kubernetes clusters with key aggregated metrics derived by summing per-node values within the group: CPU usage, CPU allocatable, memory working set, memory allocatable. Each row also reports per-group nodeCountsByReadiness ({ ready, notReady } from each node's latest k8s.node.condition_ready value) and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each cluster includes metadata attributes (k8s.cluster.name). The response type is 'list' for the default k8s.cluster.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates nodes and pods in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_allocatable / memory / memory_allocatable, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (clusterCPU, clusterCPUAllocatable, clusterMemory, clusterMemoryAllocatable) return -1 as a sentinel when no data is available for that field.",
 			Request:             new(inframonitoringtypes.PostableClusters),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.Clusters),
@@ -111,7 +111,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 			ID:                  "ListVolumes",
 			Tags:                []string{"inframonitoring"},
 			Summary:             "List Volumes for Infra Monitoring",
-			Description:         "Returns a paginated list of Kubernetes persistent volume claims (PVCs) with key volume metrics: available bytes, capacity bytes, usage (capacity - available), inodes, free inodes, and used inodes. Each row also includes metadata attributes (k8s.persistentvolumeclaim.name, k8s.pod.uid, k8s.pod.name, k8s.namespace.name, k8s.node.name, k8s.statefulset.name, k8s.cluster.name). Supports filtering via a filter expression, custom groupBy to aggregate volumes by any attribute, ordering by any of the six metrics (available, capacity, usage, inodes, inodes_free, inodes_used), and pagination via offset/limit. The response type is 'list' for the default k8s.persistentvolumeclaim.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates volumes in the group. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (volumeAvailable, volumeCapacity, volumeUsage, volumeInodes, volumeInodesFree, volumeInodesUsed) return -1 as a sentinel when no data is available for that field.",
+			Description:         "Returns a paginated list of Kubernetes persistent volume claims (PVCs) with key volume metrics: available bytes, capacity bytes, usage (capacity - available), inodes, free inodes, and used inodes. Each row also includes metadata attributes (k8s.persistentvolumeclaim.name, k8s.pod.uid, k8s.pod.name, k8s.namespace.name, k8s.node.name, k8s.statefulset.name, k8s.cluster.name). Supports filtering via a filter expression, custom groupBy to aggregate volumes by any attribute, ordering by any of the six metrics (available, capacity, usage, inodes, inodes_free, inodes_used), and pagination via offset/limit. The response type is 'list' for the default k8s.persistentvolumeclaim.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates volumes in the group. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (volumeAvailable, volumeCapacity, volumeUsage, volumeInodes, volumeInodesFree, volumeInodesUsed) return -1 as a sentinel when no data is available for that field.",
 			Request:             new(inframonitoringtypes.PostableVolumes),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.Volumes),
@@ -130,7 +130,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 			ID:                  "ListDeployments",
 			Tags:                []string{"inframonitoring"},
 			Summary:             "List Deployments for Infra Monitoring",
-			Description:         "Returns a paginated list of Kubernetes Deployments with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the deployment, plus average CPU/memory request and limit utilization (deploymentCPURequest, deploymentCPULimit, deploymentMemoryRequest, deploymentMemoryLimit). Each row also reports the latest known desiredPods (k8s.deployment.desired) and availablePods (k8s.deployment.available) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each deployment includes metadata attributes (k8s.deployment.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.deployment.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by deployments in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / available_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (deploymentCPU, deploymentCPURequest, deploymentCPULimit, deploymentMemory, deploymentMemoryRequest, deploymentMemoryLimit, desiredPods, availablePods) return -1 as a sentinel when no data is available for that field.",
+			Description:         "Returns a paginated list of Kubernetes Deployments with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the deployment, plus average CPU/memory request and limit utilization (deploymentCPURequest, deploymentCPULimit, deploymentMemoryRequest, deploymentMemoryLimit). Each row also reports the latest known desiredPods (k8s.deployment.desired) and availablePods (k8s.deployment.available) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each deployment includes metadata attributes (k8s.deployment.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.deployment.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by deployments in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / available_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (deploymentCPU, deploymentCPURequest, deploymentCPULimit, deploymentMemory, deploymentMemoryRequest, deploymentMemoryLimit, desiredPods, availablePods) return -1 as a sentinel when no data is available for that field.",
 			Request:             new(inframonitoringtypes.PostableDeployments),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.Deployments),
@@ -149,7 +149,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 			ID:                  "ListStatefulSets",
 			Tags:                []string{"inframonitoring"},
 			Summary:             "List StatefulSets for Infra Monitoring",
-			Description:         "Returns a paginated list of Kubernetes StatefulSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the statefulset, plus average CPU/memory request and limit utilization (statefulSetCPURequest, statefulSetCPULimit, statefulSetMemoryRequest, statefulSetMemoryLimit). Each row also reports the latest known desiredPods (k8s.statefulset.desired_pods) and currentPods (k8s.statefulset.current_pods) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each statefulset includes metadata attributes (k8s.statefulset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.statefulset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by statefulsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / current_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (statefulSetCPU, statefulSetCPURequest, statefulSetCPULimit, statefulSetMemory, statefulSetMemoryRequest, statefulSetMemoryLimit, desiredPods, currentPods) return -1 as a sentinel when no data is available for that field.",
+			Description:         "Returns a paginated list of Kubernetes StatefulSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the statefulset, plus average CPU/memory request and limit utilization (statefulSetCPURequest, statefulSetCPULimit, statefulSetMemoryRequest, statefulSetMemoryLimit). Each row also reports the latest known desiredPods (k8s.statefulset.desired_pods) and currentPods (k8s.statefulset.current_pods) replica counts and per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each statefulset includes metadata attributes (k8s.statefulset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.statefulset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by statefulsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_pods / current_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (statefulSetCPU, statefulSetCPURequest, statefulSetCPULimit, statefulSetMemory, statefulSetMemoryRequest, statefulSetMemoryLimit, desiredPods, currentPods) return -1 as a sentinel when no data is available for that field.",
 			Request:             new(inframonitoringtypes.PostableStatefulSets),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.StatefulSets),
@@ -168,7 +168,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 			ID:                  "ListJobs",
 			Tags:                []string{"inframonitoring"},
 			Summary:             "List Jobs for Infra Monitoring",
-			Description:         "Returns a paginated list of Kubernetes Jobs with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the job, plus average CPU/memory request and limit utilization (jobCPURequest, jobCPULimit, jobMemoryRequest, jobMemoryLimit). Each row also reports the latest known job-level counters from kube-state-metrics: desiredSuccessfulPods (k8s.job.desired_successful_pods, the target completion count), activePods (k8s.job.active_pods), failedPods (k8s.job.failed_pods, cumulative across the lifetime of the job), and successfulPods (k8s.job.successful_pods, cumulative). It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value); note podCountsByPhase.failed (current pod-phase) is distinct from failedPods (cumulative job kube-state-metric). Each job includes metadata attributes (k8s.job.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.job.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by jobs in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_successful_pods / active_pods / failed_pods / successful_pods, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (jobCPU, jobCPURequest, jobCPULimit, jobMemory, jobMemoryRequest, jobMemoryLimit, desiredSuccessfulPods, activePods, failedPods, successfulPods) return -1 as a sentinel when no data is available for that field.",
+			Description:         "Returns a paginated list of Kubernetes Jobs with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the job, plus average CPU/memory request and limit utilization (jobCPURequest, jobCPULimit, jobMemoryRequest, jobMemoryLimit). Each row also reports the latest known job-level counters from kube-state-metrics: desiredSuccessfulPods (k8s.job.desired_successful_pods, the target completion count), activePods (k8s.job.active_pods), failedPods (k8s.job.failed_pods, cumulative across the lifetime of the job), and successfulPods (k8s.job.successful_pods, cumulative). It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value); note podCountsByPhase.failed (current pod-phase) is distinct from failedPods (cumulative job kube-state-metric). Each job includes metadata attributes (k8s.job.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.job.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by jobs in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_successful_pods / active_pods / failed_pods / successful_pods, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (jobCPU, jobCPURequest, jobCPULimit, jobMemory, jobMemoryRequest, jobMemoryLimit, desiredSuccessfulPods, activePods, failedPods, successfulPods) return -1 as a sentinel when no data is available for that field.",
 			Request:             new(inframonitoringtypes.PostableJobs),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.Jobs),
@@ -187,7 +187,7 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 			ID:                  "ListDaemonSets",
 			Tags:                []string{"inframonitoring"},
 			Summary:             "List DaemonSets for Infra Monitoring",
-			Description:         "Returns a paginated list of Kubernetes DaemonSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the daemonset, plus average CPU/memory request and limit utilization (daemonSetCPURequest, daemonSetCPULimit, daemonSetMemoryRequest, daemonSetMemoryLimit). Each row also reports the latest known node-level counters from kube-state-metrics: desiredNodes (k8s.daemonset.desired_scheduled_nodes, the number of nodes the daemonset wants to run on) and currentNodes (k8s.daemonset.current_scheduled_nodes, the number of nodes the daemonset currently runs on) — note these are node counts, not pod counts. It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each daemonset includes metadata attributes (k8s.daemonset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.daemonset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by daemonsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_nodes / current_nodes, and pagination via offset/limit. Also reports missing required metrics and whether the requested time range falls before the data retention boundary. Numeric metric fields (daemonSetCPU, daemonSetCPURequest, daemonSetCPULimit, daemonSetMemory, daemonSetMemoryRequest, daemonSetMemoryLimit, desiredNodes, currentNodes) return -1 as a sentinel when no data is available for that field.",
+			Description:         "Returns a paginated list of Kubernetes DaemonSets with key aggregated pod metrics: CPU usage and memory working set summed across pods owned by the daemonset, plus average CPU/memory request and limit utilization (daemonSetCPURequest, daemonSetCPULimit, daemonSetMemoryRequest, daemonSetMemoryLimit). Each row also reports the latest known node-level counters from kube-state-metrics: desiredNodes (k8s.daemonset.desired_scheduled_nodes, the number of nodes the daemonset wants to run on) and currentNodes (k8s.daemonset.current_scheduled_nodes, the number of nodes the daemonset currently runs on) — note these are node counts, not pod counts. It also reports per-group podCountsByPhase ({ pending, running, succeeded, failed, unknown } from each pod's latest k8s.pod.phase value). Each daemonset includes metadata attributes (k8s.daemonset.name, k8s.namespace.name, k8s.cluster.name). The response type is 'list' for the default k8s.daemonset.name grouping or 'grouped_list' for custom groupBy keys; in both modes every row aggregates pods owned by daemonsets in the group. Supports filtering via a filter expression, custom groupBy, ordering by cpu / cpu_request / cpu_limit / memory / memory_request / memory_limit / desired_nodes / current_nodes, and pagination via offset/limit. Also reports whether the requested time range falls before the data retention boundary. Numeric metric fields (daemonSetCPU, daemonSetCPURequest, daemonSetCPULimit, daemonSetMemory, daemonSetMemoryRequest, daemonSetMemoryLimit, desiredNodes, currentNodes) return -1 as a sentinel when no data is available for that field.",
 			Request:             new(inframonitoringtypes.PostableDaemonSets),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.DaemonSets),

pkg/modules/cloudintegration/config.go

@@ -22,7 +22,7 @@ func newConfig() factory.Config {
 		Agent: AgentConfig{
 			// we will maintain the latest version of cloud integration agent from here,
 			// till we automate it externally or figure out a way to validate it.
-			Version: "v0.0.12",
+			Version: "v0.0.13",
 		},
 	}
 }

pkg/modules/inframonitoring/implinframonitoring/helpers.go

@@ -413,64 +413,27 @@ func (m *module) buildFilterClause(ctx context.Context, filter *qbtypes.Filter,
 // NOTE: this method is not specific to infra monitoring — it queries attributes_metadata generically.
 // Consider moving to telemetryMetaStore when a second use case emerges.
 //
-// getMetricsExistenceAndEarliestTime checks which of the given metric names have been
-// reported. It returns a list of missing metrics (those not found or with zero count)
-// and the earliest first-reported timestamp across all present metrics.
-// When all metrics are missing, minFirstReportedUnixMilli is 0.
-// TODO(nikhilmantri0902, srikanthccv): This method was designed this way because querier errors if any of the metrics
-// in the querier list was never sent, the QueryRange call throws not found error. Modify this method, if QueryRange
-// behaviour changes towards this.
-func (m *module) getMetricsExistenceAndEarliestTime(ctx context.Context, metricNames []string) ([]string, uint64, error) {
+// getEarliestMetricTime returns the earliest first_reported_unix_milli across the
+// given metric names. It is used solely for the end-time-before-retention check.
+// When none of the metrics have ever been reported, it returns 0.
+func (m *module) getEarliestMetricTime(ctx context.Context, metricNames []string) (uint64, error) {
 	if len(metricNames) == 0 {
-		return nil, 0, nil
+		return 0, nil
 	}
 
 	sb := sqlbuilder.NewSelectBuilder()
-	sb.Select("metric_name", "count(*) AS cnt", "min(first_reported_unix_milli) AS min_first_reported")
+	sb.Select("min(first_reported_unix_milli) AS min_first_reported")
 	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName))
 	sb.Where(sb.In("metric_name", sqlbuilder.List(metricNames)))
-	sb.GroupBy("metric_name")
 
 	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
 
-	rows, err := m.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
-	if err != nil {
-		return nil, 0, err
-	}
-	defer rows.Close()
-
-	type metricInfo struct {
-		count            uint64
-		minFirstReported uint64
-	}
-	found := make(map[string]metricInfo, len(metricNames))
-
-	for rows.Next() {
-		var name string
-		var cnt, minFR uint64
-		if err := rows.Scan(&name, &cnt, &minFR); err != nil {
-			return nil, 0, err
-		}
-		found[name] = metricInfo{count: cnt, minFirstReported: minFR}
-	}
-	if err := rows.Err(); err != nil {
-		return nil, 0, err
+	var minFirstReported uint64
+	if err := m.telemetryStore.ClickhouseDB().QueryRow(ctx, query, args...).Scan(&minFirstReported); err != nil {
+		return 0, err
 	}
 
-	var missingMetrics []string
-	var globalMinFirstReported uint64
-	for _, name := range metricNames {
-		info, ok := found[name]
-		if !ok || info.count == 0 {
-			missingMetrics = append(missingMetrics, name)
-			continue
-		}
-		if globalMinFirstReported == 0 || info.minFirstReported < globalMinFirstReported {
-			globalMinFirstReported = info.minFirstReported
-		}
-	}
-
-	return missingMetrics, globalMinFirstReported, nil
+	return minFirstReported, nil
 }
 
 // getMetadata fetches the latest values of additionalCols for each unique combination of groupBy keys,

pkg/modules/inframonitoring/implinframonitoring/helpers_test.go

@@ -304,7 +304,7 @@ func TestCompositeKeyFromLabels(t *testing.T) {
 			name: "daemonset and namespace group-by",
 			labels: map[string]string{
 				"k8s.daemonset.name": "web-1",
-				"k8s.namespace.name":  "ns-x",
+				"k8s.namespace.name": "ns-x",
 			},
 			groupBy:  []qbtypes.GroupByKey{daemonSetNameGroupByKey, namespaceNameGroupByKey},
 			expected: "web-1\x00ns-x",
@@ -330,6 +330,47 @@ func TestCompositeKeyFromLabels(t *testing.T) {
 			groupBy:  []qbtypes.GroupByKey{deploymentNameGroupByKey, namespaceNameGroupByKey, clusterNameGroupByKey},
 			expected: "web-1\x00ns-x\x00",
 		},
+		{
+			// volumes default group identity: (pvc, namespace, cluster).
+			name: "pvc, namespace and cluster group-by",
+			labels: map[string]string{
+				"k8s.persistentvolumeclaim.name": "data-pg-0",
+				"k8s.namespace.name":             "ns-x",
+				"k8s.cluster.name":               "cluster-a",
+			},
+			groupBy:  []qbtypes.GroupByKey{pvcNameGroupByKey, namespaceNameGroupByKey, clusterNameGroupByKey},
+			expected: "data-pg-0\x00ns-x\x00cluster-a",
+		},
+		{
+			// absent cluster label on a PVC -> empty trailing segment.
+			name: "pvc missing cluster label yields empty trailing segment",
+			labels: map[string]string{
+				"k8s.persistentvolumeclaim.name": "data-pg-0",
+				"k8s.namespace.name":             "ns-x",
+			},
+			groupBy:  []qbtypes.GroupByKey{pvcNameGroupByKey, namespaceNameGroupByKey, clusterNameGroupByKey},
+			expected: "data-pg-0\x00ns-x\x00",
+		},
+		{
+			// namespaces default group identity: (namespace, cluster) — namespaces are
+			// cluster-scoped, so cluster is the only cross-cluster disambiguator.
+			name: "namespace and cluster group-by",
+			labels: map[string]string{
+				"k8s.namespace.name": "ns-x",
+				"k8s.cluster.name":   "cluster-a",
+			},
+			groupBy:  []qbtypes.GroupByKey{namespaceNameGroupByKey, clusterNameGroupByKey},
+			expected: "ns-x\x00cluster-a",
+		},
+		{
+			// absent cluster label on a namespace -> empty trailing segment.
+			name: "namespace missing cluster label yields empty trailing segment",
+			labels: map[string]string{
+				"k8s.namespace.name": "ns-x",
+			},
+			groupBy:  []qbtypes.GroupByKey{namespaceNameGroupByKey, clusterNameGroupByKey},
+			expected: "ns-x\x00",
+		},
 	}
 
 	for _, tt := range tests {

pkg/modules/inframonitoring/implinframonitoring/module.go

@@ -78,26 +78,18 @@ func (m *module) ListHosts(ctx context.Context, orgID valuer.UUID, req *inframon
 		resp.Type = inframonitoringtypes.ResponseTypeGroupedList
 	}
 
-	// 1. Check which required metrics exist and get earliest retention time.
-	// If any required metric is missing, return early with the list of missing metrics.
-	// 2. If metrics exist but req.End is before the earliest reported time, return early with endTimeBeforeRetention=true.
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, hostsTableMetricNamesList)
+	// If req.End is before the earliest reported time for these metrics, return early
+	// with endTimeBeforeRetention=true.
+	minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, hostsTableMetricNamesList)
 	if err != nil {
 		return nil, err
 	}
-	if len(missingMetrics) > 0 {
-		resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
-		resp.Records = []inframonitoringtypes.HostRecord{}
-		resp.Total = 0
-		return resp, nil
-	}
 	if req.End < int64(minFirstReportedUnixMilli) {
 		resp.EndTimeBeforeRetention = true
 		resp.Records = []inframonitoringtypes.HostRecord{}
 		resp.Total = 0
 		return resp, nil
 	}
-	resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
 
 	// TOD(nikhilmantri0902): replace this separate ClickHouse query with a sub-query inside the main query builder query
 	// once QB supports sub-queries.
@@ -191,23 +183,16 @@ func (m *module) ListPods(ctx context.Context, orgID valuer.UUID, req *inframoni
 		resp.Type = inframonitoringtypes.ResponseTypeGroupedList
 	}
 
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, podsTableMetricNamesList)
+	minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, podsTableMetricNamesList)
 	if err != nil {
 		return nil, err
 	}
-	if len(missingMetrics) > 0 {
-		resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
-		resp.Records = []inframonitoringtypes.PodRecord{}
-		resp.Total = 0
-		return resp, nil
-	}
 	if req.End < int64(minFirstReportedUnixMilli) {
 		resp.EndTimeBeforeRetention = true
 		resp.Records = []inframonitoringtypes.PodRecord{}
 		resp.Total = 0
 		return resp, nil
 	}
-	resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
 
 	metadataMap, err := m.getPodsTableMetadata(ctx, req)
 	if err != nil {
@@ -276,23 +261,16 @@ func (m *module) ListNodes(ctx context.Context, orgID valuer.UUID, req *inframon
 		resp.Type = inframonitoringtypes.ResponseTypeGroupedList
 	}
 
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, nodesTableMetricNamesList)
+	minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, nodesTableMetricNamesList)
 	if err != nil {
 		return nil, err
 	}
-	if len(missingMetrics) > 0 {
-		resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
-		resp.Records = []inframonitoringtypes.NodeRecord{}
-		resp.Total = 0
-		return resp, nil
-	}
 	if req.End < int64(minFirstReportedUnixMilli) {
 		resp.EndTimeBeforeRetention = true
 		resp.Records = []inframonitoringtypes.NodeRecord{}
 		resp.Total = 0
 		return resp, nil
 	}
-	resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
 
 	metadataMap, err := m.getNodesTableMetadata(ctx, req)
 	if err != nil {
@@ -360,29 +338,22 @@ func (m *module) ListNamespaces(ctx context.Context, orgID valuer.UUID, req *inf
 	}
 
 	if len(req.GroupBy) == 0 {
-		req.GroupBy = []qbtypes.GroupByKey{namespaceNameGroupByKey}
+		req.GroupBy = []qbtypes.GroupByKey{namespaceNameGroupByKey, clusterNameGroupByKey}
 		resp.Type = inframonitoringtypes.ResponseTypeList
 	} else {
 		resp.Type = inframonitoringtypes.ResponseTypeGroupedList
 	}
 
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, namespacesTableMetricNamesList)
+	minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, namespacesTableMetricNamesList)
 	if err != nil {
 		return nil, err
 	}
-	if len(missingMetrics) > 0 {
-		resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
-		resp.Records = []inframonitoringtypes.NamespaceRecord{}
-		resp.Total = 0
-		return resp, nil
-	}
 	if req.End < int64(minFirstReportedUnixMilli) {
 		resp.EndTimeBeforeRetention = true
 		resp.Records = []inframonitoringtypes.NamespaceRecord{}
 		resp.Total = 0
 		return resp, nil
 	}
-	resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
 
 	metadataMap, err := m.getNamespacesTableMetadata(ctx, req)
 	if err != nil {
@@ -450,23 +421,16 @@ func (m *module) ListClusters(ctx context.Context, orgID valuer.UUID, req *infra
 		resp.Type = inframonitoringtypes.ResponseTypeGroupedList
 	}
 
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, clustersTableMetricNamesList)
+	minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, clustersTableMetricNamesList)
 	if err != nil {
 		return nil, err
 	}
-	if len(missingMetrics) > 0 {
-		resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
-		resp.Records = []inframonitoringtypes.ClusterRecord{}
-		resp.Total = 0
-		return resp, nil
-	}
 	if req.End < int64(minFirstReportedUnixMilli) {
 		resp.EndTimeBeforeRetention = true
 		resp.Records = []inframonitoringtypes.ClusterRecord{}
 		resp.Total = 0
 		return resp, nil
 	}
-	resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
 
 	metadataMap, err := m.getClustersTableMetadata(ctx, req)
 	if err != nil {
@@ -535,7 +499,7 @@ func (m *module) ListVolumes(ctx context.Context, orgID valuer.UUID, req *infram
 	}
 
 	if len(req.GroupBy) == 0 {
-		req.GroupBy = []qbtypes.GroupByKey{pvcNameGroupByKey}
+		req.GroupBy = []qbtypes.GroupByKey{pvcNameGroupByKey, namespaceNameGroupByKey, clusterNameGroupByKey}
 		resp.Type = inframonitoringtypes.ResponseTypeList
 	} else {
 		resp.Type = inframonitoringtypes.ResponseTypeGroupedList
@@ -547,23 +511,16 @@ func (m *module) ListVolumes(ctx context.Context, orgID valuer.UUID, req *infram
 	}
 	req.Filter.Expression = mergeFilterExpressions(volumesBaseFilterExpr, req.Filter.Expression)
 
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, volumesTableMetricNamesList)
+	minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, volumesTableMetricNamesList)
 	if err != nil {
 		return nil, err
 	}
-	if len(missingMetrics) > 0 {
-		resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
-		resp.Records = []inframonitoringtypes.VolumeRecord{}
-		resp.Total = 0
-		return resp, nil
-	}
 	if req.End < int64(minFirstReportedUnixMilli) {
 		resp.EndTimeBeforeRetention = true
 		resp.Records = []inframonitoringtypes.VolumeRecord{}
 		resp.Total = 0
 		return resp, nil
 	}
-	resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
 
 	metadataMap, err := m.getVolumesTableMetadata(ctx, req)
 	if err != nil {
@@ -632,23 +589,16 @@ func (m *module) ListDeployments(ctx context.Context, orgID valuer.UUID, req *in
 	}
 	req.Filter.Expression = mergeFilterExpressions(deploymentsBaseFilterExpr, req.Filter.Expression)
 
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, deploymentsTableMetricNamesList)
+	minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, deploymentsTableMetricNamesList)
 	if err != nil {
 		return nil, err
 	}
-	if len(missingMetrics) > 0 {
-		resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
-		resp.Records = []inframonitoringtypes.DeploymentRecord{}
-		resp.Total = 0
-		return resp, nil
-	}
 	if req.End < int64(minFirstReportedUnixMilli) {
 		resp.EndTimeBeforeRetention = true
 		resp.Records = []inframonitoringtypes.DeploymentRecord{}
 		resp.Total = 0
 		return resp, nil
 	}
-	resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
 
 	metadataMap, err := m.getDeploymentsTableMetadata(ctx, req)
 	if err != nil {
@@ -722,23 +672,16 @@ func (m *module) ListStatefulSets(ctx context.Context, orgID valuer.UUID, req *i
 	}
 	req.Filter.Expression = mergeFilterExpressions(statefulSetsBaseFilterExpr, req.Filter.Expression)
 
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, statefulSetsTableMetricNamesList)
+	minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, statefulSetsTableMetricNamesList)
 	if err != nil {
 		return nil, err
 	}
-	if len(missingMetrics) > 0 {
-		resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
-		resp.Records = []inframonitoringtypes.StatefulSetRecord{}
-		resp.Total = 0
-		return resp, nil
-	}
 	if req.End < int64(minFirstReportedUnixMilli) {
 		resp.EndTimeBeforeRetention = true
 		resp.Records = []inframonitoringtypes.StatefulSetRecord{}
 		resp.Total = 0
 		return resp, nil
 	}
-	resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
 
 	metadataMap, err := m.getStatefulSetsTableMetadata(ctx, req)
 	if err != nil {
@@ -814,23 +757,16 @@ func (m *module) ListJobs(ctx context.Context, orgID valuer.UUID, req *inframoni
 	}
 	req.Filter.Expression = mergeFilterExpressions(jobsBaseFilterExpr, req.Filter.Expression)
 
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, jobsTableMetricNamesList)
+	minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, jobsTableMetricNamesList)
 	if err != nil {
 		return nil, err
 	}
-	if len(missingMetrics) > 0 {
-		resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
-		resp.Records = []inframonitoringtypes.JobRecord{}
-		resp.Total = 0
-		return resp, nil
-	}
 	if req.End < int64(minFirstReportedUnixMilli) {
 		resp.EndTimeBeforeRetention = true
 		resp.Records = []inframonitoringtypes.JobRecord{}
 		resp.Total = 0
 		return resp, nil
 	}
-	resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
 
 	metadataMap, err := m.getJobsTableMetadata(ctx, req)
 	if err != nil {
@@ -906,23 +842,16 @@ func (m *module) ListDaemonSets(ctx context.Context, orgID valuer.UUID, req *inf
 	}
 	req.Filter.Expression = mergeFilterExpressions(daemonSetsBaseFilterExpr, req.Filter.Expression)
 
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(ctx, daemonSetsTableMetricNamesList)
+	minFirstReportedUnixMilli, err := m.getEarliestMetricTime(ctx, daemonSetsTableMetricNamesList)
 	if err != nil {
 		return nil, err
 	}
-	if len(missingMetrics) > 0 {
-		resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: missingMetrics}
-		resp.Records = []inframonitoringtypes.DaemonSetRecord{}
-		resp.Total = 0
-		return resp, nil
-	}
 	if req.End < int64(minFirstReportedUnixMilli) {
 		resp.EndTimeBeforeRetention = true
 		resp.Records = []inframonitoringtypes.DaemonSetRecord{}
 		resp.Total = 0
 		return resp, nil
 	}
-	resp.RequiredMetricsCheck = inframonitoringtypes.RequiredMetricsCheck{MissingMetrics: []string{}}
 
 	metadataMap, err := m.getDaemonSetsTableMetadata(ctx, req)
 	if err != nil {

pkg/querier/querier.go

@@ -119,11 +119,7 @@ func (q *querier) QueryRange(ctx context.Context, orgID valuer.UUID, req *qbtype
 	queries := make(map[string]qbtypes.Query)
 	steps := make(map[string]qbtypes.Step)
 
-	// Resolve metric metadata once per request: patches each metric-aggregation
-	// query's spec in place, returns the queries whose every aggregation was
-	// missing (used for preseeded empty results), and any dormant-metric
-	// warning string. NotFound errors for never-seen metrics are propagated.
-	missingMetricQueries, dormantMetricsWarningMsg, err := q.resolveMetricMetadata(ctx, req.CompositeQuery.Queries, req.Start, req.End)
+	missingMetricQueries, metricWarnings, err := q.resolveMetricMetadata(ctx, req.CompositeQuery.Queries, req.Start, req.End)
 	if err != nil {
 		return nil, err
 	}
@@ -240,13 +236,15 @@ func (q *querier) QueryRange(ctx context.Context, orgID valuer.UUID, req *qbtype
 				}
 			}
 		}
-		if dormantMetricsWarningMsg != "" {
+		if len(metricWarnings) > 0 {
 			if qbResp.Warning == nil {
 				qbResp.Warning = &qbtypes.QueryWarnData{}
 			}
-			qbResp.Warning.Warnings = append(qbResp.Warning.Warnings, qbtypes.QueryWarnDataAdditional{
-				Message: dormantMetricsWarningMsg,
-			})
+			for _, w := range metricWarnings {
+				qbResp.Warning.Warnings = append(qbResp.Warning.Warnings, qbtypes.QueryWarnDataAdditional{
+					Message: w,
+				})
+			}
 		}
 	}
 	return qbResp, qbErr
@@ -302,12 +300,11 @@ func (q *querier) populateQBEvent(event *qbtypes.QBEvent, queries []qbtypes.Quer
 //   - missingMetricQueries: names of queries whose every aggregation was
 //     missing. Used downstream to preseed empty result placeholders so the
 //     response still has an entry per requested query name.
-//   - dormantWarning: a human-readable warning describing metrics that exist in
-//     the store but produced no data within the query window. Empty when no
-//     such metrics are present.
-//   - err: NotFound when one or more referenced metrics have never been seen,
-//     or Internal when a metadata fetch fails.
-func (q *querier) resolveMetricMetadata(ctx context.Context, queries []qbtypes.QueryEnvelope, start, end uint64) (missingMetricQueries []string, dormantWarning string, err error) {
+//   - metricWarnings: human-readable warnings for metrics that could not be
+//     resolved: never-seen metrics and dormant metrics (seen but no data in
+//     the query window).
+//   - err: Internal when a metadata fetch fails.
+func (q *querier) resolveMetricMetadata(ctx context.Context, queries []qbtypes.QueryEnvelope, start, end uint64) (missingMetricQueries []string, metricWarnings []string, err error) {
 	metricNames := make([]string, 0)
 	for idx := range queries {
 		if queries[idx].Type != qbtypes.QueryTypeBuilder {
@@ -325,13 +322,13 @@ func (q *querier) resolveMetricMetadata(ctx context.Context, queries []qbtypes.Q
 	}
 
 	if len(metricNames) == 0 {
-		return nil, "", nil
+		return nil, nil, nil
 	}
 
 	metricTemporality, metricTypes, err := q.metadataStore.FetchTemporalityAndTypeMulti(ctx, start, end, metricNames...)
 	if err != nil {
 		q.logger.WarnContext(ctx, "failed to fetch metric temporality", errors.Attr(err), slog.Any("metrics", metricNames))
-		return nil, "", errors.NewInternalf(errors.CodeInternal, "failed to fetch metrics temporality")
+		return nil, nil, errors.NewInternalf(errors.CodeInternal, "failed to fetch metrics temporality")
 	}
 	q.logger.DebugContext(ctx, "fetched metric temporalities and types", slog.Any("metric_temporality", metricTemporality), slog.Any("metric_types", metricTypes))
 
@@ -363,7 +360,7 @@ func (q *querier) resolveMetricMetadata(ctx context.Context, queries []qbtypes.Q
 			}
 			// Type is resolved now; validate aggregation compatibility against it.
 			if err := spec.Aggregations[i].ValidateForType(); err != nil {
-				return nil, "", err
+				return nil, nil, err
 			}
 			presentAggregations = append(presentAggregations, spec.Aggregations[i])
 		}
@@ -376,7 +373,7 @@ func (q *querier) resolveMetricMetadata(ctx context.Context, queries []qbtypes.Q
 	}
 
 	if len(missingMetrics) == 0 {
-		return missingMetricQueries, "", nil
+		return missingMetricQueries, nil, nil
 	}
 
 	isInternalMetric := func(n string) bool { return strings.HasPrefix(n, "signoz.") || strings.HasPrefix(n, "signoz_") }
@@ -387,29 +384,33 @@ func (q *querier) resolveMetricMetadata(ctx context.Context, queries []qbtypes.Q
 		}
 	}
 	if len(externalMissingMetrics) == 0 {
-		// this means all missing metrics are internal, and since internal metrics
-		// aren't user-controlled, skip errors/warnings for them since users can't act on them
-		return missingMetricQueries, "", nil
+		return missingMetricQueries, nil, nil
 	}
 
-	// Classify each missing metric: never-seen → NotFound error; seen-but-no-
-	// data-in-window → dormant warning.
+	// Classify each missing metric: never-seen -> warning with empty result;
+	// seen-but-no-data-in-window -> dormant warning.
 	lastSeenInfo, _ := q.metadataStore.FetchLastSeenInfoMulti(ctx, externalMissingMetrics...)
-	nonExistentMetrics := []string{}
+	var nonExistentMetrics []string
+	var dormantMetrics []string
 	for _, name := range externalMissingMetrics {
 		if ts, ok := lastSeenInfo[name]; ok && ts > 0 {
+			dormantMetrics = append(dormantMetrics, name)
 			continue
 		}
 		nonExistentMetrics = append(nonExistentMetrics, name)
 	}
+
+	var warnings []string
+
+	// Never-seen metrics: the query already gets a preseeded empty result
+	// via the aggregation-dropping path above; we just attach a warning.
 	if len(nonExistentMetrics) == 1 {
-		return nil, "", errors.NewNotFoundf(errors.CodeNotFound, "could not find the metric %s", nonExistentMetrics[0])
-	}
-	if len(nonExistentMetrics) > 1 {
-		return nil, "", errors.NewNotFoundf(errors.CodeNotFound, "the following metrics were not found: %s", strings.Join(nonExistentMetrics, ", "))
+		warnings = append(warnings, fmt.Sprintf("metric %s has never been received. Check the metric name and instrumentation", nonExistentMetrics[0]))
+	} else if len(nonExistentMetrics) > 1 {
+		warnings = append(warnings, fmt.Sprintf("the following metrics have never been received. Check the metric names and instrumentation: %s", strings.Join(nonExistentMetrics, ", ")))
 	}
 
-	// All missing metrics are dormant — assemble the warning string.
+	// Dormant metrics: seen before but no data in the query window.
 	lastSeenStr := func(name string) string {
 		if ts, ok := lastSeenInfo[name]; ok && ts > 0 {
 			ago := humanize.RelTime(time.UnixMilli(ts), time.Now(), "ago", "from now")
@@ -417,16 +418,16 @@ func (q *querier) resolveMetricMetadata(ctx context.Context, queries []qbtypes.Q
 		}
 		return name
 	}
-	if len(externalMissingMetrics) == 1 {
-		dormantWarning = fmt.Sprintf("no data found for the metric %s in the query time range", lastSeenStr(missingMetrics[0]))
-	} else {
-		parts := make([]string, len(externalMissingMetrics))
-		for i, m := range externalMissingMetrics {
+	if len(dormantMetrics) == 1 {
+		warnings = append(warnings, fmt.Sprintf("no data found for the metric %s in the query time range", lastSeenStr(dormantMetrics[0])))
+	} else if len(dormantMetrics) > 1 {
+		parts := make([]string, len(dormantMetrics))
+		for i, m := range dormantMetrics {
 			parts[i] = lastSeenStr(m)
 		}
-		dormantWarning = fmt.Sprintf("no data found for the following metrics in the query time range: %s", strings.Join(parts, ", "))
+		warnings = append(warnings, fmt.Sprintf("no data found for the following metrics in the query time range: %s", strings.Join(parts, ", ")))
 	}
-	return missingMetricQueries, dormantWarning, nil
+	return missingMetricQueries, warnings, nil
 }
 
 func (q *querier) QueryRawStream(ctx context.Context, orgID valuer.UUID, req *qbtypes.QueryRangeRequest, client *qbtypes.RawStream) {

pkg/querier/querier_test.go

@@ -37,7 +37,7 @@ func (m *mockMetricStmtBuilder) Build(_ context.Context, _, _ uint64, _ qbtypes.
 
 func TestQueryRange_MetricTypeMissing(t *testing.T) {
 	// When a metric has UnspecifiedType and is not found in the metadata store,
-	// the querier should return a not-found error, even if the request provides a temporality
+	// the querier should return an empty result with a warning instead of an error.
 	providerSettings := instrumentationtest.New().ToProviderSettings()
 	metadataStore := telemetrytypestest.NewMockMetadataStore()
 
@@ -80,9 +80,14 @@ func TestQueryRange_MetricTypeMissing(t *testing.T) {
 		},
 	}
 
-	_, err := q.QueryRange(context.Background(), valuer.GenerateUUID(), req)
-	require.Error(t, err)
-	assert.Contains(t, err.Error(), "could not find the metric unknown_metric")
+	resp, err := q.QueryRange(context.Background(), valuer.GenerateUUID(), req)
+	require.NoError(t, err)
+	require.NotNil(t, resp)
+	require.NotNil(t, resp.Warning)
+
+	require.Len(t, resp.Warning.Warnings, 1)
+	assert.Contains(t, resp.Warning.Warnings[0].Message, "unknown_metric")
+	assert.Contains(t, resp.Warning.Warnings[0].Message, "has never been received")
 }
 
 func TestQueryRange_MetricTypeFromStore(t *testing.T) {

pkg/telemetrymetrics/statement_builder.go

@@ -101,9 +101,29 @@ func (b *MetricQueryStatementBuilder) Build(
 		return nil, err
 	}
 
+	var pairFallbackWarnings []string
+	for _, sel := range keySelectors {
+		if _, ok := keys[sel.Name]; !ok {
+			keys[sel.Name] = []*telemetrytypes.TelemetryFieldKey{{
+				Name:          sel.Name,
+				FieldContext:  telemetrytypes.FieldContextAttribute,
+				FieldDataType: telemetrytypes.FieldDataTypeString,
+				Signal:        telemetrytypes.SignalMetrics,
+			}}
+			pairFallbackWarnings = append(pairFallbackWarnings,
+				fmt.Sprintf("key `%s` not found on metric %s", sel.Name, query.Aggregations[0].MetricName),
+			)
+		}
+	}
+
 	start, end = querybuilder.AdjustedMetricTimeRange(start, end, uint64(query.StepInterval.Seconds()), query)
 
-	return b.buildPipelineStatement(ctx, start, end, query, keys, variables)
+	stmt, err := b.buildPipelineStatement(ctx, start, end, query, keys, variables)
+	if err != nil {
+		return nil, err
+	}
+	stmt.Warnings = append(stmt.Warnings, pairFallbackWarnings...)
+	return stmt, nil
 }
 
 func (b *MetricQueryStatementBuilder) buildPipelineStatement(

pkg/telemetrymetrics/stmt_builder_test.go

@@ -217,6 +217,39 @@ func TestStatementBuilder(t *testing.T) {
 			},
 			expectedErr: nil,
 		},
+		{
+			name:        "test_missing_key_falls_back_to_labels",
+			requestType: qbtypes.RequestTypeTimeSeries,
+			query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
+				Signal:       telemetrytypes.SignalMetrics,
+				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
+				Aggregations: []qbtypes.MetricAggregation{
+					{
+						MetricName:       "signoz_calls_total",
+						Type:             metrictypes.SumType,
+						Temporality:      metrictypes.Cumulative,
+						TimeAggregation:  metrictypes.TimeAggregationRate,
+						SpaceAggregation: metrictypes.SpaceAggregationSum,
+					},
+				},
+				Filter: &qbtypes.Filter{
+					Expression: "k8s.statefulset.name = 'my-statefulset'",
+				},
+				GroupBy: []qbtypes.GroupByKey{
+					{
+						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
+							Name: "k8s.statefulset.name",
+						},
+					},
+				},
+			},
+			expected: qbtypes.Statement{
+				Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `k8s.statefulset.name`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `k8s.statefulset.name`, max(value) AS per_series_value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'k8s.statefulset.name') AS `k8s.statefulset.name` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND JSONExtractString(labels, 'k8s.statefulset.name') = ? GROUP BY fingerprint, `k8s.statefulset.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `k8s.statefulset.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `k8s.statefulset.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `k8s.statefulset.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `k8s.statefulset.name`, ts",
+				Args:     []any{"signoz_calls_total", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "my-statefulset", "signoz_calls_total", uint64(1747947360000), uint64(1747983420000), 0},
+				Warnings: []string{"key `k8s.statefulset.name` not found on metric signoz_calls_total"},
+			},
+			expectedErr: nil,
+		},
 	}
 
 	fm := NewFieldMapper()

pkg/types/inframonitoringtypes/clusters.go

@@ -12,7 +12,6 @@ type Clusters struct {
 	Type                   ResponseType           `json:"type" required:"true"`
 	Records                []ClusterRecord        `json:"records" required:"true" nullable:"false"`
 	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
 	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }

pkg/types/inframonitoringtypes/daemonsets.go

@@ -12,7 +12,6 @@ type DaemonSets struct {
 	Type                   ResponseType           `json:"type" required:"true"`
 	Records                []DaemonSetRecord      `json:"records" required:"true" nullable:"false"`
 	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
 	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }

pkg/types/inframonitoringtypes/deployments.go

@@ -12,7 +12,6 @@ type Deployments struct {
 	Type                   ResponseType           `json:"type" required:"true"`
 	Records                []DeploymentRecord     `json:"records" required:"true" nullable:"false"`
 	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
 	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }

pkg/types/inframonitoringtypes/hosts.go

@@ -12,7 +12,6 @@ type Hosts struct {
 	Type                   ResponseType           `json:"type" required:"true"`
 	Records                []HostRecord           `json:"records" required:"true" nullable:"false"`
 	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
 	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }
@@ -30,10 +29,6 @@ type HostRecord struct {
 	Meta              map[string]string `json:"meta" required:"true"`
 }
 
-type RequiredMetricsCheck struct {
-	MissingMetrics []string `json:"missingMetrics" required:"true"`
-}
-
 type PostableHosts struct {
 	Start   int64                `json:"start" required:"true"`
 	End     int64                `json:"end" required:"true"`

pkg/types/inframonitoringtypes/jobs.go

@@ -12,7 +12,6 @@ type Jobs struct {
 	Type                   ResponseType           `json:"type" required:"true"`
 	Records                []JobRecord            `json:"records" required:"true" nullable:"false"`
 	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
 	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }

pkg/types/inframonitoringtypes/namespaces.go

@@ -12,7 +12,6 @@ type Namespaces struct {
 	Type                   ResponseType           `json:"type" required:"true"`
 	Records                []NamespaceRecord      `json:"records" required:"true" nullable:"false"`
 	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
 	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }

pkg/types/inframonitoringtypes/nodes.go

@@ -12,7 +12,6 @@ type Nodes struct {
 	Type                   ResponseType           `json:"type" required:"true"`
 	Records                []NodeRecord           `json:"records" required:"true" nullable:"false"`
 	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
 	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }

pkg/types/inframonitoringtypes/pods.go

@@ -12,7 +12,6 @@ type Pods struct {
 	Type                   ResponseType           `json:"type" required:"true"`
 	Records                []PodRecord            `json:"records" required:"true" nullable:"false"`
 	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
 	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }

pkg/types/inframonitoringtypes/statefulsets.go

@@ -12,7 +12,6 @@ type StatefulSets struct {
 	Type                   ResponseType           `json:"type" required:"true"`
 	Records                []StatefulSetRecord    `json:"records" required:"true" nullable:"false"`
 	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
 	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }

pkg/types/inframonitoringtypes/volumes.go

@@ -12,7 +12,6 @@ type Volumes struct {
 	Type                   ResponseType           `json:"type" required:"true"`
 	Records                []VolumeRecord         `json:"records" required:"true" nullable:"false"`
 	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
 	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }

pkg/types/ruletypes/api_params.go

@@ -338,7 +338,6 @@ func isValidLabelValue(v string) bool {
 // validate runs during UnmarshalJSON (read + write path).
 // Preserves the original pre-existing checks only so that stored rules
 // continue to load without errors.
-// TODO(srikanthccv): remove this once v1 is deprecated and removed.
 func (r *PostableRule) validate() error {
 	var errs []error
 
@@ -367,13 +366,9 @@ func (r *PostableRule) validate() error {
 
 	errs = append(errs, testTemplateParsing(r)...)
 
-	if len(errs) > 0 {
-		messages := make([]string, len(errs))
-		for i, e := range errs {
-			messages[i] = e.Error()
-		}
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "alert rule definition is not valid").
-			WithAdditional(messages...)
+	joined := errors.Join(errs...)
+	if joined != nil {
+		return errors.WrapInvalidInputf(joined, errors.CodeInvalidInput, "validation failed")
 	}
 	return nil
 }
@@ -471,13 +466,9 @@ func (r *PostableRule) Validate() error {
 
 	errs = append(errs, testTemplateParsing(r)...)
 
-	if len(errs) > 0 {
-		messages := make([]string, len(errs))
-		for i, e := range errs {
-			messages[i] = e.Error()
-		}
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "alert rule is not valid").
-			WithAdditional(messages...)
+	joined := errors.Join(errs...)
+	if joined != nil {
+		return errors.WrapInvalidInputf(joined, errors.CodeInvalidInput, "validation failed")
 	}
 	return nil
 }

pkg/types/ruletypes/validate_test.go

@@ -4,23 +4,8 @@ import (
 	"encoding/json"
 	"strings"
 	"testing"
-
-	"github.com/SigNoz/signoz/pkg/errors"
 )
 
-func errorContains(err error, substr string) bool {
-	j := errors.AsJSON(err)
-	if strings.Contains(j.Message, substr) {
-		return true
-	}
-	for _, e := range j.Errors {
-		if strings.Contains(e.Message, substr) {
-			return true
-		}
-	}
-	return false
-}
-
 // validV1Builder returns a minimal valid v1 builder rule JSON.
 func validV1Builder() string {
 	return `{
@@ -509,7 +494,7 @@ func TestValidate_PostableRule_Common(t *testing.T) {
 			if tt.wantErr {
 				if err == nil {
 					t.Errorf("expected error containing %q, got nil", tt.errSubstr)
-				} else if tt.errSubstr != "" && !errorContains(err, tt.errSubstr) {
+				} else if tt.errSubstr != "" && !strings.Contains(err.Error(), tt.errSubstr) {
 					t.Errorf("expected error containing %q, got: %v", tt.errSubstr, err)
 				}
 			} else {
@@ -702,7 +687,7 @@ func TestValidate_V1_ConditionFields(t *testing.T) {
 			if tt.wantErr {
 				if validateErr == nil {
 					t.Errorf("expected Validate() error containing %q, got nil", tt.errSubstr)
-				} else if tt.errSubstr != "" && !errorContains(validateErr, tt.errSubstr) {
+				} else if tt.errSubstr != "" && !strings.Contains(validateErr.Error(), tt.errSubstr) {
 					t.Errorf("expected error containing %q, got: %v", tt.errSubstr, validateErr)
 				}
 			} else {
@@ -1044,7 +1029,7 @@ func TestValidate_V2Alpha1(t *testing.T) {
 			if tt.wantErr {
 				if err == nil {
 					t.Errorf("expected error containing %q, got nil", tt.errSubstr)
-				} else if tt.errSubstr != "" && !errorContains(err, tt.errSubstr) {
+				} else if tt.errSubstr != "" && !strings.Contains(err.Error(), tt.errSubstr) {
 					t.Errorf("expected error containing %q, got: %v", tt.errSubstr, err)
 				}
 			} else {
@@ -1352,7 +1337,7 @@ func TestValidate_MultipleErrors(t *testing.T) {
 			t.Fatal("expected unmarshal error for wrong version")
 		}
 		// The error should mention version
-		if !errorContains(err, "version") {
+		if !strings.Contains(err.Error(), "version") {
 			t.Errorf("expected error to mention version, got: %v", err)
 		}
 	})
@@ -1370,9 +1355,10 @@ func TestValidate_MultipleErrors(t *testing.T) {
 		if validateErr == nil {
 			t.Fatal("expected Validate() error")
 		}
+		errStr := validateErr.Error()
 		// Should contain errors for thresholds, evaluation, notificationSettings
 		for _, substr := range []string{"evaluation", "notificationSettings"} {
-			if !errorContains(validateErr, substr) {
+			if !strings.Contains(errStr, substr) {
 				t.Errorf("expected error to mention %q, got: %v", substr, validateErr)
 			}
 		}
@@ -1483,7 +1469,7 @@ func TestValidate_V2Alpha1_CumulativeEvaluation(t *testing.T) {
 			if tt.wantErr {
 				if err == nil {
 					t.Errorf("expected error containing %q, got nil", tt.errSubstr)
-				} else if !errorContains(err, tt.errSubstr) {
+				} else if !strings.Contains(err.Error(), tt.errSubstr) {
 					t.Errorf("expected error containing %q, got: %v", tt.errSubstr, err)
 				}
 			} else if err != nil {

tests/integration/testdata/inframonitoring/hosts_metric_key_pair.jsonl

@@ -0,0 +1,36 @@
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "user"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 100, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "user"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 200, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "user"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 300, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "system"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 50, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "system"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 100, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "system"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 150, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "idle"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 400, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "idle"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 600, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "idle"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 800, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "wait"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 10, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "wait"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 20, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.cpu.time", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "wait"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 30, "temporality": "Cumulative", "type_": "Sum", "is_monotonic": true}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "used", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 2000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "used", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 2100000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "used", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 2200000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "free", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 6000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "free", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 5900000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "free", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 5800000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "buffered", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 500000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "buffered", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 500000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "buffered", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 500000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "cached", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1500000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "cached", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1500000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.memory.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "cached", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1500000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.cpu.load_average.15m", "labels": {"host.name": "kp-h1", "os.type": "linux"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1.5, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "system.cpu.load_average.15m", "labels": {"host.name": "kp-h1", "os.type": "linux"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1.55, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "system.cpu.load_average.15m", "labels": {"host.name": "kp-h1", "os.type": "linux"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1.6, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "system.filesystem.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "used", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 50000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.filesystem.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "used", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 51000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.filesystem.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "used", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 52000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.filesystem.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "free", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 50000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.filesystem.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "free", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 49000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.filesystem.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "free", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 48000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.filesystem.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "reserved", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 5000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.filesystem.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "reserved", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 5000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}
+{"metric_name": "system.filesystem.usage", "labels": {"host.name": "kp-h1", "os.type": "linux", "state": "reserved", "deployment.environment": "prod"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 5000000000, "temporality": "Unspecified", "type_": "Sum", "is_monotonic": false}

tests/integration/testdata/inframonitoring/namespaces_same_name_across_clusters.jsonl

@@ -0,0 +1,27 @@
+{"metric_name": "k8s.pod.cpu.usage", "labels": {"k8s.pod.uid": "dup-ns-g1-p1-uid", "k8s.pod.name": "dup-ns-g1-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0.3, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.cpu.usage", "labels": {"k8s.pod.uid": "dup-ns-g1-p1-uid", "k8s.pod.name": "dup-ns-g1-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0.3, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.cpu.usage", "labels": {"k8s.pod.uid": "dup-ns-g1-p1-uid", "k8s.pod.name": "dup-ns-g1-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0.3, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.memory.working_set", "labels": {"k8s.pod.uid": "dup-ns-g1-p1-uid", "k8s.pod.name": "dup-ns-g1-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 100000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.memory.working_set", "labels": {"k8s.pod.uid": "dup-ns-g1-p1-uid", "k8s.pod.name": "dup-ns-g1-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 100000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.memory.working_set", "labels": {"k8s.pod.uid": "dup-ns-g1-p1-uid", "k8s.pod.name": "dup-ns-g1-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 100000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.phase", "labels": {"k8s.pod.uid": "dup-ns-g1-p1-uid", "k8s.pod.name": "dup-ns-g1-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 2, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.phase", "labels": {"k8s.pod.uid": "dup-ns-g1-p1-uid", "k8s.pod.name": "dup-ns-g1-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 2, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.phase", "labels": {"k8s.pod.uid": "dup-ns-g1-p1-uid", "k8s.pod.name": "dup-ns-g1-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 2, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.cpu.usage", "labels": {"k8s.pod.uid": "dup-ns-g2-p1-uid", "k8s.pod.name": "dup-ns-g2-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0.5, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.cpu.usage", "labels": {"k8s.pod.uid": "dup-ns-g2-p1-uid", "k8s.pod.name": "dup-ns-g2-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0.5, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.cpu.usage", "labels": {"k8s.pod.uid": "dup-ns-g2-p1-uid", "k8s.pod.name": "dup-ns-g2-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0.5, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.memory.working_set", "labels": {"k8s.pod.uid": "dup-ns-g2-p1-uid", "k8s.pod.name": "dup-ns-g2-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 300000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.memory.working_set", "labels": {"k8s.pod.uid": "dup-ns-g2-p1-uid", "k8s.pod.name": "dup-ns-g2-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 300000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.memory.working_set", "labels": {"k8s.pod.uid": "dup-ns-g2-p1-uid", "k8s.pod.name": "dup-ns-g2-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 300000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.phase", "labels": {"k8s.pod.uid": "dup-ns-g2-p1-uid", "k8s.pod.name": "dup-ns-g2-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 4, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.phase", "labels": {"k8s.pod.uid": "dup-ns-g2-p1-uid", "k8s.pod.name": "dup-ns-g2-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 4, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.phase", "labels": {"k8s.pod.uid": "dup-ns-g2-p1-uid", "k8s.pod.name": "dup-ns-g2-p1", "k8s.namespace.name": "dup-ns", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 4, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.cpu.usage", "labels": {"k8s.pod.uid": "dup-ns-g3-p1-uid", "k8s.pod.name": "dup-ns-g3-p1", "k8s.namespace.name": "dup-ns"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0.1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.cpu.usage", "labels": {"k8s.pod.uid": "dup-ns-g3-p1-uid", "k8s.pod.name": "dup-ns-g3-p1", "k8s.namespace.name": "dup-ns"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0.1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.cpu.usage", "labels": {"k8s.pod.uid": "dup-ns-g3-p1-uid", "k8s.pod.name": "dup-ns-g3-p1", "k8s.namespace.name": "dup-ns"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0.1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.memory.working_set", "labels": {"k8s.pod.uid": "dup-ns-g3-p1-uid", "k8s.pod.name": "dup-ns-g3-p1", "k8s.namespace.name": "dup-ns"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 200000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.memory.working_set", "labels": {"k8s.pod.uid": "dup-ns-g3-p1-uid", "k8s.pod.name": "dup-ns-g3-p1", "k8s.namespace.name": "dup-ns"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 200000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.memory.working_set", "labels": {"k8s.pod.uid": "dup-ns-g3-p1-uid", "k8s.pod.name": "dup-ns-g3-p1", "k8s.namespace.name": "dup-ns"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 200000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.phase", "labels": {"k8s.pod.uid": "dup-ns-g3-p1-uid", "k8s.pod.name": "dup-ns-g3-p1", "k8s.namespace.name": "dup-ns"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.phase", "labels": {"k8s.pod.uid": "dup-ns-g3-p1-uid", "k8s.pod.name": "dup-ns-g3-p1", "k8s.namespace.name": "dup-ns"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.pod.phase", "labels": {"k8s.pod.uid": "dup-ns-g3-p1-uid", "k8s.pod.name": "dup-ns-g3-p1", "k8s.namespace.name": "dup-ns"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}

tests/integration/testdata/inframonitoring/volumes_same_name_across_ns_and_clusters.jsonl

@@ -0,0 +1,60 @@
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 60.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 60.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 60.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 100.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 100.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 100.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 600.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 600.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 600.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 400.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 400.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g1-p1-uid", "k8s.pod.name": "dup-pvc-g1-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 400.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 100.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 100.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 100.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 500.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 500.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 500.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 5000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 5000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 5000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 4000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 4000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g2-p1-uid", "k8s.pod.name": "dup-pvc-g2-p1", "k8s.namespace.name": "ns-y", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-a"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 4000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 50.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 50.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 50.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 300.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 300.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 300.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 3000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 3000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 3000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 500.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 500.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 500.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 2500.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 2500.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g3-p1-uid", "k8s.pod.name": "dup-pvc-g3-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup", "k8s.cluster.name": "cluster-b"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 2500.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.available", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 200.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 200.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 200.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 2000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 2000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 2000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 0.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 0.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 0.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 2000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 2000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "dup-pvc", "k8s.pod.uid": "dup-pvc-g4-p1-uid", "k8s.pod.name": "dup-pvc-g4-p1", "k8s.namespace.name": "ns-x", "k8s.node.name": "node-x", "k8s.statefulset.name": "ss-dup"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 2000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}

tests/integration/tests/inframonitoring/01_hosts.py

@@ -11,7 +11,7 @@ from fixtures import types
 from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.fs import get_testdata_file_path
 from fixtures.metrics import Metrics
-from fixtures.querier import compare_values
+from fixtures.querier import compare_values, get_all_warnings
 
 ENDPOINT = "/api/v2/infra_monitoring/hosts"
 
@@ -56,7 +56,8 @@ def test_hosts_accuracy(
     # Shape/contract.
     assert data["total"] == len(expected["records"])
     assert len(data["records"]) == len(expected["records"])
-    assert data["requiredMetricsCheck"]["missingMetrics"] == []
+    # Full data present -> no warnings surfaced.
+    assert get_all_warnings(response.json()) == []
     assert data["endTimeBeforeRetention"] is False
     assert {r["hostName"] for r in data["records"]} == set(exp_by_host.keys())
 
@@ -79,45 +80,109 @@ def test_hosts_accuracy(
             assert compare_values(record[field], exp[field], 1e-9), f"{record['hostName']}.{field}: got {record[field]}, expected {exp[field]}"
 
 
-def test_hosts_missing_metrics(
+@pytest.mark.parametrize(
+    "case",
+    [
+        # Scenario 1: a required host metric was never ingested. Post-#11754 the
+        # querier drops it instead of hard-erroring, so the endpoint returns 200
+        # with the hosts that DO have data; the never-seen metric's column is the
+        # -1 sentinel and a "has never been received" warning is surfaced.
+        pytest.param(
+            {
+                "dataset": "hosts_missing_metrics.jsonl",  # seeds only system.cpu.time
+                "body": {"filter": {"expression": "host.name = 'miss-h1'"}},
+                # singular form is "has", plural (>1 missing) is "have" -> match the common stem
+                "warn_substrings": ["never been received"],
+                "warn_names": [
+                    "system.memory.usage",
+                    "system.cpu.load_average.15m",
+                    "system.filesystem.usage",
+                ],
+                # cpu/wait derive from the present system.cpu.time; the rest come
+                # from never-seen metrics -> -1 sentinel.
+                "data_fields": ["cpu", "wait"],
+                "no_data_fields": ["memory", "load15", "diskUsage"],
+            },
+            id="metric_never_seen",
+        ),
+        # Scenario 2: groupBy a key that IS in metadata (seen on some metrics) but
+        # was never seen together with the host metrics. deployment.environment is
+        # seeded on system.memory.usage + system.filesystem.usage only, so the key
+        # resolves (the page-groups IN-filter parses -> no 400) but the cpu.time /
+        # load_average metrics miss the (metric, key) pair and the statement builder
+        # falls back to raw labels, surfacing "key `...` not found on metric ...".
+        # Still 200, no hard error.
+        pytest.param(
+            {
+                "dataset": "hosts_metric_key_pair.jsonl",
+                "body": {
+                    "filter": {"expression": "host.name = 'kp-h1'"},
+                    "groupBy": [
+                        {
+                            "name": "deployment.environment",
+                            "fieldDataType": "string",
+                            "fieldContext": "resource",
+                        }
+                    ],
+                },
+                "warn_substrings": ["key `deployment.environment` not found on metric"],
+                "warn_names": [],
+                "data_fields": [],
+                "no_data_fields": [],
+            },
+            id="metric_key_pair_not_seen",
+        ),
+    ],
+)
+def test_hosts_warnings(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token,
     insert_metrics,
+    case: dict,
 ) -> None:
-    """Seed only system.cpu.time; assert other 3 required metrics flagged missing."""
+    """Data-availability gaps surface as non-blocking warnings (200 + data),
+    not hard errors. Covers never-seen metrics (scenario 1) and never-seen
+    (metric, key) pairs via groupBy (scenario 2). Field-level expectations are
+    provisional pending a real run."""
     now = datetime.now(tz=UTC).replace(microsecond=0)
     insert_metrics(
         Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/hosts_missing_metrics.jsonl"),
+            get_testdata_file_path(f"inframonitoring/{case['dataset']}"),
             base_time=now - timedelta(minutes=4),
         )
     )
 
     token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    body: dict = {
+        "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
+        "end": int(now.timestamp() * 1000),
+        "limit": 50,
+    }
+    body.update(case["body"])
+
     response = requests.post(
         signoz.self.host_configs["8080"].get(ENDPOINT),
         headers={"authorization": f"Bearer {token}"},
-        json={
-            "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
-            "end": int(now.timestamp() * 1000),
-            "limit": 50,
-        },
+        json=body,
         timeout=5,
     )
-    assert response.status_code == HTTPStatus.OK
+    assert response.status_code == HTTPStatus.OK, response.text
     data = response.json()["data"]
+    warnings = get_all_warnings(response.json())
 
-    assert set(data["requiredMetricsCheck"]["missingMetrics"]) == {
-        "system.memory.usage",
-        "system.cpu.load_average.15m",
-        "system.filesystem.usage",
-    }
-    # Endpoint short-circuits when any required metric is missing:
-    # records is empty and total=0 regardless of which hosts have partial data.
-    # See pkg/modules/inframonitoring/implinframonitoring/module.go:84-89.
-    assert data["records"] == []
-    assert data["total"] == 0
+    for substr in case["warn_substrings"]:
+        assert any(substr in w["message"] for w in warnings), f"{substr!r} not surfaced: {warnings!r}"
+    for name in case["warn_names"]:
+        assert any(name in w["message"] for w in warnings), f"{name!r} not surfaced: {warnings!r}"
+
+    assert len(data["records"]) >= 1, f"expected at least one record: {data!r}"
+    if case["data_fields"] or case["no_data_fields"]:
+        record = data["records"][0]
+        for field in case["data_fields"]:
+            assert record[field] != -1, f"expected {field} populated, got {record[field]}"
+        for field in case["no_data_fields"]:
+            assert record[field] == -1, f"expected {field} == -1 sentinel, got {record[field]}"
 
 
 @pytest.mark.parametrize(

tests/integration/tests/inframonitoring/04_namespaces.py

@@ -317,23 +317,94 @@ def test_namespaces_pod_phase_aggregation(
     }
 
 
+# Float record fields compared with tolerance; everything else compared with ==.
+_GROUPBY_FLOAT_FIELDS = {
+    "namespaceCPU",
+    "namespaceMemory",
+}
+
+
+def _phase(pending=0, running=0, succeeded=0, failed=0, unknown=0) -> dict:
+    return {"pending": pending, "running": running, "succeeded": succeeded, "failed": failed, "unknown": unknown}
+
+
 @pytest.mark.parametrize(
-    "group_key,expected_running",
+    "scenario",
     [
-        # groupBy=[k8s.namespace.name]: one record per namespace, namespaceName
-        # populated (namespaces.go:27-30). Each namespace has 1 running pod.
+        # Explicit groupBy=[k8s.namespace.name]: one record per namespace,
+        # namespaceName populated (namespaces.go:27-30), response grouped_list.
+        # Each namespace has 1 running pod.
         pytest.param(
-            "k8s.namespace.name",
-            {"gb-ns-1": 1, "gb-ns-2": 1, "gb-ns-3": 1, "gb-ns-4": 1},
+            {
+                "fixture": "namespaces_groupby.jsonl",
+                "group_by": "k8s.namespace.name",
+                "filter": None,
+                "group_meta_keys": ["k8s.namespace.name"],
+                "expected_type": "grouped_list",
+                "groups": {
+                    "gb-ns-1": {"namespaceName": "gb-ns-1", "podCountsByPhase": _phase(running=1)},
+                    "gb-ns-2": {"namespaceName": "gb-ns-2", "podCountsByPhase": _phase(running=1)},
+                    "gb-ns-3": {"namespaceName": "gb-ns-3", "podCountsByPhase": _phase(running=1)},
+                    "gb-ns-4": {"namespaceName": "gb-ns-4", "podCountsByPhase": _phase(running=1)},
+                },
+            },
             id="namespace_name",
         ),
-        # groupBy=[k8s.cluster.name]: aggregated across each cluster's 2
-        # namespaces, namespaceName empty. Each cluster has 2 x 1 = 2 running pods.
+        # Explicit groupBy=[k8s.cluster.name]: aggregated across each cluster's 2
+        # namespaces, namespaceName empty, response grouped_list. 2 running each.
         pytest.param(
-            "k8s.cluster.name",
-            {"gb-cluster-a": 2, "gb-cluster-b": 2},
+            {
+                "fixture": "namespaces_groupby.jsonl",
+                "group_by": "k8s.cluster.name",
+                "filter": None,
+                "group_meta_keys": ["k8s.cluster.name"],
+                "expected_type": "grouped_list",
+                "groups": {
+                    "gb-cluster-a": {"namespaceName": "", "podCountsByPhase": _phase(running=2)},
+                    "gb-cluster-b": {"namespaceName": "", "podCountsByPhase": _phase(running=2)},
+                },
+            },
             id="cluster",
         ),
+        # Default groupBy (no groupBy in request) => [k8s.namespace.name,
+        # k8s.cluster.name] (module.go ListNamespaces), response list. Namespaces
+        # are cluster-scoped, so a same-named namespace must NOT collapse across
+        # clusters; the empty-cluster group (k8s.cluster.name label absent on the
+        # source pods) must appear as its own row with real metrics, not be dropped.
+        # Single pod per group => SpaceAggregationSum == seeded value.
+        # Fails on the pre-cluster default (name only) — the three groups would
+        # collapse into one summed row.
+        pytest.param(
+            {
+                "fixture": "namespaces_same_name_across_clusters.jsonl",
+                "group_by": None,
+                "filter": "k8s.namespace.name = 'dup-ns'",
+                "group_meta_keys": ["k8s.namespace.name", "k8s.cluster.name"],
+                "expected_type": "list",
+                "groups": {
+                    ("dup-ns", "cluster-a"): {
+                        "namespaceName": "dup-ns",
+                        "namespaceCPU": 0.3,
+                        "namespaceMemory": 100000000.0,
+                        "podCountsByPhase": _phase(running=1),
+                    },
+                    ("dup-ns", "cluster-b"): {
+                        "namespaceName": "dup-ns",
+                        "namespaceCPU": 0.5,
+                        "namespaceMemory": 300000000.0,
+                        "podCountsByPhase": _phase(failed=1),
+                    },
+                    # empty-cluster group: k8s.cluster.name label absent on the source pods.
+                    ("dup-ns", ""): {
+                        "namespaceName": "dup-ns",
+                        "namespaceCPU": 0.1,
+                        "namespaceMemory": 200000000.0,
+                        "podCountsByPhase": _phase(pending=1),
+                    },
+                },
+            },
+            id="default_disambiguates_cluster",
+        ),
     ],
 )
 def test_namespaces_groupby(
@@ -341,55 +412,64 @@ def test_namespaces_groupby(
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token,
     insert_metrics,
-    group_key: str,
-    expected_running: dict,
+    scenario: dict,
 ) -> None:
-    """groupBy returns one record per distinct group with aggregated pod-phase
-    counts. namespaceName is populated only when grouping by k8s.namespace.name
-    (namespaces.go:27-30 list-vs-grouped branch); meta surfaces the groupBy key."""
+    """groupBy determines row identity. Explicit groupBy returns one grouped_list
+    record per distinct group (namespaceName populated only when grouping by
+    k8s.namespace.name; namespaces.go:27-30). With no groupBy the default is
+    [k8s.namespace.name, k8s.cluster.name] (module.go ListNamespaces), so
+    same-named namespaces across clusters stay as separate, un-collapsed list rows
+    (incl. an absent-cluster group keyed by ""). meta always surfaces the grouping
+    key(s)."""
     now = datetime.now(tz=UTC).replace(microsecond=0)
     insert_metrics(
         Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/namespaces_groupby.jsonl"),
+            get_testdata_file_path(f"inframonitoring/{scenario['fixture']}"),
             base_time=now - timedelta(minutes=4),
         )
     )
 
+    body: dict = {
+        "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
+        "end": int(now.timestamp() * 1000),
+        "limit": 50,
+    }
+    if scenario["group_by"] is not None:
+        body["groupBy"] = [{"name": scenario["group_by"], "fieldDataType": "string", "fieldContext": "resource"}]
+    if scenario["filter"] is not None:
+        body["filter"] = {"expression": scenario["filter"]}
+
     token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
     response = requests.post(
         signoz.self.host_configs["8080"].get(ENDPOINT),
         headers={"authorization": f"Bearer {token}"},
-        json={
-            "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
-            "end": int(now.timestamp() * 1000),
-            "limit": 50,
-            "groupBy": [
-                {
-                    "name": group_key,
-                    "fieldDataType": "string",
-                    "fieldContext": "resource",
-                }
-            ],
-        },
+        json=body,
         timeout=5,
     )
     assert response.status_code == HTTPStatus.OK, response.text
     data = response.json()["data"]
-    assert data["total"] == len(expected_running)
 
-    group_of = lambda r: r["namespaceName"] if group_key == "k8s.namespace.name" else r["meta"][group_key]  # noqa: E731  # pylint: disable=unnecessary-lambda-assignment
-    by_group = {group_of(r): r for r in data["records"]}
-    assert set(by_group.keys()) == set(expected_running.keys())
+    groups = scenario["groups"]
+    meta_keys = scenario["group_meta_keys"]
+    assert data["type"] == scenario["expected_type"]
+    assert data["total"] == len(groups)
 
-    for group, running in expected_running.items():
-        rec = by_group[group]
-        # namespaceName populated per namespace when grouping by k8s.namespace.name,
-        # empty otherwise.
-        assert rec["namespaceName"] == (group if group_key == "k8s.namespace.name" else "")
-        assert rec["podCountsByPhase"]["running"] == running
-        for other in ("pending", "succeeded", "failed", "unknown"):
-            assert rec["podCountsByPhase"][other] == 0
-        assert group_key in rec["meta"], rec["meta"]
+    def _gid(rec: dict):
+        vals = [rec["meta"][k] for k in meta_keys]
+        return vals[0] if len(vals) == 1 else tuple(vals)
+
+    by_group = {_gid(r): r for r in data["records"]}
+    assert set(by_group.keys()) == set(groups.keys())
+
+    for gid, exp in groups.items():
+        rec = by_group[gid]
+        for k in meta_keys:
+            assert k in rec["meta"], rec["meta"]
+        for field, val in exp.items():
+            if field in _GROUPBY_FLOAT_FIELDS:
+                assert compare_values(rec[field], val, 1e-6), f"{gid}.{field}: got {rec[field]}, expected {val}"
+            else:
+                assert rec[field] == val, f"{gid}.{field}: got {rec[field]}, expected {val}"
 
 
 def test_namespaces_pagination(

tests/integration/tests/inframonitoring/06_volumes.py

@@ -376,23 +376,111 @@ def test_volumes_non_pvc_volume_filtered(
     assert rec["persistentVolumeClaimName"] == "np-real-pvc"
 
 
+# Float record fields compared with tolerance; everything else compared with ==.
+_GROUPBY_FLOAT_FIELDS = {
+    "volumeAvailable",
+    "volumeCapacity",
+    "volumeUsage",
+    "volumeInodes",
+    "volumeInodesFree",
+    "volumeInodesUsed",
+}
+
+
 @pytest.mark.parametrize(
-    "group_key,expected_groups",
+    "scenario",
     [
-        # groupBy=[k8s.persistentvolumeclaim.name]: one record per PVC,
-        # persistentVolumeClaimName populated (volumes.go:26-29).
+        # Explicit groupBy=[k8s.persistentvolumeclaim.name]: one record per PVC,
+        # persistentVolumeClaimName populated (volumes.go:26-29), response grouped_list.
         pytest.param(
-            "k8s.persistentvolumeclaim.name",
-            {"gb-pvc-a1", "gb-pvc-a2", "gb-pvc-b1", "gb-pvc-b2"},
+            {
+                "fixture": "volumes_groupby.jsonl",
+                "group_by": "k8s.persistentvolumeclaim.name",
+                "filter": None,
+                "group_meta_keys": ["k8s.persistentvolumeclaim.name"],
+                "expected_type": "grouped_list",
+                "groups": {
+                    "gb-pvc-a1": {"persistentVolumeClaimName": "gb-pvc-a1"},
+                    "gb-pvc-a2": {"persistentVolumeClaimName": "gb-pvc-a2"},
+                    "gb-pvc-b1": {"persistentVolumeClaimName": "gb-pvc-b1"},
+                    "gb-pvc-b2": {"persistentVolumeClaimName": "gb-pvc-b2"},
+                },
+            },
             id="pvc_name",
         ),
-        # groupBy=[k8s.namespace.name]: aggregated per namespace,
-        # persistentVolumeClaimName cleared (custom-groupBy branch).
+        # Explicit groupBy=[k8s.namespace.name]: aggregated per namespace,
+        # persistentVolumeClaimName cleared, response grouped_list.
         pytest.param(
-            "k8s.namespace.name",
-            {"gb-ns-a", "gb-ns-b"},
+            {
+                "fixture": "volumes_groupby.jsonl",
+                "group_by": "k8s.namespace.name",
+                "filter": None,
+                "group_meta_keys": ["k8s.namespace.name"],
+                "expected_type": "grouped_list",
+                "groups": {
+                    "gb-ns-a": {"persistentVolumeClaimName": ""},
+                    "gb-ns-b": {"persistentVolumeClaimName": ""},
+                },
+            },
             id="namespace",
         ),
+        # Default groupBy (no groupBy in request) => [k8s.persistentvolumeclaim.name,
+        # k8s.namespace.name, k8s.cluster.name] (module.go ListVolumes), response list.
+        # Same PVC name must NOT collapse across namespaces OR clusters; the
+        # empty-cluster group (k8s.cluster.name label absent on the source series)
+        # must appear as its own row with real metrics, not be dropped.
+        # Single series per group => SpaceAggregationSum == seeded value.
+        # Fails on the pre-cluster default (name+ns) — the three ns-x groups would
+        # collapse into one summed row.
+        pytest.param(
+            {
+                "fixture": "volumes_same_name_across_ns_and_clusters.jsonl",
+                "group_by": None,
+                "filter": "k8s.persistentvolumeclaim.name = 'dup-pvc'",
+                "group_meta_keys": ["k8s.persistentvolumeclaim.name", "k8s.namespace.name", "k8s.cluster.name"],
+                "expected_type": "list",
+                "groups": {
+                    ("dup-pvc", "ns-x", "cluster-a"): {
+                        "persistentVolumeClaimName": "dup-pvc",
+                        "volumeCapacity": 100.0,
+                        "volumeAvailable": 60.0,
+                        "volumeUsage": 40.0,
+                        "volumeInodes": 1000.0,
+                        "volumeInodesFree": 600.0,
+                        "volumeInodesUsed": 400.0,
+                    },
+                    ("dup-pvc", "ns-y", "cluster-a"): {
+                        "persistentVolumeClaimName": "dup-pvc",
+                        "volumeCapacity": 500.0,
+                        "volumeAvailable": 100.0,
+                        "volumeUsage": 400.0,
+                        "volumeInodes": 5000.0,
+                        "volumeInodesFree": 1000.0,
+                        "volumeInodesUsed": 4000.0,
+                    },
+                    ("dup-pvc", "ns-x", "cluster-b"): {
+                        "persistentVolumeClaimName": "dup-pvc",
+                        "volumeCapacity": 300.0,
+                        "volumeAvailable": 50.0,
+                        "volumeUsage": 250.0,
+                        "volumeInodes": 3000.0,
+                        "volumeInodesFree": 500.0,
+                        "volumeInodesUsed": 2500.0,
+                    },
+                    # empty-cluster group: k8s.cluster.name label absent on the source series.
+                    ("dup-pvc", "ns-x", ""): {
+                        "persistentVolumeClaimName": "dup-pvc",
+                        "volumeCapacity": 200.0,
+                        "volumeAvailable": 0.0,
+                        "volumeUsage": 200.0,
+                        "volumeInodes": 2000.0,
+                        "volumeInodesFree": 0.0,
+                        "volumeInodesUsed": 2000.0,
+                    },
+                },
+            },
+            id="default_disambiguates_ns_and_cluster",
+        ),
     ],
 )
 def test_volumes_groupby(
@@ -400,51 +488,64 @@ def test_volumes_groupby(
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token,
     insert_metrics,
-    group_key: str,
-    expected_groups: set,
+    scenario: dict,
 ) -> None:
-    """groupBy returns one record per distinct group. persistentVolumeClaimName
-    is populated only when grouping by k8s.persistentvolumeclaim.name
-    (volumes.go:26-29 list-vs-grouped branch); meta surfaces the groupBy key."""
+    """groupBy determines row identity. Explicit groupBy returns one grouped_list
+    record per distinct group (persistentVolumeClaimName populated only when
+    grouping by k8s.persistentvolumeclaim.name; volumes.go:26-29). With no groupBy
+    the default is [k8s.persistentvolumeclaim.name, k8s.namespace.name,
+    k8s.cluster.name] (module.go ListVolumes), so same-named PVCs across
+    namespaces/clusters stay as separate, un-collapsed list rows (incl. an
+    absent-cluster group keyed by ""). meta always surfaces the grouping key(s)."""
     now = datetime.now(tz=UTC).replace(microsecond=0)
     insert_metrics(
         Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/volumes_groupby.jsonl"),
+            get_testdata_file_path(f"inframonitoring/{scenario['fixture']}"),
             base_time=now - timedelta(minutes=4),
         )
     )
 
+    body: dict = {
+        "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
+        "end": int(now.timestamp() * 1000),
+        "limit": 50,
+    }
+    if scenario["group_by"] is not None:
+        body["groupBy"] = [{"name": scenario["group_by"], "fieldDataType": "string", "fieldContext": "resource"}]
+    if scenario["filter"] is not None:
+        body["filter"] = {"expression": scenario["filter"]}
+
     token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
     response = requests.post(
         signoz.self.host_configs["8080"].get(ENDPOINT),
         headers={"authorization": f"Bearer {token}"},
-        json={
-            "start": int((now - timedelta(minutes=5)).timestamp() * 1000),
-            "end": int(now.timestamp() * 1000),
-            "limit": 50,
-            "groupBy": [
-                {
-                    "name": group_key,
-                    "fieldDataType": "string",
-                    "fieldContext": "resource",
-                }
-            ],
-        },
+        json=body,
         timeout=5,
     )
     assert response.status_code == HTTPStatus.OK, response.text
     data = response.json()["data"]
-    assert data["total"] == len(expected_groups)
 
-    is_pvc_group = group_key == "k8s.persistentvolumeclaim.name"
-    group_of = lambda r: r["persistentVolumeClaimName"] if is_pvc_group else r["meta"][group_key]  # noqa: E731  # pylint: disable=unnecessary-lambda-assignment
-    by_group = {group_of(r): r for r in data["records"]}
-    assert set(by_group.keys()) == expected_groups
+    groups = scenario["groups"]
+    meta_keys = scenario["group_meta_keys"]
+    assert data["type"] == scenario["expected_type"]
+    assert data["total"] == len(groups)
 
-    for group, rec in by_group.items():
-        # persistentVolumeClaimName populated per PVC when grouping by it, empty otherwise.
-        assert rec["persistentVolumeClaimName"] == (group if is_pvc_group else "")
-        assert group_key in rec["meta"], rec["meta"]
+    def _gid(rec: dict):
+        vals = [rec["meta"][k] for k in meta_keys]
+        return vals[0] if len(vals) == 1 else tuple(vals)
+
+    by_group = {_gid(r): r for r in data["records"]}
+    assert set(by_group.keys()) == set(groups.keys())
+
+    for gid, exp in groups.items():
+        rec = by_group[gid]
+        for k in meta_keys:
+            assert k in rec["meta"], rec["meta"]
+        for field, val in exp.items():
+            if field in _GROUPBY_FLOAT_FIELDS:
+                assert compare_values(rec[field], val, 1e-6), f"{gid}.{field}: got {rec[field]}, expected {val}"
+            else:
+                assert rec[field] == val, f"{gid}.{field}: got {rec[field]}, expected {val}"
 
 
 def test_volumes_pagination(

tests/integration/tests/querier/03_metrics.py

@@ -614,7 +614,7 @@ def test_histogram_p90_returns_warning_outside_data_window(
     assert warnings[0]["message"].startswith(f"no data found for the metric {metric_name}")
 
 
-def test_non_existent_metrics_returns_404(
+def test_non_existent_metrics_returns_warning(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token: Callable[[str, str], str],
@@ -635,9 +635,11 @@ def test_non_existent_metrics_returns_404(
 
     start_2h = int((now - timedelta(hours=2)).timestamp() * 1000)
     response = make_query_request(signoz, token, start_2h, end_ms, [query])
-    assert response.status_code == HTTPStatus.NOT_FOUND
+    assert response.status_code == HTTPStatus.OK
 
-    assert get_error_message(response.json()) == "could not find the metric whatevergoennnsgoeshere"
+    data = response.json()
+    warnings = get_all_warnings(data)
+    assert any("whatevergoennnsgoeshere" in w["message"] and "has never been received" in w["message"] for w in warnings), f"expected never-seen metric warning, got: {warnings}"
 
 
 def test_non_existent_internal_metrics_returns_no_warning(