Merge remote-tracking branch 'origin/main' into issue_5267

* fix: enable opamp for llmpricing

* fix: test files

* chore: cleanups

* fix: don't deploy to opamp if ff is disabled

* fix: enable spanmapper behild feature flag

.github/workflows/integrationci.yaml

@@ -38,6 +38,7 @@ jobs:
       fail-fast: false
       matrix:
         suite:
+          - spanmapper
           - alerts
           - basepath
           - callbackauthn

docs/api/openapi.yml

@@ -4054,8 +4054,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesClusterRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4066,7 +4064,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesDaemonSetRecord:
@@ -4123,8 +4120,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesDaemonSetRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4135,7 +4130,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesDeploymentRecord:
@@ -4192,8 +4186,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesDeploymentRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4204,7 +4196,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesHostFilter:
@@ -4270,8 +4261,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesHostRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4282,7 +4271,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesJobRecord:
@@ -4345,8 +4333,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesJobRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4357,7 +4343,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesNamespaceRecord:
@@ -4392,8 +4377,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesNamespaceRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4404,7 +4387,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesNodeCondition:
@@ -4469,8 +4451,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesNodeRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4481,7 +4461,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesPodCountsByPhase:
@@ -4567,8 +4546,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesPodRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4579,7 +4556,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesPostableClusters:
@@ -4842,16 +4818,6 @@ components:
       - end
       - limit
       type: object
-    InframonitoringtypesRequiredMetricsCheck:
-      properties:
-        missingMetrics:
-          items:
-            type: string
-          nullable: true
-          type: array
-      required:
-      - missingMetrics
-      type: object
     InframonitoringtypesResponseType:
       enum:
       - list
@@ -4911,8 +4877,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesStatefulSetRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4923,7 +4887,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     InframonitoringtypesVolumeRecord:
@@ -4971,8 +4934,6 @@ components:
           items:
             $ref: '#/components/schemas/InframonitoringtypesVolumeRecord'
           type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
         total:
           type: integer
         type:
@@ -4983,7 +4944,6 @@ components:
       - type
       - records
       - total
-      - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
     LlmpricingruletypesGettablePricingRules:
@@ -7108,6 +7068,19 @@ components:
       required:
       - items
       type: object
+    SpantypesGettableSpanMapperTest:
+      properties:
+        collectorLogs:
+          items:
+            type: string
+          nullable: true
+          type: array
+        spans:
+          items:
+            $ref: '#/components/schemas/SpantypesSpanMapperTestSpan'
+          nullable: true
+          type: array
+      type: object
     SpantypesGettableTraceAggregations:
       properties:
         aggregations:
@@ -7195,6 +7168,39 @@ components:
       - name
       - condition
       type: object
+    SpantypesPostableSpanMapperTest:
+      properties:
+        groups:
+          items:
+            $ref: '#/components/schemas/SpantypesPostableSpanMapperTestGroup'
+          nullable: true
+          type: array
+        spans:
+          items:
+            $ref: '#/components/schemas/SpantypesSpanMapperTestSpan'
+          nullable: true
+          type: array
+      required:
+      - spans
+      - groups
+      type: object
+    SpantypesPostableSpanMapperTestGroup:
+      properties:
+        condition:
+          $ref: '#/components/schemas/SpantypesSpanMapperGroupCondition'
+        enabled:
+          type: boolean
+        mappers:
+          items:
+            $ref: '#/components/schemas/SpantypesPostableSpanMapper'
+          nullable: true
+          type: array
+        name:
+          type: string
+      required:
+      - name
+      - condition
+      type: object
     SpantypesPostableTraceAggregations:
       properties:
         aggregations:
@@ -7356,6 +7362,17 @@ components:
       - operation
       - priority
       type: object
+    SpantypesSpanMapperTestSpan:
+      properties:
+        attributes:
+          additionalProperties: {}
+          nullable: true
+          type: object
+        resource:
+          additionalProperties: {}
+          nullable: true
+          type: object
+      type: object
     SpantypesUpdatableSpanMapper:
       properties:
         config:
@@ -12984,6 +13001,69 @@ paths:
       summary: Update a span mapper
       tags:
       - spanmapper
+  /api/v1/span_mapper_groups/test:
+    post:
+      deprecated: false
+      description: Tests how span mappers would transform sample spans
+      operationId: TestSpanMappers
+      requestBody:
+        content:
+          application/json:
+            schema:
+              $ref: '#/components/schemas/SpantypesPostableSpanMapperTest'
+      responses:
+        "200":
+          content:
+            application/json:
+              schema:
+                properties:
+                  data:
+                    $ref: '#/components/schemas/SpantypesGettableSpanMapperTest'
+                  status:
+                    type: string
+                required:
+                - status
+                - data
+                type: object
+          description: OK
+        "400":
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/RenderErrorResponse'
+          description: Bad Request
+        "401":
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/RenderErrorResponse'
+          description: Unauthorized
+        "403":
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/RenderErrorResponse'
+          description: Forbidden
+        "404":
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/RenderErrorResponse'
+          description: Not Found
+        "500":
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/RenderErrorResponse'
+          description: Internal Server Error
+      security:
+      - api_key:
+        - VIEWER
+      - tokenizer:
+        - VIEWER
+      summary: Test span mappers against sample spans
+      tags:
+      - spanmapper
   /api/v1/stats:
     get:
       deprecated: false
@@ -14882,10 +14962,10 @@ 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:
@@ -14958,11 +15038,11 @@ 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:
@@ -15033,11 +15113,11 @@ 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:
@@ -15102,10 +15182,9 @@ 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:
@@ -15179,11 +15258,11 @@ 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:
@@ -15248,10 +15327,10 @@ 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:
@@ -15319,10 +15398,10 @@ 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:
@@ -15391,11 +15470,10 @@ 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:
@@ -15462,11 +15540,10 @@ 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:
@@ -15537,11 +15614,10 @@ 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:

ee/query-service/app/server.go

@@ -90,8 +90,12 @@ func NewServer(config signoz.Config, signoz *signoz.SigNoz) (*Server, error) {
 
 	// initiate agent config handler
 	agentConfMgr, err := agentConf.Initiate(&agentConf.ManagerOptions{
-		Store:         signoz.SQLStore,
-		AgentFeatures: []agentConf.AgentFeature{logParsingPipelineController},
+		Store: signoz.SQLStore,
+		AgentFeatures: []agentConf.AgentFeature{
+			logParsingPipelineController,
+			signoz.Modules.SpanMapper,
+			signoz.Modules.LLMPricingRule,
+		},
 	})
 	if err != nil {
 		return nil, err

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

@@ -5535,13 +5535,6 @@ export interface InframonitoringtypesClusterRecordDTO {
 	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
 }
 
-export interface InframonitoringtypesRequiredMetricsCheckDTO {
-	/**
-	 * @type array,null
-	 */
-	missingMetrics: string[] | null;
-}
-
 export enum InframonitoringtypesResponseTypeDTO {
 	list = 'list',
 	grouped_list = 'grouped_list',
@@ -5577,7 +5570,6 @@ export interface InframonitoringtypesClustersDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesClusterRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5655,7 +5647,6 @@ export interface InframonitoringtypesDaemonSetsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesDaemonSetRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5733,7 +5724,6 @@ export interface InframonitoringtypesDeploymentsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesDeploymentRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5819,7 +5809,6 @@ export interface InframonitoringtypesHostsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesHostRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5905,7 +5894,6 @@ export interface InframonitoringtypesJobsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesJobRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -5955,7 +5943,6 @@ export interface InframonitoringtypesNamespacesDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesNamespaceRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -6022,7 +6009,6 @@ export interface InframonitoringtypesNodesDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesNodeRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -6106,7 +6092,6 @@ export interface InframonitoringtypesPodsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesPodRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -6454,7 +6439,6 @@ export interface InframonitoringtypesStatefulSetsDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesStatefulSetRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -6523,7 +6507,6 @@ export interface InframonitoringtypesVolumesDTO {
 	 * @type array
 	 */
 	records: InframonitoringtypesVolumeRecordDTO[];
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
 	/**
 	 * @type integer
 	 */
@@ -8247,6 +8230,48 @@ export interface SpantypesGettableSpanMapperGroupsDTO {
 	items: SpantypesSpanMapperGroupDTO[];
 }
 
+export type SpantypesSpanMapperTestSpanDTOAttributesAnyOf = {
+	[key: string]: unknown;
+};
+
+/**
+ * @nullable
+ */
+export type SpantypesSpanMapperTestSpanDTOAttributes =
+	SpantypesSpanMapperTestSpanDTOAttributesAnyOf | null;
+
+export type SpantypesSpanMapperTestSpanDTOResourceAnyOf = {
+	[key: string]: unknown;
+};
+
+/**
+ * @nullable
+ */
+export type SpantypesSpanMapperTestSpanDTOResource =
+	SpantypesSpanMapperTestSpanDTOResourceAnyOf | null;
+
+export interface SpantypesSpanMapperTestSpanDTO {
+	/**
+	 * @type object,null
+	 */
+	attributes?: SpantypesSpanMapperTestSpanDTOAttributes;
+	/**
+	 * @type object,null
+	 */
+	resource?: SpantypesSpanMapperTestSpanDTOResource;
+}
+
+export interface SpantypesGettableSpanMapperTestDTO {
+	/**
+	 * @type array,null
+	 */
+	collectorLogs?: string[] | null;
+	/**
+	 * @type array,null
+	 */
+	spans?: SpantypesSpanMapperTestSpanDTO[] | null;
+}
+
 export enum SpantypesSpanAggregationTypeDTO {
 	span_count = 'span_count',
 	execution_time_percentage = 'execution_time_percentage',
@@ -8542,6 +8567,33 @@ export interface SpantypesPostableSpanMapperGroupDTO {
 	name: string;
 }
 
+export interface SpantypesPostableSpanMapperTestGroupDTO {
+	condition: SpantypesSpanMapperGroupConditionDTO | null;
+	/**
+	 * @type boolean
+	 */
+	enabled?: boolean;
+	/**
+	 * @type array,null
+	 */
+	mappers?: SpantypesPostableSpanMapperDTO[] | null;
+	/**
+	 * @type string
+	 */
+	name: string;
+}
+
+export interface SpantypesPostableSpanMapperTestDTO {
+	/**
+	 * @type array,null
+	 */
+	groups: SpantypesPostableSpanMapperTestGroupDTO[] | null;
+	/**
+	 * @type array,null
+	 */
+	spans: SpantypesSpanMapperTestSpanDTO[] | null;
+}
+
 export interface SpantypesSpanAggregationDTO {
 	aggregation: SpantypesSpanAggregationTypeDTO;
 	field: TelemetrytypesTelemetryFieldKeyDTO;
@@ -9923,6 +9975,14 @@ export type UpdateSpanMapperPathParameters = {
 	groupId: string;
 	mapperId: string;
 };
+export type TestSpanMappers200 = {
+	data: SpantypesGettableSpanMapperTestDTO;
+	/**
+	 * @type string
+	 */
+	status: string;
+};
+
 export type GetStats200Data = { [key: string]: unknown };
 
 export type GetStats200 = {

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

@@ -30,8 +30,10 @@ import type {
 	RenderErrorResponseDTO,
 	SpantypesPostableSpanMapperDTO,
 	SpantypesPostableSpanMapperGroupDTO,
+	SpantypesPostableSpanMapperTestDTO,
 	SpantypesUpdatableSpanMapperDTO,
 	SpantypesUpdatableSpanMapperGroupDTO,
+	TestSpanMappers200,
 	UpdateSpanMapperGroupPathParameters,
 	UpdateSpanMapperPathParameters,
 } from '../sigNoz.schemas';
@@ -780,3 +782,86 @@ export const useUpdateSpanMapper = <
 > => {
 	return useMutation(getUpdateSpanMapperMutationOptions(options));
 };
+/**
+ * Tests how span mappers would transform sample spans
+ * @summary Test span mappers against sample spans
+ */
+export const testSpanMappers = (
+	spantypesPostableSpanMapperTestDTO?: BodyType<SpantypesPostableSpanMapperTestDTO>,
+	signal?: AbortSignal,
+) => {
+	return GeneratedAPIInstance<TestSpanMappers200>({
+		url: `/api/v1/span_mapper_groups/test`,
+		method: 'POST',
+		headers: { 'Content-Type': 'application/json' },
+		data: spantypesPostableSpanMapperTestDTO,
+		signal,
+	});
+};
+
+export const getTestSpanMappersMutationOptions = <
+	TError = ErrorType<RenderErrorResponseDTO>,
+	TContext = unknown,
+>(options?: {
+	mutation?: UseMutationOptions<
+		Awaited<ReturnType<typeof testSpanMappers>>,
+		TError,
+		{ data?: BodyType<SpantypesPostableSpanMapperTestDTO> },
+		TContext
+	>;
+}): UseMutationOptions<
+	Awaited<ReturnType<typeof testSpanMappers>>,
+	TError,
+	{ data?: BodyType<SpantypesPostableSpanMapperTestDTO> },
+	TContext
+> => {
+	const mutationKey = ['testSpanMappers'];
+	const { mutation: mutationOptions } = options
+		? options.mutation &&
+			'mutationKey' in options.mutation &&
+			options.mutation.mutationKey
+			? options
+			: { ...options, mutation: { ...options.mutation, mutationKey } }
+		: { mutation: { mutationKey } };
+
+	const mutationFn: MutationFunction<
+		Awaited<ReturnType<typeof testSpanMappers>>,
+		{ data?: BodyType<SpantypesPostableSpanMapperTestDTO> }
+	> = (props) => {
+		const { data } = props ?? {};
+
+		return testSpanMappers(data);
+	};
+
+	return { mutationFn, ...mutationOptions };
+};
+
+export type TestSpanMappersMutationResult = NonNullable<
+	Awaited<ReturnType<typeof testSpanMappers>>
+>;
+export type TestSpanMappersMutationBody =
+	| BodyType<SpantypesPostableSpanMapperTestDTO>
+	| undefined;
+export type TestSpanMappersMutationError = ErrorType<RenderErrorResponseDTO>;
+
+/**
+ * @summary Test span mappers against sample spans
+ */
+export const useTestSpanMappers = <
+	TError = ErrorType<RenderErrorResponseDTO>,
+	TContext = unknown,
+>(options?: {
+	mutation?: UseMutationOptions<
+		Awaited<ReturnType<typeof testSpanMappers>>,
+		TError,
+		{ data?: BodyType<SpantypesPostableSpanMapperTestDTO> },
+		TContext
+	>;
+}): UseMutationResult<
+	Awaited<ReturnType<typeof testSpanMappers>>,
+	TError,
+	{ data?: BodyType<SpantypesPostableSpanMapperTestDTO> },
+	TContext
+> => {
+	return useMutation(getTestSpanMappersMutationOptions(options));
+};

frontend/src/styles.scss

@@ -794,6 +794,13 @@ notifications	-  2050
 	background: color-mix(in srgb, var(--l3-background) 20%, transparent);
 }
 
+// =================================================================
+// Monaco Editor style overrides
+.monaco-editor .find-widget.visible {
+	top: 30px !important;
+	right: 45px !important;
+}
+
 body.ai-assistant-panel-open {
 	.PylonChat-bubbleFrameContainer,
 	.PylonChat-chatWindowFrameContainer {

go.mod

@@ -9,7 +9,7 @@ require (
 	github.com/DATA-DOG/go-sqlmock v1.5.2
 	github.com/SigNoz/clickhouse-go-mock v0.14.0
 	github.com/SigNoz/govaluate v0.0.0-20240203125216-988004ccc7fd
-	github.com/SigNoz/signoz-otel-collector v0.144.3
+	github.com/SigNoz/signoz-otel-collector v0.144.6-rc.1.0.20260625043036-fb3dbb450bbd
 	github.com/antlr4-go/antlr/v4 v4.13.1
 	github.com/antonmedv/expr v1.15.3
 	github.com/bytedance/sonic v1.14.1
@@ -150,10 +150,6 @@ require (
 	github.com/ugorji/go/codec v1.3.0 // indirect
 	github.com/uptrace/opentelemetry-go-extra/otelsql v0.3.2 // indirect
 	github.com/x448/float16 v0.8.4 // indirect
-	go.opentelemetry.io/collector/client v1.54.0 // indirect
-	go.opentelemetry.io/collector/config/configoptional v1.50.0 // indirect
-	go.opentelemetry.io/collector/config/configretry v1.50.0 // indirect
-	go.opentelemetry.io/collector/exporter/exporterhelper v0.144.0 // indirect
 	go.opentelemetry.io/collector/internal/componentalias v0.148.0 // indirect
 	go.opentelemetry.io/collector/pdata/xpdata v0.148.0 // indirect
 	go.uber.org/goleak v1.3.0 // indirect

go.sum

@@ -110,11 +110,13 @@ github.com/SigNoz/expr v1.17.7-beta h1:FyZkleM5dTQ0O6muQfwGpoH5A2ohmN/XTasRCO72g
 github.com/SigNoz/expr v1.17.7-beta/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
 github.com/SigNoz/govaluate v0.0.0-20240203125216-988004ccc7fd h1:Bk43AsDYe0fhkbj57eGXx8H3ZJ4zhmQXBnrW523ktj8=
 github.com/SigNoz/govaluate v0.0.0-20240203125216-988004ccc7fd/go.mod h1:nxRcH/OEdM8QxzH37xkGzomr1O0JpYBRS6pwjsWW6Pc=
-github.com/SigNoz/signoz-otel-collector v0.144.3 h1:/7PPIqIpPsaWtrgnfHam2XVYP41ZlgEKLHzQO8oVxcA=
-github.com/SigNoz/signoz-otel-collector v0.144.3/go.mod h1:9pLVpcIQvUT88ZiNnZN/MI+XLruvwC+Xm2UzPmGjNfA=
+github.com/SigNoz/signoz-otel-collector v0.144.6-rc.1.0.20260625043036-fb3dbb450bbd h1:MGQATRMNEsBrdHzHb7uj2JIzLXXgQNcNxZHfmAAIIs8=
+github.com/SigNoz/signoz-otel-collector v0.144.6-rc.1.0.20260625043036-fb3dbb450bbd/go.mod h1:Jw1Y3s/ZOSz6RmLjZtj2A7wK6bse0T4pxs+oggBQnSs=
 github.com/Yiling-J/theine-go v0.6.2 h1:1GeoXeQ0O0AUkiwj2S9Jc0Mzx+hpqzmqsJ4kIC4M9AY=
 github.com/Yiling-J/theine-go v0.6.2/go.mod h1:08QpMa5JZ2pKN+UJCRrCasWYO1IKCdl54Xa836rpmDU=
 github.com/afex/hystrix-go v0.0.0-20180502004556-fa1af6a1f4f5/go.mod h1:SkGFH1ia65gfNATL8TAiHDNxPzPdmEL5uirI2Uyuz6c=
+github.com/alecthomas/participle/v2 v2.1.4 h1:W/H79S8Sat/krZ3el6sQMvMaahJ+XcM9WSI2naI7w2U=
+github.com/alecthomas/participle/v2 v2.1.4/go.mod h1:8tqVbpTX20Ru4NfYQgZf4mP18eXPTBViyMWiArNEgGI=
 github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
 github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
 github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
@@ -124,6 +126,10 @@ github.com/alecthomas/units v0.0.0-20240927000941-0f3dac36c52b h1:mimo19zliBX/vS
 github.com/alecthomas/units v0.0.0-20240927000941-0f3dac36c52b/go.mod h1:fvzegU4vN3H1qMT+8wDmzjAcDONcgo2/SZ/TyfdUOFs=
 github.com/andybalholm/brotli v1.2.0 h1:ukwgCxwYrmACq68yiUqwIWnGY0cTPox/M94sVwToPjQ=
 github.com/andybalholm/brotli v1.2.0/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
+github.com/antchfx/xmlquery v1.5.0 h1:uAi+mO40ZWfyU6mlUBxRVvL6uBNZ6LMU4M3+mQIBV4c=
+github.com/antchfx/xmlquery v1.5.0/go.mod h1:lJfWRXzYMK1ss32zm1GQV3gMIW/HFey3xDZmkP1SuNc=
+github.com/antchfx/xpath v1.3.6 h1:s0y+ElRRtTQdfHP609qFu0+c6bglDv20pqOViQjjdPI=
+github.com/antchfx/xpath v1.3.6/go.mod h1:i54GszH55fYfBmoZXapTHN8T8tkcHfRgLyVwwqzXNcs=
 github.com/antihax/optional v1.0.0/go.mod h1:uupD/76wgC+ih3iEmQUL+0Ugr19nfwCT1kdvxnR2qWY=
 github.com/antlr4-go/antlr/v4 v4.13.1 h1:SqQKkuVZ+zWkMMNkjy5FZe5mr5WURWnlpmOuzYWrPrQ=
 github.com/antlr4-go/antlr/v4 v4.13.1/go.mod h1:GKmUxMtwp6ZgGwZSva4eWPC5mS6vUAmOABFgjdkM7Nw=
@@ -286,6 +292,8 @@ github.com/ebitengine/purego v0.9.1 h1:a/k2f2HQU3Pi399RPW1MOaZyhKJL9w/xFpKAg4q1s
 github.com/ebitengine/purego v0.9.1/go.mod h1:iIjxzd6CiRiOG0UyXP+V1+jWqUXVjPKLAI0mRfJZTmQ=
 github.com/edsrzf/mmap-go v1.2.0 h1:hXLYlkbaPzt1SaQk+anYwKSRNhufIDCchSPkUD6dD84=
 github.com/edsrzf/mmap-go v1.2.0/go.mod h1:19H/e8pUPLicwkyNgOykDXkJ9F0MHE+Z52B8EIth78Q=
+github.com/elastic/go-grok v0.3.1 h1:WEhUxe2KrwycMnlvMimJXvzRa7DoByJB4PVUIE1ZD/U=
+github.com/elastic/go-grok v0.3.1/go.mod h1:n38ls8ZgOboZRgKcjMY8eFeZFMmcL9n2lP0iHhIDk64=
 github.com/elastic/lunes v0.2.0 h1:WI3bsdOTuaYXVe2DS1KbqA7u7FOHN4o8qJw80ZyZoQs=
 github.com/elastic/lunes v0.2.0/go.mod h1:u3W/BdONWTrh0JjNZ21C907dDc+cUZttZrGa625nf2k=
 github.com/emersion/go-sasl v0.0.0-20241020182733-b788ff22d5a6 h1:oP4q0fw+fOSWn3DfFi4EXdT+B+gTtzx8GC9xsc26Znk=
@@ -461,6 +469,7 @@ github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfU
 github.com/golang/groupcache v0.0.0-20190702054246-869f871628b6/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
 github.com/golang/groupcache v0.0.0-20191227052852-215e87163ea7/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
 github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
+github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE=
 github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
 github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
 github.com/golang/mock v1.2.0/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
@@ -674,6 +683,8 @@ github.com/huandu/xstrings v1.5.0 h1:2ag3IFq9ZDANvthTwTiqSSZLjDc+BedvHPAp5tJy2TI
 github.com/huandu/xstrings v1.5.0/go.mod h1:y5/lhBue+AyNmUVz9RLU9xbLR0o4KIIExikq4ovT0aE=
 github.com/iancoleman/orderedmap v0.3.0 h1:5cbR2grmZR/DiVt+VJopEhtVs9YGInGIxAoMJn+Ichc=
 github.com/iancoleman/orderedmap v0.3.0/go.mod h1:XuLcCUkdL5owUCQeF2Ue9uuw1EptkJDkXXS7VoV7XGE=
+github.com/iancoleman/strcase v0.3.0 h1:nTXanmYxhfFAMjZL34Ov6gkzEsSJZ5DbhxWjvSASxEI=
+github.com/iancoleman/strcase v0.3.0/go.mod h1:iwCmte+B7n89clKwxIoIXy/HfoL7AsD47ZCWhYzw7ho=
 github.com/ianlancetaylor/demangle v0.0.0-20181102032728-5e5cf60278f6/go.mod h1:aSSvb/t6k1mPoxDqO4vJh6VOCGPwU4O0C2/Eqndh1Sc=
 github.com/ianlancetaylor/demangle v0.0.0-20200824232613-28f6c0f3b639/go.mod h1:aSSvb/t6k1mPoxDqO4vJh6VOCGPwU4O0C2/Eqndh1Sc=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
@@ -866,12 +877,18 @@ github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal
 github.com/open-telemetry/opentelemetry-collector-contrib/internal/coreinternal v0.144.0/go.mod h1:O2rZKRXk1WeYhzfJBVXES/g7+PlIds/TzPZW/4NfTNA=
 github.com/open-telemetry/opentelemetry-collector-contrib/internal/exp/metrics v0.148.0 h1:CiTjQE/Hh5xK2t56ogrDK4nl0+tJPNmASCs4zEYZ/xU=
 github.com/open-telemetry/opentelemetry-collector-contrib/internal/exp/metrics v0.148.0/go.mod h1:WUFkzTiOpt7EYyL67gv1GOf3RD8qKWGtin3lY9LYzW4=
+github.com/open-telemetry/opentelemetry-collector-contrib/internal/filter v0.144.0 h1:Ywu5mU4K5TMJigiXdyZloCRs/cq3/2OnoK3WjxNHWJo=
+github.com/open-telemetry/opentelemetry-collector-contrib/internal/filter v0.144.0/go.mod h1:iebqlu6UvpiV1hO37r1sXA9fXaCaA8sQXilG0///xss=
+github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl v0.144.0 h1:TMRTvQSAeeLtkKwSrqcbectxDRPiqB6yYM3IvjC75es=
+github.com/open-telemetry/opentelemetry-collector-contrib/pkg/ottl v0.144.0/go.mod h1:1HU0qJ4hFrphDebuBs3I4DPQ6zyBFGinQ5/bXEUM7pw=
 github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatatest v0.148.0 h1:i12duJOl5VCb9mbb8FfZCaP2CjeXbNsbg82JjSe7sy8=
 github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatatest v0.148.0/go.mod h1:jyw+QvkmCrF/oYy31O2ndb5KZZK4l+iR89msnV3LN/k=
 github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil v0.148.0 h1:1TLg6YrS3Au6F7xw3ws2Njbwj13IMqPplvGFi+18fWs=
 github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil v0.148.0/go.mod h1:P8hZEDIQk4REgUWyLhSVRHwTxK6KkifKfg36BmmQ/DI=
 github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza v0.144.0 h1:EIAygME70IOdEwaSr6bA3Wcdp7hXEqRsGsVfrI5v8OA=
 github.com/open-telemetry/opentelemetry-collector-contrib/pkg/stanza v0.144.0/go.mod h1:3Y6ctEEwRg19B0jqsrQH6Hiquqte+zC0ZxpXLLSa5sA=
+github.com/open-telemetry/opentelemetry-collector-contrib/processor/attributesprocessor v0.144.0 h1:gRk73SsIJv3q/HI0kxMRN5TiIiJj+MRxrz0GEYx3jZw=
+github.com/open-telemetry/opentelemetry-collector-contrib/processor/attributesprocessor v0.144.0/go.mod h1:7b8ZcPdN6JSm6+LUq3rienoqHHiX60kyoOHDPCMM+L8=
 github.com/open-telemetry/opentelemetry-collector-contrib/processor/deltatocumulativeprocessor v0.148.0 h1:xgD/kNGp/wWY+bwY599Pc01OamYN17phRiTP934bM5Y=
 github.com/open-telemetry/opentelemetry-collector-contrib/processor/deltatocumulativeprocessor v0.148.0/go.mod h1:ZK7wvaefla9lB3bAW0rNKt7IzRPcTRQoOFqr4sZy/XM=
 github.com/open-telemetry/opentelemetry-collector-contrib/processor/logstransformprocessor v0.144.0 h1:HbmpzTixpQG/xGhQuQoiJTXQPrixe+yivAsF6tl2o4g=
@@ -1119,6 +1136,10 @@ github.com/tmthrgd/go-hex v0.0.0-20190904060850-447a3041c3bc/go.mod h1:bciPuU6GH
 github.com/tv42/httpunix v0.0.0-20150427012821-b75d8614f926/go.mod h1:9ESjWnEqriFuLhtthL60Sar/7RFoluCcXsuvEwTV5KM=
 github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
 github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
+github.com/twmb/murmur3 v1.1.8 h1:8Yt9taO/WN3l08xErzjeschgZU2QSrwm1kclYq+0aRg=
+github.com/twmb/murmur3 v1.1.8/go.mod h1:Qq/R7NUyOfr65zD+6Q5IHKsJLwP7exErjN6lyyq3OSQ=
+github.com/ua-parser/uap-go v0.0.0-20240611065828-3a4781585db6 h1:SIKIoA4e/5Y9ZOl0DCe3eVMLPOQzJxgZpfdHHeauNTM=
+github.com/ua-parser/uap-go v0.0.0-20240611065828-3a4781585db6/go.mod h1:BUbeWZiieNxAuuADTBNb3/aeje6on3DhU3rpWsQSB1E=
 github.com/ugorji/go/codec v1.3.0 h1:Qd2W2sQawAfG8XSvzwhBeoGq71zXOC/Q1E9y/wUcsUA=
 github.com/ugorji/go/codec v1.3.0/go.mod h1:pRBVtBSKl77K30Bv8R2P+cLSGaTtex6fsA2Wjqmfxj4=
 github.com/uptrace/bun v1.2.9 h1:OOt2DlIcRUMSZPr6iXDFg/LaQd59kOxbAjpIVHddKRs=

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/apiserver/signozapiserver/spanmapper.go

@@ -51,6 +51,26 @@ func (provider *provider) addSpanMapperRoutes(router *mux.Router) error {
 		return err
 	}
 
+	if err := router.Handle("/api/v1/span_mapper_groups/test", handler.New(
+		provider.authzMiddleware.ViewAccess(provider.spanMapperHandler.TestMappers),
+		handler.OpenAPIDef{
+			ID:                  "TestSpanMappers",
+			Tags:                []string{"spanmapper"},
+			Summary:             "Test span mappers against sample spans",
+			Description:         "Tests how span mappers would transform sample spans",
+			Request:             new(spantypes.PostableSpanMapperTest),
+			RequestContentType:  "application/json",
+			Response:            new(spantypes.GettableSpanMapperTest),
+			ResponseContentType: "application/json",
+			SuccessStatusCode:   http.StatusOK,
+			ErrorStatusCodes:    []int{http.StatusBadRequest, http.StatusNotFound},
+			Deprecated:          false,
+			SecuritySchemes:     newSecuritySchemes(types.RoleViewer),
+		},
+	)).Methods(http.MethodPost).GetError(); err != nil {
+		return err
+	}
+
 	if err := router.Handle("/api/v1/span_mapper_groups/{groupId}", handler.New(
 		provider.authzMiddleware.AdminAccess(provider.spanMapperHandler.UpdateGroup),
 		handler.OpenAPIDef{

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/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 {
@@ -366,23 +344,16 @@ func (m *module) ListNamespaces(ctx context.Context, orgID valuer.UUID, req *inf
 		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 {
@@ -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/modules/llmpricingrule/impllmpricingrule/module.go

@@ -6,19 +6,22 @@ import (
 	"time"
 
 	"github.com/SigNoz/signoz/pkg/errors"
+	"github.com/SigNoz/signoz/pkg/flagger"
 	"github.com/SigNoz/signoz/pkg/modules/llmpricingrule"
 	"github.com/SigNoz/signoz/pkg/query-service/agentConf"
+	"github.com/SigNoz/signoz/pkg/types/featuretypes"
 	"github.com/SigNoz/signoz/pkg/types/llmpricingruletypes"
 	"github.com/SigNoz/signoz/pkg/types/opamptypes"
 	"github.com/SigNoz/signoz/pkg/valuer"
 )
 
 type module struct {
-	store llmpricingruletypes.Store
+	store   llmpricingruletypes.Store
+	flagger flagger.Flagger
 }
 
-func NewModule(store llmpricingruletypes.Store) llmpricingrule.Module {
-	return &module{store: store}
+func NewModule(store llmpricingruletypes.Store, flagger flagger.Flagger) llmpricingrule.Module {
+	return &module{store: store, flagger: flagger}
 }
 
 func (module *module) List(ctx context.Context, orgID valuer.UUID, offset, limit int, search string, isOverride *bool) ([]*llmpricingruletypes.LLMPricingRule, int, error) {
@@ -89,6 +92,16 @@ func (module *module) AgentFeatureType() agentConf.AgentFeatureType {
 func (module *module) RecommendAgentConfig(orgID valuer.UUID, currentConfYaml []byte, configVersion *opamptypes.AgentConfigVersion) ([]byte, string, error) {
 	ctx := context.Background()
 
+	// Skip the llm pricing processor unless AI observability is enabled for the org.
+	evalCtx := featuretypes.NewFlaggerEvaluationContext(orgID)
+	enabled, err := module.flagger.Boolean(ctx, flagger.FeatureEnableAIObservability, evalCtx)
+	if err != nil {
+		return nil, "", err
+	}
+	if !enabled {
+		return currentConfYaml, "", nil
+	}
+
 	rules, err := module.getEnabledRules(ctx, orgID)
 	if err != nil {
 		return nil, "", err

pkg/modules/spanmapper/implspanmapper/handler.go

@@ -273,6 +273,35 @@ func (h *handler) DeleteMapper(rw http.ResponseWriter, r *http.Request) {
 	render.Success(rw, http.StatusNoContent, nil)
 }
 
+// TestMappers handles POST /api/v1/span_mapper_groups/test.
+func (h *handler) TestMappers(rw http.ResponseWriter, r *http.Request) {
+	ctx, cancel := context.WithTimeout(r.Context(), 10*time.Second)
+	defer cancel()
+
+	claims, err := authtypes.ClaimsFromContext(ctx)
+	if err != nil {
+		render.Error(rw, err)
+		return
+	}
+
+	orgID := valuer.MustNewUUID(claims.OrgID)
+
+	req := new(spantypes.PostableSpanMapperTest)
+	if err := binding.JSON.BindBody(r.Body, req); err != nil {
+		render.Error(rw, err)
+		return
+	}
+
+	groups := spantypes.NewSpanMapperGroupsWithMappersFromPostable(orgID, req.Groups)
+	out, collectorLogs, err := h.module.TestMappers(ctx, orgID, req.Spans, groups)
+	if err != nil {
+		render.Error(rw, err)
+		return
+	}
+
+	render.Success(rw, http.StatusOK, &spantypes.GettableSpanMapperTest{Spans: out, CollectorLogs: collectorLogs})
+}
+
 // groupIDFromPath extracts and validates the {id} or {groupId} path variable.
 func groupIDFromPath(r *http.Request) (valuer.UUID, error) {
 	vars := mux.Vars(r)

pkg/modules/spanmapper/implspanmapper/module.go

@@ -4,19 +4,23 @@ import (
 	"context"
 	"encoding/json"
 
+	"github.com/SigNoz/signoz/pkg/errors"
+	"github.com/SigNoz/signoz/pkg/flagger"
 	"github.com/SigNoz/signoz/pkg/modules/spanmapper"
 	"github.com/SigNoz/signoz/pkg/query-service/agentConf"
+	"github.com/SigNoz/signoz/pkg/types/featuretypes"
 	"github.com/SigNoz/signoz/pkg/types/opamptypes"
 	"github.com/SigNoz/signoz/pkg/types/spantypes"
 	"github.com/SigNoz/signoz/pkg/valuer"
 )
 
 type module struct {
-	store spantypes.SpanMapperStore
+	store   spantypes.SpanMapperStore
+	flagger flagger.Flagger
 }
 
-func NewModule(store spantypes.SpanMapperStore) spanmapper.Module {
-	return &module{store: store}
+func NewModule(store spantypes.SpanMapperStore, flagger flagger.Flagger) spanmapper.Module {
+	return &module{store: store, flagger: flagger}
 }
 
 func (module *module) ListGroups(ctx context.Context, orgID valuer.UUID, q *spantypes.ListSpanMapperGroupsQuery) ([]*spantypes.SpanMapperGroup, error) {
@@ -102,6 +106,52 @@ func (module *module) DeleteMapper(ctx context.Context, orgID, groupID, id value
 	return nil
 }
 
+func (module *module) TestMappers(ctx context.Context, orgID valuer.UUID, spans []spantypes.SpanMapperTestSpan, groups []*spantypes.SpanMapperGroupWithMappers) ([]spantypes.SpanMapperTestSpan, []string, error) {
+	if len(spans) == 0 {
+		return nil, nil, errors.New(errors.TypeInvalidInput, spantypes.ErrCodeMappingInvalidInput, "'spans' must contain at least one span")
+	}
+
+	resolved, err := module.backfillMappers(ctx, orgID, groups)
+	if err != nil {
+		return nil, nil, err
+	}
+
+	out, collectorLogs, err := spantypes.SimulateSpanMappersProcessing(ctx, resolved, spans)
+	if err != nil {
+		return nil, nil, err
+	}
+	return out, collectorLogs, nil
+}
+
+// backfillMappers loads saved mappers for any group whose Mappers is nil.
+func (module *module) backfillMappers(ctx context.Context, orgID valuer.UUID, groups []*spantypes.SpanMapperGroupWithMappers) ([]*spantypes.SpanMapperGroupWithMappers, error) {
+	savedGroups, err := module.store.ListGroups(ctx, orgID, nil)
+	if err != nil {
+		return nil, err
+	}
+	savedByName := make(map[string]*spantypes.SpanMapperGroup, len(savedGroups))
+	for _, g := range savedGroups {
+		savedByName[g.Name] = g
+	}
+
+	// For each group in the request, if Mappers is nil, load the saved mappers for that group name.
+	for _, g := range groups {
+		if g.Mappers != nil {
+			continue
+		}
+		saved, ok := savedByName[g.Group.Name]
+		if !ok {
+			return nil, errors.Newf(errors.TypeInvalidInput, spantypes.ErrCodeMappingGroupNotFound, "no saved group named %q to load mappers from; send 'mappers' for new or edited groups", g.Group.Name)
+		}
+		loaded, err := module.store.ListMappers(ctx, orgID, saved.ID)
+		if err != nil {
+			return nil, err
+		}
+		g.Mappers = loaded
+	}
+	return groups, nil
+}
+
 func (module *module) AgentFeatureType() agentConf.AgentFeatureType {
 	return spantypes.SpanAttrMappingFeatureType
 }
@@ -109,12 +159,22 @@ func (module *module) AgentFeatureType() agentConf.AgentFeatureType {
 func (module *module) RecommendAgentConfig(orgID valuer.UUID, currentConfYaml []byte, configVersion *opamptypes.AgentConfigVersion) ([]byte, string, error) {
 	ctx := context.Background()
 
-	enabled, err := module.listEnabledGroupsWithMappers(ctx, orgID)
+	// Skip the llm pricing processor unless AI observability is enabled for the org.
+	evalCtx := featuretypes.NewFlaggerEvaluationContext(orgID)
+	enabled, err := module.flagger.Boolean(ctx, flagger.FeatureEnableAIObservability, evalCtx)
+	if err != nil {
+		return nil, "", err
+	}
+	if !enabled {
+		return currentConfYaml, "", nil
+	}
+
+	enabledMappers, err := module.listEnabledGroupsWithMappers(ctx, orgID)
 	if err != nil {
 		return nil, "", err
 	}
 
-	updatedConf, err := spantypes.GenerateCollectorConfigWithSpanMapperProcessor(currentConfYaml, enabled)
+	updatedConf, err := spantypes.GenerateCollectorConfigWithSpanMapperProcessor(currentConfYaml, enabledMappers)
 	if err != nil {
 		return nil, "", err
 	}

pkg/modules/spanmapper/spanmapper.go

@@ -27,6 +27,7 @@ type Module interface {
 	CreateMapper(ctx context.Context, orgID, groupID valuer.UUID, mapper *spantypes.SpanMapper) error
 	UpdateMapper(ctx context.Context, orgID, groupID, id valuer.UUID, fieldContext spantypes.FieldContext, config *spantypes.SpanMapperConfig, enabled *bool, updatedBy string) error
 	DeleteMapper(ctx context.Context, orgID, groupID, id valuer.UUID) error
+	TestMappers(ctx context.Context, orgID valuer.UUID, spans []spantypes.SpanMapperTestSpan, groups []*spantypes.SpanMapperGroupWithMappers) ([]spantypes.SpanMapperTestSpan, []string, error)
 }
 
 // Handler defines the HTTP handler interface for mapping group and mapper endpoints.
@@ -42,4 +43,5 @@ type Handler interface {
 	CreateMapper(rw http.ResponseWriter, r *http.Request)
 	UpdateMapper(rw http.ResponseWriter, r *http.Request)
 	DeleteMapper(rw http.ResponseWriter, r *http.Request)
+	TestMappers(rw http.ResponseWriter, r *http.Request)
 }

pkg/query-service/app/server.go

@@ -113,6 +113,8 @@ func NewServer(config signoz.Config, signoz *signoz.SigNoz) (*Server, error) {
 			Store: signoz.SQLStore,
 			AgentFeatures: []agentConf.AgentFeature{
 				logParsingPipelineController,
+				signoz.Modules.SpanMapper,
+				signoz.Modules.LLMPricingRule,
 			},
 		},
 	)

pkg/signoz/module.go

@@ -154,8 +154,8 @@ func NewModules(
 		RuleStateHistory: implrulestatehistory.NewModule(implrulestatehistory.NewStore(telemetryStore, telemetryMetadataStore, providerSettings.Logger)),
 		CloudIntegration: cloudIntegrationModule,
 		TraceDetail:      impltracedetail.NewModule(impltracedetail.NewTraceStore(telemetryStore), providerSettings, config.TraceDetail),
-		SpanMapper:       implspanmapper.NewModule(implspanmapper.NewStore(sqlstore)),
-		LLMPricingRule:   impllmpricingrule.NewModule(impllmpricingrule.NewStore(sqlstore)),
+		SpanMapper:       implspanmapper.NewModule(implspanmapper.NewStore(sqlstore), fl),
+		LLMPricingRule:   impllmpricingrule.NewModule(impllmpricingrule.NewStore(sqlstore), fl),
 		Tag:              tagModule,
 	}
 }

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/llmpricingruletypes/pricing.go

@@ -53,7 +53,8 @@ var (
 	LLMPricingRuleCacheModeSubtract = LLMPricingRuleCacheMode{valuer.NewString("subtract")}
 	// LLMPricingRuleCacheModeAdditive: cached tokens are reported separately (Anthropic-style).
 	LLMPricingRuleCacheModeAdditive = LLMPricingRuleCacheMode{valuer.NewString("additive")}
-	// LLMPricingRuleCacheModeUnknown: provider behaviour is unknown; falls back to subtract.
+	// LLMPricingRuleCacheModeUnknown: provider behaviour is unknown. buildProcessorConfig
+	// normalizes this to an empty mode in the collector config.
 	LLMPricingRuleCacheModeUnknown = LLMPricingRuleCacheMode{valuer.NewString("unknown")}
 )
 

pkg/types/llmpricingruletypes/processorconfig.go

@@ -26,24 +26,23 @@ type LLMPricingRuleProcessorAttrs struct {
 	CacheWrite string `yaml:"cache_write" json:"cache_write"`
 }
 
-// LLMPricingRuleProcessorDefaultPricing holds the pricing unit and the list of model-specific rules.
+// LLMPricingRuleProcessorDefaultPricing holds the list of model-specific rules.
 type LLMPricingRuleProcessorDefaultPricing struct {
-	Unit  string                    `yaml:"unit" json:"unit"`
 	Rules []LLMPricingRuleProcessor `yaml:"rules" json:"rules"`
 }
 
 // LLMPricingRuleProcessor is a single pricing rule inside the processor config.
 type LLMPricingRuleProcessor struct {
-	Name    string                       `yaml:"name" json:"name"`
-	Pattern []string                     `yaml:"pattern" json:"pattern"`
-	Cache   LLMPricingRuleProcessorCache `yaml:"cache" json:"cache"`
-	In      float64                      `yaml:"in" json:"in"`
-	Out     float64                      `yaml:"out" json:"out"`
+	Name    string                        `yaml:"name" json:"name"`
+	Pattern []string                      `yaml:"pattern" json:"pattern"`
+	Cache   *LLMPricingRuleProcessorCache `yaml:"cache,omitempty" json:"cache,omitempty"`
+	In      float64                       `yaml:"in" json:"in"`
+	Out     float64                       `yaml:"out" json:"out"`
 }
 
 // LLMPricingRuleProcessorCache describes how cached tokens are accounted for.
 type LLMPricingRuleProcessorCache struct {
-	Mode  string  `yaml:"mode" json:"mode"`
+	Mode  string  `yaml:"mode,omitempty" json:"mode,omitempty"`
 	Read  float64 `yaml:"read" json:"read"`
 	Write float64 `yaml:"write" json:"write"`
 }
@@ -61,10 +60,14 @@ type LLMPricingRuleProcessorOutputAttrs struct {
 func buildProcessorConfig(rules []*LLMPricingRule) *LLMPricingRuleProcessorConfig {
 	pricingRules := make([]LLMPricingRuleProcessor, 0, len(rules))
 	for _, r := range rules {
-		var cache LLMPricingRuleProcessorCache
+		var cache *LLMPricingRuleProcessorCache
 		if r.Pricing.Cache != nil {
-			cache = LLMPricingRuleProcessorCache{
-				Mode:  r.Pricing.Cache.Mode.StringValue(),
+			mode := r.Pricing.Cache.Mode.StringValue()
+			if mode != LLMPricingRuleCacheModeSubtract.StringValue() && mode != LLMPricingRuleCacheModeAdditive.StringValue() {
+				mode = ""
+			}
+			cache = &LLMPricingRuleProcessorCache{
+				Mode:  mode,
 				Read:  r.Pricing.Cache.Read,
 				Write: r.Pricing.Cache.Write,
 			}
@@ -87,7 +90,6 @@ func buildProcessorConfig(rules []*LLMPricingRule) *LLMPricingRuleProcessorConfi
 			CacheWrite: GenAIUsageCacheCreationInputTokens,
 		},
 		DefaultPricing: LLMPricingRuleProcessorDefaultPricing{
-			Unit:  UnitPerMillionTokens.StringValue(),
 			Rules: pricingRules,
 		},
 		OutputAttrs: LLMPricingRuleProcessorOutputAttrs{

pkg/types/llmpricingruletypes/processorconfig_test.go

@@ -41,6 +41,16 @@ func makePricingRule(model string, patterns []string, cacheMode LLMPricingRuleCa
 	}
 }
 
+func makePricingRuleNoCache(model string, patterns []string, costIn, costOut float64) *LLMPricingRule {
+	return &LLMPricingRule{
+		Model:        model,
+		ModelPattern: StringSlice(patterns),
+		Unit:         UnitPerMillionTokens,
+		Pricing:      LLMRulePricing{Input: costIn, Output: costOut},
+		Enabled:      true,
+	}
+}
+
 func TestGenerateCollectorConfigWithLLMPricingProcessor(t *testing.T) {
 	tests := []struct {
 		name         string
@@ -62,6 +72,24 @@ func TestGenerateCollectorConfigWithLLMPricingProcessor(t *testing.T) {
 			rules:        nil,
 			expectedFile: "collector_no_rules.yaml",
 		},
+		// A rule without cache pricing omits the cache block entirely so the
+		// collector does not apply any cache cost.
+		{
+			name: "rule_without_cache",
+			rules: []*LLMPricingRule{
+				makePricingRuleNoCache("gpt-4o", []string{"gpt-4o*"}, 5.0, 15.0),
+			},
+			expectedFile: "collector_rule_without_cache.yaml",
+		},
+		// An unknown cache mode still emits the cache block (with prices) but omits
+		// the mode field; the collector handles a missing mode in its default branch.
+		{
+			name: "rule_cache_mode_unknown",
+			rules: []*LLMPricingRule{
+				makePricingRule("gpt-4o", []string{"gpt-4o*"}, LLMPricingRuleCacheModeUnknown, 5.0, 15.0, 2.5, 0),
+			},
+			expectedFile: "collector_rule_cache_mode_unknown.yaml",
+		},
 	}
 
 	input, err := os.ReadFile(filepath.Join("testdata", "collector_baseline.yaml"))

pkg/types/llmpricingruletypes/testdata/collector_baseline.yaml

@@ -11,7 +11,6 @@ processors:
       cache_read: gen_ai.usage.cache_read.input_tokens
       cache_write: gen_ai.usage.cache_creation.input_tokens
     default_pricing:
-      unit: per_million_tokens
       rules: []
     output_attrs:
       in: _signoz.gen_ai.cost_input

pkg/types/llmpricingruletypes/testdata/collector_no_rules.yaml

@@ -11,7 +11,6 @@ processors:
             cache_read: gen_ai.usage.cache_read.input_tokens
             cache_write: gen_ai.usage.cache_creation.input_tokens
         default_pricing:
-            unit: per_million_tokens
             rules: []
         output_attrs:
             in: _signoz.gen_ai.cost_input

pkg/types/llmpricingruletypes/testdata/collector_rule_cache_mode_unknown.yaml

@@ -0,0 +1,42 @@
+exporters:
+    otlp:
+        endpoint: localhost:4317
+processors:
+    batch: {}
+    signozllmpricing:
+        attrs:
+            model: gen_ai.request.model
+            in: gen_ai.usage.input_tokens
+            out: gen_ai.usage.output_tokens
+            cache_read: gen_ai.usage.cache_read.input_tokens
+            cache_write: gen_ai.usage.cache_creation.input_tokens
+        default_pricing:
+            rules:
+                - name: gpt-4o
+                  pattern:
+                    - gpt-4o*
+                  cache:
+                    read: 2.5
+                    write: 0
+                  in: 5
+                  out: 15
+        output_attrs:
+            in: _signoz.gen_ai.cost_input
+            out: _signoz.gen_ai.cost_output
+            cache_read: _signoz.gen_ai.cost_cache_read
+            cache_write: _signoz.gen_ai.cost_cache_write
+            total: _signoz.gen_ai.total_cost
+receivers:
+    otlp:
+        protocols:
+            grpc: null
+service:
+    pipelines:
+        traces:
+            exporters:
+                - otlp
+            processors:
+                - batch
+                - signozllmpricing
+            receivers:
+                - otlp

pkg/types/llmpricingruletypes/testdata/collector_rule_without_cache.yaml

@@ -0,0 +1,39 @@
+exporters:
+    otlp:
+        endpoint: localhost:4317
+processors:
+    batch: {}
+    signozllmpricing:
+        attrs:
+            model: gen_ai.request.model
+            in: gen_ai.usage.input_tokens
+            out: gen_ai.usage.output_tokens
+            cache_read: gen_ai.usage.cache_read.input_tokens
+            cache_write: gen_ai.usage.cache_creation.input_tokens
+        default_pricing:
+            rules:
+                - name: gpt-4o
+                  pattern:
+                    - gpt-4o*
+                  in: 5
+                  out: 15
+        output_attrs:
+            in: _signoz.gen_ai.cost_input
+            out: _signoz.gen_ai.cost_output
+            cache_read: _signoz.gen_ai.cost_cache_read
+            cache_write: _signoz.gen_ai.cost_cache_write
+            total: _signoz.gen_ai.total_cost
+receivers:
+    otlp:
+        protocols:
+            grpc: null
+service:
+    pipelines:
+        traces:
+            exporters:
+                - otlp
+            processors:
+                - batch
+                - signozllmpricing
+            receivers:
+                - otlp

pkg/types/llmpricingruletypes/testdata/collector_with_rule.yaml

@@ -11,7 +11,6 @@ processors:
             cache_read: gen_ai.usage.cache_read.input_tokens
             cache_write: gen_ai.usage.cache_creation.input_tokens
         default_pricing:
-            unit: per_million_tokens
             rules:
                 - name: gpt-4o
                   pattern:

pkg/types/spantypes/spanmappersimulator.go

@@ -0,0 +1,186 @@
+package spantypes
+
+import (
+	"context"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/SigNoz/signoz-otel-collector/pkg/collectorsimulator"
+	"github.com/SigNoz/signoz-otel-collector/processor/signozspanmapperprocessor"
+	"github.com/SigNoz/signoz/pkg/errors"
+	"go.opentelemetry.io/collector/otelcol"
+	"go.opentelemetry.io/collector/pdata/ptrace"
+	"gopkg.in/yaml.v3"
+)
+
+var (
+	ErrCodeProcessorFactoryMapFailed  = errors.MustNewCode("processor_factory_map_failed")
+	ErrCodeSpanMapperSimulationFailed = errors.MustNewCode("span_mapper_simulation_failed")
+)
+
+const spanInputOrderAttr = "__signoz_input_idx__"
+
+func SimulateSpanMappersProcessing(ctx context.Context, groups []*SpanMapperGroupWithMappers, spans []SpanMapperTestSpan) ([]SpanMapperTestSpan, []string, error) {
+	enabled := filterEnabledGroupsWithMappers(groups)
+	if len(enabled) < 1 {
+		return spans, nil, nil
+	}
+
+	// this is done to preserve the order in which the request was sent
+	for i := range spans {
+		if spans[i].Attributes == nil {
+			spans[i].Attributes = map[string]any{}
+		}
+		spans[i].Attributes[spanInputOrderAttr] = int64(i)
+	}
+	simulatorInput := SpansToPTraces(spans)
+
+	processorFactories, err := otelcol.MakeFactoryMap(signozspanmapperprocessor.NewFactory())
+	if err != nil {
+		return nil, nil, errors.WrapInternalf(err, ErrCodeProcessorFactoryMapFailed, "could not construct processor factory map")
+	}
+
+	configGenerator := func(baseConf []byte) ([]byte, error) {
+		withProcessor, err := GenerateCollectorConfigWithSpanMapperProcessor(baseConf, enabled)
+		if err != nil {
+			return nil, err
+		}
+		return wireSpanMapperIntoTracesPipeline(withProcessor)
+	}
+
+	// signozspanmapperprocessor does no batching; spans flow through immediately.
+	timeout := 200 * time.Millisecond
+
+	outputTraces, collectorErrs, simErr := collectorsimulator.SimulateTracesProcessing(
+		ctx,
+		processorFactories,
+		configGenerator,
+		simulatorInput,
+		timeout,
+	)
+	if simErr != nil {
+		if errors.Is(simErr, collectorsimulator.ErrInvalidConfig) {
+			return nil, nil, errors.WrapInvalidInputf(simErr, errors.CodeInvalidInput, "invalid config")
+		}
+		return nil, nil, errors.WrapInternalf(simErr, ErrCodeSpanMapperSimulationFailed, "could not simulate span mapper processing")
+	}
+
+	outputSpans := PTracesToSpans(outputTraces)
+
+	sort.Slice(outputSpans, func(i, j int) bool {
+		iIdx, _ := outputSpans[i].Attributes[spanInputOrderAttr].(int64)
+		jIdx, _ := outputSpans[j].Attributes[spanInputOrderAttr].(int64)
+		return iIdx < jIdx
+	})
+	for _, s := range outputSpans {
+		delete(s.Attributes, spanInputOrderAttr)
+	}
+
+	collectorWarnAndErrorLogs := []string{}
+	for _, log := range collectorErrs {
+		if log == "" || strings.Contains(log, "featuregate.go") {
+			continue
+		}
+		collectorWarnAndErrorLogs = append(collectorWarnAndErrorLogs, log)
+	}
+
+	return outputSpans, collectorWarnAndErrorLogs, nil
+}
+
+func SpansToPTraces(spans []SpanMapperTestSpan) []ptrace.Traces {
+	result := make([]ptrace.Traces, 0, len(spans))
+	for _, s := range spans {
+		td := ptrace.NewTraces()
+		rs := td.ResourceSpans().AppendEmpty()
+		if s.Resource != nil {
+			_ = rs.Resource().Attributes().FromRaw(s.Resource)
+		}
+		sl := rs.ScopeSpans().AppendEmpty()
+		span := sl.Spans().AppendEmpty()
+		if s.Attributes != nil {
+			_ = span.Attributes().FromRaw(s.Attributes)
+		}
+		result = append(result, td)
+	}
+	return result
+}
+
+func PTracesToSpans(traces []ptrace.Traces) []SpanMapperTestSpan {
+	result := []SpanMapperTestSpan{}
+	for _, td := range traces {
+		rss := td.ResourceSpans()
+		for i := 0; i < rss.Len(); i++ {
+			rs := rss.At(i)
+			resourceAttrs := rs.Resource().Attributes().AsRaw()
+			ilss := rs.ScopeSpans()
+			for j := 0; j < ilss.Len(); j++ {
+				spans := ilss.At(j).Spans()
+				for k := 0; k < spans.Len(); k++ {
+					result = append(result, SpanMapperTestSpan{
+						Attributes: spans.At(k).Attributes().AsRaw(),
+						Resource:   resourceAttrs,
+					})
+				}
+			}
+		}
+	}
+	return result
+}
+
+// wireSpanMapperIntoTracesPipeline appends "signozspanmapper" to
+// service.pipelines.traces.processors so the processor defined by
+// GenerateCollectorConfigWithSpanMapperProcessor actually runs against the
+// traces flowing through the simulator. Idempotent: skips appending if the
+// processor name is already present.
+func wireSpanMapperIntoTracesPipeline(confYaml []byte) ([]byte, error) {
+	var conf map[string]any
+	if err := yaml.Unmarshal(confYaml, &conf); err != nil {
+		return nil, errors.Wrapf(err, errors.TypeInvalidInput, ErrCodeInvalidCollectorConfig, "failed to unmarshal collector config for pipeline wiring")
+	}
+	service, _ := conf["service"].(map[string]any)
+	if service == nil {
+		return confYaml, nil
+	}
+	pipelines, _ := service["pipelines"].(map[string]any)
+	if pipelines == nil {
+		return confYaml, nil
+	}
+	traces, _ := pipelines["traces"].(map[string]any)
+	if traces == nil {
+		return confYaml, nil
+	}
+
+	procs, _ := traces["processors"].([]any)
+	for _, p := range procs {
+		if name, ok := p.(string); ok && name == ProcessorName {
+			return confYaml, nil
+		}
+	}
+	traces["processors"] = append(procs, ProcessorName)
+
+	out, err := yaml.Marshal(conf)
+	if err != nil {
+		return nil, errors.Wrapf(err, errors.TypeInternal, ErrCodeBuildMappingProcessorConfig, "failed to marshal collector config after pipeline wiring")
+	}
+	return out, nil
+}
+
+func filterEnabledGroupsWithMappers(groups []*SpanMapperGroupWithMappers) []*SpanMapperGroupWithMappers {
+	out := make([]*SpanMapperGroupWithMappers, 0, len(groups))
+	for _, gm := range groups {
+		if gm == nil || gm.Group == nil || !gm.Group.Enabled {
+			continue
+		}
+		enabled := make([]*SpanMapper, 0, len(gm.Mappers))
+		for _, m := range gm.Mappers {
+			if m != nil && m.Enabled {
+				enabled = append(enabled, m)
+			}
+		}
+		if len(enabled) > 0 {
+			out = append(out, &SpanMapperGroupWithMappers{Group: gm.Group, Mappers: enabled})
+		}
+	}
+	return out
+}

pkg/types/spantypes/spanmappersimulator_test.go

@@ -0,0 +1,43 @@
+package spantypes
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestSimulateSpanMappersProcessing_EndToEnd is an integration test: it spins
+// up an actual in-memory otel-collector pipeline with signozspanmapperprocessor
+// and verifies the produced span has the expected target attribute.
+func TestSimulateSpanMappersProcessing_EndToEnd(t *testing.T) {
+	groups := []*SpanMapperGroupWithMappers{{
+		Group: &SpanMapperGroup{
+			Name:      "llm",
+			Condition: SpanMapperGroupCondition{Attributes: []string{"model"}},
+			Enabled:   true,
+		},
+		Mappers: []*SpanMapper{{
+			Name:         "gen_ai.request.model",
+			FieldContext: FieldContextSpanAttribute,
+			Config: SpanMapperConfig{Sources: []SpanMapperSource{
+				{Key: "llm.model", Context: FieldContextSpanAttribute, Operation: SpanMapperOperationCopy, Priority: 1},
+			}},
+			Enabled: true,
+		}},
+	}}
+
+	spans := []SpanMapperTestSpan{{Attributes: map[string]any{"llm.model": "gpt-4"}}}
+
+	out, _, err := SimulateSpanMappersProcessing(context.Background(), groups, spans)
+
+	require.NoError(t, err)
+	require.Len(t, out, 1)
+	assert.Equal(t, "gpt-4", out[0].Attributes["gen_ai.request.model"], "target attribute must be populated by the spanmapper processor")
+	// Source attribute is preserved (copy, not move).
+	assert.Equal(t, "gpt-4", out[0].Attributes["llm.model"])
+	// Order-tracking attribute is stripped from the output.
+	_, hasOrderAttr := out[0].Attributes[spanInputOrderAttr]
+	assert.False(t, hasOrderAttr, "internal ordering attribute must be removed from the response")
+}

pkg/types/spantypes/spanmappertest.go

@@ -0,0 +1,54 @@
+package spantypes
+
+import (
+	"github.com/SigNoz/signoz/pkg/valuer"
+)
+
+type SpanMapperTestSpan struct {
+	Attributes map[string]any `json:"attributes"`
+	Resource   map[string]any `json:"resource"`
+}
+
+// Mappers is optional because the module can backfill from the store by Group.Name.
+type PostableSpanMapperTestGroup struct {
+	PostableSpanMapperGroup
+	Mappers []PostableSpanMapper `json:"mappers"`
+}
+
+type PostableSpanMapperTest struct {
+	Spans  []SpanMapperTestSpan          `json:"spans"  required:"true"`
+	Groups []PostableSpanMapperTestGroup `json:"groups" required:"true"`
+}
+
+type GettableSpanMapperTest struct {
+	Spans         []SpanMapperTestSpan `json:"spans"`
+	CollectorLogs []string             `json:"collectorLogs"`
+}
+
+func NewSpanMapperGroupsWithMappersFromPostable(orgID valuer.UUID, in []PostableSpanMapperTestGroup) []*SpanMapperGroupWithMappers {
+	out := make([]*SpanMapperGroupWithMappers, 0, len(in))
+	for _, pg := range in {
+		var mappers []*SpanMapper
+		if pg.Mappers != nil {
+			mappers = make([]*SpanMapper, 0, len(pg.Mappers))
+			for _, pm := range pg.Mappers {
+				mappers = append(mappers, &SpanMapper{
+					Name:         pm.Name,
+					FieldContext: pm.FieldContext,
+					Config:       pm.Config,
+					Enabled:      pm.Enabled,
+				})
+			}
+		}
+		out = append(out, &SpanMapperGroupWithMappers{
+			Group: &SpanMapperGroup{
+				OrgID:     orgID,
+				Name:      pg.Name,
+				Condition: pg.Condition,
+				Enabled:   pg.Enabled,
+			},
+			Mappers: mappers,
+		})
+	}
+	return out
+}

pkg/types/telemetrytypes/field.go

@@ -4,7 +4,6 @@ import (
 	"fmt"
 	"strings"
 
-	"github.com/SigNoz/signoz-otel-collector/exporter/jsontypeexporter"
 	"github.com/SigNoz/signoz/pkg/valuer"
 )
 
@@ -22,7 +21,7 @@ const (
 	// BodyJSONStringSearchPrefix is the prefix used for body JSON search queries.
 	// e.g., "body.status" where "body." is the prefix.
 	BodyJSONStringSearchPrefix = "body."
-	ArraySep                   = jsontypeexporter.ArraySeparator
+	ArraySep                   = "[]."
 	ArraySepSuffix             = "[]"
 	// TODO(Piyush): Remove once we've migrated to the new array syntax.
 	ArrayAnyIndex       = "[*]."

pkg/types/telemetrytypes/json_access_plan.go

@@ -6,7 +6,6 @@ import (
 	"slices"
 	"strings"
 
-	"github.com/SigNoz/signoz-otel-collector/exporter/jsontypeexporter"
 	"github.com/SigNoz/signoz/pkg/errors"
 	"github.com/SigNoz/signoz/pkg/valuer"
 )
@@ -76,7 +75,7 @@ func (n *JSONAccessNode) Alias() string {
 	parentAlias := strings.TrimLeft(n.Parent.Alias(), "`")
 	parentAlias = strings.TrimRight(parentAlias, "`")
 
-	sep := jsontypeexporter.ArraySeparator
+	sep := "[]."
 	if n.Parent.isRoot {
 		sep = "."
 	}

tests/integration/testdata/inframonitoring/daemonsets_missing_metrics.jsonl

@@ -1,3 +0,0 @@
-{"metric_name":"k8s.pod.cpu.usage","labels":{"k8s.pod.uid":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.daemonset.name":"miss-ds","k8s.node.name":"node-x","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"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":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.daemonset.name":"miss-ds","k8s.node.name":"node-x","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"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":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.daemonset.name":"miss-ds","k8s.node.name":"node-x","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:04:00+00:00","value":0.5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}

tests/integration/testdata/inframonitoring/statefulsets_missing_metrics.jsonl

@@ -1,3 +0,0 @@
-{"metric_name":"k8s.pod.cpu.usage","labels":{"k8s.pod.uid":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.statefulset.name":"miss-ss","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"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":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.statefulset.name":"miss-ss","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"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":"miss-p1-uid","k8s.pod.name":"miss-p1","k8s.statefulset.name":"miss-ss","k8s.namespace.name":"ns-miss","k8s.cluster.name":"cluster-x"},"timestamp":"2025-01-10T10:04:00+00:00","value":0.5,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}

tests/integration/testdata/inframonitoring/volumes_formula_operand_missing.jsonl

@@ -0,0 +1,12 @@
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 100000000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 100000000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.capacity", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 100000000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 1000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 1000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 1000000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 800000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 800000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.free", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 800000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:00:00+00:00", "value": 200000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:02:00+00:00", "value": 200000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}
+{"metric_name": "k8s.volume.inodes.used", "labels": {"k8s.persistentvolumeclaim.name": "fop-pvc", "k8s.pod.uid": "fop-pvc-uid", "k8s.pod.name": "pod-fop-pvc", "k8s.namespace.name": "ns-acc", "k8s.node.name": "node-x", "k8s.cluster.name": "cluster-x", "k8s.statefulset.name": "ss-x"}, "timestamp": "2025-01-10T10:04:00+00:00", "value": 200000.0, "temporality": "Unspecified", "type_": "Gauge", "is_monotonic": false}

tests/integration/testdata/inframonitoring/volumes_missing_metrics.jsonl

@@ -1,3 +0,0 @@
-{"metric_name":"k8s.volume.available","labels":{"k8s.persistentvolumeclaim.name":"miss-pvc","k8s.pod.uid":"pod-x-uid","k8s.pod.name":"pod-x","k8s.namespace.name":"ns-x","k8s.node.name":"node-x","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"ss-x"},"timestamp":"2025-01-10T10:00:00+00:00","value":1000000000.0,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
-{"metric_name":"k8s.volume.available","labels":{"k8s.persistentvolumeclaim.name":"miss-pvc","k8s.pod.uid":"pod-x-uid","k8s.pod.name":"pod-x","k8s.namespace.name":"ns-x","k8s.node.name":"node-x","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"ss-x"},"timestamp":"2025-01-10T10:02:00+00:00","value":1000000000.0,"temporality":"Unspecified","type_":"Gauge","is_monotonic":false}
-{"metric_name":"k8s.volume.available","labels":{"k8s.persistentvolumeclaim.name":"miss-pvc","k8s.pod.uid":"pod-x-uid","k8s.pod.name":"pod-x","k8s.namespace.name":"ns-x","k8s.node.name":"node-x","k8s.cluster.name":"cluster-x","k8s.statefulset.name":"ss-x"},"timestamp":"2025-01-10T10:04:00+00:00","value":1000000000.0,"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 +80,81 @@ 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",
+        ),
+    ],
+)
+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 surfacing a "never been
+    received" warning while present metrics still return data."""
     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/02_pods.py

@@ -11,26 +11,11 @@ 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
 from fixtures.time import parse_timestamp
 
 ENDPOINT = "/api/v2/infra_monitoring/pods"
 
-# Required metrics for the v2 pods endpoint
-# (pkg/modules/inframonitoring/implinframonitoring/pods_constants.go:24-32).
-REQUIRED_METRICS = {
-    "k8s.pod.cpu.usage",
-    "k8s.pod.cpu_request_utilization",
-    "k8s.pod.cpu_limit_utilization",
-    "k8s.pod.memory.working_set",
-    "k8s.pod.memory_request_utilization",
-    "k8s.pod.memory_limit_utilization",
-    "k8s.pod.phase",
-}
-
-# Numeric values emitted by the k8s.pod.phase metric (OTel kubeletstatsreceiver).
-PHASE_NUM = {"pending": 1, "running": 2, "succeeded": 3, "failed": 4, "unknown": 5}
-
 # Placeholder in JSONL labels that gets substituted with a runtime ISO string.
 START_TIME_PLACEHOLDER = "__START_TIME__"
 
@@ -116,7 +101,8 @@ def test_pods_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["meta"]["k8s.pod.name"] for r in data["records"]} == set(exp_by_name.keys())
 
@@ -162,42 +148,91 @@ def test_pods_accuracy(
         assert record["podAge"] == expected_age_ms, f"{pod_name}.podAge: got {record['podAge']}, expected {expected_age_ms}"
 
 
-def test_pods_missing_metrics(
+@pytest.mark.parametrize(
+    "case",
+    [
+        # Scenario 1: required metrics were never ingested. Post-#11754 the querier
+        # drops them (no hard error), so the endpoint returns 200 with the pod that
+        # DOES have data; never-seen columns are the -1 sentinel and a
+        # "have never been received" warning is surfaced. Pods has no formulas, so
+        # each missing metric maps straight to one -1 column.
+        pytest.param(
+            {
+                "dataset": "pods_missing_metrics.jsonl",  # seeds only k8s.pod.cpu.usage
+                "body": {"filter": {"expression": "k8s.pod.name = 'miss-p1'"}},
+                "warn_substrings": ["never been received"],
+                "warn_names": [
+                    "k8s.pod.cpu_request_utilization",
+                    "k8s.pod.cpu_limit_utilization",
+                    "k8s.pod.memory.working_set",
+                    "k8s.pod.memory_request_utilization",
+                    "k8s.pod.memory_limit_utilization",
+                ],
+                # podCPU derives from the present k8s.pod.cpu.usage; the rest from
+                # never-seen metrics -> -1 sentinel.
+                "data_fields": ["podCPU"],
+                "no_data_fields": [
+                    "podCPURequest",
+                    "podCPULimit",
+                    "podMemory",
+                    "podMemoryRequest",
+                    "podMemoryLimit",
+                ],
+            },
+            id="metric_never_seen",
+        ),
+    ],
+)
+def test_pods_warnings(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token,
     insert_metrics,
+    case: dict,
 ) -> None:
-    """Seed only k8s.pod.cpu.usage; assert other 6 required metrics flagged missing.
-
-    The endpoint short-circuits and returns empty records + total=0 when any
-    required metric is missing (module.go:192-197).
-    """
+    """A never-ingested metric surfaces a non-blocking warning (200 + data), not a
+    hard error: the endpoint returns the entity that DOES have data and the
+    never-seen columns carry the -1 sentinel. (The generic never-seen
+    (metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
+    once, for hosts, in 01_hosts.py.)"""
     now = datetime.now(tz=UTC).replace(microsecond=0)
     insert_metrics(
         _load_pods_metrics(
-            "inframonitoring/pods_missing_metrics.jsonl",
+            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, response.text
     data = response.json()["data"]
+    warnings = get_all_warnings(response.json())
 
-    assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
-    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/03_nodes.py

@@ -11,24 +11,10 @@ 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/nodes"
 
-# Required metrics for the v2 nodes endpoint
-# (pkg/modules/inframonitoring/implinframonitoring/nodes_constants.go:22-29).
-REQUIRED_METRICS = {
-    "k8s.node.cpu.usage",
-    "k8s.node.allocatable_cpu",
-    "k8s.node.memory.working_set",
-    "k8s.node.allocatable_memory",
-    "k8s.node.condition_ready",
-    "k8s.pod.phase",
-}
-
-# Numeric values emitted by k8s.node.condition_ready.
-COND_NUM = {"ready": 1, "not_ready": 0}
-
 
 def test_nodes_accuracy(
     signoz: types.SigNoz,
@@ -71,7 +57,8 @@ def test_nodes_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["nodeName"] for r in data["records"]} == set(exp_by_name.keys())
 
@@ -107,38 +94,83 @@ def test_nodes_accuracy(
         assert record["podCountsByPhase"] == exp["podCountsByPhase"]
 
 
-def test_nodes_missing_metrics(
+@pytest.mark.parametrize(
+    "case",
+    [
+        # Scenario 1: required metrics were never ingested. Post-#11754 the querier
+        # drops them (no hard error), so the endpoint returns 200 with the node that
+        # DOES have data; never-seen columns are the -1 sentinel + a
+        # "have never been received" warning. Nodes has no formulas, so each missing
+        # metric maps straight to one -1 column.
+        pytest.param(
+            {
+                "dataset": "nodes_missing_metrics.jsonl",  # seeds only k8s.node.cpu.usage
+                "body": {"filter": {"expression": "k8s.node.name = 'miss-n1'"}},
+                "warn_substrings": ["never been received"],
+                "warn_names": [
+                    "k8s.node.allocatable_cpu",
+                    "k8s.node.memory.working_set",
+                    "k8s.node.allocatable_memory",
+                ],
+                # nodeCPU derives from the present k8s.node.cpu.usage; the rest from
+                # never-seen metrics -> -1 sentinel.
+                "data_fields": ["nodeCPU"],
+                "no_data_fields": ["nodeCPUAllocatable", "nodeMemory", "nodeMemoryAllocatable"],
+            },
+            id="metric_never_seen",
+        ),
+    ],
+)
+def test_nodes_warnings(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token,
     insert_metrics,
+    case: dict,
 ) -> None:
-    """Seed only k8s.node.cpu.usage; assert other 5 required metrics flagged missing."""
+    """A never-ingested metric surfaces a non-blocking warning (200 + data), not a
+    hard error: the endpoint returns the entity that DOES have data and the
+    never-seen columns carry the -1 sentinel. (The generic never-seen
+    (metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
+    once, for hosts, in 01_hosts.py.)"""
     now = datetime.now(tz=UTC).replace(microsecond=0)
     insert_metrics(
         Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/nodes_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, response.text
     data = response.json()["data"]
+    warnings = get_all_warnings(response.json())
 
-    assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.node.cpu.usage"})
-    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

@@ -11,18 +11,10 @@ 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/namespaces"
 
-# Required metrics for the v2 namespaces endpoint
-# (pkg/modules/inframonitoring/implinframonitoring/namespaces_constants.go:22-26).
-REQUIRED_METRICS = {
-    "k8s.pod.cpu.usage",
-    "k8s.pod.memory.working_set",
-    "k8s.pod.phase",
-}
-
 
 def test_namespaces_accuracy(
     signoz: types.SigNoz,
@@ -71,7 +63,8 @@ def test_namespaces_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["namespaceName"] for r in data["records"]} == set(exp_by_name.keys())
 
@@ -99,38 +92,79 @@ def test_namespaces_accuracy(
         assert record["podCountsByPhase"] == exp["podCountsByPhase"]
 
 
-def test_namespaces_missing_metrics(
+@pytest.mark.parametrize(
+    "case",
+    [
+        # Scenario 1: a required metric was never ingested. Post-#11754 the querier
+        # drops it (no hard error), so the endpoint returns 200 with the namespace
+        # that DOES have data; the never-seen column is the -1 sentinel + a
+        # "have never been received" warning. Namespaces has no formulas (2 columns:
+        # namespaceCPU=A, namespaceMemory=D). Default groupBy is two keys
+        # [k8s.namespace.name, k8s.cluster.name]; the seed carries both so the
+        # page-groups IN-filter parses.
+        pytest.param(
+            {
+                "dataset": "namespaces_missing_metrics.jsonl",  # seeds only k8s.pod.cpu.usage
+                "body": {"filter": {"expression": "k8s.namespace.name = 'miss-ns'"}},
+                "warn_substrings": ["never been received", "k8s.pod.memory.working_set"],
+                "warn_names": [],
+                "data_fields": ["namespaceCPU"],
+                "no_data_fields": ["namespaceMemory"],
+            },
+            id="metric_never_seen",
+        ),
+    ],
+)
+def test_namespaces_warnings(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token,
     insert_metrics,
+    case: dict,
 ) -> None:
-    """Seed only k8s.pod.cpu.usage; assert other 2 required metrics flagged missing."""
+    """A never-ingested metric surfaces a non-blocking warning (200 + data), not a
+    hard error: the endpoint returns the entity that DOES have data and the
+    never-seen columns carry the -1 sentinel. (The generic never-seen
+    (metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
+    once, for hosts, in 01_hosts.py.)"""
     now = datetime.now(tz=UTC).replace(microsecond=0)
     insert_metrics(
         Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/namespaces_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, response.text
     data = response.json()["data"]
+    warnings = get_all_warnings(response.json())
 
-    assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
-    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/05_clusters.py

@@ -11,21 +11,10 @@ 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/clusters"
 
-# Required metrics for the v2 clusters endpoint
-# (pkg/modules/inframonitoring/implinframonitoring/clusters_constants.go:23-30).
-REQUIRED_METRICS = {
-    "k8s.node.cpu.usage",
-    "k8s.node.allocatable_cpu",
-    "k8s.node.memory.working_set",
-    "k8s.node.allocatable_memory",
-    "k8s.node.condition_ready",
-    "k8s.pod.phase",
-}
-
 
 def test_clusters_accuracy(
     signoz: types.SigNoz,
@@ -74,7 +63,8 @@ def test_clusters_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["clusterName"] for r in data["records"]} == set(exp_by_name.keys())
 
@@ -113,38 +103,82 @@ def test_clusters_accuracy(
         assert record["podCountsByPhase"] == exp["podCountsByPhase"]
 
 
-def test_clusters_missing_metrics(
+@pytest.mark.parametrize(
+    "case",
+    [
+        # Scenario 1: a required metric was never ingested. Post-#11754 the querier
+        # drops it (no hard error), so the endpoint returns 200 with the cluster
+        # that DOES have data; never-seen columns are the -1 sentinel + a
+        # "have never been received" warning. Clusters has no formulas
+        # (clusterCPU=A, clusterCPUAllocatable=B, clusterMemory=C,
+        # clusterMemoryAllocatable=D).
+        pytest.param(
+            {
+                "dataset": "clusters_missing_metrics.jsonl",  # seeds only k8s.node.cpu.usage
+                "body": {"filter": {"expression": "k8s.cluster.name = 'miss-cluster'"}},
+                "warn_substrings": ["never been received"],
+                "warn_names": [
+                    "k8s.node.allocatable_cpu",
+                    "k8s.node.memory.working_set",
+                    "k8s.node.allocatable_memory",
+                ],
+                "data_fields": ["clusterCPU"],
+                "no_data_fields": ["clusterCPUAllocatable", "clusterMemory", "clusterMemoryAllocatable"],
+            },
+            id="metric_never_seen",
+        ),
+    ],
+)
+def test_clusters_warnings(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token,
     insert_metrics,
+    case: dict,
 ) -> None:
-    """Seed only k8s.node.cpu.usage; assert other 5 required metrics flagged missing."""
+    """A never-ingested metric surfaces a non-blocking warning (200 + data), not a
+    hard error: the endpoint returns the entity that DOES have data and the
+    never-seen columns carry the -1 sentinel. (The generic never-seen
+    (metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
+    once, for hosts, in 01_hosts.py.)"""
     now = datetime.now(tz=UTC).replace(microsecond=0)
     insert_metrics(
         Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/clusters_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, response.text
     data = response.json()["data"]
+    warnings = get_all_warnings(response.json())
 
-    assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.node.cpu.usage"})
-    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/06_volumes.py

@@ -11,20 +11,10 @@ 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/pvcs"
 
-# Required metrics for the v2 volumes endpoint
-# (pkg/modules/inframonitoring/implinframonitoring/volumes_constants.go:20-27).
-REQUIRED_METRICS = {
-    "k8s.volume.available",
-    "k8s.volume.capacity",
-    "k8s.volume.inodes",
-    "k8s.volume.inodes.free",
-    "k8s.volume.inodes.used",
-}
-
 
 def test_volumes_accuracy(
     signoz: types.SigNoz,
@@ -71,7 +61,8 @@ def test_volumes_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["persistentVolumeClaimName"] for r in data["records"]} == set(exp_by_name.keys())
 
@@ -117,38 +108,81 @@ def test_volumes_accuracy(
             assert compare_values(record[field], exp[field], 1e-6), f"{record['persistentVolumeClaimName']}.{field}: got {record[field]}, expected {exp[field]}"
 
 
-def test_volumes_missing_metrics(
+@pytest.mark.parametrize(
+    "case",
+    [
+        # Scenario 1: a metric was never ingested. Post-#11754 the querier drops it
+        # (no hard error), so the endpoint returns 200 with whatever flowed; the
+        # never-seen column is the -1 sentinel + a "have never been received"
+        # warning. Here we omit the FORMULA OPERAND k8s.volume.available
+        # (volumeUsage = capacity - available): since A uses TimeAggregationAvg it is
+        # NOT zero-defaultable, so the formula drops the group -> volumeUsage == -1
+        # (it does NOT fall back to capacity). capacity + inodes stay real.
+        pytest.param(
+            {
+                "dataset": "volumes_formula_operand_missing.jsonl",
+                "body": {"filter": {"expression": "k8s.persistentvolumeclaim.name = 'fop-pvc'"}},
+                "warn_substrings": ["never been received", "k8s.volume.available"],
+                "warn_names": [],
+                "data_fields": ["volumeCapacity", "volumeInodes", "volumeInodesFree", "volumeInodesUsed"],
+                "no_data_fields": ["volumeAvailable", "volumeUsage"],
+            },
+            id="metric_never_seen",
+        ),
+    ],
+)
+def test_volumes_warnings(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token,
     insert_metrics,
+    case: dict,
 ) -> None:
-    """Seed only k8s.volume.available; other 4 required metrics flagged missing."""
+    """A never-ingested metric surfaces a non-blocking warning (200 + data), not a
+    hard error. Here the never-seen metric is the FORMULA OPERAND
+    k8s.volume.available (volumeUsage = capacity - available): since A uses
+    TimeAggregationAvg it is NOT zero-defaultable, so the formula drops the group
+    -> volumeUsage == -1 (it does NOT fall back to capacity); capacity + inodes
+    stay real. (The generic never-seen (metric, key)-pair-via-groupBy warning is
+    entity-agnostic and is exercised once, for hosts, in 01_hosts.py.)"""
     now = datetime.now(tz=UTC).replace(microsecond=0)
     insert_metrics(
         Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/volumes_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, response.text
     data = response.json()["data"]
+    warnings = get_all_warnings(response.json())
 
-    assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.volume.available"})
-    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/07_deployments.py

@@ -11,24 +11,10 @@ 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/deployments"
 
-# Required metrics for the v2 deployments endpoint
-# (pkg/modules/inframonitoring/implinframonitoring/deployments_constants.go:24-34).
-REQUIRED_METRICS = {
-    "k8s.pod.phase",
-    "k8s.pod.cpu.usage",
-    "k8s.pod.cpu_request_utilization",
-    "k8s.pod.cpu_limit_utilization",
-    "k8s.pod.memory.working_set",
-    "k8s.pod.memory_request_utilization",
-    "k8s.pod.memory_limit_utilization",
-    "k8s.deployment.desired",
-    "k8s.deployment.available",
-}
-
 
 def test_deployments_accuracy(
     signoz: types.SigNoz,
@@ -75,7 +61,8 @@ def test_deployments_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["deploymentName"] for r in data["records"]} == set(exp_by_name.keys())
 
@@ -123,38 +110,89 @@ def test_deployments_accuracy(
         assert record["podCountsByPhase"] == exp["podCountsByPhase"]
 
 
-def test_deployments_missing_metrics(
+@pytest.mark.parametrize(
+    "case",
+    [
+        # Scenario 1: required metrics were never ingested. Post-#11754 the querier
+        # drops them (no hard error), so the endpoint returns 200 with the deployment
+        # that DOES have data; never-seen columns are the -1 sentinel + a
+        # "have never been received" warning. No formulas; pod- and deployment-level
+        # metrics each map to one column.
+        pytest.param(
+            {
+                "dataset": "deployments_missing_metrics.jsonl",  # seeds only k8s.pod.cpu.usage
+                "body": {"filter": {"expression": "k8s.deployment.name = 'miss-dep'"}},
+                "warn_substrings": ["never been received"],
+                "warn_names": [
+                    "k8s.pod.memory.working_set",
+                    "k8s.deployment.desired",
+                    "k8s.deployment.available",
+                ],
+                "data_fields": ["deploymentCPU"],
+                "no_data_fields": [
+                    "deploymentCPURequest",
+                    "deploymentCPULimit",
+                    "deploymentMemory",
+                    "deploymentMemoryRequest",
+                    "deploymentMemoryLimit",
+                    "desiredPods",
+                    "availablePods",
+                ],
+            },
+            id="metric_never_seen",
+        ),
+    ],
+)
+def test_deployments_warnings(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token,
     insert_metrics,
+    case: dict,
 ) -> None:
-    """Seed only k8s.pod.cpu.usage; assert other 8 required metrics flagged missing."""
+    """A never-ingested metric surfaces a non-blocking warning (200 + data), not a
+    hard error: the endpoint returns the entity that DOES have data and the
+    never-seen columns carry the -1 sentinel. (The generic never-seen
+    (metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
+    once, for hosts, in 01_hosts.py.)"""
     now = datetime.now(tz=UTC).replace(microsecond=0)
     insert_metrics(
         Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/deployments_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, response.text
     data = response.json()["data"]
+    warnings = get_all_warnings(response.json())
 
-    assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
-    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/08_statefulsets.py

@@ -11,24 +11,10 @@ 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/statefulsets"
 
-# Required metrics for the v2 statefulsets endpoint
-# (pkg/modules/inframonitoring/implinframonitoring/statefulsets_constants.go:24-34).
-REQUIRED_METRICS = {
-    "k8s.pod.phase",
-    "k8s.pod.cpu.usage",
-    "k8s.pod.cpu_request_utilization",
-    "k8s.pod.cpu_limit_utilization",
-    "k8s.pod.memory.working_set",
-    "k8s.pod.memory_request_utilization",
-    "k8s.pod.memory_limit_utilization",
-    "k8s.statefulset.desired_pods",
-    "k8s.statefulset.current_pods",
-}
-
 
 def test_statefulsets_accuracy(
     signoz: types.SigNoz,
@@ -75,7 +61,8 @@ def test_statefulsets_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["statefulSetName"] for r in data["records"]} == set(exp_by_name.keys())
 
@@ -123,40 +110,6 @@ def test_statefulsets_accuracy(
         assert record["podCountsByPhase"] == exp["podCountsByPhase"]
 
 
-def test_statefulsets_missing_metrics(
-    signoz: types.SigNoz,
-    create_user_admin: None,  # pylint: disable=unused-argument
-    get_token,
-    insert_metrics,
-) -> None:
-    """Seed only k8s.pod.cpu.usage; assert other 8 required metrics flagged missing."""
-    now = datetime.now(tz=UTC).replace(microsecond=0)
-    insert_metrics(
-        Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/statefulsets_missing_metrics.jsonl"),
-            base_time=now - timedelta(minutes=4),
-        )
-    )
-
-    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,
-        },
-        timeout=5,
-    )
-    assert response.status_code == HTTPStatus.OK, response.text
-    data = response.json()["data"]
-
-    assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
-    assert data["records"] == []
-    assert data["total"] == 0
-
-
 @pytest.mark.parametrize(
     "expression,expected",
     [

tests/integration/tests/inframonitoring/09_jobs.py

@@ -11,26 +11,10 @@ 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/jobs"
 
-# Required metrics for the v2 jobs endpoint
-# (pkg/modules/inframonitoring/implinframonitoring/jobs_constants.go:24-36).
-REQUIRED_METRICS = {
-    "k8s.pod.phase",
-    "k8s.pod.cpu.usage",
-    "k8s.pod.cpu_request_utilization",
-    "k8s.pod.cpu_limit_utilization",
-    "k8s.pod.memory.working_set",
-    "k8s.pod.memory_request_utilization",
-    "k8s.pod.memory_limit_utilization",
-    "k8s.job.active_pods",
-    "k8s.job.failed_pods",
-    "k8s.job.successful_pods",
-    "k8s.job.desired_successful_pods",
-}
-
 
 def test_jobs_accuracy(
     signoz: types.SigNoz,
@@ -78,7 +62,8 @@ def test_jobs_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["jobName"] for r in data["records"]} == set(exp_by_name.keys())
 
@@ -128,38 +113,91 @@ def test_jobs_accuracy(
         assert record["podCountsByPhase"] == exp["podCountsByPhase"]
 
 
-def test_jobs_missing_metrics(
+@pytest.mark.parametrize(
+    "case",
+    [
+        # Scenario 1: required metrics were never ingested. Post-#11754 the querier
+        # drops them (no hard error), so the endpoint returns 200 with the job that
+        # DOES have data; never-seen columns are the -1 sentinel + a
+        # "have never been received" warning. No formulas; pod- and job-level
+        # metrics each map to one column.
+        pytest.param(
+            {
+                "dataset": "jobs_missing_metrics.jsonl",  # seeds only k8s.pod.cpu.usage
+                "body": {"filter": {"expression": "k8s.job.name = 'miss-job'"}},
+                "warn_substrings": ["never been received"],
+                "warn_names": [
+                    "k8s.pod.memory.working_set",
+                    "k8s.job.desired_successful_pods",
+                    "k8s.job.successful_pods",
+                ],
+                "data_fields": ["jobCPU"],
+                "no_data_fields": [
+                    "jobCPURequest",
+                    "jobCPULimit",
+                    "jobMemory",
+                    "jobMemoryRequest",
+                    "jobMemoryLimit",
+                    "desiredSuccessfulPods",
+                    "activePods",
+                    "failedPods",
+                    "successfulPods",
+                ],
+            },
+            id="metric_never_seen",
+        ),
+    ],
+)
+def test_jobs_warnings(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token,
     insert_metrics,
+    case: dict,
 ) -> None:
-    """Seed only k8s.pod.cpu.usage; assert other 10 required metrics flagged missing."""
+    """A never-ingested metric surfaces a non-blocking warning (200 + data), not a
+    hard error: the endpoint returns the entity that DOES have data and the
+    never-seen columns carry the -1 sentinel. (The generic never-seen
+    (metric, key)-pair-via-groupBy warning is entity-agnostic and is exercised
+    once, for hosts, in 01_hosts.py.)"""
     now = datetime.now(tz=UTC).replace(microsecond=0)
     insert_metrics(
         Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/jobs_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, response.text
     data = response.json()["data"]
+    warnings = get_all_warnings(response.json())
 
-    assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
-    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/10_daemonsets.py

@@ -11,24 +11,10 @@ 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/daemonsets"
 
-# Required metrics for the v2 daemonsets endpoint
-# (pkg/modules/inframonitoring/implinframonitoring/daemonsets_constants.go:24-34).
-REQUIRED_METRICS = {
-    "k8s.pod.phase",
-    "k8s.pod.cpu.usage",
-    "k8s.pod.cpu_request_utilization",
-    "k8s.pod.cpu_limit_utilization",
-    "k8s.pod.memory.working_set",
-    "k8s.pod.memory_request_utilization",
-    "k8s.pod.memory_limit_utilization",
-    "k8s.daemonset.desired_scheduled_nodes",
-    "k8s.daemonset.current_scheduled_nodes",
-}
-
 
 def test_daemonsets_accuracy(
     signoz: types.SigNoz,
@@ -75,7 +61,8 @@ def test_daemonsets_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["daemonSetName"] for r in data["records"]} == set(exp_by_name.keys())
 
@@ -123,40 +110,6 @@ def test_daemonsets_accuracy(
         assert record["podCountsByPhase"] == exp["podCountsByPhase"]
 
 
-def test_daemonsets_missing_metrics(
-    signoz: types.SigNoz,
-    create_user_admin: None,  # pylint: disable=unused-argument
-    get_token,
-    insert_metrics,
-) -> None:
-    """Seed only k8s.pod.cpu.usage; assert other 8 required metrics flagged missing."""
-    now = datetime.now(tz=UTC).replace(microsecond=0)
-    insert_metrics(
-        Metrics.load_from_file(
-            get_testdata_file_path("inframonitoring/daemonsets_missing_metrics.jsonl"),
-            base_time=now - timedelta(minutes=4),
-        )
-    )
-
-    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,
-        },
-        timeout=5,
-    )
-    assert response.status_code == HTTPStatus.OK, response.text
-    data = response.json()["data"]
-
-    assert set(data["requiredMetricsCheck"]["missingMetrics"]) == (REQUIRED_METRICS - {"k8s.pod.cpu.usage"})
-    assert data["records"] == []
-    assert data["total"] == 0
-
-
 @pytest.mark.parametrize(
     "expression,expected",
     [

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

@@ -15,7 +15,6 @@ from fixtures.querier import (
     build_builder_query,
     find_named_result,
     get_all_warnings,
-    get_error_message,
     index_series_by_label,
     make_query_request,
 )

tests/integration/tests/spanmapper/01_span_mapper.py

@@ -0,0 +1,174 @@
+from collections.abc import Callable
+from http import HTTPStatus
+
+import requests
+
+from fixtures import types
+from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
+
+GROUPS_PATH = "/api/v1/span_mapper_groups"
+
+
+def _auth_headers(token: str) -> dict[str, str]:
+    return {
+        "authorization": f"Bearer {token}",
+        "content-type": "application/json",
+    }
+
+
+def test_create_groups_and_simulate_with_backfill(
+    signoz: types.SigNoz,
+    create_user_admin: types.Operation,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+) -> None:
+    """
+    Setup:
+    Create a mapping group and a mapper through the CRUD API, then hit the
+    simulate endpoint with two groups: the saved one referenced by name only
+    (server backfills its mappers from the store) and a second, unsaved group
+    sent with inline mappers.
+
+    Tests:
+    1. Create a group (POST /span_mapper_groups) and read back its id
+    2. Create a mapper in that group (POST .../{groupId}/span_mappers)
+    3. List groups and mappers and verify what we created is persisted
+    4. Simulate spans against both groups: a matching span gets the saved
+       group's mappers (backfilled, copy) and the inline group's mappers
+       (move) applied, while a span matching no condition passes through
+    5. Delete the group and verify it (and its mappers) are gone
+    """
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+
+    create_group = requests.post(
+        signoz.self.host_configs["8080"].get(GROUPS_PATH),
+        timeout=10,
+        headers=_auth_headers(token),
+        json={
+            "name": "llm-backfill",
+            "condition": {"attributes": ["model"], "resource": []},
+            "enabled": True,
+        },
+    )
+
+    assert create_group.status_code == HTTPStatus.CREATED
+    group = create_group.json()["data"]
+    group_id = group["id"]
+    assert group["name"] == "llm-backfill"
+    assert group["enabled"] is True
+
+    create_mapper = requests.post(
+        signoz.self.host_configs["8080"].get(f"{GROUPS_PATH}/{group_id}/span_mappers"),
+        timeout=10,
+        headers=_auth_headers(token),
+        json={
+            "name": "gen_ai.request.model",
+            "fieldContext": "attribute",
+            "config": {
+                "sources": [
+                    {
+                        "key": "llm.model",
+                        "context": "attribute",
+                        "operation": "copy",
+                        "priority": 1,
+                    }
+                ]
+            },
+            "enabled": True,
+        },
+    )
+
+    assert create_mapper.status_code == HTTPStatus.CREATED
+    mapper = create_mapper.json()["data"]
+    assert mapper["name"] == "gen_ai.request.model"
+    assert mapper["group_id"] == group_id
+
+    list_groups = requests.get(
+        signoz.self.host_configs["8080"].get(GROUPS_PATH),
+        timeout=10,
+        headers=_auth_headers(token),
+    )
+    assert list_groups.status_code == HTTPStatus.OK
+    assert group_id in [g["id"] for g in list_groups.json()["data"]["items"]]
+
+    list_mappers = requests.get(
+        signoz.self.host_configs["8080"].get(f"{GROUPS_PATH}/{group_id}/span_mappers"),
+        timeout=10,
+        headers=_auth_headers(token),
+    )
+    assert list_mappers.status_code == HTTPStatus.OK
+    assert "gen_ai.request.model" in [m["name"] for m in list_mappers.json()["data"]["items"]]
+
+    simulate = requests.post(
+        signoz.self.host_configs["8080"].get(f"{GROUPS_PATH}/test"),
+        timeout=10,
+        headers=_auth_headers(token),
+        json={
+            "spans": [
+                {
+                    "attributes": {"llm.model": "gpt-4", "db.system": "postgres"},
+                    "resource": {},
+                },
+                # Matches no group condition, so it must pass through untouched.
+                {
+                    "attributes": {"http.method": "GET"},
+                    "resource": {},
+                },
+            ],
+            "groups": [
+                # No "mappers" key: the server backfills them from the saved group.
+                {
+                    "name": "llm-backfill",
+                    "condition": {"attributes": ["model"], "resource": []},
+                    "enabled": True,
+                },
+                # Unsaved group; mappers provided inline.
+                {
+                    "name": "db-inline",
+                    "condition": {"attributes": ["db"], "resource": []},
+                    "enabled": True,
+                    "mappers": [
+                        {
+                            "name": "db.name",
+                            "fieldContext": "attribute",
+                            "config": {
+                                "sources": [
+                                    {
+                                        "key": "db.system",
+                                        "context": "attribute",
+                                        "operation": "move",
+                                        "priority": 1,
+                                    }
+                                ]
+                            },
+                            "enabled": True,
+                        }
+                    ],
+                },
+            ],
+        },
+    )
+
+    assert simulate.status_code == HTTPStatus.OK
+    out_spans = simulate.json()["data"]["spans"]
+    assert len(out_spans) == 2
+    attrs = out_spans[0]["attributes"]
+    assert attrs["gen_ai.request.model"] == "gpt-4"  # backfilled mapper applied
+    assert attrs["llm.model"] == "gpt-4"  # copy preserves source
+    assert attrs["db.name"] == "postgres"  # inline mapper applied
+    assert "db.system" not in attrs  # move removes source
+    assert out_spans[1]["attributes"] == {"http.method": "GET"}  # unchanged
+
+    delete_group = requests.delete(
+        signoz.self.host_configs["8080"].get(f"{GROUPS_PATH}/{group_id}"),
+        timeout=10,
+        headers=_auth_headers(token),
+    )
+    assert delete_group.status_code == HTTPStatus.NO_CONTENT
+
+    list_after_delete = requests.get(
+        signoz.self.host_configs["8080"].get(GROUPS_PATH),
+        timeout=10,
+        headers=_auth_headers(token),
+    )
+    assert list_after_delete.status_code == HTTPStatus.OK
+    assert group_id not in [g["id"] for g in list_after_delete.json()["data"]["items"]]