fix: draft

docs/api/openapi.yml

@@ -2519,65 +2519,6 @@ components:
         enabled:
           type: boolean
       type: object
-    InframonitoringtypesClusterRecord:
-      properties:
-        clusterCPU:
-          format: double
-          type: number
-        clusterCPUAllocatable:
-          format: double
-          type: number
-        clusterMemory:
-          format: double
-          type: number
-        clusterMemoryAllocatable:
-          format: double
-          type: number
-        clusterName:
-          type: string
-        meta:
-          additionalProperties:
-            type: string
-          nullable: true
-          type: object
-        nodeCountsByReadiness:
-          $ref: '#/components/schemas/InframonitoringtypesNodeCountsByReadiness'
-        podCountsByPhase:
-          $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
-      required:
-      - clusterName
-      - clusterCPU
-      - clusterCPUAllocatable
-      - clusterMemory
-      - clusterMemoryAllocatable
-      - nodeCountsByReadiness
-      - podCountsByPhase
-      - meta
-      type: object
-    InframonitoringtypesClusters:
-      properties:
-        endTimeBeforeRetention:
-          type: boolean
-        records:
-          items:
-            $ref: '#/components/schemas/InframonitoringtypesClusterRecord'
-          nullable: true
-          type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
-        total:
-          type: integer
-        type:
-          $ref: '#/components/schemas/InframonitoringtypesResponseType'
-        warning:
-          $ref: '#/components/schemas/Querybuildertypesv5QueryWarnData'
-      required:
-      - type
-      - records
-      - total
-      - requiredMetricsCheck
-      - endTimeBeforeRetention
-      type: object
     InframonitoringtypesHostFilter:
       properties:
         expression:
@@ -2606,8 +2547,7 @@ components:
           format: double
           type: number
         meta:
-          additionalProperties:
-            type: string
+          additionalProperties: {}
           nullable: true
           type: object
         status:
@@ -2657,151 +2597,6 @@ components:
       - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
-    InframonitoringtypesNamespaceRecord:
-      properties:
-        meta:
-          additionalProperties:
-            type: string
-          nullable: true
-          type: object
-        namespaceCPU:
-          format: double
-          type: number
-        namespaceMemory:
-          format: double
-          type: number
-        namespaceName:
-          type: string
-        podCountsByPhase:
-          $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
-      required:
-      - namespaceName
-      - namespaceCPU
-      - namespaceMemory
-      - podCountsByPhase
-      - meta
-      type: object
-    InframonitoringtypesNamespaces:
-      properties:
-        endTimeBeforeRetention:
-          type: boolean
-        records:
-          items:
-            $ref: '#/components/schemas/InframonitoringtypesNamespaceRecord'
-          nullable: true
-          type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
-        total:
-          type: integer
-        type:
-          $ref: '#/components/schemas/InframonitoringtypesResponseType'
-        warning:
-          $ref: '#/components/schemas/Querybuildertypesv5QueryWarnData'
-      required:
-      - type
-      - records
-      - total
-      - requiredMetricsCheck
-      - endTimeBeforeRetention
-      type: object
-    InframonitoringtypesNodeCondition:
-      enum:
-      - ready
-      - not_ready
-      - no_data
-      type: string
-    InframonitoringtypesNodeCountsByReadiness:
-      properties:
-        notReady:
-          type: integer
-        ready:
-          type: integer
-      required:
-      - ready
-      - notReady
-      type: object
-    InframonitoringtypesNodeRecord:
-      properties:
-        condition:
-          $ref: '#/components/schemas/InframonitoringtypesNodeCondition'
-        meta:
-          additionalProperties:
-            type: string
-          nullable: true
-          type: object
-        nodeCPU:
-          format: double
-          type: number
-        nodeCPUAllocatable:
-          format: double
-          type: number
-        nodeCountsByReadiness:
-          $ref: '#/components/schemas/InframonitoringtypesNodeCountsByReadiness'
-        nodeMemory:
-          format: double
-          type: number
-        nodeMemoryAllocatable:
-          format: double
-          type: number
-        nodeName:
-          type: string
-        podCountsByPhase:
-          $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
-      required:
-      - nodeName
-      - condition
-      - nodeCountsByReadiness
-      - podCountsByPhase
-      - nodeCPU
-      - nodeCPUAllocatable
-      - nodeMemory
-      - nodeMemoryAllocatable
-      - meta
-      type: object
-    InframonitoringtypesNodes:
-      properties:
-        endTimeBeforeRetention:
-          type: boolean
-        records:
-          items:
-            $ref: '#/components/schemas/InframonitoringtypesNodeRecord'
-          nullable: true
-          type: array
-        requiredMetricsCheck:
-          $ref: '#/components/schemas/InframonitoringtypesRequiredMetricsCheck'
-        total:
-          type: integer
-        type:
-          $ref: '#/components/schemas/InframonitoringtypesResponseType'
-        warning:
-          $ref: '#/components/schemas/Querybuildertypesv5QueryWarnData'
-      required:
-      - type
-      - records
-      - total
-      - requiredMetricsCheck
-      - endTimeBeforeRetention
-      type: object
-    InframonitoringtypesPodCountsByPhase:
-      properties:
-        failed:
-          type: integer
-        pending:
-          type: integer
-        running:
-          type: integer
-        succeeded:
-          type: integer
-        unknown:
-          type: integer
-      required:
-      - pending
-      - running
-      - succeeded
-      - failed
-      - unknown
-      type: object
     InframonitoringtypesPodPhase:
       enum:
       - pending
@@ -2809,15 +2604,18 @@ components:
       - succeeded
       - failed
       - unknown
-      - no_data
+      - ""
       type: string
     InframonitoringtypesPodRecord:
       properties:
+        failedPodCount:
+          type: integer
         meta:
-          additionalProperties:
-            type: string
+          additionalProperties: {}
           nullable: true
           type: object
+        pendingPodCount:
+          type: integer
         podAge:
           format: int64
           type: integer
@@ -2830,8 +2628,6 @@ components:
         podCPURequest:
           format: double
           type: number
-        podCountsByPhase:
-          $ref: '#/components/schemas/InframonitoringtypesPodCountsByPhase'
         podMemory:
           format: double
           type: number
@@ -2845,6 +2641,12 @@ components:
           $ref: '#/components/schemas/InframonitoringtypesPodPhase'
         podUID:
           type: string
+        runningPodCount:
+          type: integer
+        succeededPodCount:
+          type: integer
+        unknownPodCount:
+          type: integer
       required:
       - podUID
       - podCPU
@@ -2854,7 +2656,11 @@ components:
       - podMemoryRequest
       - podMemoryLimit
       - podPhase
-      - podCountsByPhase
+      - pendingPodCount
+      - runningPodCount
+      - succeededPodCount
+      - failedPodCount
+      - unknownPodCount
       - podAge
       - meta
       type: object
@@ -2882,32 +2688,6 @@ components:
       - requiredMetricsCheck
       - endTimeBeforeRetention
       type: object
-    InframonitoringtypesPostableClusters:
-      properties:
-        end:
-          format: int64
-          type: integer
-        filter:
-          $ref: '#/components/schemas/Querybuildertypesv5Filter'
-        groupBy:
-          items:
-            $ref: '#/components/schemas/Querybuildertypesv5GroupByKey'
-          nullable: true
-          type: array
-        limit:
-          type: integer
-        offset:
-          type: integer
-        orderBy:
-          $ref: '#/components/schemas/Querybuildertypesv5OrderBy'
-        start:
-          format: int64
-          type: integer
-      required:
-      - start
-      - end
-      - limit
-      type: object
     InframonitoringtypesPostableHosts:
       properties:
         end:
@@ -2934,58 +2714,6 @@ components:
       - end
       - limit
       type: object
-    InframonitoringtypesPostableNamespaces:
-      properties:
-        end:
-          format: int64
-          type: integer
-        filter:
-          $ref: '#/components/schemas/Querybuildertypesv5Filter'
-        groupBy:
-          items:
-            $ref: '#/components/schemas/Querybuildertypesv5GroupByKey'
-          nullable: true
-          type: array
-        limit:
-          type: integer
-        offset:
-          type: integer
-        orderBy:
-          $ref: '#/components/schemas/Querybuildertypesv5OrderBy'
-        start:
-          format: int64
-          type: integer
-      required:
-      - start
-      - end
-      - limit
-      type: object
-    InframonitoringtypesPostableNodes:
-      properties:
-        end:
-          format: int64
-          type: integer
-        filter:
-          $ref: '#/components/schemas/Querybuildertypesv5Filter'
-        groupBy:
-          items:
-            $ref: '#/components/schemas/Querybuildertypesv5GroupByKey'
-          nullable: true
-          type: array
-        limit:
-          type: integer
-        offset:
-          type: integer
-        orderBy:
-          $ref: '#/components/schemas/Querybuildertypesv5OrderBy'
-        start:
-          format: int64
-          type: integer
-      required:
-      - start
-      - end
-      - limit
-      type: object
     InframonitoringtypesPostablePods:
       properties:
         end:
@@ -11822,77 +11550,6 @@ paths:
       summary: Health check
       tags:
       - health
-  /api/v2/infra_monitoring/clusters:
-    post:
-      deprecated: false
-      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.'
-      operationId: ListClusters
-      requestBody:
-        content:
-          application/json:
-            schema:
-              $ref: '#/components/schemas/InframonitoringtypesPostableClusters'
-      responses:
-        "200":
-          content:
-            application/json:
-              schema:
-                properties:
-                  data:
-                    $ref: '#/components/schemas/InframonitoringtypesClusters'
-                  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
-        "500":
-          content:
-            application/json:
-              schema:
-                $ref: '#/components/schemas/RenderErrorResponse'
-          description: Internal Server Error
-      security:
-      - api_key:
-        - VIEWER
-      - tokenizer:
-        - VIEWER
-      summary: List Clusters for Infra Monitoring
-      tags:
-      - inframonitoring
   /api/v2/infra_monitoring/hosts:
     post:
       deprecated: false
@@ -11961,151 +11618,12 @@ paths:
       summary: List Hosts for Infra Monitoring
       tags:
       - inframonitoring
-  /api/v2/infra_monitoring/namespaces:
-    post:
-      deprecated: false
-      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.'
-      operationId: ListNamespaces
-      requestBody:
-        content:
-          application/json:
-            schema:
-              $ref: '#/components/schemas/InframonitoringtypesPostableNamespaces'
-      responses:
-        "200":
-          content:
-            application/json:
-              schema:
-                properties:
-                  data:
-                    $ref: '#/components/schemas/InframonitoringtypesNamespaces'
-                  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
-        "500":
-          content:
-            application/json:
-              schema:
-                $ref: '#/components/schemas/RenderErrorResponse'
-          description: Internal Server Error
-      security:
-      - api_key:
-        - VIEWER
-      - tokenizer:
-        - VIEWER
-      summary: List Namespaces for Infra Monitoring
-      tags:
-      - inframonitoring
-  /api/v2/infra_monitoring/nodes:
-    post:
-      deprecated: false
-      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.'
-      operationId: ListNodes
-      requestBody:
-        content:
-          application/json:
-            schema:
-              $ref: '#/components/schemas/InframonitoringtypesPostableNodes'
-      responses:
-        "200":
-          content:
-            application/json:
-              schema:
-                properties:
-                  data:
-                    $ref: '#/components/schemas/InframonitoringtypesNodes'
-                  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
-        "500":
-          content:
-            application/json:
-              schema:
-                $ref: '#/components/schemas/RenderErrorResponse'
-          description: Internal Server Error
-      security:
-      - api_key:
-        - VIEWER
-      - tokenizer:
-        - VIEWER
-      summary: List Nodes for Infra Monitoring
-      tags:
-      - inframonitoring
   /api/v2/infra_monitoring/pods:
     post:
       deprecated: false
       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),
+        utilization, current pod phase (pending/running/succeeded/failed/unknown),
         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
@@ -12113,13 +11631,13 @@ paths:
         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.'
+        keys (each row aggregates pods in the group with per-phase counts: pendingPodCount,
+        runningPodCount, succeededPodCount, failedPodCount, unknownPodCount 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.'
       operationId: ListPods
       requestBody:
         content:

frontend/package.json

@@ -239,12 +239,10 @@
   },
   "lint-staged": {
     "*.(js|jsx|ts|tsx)": [
+      "oxlint --fix",
+      "oxfmt --write",
       "sh -c tsgo --noEmit"
     ],
-    "*.(js|jsx|ts|tsx|scss|css)": [
-      "oxlint --fix --quiet --no-error-on-unmatched-pattern",
-      "oxfmt --write"
-    ],
     "*.(scss|css)": [
       "stylelint"
     ]

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

@@ -12,15 +12,9 @@ import type {
 } from 'react-query';
 
 import type {
-	InframonitoringtypesPostableClustersDTO,
 	InframonitoringtypesPostableHostsDTO,
-	InframonitoringtypesPostableNamespacesDTO,
-	InframonitoringtypesPostableNodesDTO,
 	InframonitoringtypesPostablePodsDTO,
-	ListClusters200,
 	ListHosts200,
-	ListNamespaces200,
-	ListNodes200,
 	ListPods200,
 	RenderErrorResponseDTO,
 } from '../sigNoz.schemas';
@@ -28,90 +22,6 @@ import type {
 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.
- * @summary List Clusters for Infra Monitoring
- */
-export const listClusters = (
-	inframonitoringtypesPostableClustersDTO: BodyType<InframonitoringtypesPostableClustersDTO>,
-	signal?: AbortSignal,
-) => {
-	return GeneratedAPIInstance<ListClusters200>({
-		url: `/api/v2/infra_monitoring/clusters`,
-		method: 'POST',
-		headers: { 'Content-Type': 'application/json' },
-		data: inframonitoringtypesPostableClustersDTO,
-		signal,
-	});
-};
-
-export const getListClustersMutationOptions = <
-	TError = ErrorType<RenderErrorResponseDTO>,
-	TContext = unknown,
->(options?: {
-	mutation?: UseMutationOptions<
-		Awaited<ReturnType<typeof listClusters>>,
-		TError,
-		{ data: BodyType<InframonitoringtypesPostableClustersDTO> },
-		TContext
-	>;
-}): UseMutationOptions<
-	Awaited<ReturnType<typeof listClusters>>,
-	TError,
-	{ data: BodyType<InframonitoringtypesPostableClustersDTO> },
-	TContext
-> => {
-	const mutationKey = ['listClusters'];
-	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 listClusters>>,
-		{ data: BodyType<InframonitoringtypesPostableClustersDTO> }
-	> = (props) => {
-		const { data } = props ?? {};
-
-		return listClusters(data);
-	};
-
-	return { mutationFn, ...mutationOptions };
-};
-
-export type ListClustersMutationResult = NonNullable<
-	Awaited<ReturnType<typeof listClusters>>
->;
-export type ListClustersMutationBody =
-	BodyType<InframonitoringtypesPostableClustersDTO>;
-export type ListClustersMutationError = ErrorType<RenderErrorResponseDTO>;
-
-/**
- * @summary List Clusters for Infra Monitoring
- */
-export const useListClusters = <
-	TError = ErrorType<RenderErrorResponseDTO>,
-	TContext = unknown,
->(options?: {
-	mutation?: UseMutationOptions<
-		Awaited<ReturnType<typeof listClusters>>,
-		TError,
-		{ data: BodyType<InframonitoringtypesPostableClustersDTO> },
-		TContext
-	>;
-}): UseMutationResult<
-	Awaited<ReturnType<typeof listClusters>>,
-	TError,
-	{ data: BodyType<InframonitoringtypesPostableClustersDTO> },
-	TContext
-> => {
-	const mutationOptions = getListClustersMutationOptions(options);
-
-	return useMutation(mutationOptions);
-};
 /**
  * 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.
  * @summary List Hosts for Infra Monitoring
@@ -197,175 +107,7 @@ export const useListHosts = <
 	return useMutation(mutationOptions);
 };
 /**
- * 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.
- * @summary List Namespaces for Infra Monitoring
- */
-export const listNamespaces = (
-	inframonitoringtypesPostableNamespacesDTO: BodyType<InframonitoringtypesPostableNamespacesDTO>,
-	signal?: AbortSignal,
-) => {
-	return GeneratedAPIInstance<ListNamespaces200>({
-		url: `/api/v2/infra_monitoring/namespaces`,
-		method: 'POST',
-		headers: { 'Content-Type': 'application/json' },
-		data: inframonitoringtypesPostableNamespacesDTO,
-		signal,
-	});
-};
-
-export const getListNamespacesMutationOptions = <
-	TError = ErrorType<RenderErrorResponseDTO>,
-	TContext = unknown,
->(options?: {
-	mutation?: UseMutationOptions<
-		Awaited<ReturnType<typeof listNamespaces>>,
-		TError,
-		{ data: BodyType<InframonitoringtypesPostableNamespacesDTO> },
-		TContext
-	>;
-}): UseMutationOptions<
-	Awaited<ReturnType<typeof listNamespaces>>,
-	TError,
-	{ data: BodyType<InframonitoringtypesPostableNamespacesDTO> },
-	TContext
-> => {
-	const mutationKey = ['listNamespaces'];
-	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 listNamespaces>>,
-		{ data: BodyType<InframonitoringtypesPostableNamespacesDTO> }
-	> = (props) => {
-		const { data } = props ?? {};
-
-		return listNamespaces(data);
-	};
-
-	return { mutationFn, ...mutationOptions };
-};
-
-export type ListNamespacesMutationResult = NonNullable<
-	Awaited<ReturnType<typeof listNamespaces>>
->;
-export type ListNamespacesMutationBody =
-	BodyType<InframonitoringtypesPostableNamespacesDTO>;
-export type ListNamespacesMutationError = ErrorType<RenderErrorResponseDTO>;
-
-/**
- * @summary List Namespaces for Infra Monitoring
- */
-export const useListNamespaces = <
-	TError = ErrorType<RenderErrorResponseDTO>,
-	TContext = unknown,
->(options?: {
-	mutation?: UseMutationOptions<
-		Awaited<ReturnType<typeof listNamespaces>>,
-		TError,
-		{ data: BodyType<InframonitoringtypesPostableNamespacesDTO> },
-		TContext
-	>;
-}): UseMutationResult<
-	Awaited<ReturnType<typeof listNamespaces>>,
-	TError,
-	{ data: BodyType<InframonitoringtypesPostableNamespacesDTO> },
-	TContext
-> => {
-	const mutationOptions = getListNamespacesMutationOptions(options);
-
-	return useMutation(mutationOptions);
-};
-/**
- * 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.
- * @summary List Nodes for Infra Monitoring
- */
-export const listNodes = (
-	inframonitoringtypesPostableNodesDTO: BodyType<InframonitoringtypesPostableNodesDTO>,
-	signal?: AbortSignal,
-) => {
-	return GeneratedAPIInstance<ListNodes200>({
-		url: `/api/v2/infra_monitoring/nodes`,
-		method: 'POST',
-		headers: { 'Content-Type': 'application/json' },
-		data: inframonitoringtypesPostableNodesDTO,
-		signal,
-	});
-};
-
-export const getListNodesMutationOptions = <
-	TError = ErrorType<RenderErrorResponseDTO>,
-	TContext = unknown,
->(options?: {
-	mutation?: UseMutationOptions<
-		Awaited<ReturnType<typeof listNodes>>,
-		TError,
-		{ data: BodyType<InframonitoringtypesPostableNodesDTO> },
-		TContext
-	>;
-}): UseMutationOptions<
-	Awaited<ReturnType<typeof listNodes>>,
-	TError,
-	{ data: BodyType<InframonitoringtypesPostableNodesDTO> },
-	TContext
-> => {
-	const mutationKey = ['listNodes'];
-	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 listNodes>>,
-		{ data: BodyType<InframonitoringtypesPostableNodesDTO> }
-	> = (props) => {
-		const { data } = props ?? {};
-
-		return listNodes(data);
-	};
-
-	return { mutationFn, ...mutationOptions };
-};
-
-export type ListNodesMutationResult = NonNullable<
-	Awaited<ReturnType<typeof listNodes>>
->;
-export type ListNodesMutationBody =
-	BodyType<InframonitoringtypesPostableNodesDTO>;
-export type ListNodesMutationError = ErrorType<RenderErrorResponseDTO>;
-
-/**
- * @summary List Nodes for Infra Monitoring
- */
-export const useListNodes = <
-	TError = ErrorType<RenderErrorResponseDTO>,
-	TContext = unknown,
->(options?: {
-	mutation?: UseMutationOptions<
-		Awaited<ReturnType<typeof listNodes>>,
-		TError,
-		{ data: BodyType<InframonitoringtypesPostableNodesDTO> },
-		TContext
-	>;
-}): UseMutationResult<
-	Awaited<ReturnType<typeof listNodes>>,
-	TError,
-	{ data: BodyType<InframonitoringtypesPostableNodesDTO> },
-	TContext
-> => {
-	const mutationOptions = getListNodesMutationOptions(options);
-
-	return useMutation(mutationOptions);
-};
-/**
- * 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), 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: pendingPodCount, runningPodCount, succeededPodCount, failedPodCount, unknownPodCount 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.
  * @summary List Pods for Infra Monitoring
  */
 export const listPods = (

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

@@ -4567,66 +4567,6 @@ export interface GlobaltypesTokenizerConfigDTO {
 	enabled?: boolean;
 }
 
-/**
- * @nullable
- */
-export type InframonitoringtypesClusterRecordDTOMeta = {
-	[key: string]: string;
-} | null;
-
-export interface InframonitoringtypesClusterRecordDTO {
-	/**
-	 * @type number
-	 * @format double
-	 */
-	clusterCPU: number;
-	/**
-	 * @type number
-	 * @format double
-	 */
-	clusterCPUAllocatable: number;
-	/**
-	 * @type number
-	 * @format double
-	 */
-	clusterMemory: number;
-	/**
-	 * @type number
-	 * @format double
-	 */
-	clusterMemoryAllocatable: number;
-	/**
-	 * @type string
-	 */
-	clusterName: string;
-	/**
-	 * @type object
-	 * @nullable true
-	 */
-	meta: InframonitoringtypesClusterRecordDTOMeta;
-	nodeCountsByReadiness: InframonitoringtypesNodeCountsByReadinessDTO;
-	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
-}
-
-export interface InframonitoringtypesClustersDTO {
-	/**
-	 * @type boolean
-	 */
-	endTimeBeforeRetention: boolean;
-	/**
-	 * @type array
-	 * @nullable true
-	 */
-	records: InframonitoringtypesClusterRecordDTO[] | null;
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
-	/**
-	 * @type integer
-	 */
-	total: number;
-	type: InframonitoringtypesResponseTypeDTO;
-	warning?: Querybuildertypesv5QueryWarnDataDTO;
-}
-
 export interface InframonitoringtypesHostFilterDTO {
 	/**
 	 * @type string
@@ -4639,7 +4579,7 @@ export interface InframonitoringtypesHostFilterDTO {
  * @nullable
  */
 export type InframonitoringtypesHostRecordDTOMeta = {
-	[key: string]: string;
+	[key: string]: unknown;
 } | null;
 
 export interface InframonitoringtypesHostRecordDTO {
@@ -4712,176 +4652,35 @@ export interface InframonitoringtypesHostsDTO {
 	warning?: Querybuildertypesv5QueryWarnDataDTO;
 }
 
-/**
- * @nullable
- */
-export type InframonitoringtypesNamespaceRecordDTOMeta = {
-	[key: string]: string;
-} | null;
-
-export interface InframonitoringtypesNamespaceRecordDTO {
-	/**
-	 * @type object
-	 * @nullable true
-	 */
-	meta: InframonitoringtypesNamespaceRecordDTOMeta;
-	/**
-	 * @type number
-	 * @format double
-	 */
-	namespaceCPU: number;
-	/**
-	 * @type number
-	 * @format double
-	 */
-	namespaceMemory: number;
-	/**
-	 * @type string
-	 */
-	namespaceName: string;
-	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
-}
-
-export interface InframonitoringtypesNamespacesDTO {
-	/**
-	 * @type boolean
-	 */
-	endTimeBeforeRetention: boolean;
-	/**
-	 * @type array
-	 * @nullable true
-	 */
-	records: InframonitoringtypesNamespaceRecordDTO[] | null;
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
-	/**
-	 * @type integer
-	 */
-	total: number;
-	type: InframonitoringtypesResponseTypeDTO;
-	warning?: Querybuildertypesv5QueryWarnDataDTO;
-}
-
-export enum InframonitoringtypesNodeConditionDTO {
-	ready = 'ready',
-	not_ready = 'not_ready',
-	no_data = 'no_data',
-}
-export interface InframonitoringtypesNodeCountsByReadinessDTO {
-	/**
-	 * @type integer
-	 */
-	notReady: number;
-	/**
-	 * @type integer
-	 */
-	ready: number;
-}
-
-/**
- * @nullable
- */
-export type InframonitoringtypesNodeRecordDTOMeta = {
-	[key: string]: string;
-} | null;
-
-export interface InframonitoringtypesNodeRecordDTO {
-	condition: InframonitoringtypesNodeConditionDTO;
-	/**
-	 * @type object
-	 * @nullable true
-	 */
-	meta: InframonitoringtypesNodeRecordDTOMeta;
-	/**
-	 * @type number
-	 * @format double
-	 */
-	nodeCPU: number;
-	/**
-	 * @type number
-	 * @format double
-	 */
-	nodeCPUAllocatable: number;
-	nodeCountsByReadiness: InframonitoringtypesNodeCountsByReadinessDTO;
-	/**
-	 * @type number
-	 * @format double
-	 */
-	nodeMemory: number;
-	/**
-	 * @type number
-	 * @format double
-	 */
-	nodeMemoryAllocatable: number;
-	/**
-	 * @type string
-	 */
-	nodeName: string;
-	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
-}
-
-export interface InframonitoringtypesNodesDTO {
-	/**
-	 * @type boolean
-	 */
-	endTimeBeforeRetention: boolean;
-	/**
-	 * @type array
-	 * @nullable true
-	 */
-	records: InframonitoringtypesNodeRecordDTO[] | null;
-	requiredMetricsCheck: InframonitoringtypesRequiredMetricsCheckDTO;
-	/**
-	 * @type integer
-	 */
-	total: number;
-	type: InframonitoringtypesResponseTypeDTO;
-	warning?: Querybuildertypesv5QueryWarnDataDTO;
-}
-
-export interface InframonitoringtypesPodCountsByPhaseDTO {
-	/**
-	 * @type integer
-	 */
-	failed: number;
-	/**
-	 * @type integer
-	 */
-	pending: number;
-	/**
-	 * @type integer
-	 */
-	running: number;
-	/**
-	 * @type integer
-	 */
-	succeeded: number;
-	/**
-	 * @type integer
-	 */
-	unknown: number;
-}
-
 export enum InframonitoringtypesPodPhaseDTO {
 	pending = 'pending',
 	running = 'running',
 	succeeded = 'succeeded',
 	failed = 'failed',
 	unknown = 'unknown',
-	no_data = 'no_data',
+	'' = '',
 }
 /**
  * @nullable
  */
 export type InframonitoringtypesPodRecordDTOMeta = {
-	[key: string]: string;
+	[key: string]: unknown;
 } | null;
 
 export interface InframonitoringtypesPodRecordDTO {
+	/**
+	 * @type integer
+	 */
+	failedPodCount: number;
 	/**
 	 * @type object
 	 * @nullable true
 	 */
 	meta: InframonitoringtypesPodRecordDTOMeta;
+	/**
+	 * @type integer
+	 */
+	pendingPodCount: number;
 	/**
 	 * @type integer
 	 * @format int64
@@ -4902,7 +4701,6 @@ export interface InframonitoringtypesPodRecordDTO {
 	 * @format double
 	 */
 	podCPURequest: number;
-	podCountsByPhase: InframonitoringtypesPodCountsByPhaseDTO;
 	/**
 	 * @type number
 	 * @format double
@@ -4923,6 +4721,18 @@ export interface InframonitoringtypesPodRecordDTO {
 	 * @type string
 	 */
 	podUID: string;
+	/**
+	 * @type integer
+	 */
+	runningPodCount: number;
+	/**
+	 * @type integer
+	 */
+	succeededPodCount: number;
+	/**
+	 * @type integer
+	 */
+	unknownPodCount: number;
 }
 
 export interface InframonitoringtypesPodsDTO {
@@ -4944,34 +4754,6 @@ export interface InframonitoringtypesPodsDTO {
 	warning?: Querybuildertypesv5QueryWarnDataDTO;
 }
 
-export interface InframonitoringtypesPostableClustersDTO {
-	/**
-	 * @type integer
-	 * @format int64
-	 */
-	end: number;
-	filter?: Querybuildertypesv5FilterDTO;
-	/**
-	 * @type array
-	 * @nullable true
-	 */
-	groupBy?: Querybuildertypesv5GroupByKeyDTO[] | null;
-	/**
-	 * @type integer
-	 */
-	limit: number;
-	/**
-	 * @type integer
-	 */
-	offset?: number;
-	orderBy?: Querybuildertypesv5OrderByDTO;
-	/**
-	 * @type integer
-	 * @format int64
-	 */
-	start: number;
-}
-
 export interface InframonitoringtypesPostableHostsDTO {
 	/**
 	 * @type integer
@@ -5000,62 +4782,6 @@ export interface InframonitoringtypesPostableHostsDTO {
 	start: number;
 }
 
-export interface InframonitoringtypesPostableNamespacesDTO {
-	/**
-	 * @type integer
-	 * @format int64
-	 */
-	end: number;
-	filter?: Querybuildertypesv5FilterDTO;
-	/**
-	 * @type array
-	 * @nullable true
-	 */
-	groupBy?: Querybuildertypesv5GroupByKeyDTO[] | null;
-	/**
-	 * @type integer
-	 */
-	limit: number;
-	/**
-	 * @type integer
-	 */
-	offset?: number;
-	orderBy?: Querybuildertypesv5OrderByDTO;
-	/**
-	 * @type integer
-	 * @format int64
-	 */
-	start: number;
-}
-
-export interface InframonitoringtypesPostableNodesDTO {
-	/**
-	 * @type integer
-	 * @format int64
-	 */
-	end: number;
-	filter?: Querybuildertypesv5FilterDTO;
-	/**
-	 * @type array
-	 * @nullable true
-	 */
-	groupBy?: Querybuildertypesv5GroupByKeyDTO[] | null;
-	/**
-	 * @type integer
-	 */
-	limit: number;
-	/**
-	 * @type integer
-	 */
-	offset?: number;
-	orderBy?: Querybuildertypesv5OrderByDTO;
-	/**
-	 * @type integer
-	 * @format int64
-	 */
-	start: number;
-}
-
 export interface InframonitoringtypesPostablePodsDTO {
 	/**
 	 * @type integer
@@ -9399,14 +9125,6 @@ export type Healthz503 = {
 	status: string;
 };
 
-export type ListClusters200 = {
-	data: InframonitoringtypesClustersDTO;
-	/**
-	 * @type string
-	 */
-	status: string;
-};
-
 export type ListHosts200 = {
 	data: InframonitoringtypesHostsDTO;
 	/**
@@ -9415,22 +9133,6 @@ export type ListHosts200 = {
 	status: string;
 };
 
-export type ListNamespaces200 = {
-	data: InframonitoringtypesNamespacesDTO;
-	/**
-	 * @type string
-	 */
-	status: string;
-};
-
-export type ListNodes200 = {
-	data: InframonitoringtypesNodesDTO;
-	/**
-	 * @type string
-	 */
-	status: string;
-};
-
 export type ListPods200 = {
 	data: InframonitoringtypesPodsDTO;
 	/**

frontend/src/components/TanStackTableView/__tests__/useTableParams.test.tsx

@@ -398,7 +398,7 @@ describe('useTableParams (selective URL mode — partial config object)', () =>
 			.filter(Boolean)
 			.pop();
 		expect(lastExpanded).toBeDefined();
-		expect(JSON.parse(lastExpanded!)).toStrictEqual(
+		expect(JSON.parse(lastExpanded!)).toEqual(
 			expect.arrayContaining(['row-1', 'row-2']),
 		);
 

pkg/apiserver/signozapiserver/inframonitoring.go

@@ -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), 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: pendingPodCount, runningPodCount, succeededPodCount, failedPodCount, unknownPodCount 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.",
 			Request:             new(inframonitoringtypes.PostablePods),
 			RequestContentType:  "application/json",
 			Response:            new(inframonitoringtypes.Pods),
@@ -48,62 +48,5 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 		return err
 	}
 
-	if err := router.Handle("/api/v2/infra_monitoring/nodes", handler.New(
-		provider.authZ.ViewAccess(provider.infraMonitoringHandler.ListNodes),
-		handler.OpenAPIDef{
-			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.",
-			Request:             new(inframonitoringtypes.PostableNodes),
-			RequestContentType:  "application/json",
-			Response:            new(inframonitoringtypes.Nodes),
-			ResponseContentType: "application/json",
-			SuccessStatusCode:   http.StatusOK,
-			ErrorStatusCodes:    []int{http.StatusBadRequest, http.StatusUnauthorized},
-			Deprecated:          false,
-			SecuritySchemes:     newSecuritySchemes(types.RoleViewer),
-		})).Methods(http.MethodPost).GetError(); err != nil {
-		return err
-	}
-
-	if err := router.Handle("/api/v2/infra_monitoring/namespaces", handler.New(
-		provider.authZ.ViewAccess(provider.infraMonitoringHandler.ListNamespaces),
-		handler.OpenAPIDef{
-			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.",
-			Request:             new(inframonitoringtypes.PostableNamespaces),
-			RequestContentType:  "application/json",
-			Response:            new(inframonitoringtypes.Namespaces),
-			ResponseContentType: "application/json",
-			SuccessStatusCode:   http.StatusOK,
-			ErrorStatusCodes:    []int{http.StatusBadRequest, http.StatusUnauthorized},
-			Deprecated:          false,
-			SecuritySchemes:     newSecuritySchemes(types.RoleViewer),
-		})).Methods(http.MethodPost).GetError(); err != nil {
-		return err
-	}
-
-	if err := router.Handle("/api/v2/infra_monitoring/clusters", handler.New(
-		provider.authZ.ViewAccess(provider.infraMonitoringHandler.ListClusters),
-		handler.OpenAPIDef{
-			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.",
-			Request:             new(inframonitoringtypes.PostableClusters),
-			RequestContentType:  "application/json",
-			Response:            new(inframonitoringtypes.Clusters),
-			ResponseContentType: "application/json",
-			SuccessStatusCode:   http.StatusOK,
-			ErrorStatusCodes:    []int{http.StatusBadRequest, http.StatusUnauthorized},
-			Deprecated:          false,
-			SecuritySchemes:     newSecuritySchemes(types.RoleViewer),
-		})).Methods(http.MethodPost).GetError(); err != nil {
-		return err
-	}
-
 	return nil
 }

pkg/errors/v2/code.go

@@ -0,0 +1,99 @@
+package v2
+
+import (
+	"regexp"
+	"sync"
+	"time"
+)
+
+// Code is a dotted, hierarchical identifier registered at process start. It
+// encodes domain (subsystem), op (verb), optional sub (qualifier), and a
+// terminal reason. Codes are values; two Codes with the same string are equal
+// by value and safe to compare with ==.
+type Code struct{ s string }
+
+// String returns the dotted code as it appears on the wire. Empty for the
+// zero value.
+func (c Code) String() string { return c.s }
+
+// codePattern allows 2-4 dotted segments, each starting with a lowercase
+// letter and continuing with [a-z0-9_]. One segment is too broad (use a
+// domain prefix); five or more means the domain should be split.
+var codePattern = regexp.MustCompile(`^[a-z][a-z0-9_]*(\.[a-z][a-z0-9_]*){1,3}$`)
+
+// Meta is the per-code default envelope applied by constructors before
+// per-call options. Every field has a natural per-code default — an auth
+// code always wants Reauthenticate, every documented code wants its docs
+// URL — so the registry is the right place to declare them once.
+type Meta struct {
+	Category    Category
+	Fault       Fault
+	Retry       Retry
+	Remediation Remediation
+	Refs        map[RefKind]string
+}
+
+// Retry tells the caller how and when to retry. After is meaningful only
+// when Policy == RetryAfter.
+type Retry struct {
+	Policy RetryPolicy
+	After  time.Duration
+}
+
+var (
+	registryMu sync.RWMutex
+	registry   = map[string]Meta{}
+)
+
+// Register installs a code with its default Meta and returns the Code value.
+// It panics on a malformed code string or a duplicate registration — both
+// indicate a programming error that must be caught at boot, not at first
+// failure.
+//
+// Call from the owning domain's package init or top-level var block:
+//
+//	var CodeUnknownFunction = errors.Register("query.parse.unknown_function", errors.Meta{
+//	    Category: errors.CategoryInvalidInput,
+//	    Fault:    errors.FaultCaller,
+//	    Retry:    errors.Retry{Policy: errors.RetryAfterFix},
+//	})
+func Register(s string, meta Meta) Code {
+	if !codePattern.MatchString(s) {
+		panic("errors/v2: malformed code: " + s)
+	}
+	registryMu.Lock()
+	defer registryMu.Unlock()
+	if _, ok := registry[s]; ok {
+		panic("errors/v2: duplicate code: " + s)
+	}
+	registry[s] = meta
+	return Code{s: s}
+}
+
+// MetaOf returns the Meta a code was registered with. Returns the zero Meta
+// and false for unregistered or zero codes.
+func MetaOf(c Code) (Meta, bool) {
+	if c.s == "" {
+		return Meta{}, false
+	}
+	registryMu.RLock()
+	defer registryMu.RUnlock()
+	m, ok := registry[c.s]
+	return m, ok
+}
+
+// registerOrGet is the internal idempotent register used by adapters that
+// may see the same code (e.g. legacy.<v1>) more than once across the process
+// lifetime. It panics on malformed codes — duplicate codes silently keep the
+// existing Meta.
+func registerOrGet(s string, meta Meta) Code {
+	if !codePattern.MatchString(s) {
+		panic("errors/v2: malformed code: " + s)
+	}
+	registryMu.Lock()
+	defer registryMu.Unlock()
+	if _, ok := registry[s]; !ok {
+		registry[s] = meta
+	}
+	return Code{s: s}
+}

pkg/errors/v2/enums.go

@@ -0,0 +1,93 @@
+package v2
+
+// The enums in this file are closed sets. Each value is a package-level var of
+// an unexported-field struct, so external code cannot synthesize new values —
+// it must reference one of the defined ones. String() returns the stable
+// snake_case wire name; once shipped, those names are append-only.
+
+// Category groups errors by what kind of failure occurred. It is the coarsest
+// branch-worthy axis and is intended to be a superset of gRPC status codes
+// extended with cases SigNoz cares about (e.g. license issues land under
+// FailedDependency or ResourceExhausted depending on context).
+type Category struct{ s string }
+
+func (c Category) String() string { return c.s }
+
+var (
+	CategoryInvalidInput      = Category{"invalid_input"}      // request was malformed or violated a documented constraint.
+	CategoryNotFound          = Category{"not_found"}          // referenced resource does not exist.
+	CategoryAlreadyExists     = Category{"already_exists"}     // resource creation conflicts with an existing one.
+	CategoryConflict          = Category{"conflict"}           // concurrent modification or state mismatch (e.g. stale revision).
+	CategoryPrecondition      = Category{"precondition"}       // a required precondition (system or caller-asserted) was not met.
+	CategoryUnauthenticated   = Category{"unauthenticated"}    // credentials are missing or invalid.
+	CategoryForbidden         = Category{"forbidden"}          // authenticated but not authorized for this action.
+	CategoryResourceExhausted = Category{"resource_exhausted"} // quota, rate limit, or other budget exceeded.
+	CategoryFailedDependency  = Category{"failed_dependency"}  // an upstream service we depend on failed (db, license, etc.).
+	CategoryUnavailable       = Category{"unavailable"}        // service is temporarily down; retry with backoff.
+	CategoryTimeout           = Category{"timeout"}            // deadline exceeded before the operation completed.
+	CategoryCanceled          = Category{"canceled"}           // caller or context canceled the operation.
+	CategoryUnimplemented     = Category{"unimplemented"}      // operation is not supported (or not yet) by this server.
+	CategoryDataLoss          = Category{"data_loss"}          // unrecoverable data corruption or loss detected.
+	CategoryInternal          = Category{"internal"}           // bug — invariant broken; should not occur in normal operation.
+)
+
+// Fault attributes responsibility. An agent uses this to decide whether to
+// fix the request (Caller), retry/escalate (Server, Upstream), or page a
+// human (Operator).
+type Fault struct{ s string }
+
+func (f Fault) String() string { return f.s }
+
+var (
+	FaultCaller   = Fault{"caller"}
+	FaultServer   = Fault{"server"}
+	FaultUpstream = Fault{"upstream"}
+	FaultOperator = Fault{"operator"}
+)
+
+// RetryPolicy tells the caller how to behave on retry. Backoff implies the
+// caller should use its own backoff schedule; After means honor Retry.After
+// exactly; AfterFix and AfterAuth signal that retry is pointless until the
+// caller fixes the request or re-authenticates.
+type RetryPolicy struct{ s string }
+
+func (r RetryPolicy) String() string { return r.s }
+
+var (
+	RetryNever     = RetryPolicy{"never"}
+	RetryImmediate = RetryPolicy{"immediate"}
+	RetryBackoff   = RetryPolicy{"backoff"}
+	RetryAfter     = RetryPolicy{"after"}
+	RetryAfterFix  = RetryPolicy{"after_fix"}
+	RetryAfterAuth = RetryPolicy{"after_auth"}
+)
+
+// Remediation names the single recommended next action. It does not execute.
+type Remediation struct{ s string }
+
+func (r Remediation) String() string { return r.s }
+
+var (
+	RemediationNone            = Remediation{"none"}
+	RemediationFixInput        = Remediation{"fix_input"}
+	RemediationReauthenticate  = Remediation{"reauthenticate"}
+	RemediationWaitAndRetry    = Remediation{"wait_and_retry"}
+	RemediationFailover        = Remediation{"failover"}
+	RemediationContactOperator = Remediation{"contact_operator"}
+	RemediationFileBug         = Remediation{"file_bug"}
+	RemediationUpgradeLicense  = Remediation{"upgrade_license"}
+)
+
+// RefKind classifies a reference URL attached to the error.
+type RefKind struct{ s string }
+
+func (r RefKind) String() string { return r.s }
+
+var (
+	RefDocs      = RefKind{"docs"}
+	RefRunbook   = RefKind{"runbook"}
+	RefDashboard = RefKind{"dashboard"}
+	RefTrace     = RefKind{"trace"}
+	RefSource    = RefKind{"source"}
+	RefIssue     = RefKind{"issue"}
+)

pkg/errors/v2/error.go

@@ -0,0 +1,248 @@
+// Package v2 is the redesigned pkg/errors.
+//
+// Every branch-worthy field on the Error struct is a closed enum and every
+// variable part is a typed key/value. The intent is to make errors first-class
+// data for programmatic consumers — SDK clients, UI surfaces, alerting, and
+// LLM agents — without sacrificing human readability.
+//
+// Domain and op are encoded into Code (e.g. "query.parse.unknown_function")
+// rather than carried as separate struct fields. Frames[0] is the
+// authoritative call-site location, captured at construction time.
+package v2
+
+import (
+	stderrors "errors"
+	"fmt"
+	"io"
+	"sort"
+	"strconv"
+	"strings"
+)
+
+// Error is the redesigned error value. *Error is the canonical form passed
+// around — the zero value is unused, construct via New / Newf / Wrap / Wrapf.
+//
+// Frames are intentionally not a struct field: resolving captured PCs into
+// func/file/line is the dominant construction cost, so we capture PCs eagerly
+// at construction time (so the snapshot is faithful to the call site) and
+// resolve them lazily via Frames() only when something actually inspects them.
+type Error struct {
+	// WHAT
+	Category Category
+	Code     Code
+	Title    string
+	Detail   string
+
+	// WHY / WHO
+	Cause error
+	Fault Fault
+
+	// WHAT NEXT
+	Retry       Retry
+	Remediation Remediation
+	Refs        map[RefKind]string
+
+	// CONTEXT
+	Attrs   map[string]any
+	TraceID string
+	SpanID  string
+
+	// stack is the captured PCs plus a memoized []Frame; never read directly,
+	// always go through Frames().
+	stack *frameStack
+}
+
+// Frames returns the captured stack, resolved to func/file/line on first
+// access. Frames[0] is the constructor's caller. Safe for concurrent use.
+func (e *Error) Frames() []Frame {
+	if e == nil {
+		return nil
+	}
+	return e.stack.frames()
+}
+
+// New creates an Error for a registered Code. Defaults from the registered
+// Meta are applied first; opts override per call site.
+func New(code Code, title string, opts ...Option) *Error {
+	e := &Error{Code: code, Title: title, stack: captureStack(3)}
+	applyMeta(e)
+	for _, opt := range opts {
+		opt(e)
+	}
+	return e
+}
+
+// Newf is New with fmt.Sprintf-style formatting for the title.
+func Newf(code Code, format string, args ...any) *Error {
+	e := &Error{Code: code, Title: fmt.Sprintf(format, args...), stack: captureStack(3)}
+	applyMeta(e)
+	return e
+}
+
+// Wrap creates an Error that wraps cause. The new error's Title is the
+// caller-supplied title (not the cause's message), so Error() reports what
+// went wrong at this layer — the cause is reachable via Unwrap.
+func Wrap(cause error, code Code, title string, opts ...Option) *Error {
+	e := &Error{Code: code, Title: title, Cause: cause, stack: captureStack(3)}
+	applyMeta(e)
+	for _, opt := range opts {
+		opt(e)
+	}
+	return e
+}
+
+// Wrapf is Wrap with fmt.Sprintf-style formatting for the title.
+func Wrapf(cause error, code Code, format string, args ...any) *Error {
+	e := &Error{Code: code, Title: fmt.Sprintf(format, args...), Cause: cause, stack: captureStack(3)}
+	applyMeta(e)
+	return e
+}
+
+// applyMeta copies default values from the registered Meta into a fresh
+// Error. It runs before per-call options so options win.
+func applyMeta(e *Error) {
+	meta, ok := MetaOf(e.Code)
+	if !ok {
+		return
+	}
+	if (e.Category == Category{}) {
+		e.Category = meta.Category
+	}
+	if (e.Fault == Fault{}) {
+		e.Fault = meta.Fault
+	}
+	if (e.Retry == Retry{}) {
+		e.Retry = meta.Retry
+	}
+	if (e.Remediation == Remediation{}) {
+		e.Remediation = meta.Remediation
+	}
+	if len(meta.Refs) > 0 {
+		if e.Refs == nil {
+			e.Refs = make(map[RefKind]string, len(meta.Refs))
+		}
+		for k, v := range meta.Refs {
+			if _, exists := e.Refs[k]; !exists {
+				e.Refs[k] = v
+			}
+		}
+	}
+}
+
+// Error returns the Title (the message specifically attached at this wrap
+// site), not the cause's message. This fixes the v1 surprise where Error()
+// returned the wrapped cause's text.
+func (e *Error) Error() string {
+	if e == nil {
+		return "<nil>"
+	}
+	return e.Title
+}
+
+// Unwrap returns the wrapped cause, enabling errors.Is / errors.As.
+func (e *Error) Unwrap() error {
+	if e == nil {
+		return nil
+	}
+	return e.Cause
+}
+
+// Format implements fmt.Formatter.
+//
+//	%s, %v   →  Title only
+//	%+v      →  full chain: code, title, frames, attrs, recursive cause
+func (e *Error) Format(f fmt.State, verb rune) {
+	switch verb {
+	case 's':
+		_, _ = io.WriteString(f, e.Title)
+	case 'v':
+		if f.Flag('+') {
+			_, _ = io.WriteString(f, e.fullString())
+			return
+		}
+		_, _ = io.WriteString(f, e.Title)
+	case 'q':
+		fmt.Fprintf(f, "%q", e.Title)
+	default:
+		fmt.Fprintf(f, "%%!%c(*errors/v2.Error)", verb)
+	}
+}
+
+// fullString produces the %+v rendering. Format is intentionally
+// human-readable rather than machine-parseable; consumers that want structure
+// should marshal to JSON.
+func (e *Error) fullString() string {
+	var b strings.Builder
+	e.appendFull(&b, 0)
+	return b.String()
+}
+
+func (e *Error) appendFull(b *strings.Builder, depth int) {
+	indent := strings.Repeat("  ", depth)
+	fmt.Fprintf(b, "%s[%s] %s\n", indent, e.Code.s, e.Title)
+	if e.Detail != "" {
+		fmt.Fprintf(b, "%s  detail: %s\n", indent, e.Detail)
+	}
+	if len(e.Attrs) > 0 {
+		// Stable key order for deterministic output.
+		keys := make([]string, 0, len(e.Attrs))
+		for k := range e.Attrs {
+			keys = append(keys, k)
+		}
+		sort.Strings(keys)
+		fmt.Fprintf(b, "%s  attrs:\n", indent)
+		for _, k := range keys {
+			fmt.Fprintf(b, "%s    %s=%v\n", indent, k, e.Attrs[k])
+		}
+	}
+	if frames := e.Frames(); len(frames) > 0 {
+		fmt.Fprintf(b, "%s  frames:\n", indent)
+		for _, fr := range frames {
+			fmt.Fprintf(b, "%s    %s\n%s      %s:%s\n", indent, fr.Func, indent, fr.File, strconv.Itoa(fr.Line))
+		}
+	}
+	if e.Cause != nil {
+		fmt.Fprintf(b, "%scaused by:\n", indent)
+		var ce *Error
+		if stderrors.As(e.Cause, &ce) && ce != nil {
+			ce.appendFull(b, depth+1)
+		} else {
+			fmt.Fprintf(b, "%s  %s\n", indent, e.Cause.Error())
+		}
+	}
+}
+
+// AsError extracts a *Error from anywhere in err's wrap chain. It is the
+// common shortcut around errors.As for code that always wants this package's
+// type.
+func AsError(err error) (*Error, bool) {
+	if err == nil {
+		return nil, false
+	}
+	var e *Error
+	if stderrors.As(err, &e) {
+		return e, true
+	}
+	return nil, false
+}
+
+// Is reports whether err or any error in its chain has the given Code.
+// Convenience wrapper that's friendlier than errors.As at call sites that
+// only care about code identity.
+func Is(err error, code Code) bool {
+	e, ok := AsError(err)
+	if !ok {
+		return false
+	}
+	for e != nil {
+		if e.Code == code {
+			return true
+		}
+		next, ok := AsError(e.Cause)
+		if !ok {
+			return false
+		}
+		e = next
+	}
+	return false
+}

pkg/errors/v2/example.go

@@ -0,0 +1,90 @@
+package v2
+
+// This file is a self-contained walkthrough of how a domain integrates with
+// pkg/errors/v2. It mirrors what a real pkg/<domain>/errors.go looks like in
+// practice — registering codes, constructing typed errors at failure sites,
+// and consuming them at API boundaries. The "example.*" namespace is reserved
+// for these demo codes so they never collide with a real domain's
+// registrations.
+
+// 1. Register codes at package init time. Each Register call panics on
+// malformed code or duplicate registration, so misconfiguration is caught
+// at process boot, not at first failure.
+var (
+	// A caller-fault, fix-the-input error: rejected before any work happens.
+	exampleCodeInvalidQuery = Register("example.query.invalid_filter", Meta{
+		Category:    CategoryInvalidInput,
+		Fault:       FaultCaller,
+		Remediation: RemediationFixInput,
+		Retry:       Retry{Policy: RetryAfterFix},
+		Refs: map[RefKind]string{
+			RefDocs: "https://signoz.io/docs/query/filters",
+		},
+	})
+
+	// A quota error: the caller's request was well-formed but their plan
+	// doesn't allow it. The recommended remediation is structural (upgrade),
+	// not "try again later."
+	exampleCodeQuotaExceeded = Register("example.billing.quota_exceeded", Meta{
+		Category:    CategoryResourceExhausted,
+		Fault:       FaultCaller,
+		Remediation: RemediationUpgradeLicense,
+		Retry:       Retry{Policy: RetryNever},
+	})
+)
+
+// 2. Construct errors at the failure site. Notice that variable parts of
+// the message (the offending field, the limits) live in typed Attrs, not in
+// the title prose — a downstream agent can read them without parsing English.
+func exampleRejectInvalidFilter(field string) *Error {
+	return New(exampleCodeInvalidQuery, "filter is not supported",
+		WithAttr("field", field),
+	)
+}
+
+// 3. Consume errors at the API boundary. Branching on Category gives the
+// HTTP status; Retry tells an SDK how to behave; Fault drives logging
+// classification (caller errors are warnings, server/upstream errors page).
+func exampleClassifyForHTTP(err error) (status int, retry RetryPolicy) {
+	e, ok := AsError(err)
+	if !ok {
+		return 500, RetryNever
+	}
+	switch e.Category {
+	case CategoryInvalidInput, CategoryPrecondition:
+		status = 400
+	case CategoryUnauthenticated:
+		status = 401
+	case CategoryForbidden:
+		status = 403
+	case CategoryNotFound:
+		status = 404
+	case CategoryConflict, CategoryAlreadyExists:
+		status = 409
+	case CategoryResourceExhausted:
+		status = 429
+	case CategoryUnavailable, CategoryTimeout:
+		status = 503
+	case CategoryUnimplemented:
+		status = 501
+	default:
+		status = 500
+	}
+	return status, e.Retry.Policy
+}
+
+// 4. Identify a specific failure mode by Code. Is walks the cause chain so
+// a wrapper at the HTTP layer still matches when the root cause was raised
+// deep in the call graph.
+func exampleIsQuotaExceeded(err error) bool {
+	return Is(err, exampleCodeQuotaExceeded)
+}
+
+// The example helpers are reference-only: they exist to document call-site
+// patterns, not to be called from anywhere in the binary. This anchor keeps
+// them visible to readers (and the linter) without exporting demo code.
+var _ = []any{
+	exampleRejectInvalidFilter,
+	exampleClassifyForHTTP,
+	exampleIsQuotaExceeded,
+}

pkg/errors/v2/frame.go

@@ -0,0 +1,65 @@
+package v2
+
+import (
+	"runtime"
+	"sync"
+)
+
+// Frame is a single line in the call stack. Frames[0] is the constructor's
+// caller — the authoritative "where this error came from" — and downstream
+// consumers can filter (e.g. "frames inside our code") without regex
+// reparsing of a pre-formatted stack string.
+type Frame struct {
+	Func string `json:"func,omitempty"`
+	File string `json:"file,omitempty"`
+	Line int    `json:"line,omitempty"`
+}
+
+// frameStack carries the PCs captured at construction plus the resolved
+// []Frame slice, behind a sync.Once. Resolving frames into func/file/line is
+// expensive (runtime.CallersFrames walks the symbol table); the vast majority
+// of errors are constructed and never inspected, so we only pay that cost
+// when a consumer actually asks for frames (Frames()/MarshalJSON/%+v).
+//
+// The PC capture itself is cheap and happens at construction so that
+// Frames[0] is a faithful "where" record of the original call site.
+type frameStack struct {
+	pcs []uintptr
+
+	once     sync.Once
+	resolved []Frame
+}
+
+// captureStack is called by every constructor. skip drops runtime.Callers,
+// captureStack itself, and the constructor frame so that the first PC is the
+// user code that invoked the constructor.
+func captureStack(skip int) *frameStack {
+	const depth = 32
+	pcs := make([]uintptr, depth)
+	n := runtime.Callers(skip, pcs)
+	if n == 0 {
+		return nil
+	}
+	return &frameStack{pcs: pcs[:n:n]}
+}
+
+// frames resolves the captured PCs into []Frame. The resolution is memoized
+// — concurrent calls are safe and only one of them does the work.
+func (s *frameStack) frames() []Frame {
+	if s == nil {
+		return nil
+	}
+	s.once.Do(func() {
+		cf := runtime.CallersFrames(s.pcs)
+		out := make([]Frame, 0, len(s.pcs))
+		for {
+			f, more := cf.Next()
+			out = append(out, Frame{Func: f.Function, File: f.File, Line: f.Line})
+			if !more {
+				break
+			}
+		}
+		s.resolved = out
+	})
+	return s.resolved
+}

pkg/errors/v2/http.go

@@ -0,0 +1,175 @@
+package v2
+
+import (
+	"encoding/json"
+	"net/url"
+)
+
+// CodeUnknown is the sentinel returned when AsJSON / AsURLValues are called
+// on a non-*Error. A consumer that sees this on the wire should read it as
+// "the producer did not raise a v2 Error and we projected it through the
+// fallback path" — i.e. somewhere upstream is still using std errors or v1.
+var CodeUnknown = Register("unknown.unset", Meta{
+	Category: CategoryInternal,
+	Fault:    FaultServer,
+	Retry:    Retry{Policy: RetryNever},
+})
+
+// JSON is the wire envelope for an Error. It is intentionally a superset of
+// v1's pkg/errors.JSON: SDK clients that only read v1's {code, message, url,
+// errors[]} keep working, while v2 consumers can branch on the new typed
+// fields (category, fault, retry, remediation, attrs, refs, cause).
+type JSON struct {
+	Code        string            `json:"code" required:"true"`
+	Title       string            `json:"title" required:"true"`
+	Detail      string            `json:"detail,omitempty"`
+	Category    string            `json:"category,omitempty"`
+	Fault       string            `json:"fault,omitempty"`
+	Retry       *RetryJSON        `json:"retry,omitempty"`
+	Remediation string            `json:"remediation,omitempty"`
+	Attrs       map[string]any    `json:"attrs,omitempty"`
+	Refs        map[string]string `json:"refs,omitempty"`
+	Frames      []Frame           `json:"frames,omitempty"`
+	TraceID     string            `json:"trace_id,omitempty"`
+	SpanID      string            `json:"span_id,omitempty"`
+	Cause       *CauseJSON        `json:"cause,omitempty"`
+}
+
+// RetryJSON renders Retry as an object so consumers can branch on policy
+// before consulting AfterMS. AfterMS is omitted unless policy is "after".
+type RetryJSON struct {
+	Policy  string `json:"policy"`
+	AfterMS int64  `json:"after_ms,omitempty"`
+}
+
+// CauseJSON is the thin recursive shape for a cause chain. Only code, title,
+// and a nested cause are guaranteed — producers may add more, consumers must
+// not rely on it.
+type CauseJSON struct {
+	Code  string     `json:"code,omitempty"`
+	Title string     `json:"title"`
+	Cause *CauseJSON `json:"cause,omitempty"`
+}
+
+// AsJSON projects any error onto the v2 wire envelope. If cause is a
+// *Error (anywhere in its wrap chain) every field is filled from it;
+// otherwise the result is a CodeUnknown envelope with Title=cause.Error()
+// so the wire shape is always valid and never panics.
+func AsJSON(cause error) *JSON {
+	if cause == nil {
+		return nil
+	}
+	e, ok := AsError(cause)
+	if !ok {
+		return &JSON{
+			Code:     CodeUnknown.s,
+			Title:    cause.Error(),
+			Category: CategoryInternal.s,
+			Fault:    FaultServer.s,
+		}
+	}
+	return errorToJSON(e)
+}
+
+func errorToJSON(e *Error) *JSON {
+	out := &JSON{
+		Code:        e.Code.s,
+		Title:       e.Title,
+		Detail:      e.Detail,
+		Category:    e.Category.s,
+		Fault:       e.Fault.s,
+		Remediation: e.Remediation.s,
+		Attrs:       e.Attrs,
+		TraceID:     e.TraceID,
+		SpanID:      e.SpanID,
+	}
+	if (e.Retry.Policy != RetryPolicy{}) {
+		out.Retry = &RetryJSON{Policy: e.Retry.Policy.s}
+		if e.Retry.Policy == RetryAfter && e.Retry.After > 0 {
+			out.Retry.AfterMS = e.Retry.After.Milliseconds()
+		}
+	}
+	if len(e.Refs) > 0 {
+		out.Refs = make(map[string]string, len(e.Refs))
+		for k, v := range e.Refs {
+			out.Refs[k.s] = v
+		}
+	}
+	if frames := e.Frames(); len(frames) > 0 {
+		out.Frames = frames
+	}
+	if e.Cause != nil {
+		out.Cause = causeToJSON(e.Cause)
+	}
+	return out
+}
+
+func causeToJSON(err error) *CauseJSON {
+	if err == nil {
+		return nil
+	}
+	if e, ok := err.(*Error); ok {
+		c := &CauseJSON{Code: e.Code.s, Title: e.Title}
+		if e.Cause != nil {
+			c.Cause = causeToJSON(e.Cause)
+		}
+		return c
+	}
+	// Non-*Error leaf: only Title is set, no Code.
+	return &CauseJSON{Title: err.Error()}
+}
+
+// AsURLValues projects an error onto a flat url.Values, matching v1's shape
+// for callers (e.g. OAuth/SSO redirects) that smuggle errors back through a
+// query string. Complex fields (attrs, refs, retry, frames, cause) are
+// JSON-marshaled into a single value rather than spread across multiple
+// keys, since query strings have no good representation for nested data.
+func AsURLValues(cause error) url.Values {
+	j := AsJSON(cause)
+	if j == nil {
+		return url.Values{}
+	}
+	v := url.Values{
+		"code":  {j.Code},
+		"title": {j.Title},
+	}
+	if j.Detail != "" {
+		v.Set("detail", j.Detail)
+	}
+	if j.Category != "" {
+		v.Set("category", j.Category)
+	}
+	if j.Fault != "" {
+		v.Set("fault", j.Fault)
+	}
+	if j.Remediation != "" {
+		v.Set("remediation", j.Remediation)
+	}
+	if j.TraceID != "" {
+		v.Set("trace_id", j.TraceID)
+	}
+	if j.SpanID != "" {
+		v.Set("span_id", j.SpanID)
+	}
+	if j.Retry != nil {
+		if b, err := json.Marshal(j.Retry); err == nil {
+			v.Set("retry", string(b))
+		}
+	}
+	if len(j.Refs) > 0 {
+		if b, err := json.Marshal(j.Refs); err == nil {
+			v.Set("refs", string(b))
+		}
+	}
+	if len(j.Attrs) > 0 {
+		if b, err := json.Marshal(j.Attrs); err == nil {
+			v.Set("attrs", string(b))
+		}
+	}
+	if j.Cause != nil {
+		if b, err := json.Marshal(j.Cause); err == nil {
+			v.Set("cause", string(b))
+		}
+	}
+	return v
+}

pkg/errors/v2/options.go

@@ -0,0 +1,85 @@
+package v2
+
+import "time"
+
+// Option mutates an Error during construction. Options are applied after the
+// registered Meta defaults so a per-call WithFault wins over the code's
+// default Fault.
+type Option func(*Error)
+
+// WithTitle overrides the title (used when Newf's formatted string is not
+// what you want, or after a Wrap that took its title from the cause).
+func WithTitle(s string) Option { return func(e *Error) { e.Title = s } }
+
+// WithDetail adds a long, user-safe explanation. Detail must never include
+// raw cause text; the cause is already in the chain.
+func WithDetail(s string) Option { return func(e *Error) { e.Detail = s } }
+
+// WithCategory overrides the registered Category.
+func WithCategory(c Category) Option { return func(e *Error) { e.Category = c } }
+
+// WithFault overrides the registered Fault.
+func WithFault(f Fault) Option { return func(e *Error) { e.Fault = f } }
+
+// WithRetry overrides the registered Retry.
+func WithRetry(r Retry) Option { return func(e *Error) { e.Retry = r } }
+
+// WithRetryAfter is a convenience for the common RetryAfter case.
+func WithRetryAfter(d time.Duration) Option {
+	return func(e *Error) { e.Retry = Retry{Policy: RetryAfter, After: d} }
+}
+
+// WithRemediation overrides the registered Remediation.
+//
+// Convention for "did you mean" hints: stash a []string under
+// Attrs["suggestions"], ranked best-first. Each element should be a complete,
+// copy-pasteable replacement — not an explanation of what went wrong (use
+// WithDetail for that). Once 3-4 domains adopt the convention identically,
+// promote to a first-class field.
+func WithRemediation(r Remediation) Option { return func(e *Error) { e.Remediation = r } }
+
+// WithRef adds (or replaces) a single reference URL keyed by kind.
+func WithRef(kind RefKind, url string) Option {
+	return func(e *Error) {
+		if e.Refs == nil {
+			e.Refs = make(map[RefKind]string, 1)
+		}
+		e.Refs[kind] = url
+	}
+}
+
+// WithAttr sets a single typed attribute. Prefer typed per-domain helpers
+// (e.g. WithQueryAttrs(q Query)) over raw WithAttr at call sites — they keep
+// the attr keys consistent and let the compiler reject typos.
+func WithAttr(key string, value any) Option {
+	return func(e *Error) {
+		if e.Attrs == nil {
+			e.Attrs = make(map[string]any, 1)
+		}
+		e.Attrs[key] = value
+	}
+}
+
+// WithAttrs merges a map of attributes; later keys win.
+func WithAttrs(attrs map[string]any) Option {
+	return func(e *Error) {
+		if len(attrs) == 0 {
+			return
+		}
+		if e.Attrs == nil {
+			e.Attrs = make(map[string]any, len(attrs))
+		}
+		for k, v := range attrs {
+			e.Attrs[k] = v
+		}
+	}
+}
+
+// WithTrace stamps the error with OTel trace and span IDs so the JSON
+// response can link back to the originating span.
+func WithTrace(traceID, spanID string) Option {
+	return func(e *Error) {
+		e.TraceID = traceID
+		e.SpanID = spanID
+	}
+}

pkg/modules/inframonitoring/implinframonitoring/clusters.go

@@ -1,140 +0,0 @@
-package implinframonitoring
-
-import (
-	"context"
-	"slices"
-
-	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-	"github.com/SigNoz/signoz/pkg/valuer"
-)
-
-// buildClusterRecords assembles the page records. Node condition counts and
-// pod phase counts come from the respective per-group maps in both modes;
-// every row is a group of nodes+pods, so there's no per-row "current state"
-// concept (analogous to namespaces).
-func buildClusterRecords(
-	resp *qbtypes.QueryRangeResponse,
-	pageGroups []map[string]string,
-	groupBy []qbtypes.GroupByKey,
-	metadataMap map[string]map[string]string,
-	nodeConditionCountsMap map[string]nodeConditionCounts,
-	podPhaseCountsMap map[string]podPhaseCounts,
-) []inframonitoringtypes.ClusterRecord {
-	metricsMap := parseFullQueryResponse(resp, groupBy)
-
-	records := make([]inframonitoringtypes.ClusterRecord, 0, len(pageGroups))
-	for _, labels := range pageGroups {
-		compositeKey := compositeKeyFromLabels(labels, groupBy)
-		clusterName := labels[clusterNameAttrKey]
-
-		record := inframonitoringtypes.ClusterRecord{ // initialize with default values
-			ClusterName:              clusterName,
-			ClusterCPU:               -1,
-			ClusterCPUAllocatable:    -1,
-			ClusterMemory:            -1,
-			ClusterMemoryAllocatable: -1,
-			Meta:                     map[string]string{},
-		}
-
-		if metrics, ok := metricsMap[compositeKey]; ok {
-			if v, exists := metrics["A"]; exists {
-				record.ClusterCPU = v
-			}
-			if v, exists := metrics["B"]; exists {
-				record.ClusterCPUAllocatable = v
-			}
-			if v, exists := metrics["C"]; exists {
-				record.ClusterMemory = v
-			}
-			if v, exists := metrics["D"]; exists {
-				record.ClusterMemoryAllocatable = v
-			}
-		}
-
-		if conditionCountsForGroup, ok := nodeConditionCountsMap[compositeKey]; ok {
-			record.NodeCountsByReadiness = inframonitoringtypes.NodeCountsByReadiness{
-				Ready:    conditionCountsForGroup.Ready,
-				NotReady: conditionCountsForGroup.NotReady,
-			}
-		}
-
-		if phaseCountsForGroup, ok := podPhaseCountsMap[compositeKey]; ok {
-			record.PodCountsByPhase = inframonitoringtypes.PodCountsByPhase{
-				Pending:   phaseCountsForGroup.Pending,
-				Running:   phaseCountsForGroup.Running,
-				Succeeded: phaseCountsForGroup.Succeeded,
-				Failed:    phaseCountsForGroup.Failed,
-				Unknown:   phaseCountsForGroup.Unknown,
-			}
-		}
-
-		if attrs, ok := metadataMap[compositeKey]; ok {
-			for k, v := range attrs {
-				record.Meta[k] = v
-			}
-		}
-
-		records = append(records, record)
-	}
-	return records
-}
-
-func (m *module) getTopClusterGroups(
-	ctx context.Context,
-	orgID valuer.UUID,
-	req *inframonitoringtypes.PostableClusters,
-	metadataMap map[string]map[string]string,
-) ([]map[string]string, error) {
-	orderByKey := req.OrderBy.Key.Name
-	queryNamesForOrderBy := orderByToClustersQueryNames[orderByKey]
-	rankingQueryName := queryNamesForOrderBy[len(queryNamesForOrderBy)-1]
-
-	topReq := &qbtypes.QueryRangeRequest{
-		Start:       uint64(req.Start),
-		End:         uint64(req.End),
-		RequestType: qbtypes.RequestTypeScalar,
-		CompositeQuery: qbtypes.CompositeQuery{
-			Queries: make([]qbtypes.QueryEnvelope, 0, len(queryNamesForOrderBy)),
-		},
-	}
-
-	for _, envelope := range m.newClustersTableListQuery().CompositeQuery.Queries {
-		if !slices.Contains(queryNamesForOrderBy, envelope.GetQueryName()) {
-			continue
-		}
-		copied := envelope
-		if copied.Type == qbtypes.QueryTypeBuilder {
-			existingExpr := ""
-			if f := copied.GetFilter(); f != nil {
-				existingExpr = f.Expression
-			}
-			reqFilterExpr := ""
-			if req.Filter != nil {
-				reqFilterExpr = req.Filter.Expression
-			}
-			merged := mergeFilterExpressions(existingExpr, reqFilterExpr)
-			copied.SetFilter(&qbtypes.Filter{Expression: merged})
-			copied.SetGroupBy(req.GroupBy)
-		}
-		topReq.CompositeQuery.Queries = append(topReq.CompositeQuery.Queries, copied)
-	}
-
-	resp, err := m.querier.QueryRange(ctx, orgID, topReq)
-	if err != nil {
-		return nil, err
-	}
-
-	allMetricGroups := parseAndSortGroups(resp, rankingQueryName, req.GroupBy, req.OrderBy.Direction)
-	return paginateWithBackfill(allMetricGroups, metadataMap, req.GroupBy, req.Offset, req.Limit), nil
-}
-
-func (m *module) getClustersTableMetadata(ctx context.Context, req *inframonitoringtypes.PostableClusters) (map[string]map[string]string, error) {
-	var nonGroupByAttrs []string
-	for _, key := range clusterAttrKeysForMetadata {
-		if !isKeyInGroupByAttrs(req.GroupBy, key) {
-			nonGroupByAttrs = append(nonGroupByAttrs, key)
-		}
-	}
-	return m.getMetadata(ctx, clustersTableMetricNamesList, req.GroupBy, nonGroupByAttrs, req.Filter, req.Start, req.End)
-}

pkg/modules/inframonitoring/implinframonitoring/clusters_constants.go

@@ -1,140 +0,0 @@
-package implinframonitoring
-
-import (
-	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
-	"github.com/SigNoz/signoz/pkg/types/metrictypes"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
-)
-
-// TODO(nikhilmantri0902): change to k8s.cluster.uid after showing the missing
-// data banner. Carried forward from v1 (see k8sClusterUIDAttrKey in
-// pkg/query-service/app/inframetrics/clusters.go).
-const clusterNameAttrKey = "k8s.cluster.name"
-
-var clusterNameGroupByKey = qbtypes.GroupByKey{
-	TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-		Name:          clusterNameAttrKey,
-		FieldContext:  telemetrytypes.FieldContextResource,
-		FieldDataType: telemetrytypes.FieldDataTypeString,
-	},
-}
-
-// clustersTableMetricNamesList drives the existence/retention check.
-// Includes k8s.node.condition_ready and k8s.pod.phase so the response
-// short-circuits cleanly when a cluster doesn't ship those metrics — even
-// though they aren't part of the QB composite query (they're queried separately
-// via getPerGroupNodeConditionCounts and getPerGroupPodPhaseCounts).
-var clustersTableMetricNamesList = []string{
-	"k8s.node.cpu.usage",
-	"k8s.node.allocatable_cpu",
-	"k8s.node.memory.working_set",
-	"k8s.node.allocatable_memory",
-	"k8s.node.condition_ready", //TODO(nikhilmantri0902): should these metrics be used to count groups k8s.node.condition_ready and k8s.pod.phase
-	"k8s.pod.phase",
-}
-
-var clusterAttrKeysForMetadata = []string{
-	"k8s.cluster.name",
-}
-
-var orderByToClustersQueryNames = map[string][]string{
-	inframonitoringtypes.ClustersOrderByCPU:               {"A"},
-	inframonitoringtypes.ClustersOrderByCPUAllocatable:    {"B"},
-	inframonitoringtypes.ClustersOrderByMemory:            {"C"},
-	inframonitoringtypes.ClustersOrderByMemoryAllocatable: {"D"},
-}
-
-// newClustersTableListQuery builds the composite QB v5 request for the clusters list.
-// Cluster-scope metrics are derived by summing per-node metrics within the
-// group (default group: k8s.cluster.name). Node condition counts and pod phase
-// counts are derived separately via getPerGroupNodeConditionCounts and
-// getPerGroupPodPhaseCounts respectively (works for both list and grouped_list
-// modes), so neither is included here. Query letters A/B/C/D mirror the v1
-// implementation and the v2 nodes list.
-func (m *module) newClustersTableListQuery() *qbtypes.QueryRangeRequest {
-	queries := []qbtypes.QueryEnvelope{
-		// Query A: CPU usage — sum of node CPU within the group.
-		{
-			Type: qbtypes.QueryTypeBuilder,
-			Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Name:   "A",
-				Signal: telemetrytypes.SignalMetrics,
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "k8s.node.cpu.usage",
-						TimeAggregation:  metrictypes.TimeAggregationAvg,
-						SpaceAggregation: metrictypes.SpaceAggregationSum,
-						ReduceTo:         qbtypes.ReduceToAvg,
-					},
-				},
-				GroupBy:  []qbtypes.GroupByKey{clusterNameGroupByKey},
-				Disabled: false,
-			},
-		},
-		// Query B: CPU allocatable — sum of node allocatable CPU within the group.
-		// TimeAggregationLatest is the closest v5 equivalent of v1's AnyLast;
-		// allocatable values change rarely so divergence in practice is negligible.
-		{
-			Type: qbtypes.QueryTypeBuilder,
-			Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Name:   "B",
-				Signal: telemetrytypes.SignalMetrics,
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "k8s.node.allocatable_cpu",
-						TimeAggregation:  metrictypes.TimeAggregationLatest,
-						SpaceAggregation: metrictypes.SpaceAggregationSum,
-						ReduceTo:         qbtypes.ReduceToAvg,
-					},
-				},
-				GroupBy:  []qbtypes.GroupByKey{clusterNameGroupByKey},
-				Disabled: false,
-			},
-		},
-		// Query C: Memory working set — sum of node memory within the group.
-		{
-			Type: qbtypes.QueryTypeBuilder,
-			Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Name:   "C",
-				Signal: telemetrytypes.SignalMetrics,
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "k8s.node.memory.working_set",
-						TimeAggregation:  metrictypes.TimeAggregationAvg,
-						SpaceAggregation: metrictypes.SpaceAggregationSum,
-						ReduceTo:         qbtypes.ReduceToAvg,
-					},
-				},
-				GroupBy:  []qbtypes.GroupByKey{clusterNameGroupByKey},
-				Disabled: false,
-			},
-		},
-		// Query D: Memory allocatable — sum of node allocatable memory within the group.
-		// Same Latest caveat as Query B.
-		{
-			Type: qbtypes.QueryTypeBuilder,
-			Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Name:   "D",
-				Signal: telemetrytypes.SignalMetrics,
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "k8s.node.allocatable_memory",
-						TimeAggregation:  metrictypes.TimeAggregationLatest,
-						SpaceAggregation: metrictypes.SpaceAggregationSum,
-						ReduceTo:         qbtypes.ReduceToAvg,
-					},
-				},
-				GroupBy:  []qbtypes.GroupByKey{clusterNameGroupByKey},
-				Disabled: false,
-			},
-		},
-	}
-
-	return &qbtypes.QueryRangeRequest{
-		RequestType: qbtypes.RequestTypeScalar,
-		CompositeQuery: qbtypes.CompositeQuery{
-			Queries: queries,
-		},
-	}
-}

pkg/modules/inframonitoring/implinframonitoring/handler.go

@@ -69,75 +69,3 @@ func (h *handler) ListPods(rw http.ResponseWriter, req *http.Request) {
 
 	render.Success(rw, http.StatusOK, result)
 }
-
-func (h *handler) ListNodes(rw http.ResponseWriter, req *http.Request) {
-	claims, err := authtypes.ClaimsFromContext(req.Context())
-	if err != nil {
-		render.Error(rw, err)
-		return
-	}
-
-	orgID := valuer.MustNewUUID(claims.OrgID)
-
-	var parsedReq inframonitoringtypes.PostableNodes
-	if err := binding.JSON.BindBody(req.Body, &parsedReq); err != nil {
-		render.Error(rw, err)
-		return
-	}
-
-	result, err := h.module.ListNodes(req.Context(), orgID, &parsedReq)
-	if err != nil {
-		render.Error(rw, err)
-		return
-	}
-
-	render.Success(rw, http.StatusOK, result)
-}
-
-func (h *handler) ListNamespaces(rw http.ResponseWriter, req *http.Request) {
-	claims, err := authtypes.ClaimsFromContext(req.Context())
-	if err != nil {
-		render.Error(rw, err)
-		return
-	}
-
-	orgID := valuer.MustNewUUID(claims.OrgID)
-
-	var parsedReq inframonitoringtypes.PostableNamespaces
-	if err := binding.JSON.BindBody(req.Body, &parsedReq); err != nil {
-		render.Error(rw, err)
-		return
-	}
-
-	result, err := h.module.ListNamespaces(req.Context(), orgID, &parsedReq)
-	if err != nil {
-		render.Error(rw, err)
-		return
-	}
-
-	render.Success(rw, http.StatusOK, result)
-}
-
-func (h *handler) ListClusters(rw http.ResponseWriter, req *http.Request) {
-	claims, err := authtypes.ClaimsFromContext(req.Context())
-	if err != nil {
-		render.Error(rw, err)
-		return
-	}
-
-	orgID := valuer.MustNewUUID(claims.OrgID)
-
-	var parsedReq inframonitoringtypes.PostableClusters
-	if err := binding.JSON.BindBody(req.Body, &parsedReq); err != nil {
-		render.Error(rw, err)
-		return
-	}
-
-	result, err := h.module.ListClusters(req.Context(), orgID, &parsedReq)
-	if err != nil {
-		render.Error(rw, err)
-		return
-	}
-
-	render.Success(rw, http.StatusOK, result)
-}

pkg/modules/inframonitoring/implinframonitoring/hosts.go

@@ -174,7 +174,7 @@ func buildHostRecords(
 			Wait:              -1,
 			Load15:            -1,
 			DiskUsage:         -1,
-			Meta:              map[string]string{},
+			Meta:              map[string]any{},
 		}
 
 		if metrics, ok := metricsMap[compositeKey]; ok {

pkg/modules/inframonitoring/implinframonitoring/internaltypes.go

@@ -23,9 +23,3 @@ type podPhaseCounts struct {
 	Failed    int
 	Unknown   int
 }
-
-// nodeConditionCounts holds per-group node counts bucketed by latest condition_ready in window.
-type nodeConditionCounts struct {
-	Ready    int
-	NotReady int
-}

pkg/modules/inframonitoring/implinframonitoring/module.go

@@ -242,289 +242,3 @@ func (m *module) ListPods(ctx context.Context, orgID valuer.UUID, req *inframoni
 
 	return resp, nil
 }
-
-func (m *module) ListNodes(ctx context.Context, orgID valuer.UUID, req *inframonitoringtypes.PostableNodes) (*inframonitoringtypes.Nodes, error) {
-	if err := req.Validate(); err != nil {
-		return nil, err
-	}
-
-	resp := &inframonitoringtypes.Nodes{}
-
-	if req.OrderBy == nil {
-		req.OrderBy = &qbtypes.OrderBy{
-			Key: qbtypes.OrderByKey{
-				TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-					Name: inframonitoringtypes.NodesOrderByCPU,
-				},
-			},
-			Direction: qbtypes.OrderDirectionDesc,
-		}
-	}
-
-	if len(req.GroupBy) == 0 {
-		req.GroupBy = []qbtypes.GroupByKey{nodeNameGroupByKey}
-		resp.Type = inframonitoringtypes.ResponseTypeList
-	} else {
-		resp.Type = inframonitoringtypes.ResponseTypeGroupedList
-	}
-
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(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 {
-		return nil, err
-	}
-
-	resp.Total = len(metadataMap)
-
-	pageGroups, err := m.getTopNodeGroups(ctx, orgID, req, metadataMap)
-	if err != nil {
-		return nil, err
-	}
-
-	if len(pageGroups) == 0 {
-		resp.Records = []inframonitoringtypes.NodeRecord{}
-		return resp, nil
-	}
-
-	filterExpr := ""
-	if req.Filter != nil {
-		filterExpr = req.Filter.Expression
-	}
-
-	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newNodesTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
-		return nil, err
-	}
-
-	nodeConditionCounts, err := m.getPerGroupNodeConditionCounts(ctx, req, pageGroups)
-	if err != nil {
-		return nil, err
-	}
-
-	// Reuse the pods phase-counts CTE function via a temp struct — it reads only
-	// Start/End/Filter/GroupBy from PostablePods.
-	podPhaseCounts, err := m.getPerGroupPodPhaseCounts(ctx, &inframonitoringtypes.PostablePods{
-		Start:   req.Start,
-		End:     req.End,
-		Filter:  req.Filter,
-		GroupBy: req.GroupBy,
-	}, pageGroups)
-	if err != nil {
-		return nil, err
-	}
-
-	isNodeNameInGroupBy := isKeyInGroupByAttrs(req.GroupBy, nodeNameAttrKey)
-	resp.Records = buildNodeRecords(isNodeNameInGroupBy, queryResp, pageGroups, req.GroupBy, metadataMap, nodeConditionCounts, podPhaseCounts)
-	resp.Warning = queryResp.Warning
-
-	return resp, nil
-}
-
-func (m *module) ListNamespaces(ctx context.Context, orgID valuer.UUID, req *inframonitoringtypes.PostableNamespaces) (*inframonitoringtypes.Namespaces, error) {
-	if err := req.Validate(); err != nil {
-		return nil, err
-	}
-
-	resp := &inframonitoringtypes.Namespaces{}
-
-	if req.OrderBy == nil {
-		req.OrderBy = &qbtypes.OrderBy{
-			Key: qbtypes.OrderByKey{
-				TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-					Name: inframonitoringtypes.NamespacesOrderByCPU,
-				},
-			},
-			Direction: qbtypes.OrderDirectionDesc,
-		}
-	}
-
-	if len(req.GroupBy) == 0 {
-		req.GroupBy = []qbtypes.GroupByKey{namespaceNameGroupByKey}
-		resp.Type = inframonitoringtypes.ResponseTypeList
-	} else {
-		resp.Type = inframonitoringtypes.ResponseTypeGroupedList
-	}
-
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(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 {
-		return nil, err
-	}
-
-	resp.Total = len(metadataMap)
-
-	pageGroups, err := m.getTopNamespaceGroups(ctx, orgID, req, metadataMap)
-	if err != nil {
-		return nil, err
-	}
-
-	if len(pageGroups) == 0 {
-		resp.Records = []inframonitoringtypes.NamespaceRecord{}
-		return resp, nil
-	}
-
-	filterExpr := ""
-	if req.Filter != nil {
-		filterExpr = req.Filter.Expression
-	}
-
-	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newNamespacesTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
-		return nil, err
-	}
-
-	// Reuse the pods phase-counts CTE function via a temp struct — it reads only
-	// Start/End/Filter/GroupBy from PostablePods.
-	phaseCounts, err := m.getPerGroupPodPhaseCounts(ctx, &inframonitoringtypes.PostablePods{
-		Start:   req.Start,
-		End:     req.End,
-		Filter:  req.Filter,
-		GroupBy: req.GroupBy,
-	}, pageGroups)
-	if err != nil {
-		return nil, err
-	}
-
-	resp.Records = buildNamespaceRecords(queryResp, pageGroups, req.GroupBy, metadataMap, phaseCounts)
-	resp.Warning = queryResp.Warning
-
-	return resp, nil
-}
-
-func (m *module) ListClusters(ctx context.Context, orgID valuer.UUID, req *inframonitoringtypes.PostableClusters) (*inframonitoringtypes.Clusters, error) {
-	if err := req.Validate(); err != nil {
-		return nil, err
-	}
-
-	resp := &inframonitoringtypes.Clusters{}
-
-	if req.OrderBy == nil {
-		req.OrderBy = &qbtypes.OrderBy{
-			Key: qbtypes.OrderByKey{
-				TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-					Name: inframonitoringtypes.ClustersOrderByCPU,
-				},
-			},
-			Direction: qbtypes.OrderDirectionDesc,
-		}
-	}
-
-	if len(req.GroupBy) == 0 {
-		req.GroupBy = []qbtypes.GroupByKey{clusterNameGroupByKey}
-		resp.Type = inframonitoringtypes.ResponseTypeList
-	} else {
-		resp.Type = inframonitoringtypes.ResponseTypeGroupedList
-	}
-
-	missingMetrics, minFirstReportedUnixMilli, err := m.getMetricsExistenceAndEarliestTime(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 {
-		return nil, err
-	}
-
-	resp.Total = len(metadataMap)
-
-	pageGroups, err := m.getTopClusterGroups(ctx, orgID, req, metadataMap)
-	if err != nil {
-		return nil, err
-	}
-
-	if len(pageGroups) == 0 {
-		resp.Records = []inframonitoringtypes.ClusterRecord{}
-		return resp, nil
-	}
-
-	filterExpr := ""
-	if req.Filter != nil {
-		filterExpr = req.Filter.Expression
-	}
-
-	fullQueryReq := buildFullQueryRequest(req.Start, req.End, filterExpr, req.GroupBy, pageGroups, m.newClustersTableListQuery())
-	queryResp, err := m.querier.QueryRange(ctx, orgID, fullQueryReq)
-	if err != nil {
-		return nil, err
-	}
-
-	// Reuse the nodes condition-counts CTE function via a temp struct — it reads only
-	// Start/End/Filter/GroupBy from PostableNodes. With default groupBy
-	// [k8s.cluster.name], counts are bucketed per cluster; with a custom groupBy,
-	// they aggregate across clusters in that group.
-	nodeConditionCountsMap, err := m.getPerGroupNodeConditionCounts(ctx, &inframonitoringtypes.PostableNodes{
-		Start:   req.Start,
-		End:     req.End,
-		Filter:  req.Filter,
-		GroupBy: req.GroupBy,
-	}, pageGroups)
-	if err != nil {
-		return nil, err
-	}
-
-	// Same pattern for pod phase counts via PostablePods shim.
-	podPhaseCountsMap, err := m.getPerGroupPodPhaseCounts(ctx, &inframonitoringtypes.PostablePods{
-		Start:   req.Start,
-		End:     req.End,
-		Filter:  req.Filter,
-		GroupBy: req.GroupBy,
-	}, pageGroups)
-	if err != nil {
-		return nil, err
-	}
-
-	resp.Records = buildClusterRecords(queryResp, pageGroups, req.GroupBy, metadataMap, nodeConditionCountsMap, podPhaseCountsMap)
-	resp.Warning = queryResp.Warning
-
-	return resp, nil
-}

pkg/modules/inframonitoring/implinframonitoring/namespaces.go

@@ -1,123 +0,0 @@
-package implinframonitoring
-
-import (
-	"context"
-	"slices"
-
-	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-	"github.com/SigNoz/signoz/pkg/valuer"
-)
-
-// buildNamespaceRecords assembles the page records. Pod phase counts come from
-// phaseCounts in both modes; every row is a group of pods, so there's no
-// per-row "current phase" concept (unlike pods/nodes list mode).
-func buildNamespaceRecords(
-	resp *qbtypes.QueryRangeResponse,
-	pageGroups []map[string]string,
-	groupBy []qbtypes.GroupByKey,
-	metadataMap map[string]map[string]string,
-	phaseCounts map[string]podPhaseCounts,
-) []inframonitoringtypes.NamespaceRecord {
-	metricsMap := parseFullQueryResponse(resp, groupBy)
-
-	records := make([]inframonitoringtypes.NamespaceRecord, 0, len(pageGroups))
-	for _, labels := range pageGroups {
-		compositeKey := compositeKeyFromLabels(labels, groupBy)
-		namespaceName := labels[namespaceNameAttrKey]
-
-		record := inframonitoringtypes.NamespaceRecord{ // initialize with default values
-			NamespaceName:   namespaceName,
-			NamespaceCPU:    -1,
-			NamespaceMemory: -1,
-			Meta:            map[string]string{},
-		}
-
-		if metrics, ok := metricsMap[compositeKey]; ok {
-			if v, exists := metrics["A"]; exists {
-				record.NamespaceCPU = v
-			}
-			if v, exists := metrics["D"]; exists {
-				record.NamespaceMemory = v
-			}
-		}
-
-		if phaseCountsForGroup, ok := phaseCounts[compositeKey]; ok {
-			record.PodCountsByPhase = inframonitoringtypes.PodCountsByPhase{
-				Pending:   phaseCountsForGroup.Pending,
-				Running:   phaseCountsForGroup.Running,
-				Succeeded: phaseCountsForGroup.Succeeded,
-				Failed:    phaseCountsForGroup.Failed,
-				Unknown:   phaseCountsForGroup.Unknown,
-			}
-		}
-
-		if attrs, ok := metadataMap[compositeKey]; ok {
-			for k, v := range attrs {
-				record.Meta[k] = v
-			}
-		}
-
-		records = append(records, record)
-	}
-	return records
-}
-
-func (m *module) getTopNamespaceGroups(
-	ctx context.Context,
-	orgID valuer.UUID,
-	req *inframonitoringtypes.PostableNamespaces,
-	metadataMap map[string]map[string]string,
-) ([]map[string]string, error) {
-	orderByKey := req.OrderBy.Key.Name
-	queryNamesForOrderBy := orderByToNamespacesQueryNames[orderByKey]
-	rankingQueryName := queryNamesForOrderBy[len(queryNamesForOrderBy)-1]
-
-	topReq := &qbtypes.QueryRangeRequest{
-		Start:       uint64(req.Start),
-		End:         uint64(req.End),
-		RequestType: qbtypes.RequestTypeScalar,
-		CompositeQuery: qbtypes.CompositeQuery{
-			Queries: make([]qbtypes.QueryEnvelope, 0, len(queryNamesForOrderBy)),
-		},
-	}
-
-	for _, envelope := range m.newNamespacesTableListQuery().CompositeQuery.Queries {
-		if !slices.Contains(queryNamesForOrderBy, envelope.GetQueryName()) {
-			continue
-		}
-		copied := envelope
-		if copied.Type == qbtypes.QueryTypeBuilder {
-			existingExpr := ""
-			if f := copied.GetFilter(); f != nil {
-				existingExpr = f.Expression
-			}
-			reqFilterExpr := ""
-			if req.Filter != nil {
-				reqFilterExpr = req.Filter.Expression
-			}
-			merged := mergeFilterExpressions(existingExpr, reqFilterExpr)
-			copied.SetFilter(&qbtypes.Filter{Expression: merged})
-			copied.SetGroupBy(req.GroupBy)
-		}
-		topReq.CompositeQuery.Queries = append(topReq.CompositeQuery.Queries, copied)
-	}
-
-	resp, err := m.querier.QueryRange(ctx, orgID, topReq)
-	if err != nil {
-		return nil, err
-	}
-
-	allMetricGroups := parseAndSortGroups(resp, rankingQueryName, req.GroupBy, req.OrderBy.Direction)
-	return paginateWithBackfill(allMetricGroups, metadataMap, req.GroupBy, req.Offset, req.Limit), nil
-}
-
-func (m *module) getNamespacesTableMetadata(ctx context.Context, req *inframonitoringtypes.PostableNamespaces) (map[string]map[string]string, error) {
-	var nonGroupByAttrs []string
-	for _, key := range namespaceAttrKeysForMetadata {
-		if !isKeyInGroupByAttrs(req.GroupBy, key) {
-			nonGroupByAttrs = append(nonGroupByAttrs, key)
-		}
-	}
-	return m.getMetadata(ctx, namespacesTableMetricNamesList, req.GroupBy, nonGroupByAttrs, req.Filter, req.Start, req.End)
-}

pkg/modules/inframonitoring/implinframonitoring/namespaces_constants.go

@@ -1,92 +0,0 @@
-package implinframonitoring
-
-import (
-	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
-	"github.com/SigNoz/signoz/pkg/types/metrictypes"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
-)
-
-const (
-	namespaceNameAttrKey = "k8s.namespace.name"
-)
-
-var namespaceNameGroupByKey = qbtypes.GroupByKey{
-	TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-		Name:          namespaceNameAttrKey,
-		FieldContext:  telemetrytypes.FieldContextResource,
-		FieldDataType: telemetrytypes.FieldDataTypeString,
-	},
-}
-
-// namespacesTableMetricNamesList drives the existence/retention check.
-// Includes k8s.pod.phase so the response short-circuits cleanly when a
-// cluster doesn't ship the metric — even though phase isn't part of the
-// QB composite query (it's queried separately via getPerGroupPodPhaseCounts).
-var namespacesTableMetricNamesList = []string{
-	"k8s.pod.cpu.usage",
-	"k8s.pod.memory.working_set",
-	"k8s.pod.phase",
-}
-
-var namespaceAttrKeysForMetadata = []string{
-	"k8s.namespace.name",
-	"k8s.cluster.name",
-}
-
-var orderByToNamespacesQueryNames = map[string][]string{
-	inframonitoringtypes.NamespacesOrderByCPU:    {"A"},
-	inframonitoringtypes.NamespacesOrderByMemory: {"D"},
-}
-
-// newNamespacesTableListQuery builds the composite QB v5 request for the namespaces list.
-// Pod phase counts are derived separately via getPerGroupPodPhaseCounts (works for both
-// list and grouped_list modes), so no phase query is included here.
-// Query letters A and D are kept aligned with the v1 implementation.
-func (m *module) newNamespacesTableListQuery() *qbtypes.QueryRangeRequest {
-	queries := []qbtypes.QueryEnvelope{
-		// Query A: CPU usage — sum of pod CPU within the group.
-		{
-			Type: qbtypes.QueryTypeBuilder,
-			Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Name:   "A",
-				Signal: telemetrytypes.SignalMetrics,
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "k8s.pod.cpu.usage",
-						TimeAggregation:  metrictypes.TimeAggregationAvg,
-						SpaceAggregation: metrictypes.SpaceAggregationSum,
-						ReduceTo:         qbtypes.ReduceToAvg,
-					},
-				},
-				GroupBy:  []qbtypes.GroupByKey{namespaceNameGroupByKey},
-				Disabled: false,
-			},
-		},
-		// Query D: Memory working set — sum of pod memory within the group.
-		{
-			Type: qbtypes.QueryTypeBuilder,
-			Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Name:   "D",
-				Signal: telemetrytypes.SignalMetrics,
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "k8s.pod.memory.working_set",
-						TimeAggregation:  metrictypes.TimeAggregationAvg,
-						SpaceAggregation: metrictypes.SpaceAggregationSum,
-						ReduceTo:         qbtypes.ReduceToAvg,
-					},
-				},
-				GroupBy:  []qbtypes.GroupByKey{namespaceNameGroupByKey},
-				Disabled: false,
-			},
-		},
-	}
-
-	return &qbtypes.QueryRangeRequest{
-		RequestType: qbtypes.RequestTypeScalar,
-		CompositeQuery: qbtypes.CompositeQuery{
-			Queries: queries,
-		},
-	}
-}

pkg/modules/inframonitoring/implinframonitoring/nodes.go

@@ -1,312 +0,0 @@
-package implinframonitoring
-
-import (
-	"context"
-	"fmt"
-	"slices"
-	"strings"
-
-	"github.com/SigNoz/signoz/pkg/querybuilder"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
-	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
-	"github.com/SigNoz/signoz/pkg/types/metrictypes"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-	"github.com/SigNoz/signoz/pkg/valuer"
-	"github.com/huandu/go-sqlbuilder"
-)
-
-// buildNodeRecords assembles the page records. Condition counts come from
-// conditionCounts in both modes. In list mode (isNodeNameInGroupBy=true) each
-// group is one node, so exactly one count is 1; Condition is derived from
-// which one. In grouped_list mode Condition stays NodeConditionNoData.
-func buildNodeRecords(
-	isNodeNameInGroupBy bool,
-	resp *qbtypes.QueryRangeResponse,
-	pageGroups []map[string]string,
-	groupBy []qbtypes.GroupByKey,
-	metadataMap map[string]map[string]string,
-	nodeConditionCounts map[string]nodeConditionCounts,
-	podPhaseCounts map[string]podPhaseCounts,
-) []inframonitoringtypes.NodeRecord {
-	metricsMap := parseFullQueryResponse(resp, groupBy)
-
-	records := make([]inframonitoringtypes.NodeRecord, 0, len(pageGroups))
-	for _, labels := range pageGroups {
-		compositeKey := compositeKeyFromLabels(labels, groupBy)
-		nodeName := labels[nodeNameAttrKey]
-
-		record := inframonitoringtypes.NodeRecord{ // initialize with default values
-			NodeName:              nodeName,
-			Condition:             inframonitoringtypes.NodeConditionNoData,
-			NodeCPU:               -1,
-			NodeCPUAllocatable:    -1,
-			NodeMemory:            -1,
-			NodeMemoryAllocatable: -1,
-			Meta:                  map[string]string{},
-		}
-
-		if metrics, ok := metricsMap[compositeKey]; ok {
-			if v, exists := metrics["A"]; exists {
-				record.NodeCPU = v
-			}
-			if v, exists := metrics["B"]; exists {
-				record.NodeCPUAllocatable = v
-			}
-			if v, exists := metrics["C"]; exists {
-				record.NodeMemory = v
-			}
-			if v, exists := metrics["D"]; exists {
-				record.NodeMemoryAllocatable = v
-			}
-		}
-
-		if nodeConditionCountsForGroup, ok := nodeConditionCounts[compositeKey]; ok {
-			record.NodeCountsByReadiness = inframonitoringtypes.NodeCountsByReadiness{
-				Ready:    nodeConditionCountsForGroup.Ready,
-				NotReady: nodeConditionCountsForGroup.NotReady,
-			}
-
-			// In list mode each group is one node; the count==1 bucket identifies the condition.
-			if isNodeNameInGroupBy {
-				switch {
-				case nodeConditionCountsForGroup.Ready == 1:
-					record.Condition = inframonitoringtypes.NodeConditionReady
-				case nodeConditionCountsForGroup.NotReady == 1:
-					record.Condition = inframonitoringtypes.NodeConditionNotReady
-				}
-			}
-		}
-
-		if podPhaseCountsForGroup, ok := podPhaseCounts[compositeKey]; ok {
-			record.PodCountsByPhase = inframonitoringtypes.PodCountsByPhase{
-				Pending:   podPhaseCountsForGroup.Pending,
-				Running:   podPhaseCountsForGroup.Running,
-				Succeeded: podPhaseCountsForGroup.Succeeded,
-				Failed:    podPhaseCountsForGroup.Failed,
-				Unknown:   podPhaseCountsForGroup.Unknown,
-			}
-		}
-
-		if attrs, ok := metadataMap[compositeKey]; ok {
-			for k, v := range attrs {
-				record.Meta[k] = v
-			}
-		}
-
-		records = append(records, record)
-	}
-	return records
-}
-
-func (m *module) getTopNodeGroups(
-	ctx context.Context,
-	orgID valuer.UUID,
-	req *inframonitoringtypes.PostableNodes,
-	metadataMap map[string]map[string]string,
-) ([]map[string]string, error) {
-	orderByKey := req.OrderBy.Key.Name
-	queryNamesForOrderBy := orderByToNodesQueryNames[orderByKey]
-	rankingQueryName := queryNamesForOrderBy[len(queryNamesForOrderBy)-1]
-
-	topReq := &qbtypes.QueryRangeRequest{
-		Start:       uint64(req.Start),
-		End:         uint64(req.End),
-		RequestType: qbtypes.RequestTypeScalar,
-		CompositeQuery: qbtypes.CompositeQuery{
-			Queries: make([]qbtypes.QueryEnvelope, 0, len(queryNamesForOrderBy)),
-		},
-	}
-
-	for _, envelope := range m.newNodesTableListQuery().CompositeQuery.Queries {
-		if !slices.Contains(queryNamesForOrderBy, envelope.GetQueryName()) {
-			continue
-		}
-		copied := envelope
-		if copied.Type == qbtypes.QueryTypeBuilder {
-			existingExpr := ""
-			if f := copied.GetFilter(); f != nil {
-				existingExpr = f.Expression
-			}
-			reqFilterExpr := ""
-			if req.Filter != nil {
-				reqFilterExpr = req.Filter.Expression
-			}
-			merged := mergeFilterExpressions(existingExpr, reqFilterExpr)
-			copied.SetFilter(&qbtypes.Filter{Expression: merged})
-			copied.SetGroupBy(req.GroupBy)
-		}
-		topReq.CompositeQuery.Queries = append(topReq.CompositeQuery.Queries, copied)
-	}
-
-	resp, err := m.querier.QueryRange(ctx, orgID, topReq)
-	if err != nil {
-		return nil, err
-	}
-
-	allMetricGroups := parseAndSortGroups(resp, rankingQueryName, req.GroupBy, req.OrderBy.Direction)
-	return paginateWithBackfill(allMetricGroups, metadataMap, req.GroupBy, req.Offset, req.Limit), nil
-}
-
-func (m *module) getNodesTableMetadata(ctx context.Context, req *inframonitoringtypes.PostableNodes) (map[string]map[string]string, error) {
-	var nonGroupByAttrs []string
-	for _, key := range nodeAttrKeysForMetadata {
-		if !isKeyInGroupByAttrs(req.GroupBy, key) {
-			nonGroupByAttrs = append(nonGroupByAttrs, key)
-		}
-	}
-	return m.getMetadata(ctx, nodesTableMetricNamesList, req.GroupBy, nonGroupByAttrs, req.Filter, req.Start, req.End)
-}
-
-// getPerGroupNodeConditionCounts computes per-group node counts bucketed by each
-// node's latest condition_ready value (0 / 1) in the requested window.
-// Pipeline:
-//
-//	timeSeriesFPs:           fp ↔ (node_name, groupBy cols) from the time_series table.
-//	                         User filter + page-groups filter applied here.
-//	latestConditionPerNode:  INNER JOIN samples × timeSeriesFPs, collapsed to
-//	                         the latest condition value per node via argMax(value, unix_milli).
-//	countNodesPerCondition:  per-group uniqExactIf into ready/not_ready buckets.
-//
-// Groups absent from the result map have implicit zero counts (caller default).
-func (m *module) getPerGroupNodeConditionCounts(
-	ctx context.Context,
-	req *inframonitoringtypes.PostableNodes,
-	pageGroups []map[string]string,
-) (map[string]nodeConditionCounts, error) {
-	if len(pageGroups) == 0 || len(req.GroupBy) == 0 {
-		return map[string]nodeConditionCounts{}, nil
-	}
-
-	// Merged filter expression (user filter + page-groups IN clauses).
-	reqFilterExpr := ""
-	if req.Filter != nil {
-		reqFilterExpr = req.Filter.Expression
-	}
-	pageGroupsFilterExpr := buildPageGroupsFilterExpr(pageGroups)
-	filterExpr := mergeFilterExpressions(reqFilterExpr, pageGroupsFilterExpr)
-
-	// Resolve tables. Same convention as pods.
-	adjustedStart, adjustedEnd, _, localTimeSeriesTable := telemetrymetrics.WhichTSTableToUse(
-		uint64(req.Start), uint64(req.End), nil,
-	)
-	samplesTable := telemetrymetrics.WhichSamplesTableToUse(
-		uint64(req.Start), uint64(req.End),
-		metrictypes.UnspecifiedType, metrictypes.TimeAggregationUnspecified, nil,
-	)
-	valueCol := telemetrymetrics.ValueColumnForSamplesTable(samplesTable)
-
-	// ----- timeSeriesFPs -----
-	timeSeriesFPs := sqlbuilder.NewSelectBuilder()
-	timeSeriesFPsSelectCols := []string{
-		"fingerprint",
-		fmt.Sprintf("JSONExtractString(labels, %s) AS node_name", timeSeriesFPs.Var(nodeNameAttrKey)),
-	}
-	for _, key := range req.GroupBy {
-		timeSeriesFPsSelectCols = append(timeSeriesFPsSelectCols,
-			fmt.Sprintf("JSONExtractString(labels, %s) AS %s", timeSeriesFPs.Var(key.Name), quoteIdentifier(key.Name)),
-		)
-	}
-	timeSeriesFPs.Select(timeSeriesFPsSelectCols...)
-	timeSeriesFPs.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
-	timeSeriesFPs.Where(
-		timeSeriesFPs.E("metric_name", nodeConditionMetricName),
-		timeSeriesFPs.GE("unix_milli", adjustedStart),
-		timeSeriesFPs.L("unix_milli", adjustedEnd),
-	)
-	if filterExpr != "" {
-		filterClause, err := m.buildFilterClause(ctx, &qbtypes.Filter{Expression: filterExpr}, req.Start, req.End)
-		if err != nil {
-			return nil, err
-		}
-		if filterClause != nil {
-			timeSeriesFPs.AddWhereClause(filterClause)
-		}
-	}
-	timeSeriesFPsGroupBy := []string{"fingerprint", "node_name"}
-	for _, key := range req.GroupBy {
-		timeSeriesFPsGroupBy = append(timeSeriesFPsGroupBy, quoteIdentifier(key.Name))
-	}
-	timeSeriesFPs.GroupBy(timeSeriesFPsGroupBy...)
-	timeSeriesFPsSQL, timeSeriesFPsArgs := timeSeriesFPs.BuildWithFlavor(sqlbuilder.ClickHouse)
-
-	// ----- latestConditionPerNode -----
-	latestConditionPerNode := sqlbuilder.NewSelectBuilder()
-	latestConditionPerNodeSelectCols := []string{"tsfp.node_name AS node_name"}
-	latestConditionPerNodeGroupBy := []string{"node_name"}
-	for _, key := range req.GroupBy {
-		col := quoteIdentifier(key.Name)
-		latestConditionPerNodeSelectCols = append(latestConditionPerNodeSelectCols, fmt.Sprintf("tsfp.%s AS %s", col, col))
-		latestConditionPerNodeGroupBy = append(latestConditionPerNodeGroupBy, col)
-	}
-	latestConditionPerNodeSelectCols = append(latestConditionPerNodeSelectCols,
-		fmt.Sprintf("argMax(samples.%s, samples.unix_milli) AS condition_value", valueCol),
-	)
-	latestConditionPerNode.Select(latestConditionPerNodeSelectCols...)
-	latestConditionPerNode.From(fmt.Sprintf(
-		"%s.%s AS samples INNER JOIN time_series_fps AS tsfp ON samples.fingerprint = tsfp.fingerprint",
-		telemetrymetrics.DBName, samplesTable,
-	))
-	latestConditionPerNode.Where(
-		latestConditionPerNode.E("samples.metric_name", nodeConditionMetricName),
-		latestConditionPerNode.GE("samples.unix_milli", req.Start),
-		latestConditionPerNode.L("samples.unix_milli", req.End),
-		"tsfp.node_name != ''",
-	)
-	latestConditionPerNode.GroupBy(latestConditionPerNodeGroupBy...)
-	latestConditionPerNodeSQL, latestConditionPerNodeArgs := latestConditionPerNode.BuildWithFlavor(sqlbuilder.ClickHouse)
-
-	// ----- countNodesPerCondition (outer SELECT) -----
-	countNodesPerConditionSelectCols := make([]string, 0, len(req.GroupBy)+2)
-	countNodesPerConditionGroupBy := make([]string, 0, len(req.GroupBy))
-	for _, key := range req.GroupBy {
-		col := quoteIdentifier(key.Name)
-		countNodesPerConditionSelectCols = append(countNodesPerConditionSelectCols, col)
-		countNodesPerConditionGroupBy = append(countNodesPerConditionGroupBy, col)
-	}
-	countNodesPerConditionSelectCols = append(countNodesPerConditionSelectCols,
-		fmt.Sprintf("uniqExactIf(node_name, condition_value = %d) AS ready_count", inframonitoringtypes.NodeConditionNumReady),
-		fmt.Sprintf("uniqExactIf(node_name, condition_value = %d) AS not_ready_count", inframonitoringtypes.NodeConditionNumNotReady),
-	)
-	countNodesPerConditionSQL := fmt.Sprintf(
-		"SELECT %s FROM latest_condition_per_node GROUP BY %s",
-		strings.Join(countNodesPerConditionSelectCols, ", "),
-		strings.Join(countNodesPerConditionGroupBy, ", "),
-	)
-
-	// Combine CTEs + outer.
-	cteFragments := []string{
-		fmt.Sprintf("time_series_fps AS (%s)", timeSeriesFPsSQL),
-		fmt.Sprintf("latest_condition_per_node AS (%s)", latestConditionPerNodeSQL),
-	}
-	finalSQL := querybuilder.CombineCTEs(cteFragments) + countNodesPerConditionSQL
-	finalArgs := querybuilder.PrependArgs([][]any{timeSeriesFPsArgs, latestConditionPerNodeArgs}, nil)
-
-	rows, err := m.telemetryStore.ClickhouseDB().Query(ctx, finalSQL, finalArgs...)
-	if err != nil {
-		return nil, err
-	}
-	defer rows.Close()
-
-	result := make(map[string]nodeConditionCounts)
-	for rows.Next() {
-		groupVals := make([]string, len(req.GroupBy))
-		scanPtrs := make([]any, 0, len(req.GroupBy)+2)
-		for i := range groupVals {
-			scanPtrs = append(scanPtrs, &groupVals[i])
-		}
-		var ready, notReady uint64
-		scanPtrs = append(scanPtrs, &ready, &notReady)
-
-		if err := rows.Scan(scanPtrs...); err != nil {
-			return nil, err
-		}
-		result[compositeKeyFromList(groupVals)] = nodeConditionCounts{
-			Ready:    int(ready),
-			NotReady: int(notReady),
-		}
-	}
-	if err := rows.Err(); err != nil {
-		return nil, err
-	}
-	return result, nil
-}

pkg/modules/inframonitoring/implinframonitoring/nodes_constants.go

@@ -1,133 +0,0 @@
-package implinframonitoring
-
-import (
-	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
-	"github.com/SigNoz/signoz/pkg/types/metrictypes"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
-)
-
-const (
-	nodeNameAttrKey         = "k8s.node.name"
-	nodeConditionMetricName = "k8s.node.condition_ready"
-)
-
-var nodeNameGroupByKey = qbtypes.GroupByKey{
-	TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-		Name:          nodeNameAttrKey,
-		FieldContext:  telemetrytypes.FieldContextResource,
-		FieldDataType: telemetrytypes.FieldDataTypeString,
-	},
-}
-
-// nodesTableMetricNamesList drives the existence/retention check.
-// Includes condition_ready and pod.phase also.
-var nodesTableMetricNamesList = []string{
-	"k8s.node.cpu.usage",
-	"k8s.node.allocatable_cpu",
-	"k8s.node.memory.working_set",
-	"k8s.node.allocatable_memory",
-	"k8s.node.condition_ready",
-	"k8s.pod.phase",
-}
-
-var nodeAttrKeysForMetadata = []string{
-	"k8s.node.uid",
-	"k8s.cluster.name",
-}
-
-var orderByToNodesQueryNames = map[string][]string{
-	inframonitoringtypes.NodesOrderByCPU:               {"A"},
-	inframonitoringtypes.NodesOrderByCPUAllocatable:    {"B"},
-	inframonitoringtypes.NodesOrderByMemory:            {"C"},
-	inframonitoringtypes.NodesOrderByMemoryAllocatable: {"D"},
-}
-
-// newNodesTableListQuery builds the composite QB v5 request for the nodes list.
-// Node condition is derived separately via getPerGroupNodeConditionCounts (works
-// for both list and grouped_list modes), so no condition query is included here.
-func (m *module) newNodesTableListQuery() *qbtypes.QueryRangeRequest {
-	queries := []qbtypes.QueryEnvelope{
-		// Query A: CPU usage
-		{
-			Type: qbtypes.QueryTypeBuilder,
-			Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Name:   "A",
-				Signal: telemetrytypes.SignalMetrics,
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "k8s.node.cpu.usage",
-						TimeAggregation:  metrictypes.TimeAggregationAvg,
-						SpaceAggregation: metrictypes.SpaceAggregationSum,
-						ReduceTo:         qbtypes.ReduceToAvg,
-					},
-				},
-				GroupBy:  []qbtypes.GroupByKey{nodeNameGroupByKey},
-				Disabled: false,
-			},
-		},
-		// Query B: CPU allocatable.
-		// TimeAggregationLatest is the closest v5 equivalent of v1's AnyLast;
-		// allocatable values change rarely so divergence in practice is negligible.
-		{
-			Type: qbtypes.QueryTypeBuilder,
-			Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Name:   "B",
-				Signal: telemetrytypes.SignalMetrics,
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "k8s.node.allocatable_cpu",
-						TimeAggregation:  metrictypes.TimeAggregationLatest,
-						SpaceAggregation: metrictypes.SpaceAggregationSum,
-						ReduceTo:         qbtypes.ReduceToAvg,
-					},
-				},
-				GroupBy:  []qbtypes.GroupByKey{nodeNameGroupByKey},
-				Disabled: false,
-			},
-		},
-		// Query C: Memory working set
-		{
-			Type: qbtypes.QueryTypeBuilder,
-			Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Name:   "C",
-				Signal: telemetrytypes.SignalMetrics,
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "k8s.node.memory.working_set",
-						TimeAggregation:  metrictypes.TimeAggregationAvg,
-						SpaceAggregation: metrictypes.SpaceAggregationSum,
-						ReduceTo:         qbtypes.ReduceToAvg,
-					},
-				},
-				GroupBy:  []qbtypes.GroupByKey{nodeNameGroupByKey},
-				Disabled: false,
-			},
-		},
-		// Query D: Memory allocatable. Same Latest caveat as Query B.
-		{
-			Type: qbtypes.QueryTypeBuilder,
-			Spec: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Name:   "D",
-				Signal: telemetrytypes.SignalMetrics,
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "k8s.node.allocatable_memory",
-						TimeAggregation:  metrictypes.TimeAggregationLatest,
-						SpaceAggregation: metrictypes.SpaceAggregationSum,
-						ReduceTo:         qbtypes.ReduceToAvg,
-					},
-				},
-				GroupBy:  []qbtypes.GroupByKey{nodeNameGroupByKey},
-				Disabled: false,
-			},
-		},
-	}
-
-	return &qbtypes.QueryRangeRequest{
-		RequestType: qbtypes.RequestTypeScalar,
-		CompositeQuery: qbtypes.CompositeQuery{
-			Queries: queries,
-		},
-	}
-}

pkg/modules/inframonitoring/implinframonitoring/pods.go

@@ -19,7 +19,7 @@ import (
 // buildPodRecords assembles the page records. Phase counts come from
 // phaseCounts in both modes. In list mode (isPodUIDInGroupBy=true) each
 // group is one pod, so exactly one count is 1; PodPhase is derived from
-// which one. In grouped_list mode PodPhase stays PodPhaseNoData.
+// which one. In grouped_list mode PodPhase stays PodPhaseNone.
 func buildPodRecords(
 	isPodUIDInGroupBy bool,
 	resp *qbtypes.QueryRangeResponse,
@@ -38,7 +38,7 @@ func buildPodRecords(
 
 		record := inframonitoringtypes.PodRecord{ // initialize with default values
 			PodUID:           podUID,
-			PodPhase:         inframonitoringtypes.PodPhaseNoData,
+			PodPhase:         inframonitoringtypes.PodPhaseNone,
 			PodCPU:           -1,
 			PodCPURequest:    -1,
 			PodCPULimit:      -1,
@@ -46,7 +46,7 @@ func buildPodRecords(
 			PodMemoryRequest: -1,
 			PodMemoryLimit:   -1,
 			PodAge:           -1,
-			Meta:             map[string]string{},
+			Meta:             map[string]any{},
 		}
 
 		if metrics, ok := metricsMap[compositeKey]; ok {
@@ -71,13 +71,11 @@ func buildPodRecords(
 		}
 
 		if phaseCountsForGroup, ok := phaseCounts[compositeKey]; ok {
-			record.PodCountsByPhase = inframonitoringtypes.PodCountsByPhase{
-				Pending:   phaseCountsForGroup.Pending,
-				Running:   phaseCountsForGroup.Running,
-				Succeeded: phaseCountsForGroup.Succeeded,
-				Failed:    phaseCountsForGroup.Failed,
-				Unknown:   phaseCountsForGroup.Unknown,
-			}
+			record.PendingPodCount = phaseCountsForGroup.Pending
+			record.RunningPodCount = phaseCountsForGroup.Running
+			record.SucceededPodCount = phaseCountsForGroup.Succeeded
+			record.FailedPodCount = phaseCountsForGroup.Failed
+			record.UnknownPodCount = phaseCountsForGroup.Unknown
 
 			// In list mode each group is one pod; the count==1 bucket identifies the phase.
 			if isPodUIDInGroupBy {

pkg/modules/inframonitoring/inframonitoring.go

@@ -11,15 +11,9 @@ import (
 type Handler interface {
 	ListHosts(http.ResponseWriter, *http.Request)
 	ListPods(http.ResponseWriter, *http.Request)
-	ListNodes(http.ResponseWriter, *http.Request)
-	ListNamespaces(http.ResponseWriter, *http.Request)
-	ListClusters(http.ResponseWriter, *http.Request)
 }
 
 type Module interface {
 	ListHosts(ctx context.Context, orgID valuer.UUID, req *inframonitoringtypes.PostableHosts) (*inframonitoringtypes.Hosts, error)
 	ListPods(ctx context.Context, orgID valuer.UUID, req *inframonitoringtypes.PostablePods) (*inframonitoringtypes.Pods, error)
-	ListNodes(ctx context.Context, orgID valuer.UUID, req *inframonitoringtypes.PostableNodes) (*inframonitoringtypes.Nodes, error)
-	ListNamespaces(ctx context.Context, orgID valuer.UUID, req *inframonitoringtypes.PostableNamespaces) (*inframonitoringtypes.Namespaces, error)
-	ListClusters(ctx context.Context, orgID valuer.UUID, req *inframonitoringtypes.PostableClusters) (*inframonitoringtypes.Clusters, error)
 }

pkg/querybuilder/having_expression_validator.go

@@ -1,15 +1,40 @@
 package querybuilder
 
 import (
+	"fmt"
 	"sort"
 	"strings"
 
-	"github.com/SigNoz/signoz/pkg/errors"
+	errors "github.com/SigNoz/signoz/pkg/errors/v2"
 	grammar "github.com/SigNoz/signoz/pkg/parser/havingexpression/grammar"
 	"github.com/antlr4-go/antlr/v4"
 	"github.com/huandu/go-sqlbuilder"
 )
 
+// HAVING-expression validator codes. All three are caller-fault, fix-the-input
+// errors — the user wrote an expression we cannot turn into SQL — so retry
+// is pointless until the expression itself changes.
+var (
+	codeHavingStringLiteral = errors.Register("querybuilder.having.string_literal", errors.Meta{
+		Category:    errors.CategoryInvalidInput,
+		Fault:       errors.FaultCaller,
+		Retry:       errors.Retry{Policy: errors.RetryAfterFix},
+		Remediation: errors.RemediationFixInput,
+	})
+	codeHavingInvalidReference = errors.Register("querybuilder.having.invalid_reference", errors.Meta{
+		Category:    errors.CategoryInvalidInput,
+		Fault:       errors.FaultCaller,
+		Retry:       errors.Retry{Policy: errors.RetryAfterFix},
+		Remediation: errors.RemediationFixInput,
+	})
+	codeHavingSyntaxError = errors.Register("querybuilder.having.syntax_error", errors.Meta{
+		Category:    errors.CategoryInvalidInput,
+		Fault:       errors.FaultCaller,
+		Retry:       errors.Retry{Policy: errors.RetryAfterFix},
+		Remediation: errors.RemediationFixInput,
+	})
+)
+
 // havingExpressionRewriteVisitor walks the parse tree of a HavingExpression in a single
 // pass, simultaneously rewriting user-facing references to their SQL column names and
 // collecting any references that could not be resolved.
@@ -281,10 +306,10 @@ func (r *HavingExpressionRewriter) rewriteAndValidate(expression string) (string
 	// This is checked before invalid references so that "contains string literals" takes
 	// priority when a bare string literal is also an unresolvable operand.
 	if v.hasStringLiteral {
-		return "", errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
+		return "", errors.New(codeHavingStringLiteral,
 			"`Having` expression contains string literals",
-		).WithAdditional("Aggregator results are numeric")
+			errors.WithDetail("Aggregator results are numeric"),
+		)
 	}
 
 	if len(v.invalid) > 0 {
@@ -294,7 +319,10 @@ func (r *HavingExpressionRewriter) rewriteAndValidate(expression string) (string
 			validKeys = append(validKeys, k)
 		}
 		sort.Strings(validKeys)
-		additional := []string{"Valid references are: [" + strings.Join(validKeys, ", ") + "]"}
+		opts := []errors.Option{
+			errors.WithAttr("invalid_refs", v.invalid),
+			errors.WithAttr("valid_refs", validKeys),
+		}
 		if len(v.invalid) == 1 {
 			inv := v.invalid[0]
 			// Only suggest for plain identifier typos, not for unresolved function
@@ -303,15 +331,13 @@ func (r *HavingExpressionRewriter) rewriteAndValidate(expression string) (string
 			// a simple string substitution produce a corrupt expression.
 			isFuncCall := strings.Contains(original, inv+"(")
 			if match, dist := closestMatch(inv, validKeys); !isFuncCall && !strings.Contains(match, "(") && dist <= 3 {
-				corrected := strings.ReplaceAll(original, inv, match)
-				additional = append(additional, "Suggestion: `"+corrected+"`")
+				opts = append(opts, errors.WithAttr("suggestions", []string{strings.ReplaceAll(original, inv, match)}))
 			}
 		}
-		return "", errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
-			"Invalid references in `Having` expression: [%s]",
-			strings.Join(v.invalid, ", "),
-		).WithAdditional(additional...)
+		return "", errors.New(codeHavingInvalidReference,
+			fmt.Sprintf("Invalid references in `Having` expression: [%s]", strings.Join(v.invalid, ", ")),
+			opts...,
+		)
 	}
 
 	// Layer 3 – ANTLR syntax errors. We parse the original expression, so error messages
@@ -328,17 +354,20 @@ func (r *HavingExpressionRewriter) rewriteAndValidate(expression string) (string
 		if detail == "" {
 			detail = "check the expression syntax"
 		}
-		additional := []string{detail}
+		opts := []errors.Option{
+			errors.WithDetail(detail),
+			errors.WithAttr("syntax_errors", msgs),
+		}
 		// For single-error expressions, try to produce an actionable suggestion.
 		if len(allSyntaxErrors) == 1 {
 			if s := havingSuggestion(allSyntaxErrors[0], original); s != "" {
-				additional = append(additional, "Suggestion: `"+s+"`")
+				opts = append(opts, errors.WithAttr("suggestions", []string{s}))
 			}
 		}
-		return "", errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
+		return "", errors.New(codeHavingSyntaxError,
 			"Syntax error in `Having` expression",
-		).WithAdditional(additional...)
+			opts...,
+		)
 	}
 
 	return result, nil

pkg/types/inframonitoringtypes/clusters.go

@@ -1,105 +0,0 @@
-package inframonitoringtypes
-
-import (
-	"encoding/json"
-	"slices"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-)
-
-type Clusters struct {
-	Type                   ResponseType           `json:"type" required:"true"`
-	Records                []ClusterRecord        `json:"records" required:"true"`
-	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
-	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
-	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
-}
-
-type ClusterRecord struct {
-	// TODO(nikhilmantri0902): once the underlying attr key is migrated to
-	// k8s.cluster.uid (see clusterNameAttrKey TODO in implinframonitoring),
-	// surface ClusterUID alongside (or replace) ClusterName.
-	ClusterName              string                `json:"clusterName" required:"true"`
-	ClusterCPU               float64               `json:"clusterCPU" required:"true"`
-	ClusterCPUAllocatable    float64               `json:"clusterCPUAllocatable" required:"true"`
-	ClusterMemory            float64               `json:"clusterMemory" required:"true"`
-	ClusterMemoryAllocatable float64               `json:"clusterMemoryAllocatable" required:"true"`
-	NodeCountsByReadiness    NodeCountsByReadiness `json:"nodeCountsByReadiness" required:"true"`
-	PodCountsByPhase         PodCountsByPhase      `json:"podCountsByPhase" required:"true"`
-	Meta                     map[string]string     `json:"meta" required:"true"`
-}
-
-// PostableClusters is the request body for the v2 clusters list API.
-type PostableClusters struct {
-	Start   int64                `json:"start" required:"true"`
-	End     int64                `json:"end" required:"true"`
-	Filter  *qbtypes.Filter      `json:"filter"`
-	GroupBy []qbtypes.GroupByKey `json:"groupBy"`
-	OrderBy *qbtypes.OrderBy     `json:"orderBy"`
-	Offset  int                  `json:"offset"`
-	Limit   int                  `json:"limit" required:"true"`
-}
-
-// Validate ensures PostableClusters contains acceptable values.
-func (req *PostableClusters) Validate() error {
-	if req == nil {
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "request is nil")
-	}
-
-	if req.Start <= 0 {
-		return errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
-			"invalid start time %d: start must be greater than 0",
-			req.Start,
-		)
-	}
-
-	if req.End <= 0 {
-		return errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
-			"invalid end time %d: end must be greater than 0",
-			req.End,
-		)
-	}
-
-	if req.Start >= req.End {
-		return errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
-			"invalid time range: start (%d) must be less than end (%d)",
-			req.Start,
-			req.End,
-		)
-	}
-
-	if req.Limit < 1 || req.Limit > 5000 {
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "limit must be between 1 and 5000")
-	}
-
-	if req.Offset < 0 {
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "offset cannot be negative")
-	}
-
-	if req.OrderBy != nil {
-		if !slices.Contains(ClustersValidOrderByKeys, req.OrderBy.Key.Name) {
-			return errors.NewInvalidInputf(errors.CodeInvalidInput, "invalid order by key: %s", req.OrderBy.Key.Name)
-		}
-		if req.OrderBy.Direction != qbtypes.OrderDirectionAsc && req.OrderBy.Direction != qbtypes.OrderDirectionDesc {
-			return errors.NewInvalidInputf(errors.CodeInvalidInput, "invalid order by direction: %s", req.OrderBy.Direction)
-		}
-	}
-
-	return nil
-}
-
-// UnmarshalJSON validates input immediately after decoding.
-func (req *PostableClusters) UnmarshalJSON(data []byte) error {
-	type raw PostableClusters
-	var decoded raw
-	if err := json.Unmarshal(data, &decoded); err != nil {
-		return err
-	}
-	*req = PostableClusters(decoded)
-	return req.Validate()
-}

pkg/types/inframonitoringtypes/clusters_constants.go

@@ -1,15 +0,0 @@
-package inframonitoringtypes
-
-const (
-	ClustersOrderByCPU               = "cpu"
-	ClustersOrderByCPUAllocatable    = "cpu_allocatable"
-	ClustersOrderByMemory            = "memory"
-	ClustersOrderByMemoryAllocatable = "memory_allocatable"
-)
-
-var ClustersValidOrderByKeys = []string{
-	ClustersOrderByCPU,
-	ClustersOrderByCPUAllocatable,
-	ClustersOrderByMemory,
-	ClustersOrderByMemoryAllocatable,
-}

pkg/types/inframonitoringtypes/clusters_test.go

@@ -1,291 +0,0 @@
-package inframonitoringtypes
-
-import (
-	"testing"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
-	"github.com/SigNoz/signoz/pkg/valuer"
-	"github.com/stretchr/testify/require"
-)
-
-func TestPostableClusters_Validate(t *testing.T) {
-	tests := []struct {
-		name    string
-		req     *PostableClusters
-		wantErr bool
-	}{
-		{
-			name: "valid request",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: false,
-		},
-		{
-			name:    "nil request",
-			req:     nil,
-			wantErr: true,
-		},
-		{
-			name: "start time zero",
-			req: &PostableClusters{
-				Start:  0,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "start time negative",
-			req: &PostableClusters{
-				Start:  -1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "end time zero",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    0,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "start time greater than end time",
-			req: &PostableClusters{
-				Start:  2000,
-				End:    1000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "start time equal to end time",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    1000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "limit zero",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  0,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "limit negative",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  -10,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "limit exceeds max",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  5001,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "offset negative",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: -5,
-			},
-			wantErr: true,
-		},
-		{
-			name: "orderBy nil is valid",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with valid key cpu and direction asc",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: ClustersOrderByCPU,
-						},
-					},
-					Direction: qbtypes.OrderDirectionAsc,
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with valid key cpu_allocatable and direction desc",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: ClustersOrderByCPUAllocatable,
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with valid key memory and direction desc",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: ClustersOrderByMemory,
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with valid key memory_allocatable and direction asc",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: ClustersOrderByMemoryAllocatable,
-						},
-					},
-					Direction: qbtypes.OrderDirectionAsc,
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with condition key is rejected",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "condition",
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: true,
-		},
-		{
-			name: "orderBy with pod_phase key is rejected",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "pod_phase",
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: true,
-		},
-		{
-			name: "orderBy with invalid key",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "unknown",
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: true,
-		},
-		{
-			name: "orderBy with valid key but invalid direction",
-			req: &PostableClusters{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: ClustersOrderByMemory,
-						},
-					},
-					Direction: qbtypes.OrderDirection{String: valuer.NewString("invalid")},
-				},
-			},
-			wantErr: true,
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			err := tt.req.Validate()
-			if tt.wantErr {
-				require.Error(t, err)
-				require.True(t, errors.Ast(err, errors.TypeInvalidInput), "expected error to be of type InvalidInput")
-			} else {
-				require.NoError(t, err)
-			}
-		})
-	}
-}

pkg/types/inframonitoringtypes/hosts.go

@@ -18,16 +18,16 @@ type Hosts struct {
 }
 
 type HostRecord struct {
-	HostName          string            `json:"hostName" required:"true"`
-	Status            HostStatus        `json:"status" required:"true"`
-	ActiveHostCount   int               `json:"activeHostCount" required:"true"`
-	InactiveHostCount int               `json:"inactiveHostCount" required:"true"`
-	CPU               float64           `json:"cpu" required:"true"`
-	Memory            float64           `json:"memory" required:"true"`
-	Wait              float64           `json:"wait" required:"true"`
-	Load15            float64           `json:"load15" required:"true"`
-	DiskUsage         float64           `json:"diskUsage" required:"true"`
-	Meta              map[string]string `json:"meta" required:"true"`
+	HostName          string                 `json:"hostName" required:"true"`
+	Status            HostStatus             `json:"status" required:"true"`
+	ActiveHostCount   int                    `json:"activeHostCount" required:"true"`
+	InactiveHostCount int                    `json:"inactiveHostCount" required:"true"`
+	CPU               float64                `json:"cpu" required:"true"`
+	Memory            float64                `json:"memory" required:"true"`
+	Wait              float64                `json:"wait" required:"true"`
+	Load15            float64                `json:"load15" required:"true"`
+	DiskUsage         float64                `json:"diskUsage" required:"true"`
+	Meta              map[string]interface{} `json:"meta" required:"true"`
 }
 
 type RequiredMetricsCheck struct {

pkg/types/inframonitoringtypes/namespaces.go

@@ -1,99 +0,0 @@
-package inframonitoringtypes
-
-import (
-	"encoding/json"
-	"slices"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-)
-
-type Namespaces struct {
-	Type                   ResponseType           `json:"type" required:"true"`
-	Records                []NamespaceRecord      `json:"records" required:"true"`
-	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
-	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
-	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
-}
-
-type NamespaceRecord struct {
-	NamespaceName    string            `json:"namespaceName" required:"true"`
-	NamespaceCPU     float64           `json:"namespaceCPU" required:"true"`
-	NamespaceMemory  float64           `json:"namespaceMemory" required:"true"`
-	PodCountsByPhase PodCountsByPhase  `json:"podCountsByPhase" required:"true"`
-	Meta             map[string]string `json:"meta" required:"true"`
-}
-
-// PostableNamespaces is the request body for the v2 namespaces list API.
-type PostableNamespaces struct {
-	Start   int64                `json:"start" required:"true"`
-	End     int64                `json:"end" required:"true"`
-	Filter  *qbtypes.Filter      `json:"filter"`
-	GroupBy []qbtypes.GroupByKey `json:"groupBy"`
-	OrderBy *qbtypes.OrderBy     `json:"orderBy"`
-	Offset  int                  `json:"offset"`
-	Limit   int                  `json:"limit" required:"true"`
-}
-
-// Validate ensures PostableNamespaces contains acceptable values.
-func (req *PostableNamespaces) Validate() error {
-	if req == nil {
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "request is nil")
-	}
-
-	if req.Start <= 0 {
-		return errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
-			"invalid start time %d: start must be greater than 0",
-			req.Start,
-		)
-	}
-
-	if req.End <= 0 {
-		return errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
-			"invalid end time %d: end must be greater than 0",
-			req.End,
-		)
-	}
-
-	if req.Start >= req.End {
-		return errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
-			"invalid time range: start (%d) must be less than end (%d)",
-			req.Start,
-			req.End,
-		)
-	}
-
-	if req.Limit < 1 || req.Limit > 5000 {
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "limit must be between 1 and 5000")
-	}
-
-	if req.Offset < 0 {
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "offset cannot be negative")
-	}
-
-	if req.OrderBy != nil {
-		if !slices.Contains(NamespacesValidOrderByKeys, req.OrderBy.Key.Name) {
-			return errors.NewInvalidInputf(errors.CodeInvalidInput, "invalid order by key: %s", req.OrderBy.Key.Name)
-		}
-		if req.OrderBy.Direction != qbtypes.OrderDirectionAsc && req.OrderBy.Direction != qbtypes.OrderDirectionDesc {
-			return errors.NewInvalidInputf(errors.CodeInvalidInput, "invalid order by direction: %s", req.OrderBy.Direction)
-		}
-	}
-
-	return nil
-}
-
-// UnmarshalJSON validates input immediately after decoding.
-func (req *PostableNamespaces) UnmarshalJSON(data []byte) error {
-	type raw PostableNamespaces
-	var decoded raw
-	if err := json.Unmarshal(data, &decoded); err != nil {
-		return err
-	}
-	*req = PostableNamespaces(decoded)
-	return req.Validate()
-}

pkg/types/inframonitoringtypes/namespaces_constants.go

@@ -1,11 +0,0 @@
-package inframonitoringtypes
-
-const (
-	NamespacesOrderByCPU    = "cpu"
-	NamespacesOrderByMemory = "memory"
-)
-
-var NamespacesValidOrderByKeys = []string{
-	NamespacesOrderByCPU,
-	NamespacesOrderByMemory,
-}

pkg/types/inframonitoringtypes/namespaces_test.go

@@ -1,237 +0,0 @@
-package inframonitoringtypes
-
-import (
-	"testing"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
-	"github.com/SigNoz/signoz/pkg/valuer"
-	"github.com/stretchr/testify/require"
-)
-
-func TestPostableNamespaces_Validate(t *testing.T) {
-	tests := []struct {
-		name    string
-		req     *PostableNamespaces
-		wantErr bool
-	}{
-		{
-			name: "valid request",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: false,
-		},
-		{
-			name:    "nil request",
-			req:     nil,
-			wantErr: true,
-		},
-		{
-			name: "start time zero",
-			req: &PostableNamespaces{
-				Start:  0,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "start time negative",
-			req: &PostableNamespaces{
-				Start:  -1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "end time zero",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    0,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "start time greater than end time",
-			req: &PostableNamespaces{
-				Start:  2000,
-				End:    1000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "start time equal to end time",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    1000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "limit zero",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  0,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "limit negative",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  -10,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "limit exceeds max",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  5001,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "offset negative",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: -5,
-			},
-			wantErr: true,
-		},
-		{
-			name: "orderBy nil is valid",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with valid key cpu and direction asc",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: NamespacesOrderByCPU,
-						},
-					},
-					Direction: qbtypes.OrderDirectionAsc,
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with valid key memory and direction desc",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: NamespacesOrderByMemory,
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with pod_phase key is rejected",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "pod_phase",
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: true,
-		},
-		{
-			name: "orderBy with invalid key",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "unknown",
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: true,
-		},
-		{
-			name: "orderBy with valid key but invalid direction",
-			req: &PostableNamespaces{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: NamespacesOrderByMemory,
-						},
-					},
-					Direction: qbtypes.OrderDirection{String: valuer.NewString("invalid")},
-				},
-			},
-			wantErr: true,
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			err := tt.req.Validate()
-			if tt.wantErr {
-				require.Error(t, err)
-				require.True(t, errors.Ast(err, errors.TypeInvalidInput), "expected error to be of type InvalidInput")
-			} else {
-				require.NoError(t, err)
-			}
-		})
-	}
-}

pkg/types/inframonitoringtypes/nodes.go

@@ -1,110 +0,0 @@
-package inframonitoringtypes
-
-import (
-	"encoding/json"
-	"slices"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-)
-
-type Nodes struct {
-	Type                   ResponseType           `json:"type" required:"true"`
-	Records                []NodeRecord           `json:"records" required:"true"`
-	Total                  int                    `json:"total" required:"true"`
-	RequiredMetricsCheck   RequiredMetricsCheck   `json:"requiredMetricsCheck" required:"true"`
-	EndTimeBeforeRetention bool                   `json:"endTimeBeforeRetention" required:"true"`
-	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
-}
-
-// NodeCountsByReadiness buckets node counts by their latest k8s.node.condition_ready
-// value in the time window. Reusable across record types (node / cluster).
-type NodeCountsByReadiness struct {
-	Ready    int `json:"ready" required:"true"`
-	NotReady int `json:"notReady" required:"true"`
-}
-
-type NodeRecord struct {
-	NodeName              string                `json:"nodeName" required:"true"`
-	Condition             NodeCondition         `json:"condition" required:"true"`
-	NodeCountsByReadiness NodeCountsByReadiness `json:"nodeCountsByReadiness" required:"true"`
-	PodCountsByPhase      PodCountsByPhase      `json:"podCountsByPhase" required:"true"`
-	NodeCPU               float64               `json:"nodeCPU" required:"true"`
-	NodeCPUAllocatable    float64               `json:"nodeCPUAllocatable" required:"true"`
-	NodeMemory            float64               `json:"nodeMemory" required:"true"`
-	NodeMemoryAllocatable float64               `json:"nodeMemoryAllocatable" required:"true"`
-	Meta                  map[string]string     `json:"meta" required:"true"`
-}
-
-// PostableNodes is the request body for the v2 nodes list API.
-type PostableNodes struct {
-	Start   int64                `json:"start" required:"true"`
-	End     int64                `json:"end" required:"true"`
-	Filter  *qbtypes.Filter      `json:"filter"`
-	GroupBy []qbtypes.GroupByKey `json:"groupBy"`
-	OrderBy *qbtypes.OrderBy     `json:"orderBy"`
-	Offset  int                  `json:"offset"`
-	Limit   int                  `json:"limit" required:"true"`
-}
-
-// Validate ensures PostableNodes contains acceptable values.
-func (req *PostableNodes) Validate() error {
-	if req == nil {
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "request is nil")
-	}
-
-	if req.Start <= 0 {
-		return errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
-			"invalid start time %d: start must be greater than 0",
-			req.Start,
-		)
-	}
-
-	if req.End <= 0 {
-		return errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
-			"invalid end time %d: end must be greater than 0",
-			req.End,
-		)
-	}
-
-	if req.Start >= req.End {
-		return errors.NewInvalidInputf(
-			errors.CodeInvalidInput,
-			"invalid time range: start (%d) must be less than end (%d)",
-			req.Start,
-			req.End,
-		)
-	}
-
-	if req.Limit < 1 || req.Limit > 5000 {
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "limit must be between 1 and 5000")
-	}
-
-	if req.Offset < 0 {
-		return errors.NewInvalidInputf(errors.CodeInvalidInput, "offset cannot be negative")
-	}
-
-	if req.OrderBy != nil {
-		if !slices.Contains(NodesValidOrderByKeys, req.OrderBy.Key.Name) {
-			return errors.NewInvalidInputf(errors.CodeInvalidInput, "invalid order by key: %s", req.OrderBy.Key.Name)
-		}
-		if req.OrderBy.Direction != qbtypes.OrderDirectionAsc && req.OrderBy.Direction != qbtypes.OrderDirectionDesc {
-			return errors.NewInvalidInputf(errors.CodeInvalidInput, "invalid order by direction: %s", req.OrderBy.Direction)
-		}
-	}
-
-	return nil
-}
-
-// UnmarshalJSON validates input immediately after decoding.
-func (req *PostableNodes) UnmarshalJSON(data []byte) error {
-	type raw PostableNodes
-	var decoded raw
-	if err := json.Unmarshal(data, &decoded); err != nil {
-		return err
-	}
-	*req = PostableNodes(decoded)
-	return req.Validate()
-}

pkg/types/inframonitoringtypes/nodes_constants.go

@@ -1,42 +0,0 @@
-package inframonitoringtypes
-
-import "github.com/SigNoz/signoz/pkg/valuer"
-
-type NodeCondition struct {
-	valuer.String
-}
-
-var (
-	NodeConditionReady    = NodeCondition{valuer.NewString("ready")}
-	NodeConditionNotReady = NodeCondition{valuer.NewString("not_ready")}
-	NodeConditionNoData   = NodeCondition{valuer.NewString("no_data")}
-)
-
-func (NodeCondition) Enum() []any {
-	return []any{
-		NodeConditionReady,
-		NodeConditionNotReady,
-		NodeConditionNoData,
-	}
-}
-
-// Numeric values emitted by the k8s.node.condition_ready metric
-// (source: OTel kubeletstats receiver).
-const (
-	NodeConditionNumReady    = 1
-	NodeConditionNumNotReady = 0
-)
-
-const (
-	NodesOrderByCPU               = "cpu"
-	NodesOrderByCPUAllocatable    = "cpu_allocatable"
-	NodesOrderByMemory            = "memory"
-	NodesOrderByMemoryAllocatable = "memory_allocatable"
-)
-
-var NodesValidOrderByKeys = []string{
-	NodesOrderByCPU,
-	NodesOrderByCPUAllocatable,
-	NodesOrderByMemory,
-	NodesOrderByMemoryAllocatable,
-}

pkg/types/inframonitoringtypes/nodes_test.go

@@ -1,255 +0,0 @@
-package inframonitoringtypes
-
-import (
-	"testing"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
-	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
-	"github.com/SigNoz/signoz/pkg/valuer"
-	"github.com/stretchr/testify/require"
-)
-
-func TestPostableNodes_Validate(t *testing.T) {
-	tests := []struct {
-		name    string
-		req     *PostableNodes
-		wantErr bool
-	}{
-		{
-			name: "valid request",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: false,
-		},
-		{
-			name:    "nil request",
-			req:     nil,
-			wantErr: true,
-		},
-		{
-			name: "start time zero",
-			req: &PostableNodes{
-				Start:  0,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "start time negative",
-			req: &PostableNodes{
-				Start:  -1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "end time zero",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    0,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "start time greater than end time",
-			req: &PostableNodes{
-				Start:  2000,
-				End:    1000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "start time equal to end time",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    1000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "limit zero",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  0,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "limit negative",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  -10,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "limit exceeds max",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  5001,
-				Offset: 0,
-			},
-			wantErr: true,
-		},
-		{
-			name: "offset negative",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: -5,
-			},
-			wantErr: true,
-		},
-		{
-			name: "orderBy nil is valid",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with valid key cpu and direction asc",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: NodesOrderByCPU,
-						},
-					},
-					Direction: qbtypes.OrderDirectionAsc,
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with valid key cpu_allocatable and direction desc",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: NodesOrderByCPUAllocatable,
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with valid key memory_allocatable and direction asc",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: NodesOrderByMemoryAllocatable,
-						},
-					},
-					Direction: qbtypes.OrderDirectionAsc,
-				},
-			},
-			wantErr: false,
-		},
-		{
-			name: "orderBy with condition key is rejected",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "condition",
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: true,
-		},
-		{
-			name: "orderBy with invalid key",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "unknown",
-						},
-					},
-					Direction: qbtypes.OrderDirectionDesc,
-				},
-			},
-			wantErr: true,
-		},
-		{
-			name: "orderBy with valid key but invalid direction",
-			req: &PostableNodes{
-				Start:  1000,
-				End:    2000,
-				Limit:  100,
-				Offset: 0,
-				OrderBy: &qbtypes.OrderBy{
-					Key: qbtypes.OrderByKey{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: NodesOrderByMemory,
-						},
-					},
-					Direction: qbtypes.OrderDirection{String: valuer.NewString("invalid")},
-				},
-			},
-			wantErr: true,
-		},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			err := tt.req.Validate()
-			if tt.wantErr {
-				require.Error(t, err)
-				require.True(t, errors.Ast(err, errors.TypeInvalidInput), "expected error to be of type InvalidInput")
-			} else {
-				require.NoError(t, err)
-			}
-		})
-	}
-}

pkg/types/inframonitoringtypes/pods.go

@@ -17,28 +17,22 @@ type Pods struct {
 	Warning                *qbtypes.QueryWarnData `json:"warning,omitempty"`
 }
 
-// PodCountsByPhase buckets pod counts by their latest phase in the time window.
-// Reusable across record types (pod / namespace / cluster).
-type PodCountsByPhase struct {
-	Pending   int `json:"pending" required:"true"`
-	Running   int `json:"running" required:"true"`
-	Succeeded int `json:"succeeded" required:"true"`
-	Failed    int `json:"failed" required:"true"`
-	Unknown   int `json:"unknown" required:"true"`
-}
-
 type PodRecord struct {
-	PodUID           string            `json:"podUID" required:"true"`
-	PodCPU           float64           `json:"podCPU" required:"true"`
-	PodCPURequest    float64           `json:"podCPURequest" required:"true"`
-	PodCPULimit      float64           `json:"podCPULimit" required:"true"`
-	PodMemory        float64           `json:"podMemory" required:"true"`
-	PodMemoryRequest float64           `json:"podMemoryRequest" required:"true"`
-	PodMemoryLimit   float64           `json:"podMemoryLimit" required:"true"`
-	PodPhase         PodPhase          `json:"podPhase" required:"true"`
-	PodCountsByPhase PodCountsByPhase  `json:"podCountsByPhase" required:"true"`
-	PodAge           int64             `json:"podAge" required:"true"`
-	Meta             map[string]string `json:"meta" required:"true"`
+	PodUID            string                 `json:"podUID" required:"true"`
+	PodCPU            float64                `json:"podCPU" required:"true"`
+	PodCPURequest     float64                `json:"podCPURequest" required:"true"`
+	PodCPULimit       float64                `json:"podCPULimit" required:"true"`
+	PodMemory         float64                `json:"podMemory" required:"true"`
+	PodMemoryRequest  float64                `json:"podMemoryRequest" required:"true"`
+	PodMemoryLimit    float64                `json:"podMemoryLimit" required:"true"`
+	PodPhase          PodPhase               `json:"podPhase" required:"true"`
+	PendingPodCount   int                    `json:"pendingPodCount" required:"true"`
+	RunningPodCount   int                    `json:"runningPodCount" required:"true"`
+	SucceededPodCount int                    `json:"succeededPodCount" required:"true"`
+	FailedPodCount    int                    `json:"failedPodCount" required:"true"`
+	UnknownPodCount   int                    `json:"unknownPodCount" required:"true"`
+	PodAge            int64                  `json:"podAge" required:"true"`
+	Meta              map[string]interface{} `json:"meta" required:"true"`
 }
 
 // PostablePods is the request body for the v2 pods list API.

pkg/types/inframonitoringtypes/pods_constants.go

@@ -12,7 +12,7 @@ var (
 	PodPhaseSucceeded = PodPhase{valuer.NewString("succeeded")}
 	PodPhaseFailed    = PodPhase{valuer.NewString("failed")}
 	PodPhaseUnknown   = PodPhase{valuer.NewString("unknown")}
-	PodPhaseNoData    = PodPhase{valuer.NewString("no_data")}
+	PodPhaseNone      = PodPhase{valuer.NewString("")}
 )
 
 func (PodPhase) Enum() []any {
@@ -22,7 +22,7 @@ func (PodPhase) Enum() []any {
 		PodPhaseSucceeded,
 		PodPhaseFailed,
 		PodPhaseUnknown,
-		PodPhaseNoData,
+		PodPhaseNone,
 	}
 }