chore: v2 clusters list api

docs/api/openapi.yml

@@ -2396,6 +2396,79 @@ 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
+        failedPodCount:
+          type: integer
+        meta:
+          additionalProperties: {}
+          nullable: true
+          type: object
+        notReadyNodesCount:
+          type: integer
+        pendingPodCount:
+          type: integer
+        readyNodesCount:
+          type: integer
+        runningPodCount:
+          type: integer
+        succeededPodCount:
+          type: integer
+        unknownPodCount:
+          type: integer
+      required:
+      - clusterName
+      - clusterCPU
+      - clusterCPUAllocatable
+      - clusterMemory
+      - clusterMemoryAllocatable
+      - readyNodesCount
+      - notReadyNodesCount
+      - pendingPodCount
+      - runningPodCount
+      - succeededPodCount
+      - failedPodCount
+      - unknownPodCount
+      - 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:
@@ -2691,6 +2764,32 @@ 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:
@@ -11169,6 +11268,78 @@ 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 node counts bucketed by each node''s latest k8s.node.condition_ready
+        value (readyNodesCount, notReadyNodesCount) and per-group pod counts bucketed
+        by each pod''s latest k8s.pod.phase value (pendingPodCount, runningPodCount,
+        succeededPodCount, failedPodCount, unknownPodCount). 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

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

@@ -12,10 +12,12 @@ import type {
 } from 'react-query';
 
 import type {
+	InframonitoringtypesPostableClustersDTO,
 	InframonitoringtypesPostableHostsDTO,
 	InframonitoringtypesPostableNamespacesDTO,
 	InframonitoringtypesPostableNodesDTO,
 	InframonitoringtypesPostablePodsDTO,
+	ListClusters200,
 	ListHosts200,
 	ListNamespaces200,
 	ListNodes200,
@@ -26,6 +28,90 @@ 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 node counts bucketed by each node's latest k8s.node.condition_ready value (readyNodesCount, notReadyNodesCount) and per-group pod counts bucketed by each pod's latest k8s.pod.phase value (pendingPodCount, runningPodCount, succeededPodCount, failedPodCount, unknownPodCount). 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

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

@@ -3158,6 +3158,92 @@ export interface GlobaltypesTokenizerConfigDTO {
 	enabled?: boolean;
 }
 
+/**
+ * @nullable
+ */
+export type InframonitoringtypesClusterRecordDTOMeta = {
+	[key: string]: unknown;
+} | 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 integer
+	 */
+	failedPodCount: number;
+	/**
+	 * @type object
+	 * @nullable true
+	 */
+	meta: InframonitoringtypesClusterRecordDTOMeta;
+	/**
+	 * @type integer
+	 */
+	notReadyNodesCount: number;
+	/**
+	 * @type integer
+	 */
+	pendingPodCount: number;
+	/**
+	 * @type integer
+	 */
+	readyNodesCount: number;
+	/**
+	 * @type integer
+	 */
+	runningPodCount: number;
+	/**
+	 * @type integer
+	 */
+	succeededPodCount: number;
+	/**
+	 * @type integer
+	 */
+	unknownPodCount: number;
+}
+
+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
@@ -3485,6 +3571,34 @@ 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
@@ -7668,6 +7782,14 @@ export type Healthz503 = {
 	status: string;
 };
 
+export type ListClusters200 = {
+	data: InframonitoringtypesClustersDTO;
+	/**
+	 * @type string
+	 */
+	status: string;
+};
+
 export type ListHosts200 = {
 	data: InframonitoringtypesHostsDTO;
 	/**

pkg/apiserver/signozapiserver/inframonitoring.go

@@ -86,5 +86,24 @@ func (provider *provider) addInfraMonitoringRoutes(router *mux.Router) error {
 		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 node counts bucketed by each node's latest k8s.node.condition_ready value (readyNodesCount, notReadyNodesCount) and per-group pod counts bucketed by each pod's latest k8s.pod.phase value (pendingPodCount, runningPodCount, succeededPodCount, failedPodCount, unknownPodCount). 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/modules/inframonitoring/implinframonitoring/clusters.go

@@ -0,0 +1,136 @@
+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]any{},
+		}
+
+		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.ReadyNodesCount = conditionCountsForGroup.Ready
+			record.NotReadyNodesCount = conditionCountsForGroup.NotReady
+		}
+
+		if phaseCountsForGroup, ok := podPhaseCountsMap[compositeKey]; ok {
+			record.PendingPodCount = phaseCountsForGroup.Pending
+			record.RunningPodCount = phaseCountsForGroup.Running
+			record.SucceededPodCount = phaseCountsForGroup.Succeeded
+			record.FailedPodCount = phaseCountsForGroup.Failed
+			record.UnknownPodCount = 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

@@ -0,0 +1,140 @@
+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",
+	"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

@@ -117,3 +117,27 @@ func (h *handler) ListNamespaces(rw http.ResponseWriter, req *http.Request) {
 
 	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/module.go

@@ -414,3 +414,105 @@ func (m *module) ListNamespaces(ctx context.Context, orgID valuer.UUID, req *inf
 
 	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/inframonitoring.go

@@ -13,6 +13,7 @@ type Handler interface {
 	ListPods(http.ResponseWriter, *http.Request)
 	ListNodes(http.ResponseWriter, *http.Request)
 	ListNamespaces(http.ResponseWriter, *http.Request)
+	ListClusters(http.ResponseWriter, *http.Request)
 }
 
 type Module interface {
@@ -20,4 +21,5 @@ type Module interface {
 	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/types/inframonitoringtypes/clusters.go

@@ -0,0 +1,110 @@
+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"`
+	ReadyNodesCount          int                    `json:"readyNodesCount" required:"true"`
+	NotReadyNodesCount       int                    `json:"notReadyNodesCount" 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"`
+	Meta                     map[string]interface{} `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

@@ -0,0 +1,15 @@
+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

@@ -0,0 +1,291 @@
+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)
+			}
+		})
+	}
+}