fix: refactor integration tests

* feat(authz): expose telemetry resources in generated frontend permissions

* feat(authz): add support for telemetry resources on roles page (#12296)

* feat(create-edit-role): add support for telemetry resource

* test(create-edit-role): add tests for telemetry resource

* fix(pr): address comments

* fix(authz): app routing and sidebar fixes when no built-in role (#12307)

* fix(sidebar): render fallback when user preferences fails on sidenav

Otherwise, it fails and don't show any menu that can be pinned

* feat(app-routing): bypass unauthorized when authz is enabled

Those pages should render to allow us to handle authz
directly in each page/component

* fix(private): drop feature flag gate

* fix(authz): backfill managed role transaction groups for meter metrics

* feat(authz): resolve conflicts

* refactor(telemetry-selector): couple fixes after feedback on ux/ui (#12316)

* fix(pr): address more ux feedback

---------

Co-authored-by: Vinicius Lourenço <12551007+H4ad@users.noreply.github.com>
Co-authored-by: Vinícius Lourenço <vinicius@signoz.io>

.github/workflows/integrationci.yaml

@@ -53,6 +53,7 @@ jobs:
           - queriermetrics
           - querierscalar
           - queriercommon
+          - querierai
           - rawexportdata
           - promqlconformance
           - querierauthz

cmd/authz.go

@@ -93,9 +93,13 @@ func runGenerateAuthz(_ context.Context) error {
 	registry := coretypes.NewRegistry()
 
 	allowedResources := map[string]bool{
-		coretypes.NewResourceRef(coretypes.ResourceServiceAccount).String():           true,
-		coretypes.NewResourceRef(coretypes.ResourceRole).String():                     true,
-		coretypes.NewResourceRef(coretypes.ResourceMetaResourceFactorAPIKey).String(): true,
+		coretypes.NewResourceRef(coretypes.ResourceServiceAccount).String():                true,
+		coretypes.NewResourceRef(coretypes.ResourceRole).String():                          true,
+		coretypes.NewResourceRef(coretypes.ResourceMetaResourceFactorAPIKey).String():      true,
+		coretypes.NewResourceRef(coretypes.ResourceTelemetryResourceLogs).String():         true,
+		coretypes.NewResourceRef(coretypes.ResourceTelemetryResourceTraces).String():       true,
+		coretypes.NewResourceRef(coretypes.ResourceTelemetryResourceMetrics).String():      true,
+		coretypes.NewResourceRef(coretypes.ResourceTelemetryResourceMeterMetrics).String(): true,
 	}
 
 	allowedTypes := map[string]bool{}

cmd/enterprise/meter.go

@@ -2,9 +2,9 @@ package main
 
 import (
 	"github.com/SigNoz/signoz/pkg/metercollector"
-	"github.com/SigNoz/signoz/pkg/telemetrylogs"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
-	"github.com/SigNoz/signoz/pkg/telemetrytraces"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/logstelemetryschema"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/tracestelemetryschema"
 	"github.com/SigNoz/signoz/pkg/types/retentiontypes"
 	"github.com/SigNoz/signoz/pkg/types/zeustypes"
 )
@@ -25,8 +25,8 @@ var meterConfigs = []metercollector.Config{
 			Name:                 zeustypes.MeterLogSize,
 			Unit:                 zeustypes.MeterUnitBytes,
 			Aggregation:          zeustypes.MeterAggregationSum,
-			DBName:               telemetrylogs.DBName,
-			TableName:            telemetrylogs.LogsV2LocalTableName,
+			DBName:               logstelemetryschema.DBName,
+			TableName:            logstelemetryschema.LogsV2LocalTableName,
 			DefaultRetentionDays: retentiontypes.DefaultLogsRetentionDays,
 		},
 	},
@@ -36,8 +36,8 @@ var meterConfigs = []metercollector.Config{
 			Name:                 zeustypes.MeterSpanSize,
 			Unit:                 zeustypes.MeterUnitBytes,
 			Aggregation:          zeustypes.MeterAggregationSum,
-			DBName:               telemetrytraces.DBName,
-			TableName:            telemetrytraces.SpanIndexV3LocalTableName,
+			DBName:               tracestelemetryschema.DBName,
+			TableName:            tracestelemetryschema.SpanIndexV3LocalTableName,
 			DefaultRetentionDays: retentiontypes.DefaultTracesRetentionDays,
 		},
 	},
@@ -47,8 +47,8 @@ var meterConfigs = []metercollector.Config{
 			Name:                 zeustypes.MeterDatapointCount,
 			Unit:                 zeustypes.MeterUnitCount,
 			Aggregation:          zeustypes.MeterAggregationSum,
-			DBName:               telemetrymetrics.DBName,
-			TableName:            telemetrymetrics.SamplesV4LocalTableName,
+			DBName:               metricstelemetryschema.DBName,
+			TableName:            metricstelemetryschema.SamplesV4LocalTableName,
 			DefaultRetentionDays: retentiontypes.DefaultMetricsRetentionDays,
 		},
 	},

docs/api/openapi.yml

@@ -1496,6 +1496,7 @@ components:
       - redis
       - cloudsql_postgres
       - memorystore_redis
+      - computeengine
       type: string
     CloudintegrationtypesServiceMetadata:
       properties:
@@ -6899,6 +6900,7 @@ components:
     Querybuildertypesv5QueryEnvelope:
       discriminator:
         mapping:
+          builder_ai_query: '#/components/schemas/Querybuildertypesv5QueryEnvelopeBuilderAI'
           builder_formula: '#/components/schemas/Querybuildertypesv5QueryEnvelopeFormula'
           builder_query: '#/components/schemas/Querybuildertypesv5QueryEnvelopeBuilder'
           builder_trace_operator: '#/components/schemas/Querybuildertypesv5QueryEnvelopeTraceOperator'
@@ -6907,6 +6909,7 @@ components:
         propertyName: type
       oneOf:
       - $ref: '#/components/schemas/Querybuildertypesv5QueryEnvelopeBuilder'
+      - $ref: '#/components/schemas/Querybuildertypesv5QueryEnvelopeBuilderAI'
       - $ref: '#/components/schemas/Querybuildertypesv5QueryEnvelopeFormula'
       - $ref: '#/components/schemas/Querybuildertypesv5QueryEnvelopeTraceOperator'
       - $ref: '#/components/schemas/Querybuildertypesv5QueryEnvelopePromQL'
@@ -6921,6 +6924,15 @@ components:
       required:
       - type
       type: object
+    Querybuildertypesv5QueryEnvelopeBuilderAI:
+      properties:
+        spec:
+          $ref: '#/components/schemas/Querybuildertypesv5QueryBuilderQueryGithubComSigNozSignozPkgTypesQuerybuildertypesQuerybuildertypesv5TraceAggregation'
+        type:
+          $ref: '#/components/schemas/Querybuildertypesv5QueryType'
+      required:
+      - type
+      type: object
     Querybuildertypesv5QueryEnvelopeClickHouseSQL:
       properties:
         spec:
@@ -7034,6 +7046,7 @@ components:
     Querybuildertypesv5QueryType:
       enum:
       - builder_query
+      - builder_ai_query
       - builder_formula
       - builder_trace_operator
       - clickhouse_sql

ee/metercollector/telemetrymetercollector/provider.go

@@ -16,7 +16,7 @@ import (
 	"github.com/SigNoz/signoz/pkg/factory"
 	"github.com/SigNoz/signoz/pkg/metercollector"
 	"github.com/SigNoz/signoz/pkg/modules/retention"
-	"github.com/SigNoz/signoz/pkg/telemetrymeter"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metertelemetryschema"
 	"github.com/SigNoz/signoz/pkg/telemetrystore"
 	"github.com/SigNoz/signoz/pkg/types/licensetypes"
 	"github.com/SigNoz/signoz/pkg/types/retentiontypes"
@@ -153,7 +153,7 @@ func (provider *Provider) Collect(
 func buildOriginQuery(meterName string) (string, []any) {
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("toInt64(ifNull(min(unix_milli), 0))")
-	sb.From(telemetrymeter.DBName + "." + telemetrymeter.SamplesTableName)
+	sb.From(metertelemetryschema.DBName + "." + metertelemetryschema.SamplesTableName)
 	sb.Where(sb.Equal("metric_name", meterName))
 	return sb.BuildWithFlavor(sqlbuilder.ClickHouse)
 }
@@ -171,7 +171,7 @@ func buildQuery(meterName string, segment *retentiontypes.RetentionPolicySegment
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select(selects...)
-	sb.From(telemetrymeter.DBName + "." + telemetrymeter.SamplesTableName)
+	sb.From(metertelemetryschema.DBName + "." + metertelemetryschema.SamplesTableName)
 	sb.Where(
 		sb.Equal("metric_name", meterName),
 		sb.GTE("unix_milli", segment.StartMs),

ee/modules/metricreductionrule/implmetricreductionrule/clickhouse.go

@@ -8,16 +8,16 @@ import (
 	sqlbuilder "github.com/huandu/go-sqlbuilder"
 
 	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
 	"github.com/SigNoz/signoz/pkg/telemetrystore"
 	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
 	"github.com/SigNoz/signoz/pkg/types/metricreductionruletypes"
 )
 
 var (
-	reductionRulesTable = telemetrymetrics.DBName + "." + telemetrymetrics.ReductionRulesTableName
-	metadataTable       = telemetrymetrics.DBName + "." + telemetrymetrics.AttributesMetadataTableName
-	bufferSeriesTable   = telemetrymetrics.DBName + "." + telemetrymetrics.TimeseriesV4BufferTableName
+	reductionRulesTable = metricstelemetryschema.DBName + "." + metricstelemetryschema.ReductionRulesTableName
+	metadataTable       = metricstelemetryschema.DBName + "." + metricstelemetryschema.AttributesMetadataTableName
+	bufferSeriesTable   = metricstelemetryschema.DBName + "." + metricstelemetryschema.TimeseriesV4BufferTableName
 )
 
 const timeSeriesBucketMilli = int64(time.Hour / time.Millisecond)
@@ -192,7 +192,7 @@ func (c *clickhouse) ingestedSeriesCount(ctx context.Context, metricNames []stri
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("metric_name", "uniq(fingerprint)")
-	sb.From(telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName)
+	sb.From(metricstelemetryschema.DBName + "." + metricstelemetryschema.SamplesV4BufferTableName)
 	conds := []string{
 		sb.In("metric_name", names...),
 		sb.GE("unix_milli", startMs),
@@ -229,8 +229,8 @@ func (c *clickhouse) ingestedSeriesCount(ctx context.Context, metricNames []stri
 // reduced sample tables.
 func (c *clickhouse) reducedSeriesCount(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[string]uint64, error) {
 	out := make(map[string]uint64, len(metricNames))
-	for _, table := range []string{telemetrymetrics.SamplesV4ReducedLastTableName, telemetrymetrics.SamplesV4ReducedSumTableName} {
-		counts, err := c.reducedSeriesCountForTable(ctx, telemetrymetrics.DBName+"."+table, metricNames, effectiveFrom, startMs, endMs)
+	for _, table := range []string{metricstelemetryschema.SamplesV4ReducedLastTableName, metricstelemetryschema.SamplesV4ReducedSumTableName} {
+		counts, err := c.reducedSeriesCountForTable(ctx, metricstelemetryschema.DBName+"."+table, metricNames, effectiveFrom, startMs, endMs)
 		if err != nil {
 			return nil, err
 		}
@@ -300,9 +300,9 @@ func (c *clickhouse) RankByVolume(ctx context.Context, metricNames []string, eff
 		direction = "DESC"
 	}
 
-	ingestedTable := telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName
-	reducedLast := telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4ReducedLastTableName
-	reducedSum := telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4ReducedSumTableName
+	ingestedTable := metricstelemetryschema.DBName + "." + metricstelemetryschema.SamplesV4BufferTableName
+	reducedLast := metricstelemetryschema.DBName + "." + metricstelemetryschema.SamplesV4ReducedLastTableName
+	reducedSum := metricstelemetryschema.DBName + "." + metricstelemetryschema.SamplesV4ReducedSumTableName
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("base.metric_name AS metric_name", "ifNull(i.cnt, 0) AS ingested", "ifNull(d.cnt, 0) AS reduced")
@@ -352,16 +352,16 @@ func (c *clickhouse) SampleVolumeByMetric(ctx context.Context, metricNames []str
 	}
 	ctx = c.withThreads(ctx)
 
-	ingested, err := c.countSamplesByMetric(ctx, telemetrymetrics.DBName+"."+telemetrymetrics.SamplesV4BufferTableName, "count()", metricNames, effectiveFrom, startMs, endMs)
+	ingested, err := c.countSamplesByMetric(ctx, metricstelemetryschema.DBName+"."+metricstelemetryschema.SamplesV4BufferTableName, "count()", metricNames, effectiveFrom, startMs, endMs)
 	if err != nil {
 		return nil, err
 	}
 
-	last, err := c.countSamplesByMetric(ctx, telemetrymetrics.DBName+"."+telemetrymetrics.SamplesV4ReducedLastTableName, "uniq(reduced_fingerprint, unix_milli)", metricNames, effectiveFrom, startMs, endMs)
+	last, err := c.countSamplesByMetric(ctx, metricstelemetryschema.DBName+"."+metricstelemetryschema.SamplesV4ReducedLastTableName, "uniq(reduced_fingerprint, unix_milli)", metricNames, effectiveFrom, startMs, endMs)
 	if err != nil {
 		return nil, err
 	}
-	sum, err := c.countSamplesByMetric(ctx, telemetrymetrics.DBName+"."+telemetrymetrics.SamplesV4ReducedSumTableName, "uniq(reduced_fingerprint, unix_milli)", metricNames, effectiveFrom, startMs, endMs)
+	sum, err := c.countSamplesByMetric(ctx, metricstelemetryschema.DBName+"."+metricstelemetryschema.SamplesV4ReducedSumTableName, "uniq(reduced_fingerprint, unix_milli)", metricNames, effectiveFrom, startMs, endMs)
 	if err != nil {
 		return nil, err
 	}
@@ -419,7 +419,7 @@ func (c *clickhouse) TotalVolume(ctx context.Context, startMs, endMs int64) (uin
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("uniq(fingerprint)", "count()")
-	sb.From(telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName)
+	sb.From(metricstelemetryschema.DBName + "." + metricstelemetryschema.SamplesV4BufferTableName)
 	sb.Where(sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs))
 
 	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
@@ -470,7 +470,7 @@ func (c *clickhouse) SampleTimeseries(ctx context.Context, ruledMetrics []string
 func (c *clickhouse) totalSamplesByBucket(ctx context.Context, startMs, endMs int64) (map[int64]uint64, error) {
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select(sampleBucketExpr, "count()")
-	sb.From(telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName)
+	sb.From(metricstelemetryschema.DBName + "." + metricstelemetryschema.SamplesV4BufferTableName)
 	sb.Where(sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs))
 	sb.GroupBy("bucket")
 
@@ -485,7 +485,7 @@ func (c *clickhouse) ruledIngestedSamplesByBucket(ctx context.Context, metricNam
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select(sampleBucketExpr, "count()")
-	sb.From(telemetrymetrics.DBName + "." + telemetrymetrics.SamplesV4BufferTableName)
+	sb.From(metricstelemetryschema.DBName + "." + metricstelemetryschema.SamplesV4BufferTableName)
 	conds := []string{sb.In("metric_name", names...), sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs)}
 	if len(effectiveFrom) > 0 {
 		conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))
@@ -499,7 +499,7 @@ func (c *clickhouse) ruledIngestedSamplesByBucket(ctx context.Context, metricNam
 // reduced 60s rows are versioned by computed_at, so count distinct buckets.
 func (c *clickhouse) ruledRetainedSamplesByBucket(ctx context.Context, metricNames []string, effectiveFrom map[string]int64, startMs, endMs int64) (map[int64]uint64, error) {
 	out := make(map[int64]uint64)
-	for _, table := range []string{telemetrymetrics.SamplesV4ReducedLastTableName, telemetrymetrics.SamplesV4ReducedSumTableName} {
+	for _, table := range []string{metricstelemetryschema.SamplesV4ReducedLastTableName, metricstelemetryschema.SamplesV4ReducedSumTableName} {
 		names := make([]any, len(metricNames))
 		for i, name := range metricNames {
 			names[i] = name
@@ -507,7 +507,7 @@ func (c *clickhouse) ruledRetainedSamplesByBucket(ctx context.Context, metricNam
 
 		sb := sqlbuilder.NewSelectBuilder()
 		sb.Select(sampleBucketExpr, "uniq(reduced_fingerprint, unix_milli)")
-		sb.From(telemetrymetrics.DBName + "." + table)
+		sb.From(metricstelemetryschema.DBName + "." + table)
 		conds := []string{sb.In("metric_name", names...), sb.GE("unix_milli", startMs), sb.LT("unix_milli", endMs)}
 		if len(effectiveFrom) > 0 {
 			conds = append(conds, strictEffectiveFrom(sb, metricNames, effectiveFrom))

frontend/docs/authz-guide.md

@@ -0,0 +1,136 @@
+# AuthZ Guide
+
+How to structure a page so it works with the permission system.
+
+We are migrating from the `ADMIN | EDITOR | VIEWER` roles to per-action checks. Instead of granting `VIEWER` and
+exposing everything, a user can now be granted access to a single resource, eg: `Logs` only.
+
+- [Prerequisites](#prerequisites)
+- [Core rules](#core-rules)
+- [Page patterns](#page-patterns)
+- [What "blocked" means](#what-blocked-means)
+- [Migration checklist](#migration-checklist)
+- [Testing](#testing)
+
+## Prerequisites
+
+Check whether the resource your page represents is supported: see
+[permissions.type.ts](../src/lib/authz/hooks/useAuthZ/permissions.type.ts) for the current resources and their allowed
+verbs.
+
+**If the resource is not listed there, skip authz for now**. The backend does not enforce it yet, so any frontend
+check would be decorative. Revisit once the resource is generated into that file (it is auto-generated from the
+backend).
+
+## Core rules
+
+These hold for every page. The per-pattern sections below only add to them.
+
+1. **A page is always reachable, regardless of permission.** The intended action must be known before permission can
+   be checked, so the route renders first and individual pieces are gated.
+2. **`update` requires both `read` and `update`.** A user who can write but cannot read the current value must not get
+   an edit affordance.
+3. **`delete` is independent of `read`.** Delete controls stay visible for a user who holds `delete` but not `read`.
+4. **Never gate per row.** If a user can `list`, render every row. Check `read` only when the row is opened (drawer or
+   detail route).
+5. **Gate the narrowest thing that works**, a button over a section, a section over a page.
+6. **A resource may be gated while a sub-resource is not.** A user without `read` on Service Accounts can still hold
+   `create` on API Keys, so blocking the outer container would hide work they are allowed to do.
+7. **Verbs not covered here** (`attach`, `detach`, `assignee`) behave like `delete`: gate the control that triggers
+   them, not the surrounding content.
+
+## Page patterns
+
+### List page
+
+![Visual rules for structuring a list page](./assets/list-example.svg)
+
+Without `list`, but with any of `read` / `create` / `update`, only the table is blocked:
+
+- Title, description, search filters and action buttons stay visible.
+- Filters and any control that drives the table are non-interactive.
+- The create button stays enabled if the user holds `create`.
+
+### Edit page
+
+![Visual rules for structuring an edit page](./assets/edit-example.svg)
+
+Without `read`:
+
+- Block the content with `withAuthZContent`, not the whole route.
+- Keep delete visible (rule 3).
+- Keep update blocked (rule 2).
+
+### Drawer
+
+![Visual rules for structuring a drawer](./assets/drawer-example.svg)
+
+Without `read`:
+
+- Block the drawer body, not the drawer itself.
+- Prefer routing that carries the resource ID in the URL, so delete stays reachable without `read`.
+- Keep update blocked (rule 2).
+- Watch for sub-resources the user may still be allowed to act on (rule 6).
+
+### Create
+
+Without `create`:
+
+| Entry point           | Gate with                                                     |
+| --------------------- | ------------------------------------------------------------- |
+| Button                | `AuthZButton`                                                 |
+| Dedicated create page | `withAuthZPage`                                               |
+| Create drawer opened directly (deep link) | `withAuthZContent` on the body + `AuthZButton` on footer actions |
+
+### Delete
+
+Gate the control with `AuthZButton`, or `AuthZTooltip` for a non-button trigger such as an icon or menu item.
+
+### Quick filters
+
+![Visual rules for structuring a page with quick filters](./assets/quick-filters-example.svg)
+
+## What "blocked" means
+
+Blocking is always a visible denial, never a silent removal. Use the components in
+[`lib/authz/components`](../src/lib/authz/components/README.md) rather than hand-rolling a check, they carry the
+denial message and the loading state.
+
+| Scope           | Component                                 | Denied state                                |
+| --------------- | ----------------------------------------- | ------------------------------------------- |
+| Button          | `AuthZButton`                             | Disabled + tooltip                          |
+| Any element      | `AuthZTooltip`                            | Disabled child + tooltip                    |
+| Section         | `withAuthZContent` / `AuthZGuardContent`  | Inline `PermissionDeniedCallout`            |
+| Page / route    | `withAuthZPage` / `AuthZGuardPage`        | `PermissionDeniedFullPage`                  |
+| Custom fallback | `withAuthZ` / `AuthZGuard`                | Whatever you pass as `fallback`             |
+
+Prefer the HOC (`withAuthZ*`); reach for the JSX guard (`AuthZGuard*`) when the gate depends on conditional rendering
+and an HOC cannot express it. The components README has the full decision tree and how to build the `checks` array.
+
+## Migration checklist
+
+Use the existing components. Create a new one only if none fit.
+
+- [ ] Can I apply a `withAuthZ*` variant directly, or must I extract the content into a component first?
+  - If extraction is needed, declare the new content component in the same file to keep the diff small, then move it
+    to its own file in a follow-up commit or PR.
+- [ ] Is the layout structured to respect the [core rules](#core-rules)?
+  - If not, raise it in the frontend Slack channel before reshaping the page.
+- [ ] Am I gating a shared component rather than a page or section?
+  - If so, it must stay functional with no permission. Example: the Query Builder works without field suggestions when
+    the user cannot read them.
+
+## Testing
+
+### Devtool
+
+Press `Cmd + K` (`Ctrl + K` on Windows/Linux) to open the shortcuts, search for `AuthZ`, and pick the first
+result. The devtool simulates granted and denied permissions across the UI.
+
+Available only in local development, it is stripped from production builds.
+
+### Unit tests
+
+[`lib/authz/utils/README.md`](../src/lib/authz/utils/README.md) covers the `*.authz.test.tsx` naming convention, the
+MSW handlers (`setupAuthzAdmin`, `setupAuthzDenyAll`, `setupAuthzDeny`, `setupAuthzAllow`,
+`setupAuthzGrantByPrefix`), and how to test the loading state.

frontend/src/AppRoutes/Private.tsx

@@ -14,7 +14,10 @@ import { useAppContext } from 'providers/App/App';
 import { LicensePlatform, LicenseState } from 'types/api/licensesV3/getActive';
 import { OrgPreference } from 'types/api/preferences/preference';
 import { USER_ROLES } from 'types/roles';
-import { routePermission } from 'utils/permission';
+import {
+	routePermission,
+	routeWithInitialAuthZSupport,
+} from 'utils/permission';
 
 import routes, {
 	LIST_LICENSES,
@@ -42,7 +45,6 @@ function PrivateRoute({ children }: PrivateRouteProps): JSX.Element {
 	const isAdmin = user.role === USER_ROLES.ADMIN;
 	const isAIAssistantEnabled = useIsAIAssistantEnabled();
 	const isAIObservabilityEnabled = useIsAIObservabilityEnabled();
-
 	const mapRoutes = useMemo(
 		() =>
 			new Map(
@@ -226,7 +228,16 @@ function PrivateRoute({ children }: PrivateRouteProps): JSX.Element {
 		if (isPrivate) {
 			if (isLoggedInState) {
 				const route = routePermission[key];
-				if (route && route.find((e) => e === user.role) === undefined) {
+				const hasInitialAuthZSupport = Object.hasOwn(
+					routeWithInitialAuthZSupport,
+					key,
+				);
+
+				if (
+					route &&
+					route.find((e) => e === user.role) === undefined &&
+					hasInitialAuthZSupport === false
+				) {
 					return <Redirect to={ROUTES.UN_AUTHORIZED} />;
 				}
 			} else {

frontend/src/AppRoutes/__tests__/Private.test.tsx

@@ -17,6 +17,7 @@ import {
 } from 'types/api/licensesV3/getActive';
 import { OrgPreference } from 'types/api/preferences/preference';
 import { ROLES, USER_ROLES } from 'types/roles';
+import { routeWithInitialAuthZSupport } from 'utils/permission';
 
 import PrivateRoute from '../Private';
 
@@ -178,6 +179,7 @@ function createMockAppContext(
 		isFetchingHosts: false,
 		isFetchingFeatureFlags: false,
 		isFetchingOrgPreferences: false,
+		isFetchingUserPreferences: false,
 		userFetchError: null,
 		activeLicenseFetchError: null,
 		hostsFetchError: null,
@@ -198,24 +200,39 @@ function createMockAppContext(
 	};
 }
 
+// Roles that no authz-aware route grants through the legacy routePermission table
+const DENIED_ROLES: ROLES[] = [
+	USER_ROLES.ANONYMOUS as ROLES,
+	USER_ROLES.AUTHOR as ROLES,
+];
+
+const PERMITTED_ROLES: ROLES[] = [
+	USER_ROLES.ADMIN as ROLES,
+	USER_ROLES.EDITOR as ROLES,
+	USER_ROLES.VIEWER as ROLES,
+];
+
+interface AuthzRouteCase {
+	path: string;
+	deniedRoles: ROLES[];
+}
+
 interface RenderPrivateRouteOptions {
 	initialRoute?: string;
 	appContext?: Partial<IAppContext>;
 	isCloudUser?: boolean;
 }
 
-function renderPrivateRoute(options: RenderPrivateRouteOptions = {}): void {
-	const {
-		initialRoute = ROUTES.HOME,
-		appContext = {},
-		isCloudUser = true,
-	} = options;
+function buildPrivateRouteTree(
+	options: RenderPrivateRouteOptions,
+): ReactElement {
+	const { initialRoute = ROUTES.HOME, appContext = {} } = options;
 
-	mockIsCloudUser = isCloudUser;
+	const contextValue = createMockAppContext({
+		...appContext,
+	});
 
-	const contextValue = createMockAppContext(appContext);
-
-	render(
+	return (
 		<QueryClientProvider client={queryClient}>
 			<MemoryRouter initialEntries={[initialRoute]}>
 				<AppContext.Provider value={contextValue}>
@@ -229,10 +246,15 @@ function renderPrivateRoute(options: RenderPrivateRouteOptions = {}): void {
 					</PrivateRoute>
 				</AppContext.Provider>
 			</MemoryRouter>
-		</QueryClientProvider>,
+		</QueryClientProvider>
 	);
 }
 
+function renderPrivateRoute(options: RenderPrivateRouteOptions = {}): void {
+	mockIsCloudUser = options.isCloudUser ?? true;
+	render(buildPrivateRouteTree(options));
+}
+
 // Generic assertion helpers for navigation behavior
 // Using location-based assertions since Private.tsx now uses Redirect component
 
@@ -1432,6 +1454,25 @@ describe('PrivateRoute', () => {
 
 			assertStaysOnRoute(ROUTES.GET_STARTED_WITH_CLOUD);
 		});
+
+		it.each([...PERMITTED_ROLES, ...DENIED_ROLES])(
+			'should render the unauthorized page for a %s instead of bouncing off it',
+			(role) => {
+				// routePermission.UN_AUTHORIZED must grant every role: a role denied here
+				// is redirected to /un-authorized and then redirected away from it again,
+				// which loops until React bails out with a blank screen.
+				renderPrivateRoute({
+					initialRoute: ROUTES.UN_AUTHORIZED,
+					appContext: {
+						isLoggedIn: true,
+						user: createMockUser({ role }),
+					},
+				});
+
+				assertStaysOnRoute(ROUTES.UN_AUTHORIZED);
+				assertRendersChildren();
+			},
+		);
 	});
 
 	describe('Edge Cases', () => {
@@ -1477,6 +1518,174 @@ describe('PrivateRoute', () => {
 		});
 	});
 
+	describe('AuthZ Support (routeWithInitialAuthZSupport)', () => {
+		// Routes in routeWithInitialAuthZSupport always bypass legacy role check
+		const AUTHZ_ROUTE_CASES: Record<
+			keyof typeof routeWithInitialAuthZSupport,
+			AuthzRouteCase
+		> = {
+			// Everything under /settings resolves to the non-exact SETTINGS route
+			SETTINGS: { path: ROUTES.SETTINGS, deniedRoles: DENIED_ROLES },
+			MY_SETTINGS: { path: ROUTES.MY_SETTINGS, deniedRoles: DENIED_ROLES },
+			ROLES_SETTINGS: { path: ROUTES.ROLES_SETTINGS, deniedRoles: DENIED_ROLES },
+			ROLE_CREATE: { path: ROUTES.ROLE_CREATE, deniedRoles: DENIED_ROLES },
+			ROLE_DETAILS: {
+				path: ROUTES.ROLE_DETAILS.replace(':roleId', 'role-id-1'),
+				deniedRoles: DENIED_ROLES,
+			},
+			ROLE_EDIT: {
+				path: ROUTES.ROLE_EDIT.replace(':roleId', 'role-id-1'),
+				deniedRoles: DENIED_ROLES,
+			},
+			SERVICE_ACCOUNTS_SETTINGS: {
+				path: ROUTES.SERVICE_ACCOUNTS_SETTINGS,
+				deniedRoles: DENIED_ROLES,
+			},
+			TRACES_EXPLORER: { path: ROUTES.TRACES_EXPLORER, deniedRoles: DENIED_ROLES },
+			TRACE: { path: ROUTES.TRACE, deniedRoles: DENIED_ROLES },
+			TRACE_DETAIL: {
+				path: ROUTES.TRACE_DETAIL.replace(':id', 'trace-id-1'),
+				deniedRoles: DENIED_ROLES,
+			},
+			TRACE_DETAIL_OLD: {
+				path: ROUTES.TRACE_DETAIL_OLD.replace(':id', 'trace-id-1'),
+				deniedRoles: DENIED_ROLES,
+			},
+			// LOGS and LOGS_EXPLORER share a path - matchPath resolves it to whichever
+			// route definition comes last, and both keys are authz-aware either way.
+			LOGS: { path: ROUTES.LOGS, deniedRoles: DENIED_ROLES },
+			LOGS_EXPLORER: { path: ROUTES.LOGS_EXPLORER, deniedRoles: DENIED_ROLES },
+			LIVE_LOGS: { path: ROUTES.LIVE_LOGS, deniedRoles: DENIED_ROLES },
+			OLD_LOGS_EXPLORER: {
+				path: ROUTES.OLD_LOGS_EXPLORER,
+				deniedRoles: DENIED_ROLES,
+			},
+			METRICS_EXPLORER: {
+				path: ROUTES.METRICS_EXPLORER,
+				deniedRoles: DENIED_ROLES,
+			},
+			METRICS_EXPLORER_EXPLORER: {
+				path: ROUTES.METRICS_EXPLORER_EXPLORER,
+				deniedRoles: DENIED_ROLES,
+			},
+			METRICS_EXPLORER_VOLUME_CONTROL: {
+				path: ROUTES.METRICS_EXPLORER_VOLUME_CONTROL,
+				deniedRoles: DENIED_ROLES,
+			},
+			METER: { path: ROUTES.METER, deniedRoles: DENIED_ROLES },
+			METER_EXPLORER: { path: ROUTES.METER_EXPLORER, deniedRoles: DENIED_ROLES },
+			// SUPPORT already grants ANONYMOUS in routePermission, so only AUTHOR
+			// exercises the redirect branch here.
+			SUPPORT: {
+				path: ROUTES.SUPPORT,
+				deniedRoles: [USER_ROLES.AUTHOR as ROLES],
+			},
+		};
+
+		const authzRouteRolePairs: [string, string, ROLES][] = Object.entries(
+			AUTHZ_ROUTE_CASES,
+		).flatMap(([name, { path, deniedRoles }]) =>
+			deniedRoles.map((role): [string, string, ROLES] => [name, path, role]),
+		);
+
+		// Routes with no authz check - legacy role check still applies
+		const NON_AUTHZ_ROUTE_CASES: [string, string, ROLES][] = [
+			['ALERTS_NEW', ROUTES.ALERTS_NEW, USER_ROLES.VIEWER as ROLES],
+			['LIST_LICENSES', ROUTES.LIST_LICENSES, USER_ROLES.EDITOR as ROLES],
+			['ONBOARDING', ROUTES.ONBOARDING, USER_ROLES.VIEWER as ROLES],
+			['APPLICATION', ROUTES.APPLICATION, USER_ROLES.ANONYMOUS as ROLES],
+			[
+				'METRICS_EXPLORER_VIEWS',
+				ROUTES.METRICS_EXPLORER_VIEWS,
+				USER_ROLES.ANONYMOUS as ROLES,
+			],
+		];
+
+		it.each(authzRouteRolePairs)(
+			'should not redirect %s (%s) for role %s - authz routes bypass legacy role check',
+			(_name, path, role) => {
+				// Routes in routeWithInitialAuthZSupport always bypass the legacy role check.
+				// Authorization is handled by downstream components via fine-grained authz.
+				renderPrivateRoute({
+					initialRoute: path,
+					appContext: {
+						isLoggedIn: true,
+						user: createMockUser({ role }),
+					},
+				});
+
+				assertStaysOnRoute(path);
+				assertRendersChildren();
+			},
+		);
+
+		it.each([...PERMITTED_ROLES, ...DENIED_ROLES])(
+			'should not redirect a %s from an authz-aware route',
+			(role) => {
+				// All roles pass through - authorization handled downstream
+				renderPrivateRoute({
+					initialRoute: ROUTES.LOGS_EXPLORER,
+					appContext: {
+						isLoggedIn: true,
+						user: createMockUser({ role }),
+					},
+				});
+
+				assertStaysOnRoute(ROUTES.LOGS_EXPLORER);
+				assertRendersChildren();
+			},
+		);
+
+		it.each(NON_AUTHZ_ROUTE_CASES)(
+			'should redirect %s (%s) for role %s - non-authz routes use legacy role check',
+			async (_name, path, role) => {
+				// Routes NOT in routeWithInitialAuthZSupport still use legacy role check
+				renderPrivateRoute({
+					initialRoute: path,
+					appContext: {
+						isLoggedIn: true,
+						user: createMockUser({ role }),
+					},
+				});
+
+				await assertRedirectsTo(ROUTES.UN_AUTHORIZED);
+			},
+		);
+
+		it.each(authzRouteRolePairs)(
+			'should still redirect unauthenticated users away from %s (%s) with role %s',
+			async (_name, path, role) => {
+				// The authz bypass only relaxes the role check, never the login check.
+				renderPrivateRoute({
+					initialRoute: path,
+					appContext: {
+						isLoggedIn: false,
+						user: createMockUser({ role }),
+					},
+				});
+
+				await assertRedirectsTo(ROUTES.LOGIN);
+			},
+		);
+
+		it('should still redirect to workspace locked from an authz-aware route', async () => {
+			// Workspace guards run before the role check and must not be bypassed.
+			renderPrivateRoute({
+				initialRoute: ROUTES.LOGS_EXPLORER,
+				appContext: {
+					isLoggedIn: true,
+					isFetchingActiveLicense: false,
+					activeLicense: createMockLicense({ platform: LicensePlatform.CLOUD }),
+					trialInfo: createMockTrialInfo({ workSpaceBlock: true }),
+					user: createMockUser({ role: USER_ROLES.VIEWER as ROLES }),
+				},
+				isCloudUser: true,
+			});
+
+			await assertRedirectsTo(ROUTES.WORKSPACE_LOCKED);
+		});
+	});
+
 	describe('Old channel route redirects', () => {
 		it.each([
 			['/settings/channels', '/alerts', 'tab=Channels'],

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

@@ -2815,6 +2815,7 @@ export enum CloudintegrationtypesServiceIDDTO {
 	redis = 'redis',
 	cloudsql_postgres = 'cloudsql_postgres',
 	memorystore_redis = 'memorystore_redis',
+	computeengine = 'computeengine',
 }
 export type CloudintegrationtypesCloudIntegrationServiceDTOAnyOf = {
 	/**
@@ -4298,6 +4299,18 @@ export interface Querybuildertypesv5QueryEnvelopeBuilderDTO {
 	type: Querybuildertypesv5QueryEnvelopeBuilderDTOType;
 }
 
+export enum Querybuildertypesv5QueryEnvelopeBuilderAIDTOType {
+	builder_ai_query = 'builder_ai_query',
+}
+export interface Querybuildertypesv5QueryEnvelopeBuilderAIDTO {
+	spec?: Querybuildertypesv5QueryBuilderQueryGithubComSigNozSignozPkgTypesQuerybuildertypesQuerybuildertypesv5TraceAggregationDTO;
+	/**
+	 * @type string
+	 * @enum builder_ai_query
+	 */
+	type: Querybuildertypesv5QueryEnvelopeBuilderAIDTOType;
+}
+
 export interface Querybuildertypesv5QueryBuilderFormulaDTO {
 	/**
 	 * @type boolean
@@ -4481,6 +4494,7 @@ export interface Querybuildertypesv5QueryEnvelopeClickHouseSQLDTO {
 
 export type Querybuildertypesv5QueryEnvelopeDTO =
 	| Querybuildertypesv5QueryEnvelopeBuilderDTO
+	| Querybuildertypesv5QueryEnvelopeBuilderAIDTO
 	| Querybuildertypesv5QueryEnvelopeFormulaDTO
 	| Querybuildertypesv5QueryEnvelopeTraceOperatorDTO
 	| Querybuildertypesv5QueryEnvelopePromQLDTO
@@ -8284,6 +8298,7 @@ export interface Querybuildertypesv5QueryRangeResponseDTO {
 
 export enum Querybuildertypesv5QueryTypeDTO {
 	builder_query = 'builder_query',
+	builder_ai_query = 'builder_ai_query',
 	builder_formula = 'builder_formula',
 	builder_trace_operator = 'builder_trace_operator',
 	clickhouse_sql = 'clickhouse_sql',

frontend/src/components/LogDetail/index.tsx

@@ -438,7 +438,11 @@ function LogDetailInner({
 			destroyOnClose
 			closeIcon={<X size={16} style={{ marginTop: Spacing.MARGIN_1 }} />}
 		>
-			<div className="log-detail-drawer__content" data-log-detail-ignore="true">
+			<div
+				className="log-detail-drawer__content"
+				data-log-detail-ignore="true"
+				data-testid="log-detail-drawer"
+			>
 				<div className="log-detail-drawer__log">
 					<Divider type="vertical" className={cx('log-type-indicator', logType)} />
 					<Tooltip

frontend/src/components/QueryBuilderV2/QueryV2/QuerySearch/QuerySearch.tsx

@@ -49,7 +49,11 @@ import { unquote } from 'utils/stringUtils';
 import { getRecentQueries } from 'lib/recentQueries/getRecentQueries';
 import type { SignalType } from 'types/api/v5/queryRange';
 
-import { queryExamples, SUGGESTIONS_SECTION } from './constants';
+import {
+	queryExamples,
+	SUGGESTION_FETCH_DEBOUNCE_MS,
+	SUGGESTIONS_SECTION,
+} from './constants';
 import {
 	combineInitialAndUserExpression,
 	dedupeOptionsByLabel,
@@ -353,7 +357,7 @@ function QuerySearch({
 	);
 
 	const debouncedFetchKeySuggestions = useMemo(
-		() => debounce(fetchKeySuggestions, 300),
+		() => debounce(fetchKeySuggestions, SUGGESTION_FETCH_DEBOUNCE_MS),
 		[fetchKeySuggestions],
 	);
 
@@ -584,7 +588,7 @@ function QuerySearch({
 	);
 
 	const debouncedFetchValueSuggestions = useMemo(
-		() => debounce(fetchValueSuggestions, 300),
+		() => debounce(fetchValueSuggestions, SUGGESTION_FETCH_DEBOUNCE_MS),
 		[fetchValueSuggestions],
 	);
 

frontend/src/components/QueryBuilderV2/QueryV2/QuerySearch/constants.ts

@@ -1,6 +1,8 @@
 export const RECENTS_SECTION = { name: 'Recent searches', rank: 1 } as const;
 export const SUGGESTIONS_SECTION = { name: 'Suggestions', rank: 2 } as const;
 
+export const SUGGESTION_FETCH_DEBOUNCE_MS = 300;
+
 // TODO: move to using TelemetrytypesFieldContextDTO when we migrate getKeySuggestions API (Part of https://github.com/SigNoz/engineering-pod/issues/5289)
 export const FIELD_CONTEXTS = [
 	'attribute',

frontend/src/components/QueryBuilderV2/QueryV2/__tests__/QuerySearch.contextSuggestions.test.tsx

@@ -23,6 +23,13 @@ jest.mock('providers/Dashboard/store/useDashboardStore', () => ({
 	}),
 }));
 
+// Shrink the suggestion-fetch debounce (300ms in prod) so these integration
+// tests aren't paced by it; coalescing semantics stay intact.
+jest.mock('../QuerySearch/constants', () => ({
+	...jest.requireActual('../QuerySearch/constants'),
+	SUGGESTION_FETCH_DEBOUNCE_MS: 30,
+}));
+
 jest.mock('hooks/queryBuilder/useQueryBuilder', () => {
 	const handleRunQuery = jest.fn();
 	return {

frontend/src/components/TanStackTableView/TanStackCustomTableRow.tsx

@@ -88,6 +88,7 @@ function TanStackCustomTableRow<TData, TItemKey = string>({
 			{...props}
 			className={rowClassName}
 			style={rowStyle}
+			data-testid={context?.getRowTestId?.(rowData)}
 			onMouseEnter={handleMouseEnter}
 			onMouseLeave={clearHovered}
 		>
@@ -154,6 +155,12 @@ function areTableRowPropsEqual<TData, TItemKey = string>(
 			return false;
 		}
 
+		const prevTestId = prev.context?.getRowTestId?.(prevData) ?? '';
+		const nextTestId = next.context?.getRowTestId?.(nextData) ?? '';
+		if (prevTestId !== nextTestId) {
+			return false;
+		}
+
 		const prevStyle = prev.context?.getRowStyle?.(prevData);
 		const nextStyle = next.context?.getRowStyle?.(nextData);
 		if (prevStyle !== nextStyle) {

frontend/src/components/TanStackTableView/TanStackRow.tsx

@@ -33,7 +33,6 @@ function TanStackRowCellsInner<TData, TItemKey = string>({
 	// Stable references via destructuring, keep them as is
 	const onRowClick = context?.onRowClick;
 	const onRowClickNewTab = context?.onRowClickNewTab;
-	const onRowDeactivate = context?.onRowDeactivate;
 	const isRowActive = context?.isRowActive;
 	const getRowKeyData = context?.getRowKeyData;
 	const rowIndex = row.index;
@@ -52,21 +51,9 @@ function TanStackRowCellsInner<TData, TItemKey = string>({
 			}
 
 			const isActive = isRowActive?.(rowData) ?? false;
-			if (isActive && onRowDeactivate) {
-				onRowDeactivate();
-			} else {
-				onRowClick?.(rowData, itemKey);
-			}
+			onRowClick?.(rowData, itemKey, { isActive });
 		},
-		[
-			isRowActive,
-			onRowDeactivate,
-			onRowClick,
-			onRowClickNewTab,
-			rowData,
-			getRowKeyData,
-			rowIndex,
-		],
+		[isRowActive, onRowClick, onRowClickNewTab, rowData, getRowKeyData, rowIndex],
 	);
 
 	if (itemKind === 'expansion') {
@@ -120,7 +107,6 @@ function areRowCellsPropsEqual<TData>(
 		prev.columnVisibilityKey === next.columnVisibilityKey &&
 		prev.context?.onRowClick === next.context?.onRowClick &&
 		prev.context?.onRowClickNewTab === next.context?.onRowClickNewTab &&
-		prev.context?.onRowDeactivate === next.context?.onRowDeactivate &&
 		prev.context?.isRowActive === next.context?.isRowActive &&
 		prev.context?.getRowKeyData === next.context?.getRowKeyData &&
 		prev.context?.renderRowActions === next.context?.renderRowActions &&

frontend/src/components/TanStackTableView/TanStackTable.tsx

@@ -92,11 +92,11 @@ function TanStackTableInner<TData, TItemKey = string>(
 		getGroupKey,
 		getRowStyle,
 		getRowClassName,
+		getRowTestId,
 		isRowActive,
 		renderRowActions,
 		onRowClick,
 		onRowClickNewTab,
-		onRowDeactivate,
 		onSort,
 		activeRowIndex,
 		renderExpandedRow,
@@ -378,11 +378,11 @@ function TanStackTableInner<TData, TItemKey = string>(
 		() => ({
 			getRowStyle,
 			getRowClassName,
+			getRowTestId,
 			isRowActive,
 			renderRowActions,
 			onRowClick,
 			onRowClickNewTab,
-			onRowDeactivate,
 			renderExpandedRow,
 			getRowKeyData,
 			colCount: visibleColumnsCount,
@@ -396,11 +396,11 @@ function TanStackTableInner<TData, TItemKey = string>(
 		[
 			getRowStyle,
 			getRowClassName,
+			getRowTestId,
 			isRowActive,
 			renderRowActions,
 			onRowClick,
 			onRowClickNewTab,
-			onRowDeactivate,
 			renderExpandedRow,
 			getRowKeyData,
 			visibleColumnsCount,

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

@@ -85,7 +85,9 @@ describe('TanStackRowCells', () => {
 			</table>,
 		);
 		await user.click(screen.getAllByRole('cell')[0]);
-		expect(onRowClick).toHaveBeenCalledWith({ id: 'r1' }, 'r1');
+		expect(onRowClick).toHaveBeenCalledWith({ id: 'r1' }, 'r1', {
+			isActive: false,
+		});
 	});
 
 	it('fires onRowClick with empty itemKey when getRowKeyData is not provided', async () => {
@@ -117,17 +119,19 @@ describe('TanStackRowCells', () => {
 			</table>,
 		);
 		await user.click(screen.getAllByRole('cell')[0]);
-		expect(onRowClick).toHaveBeenCalledWith({ id: 'r1' }, '');
+		expect(onRowClick).toHaveBeenCalledWith({ id: 'r1' }, '', {
+			isActive: false,
+		});
 	});
 
-	it('calls onRowDeactivate instead of onRowClick when row is active', async () => {
+	it('calls onRowClick with isActive: true when the row is active', async () => {
+		// The table no longer owns open/close — it reports the active state and the
+		// consumer routes the click. An active row must still fire onRowClick.
 		const user = userEvent.setup();
 		const onRowClick = jest.fn();
-		const onRowDeactivate = jest.fn();
 		const ctx: TableRowContext<Row> = {
 			colCount: 1,
 			onRowClick,
-			onRowDeactivate,
 			isRowActive: () => true,
 			getRowKeyData: () => ({ finalKey: 'r1', itemKey: 'r1' }),
 			hasSingleColumn: false,
@@ -152,8 +156,44 @@ describe('TanStackRowCells', () => {
 			</table>,
 		);
 		await user.click(screen.getAllByRole('cell')[0]);
-		expect(onRowDeactivate).toHaveBeenCalled();
-		expect(onRowClick).not.toHaveBeenCalled();
+		expect(onRowClick).toHaveBeenCalledWith({ id: 'r1' }, 'r1', {
+			isActive: true,
+		});
+	});
+
+	it('calls onRowClick with isActive: false when the row is not active', async () => {
+		const user = userEvent.setup();
+		const onRowClick = jest.fn();
+		const ctx: TableRowContext<Row> = {
+			colCount: 1,
+			onRowClick,
+			isRowActive: () => false,
+			getRowKeyData: () => ({ finalKey: 'r1', itemKey: 'r1' }),
+			hasSingleColumn: false,
+			columnOrderKey: '',
+			columnVisibilityKey: '',
+		};
+		const row = buildMockRow([{ id: 'body' }]);
+		render(
+			<table>
+				<tbody>
+					<tr>
+						<TanStackRowCells<Row>
+							row={row as never}
+							context={ctx}
+							itemKind="row"
+							hasSingleColumn={false}
+							columnOrderKey=""
+							columnVisibilityKey=""
+						/>
+					</tr>
+				</tbody>
+			</table>,
+		);
+		await user.click(screen.getAllByRole('cell')[0]);
+		expect(onRowClick).toHaveBeenCalledWith({ id: 'r1' }, 'r1', {
+			isActive: false,
+		});
 	});
 
 	it('does not render renderRowActions before hover', () => {

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

@@ -611,6 +611,7 @@ describe('TanStackTableView Integration', () => {
 			expect(onRowClick).toHaveBeenCalledWith(
 				expect.objectContaining({ id: '1', name: 'Item 1' }),
 				'1',
+				{ isActive: false },
 			);
 		});
 
@@ -639,6 +640,7 @@ describe('TanStackTableView Integration', () => {
 			expect(onRowClick).toHaveBeenCalledWith(
 				expect.objectContaining({ id: '1', name: 'Item 1' }),
 				{ id: '1', name: 'Item 1' },
+				{ isActive: false },
 			);
 		});
 
@@ -659,15 +661,15 @@ describe('TanStackTableView Integration', () => {
 			expect(row).toHaveClass('tableRowActive');
 		});
 
-		it('calls onRowDeactivate when clicking active row', async () => {
+		it('calls onRowClick with isActive: true when clicking the active row', async () => {
+			// The consumer owns open/close routing — the table just reports the
+			// active state via the click context.
 			const user = userEvent.setup();
 			const onRowClick = jest.fn();
-			const onRowDeactivate = jest.fn();
 
 			renderTanStackTable({
 				props: {
 					onRowClick,
-					onRowDeactivate,
 					isRowActive: (row) => row.id === '1',
 				},
 			});
@@ -678,8 +680,11 @@ describe('TanStackTableView Integration', () => {
 
 			await user.click(screen.getByText('Item 1'));
 
-			expect(onRowDeactivate).toHaveBeenCalled();
-			expect(onRowClick).not.toHaveBeenCalled();
+			expect(onRowClick).toHaveBeenCalledWith(
+				expect.objectContaining({ id: '1' }),
+				expect.anything(),
+				{ isActive: true },
+			);
 		});
 
 		it('opens in new tab on ctrl+click', async () => {

frontend/src/components/TanStackTableView/index.tsx

@@ -116,9 +116,11 @@ export * from './useTableParams';
  *   getItemKey={(row) => row.id}
  *   isRowActive={(row) => row.id === selectedId}
  *   activeRowIndex={selectedIndex}
- *   onRowClick={(row, itemKey) => setSelectedId(itemKey)}
+ *   // The table reports the click + the row's active state; the consumer owns open/close.
+ *   onRowClick={(row, itemKey, { isActive }) =>
+ *     setSelectedId(isActive ? undefined : itemKey)
+ *   }
  *   onRowClickNewTab={(row, itemKey) => openInNewTab(itemKey)}
- *   onRowDeactivate={() => setSelectedId(undefined)}
  *   getRowClassName={(row) => (row.severity === 'error' ? 'row-error' : '')}
  *   getRowStyle={(row) => (row.dimmed ? { opacity: 0.5 } : {})}
  *   renderRowActions={(row) => <Button size="small">Open</Button>}

frontend/src/components/TanStackTableView/types.ts

@@ -81,15 +81,19 @@ export type FlatItem<TData> =
 	| { kind: 'row'; row: TanStackRowType<TData> }
 	| { kind: 'expansion'; row: TanStackRowType<TData> };
 
+export type RowClickContext = {
+	isActive: boolean;
+};
+
 export type TableRowContext<TData, TItemKey = string> = {
 	getRowStyle?: (row: TData) => CSSProperties;
 	getRowClassName?: (row: TData) => string;
+	getRowTestId?: (row: TData) => string;
 	isRowActive?: (row: TData) => boolean;
 	renderRowActions?: (row: TData) => ReactNode;
-	onRowClick?: (row: TData, itemKey: TItemKey) => void;
+	onRowClick?: (row: TData, itemKey: TItemKey, context: RowClickContext) => void;
 	/** Called when ctrl+click or cmd+click on a row */
 	onRowClickNewTab?: (row: TData, itemKey: TItemKey) => void;
-	onRowDeactivate?: () => void;
 	renderExpandedRow?: (
 		row: TData,
 		rowKey: string,
@@ -178,12 +182,12 @@ export type TanStackTableProps<TData, TItemKey = string> = {
 	getGroupKey?: (row: TData) => Record<string, string>;
 	getRowStyle?: (row: TData) => CSSProperties;
 	getRowClassName?: (row: TData) => string;
+	getRowTestId?: (row: TData) => string;
 	isRowActive?: (row: TData) => boolean;
 	renderRowActions?: (row: TData) => ReactNode;
-	onRowClick?: (row: TData, itemKey: TItemKey) => void;
+	onRowClick?: (row: TData, itemKey: TItemKey, context: RowClickContext) => void;
 	/** Called when ctrl+click or cmd+click on a row */
 	onRowClickNewTab?: (row: TData, itemKey: TItemKey) => void;
-	onRowDeactivate?: () => void;
 	activeRowIndex?: number;
 	renderExpandedRow?: (
 		row: TData,

frontend/src/container/AppLayout/index.tsx

@@ -104,6 +104,7 @@ function AppLayout(props: AppLayoutProps): JSX.Element {
 		isFetchingFeatureFlags,
 		featureFlagsFetchError,
 		userPreferences,
+		isFetchingUserPreferences,
 		updateChangelog,
 		toggleChangelogModal,
 		showChangelogModal,
@@ -724,12 +725,12 @@ function AppLayout(props: AppLayoutProps): JSX.Element {
 		}
 	}, []);
 
-	// Set sidebar as loaded after user preferences are fetched
+	// Set sidebar as loaded after user preferences fetch completes (success or error)
 	useEffect(() => {
-		if (userPreferences !== null) {
+		if (!isFetchingUserPreferences) {
 			setIsSidebarLoaded(true);
 		}
-	}, [userPreferences]);
+	}, [isFetchingUserPreferences]);
 
 	// Use localStorage value as fallback until preferences are loaded
 	const isSideNavPinned = isSidebarLoaded

frontend/src/container/LiveLogs/LiveLogsList/LiveLogsList.styles.scss

@@ -60,3 +60,7 @@
 		}
 	}
 }
+
+.logs-linked-row td {
+	background-color: var(--row-active-bg) !important;
+}

frontend/src/container/LiveLogs/LiveLogsList/index.tsx

@@ -204,6 +204,9 @@ function LiveLogsList({
 							data={formattedLogs}
 							isLoading={false}
 							isRowActive={(log): boolean => log.id === activeLog?.id}
+							getRowClassName={(log): string =>
+								log.id === activeLogId ? 'logs-linked-row' : ''
+							}
 							getRowStyle={(log): CSSProperties =>
 								({
 									'--row-active-bg': getRowBackgroundColor(
@@ -216,10 +219,13 @@ function LiveLogsList({
 									),
 								}) as CSSProperties
 							}
-							onRowClick={(log): void => {
-								handleSetActiveLog(log);
+							onRowClick={(log, _itemKey, { isActive }): void => {
+								if (isActive) {
+									handleCloseLogDetail();
+								} else {
+									handleSetActiveLog(log);
+								}
 							}}
-							onRowDeactivate={handleCloseLogDetail}
 							activeRowIndex={activeLogIndex}
 							renderRowActions={(log): ReactNode => (
 								<LogLinesActionButtons

frontend/src/container/LogsExplorerList/LogsExplorerList.style.scss

@@ -323,3 +323,7 @@
 		}
 	}
 }
+
+.logs-linked-row td {
+	background-color: var(--row-active-bg) !important;
+}

frontend/src/container/LogsExplorerList/index.tsx

@@ -211,9 +211,11 @@ function LogsExplorerList({
 					data={logs}
 					isLoading={isLoading || isFetching}
 					onEndReached={onEndReached}
-					isRowActive={(log): boolean =>
-						log.id === activeLog?.id || log.id === activeLogId
+					isRowActive={(log): boolean => log.id === activeLog?.id}
+					getRowClassName={(log): string =>
+						log.id === activeLogId ? 'logs-linked-row' : ''
 					}
+					getRowTestId={(log): string => `logs-table-row-${log.id}`}
 					getRowStyle={(log): CSSProperties =>
 						({
 							'--row-active-bg': getRowBackgroundColor(
@@ -226,10 +228,13 @@ function LogsExplorerList({
 							),
 						}) as CSSProperties
 					}
-					onRowClick={(log): void => {
-						handleSetActiveLog(log);
+					onRowClick={(log, _itemKey, { isActive }): void => {
+						if (isActive) {
+							handleCloseLogDetail();
+						} else {
+							handleSetActiveLog(log);
+						}
 					}}
-					onRowDeactivate={handleCloseLogDetail}
 					activeRowIndex={activeLogIndex}
 					renderRowActions={(log): ReactNode => (
 						<LogLinesActionButtons
@@ -282,6 +287,7 @@ function LogsExplorerList({
 		options.maxLines,
 		options.fontSize,
 		activeLogIndex,
+		activeLogId,
 		logs,
 		onEndReached,
 		getItemContent,

frontend/src/container/RolesSettings/CreateEditRolePage/__tests__/JsonEditor.test.tsx

@@ -151,7 +151,9 @@ describe('JsonEditor', () => {
 			);
 			await user.click(await within(readToggle).findByText('Only selected'));
 
-			const input = screen.getByTestId('item-input-selector-input');
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
 			await user.type(input, 'test-key-123{enter}');
 
 			await switchToJsonMode();

frontend/src/container/RolesSettings/CreateEditRolePage/__tests__/PermissionEditor.test.tsx

@@ -1,17 +1,8 @@
-import { Route, Switch } from 'react-router-dom';
-import ROUTES from 'constants/routes';
 import { server } from 'mocks-server/server';
-import { render, screen, userEvent, waitFor, within } from 'tests/test-utils';
+import { screen, userEvent, waitFor, within } from 'tests/test-utils';
 import { setupAuthzAdmin } from 'lib/authz/utils/authz-test-utils';
-import { TooltipProvider } from '@signozhq/ui/tooltip';
 
-import CreateEditRolePage from '../CreateEditRolePage';
-
-async function expandAllCards(): Promise<void> {
-	const user = userEvent.setup();
-	const expandButton = await screen.findByTestId('expand-all-button');
-	await user.click(expandButton);
-}
+import { expandAllCards, renderCreateRolePage } from './testUtils';
 
 beforeEach(() => {
 	server.use(setupAuthzAdmin());
@@ -21,35 +12,16 @@ afterEach(() => {
 	server.resetHandlers();
 });
 
-async function renderPage(): Promise<ReturnType<typeof render>> {
-	const result = render(
-		<TooltipProvider>
-			<Switch>
-				<Route path={ROUTES.ROLES_SETTINGS} exact>
-					<div data-testid="roles-list-redirect" />
-				</Route>
-				<Route path={ROUTES.ROLE_CREATE}>
-					<CreateEditRolePage />
-				</Route>
-			</Switch>
-		</TooltipProvider>,
-		undefined,
-		{ initialRoute: '/settings/roles/new' },
-	);
-	await screen.findByTestId('permission-editor');
-	return result;
-}
-
 describe('PermissionEditor', () => {
 	describe('mode toggle', () => {
 		it('renders permission editor with testId', async () => {
-			await renderPage();
+			await renderCreateRolePage();
 
 			expect(screen.getByTestId('permission-editor')).toBeInTheDocument();
 		});
 
 		it('defaults to interactive mode', async () => {
-			await renderPage();
+			await renderCreateRolePage();
 
 			const interactiveRadio = screen.getByTestId(
 				'permission-editor-mode-interactive',
@@ -59,7 +31,7 @@ describe('PermissionEditor', () => {
 
 		it('switches to JSON mode when clicked', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 
 			const jsonRadio = screen.getByTestId('permission-editor-mode-json');
 			await user.click(jsonRadio);
@@ -70,7 +42,7 @@ describe('PermissionEditor', () => {
 
 		it('switches back to interactive mode', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 
 			const jsonRadio = screen.getByTestId('permission-editor-mode-json');
 			await user.click(jsonRadio);
@@ -87,7 +59,7 @@ describe('PermissionEditor', () => {
 
 	describe('resource cards', () => {
 		it('renders all resource cards', async () => {
-			await renderPage();
+			await renderCreateRolePage();
 
 			expect(
 				screen.getByTestId('resource-card-factor-api-key'),
@@ -99,7 +71,7 @@ describe('PermissionEditor', () => {
 		});
 
 		it('resource cards are collapsed by default', async () => {
-			await renderPage();
+			await renderCreateRolePage();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
 			const header = within(apiKeyCard).getByTestId(
@@ -111,7 +83,7 @@ describe('PermissionEditor', () => {
 
 		it('expands resource card when header clicked', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
 			const header = within(apiKeyCard).getByTestId(
@@ -125,7 +97,7 @@ describe('PermissionEditor', () => {
 
 		it('collapses expanded resource card when header clicked again', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
 			const header = within(apiKeyCard).getByTestId(
@@ -139,7 +111,7 @@ describe('PermissionEditor', () => {
 		});
 
 		it('shows granted count in resource card header', async () => {
-			await renderPage();
+			await renderCreateRolePage();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
 			await expect(
@@ -150,7 +122,7 @@ describe('PermissionEditor', () => {
 
 	describe('action toggles', () => {
 		it('renders action toggles for each available action', async () => {
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -169,7 +141,7 @@ describe('PermissionEditor', () => {
 		});
 
 		it('defaults all actions to None scope', async () => {
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -187,7 +159,7 @@ describe('PermissionEditor', () => {
 
 		it('changes scope to All when clicked', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -208,7 +180,7 @@ describe('PermissionEditor', () => {
 
 		it('updates granted count when scope changed', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -227,7 +199,7 @@ describe('PermissionEditor', () => {
 	describe('Only Selected scope', () => {
 		it('shows item input selector when Only Selected is chosen', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -239,12 +211,14 @@ describe('PermissionEditor', () => {
 				await within(createToggle).findByText('Only selected');
 			await user.click(onlySelectedBtn);
 
-			expect(screen.getByTestId('item-input-selector')).toBeInTheDocument();
+			expect(
+				screen.getByTestId('item-input-selector-factor-api-key-read'),
+			).toBeInTheDocument();
 		});
 
 		it('adds item when typed and Enter pressed', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -254,7 +228,9 @@ describe('PermissionEditor', () => {
 
 			await user.click(await within(createToggle).findByText('Only selected'));
 
-			const input = screen.getByTestId('item-input-selector-input');
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
 			await user.type(input, 'api-key-001{enter}');
 
 			await expect(screen.findByText('api-key-001')).resolves.toBeInTheDocument();
@@ -262,7 +238,7 @@ describe('PermissionEditor', () => {
 
 		it('adds item when Add button clicked', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -272,10 +248,14 @@ describe('PermissionEditor', () => {
 
 			await user.click(await within(createToggle).findByText('Only selected'));
 
-			const input = screen.getByTestId('item-input-selector-input');
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
 			await user.type(input, 'api-key-002');
 
-			const addBtn = screen.getByTestId('item-input-selector-add-btn');
+			const addBtn = screen.getByTestId(
+				'item-input-selector-add-btn-factor-api-key-read',
+			);
 			await user.click(addBtn);
 
 			await expect(screen.findByText('api-key-002')).resolves.toBeInTheDocument();
@@ -283,7 +263,7 @@ describe('PermissionEditor', () => {
 
 		it('adds multiple items separated by comma', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -293,7 +273,9 @@ describe('PermissionEditor', () => {
 
 			await user.click(await within(createToggle).findByText('Only selected'));
 
-			const input = screen.getByTestId('item-input-selector-input');
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
 			await user.type(input, 'key-a, key-b, key-c{enter}');
 
 			await expect(screen.findByText('key-a')).resolves.toBeInTheDocument();
@@ -303,7 +285,7 @@ describe('PermissionEditor', () => {
 
 		it('adds multiple items separated by space', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -313,7 +295,9 @@ describe('PermissionEditor', () => {
 
 			await user.click(await within(createToggle).findByText('Only selected'));
 
-			const input = screen.getByTestId('item-input-selector-input');
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
 			await user.type(input, 'key-x key-y key-z{enter}');
 
 			await expect(screen.findByText('key-x')).resolves.toBeInTheDocument();
@@ -323,7 +307,7 @@ describe('PermissionEditor', () => {
 
 		it('does not add duplicate items', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -333,7 +317,9 @@ describe('PermissionEditor', () => {
 
 			await user.click(await within(createToggle).findByText('Only selected'));
 
-			const input = screen.getByTestId('item-input-selector-input');
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
 			await user.type(input, 'same-key{enter}');
 			await user.type(input, 'same-key{enter}');
 
@@ -343,7 +329,7 @@ describe('PermissionEditor', () => {
 
 		it('removes item when X clicked', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -353,20 +339,138 @@ describe('PermissionEditor', () => {
 
 			await user.click(await within(createToggle).findByText('Only selected'));
 
-			const input = screen.getByTestId('item-input-selector-input');
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
 			await user.type(input, 'removable-key{enter}');
 
-			const removeBtn = screen.getByRole('button', {
-				name: /remove removable-key/i,
+			const badge = await screen.findByTestId('item-badge-factor-api-key-read-0');
+			const removeBtn = within(badge).getByRole('button', {
+				name: 'Remove removable-key',
 			});
 			await user.click(removeBtn);
 
 			expect(screen.queryByText('removable-key')).not.toBeInTheDocument();
 		});
 
+		it('names each badge close button after the item it removes', async () => {
+			const user = userEvent.setup();
+			await renderCreateRolePage();
+			await expandAllCards();
+
+			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
+			const readToggle = within(apiKeyCard).getByTestId(
+				'action-toggle-factor-api-key-read',
+			);
+			await user.click(await within(readToggle).findByText('Only selected'));
+
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
+			await user.type(input, 'key-one key-two{enter}');
+
+			const firstBadge = await screen.findByTestId(
+				'item-badge-factor-api-key-read-0',
+			);
+			const secondBadge = screen.getByTestId('item-badge-factor-api-key-read-1');
+
+			expect(
+				within(firstBadge).getByRole('button', { name: 'Remove key-one' }),
+			).toBeInTheDocument();
+			expect(
+				within(secondBadge).getByRole('button', { name: 'Remove key-two' }),
+			).toBeInTheDocument();
+		});
+
+		it('exposes the full item value as a title so truncated badges stay readable', async () => {
+			const user = userEvent.setup();
+			await renderCreateRolePage();
+			await expandAllCards();
+
+			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
+			const readToggle = within(apiKeyCard).getByTestId(
+				'action-toggle-factor-api-key-read',
+			);
+			await user.click(await within(readToggle).findByText('Only selected'));
+
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
+			await user.type(input, 'a-very-long-api-key-identifier-000001{enter}');
+
+			const badge = await screen.findByTestId('item-badge-factor-api-key-read-0');
+			expect(
+				within(badge).getByTitle('a-very-long-api-key-identifier-000001'),
+			).toBeInTheDocument();
+		});
+
+		it('moves focus to the previous badge when closed with the keyboard', async () => {
+			const user = userEvent.setup();
+			await renderCreateRolePage();
+			await expandAllCards();
+
+			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
+			const readToggle = within(apiKeyCard).getByTestId(
+				'action-toggle-factor-api-key-read',
+			);
+			await user.click(await within(readToggle).findByText('Only selected'));
+
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
+			await user.type(input, 'key-one key-two{enter}');
+
+			const secondBadge = await screen.findByTestId(
+				'item-badge-factor-api-key-read-1',
+			);
+			within(secondBadge).getByRole('button', { name: 'Remove key-two' }).focus();
+
+			await user.keyboard('{Enter}');
+
+			await waitFor(() => {
+				const firstBadge = screen.getByTestId('item-badge-factor-api-key-read-0');
+				expect(
+					within(firstBadge).getByRole('button', { name: 'Remove key-one' }),
+				).toHaveFocus();
+			});
+		});
+
+		it('does not steal focus when a badge is closed with the mouse', async () => {
+			const user = userEvent.setup();
+			await renderCreateRolePage();
+			await expandAllCards();
+
+			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
+			const readToggle = within(apiKeyCard).getByTestId(
+				'action-toggle-factor-api-key-read',
+			);
+			await user.click(await within(readToggle).findByText('Only selected'));
+
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
+			await user.type(input, 'key-one key-two{enter}');
+
+			const secondBadge = await screen.findByTestId(
+				'item-badge-factor-api-key-read-1',
+			);
+			await user.click(
+				within(secondBadge).getByRole('button', { name: 'Remove key-two' }),
+			);
+
+			await waitFor(() => {
+				expect(screen.queryByText('key-two')).not.toBeInTheDocument();
+			});
+
+			const firstBadge = screen.getByTestId('item-badge-factor-api-key-read-0');
+			expect(
+				within(firstBadge).getByRole('button', { name: 'Remove key-one' }),
+			).not.toHaveFocus();
+		});
+
 		it('shows Add button disabled when input is empty', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -376,7 +480,9 @@ describe('PermissionEditor', () => {
 
 			await user.click(await within(createToggle).findByText('Only selected'));
 
-			const addBtn = screen.getByTestId('item-input-selector-add-btn');
+			const addBtn = screen.getByTestId(
+				'item-input-selector-add-btn-factor-api-key-read',
+			);
 			expect(addBtn).toBeDisabled();
 		});
 	});
@@ -384,7 +490,7 @@ describe('PermissionEditor', () => {
 	describe('scope change confirmation dialog', () => {
 		it('shows confirm dialog when leaving Only Selected with items', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -394,7 +500,9 @@ describe('PermissionEditor', () => {
 
 			await user.click(await within(createToggle).findByText('Only selected'));
 
-			const input = screen.getByTestId('item-input-selector-input');
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
 			await user.type(input, 'will-be-cleared{enter}');
 
 			await user.click(await within(createToggle).findByText('All'));
@@ -406,7 +514,7 @@ describe('PermissionEditor', () => {
 
 		it('clears items when confirmed', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -416,7 +524,9 @@ describe('PermissionEditor', () => {
 
 			await user.click(await within(createToggle).findByText('Only selected'));
 
-			const input = screen.getByTestId('item-input-selector-input');
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
 			await user.type(input, 'to-be-cleared{enter}');
 
 			await user.click(await within(createToggle).findByText('All'));
@@ -433,7 +543,7 @@ describe('PermissionEditor', () => {
 
 		it('keeps items when cancelled', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -443,7 +553,9 @@ describe('PermissionEditor', () => {
 
 			await user.click(await within(createToggle).findByText('Only selected'));
 
-			const input = screen.getByTestId('item-input-selector-input');
+			const input = screen.getByTestId(
+				'item-input-selector-input-factor-api-key-read',
+			);
 			await user.type(input, 'preserved-key{enter}');
 
 			await user.click(await within(createToggle).findByText('None'));
@@ -455,12 +567,14 @@ describe('PermissionEditor', () => {
 				screen.findByText('preserved-key'),
 			).resolves.toBeInTheDocument();
 
-			expect(screen.getByTestId('item-input-selector')).toBeInTheDocument();
+			expect(
+				screen.getByTestId('item-input-selector-factor-api-key-read'),
+			).toBeInTheDocument();
 		});
 
 		it('does not show dialog when leaving Only Selected with no items', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -479,7 +593,7 @@ describe('PermissionEditor', () => {
 
 	describe('verbs without Only Selected option', () => {
 		it('does not show Only Selected for list verb', async () => {
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -501,7 +615,7 @@ describe('PermissionEditor', () => {
 
 	describe('collapse/expand all resources', () => {
 		it('shows expand/collapse toggle group', async () => {
-			await renderPage();
+			await renderCreateRolePage();
 
 			expect(screen.getByTestId('toggle-all-group')).toBeInTheDocument();
 			expect(screen.getByTestId('expand-all-button')).toBeInTheDocument();
@@ -509,7 +623,7 @@ describe('PermissionEditor', () => {
 		});
 
 		it('expands all cards when expand button clicked', async () => {
-			await renderPage();
+			await renderCreateRolePage();
 			await expandAllCards();
 
 			const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
@@ -523,7 +637,7 @@ describe('PermissionEditor', () => {
 	describe('resource card error states', () => {
 		it('shows error border on collapsed card with validation error', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 
 			const nameInput = screen.getByTestId('role-name-input');
 			await user.type(nameInput, 'valid-role');
@@ -553,7 +667,7 @@ describe('PermissionEditor', () => {
 
 		it('hides error border when card is expanded', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 
 			const nameInput = screen.getByTestId('role-name-input');
 			await user.type(nameInput, 'valid-role');
@@ -590,7 +704,7 @@ describe('PermissionEditor', () => {
 
 		it('clears validation error when permission is changed', async () => {
 			const user = userEvent.setup();
-			await renderPage();
+			await renderCreateRolePage();
 
 			const nameInput = screen.getByTestId('role-name-input');
 			await user.type(nameInput, 'valid-role');

frontend/src/container/RolesSettings/CreateEditRolePage/__tests__/PermissionEditor.wizard.test.tsx

@@ -0,0 +1,462 @@
+import { server } from 'mocks-server/server';
+import { screen, userEvent, waitFor, within } from 'tests/test-utils';
+import { setupAuthzAdmin } from 'lib/authz/utils/authz-test-utils';
+
+import { expandAllCards, renderCreateRolePage } from './testUtils';
+
+beforeEach(() => {
+	server.use(setupAuthzAdmin());
+});
+
+afterEach(() => {
+	server.resetHandlers();
+});
+
+async function selectOnlySelected(
+	user: ReturnType<typeof userEvent.setup>,
+	resource = 'logs',
+): Promise<void> {
+	await renderCreateRolePage();
+	await expandAllCards();
+
+	const card = screen.getByTestId(`resource-card-${resource}`);
+	const readToggle = within(card).getByTestId(`action-toggle-${resource}-read`);
+	await user.click(await within(readToggle).findByText('Only selected'));
+}
+
+async function selectLogsOnlySelected(
+	user: ReturnType<typeof userEvent.setup>,
+): Promise<void> {
+	await selectOnlySelected(user, 'logs');
+}
+
+async function openWizard(
+	user: ReturnType<typeof userEvent.setup>,
+	resource = 'logs',
+): Promise<void> {
+	await selectOnlySelected(user, resource);
+
+	await user.click(
+		screen.getByTestId(`telemetry-wizard-trigger-${resource}-read`),
+	);
+	await screen.findByTestId(`telemetry-wizard-dialog-${resource}-read`);
+}
+
+async function openLogsWizard(
+	user: ReturnType<typeof userEvent.setup>,
+): Promise<void> {
+	await openWizard(user, 'logs');
+}
+
+describe('PermissionEditor - TelemetrySelectorWizard', () => {
+	it('shows wizard button for telemetry resources', async () => {
+		const user = userEvent.setup();
+		await selectLogsOnlySelected(user);
+
+		expect(
+			screen.getByTestId('telemetry-wizard-trigger-logs-read'),
+		).toBeInTheDocument();
+	});
+
+	it('does not show wizard button for non-telemetry resources', async () => {
+		await renderCreateRolePage();
+		await expandAllCards();
+
+		const apiKeyCard = screen.getByTestId('resource-card-factor-api-key');
+		const readToggle = within(apiKeyCard).getByTestId(
+			'action-toggle-factor-api-key-read',
+		);
+
+		const user = userEvent.setup();
+		await user.click(await within(readToggle).findByText('Only selected'));
+
+		expect(
+			screen.queryByTestId('telemetry-wizard-trigger-logs-read'),
+		).not.toBeInTheDocument();
+	});
+
+	it('opens wizard dialog when trigger clicked', async () => {
+		const user = userEvent.setup();
+		await selectLogsOnlySelected(user);
+
+		await user.click(screen.getByTestId('telemetry-wizard-trigger-logs-read'));
+
+		await expect(
+			screen.findByTestId('telemetry-wizard-dialog-logs-read'),
+		).resolves.toBeInTheDocument();
+	});
+
+	it('adds a query-type wildcard when the value is left empty', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.click(screen.getByTestId('wizard-add-btn-logs-read'));
+
+		await expect(
+			screen.findByText('builder_query/*'),
+		).resolves.toBeInTheDocument();
+	});
+
+	it('does not offer builder sub query', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.click(screen.getByTestId('wizard-query-type-select-logs-read'));
+
+		expect(screen.queryByText('Builder Sub Query')).not.toBeInTheDocument();
+	});
+
+	it('does not show PromQL for logs', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.click(screen.getByTestId('wizard-query-type-select-logs-read'));
+
+		expect(
+			screen.queryByTestId('wizard-query-type-option-promql-logs-read'),
+		).not.toBeInTheDocument();
+	});
+
+	it('does not show PromQL for traces', async () => {
+		const user = userEvent.setup();
+		await openWizard(user, 'traces');
+
+		await user.click(screen.getByTestId('wizard-query-type-select-traces-read'));
+
+		expect(
+			screen.queryByTestId('wizard-query-type-option-promql-traces-read'),
+		).not.toBeInTheDocument();
+	});
+
+	it('allows PromQL for metrics', async () => {
+		const user = userEvent.setup();
+		await openWizard(user, 'metrics');
+
+		await user.click(screen.getByTestId('wizard-query-type-select-metrics-read'));
+		await user.click(
+			await screen.findByTestId('wizard-query-type-option-promql-metrics-read'),
+		);
+
+		await user.click(screen.getByTestId('wizard-add-btn-metrics-read'));
+
+		await expect(screen.findByText('promql/*')).resolves.toBeInTheDocument();
+	});
+
+	it('hardcodes the key and does not let it be edited', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		const keyInput = screen.getByTestId('wizard-key-input-logs-read');
+		expect(keyInput).toHaveValue('signoz.workspace.key.id');
+		expect(keyInput).toBeDisabled();
+	});
+
+	it('hides Key field for query types that do not support key scoping', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.click(screen.getByTestId('wizard-query-type-select-logs-read'));
+		await user.click(await screen.findByText('ClickHouse SQL'));
+
+		expect(
+			screen.queryByTestId('wizard-key-input-logs-read'),
+		).not.toBeInTheDocument();
+	});
+
+	it('adds a key-scoped selector when the value is filled', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.type(screen.getByTestId('wizard-value-input-logs-read'), '123');
+
+		expect(screen.getByTestId('wizard-selector-input-logs-read')).toHaveValue(
+			'builder_query/signoz.workspace.key.id/123',
+		);
+
+		await user.click(screen.getByTestId('wizard-add-btn-logs-read'));
+
+		await expect(
+			screen.findByText('builder_query/signoz.workspace.key.id/123'),
+		).resolves.toBeInTheDocument();
+	});
+
+	it('replaces the value with a wildcard when any resource is checked', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.click(screen.getByLabelText('Any value'));
+
+		expect(screen.getByTestId('wizard-value-input-logs-read')).toHaveValue('*');
+
+		await user.click(screen.getByTestId('wizard-add-btn-logs-read'));
+
+		await expect(
+			screen.findByText('builder_query/signoz.workspace.key.id/*'),
+		).resolves.toBeInTheDocument();
+	});
+
+	it('clears the value when any resource is unchecked', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		const anyResource = screen.getByLabelText('Any value');
+		await user.click(anyResource);
+		expect(anyResource).toBeChecked();
+
+		await user.click(anyResource);
+
+		expect(anyResource).not.toBeChecked();
+		expect(screen.getByTestId('wizard-value-input-logs-read')).toHaveValue('');
+	});
+
+	it('checks any resource when the value is typed as a wildcard', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.type(screen.getByTestId('wizard-value-input-logs-read'), '*');
+
+		expect(screen.getByLabelText('Any value')).toBeChecked();
+	});
+
+	it('disables value scoping for query types that do not support it', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.click(screen.getByTestId('wizard-query-type-select-logs-read'));
+		await user.click(await screen.findByText('ClickHouse SQL'));
+
+		expect(screen.getByTestId('wizard-value-input-logs-read')).toBeDisabled();
+		expect(screen.getByLabelText('Any value')).toBeDisabled();
+	});
+
+	it('clears the value when switching to a query type without key scoping', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.type(screen.getByTestId('wizard-value-input-logs-read'), '123');
+
+		await user.click(screen.getByTestId('wizard-query-type-select-logs-read'));
+		await user.click(await screen.findByText('ClickHouse SQL'));
+
+		expect(screen.getByTestId('wizard-value-input-logs-read')).toHaveValue('');
+		expect(screen.getByTestId('wizard-selector-input-logs-read')).toHaveValue(
+			'clickhouse_sql/*',
+		);
+
+		await user.click(screen.getByTestId('wizard-add-btn-logs-read'));
+
+		await expect(
+			screen.findByText('clickhouse_sql/*'),
+		).resolves.toBeInTheDocument();
+	});
+
+	it('follows a hand-edited selector on the query type and value inputs', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		const selectorInput = screen.getByTestId('wizard-selector-input-logs-read');
+		await user.clear(selectorInput);
+		await user.type(
+			selectorInput,
+			'clickhouse_sql/signoz.workspace.key.id/checkout',
+		);
+
+		const selectTrigger = screen.getByTestId(
+			'wizard-query-type-select-logs-read',
+		);
+		expect(within(selectTrigger).getByText('ClickHouse SQL')).toBeInTheDocument();
+		expect(screen.getByTestId('wizard-value-input-logs-read')).toHaveValue(
+			'checkout',
+		);
+	});
+
+	it('checks any resource when the selector is edited to a wildcard value', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		const selectorInput = screen.getByTestId('wizard-selector-input-logs-read');
+		await user.clear(selectorInput);
+		await user.type(selectorInput, 'builder_query/signoz.workspace.key.id/*');
+
+		expect(screen.getByLabelText('Any value')).toBeChecked();
+	});
+
+	it('keeps the key input hardcoded when the selector uses another key', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		const selectorInput = screen.getByTestId('wizard-selector-input-logs-read');
+		await user.clear(selectorInput);
+		await user.type(selectorInput, 'builder_query/service.name/frontend');
+
+		expect(screen.getByTestId('wizard-key-input-logs-read')).toHaveValue(
+			'signoz.workspace.key.id',
+		);
+		expect(
+			screen.getByTestId('wizard-selector-hint-logs-read'),
+		).toHaveTextContent('Allow service.name=frontend for Builder Query queries.');
+		expect(screen.getByTestId('wizard-add-btn-logs-read')).not.toBeDisabled();
+	});
+
+	it('restores the hardcoded key in the selector once the value changes', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		const selectorInput = screen.getByTestId('wizard-selector-input-logs-read');
+		await user.clear(selectorInput);
+		await user.type(selectorInput, 'builder_query/service.name/frontend');
+
+		await user.type(screen.getByTestId('wizard-value-input-logs-read'), '2');
+
+		expect(selectorInput).toHaveValue(
+			'builder_query/signoz.workspace.key.id/frontend2',
+		);
+		expect(screen.getByTestId('wizard-add-btn-logs-read')).not.toBeDisabled();
+	});
+
+	it('blocks adding when the selector has an unknown query type', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		const selectorInput = screen.getByTestId('wizard-selector-input-logs-read');
+		await user.clear(selectorInput);
+		await user.type(selectorInput, 'sql_query/*');
+
+		expect(
+			screen.getByTestId('wizard-selector-hint-logs-read'),
+		).toHaveTextContent('"sql_query" is not a supported query type.');
+		expect(screen.getByTestId('wizard-add-btn-logs-read')).toBeDisabled();
+	});
+
+	it('blocks adding when the selector is emptied', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.clear(screen.getByTestId('wizard-selector-input-logs-read'));
+
+		expect(
+			screen.getByTestId('wizard-selector-hint-logs-read'),
+		).toHaveTextContent('Enter a selector.');
+		expect(screen.getByTestId('wizard-add-btn-logs-read')).toBeDisabled();
+	});
+
+	it('adds the hand-edited selector verbatim', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		const selectorInput = screen.getByTestId('wizard-selector-input-logs-read');
+		await user.clear(selectorInput);
+		await user.type(selectorInput, 'builder_query/signoz.workspace.key.id/a/b');
+
+		await user.click(screen.getByTestId('wizard-add-btn-logs-read'));
+
+		await expect(
+			screen.findByText('builder_query/signoz.workspace.key.id/a/b'),
+		).resolves.toBeInTheDocument();
+	});
+
+	it('closes dialog after adding selector', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.click(screen.getByTestId('wizard-add-btn-logs-read'));
+
+		await waitFor(() => {
+			expect(
+				screen.queryByTestId('telemetry-wizard-dialog-logs-read'),
+			).not.toBeInTheDocument();
+		});
+	});
+
+	it('does not add duplicate selectors', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+		await user.click(screen.getByTestId('wizard-add-btn-logs-read'));
+
+		await user.click(screen.getByTestId('telemetry-wizard-trigger-logs-read'));
+		await screen.findByTestId('telemetry-wizard-dialog-logs-read');
+		await user.click(screen.getByTestId('wizard-add-btn-logs-read'));
+
+		const badges = screen.getAllByText('builder_query/*');
+		expect(badges).toHaveLength(1);
+	});
+
+	it('resets wizard state when dialog is closed and reopened', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.type(screen.getByTestId('wizard-value-input-logs-read'), '123');
+		await user.click(screen.getByTestId('wizard-query-type-select-logs-read'));
+		await user.click(await screen.findByText('ClickHouse SQL'));
+
+		await user.click(screen.getByRole('button', { name: /cancel/i }));
+
+		await waitFor(() => {
+			expect(
+				screen.queryByTestId('telemetry-wizard-dialog-logs-read'),
+			).not.toBeInTheDocument();
+		});
+
+		await user.click(screen.getByTestId('telemetry-wizard-trigger-logs-read'));
+		const selectTrigger = await screen.findByTestId(
+			'wizard-query-type-select-logs-read',
+		);
+
+		expect(within(selectTrigger).getByText('Builder Query')).toBeInTheDocument();
+		expect(screen.getByTestId('wizard-value-input-logs-read')).toHaveValue('');
+		expect(screen.getByTestId('wizard-selector-input-logs-read')).toHaveValue(
+			'builder_query/*',
+		);
+	});
+
+	it('previews the query-type wildcard while the value is empty', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		expect(screen.getByTestId('wizard-selector-input-logs-read')).toHaveValue(
+			'builder_query/*',
+		);
+		expect(
+			screen.getByTestId('wizard-selector-hint-logs-read'),
+		).toHaveTextContent('Allow every "Builder Query" query.');
+	});
+
+	it('describes a key-scoped selector', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.type(screen.getByTestId('wizard-value-input-logs-read'), '123');
+
+		expect(
+			screen.getByTestId('wizard-selector-hint-logs-read'),
+		).toHaveTextContent(
+			'Allow signoz.workspace.key.id=123 for Builder Query queries.',
+		);
+	});
+
+	it('describes an any-resource selector', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.click(screen.getByLabelText('Any value'));
+
+		expect(
+			screen.getByTestId('wizard-selector-hint-logs-read'),
+		).toHaveTextContent(
+			'Allow every signoz.workspace.key.id for Builder Query queries.',
+		);
+	});
+
+	it('does not show query type descriptions', async () => {
+		const user = userEvent.setup();
+		await openLogsWizard(user);
+
+		await user.click(screen.getByTestId('wizard-query-type-select-logs-read'));
+
+		expect(
+			screen.queryByText(
+				'Visual query builder for selecting data sources, filters, and aggregations',
+			),
+		).not.toBeInTheDocument();
+	});
+});

frontend/src/container/RolesSettings/CreateEditRolePage/__tests__/testUtils.tsx

@@ -0,0 +1,33 @@
+import { Route, Switch } from 'react-router-dom';
+import ROUTES from 'constants/routes';
+import { render, screen, userEvent } from 'tests/test-utils';
+import { TooltipProvider } from '@signozhq/ui/tooltip';
+
+import CreateEditRolePage from '../CreateEditRolePage';
+
+export async function renderCreateRolePage(): Promise<
+	ReturnType<typeof render>
+> {
+	const result = render(
+		<TooltipProvider>
+			<Switch>
+				<Route path={ROUTES.ROLES_SETTINGS} exact>
+					<div data-testid="roles-list-redirect" />
+				</Route>
+				<Route path={ROUTES.ROLE_CREATE}>
+					<CreateEditRolePage />
+				</Route>
+			</Switch>
+		</TooltipProvider>,
+		undefined,
+		{ initialRoute: '/settings/roles/new' },
+	);
+	await screen.findByTestId('permission-editor');
+	return result;
+}
+
+export async function expandAllCards(): Promise<void> {
+	const user = userEvent.setup();
+	const expandButton = await screen.findByTestId('expand-all-button');
+	await user.click(expandButton);
+}

frontend/src/container/RolesSettings/CreateEditRolePage/components/ActionToggle.tsx

@@ -7,6 +7,7 @@ import { Typography } from '@signozhq/ui/typography';
 import { PermissionScope } from '../../types';
 import { getResourcePanel } from '../../permissions.config';
 import ItemInputSelector from './ItemInputSelector';
+import TelemetrySelectorWizard from './TelemetrySelectorWizard';
 
 import styles from './ActionToggle.module.scss';
 import { AuthZResource, AuthZVerb } from 'lib/authz/hooks/useAuthZ/types';
@@ -39,10 +40,13 @@ function ActionToggle({
 	onSelectedIdsChange,
 	hasError = false,
 }: ActionToggleProps): JSX.Element {
+	const panel = getResourcePanel(resource);
+
 	const [confirmDialogOpen, setConfirmDialogOpen] = useState(false);
 	const [pendingScope, setPendingScope] = useState<PermissionScope | null>(null);
 
 	const displayLabel = getActionLabel(action);
+	const selectorTestId = `${resource}-${action}`;
 
 	const scopeItems: Array<{ value: PermissionScope; label: string }> =
 		useMemo(() => {
@@ -121,11 +125,25 @@ function ActionToggle({
 						<Divider />
 
 						<ItemInputSelector
-							placeholder={getResourcePanel(resource).selectorPlaceholder}
+							placeholder={panel.selectorPlaceholder}
 							selectedIds={selectedIds}
 							onChange={onSelectedIdsChange}
-							docsAnchor={getResourcePanel(resource).docsAnchor}
+							testId={selectorTestId}
+							docsAnchor={panel.docsAnchor}
 							hasError={hasError}
+							prefixElement={
+								panel.selectorType === 'telemetryBuilder' ? (
+									<TelemetrySelectorWizard
+										resource={resource}
+										testId={selectorTestId}
+										onAdd={(selector): void => {
+											if (!selectedIds.includes(selector)) {
+												onSelectedIdsChange([...selectedIds, selector]);
+											}
+										}}
+									/>
+								) : null
+							}
 						/>
 					</div>
 				)}

frontend/src/container/RolesSettings/CreateEditRolePage/components/ItemInputSelector.module.scss

@@ -4,9 +4,10 @@
 	gap: var(--spacing-4);
 	background: var(--l1-background);
 	border: 1px solid var(--l1-border);
-	border-radius: 4px;
+	border-radius: var(--radius-2);
 	padding: var(--spacing-4);
 
+	--input-prefix-padding: var(--spacing-2);
 	--input-suffix-padding: var(--spacing-2);
 }
 
@@ -41,6 +42,11 @@
 	overflow-y: auto;
 }
 
+.itemInputSelectorBadge {
+	--badge-border-radius: 4px;
+	--badge-hover-background: var(--l2-background) !important;
+}
+
 .itemInputSelectorInfoIcon {
 	flex-shrink: 0;
 	color: var(--l2-foreground);
@@ -51,55 +57,7 @@
 	}
 }
 
-.itemInputSelectorBadge {
-	display: inline-flex;
-	align-items: center;
-	gap: 4px;
-	max-width: 140px;
-	padding: 2px 4px 2px 6px;
-	background: var(--l2-background);
-	border: 1px solid var(--l2-border);
-	border-radius: 4px;
-}
-
-.itemInputSelectorBadgeLabel {
-	flex: 1;
-	min-width: 0;
-}
-
-.itemInputSelectorBadgeRemove {
-	flex-shrink: 0;
-	display: flex;
-	align-items: center;
-	justify-content: center;
-	width: 14px;
-	height: 14px;
-	padding: 0;
-	background: transparent;
-	border: none;
-	border-radius: 2px;
-	color: var(--l2-foreground);
-	cursor: pointer;
-	transition:
-		background 0.15s ease,
-		color 0.15s ease;
-
-	&:hover {
-		background: var(--l1-background);
-		color: var(--l1-foreground);
-	}
-}
-
 .itemInputSelectorHint {
 	margin: 0;
 	color: var(--l2-foreground);
-
-	a {
-		color: var(--primary);
-		text-decoration: none;
-
-		&:hover {
-			text-decoration: underline;
-		}
-	}
 }

frontend/src/container/RolesSettings/CreateEditRolePage/components/ItemInputSelector.tsx

@@ -1,5 +1,6 @@
 import { useCallback, useRef, useState } from 'react';
-import { Info, Plus, X } from '@signozhq/icons';
+import { Info, Plus } from '@signozhq/icons';
+import { Badge } from '@signozhq/ui/badge';
 import { Button } from '@signozhq/ui/button';
 import { Input } from '@signozhq/ui/input';
 import { Typography } from '@signozhq/ui/typography';
@@ -15,8 +16,10 @@ export interface ItemInputSelectorProps {
 	placeholder: string;
 	selectedIds: string[];
 	onChange: (ids: string[]) => void;
+	testId: string;
 	docsAnchor?: string;
 	hasError?: boolean;
+	prefixElement?: React.ReactNode;
 }
 
 function parseInputValues(input: string): string[] {
@@ -30,11 +33,13 @@ function ItemInputSelector({
 	placeholder,
 	selectedIds,
 	onChange,
+	testId,
 	docsAnchor = 'role',
 	hasError = false,
+	prefixElement,
 }: ItemInputSelectorProps): JSX.Element {
 	const [inputValue, setInputValue] = useState('');
-	const footerRef = useRef<HTMLDivElement>(null);
+	const badgesRef = useRef<HTMLDivElement>(null);
 
 	const addValues = useCallback(
 		(input: string): void => {
@@ -87,26 +92,24 @@ function ItemInputSelector({
 		[selectedIds, onChange],
 	);
 
-	const handleBadgeKeyDown = useCallback(
-		(
-			e: React.KeyboardEvent<HTMLButtonElement>,
-			itemId: string,
-			index: number,
-		): void => {
-			if (e.key !== 'Enter' && e.key !== ' ') {
-				return;
-			}
-
+	const handleBadgeClose = useCallback(
+		(e: React.MouseEvent, itemId: string, index: number): void => {
 			e.preventDefault();
 			handleRemove(itemId);
 
+			// Activating a button via Enter/Space reports detail 0;
+			// a real click reports 1 or more
+			// Only trigger focus when using keyboard
+			const isKeyboardActivation = e.detail === 0;
+
+			if (!isKeyboardActivation) {
+				return;
+			}
+
 			const targetIndex = index > 0 ? index - 1 : 0;
 			requestAnimationFrame(() => {
-				const buttons = footerRef.current?.querySelectorAll('button');
-				const targetButton = buttons?.[targetIndex] as
-					| HTMLButtonElement
-					| undefined;
-				targetButton?.focus();
+				const buttons = badgesRef.current?.querySelectorAll('button');
+				buttons?.[targetIndex]?.focus();
 			});
 		},
 		[handleRemove],
@@ -120,7 +123,7 @@ function ItemInputSelector({
 				styles.itemInputSelector,
 				showError ? styles.itemInputSelectorError : '',
 			)}
-			data-testid="item-input-selector"
+			data-testid={`item-input-selector-${testId}`}
 		>
 			<Input
 				placeholder={placeholder}
@@ -128,14 +131,15 @@ function ItemInputSelector({
 				onChange={handleInputChange}
 				onKeyDown={handleInputKeyDown}
 				onBlur={handleInputBlur}
-				data-testid="item-input-selector-input"
+				data-testid={`item-input-selector-input-${testId}`}
+				prefix={prefixElement}
 				suffix={
 					<Button
 						variant="solid"
 						size="sm"
 						onClick={handleAddClick}
 						disabled={!inputValue.trim()}
-						data-testid="item-input-selector-add-btn"
+						data-testid={`item-input-selector-add-btn-${testId}`}
 					>
 						<Plus size={14} />
 						Add
@@ -144,28 +148,22 @@ function ItemInputSelector({
 			/>
 
 			{selectedIds.length > 0 ? (
-				<div ref={footerRef} className={styles.itemInputSelectorFooter}>
-					<div className={styles.itemInputSelectorBadges}>
+				<div className={styles.itemInputSelectorFooter}>
+					<div ref={badgesRef} className={styles.itemInputSelectorBadges}>
 						{selectedIds.map((id, index) => (
-							<span key={id} className={styles.itemInputSelectorBadge} title={id}>
-								<Typography
-									as="span"
-									size="small"
-									truncate={1}
-									className={styles.itemInputSelectorBadgeLabel}
-								>
+							<Badge
+								key={id}
+								color="secondary"
+								className={styles.itemInputSelectorBadge}
+								testId={`item-badge-${testId}-${index}`}
+								closable
+								closeAriaLabel={`Remove ${id}`}
+								onClose={(e): void => handleBadgeClose(e, id, index)}
+							>
+								<Typography as="span" size="small" truncate={1} title={id}>
 									{id}
 								</Typography>
-								<button
-									type="button"
-									className={styles.itemInputSelectorBadgeRemove}
-									onClick={(): void => handleRemove(id)}
-									onKeyDown={(e): void => handleBadgeKeyDown(e, id, index)}
-									aria-label={`Remove ${id}`}
-								>
-									<X size={10} />
-								</button>
-							</span>
+							</Badge>
 						))}
 					</div>
 					<TooltipSimple

frontend/src/container/RolesSettings/CreateEditRolePage/components/TelemetrySelectorWizard.constants.ts

@@ -0,0 +1,50 @@
+// intentionally omitting few query types
+// from pkg/types/querybuildertypes/querybuildertypesv5/query_type.go
+export type QueryTypeId = 'builder_query' | 'promql' | 'clickhouse_sql';
+
+export interface QueryTypeOption {
+	id: QueryTypeId;
+	label: string;
+	supportsKeyScoping: boolean;
+	metricsOnly?: boolean;
+}
+
+export const QUERY_TYPES: readonly QueryTypeOption[] = [
+	{
+		id: 'builder_query',
+		label: 'Builder Query',
+		supportsKeyScoping: true,
+	},
+	{
+		id: 'promql',
+		label: 'PromQL',
+		supportsKeyScoping: false,
+		metricsOnly: true,
+	},
+	{
+		id: 'clickhouse_sql',
+		label: 'ClickHouse SQL',
+		supportsKeyScoping: false,
+	},
+] as const;
+
+export const DEFAULT_QUERY_TYPE: QueryTypeId = 'builder_query';
+
+export const SUPPORTED_GRANT_KEY = 'signoz.workspace.key.id';
+
+export const ANY_RESOURCE_VALUE = '*';
+
+export interface SelectorDraft {
+	queryType: QueryTypeId;
+	value: string;
+}
+
+export interface ParsedSelector {
+	queryType?: QueryTypeId;
+	value: string;
+}
+
+export interface SelectorValidation {
+	message: string;
+	isError: boolean;
+}

frontend/src/container/RolesSettings/CreateEditRolePage/components/TelemetrySelectorWizard.module.scss

@@ -0,0 +1,52 @@
+.wizardDialog {
+	border-color: var(--l1-border);
+
+	--select-trigger-background-color: var(--l3-background);
+	--select-trigger-border-color: var(--l3-background);
+	--select-content-background: var(--l3-background);
+	--select-item-highlight-background: var(--l3-background-hover);
+	--select-trigger-outline-width: 1px;
+	--select-trigger-outline-offset: 0px;
+
+	--input-background: var(--l3-background);
+	--input-hover-background: var(--l3-background);
+	--input-focus-background: var(--l3-background);
+	--input-disabled-background: var(--l3-background);
+	--input-border-color: var(--l3-border);
+	--input-hover-border-color: var(--l3-border);
+	--input-focus-border-color: var(--l3-border);
+
+	outline: none;
+
+	& > div {
+		background-color: var(--l2-background);
+	}
+}
+
+.wizardBody {
+	display: flex;
+	flex-direction: column;
+	gap: var(--spacing-6);
+}
+
+.wizardField {
+	display: flex;
+	flex-direction: column;
+	gap: var(--spacing-2);
+}
+
+.wizardValueRow {
+	display: flex;
+	align-items: center;
+	gap: var(--spacing-3);
+}
+
+.wizardValueInput {
+	flex: 1;
+	min-width: 0;
+}
+
+.selectContent {
+	z-index: 10;
+	background-color: var(--l3-background);
+}

frontend/src/container/RolesSettings/CreateEditRolePage/components/TelemetrySelectorWizard.tsx

@@ -0,0 +1,190 @@
+import { Wand } from '@signozhq/icons';
+import { Button } from '@signozhq/ui/button';
+import { Checkbox } from '@signozhq/ui/checkbox';
+import { DialogWrapper } from '@signozhq/ui/dialog';
+import { Input } from '@signozhq/ui/input';
+import {
+	Select,
+	SelectContent,
+	SelectItem,
+	SelectTrigger,
+	SelectValue,
+} from '@signozhq/ui/select';
+import { Typography } from '@signozhq/ui/typography';
+
+import {
+	ANY_RESOURCE_VALUE,
+	QUERY_TYPES,
+	SUPPORTED_GRANT_KEY,
+} from './TelemetrySelectorWizard.constants';
+import { isQueryTypeAvailable } from './TelemetrySelectorWizard.utils';
+import useTelemetrySelectorWizard from './useTelemetrySelectorWizard';
+
+import styles from './TelemetrySelectorWizard.module.scss';
+import { AuthZResource } from 'lib/authz/hooks/useAuthZ/types';
+
+interface TelemetrySelectorWizardProps {
+	onAdd: (selector: string) => void;
+	resource: AuthZResource;
+	testId: string;
+}
+
+function TelemetrySelectorWizard({
+	onAdd,
+	resource,
+	testId,
+}: TelemetrySelectorWizardProps): JSX.Element {
+	const {
+		open,
+		queryType,
+		selectedQueryType,
+		value,
+		selector,
+		isAnyResource,
+		supportsKeyScoping,
+		validation,
+		canAdd,
+		handleOpenChange,
+		handleQueryTypeChange,
+		handleValueChange,
+		handleAnyResourceChange,
+		handleSelectorChange,
+		handleAdd,
+		handleInputKeyDown,
+	} = useTelemetrySelectorWizard({ onAdd });
+
+	const trigger = (
+		<Button
+			variant="solid"
+			size="sm"
+			data-testid={`telemetry-wizard-trigger-${testId}`}
+		>
+			<Wand size={14} />
+			Wizard
+		</Button>
+	);
+
+	const footer = (
+		<>
+			<Button
+				variant="ghost"
+				color="secondary"
+				onClick={(): void => handleOpenChange(false)}
+			>
+				Cancel
+			</Button>
+			<Button
+				variant="solid"
+				onClick={handleAdd}
+				disabled={!canAdd}
+				data-testid={`wizard-add-btn-${testId}`}
+			>
+				Add Selector
+			</Button>
+		</>
+	);
+
+	return (
+		<DialogWrapper
+			open={open}
+			onOpenChange={handleOpenChange}
+			title="Selector Wizard"
+			width="wide"
+			testId={`telemetry-wizard-dialog-${testId}`}
+			trigger={trigger}
+			footer={footer}
+			className={styles.wizardDialog}
+		>
+			<div className={styles.wizardBody}>
+				<div className={styles.wizardField}>
+					<Typography as="label" weight="medium">
+						Query Type
+					</Typography>
+					<Select value={queryType} onChange={handleQueryTypeChange}>
+						<SelectTrigger data-testid={`wizard-query-type-select-${testId}`}>
+							<SelectValue>{selectedQueryType?.label}</SelectValue>
+						</SelectTrigger>
+						<SelectContent withPortal={false} className={styles.selectContent}>
+							{QUERY_TYPES.filter((queryTypeOption) =>
+								isQueryTypeAvailable(queryTypeOption, resource),
+							).map((queryTypeOption) => (
+								<SelectItem
+									key={queryTypeOption.id}
+									value={queryTypeOption.id}
+									testId={`wizard-query-type-option-${queryTypeOption.id}-${testId}`}
+								>
+									{queryTypeOption.label}
+								</SelectItem>
+							))}
+						</SelectContent>
+					</Select>
+				</div>
+
+				{supportsKeyScoping && (
+					<div className={styles.wizardField}>
+						<Typography as="label" weight="medium">
+							Key
+						</Typography>
+						<Input
+							value={SUPPORTED_GRANT_KEY}
+							readOnly
+							disabled
+							testId={`wizard-key-input-${testId}`}
+						/>
+					</div>
+				)}
+
+				<div className={styles.wizardField}>
+					<Typography as="label" weight="medium">
+						Value
+					</Typography>
+					<div className={styles.wizardValueRow}>
+						<Input
+							className={styles.wizardValueInput}
+							placeholder={
+								supportsKeyScoping
+									? 'Value or leave empty to allow every query'
+									: ANY_RESOURCE_VALUE
+							}
+							value={value}
+							disabled={!supportsKeyScoping}
+							onChange={handleValueChange}
+							onKeyDown={handleInputKeyDown}
+							testId={`wizard-value-input-${testId}`}
+						/>
+						<Checkbox
+							id={`wizard-any-resource-${testId}`}
+							value={isAnyResource}
+							disabled={!supportsKeyScoping}
+							onChange={(checked): void => handleAnyResourceChange(checked === true)}
+							testId={`wizard-any-resource-checkbox-${testId}`}
+						>
+							Any value
+						</Checkbox>
+					</div>
+				</div>
+
+				<div className={styles.wizardField}>
+					<Typography as="label" weight="medium">
+						Selector
+					</Typography>
+					<Input
+						value={selector}
+						onChange={handleSelectorChange}
+						onKeyDown={handleInputKeyDown}
+						testId={`wizard-selector-input-${testId}`}
+					/>
+					<Typography.Text
+						size="small"
+						color={validation.isError ? 'danger' : 'muted'}
+						testId={`wizard-selector-hint-${testId}`}
+					>
+						{validation.message}
+					</Typography.Text>
+				</div>
+			</div>
+		</DialogWrapper>
+	);
+}
+
+export default TelemetrySelectorWizard;

frontend/src/container/RolesSettings/CreateEditRolePage/components/TelemetrySelectorWizard.utils.ts

@@ -0,0 +1,139 @@
+import { AuthZResource } from 'lib/authz/hooks/useAuthZ/types';
+
+import {
+	ANY_RESOURCE_VALUE,
+	ParsedSelector,
+	QUERY_TYPES,
+	QueryTypeId,
+	QueryTypeOption,
+	SelectorDraft,
+	SelectorValidation,
+	SUPPORTED_GRANT_KEY,
+} from './TelemetrySelectorWizard.constants';
+
+const METRIC_RESOURCES: ReadonlySet<AuthZResource> = new Set<AuthZResource>([
+	'metrics',
+	'meter-metrics',
+]);
+
+export function getQueryTypeOption(
+	queryType: string,
+): QueryTypeOption | undefined {
+	return QUERY_TYPES.find((option) => option.id === queryType);
+}
+
+export function isQueryTypeAvailable(
+	option: QueryTypeOption,
+	resource: AuthZResource,
+): boolean {
+	return !option.metricsOnly || METRIC_RESOURCES.has(resource);
+}
+
+export function supportsKeyScoping(queryType: string): boolean {
+	return getQueryTypeOption(queryType)?.supportsKeyScoping ?? false;
+}
+
+export function isAnyResourceValue(value: string): boolean {
+	return value.trim() === ANY_RESOURCE_VALUE;
+}
+
+function splitSelector(selector: string): string[] {
+	const parts = selector.split('/');
+
+	if (parts.length <= 3) {
+		return parts;
+	}
+
+	return [parts[0], parts[1], parts.slice(2).join('/')];
+}
+
+export function buildSelector({ queryType, value }: SelectorDraft): string {
+	const trimmedValue = value.trim();
+
+	if (!supportsKeyScoping(queryType) || !trimmedValue) {
+		return `${queryType}/${ANY_RESOURCE_VALUE}`;
+	}
+
+	return `${queryType}/${SUPPORTED_GRANT_KEY}/${trimmedValue}`;
+}
+
+export function parseSelector(selector: string): ParsedSelector {
+	const parts = splitSelector(selector.trim());
+
+	return {
+		queryType: getQueryTypeOption(parts[0])?.id,
+		value: parts.length >= 3 ? parts[2] : '',
+	};
+}
+
+/**
+ * This does a basic validation, intentionally omitting deep validations since this is to be made at backend,
+ * so this will allow to produce invalid selectors, and the validation will be done after the user try to save
+ */
+export function validateSelector(selector: string): SelectorValidation {
+	const trimmed = selector.trim();
+
+	if (!trimmed) {
+		return { message: 'Enter a selector.', isError: true };
+	}
+
+	if (trimmed === ANY_RESOURCE_VALUE) {
+		return { message: 'Allow every query of every type.', isError: false };
+	}
+
+	const parts = splitSelector(trimmed);
+	const option = getQueryTypeOption(parts[0]);
+
+	if (!option) {
+		return {
+			message: `"${parts[0]}" is not a supported query type.`,
+			isError: true,
+		};
+	}
+
+	if (parts.length < 3) {
+		if (parts.length === 2 && parts[1] !== ANY_RESOURCE_VALUE) {
+			if (!option.supportsKeyScoping) {
+				return {
+					message: `This query type does not support key scoping. Use ${option.id}/*`,
+					isError: false, // intentionally not an error
+				};
+			}
+
+			return {
+				message: `Use <query-type>/${ANY_RESOURCE_VALUE} or <query-type>/${SUPPORTED_GRANT_KEY}/<value>.`,
+				isError: false, // intentionally not an error
+			};
+		}
+
+		return {
+			message: `Allow every "${option.label}" query.`,
+			isError: false,
+		};
+	}
+
+	const [, key, value] = parts;
+
+	if (value === ANY_RESOURCE_VALUE) {
+		return {
+			message: `Allow every ${key} for ${option.label} queries.`,
+			isError: false,
+		};
+	}
+
+	if (!option.supportsKeyScoping) {
+		return {
+			message: `This query type does not support key scoping. Use ${option.id}/*`,
+			isError: false, // intentionally not an error
+		};
+	}
+
+	return {
+		message: `Allow ${key}=${value} for ${option.label} queries.`,
+		isError: false,
+	};
+}
+
+export function getDefaultSelector(queryType: QueryTypeId): string {
+	return buildSelector({ queryType, value: '' });
+}

frontend/src/container/RolesSettings/CreateEditRolePage/components/jsonSchema.config.ts

@@ -76,9 +76,10 @@ function createGrantPermissionAsReadonly(
 	return {
 		label: 'readonly',
 		insertText: resources
-			.filter(
-				(r) => r.allowedVerbs.includes('read') || r.allowedVerbs.includes('list'),
-			)
+			.filter((r) => {
+				const verbs: readonly string[] = r.allowedVerbs;
+				return verbs.includes('read') || verbs.includes('list');
+			})
 			.flatMap((r) => {
 				const verbs = r.allowedVerbs.filter((v) => v === 'read' || v === 'list');
 				return verbs.map(
@@ -103,7 +104,12 @@ function buildResourceSnippets(): SnippetDef[] {
 	for (const resource of resources) {
 		const { kind, type, allowedVerbs } = resource;
 
-		snippets.push(createGrantAllPermissionSnippet(kind, allowedVerbs, type));
+		// If only one verb is supported, no point on add grant all
+		// that will only add one permission at time, just leave the verb snippet
+		// and it will look cleaner
+		if (allowedVerbs.length > 1) {
+			snippets.push(createGrantAllPermissionSnippet(kind, allowedVerbs, type));
+		}
 
 		for (const verb of allowedVerbs) {
 			snippets.push(createGrantPermissionToVerbAndKind(kind, verb, type));

frontend/src/container/RolesSettings/CreateEditRolePage/components/useTelemetrySelectorWizard.ts

@@ -0,0 +1,157 @@
+import { useCallback, useMemo, useState } from 'react';
+
+import {
+	ANY_RESOURCE_VALUE,
+	DEFAULT_QUERY_TYPE,
+	QueryTypeId,
+	QueryTypeOption,
+	SelectorValidation,
+} from './TelemetrySelectorWizard.constants';
+import {
+	buildSelector,
+	getDefaultSelector,
+	getQueryTypeOption,
+	isAnyResourceValue,
+	parseSelector,
+	validateSelector,
+} from './TelemetrySelectorWizard.utils';
+
+interface UseTelemetrySelectorWizardParams {
+	onAdd: (selector: string) => void;
+}
+
+interface UseTelemetrySelectorWizardResult {
+	open: boolean;
+	queryType: QueryTypeId;
+	selectedQueryType: QueryTypeOption | undefined;
+	value: string;
+	selector: string;
+	isAnyResource: boolean;
+	supportsKeyScoping: boolean;
+	validation: SelectorValidation;
+	canAdd: boolean;
+	handleOpenChange: (nextOpen: boolean) => void;
+	handleQueryTypeChange: (value: string | string[]) => void;
+	handleValueChange: (event: React.ChangeEvent<HTMLInputElement>) => void;
+	handleAnyResourceChange: (checked: boolean) => void;
+	handleSelectorChange: (event: React.ChangeEvent<HTMLInputElement>) => void;
+	handleAdd: () => void;
+	handleInputKeyDown: (event: React.KeyboardEvent<HTMLInputElement>) => void;
+}
+
+function useTelemetrySelectorWizard({
+	onAdd,
+}: UseTelemetrySelectorWizardParams): UseTelemetrySelectorWizardResult {
+	const [open, setOpen] = useState(false);
+	const [queryType, setQueryType] = useState<QueryTypeId>(DEFAULT_QUERY_TYPE);
+	const [value, setValue] = useState('');
+	const [selector, setSelector] = useState(() =>
+		getDefaultSelector(DEFAULT_QUERY_TYPE),
+	);
+
+	const selectedQueryType = useMemo(
+		() => getQueryTypeOption(queryType),
+		[queryType],
+	);
+	const supportsKeyScoping = selectedQueryType?.supportsKeyScoping ?? false;
+
+	const validation = useMemo(() => validateSelector(selector), [selector]);
+
+	const applyDraft = useCallback(
+		(nextQueryType: QueryTypeId, nextValue: string): void => {
+			setQueryType(nextQueryType);
+			setValue(nextValue);
+			setSelector(buildSelector({ queryType: nextQueryType, value: nextValue }));
+		},
+		[],
+	);
+
+	const handleQueryTypeChange = useCallback(
+		(next: string | string[]): void => {
+			const selected = (Array.isArray(next) ? next[0] : next) as QueryTypeId;
+			const keepsValue = getQueryTypeOption(selected)?.supportsKeyScoping ?? false;
+
+			applyDraft(selected, keepsValue ? value : '');
+		},
+		[applyDraft, value],
+	);
+
+	const handleValueChange = useCallback(
+		(event: React.ChangeEvent<HTMLInputElement>): void => {
+			applyDraft(queryType, event.target.value);
+		},
+		[applyDraft, queryType],
+	);
+
+	const handleAnyResourceChange = useCallback(
+		(checked: boolean): void => {
+			applyDraft(queryType, checked ? ANY_RESOURCE_VALUE : '');
+		},
+		[applyDraft, queryType],
+	);
+
+	const handleSelectorChange = useCallback(
+		(event: React.ChangeEvent<HTMLInputElement>): void => {
+			const nextSelector = event.target.value;
+			setSelector(nextSelector);
+
+			const parsed = parseSelector(nextSelector);
+			if (parsed.queryType) {
+				setQueryType(parsed.queryType);
+			}
+			setValue(parsed.value);
+		},
+		[],
+	);
+
+	const handleOpenChange = useCallback((nextOpen: boolean): void => {
+		setOpen(nextOpen);
+
+		if (!nextOpen) {
+			setQueryType(DEFAULT_QUERY_TYPE);
+			setValue('');
+			setSelector(getDefaultSelector(DEFAULT_QUERY_TYPE));
+		}
+	}, []);
+
+	const handleAdd = useCallback((): void => {
+		const trimmed = selector.trim();
+
+		if (validateSelector(trimmed).isError) {
+			return;
+		}
+
+		onAdd(trimmed);
+		handleOpenChange(false);
+	}, [selector, onAdd, handleOpenChange]);
+
+	const handleInputKeyDown = useCallback(
+		(event: React.KeyboardEvent<HTMLInputElement>): void => {
+			if (event.key === 'Enter') {
+				handleAdd();
+			}
+		},
+		[handleAdd],
+	);
+
+	return {
+		open,
+		queryType,
+		selectedQueryType,
+		value,
+		selector,
+		isAnyResource: isAnyResourceValue(value),
+		supportsKeyScoping,
+		validation,
+		canAdd: !validation.isError,
+		handleOpenChange,
+		handleQueryTypeChange,
+		handleValueChange,
+		handleAnyResourceChange,
+		handleSelectorChange,
+		handleAdd,
+		handleInputKeyDown,
+	};
+}
+
+export default useTelemetrySelectorWizard;

frontend/src/container/RolesSettings/hooks/__tests__/useRolePermissions.test.ts

@@ -329,11 +329,15 @@ describe('transformTransactionGroupsToResourcePermissions', () => {
 	it('returns all resources from RESOURCE_ORDER even with empty transaction groups', () => {
 		const result = transformTransactionGroupsToResourcePermissions([]);
 
-		expect(result).toHaveLength(3);
+		expect(result).toHaveLength(7);
 		expect(result.map((r) => r.resourceKind)).toStrictEqual([
 			'factor-api-key',
 			'role',
 			'serviceaccount',
+			'logs',
+			'traces',
+			'metrics',
+			'meter-metrics',
 		]);
 	});
 
@@ -414,11 +418,15 @@ describe('createEmptyRolePermissions', () => {
 	it('creates permissions for all resources in RESOURCE_ORDER', () => {
 		const result = createEmptyRolePermissions();
 
-		expect(result).toHaveLength(3);
+		expect(result).toHaveLength(7);
 		expect(result.map((r) => r.resourceKind)).toStrictEqual([
 			'factor-api-key',
 			'role',
 			'serviceaccount',
+			'logs',
+			'traces',
+			'metrics',
+			'meter-metrics',
 		]);
 	});
 

frontend/src/container/RolesSettings/permissions.config.ts

@@ -1,4 +1,12 @@
-import { Bot, Key, Shield } from '@signozhq/icons';
+import {
+	Bot,
+	ChartLine,
+	DraftingCompass,
+	Gauge,
+	Key,
+	Logs,
+	Shield,
+} from '@signozhq/icons';
 
 import permissionsType from 'lib/authz/hooks/useAuthZ/permissions.type';
 import {
@@ -14,12 +22,15 @@ type IconComponent = typeof Shield;
 
 const OBJECT_SCOPED_VERB_SET = new Set<string>(OBJECT_SCOPED_VERBS);
 
+export type SelectorType = 'input' | 'telemetryBuilder';
+
 export interface ResourcePanelConfig {
 	label: string;
 	description: string;
 	icon: IconComponent;
 	selectorPlaceholder: string;
 	docsAnchor: string;
+	selectorType?: SelectorType;
 }
 
 /**
@@ -50,6 +61,42 @@ export const RESOURCE_PANELS: Record<AuthZResource, ResourcePanelConfig> = {
 			'Type service account ID, separate multiple with comma or space',
 		docsAnchor: 'service-account',
 	},
+	logs: {
+		label: 'Logs',
+		description: 'Log data collected across the workspace.',
+		icon: Logs,
+		selectorPlaceholder:
+			'Enter selector as <query-type>/<key>/<value> or <query-type>/* or use wizard...',
+		docsAnchor: 'logs',
+		selectorType: 'telemetryBuilder',
+	},
+	traces: {
+		label: 'Traces',
+		description: 'Distributed tracing data collected across the workspace.',
+		icon: DraftingCompass,
+		selectorPlaceholder:
+			'Enter selector as <query-type>/<key>/<value> or <query-type>/* or use wizard...',
+		docsAnchor: 'traces',
+		selectorType: 'telemetryBuilder',
+	},
+	metrics: {
+		label: 'Metrics',
+		description: 'Metric data collected across the workspace.',
+		icon: ChartLine,
+		selectorPlaceholder:
+			'Enter selector as <query-type>/<key>/<value> or <query-type>/* or use wizard...',
+		docsAnchor: 'metrics',
+		selectorType: 'telemetryBuilder',
+	},
+	'meter-metrics': {
+		label: 'Meter Metrics',
+		description: 'Usage metering data for the workspace.',
+		icon: Gauge,
+		selectorPlaceholder:
+			'Enter selector as <query-type>/<key>/<value> or <query-type>/* or use wizard...',
+		docsAnchor: 'meter-metrics',
+		selectorType: 'telemetryBuilder',
+	},
 };
 
 export const RESOURCE_ORDER = Object.keys(RESOURCE_PANELS) as AuthZResource[];

frontend/src/container/RoutingPolicies/__tests__/testUtils.ts

@@ -108,6 +108,7 @@ export function getAppContextMockState(
 		isFetchingHosts: false,
 		isFetchingFeatureFlags: false,
 		isFetchingOrgPreferences: false,
+		isFetchingUserPreferences: false,
 		userFetchError: undefined,
 		activeLicenseFetchError: null,
 		hostsFetchError: undefined,

frontend/src/container/SideNav/SideNav.tsx

@@ -144,6 +144,7 @@ function SideNav({ isPinned }: { isPinned: boolean }): JSX.Element {
 		trialInfo,
 		isLoggedIn,
 		userPreferences,
+		isFetchingUserPreferences,
 		changelog,
 		toggleChangelogModal,
 		updateUserPreferenceInContext,
@@ -261,6 +262,11 @@ function SideNav({ isPinned }: { isPinned: boolean }): JSX.Element {
 
 	// Compute initial pinned items and secondary menu items synchronously to avoid flash
 	const computedPinnedMenuItems = useMemo(() => {
+		// While loading, return empty to avoid flash
+		if (isFetchingUserPreferences) {
+			return [];
+		}
+
 		const navShortcutsPreference = userPreferences?.find(
 			(preference) => preference.name === USER_PREFERENCES.NAV_SHORTCUTS,
 		);
@@ -268,11 +274,6 @@ function SideNav({ isPinned }: { isPinned: boolean }): JSX.Element {
 			| string[]
 			| undefined;
 
-		// If userPreferences not loaded yet, return empty to avoid showing defaults before preferences load
-		if (userPreferences === null) {
-			return [];
-		}
-
 		// If preference exists with non-empty array, use stored shortcuts
 		if (isArray(navShortcuts) && navShortcuts.length > 0) {
 			return navShortcuts
@@ -282,9 +283,9 @@ function SideNav({ isPinned }: { isPinned: boolean }): JSX.Element {
 				.filter((item): item is SidebarItem => item !== undefined);
 		}
 
-		// No preference, or empty array → use defaults
+		// No preference, or empty array, or error loading → use defaults
 		return defaultMoreMenuItems.filter((item) => item.isPinned);
-	}, [userPreferences]);
+	}, [isFetchingUserPreferences, userPreferences]);
 
 	const computedSecondaryMenuItems = useMemo(() => {
 		const shouldShowIntegrationsValue =
@@ -322,12 +323,16 @@ function SideNav({ isPinned }: { isPinned: boolean }): JSX.Element {
 	// Sync state only on initial load when userPreferences first becomes available
 	useEffect(() => {
 		// Only sync once: when userPreferences loads for the first time
-		if (!hasInitializedRef.current && userPreferences !== null) {
+		if (!hasInitializedRef.current && isFetchingUserPreferences === false) {
 			setPinnedMenuItems(computedPinnedMenuItems);
 			setSecondaryMenuItems(computedSecondaryMenuItems);
 			hasInitializedRef.current = true;
 		}
-	}, [computedPinnedMenuItems, computedSecondaryMenuItems, userPreferences]);
+	}, [
+		computedPinnedMenuItems,
+		computedSecondaryMenuItems,
+		isFetchingUserPreferences,
+	]);
 
 	const isChatSupportEnabled = featureFlags?.find(
 		(flag) => flag.name === FeatureKeys.CHAT_SUPPORT,

frontend/src/hooks/useCopyToClipboard.ts

@@ -1,62 +0,0 @@
-import { useCallback, useEffect, useRef, useState } from 'react';
-
-const DEFAULT_COPIED_RESET_MS = 2000;
-
-export interface UseCopyToClipboardOptions {
-	/** How long (ms) to keep "copied" state before resetting. Default 2000. */
-	copiedResetMs?: number;
-}
-
-export type ID = number | string | null;
-
-export interface UseCopyToClipboardReturn {
-	/** Copy text to clipboard. Pass an optional id to track which item was copied (e.g. seriesIndex). */
-	copyToClipboard: (text: string, id?: ID) => void;
-	/** True when something was just copied and still within the reset threshold. */
-	isCopied: boolean;
-	/** The id passed to the last successful copy, or null after reset. Use to show "copied" state for a specific item (e.g. copiedId === item.seriesIndex). */
-	id: ID;
-}
-
-export function useCopyToClipboard(
-	options: UseCopyToClipboardOptions = {},
-): UseCopyToClipboardReturn {
-	const { copiedResetMs = DEFAULT_COPIED_RESET_MS } = options;
-	const [state, setState] = useState<{ isCopied: boolean; id: ID }>({
-		isCopied: false,
-		id: null,
-	});
-	const timeoutRef = useRef<ReturnType<typeof setTimeout> | null>(null);
-
-	useEffect(() => {
-		return (): void => {
-			if (timeoutRef.current) {
-				clearTimeout(timeoutRef.current);
-				timeoutRef.current = null;
-			}
-		};
-	}, []);
-
-	const copyToClipboard = useCallback(
-		(text: string, id?: ID): void => {
-			// oxlint-disable-next-line signoz/no-navigator-clipboard
-			navigator.clipboard.writeText(text).then(() => {
-				if (timeoutRef.current) {
-					clearTimeout(timeoutRef.current);
-				}
-				setState({ isCopied: true, id: id ?? null });
-				timeoutRef.current = setTimeout(() => {
-					setState({ isCopied: false, id: null });
-					timeoutRef.current = null;
-				}, copiedResetMs);
-			});
-		},
-		[copiedResetMs],
-	);
-
-	return {
-		copyToClipboard,
-		isCopied: state.isCopied,
-		id: state.id,
-	};
-}

frontend/src/lib/authz/components/PermissionDeniedCallout/PermissionDeniedCallout.test.tsx

@@ -19,7 +19,7 @@ describe('PermissionDeniedCallout', () => {
 	it('renders multiple denied permissions', () => {
 		const deniedPermissions = [
 			buildPermission('read', buildObjectString('serviceaccount', '*')),
-			buildPermission('update', buildObjectString('role', 'admin')),
+			buildPermission('update', buildObjectString<'update'>('role', 'admin')),
 		];
 		render(<PermissionDeniedCallout deniedPermissions={deniedPermissions} />);
 

frontend/src/lib/authz/components/PermissionDeniedFullPage/PermissionDeniedFullPage.test.tsx

@@ -20,7 +20,7 @@ describe('PermissionDeniedFullPage', () => {
 	it('renders with multiple denied permissions', () => {
 		const deniedPermissions = [
 			buildPermission('read', buildObjectString('role', 'admin')),
-			buildPermission('update', buildObjectString('role', 'admin')),
+			buildPermission('update', buildObjectString<'update'>('role', 'admin')),
 		];
 		render(<PermissionDeniedFullPage deniedPermissions={deniedPermissions} />);
 		expect(screen.getByText(/read:role:admin/)).toBeInTheDocument();

frontend/src/lib/authz/hooks/useAuthZ/permissions.type.ts

@@ -35,6 +35,26 @@ export default {
 					'update',
 				],
 			},
+			{
+				kind: 'logs',
+				type: 'telemetryresource',
+				allowedVerbs: ['read'],
+			},
+			{
+				kind: 'meter-metrics',
+				type: 'telemetryresource',
+				allowedVerbs: ['read'],
+			},
+			{
+				kind: 'metrics',
+				type: 'telemetryresource',
+				allowedVerbs: ['read'],
+			},
+			{
+				kind: 'traces',
+				type: 'telemetryresource',
+				allowedVerbs: ['read'],
+			},
 		],
 		relations: {
 			assignee: ['role'],
@@ -43,7 +63,7 @@ export default {
 			delete: ['metaresource', 'role', 'serviceaccount'],
 			detach: ['metaresource', 'role', 'serviceaccount'],
 			list: ['metaresource', 'role', 'serviceaccount'],
-			read: ['metaresource', 'role', 'serviceaccount'],
+			read: ['metaresource', 'role', 'serviceaccount', 'telemetryresource'],
 			update: ['metaresource', 'role', 'serviceaccount'],
 		},
 	},

frontend/src/lib/authz/hooks/useAuthZ/utils.ts

@@ -23,6 +23,40 @@ export function buildPermission<R extends AuthZRelation>(
 	return `${relation}${PermissionSeparator}${object}` as BrandedPermission;
 }
 
+/**
+ * Builds an object string for use with `buildPermission`.
+ *
+ * ## Type Inference Behavior
+ *
+ * TypeScript infers `R` from `resource`. If a resource belongs to multiple relations,
+ * the return type becomes a union of all matching `AuthZObject` types.
+ *
+ * Example: 'role' is valid for 'read', 'update', 'delete', 'assignee'.
+ * Without explicit generic, return type = `AuthZObject<'read' | 'update' | 'delete' | 'assignee'>`.
+ *
+ * ## When to specify explicit generic
+ *
+ * **Needed** when resource belongs to multiple relations AND you pass result to `buildPermission`
+ * with a relation that has FEWER valid resources than others:
+ *
+ * ```ts
+ * // ERROR: 'read' includes telemetry resources, 'update' does not
+ * buildPermission('update', buildObjectString('role', 'admin'))
+ *
+ * // OK: explicit generic narrows return type
+ * buildPermission('update', buildObjectString<'update'>('role', 'admin'))
+ * ```
+ *
+ * **Not needed** when:
+ * - Resource only belongs to one relation in the constraint
+ * - Using with 'read' relation (widest type, accepts all)
+ * - Storing in a variable typed as `BrandedPermission` (already opaque)
+ *
+ * ```ts
+ * // OK: 'read' is widest, accepts union return type
+ * buildPermission('read', buildObjectString('role', 'admin'))
+ * ```
+ */
 export function buildObjectString<
 	R extends 'delete' | 'read' | 'update' | 'assignee',
 >(resource: ResourcesForRelation<R>, objectId: string): AuthZObject<R> {

frontend/src/lib/uPlotV2/components/Legend/Legend.tsx

@@ -1,13 +1,11 @@
 import { useCallback, useMemo, useRef, useState } from 'react';
 import { VirtuosoGrid } from 'react-virtuoso';
 import { Input } from 'antd';
-import { Button } from '@signozhq/ui/button';
 import { TooltipSimple } from '@signozhq/ui/tooltip';
 import cx from 'classnames';
-import { useCopyToClipboard } from 'hooks/useCopyToClipboard';
 import { useResizeObserver } from 'hooks/useDimensions';
 import { LegendItem } from 'lib/uPlotV2/config/types';
-import { Check, Copy } from '@signozhq/icons';
+import CopyButton from 'periscope/components/CopyButton/CopyButton';
 
 import { LegendPosition, LegendProps } from '../types';
 
@@ -33,7 +31,6 @@ export default function Legend({
 }: LegendProps): JSX.Element {
 	const legendContainerRef = useRef<HTMLDivElement | null>(null);
 	const [legendSearchQuery, setLegendSearchQuery] = useState('');
-	const { copyToClipboard, id: copiedId } = useCopyToClipboard();
 
 	// Search is intrinsic to the right-positioned legend.
 	const searchEnabled = position === LegendPosition.RIGHT;
@@ -57,17 +54,8 @@ export default function Legend({
 		return items.filter((item) => item.label?.toLowerCase().includes(query));
 	}, [searchEnabled, legendSearchQuery, items]);
 
-	const handleCopyLegendItem = useCallback(
-		(e: React.MouseEvent, seriesIndex: number, label: string): void => {
-			e.stopPropagation();
-			copyToClipboard(label, seriesIndex);
-		},
-		[copyToClipboard],
-	);
-
 	const renderLegendItem = useCallback(
 		(item: LegendItem): JSX.Element => {
-			const isCopied = copiedId === item.seriesIndex;
 			// `color` is uPlot's stroke union (string | fn | gradient); only a string
 			// is a usable CSS colour for the marker.
 			const markerColor = typeof item.color === 'string' ? item.color : undefined;
@@ -91,36 +79,18 @@ export default function Legend({
 						</div>
 					</TooltipSimple>
 					{showCopy && (
-						<TooltipSimple
-							title={isCopied ? 'Copied' : 'Copy'}
-							arrow
-							side="top"
-							disableHoverableContent
-						>
-							<Button
-								type="button"
-								size="icon"
-								variant="ghost"
-								color="secondary"
-								className="legend-copy-button"
-								onClick={(e): void =>
-									handleCopyLegendItem(e, item.seriesIndex, item.label ?? '')
-								}
-								aria-label={`Copy ${item.label}`}
-								// data-testid (not testId): TooltipSimple's trigger injects
-								// data-testid:undefined via Radix Slot, and Button spreads
-								// incoming props after its own testId — so set it as a prop
-								// that wins the Slot merge and survives the spread.
-								data-testid="legend-copy"
-							>
-								{isCopied ? <Check size={12} /> : <Copy size={12} />}
-							</Button>
-						</TooltipSimple>
+						<CopyButton
+							value={item.label ?? ''}
+							size={12}
+							className="legend-copy-button"
+							ariaLabel={`Copy ${item.label}`}
+							testId="legend-copy"
+						/>
 					)}
 				</div>
 			);
 		},
-		[copiedId, focusedSeriesIndex, handleCopyLegendItem, position, showCopy],
+		[focusedSeriesIndex, position, showCopy],
 	);
 
 	const isEmptyState = useMemo(() => {

frontend/src/lib/uPlotV2/components/__tests__/UPlotLegend.test.tsx

@@ -1,11 +1,5 @@
 import React from 'react';
-import {
-	fireEvent,
-	render,
-	RenderResult,
-	screen,
-	within,
-} from '@testing-library/react';
+import { render, RenderResult, screen } from '@testing-library/react';
 import userEvent from '@testing-library/user-event';
 import { TooltipProvider } from '@signozhq/ui/tooltip';
 import { LegendItem } from 'lib/uPlotV2/config/types';
@@ -15,9 +9,6 @@ import { useLegendActions } from '../../hooks/useLegendActions';
 import UPlotLegend from '../Legend/UPlotLegend';
 import { LegendPosition } from '../types';
 
-const mockWriteText = jest.fn().mockResolvedValue(undefined);
-let clipboardSpy: jest.SpyInstance | undefined;
-
 jest.mock('react-virtuoso', () => ({
 	VirtuosoGrid: ({
 		data,
@@ -49,15 +40,6 @@ const mockUseLegendActions = useLegendActions as jest.MockedFunction<
 >;
 
 describe('UPlotLegend', () => {
-	beforeAll(() => {
-		// JSDOM does not define navigator.clipboard; add it so we can spy on writeText
-		Object.defineProperty(navigator, 'clipboard', {
-			value: { writeText: () => Promise.resolve() },
-			writable: true,
-			configurable: true,
-		});
-	});
-
 	const baseLegendItemsMap = {
 		0: {
 			seriesIndex: 0,
@@ -89,11 +71,6 @@ describe('UPlotLegend', () => {
 		onLegendMouseMove = jest.fn();
 		onLegendMouseLeave = jest.fn();
 		onFocusSeries = jest.fn();
-		mockWriteText.mockClear();
-
-		clipboardSpy = jest
-			.spyOn(navigator.clipboard, 'writeText')
-			.mockImplementation(mockWriteText);
 
 		mockUseLegendsSync.mockReturnValue({
 			legendItemsMap: baseLegendItemsMap,
@@ -110,7 +87,6 @@ describe('UPlotLegend', () => {
 	});
 
 	afterEach(() => {
-		clipboardSpy?.mockRestore();
 		jest.clearAllMocks();
 	});
 
@@ -237,47 +213,4 @@ describe('UPlotLegend', () => {
 			expect(onLegendMouseLeave).toHaveBeenCalledTimes(1);
 		});
 	});
-
-	describe('copy action', () => {
-		it('copies the legend label to clipboard when copy button is clicked', () => {
-			renderLegend(LegendPosition.RIGHT);
-
-			const firstLegendItem = document.querySelector(
-				'[data-legend-item-id="0"]',
-			) as HTMLElement;
-			const copyButton = within(firstLegendItem).getByTestId('legend-copy');
-
-			fireEvent.click(copyButton);
-
-			expect(mockWriteText).toHaveBeenCalledTimes(1);
-			expect(mockWriteText).toHaveBeenCalledWith('A');
-		});
-
-		it('copies the correct label when copy is clicked on a different legend item', () => {
-			renderLegend(LegendPosition.RIGHT);
-
-			const thirdLegendItem = document.querySelector(
-				'[data-legend-item-id="2"]',
-			) as HTMLElement;
-			const copyButton = within(thirdLegendItem).getByTestId('legend-copy');
-
-			fireEvent.click(copyButton);
-
-			expect(mockWriteText).toHaveBeenCalledTimes(1);
-			expect(mockWriteText).toHaveBeenCalledWith('C');
-		});
-
-		it('does not call onLegendClick when copy button is clicked', () => {
-			renderLegend(LegendPosition.RIGHT);
-
-			const firstLegendItem = document.querySelector(
-				'[data-legend-item-id="0"]',
-			) as HTMLElement;
-			const copyButton = within(firstLegendItem).getByTestId('legend-copy');
-
-			fireEvent.click(copyButton);
-
-			expect(onLegendClick).not.toHaveBeenCalled();
-		});
-	});
 });

frontend/src/periscope/components/CopyButton/CopyButton.tsx

@@ -1,10 +1,10 @@
-import { CSSProperties, useCallback } from 'react';
+import { CSSProperties, type MouseEvent, useCallback } from 'react';
 import { Check, Copy } from '@signozhq/icons';
 import { Button } from '@signozhq/ui/button';
 import cx from 'classnames';
-import { useCopyToClipboard } from 'hooks/useCopyToClipboard';
 
 import styles from './CopyButton.module.scss';
+import { useCopyButton } from './useCopyButton';
 
 export interface CopyButtonProps {
 	/** Text written to the clipboard on click. */
@@ -30,11 +30,15 @@ function CopyButton({
 	className,
 	testId,
 }: CopyButtonProps): JSX.Element {
-	const { copyToClipboard, isCopied } = useCopyToClipboard();
+	const { copyToClipboard, isCopied } = useCopyButton();
 
-	const handleClick = useCallback((): void => {
-		copyToClipboard(value);
-	}, [copyToClipboard, value]);
+	const handleClick = useCallback(
+		(e: MouseEvent<HTMLButtonElement>): void => {
+			e.stopPropagation();
+			copyToClipboard(value);
+		},
+		[copyToClipboard, value],
+	);
 
 	const stackStyle: CSSProperties = { width: size, height: size };
 

frontend/src/periscope/components/CopyButton/__test__/CopyButton.test.tsx

@@ -0,0 +1,65 @@
+import { act, render, screen } from '@testing-library/react';
+import userEvent from '@testing-library/user-event';
+
+import CopyButton from '../CopyButton';
+
+const mockCopy = jest.fn();
+
+// Exercise the real useCopyButton — stub only react-use's underlying copy so the
+// click doesn't hit copy-to-clipboard's jsdom fallback (window.prompt).
+jest.mock('react-use', () => ({
+	...jest.requireActual('react-use'),
+	useCopyToClipboard: (): [unknown, jest.Mock] => [null, mockCopy],
+}));
+
+describe('CopyButton', () => {
+	let user: ReturnType<typeof userEvent.setup>;
+
+	beforeEach(() => {
+		jest.useFakeTimers();
+		user = userEvent.setup({ advanceTimers: jest.advanceTimersByTime });
+		mockCopy.mockClear();
+	});
+
+	afterEach(() => {
+		jest.runOnlyPendingTimers();
+		jest.useRealTimers();
+	});
+
+	it('copies its value on click', async () => {
+		render(<CopyButton value="hello" testId="copy" />);
+
+		await user.click(screen.getByTestId('copy'));
+
+		expect(mockCopy).toHaveBeenCalledWith('hello');
+	});
+
+	it('does not trigger parent click handlers (stops propagation)', async () => {
+		const onParentClick = jest.fn();
+		render(
+			// oxlint-disable-next-line jsx-a11y/no-static-element-interactions, jsx-a11y/click-events-have-key-events
+			<div onClick={onParentClick}>
+				<CopyButton value="x" testId="copy" />
+			</div>,
+		);
+
+		await user.click(screen.getByTestId('copy'));
+
+		expect(onParentClick).not.toHaveBeenCalled();
+	});
+
+	it('shows the copied state after clicking and reverts after the reset window', async () => {
+		const { container } = render(<CopyButton value="hello" testId="copy" />);
+		const iconStack = container.querySelector('[data-copied]') as HTMLElement;
+
+		expect(iconStack).toHaveAttribute('data-copied', 'false');
+
+		await user.click(screen.getByTestId('copy'));
+		expect(iconStack).toHaveAttribute('data-copied', 'true');
+
+		act(() => {
+			jest.runOnlyPendingTimers();
+		});
+		expect(iconStack).toHaveAttribute('data-copied', 'false');
+	});
+});

frontend/src/periscope/components/CopyButton/constants.ts

@@ -0,0 +1,2 @@
+/** How long (ms) CopyButton stays in the "copied" state before reverting. */
+export const COPIED_RESET_MS = 1000;

frontend/src/periscope/components/CopyButton/useCopyButton.ts

@@ -0,0 +1,44 @@
+import { useCallback, useEffect, useRef, useState } from 'react';
+import { useCopyToClipboard } from 'react-use';
+
+import { COPIED_RESET_MS } from './constants';
+
+export interface UseCopyButtonReturn {
+	copyToClipboard: (text: string) => void;
+	isCopied: boolean;
+}
+
+export function useCopyButton(): UseCopyButtonReturn {
+	const [, copy] = useCopyToClipboard();
+	const [isCopied, setIsCopied] = useState(false);
+	const timeoutRef = useRef<ReturnType<typeof setTimeout> | null>(null);
+
+	useEffect(() => {
+		return (): void => {
+			if (timeoutRef.current) {
+				clearTimeout(timeoutRef.current);
+				timeoutRef.current = null;
+			}
+		};
+	}, []);
+
+	const copyToClipboard = useCallback(
+		(text: string): void => {
+			copy(text);
+			if (timeoutRef.current) {
+				clearTimeout(timeoutRef.current);
+			}
+			setIsCopied(true);
+			timeoutRef.current = setTimeout(() => {
+				setIsCopied(false);
+				timeoutRef.current = null;
+			}, COPIED_RESET_MS);
+		},
+		[copy],
+	);
+
+	return {
+		copyToClipboard,
+		isCopied,
+	};
+}

frontend/src/providers/App/App.tsx

@@ -434,6 +434,7 @@ export function AppProvider({ children }: PropsWithChildren): JSX.Element {
 			isFetchingHosts,
 			isFetchingFeatureFlags,
 			isFetchingOrgPreferences,
+			isFetchingUserPreferences,
 			userFetchError,
 			activeLicenseFetchError,
 			hostsFetchError,
@@ -464,6 +465,7 @@ export function AppProvider({ children }: PropsWithChildren): JSX.Element {
 			isFetchingHosts,
 			isFetchingFeatureFlags,
 			isFetchingOrgPreferences,
+			isFetchingUserPreferences,
 			isFetchingUser,
 			isLoggedIn,
 			hostsData,

frontend/src/providers/App/types.ts

@@ -27,6 +27,7 @@ export interface IAppContext {
 	isFetchingHosts: boolean;
 	isFetchingFeatureFlags: boolean;
 	isFetchingOrgPreferences: boolean;
+	isFetchingUserPreferences: boolean;
 	userFetchError: unknown;
 	activeLicenseFetchError: APIError | null;
 	hostsFetchError: unknown;

frontend/src/tests/test-utils.tsx

@@ -242,6 +242,7 @@ export function getAppContextMock(
 		userPreferences: [],
 		updateUserPreferenceInContext: jest.fn(),
 		isFetchingOrgPreferences: false,
+		isFetchingUserPreferences: false,
 		orgPreferencesFetchError: null,
 		isLoggedIn: true,
 		isPreflightLoading: false,

frontend/src/utils/permission/index.ts

@@ -23,6 +23,11 @@ export type ComponentTypes =
 	| 'add_panel_locked_dashboard'
 	| 'manage_llm_pricing';
 
+/**
+ * @deprecated Before adding a new value here, check if what you want to add permission is supported by authz.
+ * If so, read AuthZ Guidelines on how to add permission check via AuthZ.
+ * If not, you can keep adding to this record.
+ */
 export const componentPermission: Record<ComponentTypes, ROLES[]> = {
 	current_org_settings: ['ADMIN'],
 	invite_members: ['ADMIN'],
@@ -46,11 +51,16 @@ export const componentPermission: Record<ComponentTypes, ROLES[]> = {
 	manage_llm_pricing: ['ADMIN'],
 };
 
+/**
+ * @deprecated You can still add new permissions/routes here but be aware if this page/module supports authz.
+ * If so, also implement the correct authz checks in the page itself, and here you can add ADMIN/EDITOR/VIEWER,
+ * and also update/include the route at {@link routeWithInitialAuthZSupport}
+ */
 export const routePermission: Record<keyof typeof ROUTES, ROLES[]> = {
 	HOME: ['ADMIN', 'EDITOR', 'VIEWER'],
 	ALERTS_NEW: ['ADMIN', 'EDITOR'],
 	ORG_SETTINGS: ['ADMIN'],
-	MY_SETTINGS: ['ADMIN', 'EDITOR', 'VIEWER', 'ANONYMOUS'],
+	MY_SETTINGS: ['ADMIN', 'EDITOR', 'VIEWER'],
 	SERVICE_MAP: ['ADMIN', 'EDITOR', 'VIEWER'],
 	ALL_CHANNELS: ['ADMIN', 'EDITOR', 'VIEWER'],
 	INGESTION_SETTINGS: ['ADMIN', 'EDITOR', 'VIEWER'],
@@ -75,13 +85,15 @@ export const routePermission: Record<keyof typeof ROUTES, ROLES[]> = {
 	NOT_FOUND: ['ADMIN', 'VIEWER', 'EDITOR', 'ANONYMOUS'],
 	PASSWORD_RESET: ['ADMIN', 'EDITOR', 'VIEWER'],
 	SERVICE_METRICS: ['ADMIN', 'EDITOR', 'VIEWER'],
-	SETTINGS: ['ADMIN', 'EDITOR', 'VIEWER', 'ANONYMOUS'],
+	SETTINGS: ['ADMIN', 'EDITOR', 'VIEWER'],
 	SIGN_UP: ['ADMIN', 'EDITOR', 'VIEWER'],
 	TRACES_EXPLORER: ['ADMIN', 'EDITOR', 'VIEWER'],
 	TRACE: ['ADMIN', 'EDITOR', 'VIEWER'],
 	TRACE_DETAIL: ['ADMIN', 'EDITOR', 'VIEWER'],
 	TRACE_DETAIL_OLD: ['ADMIN', 'EDITOR', 'VIEWER'],
-	UN_AUTHORIZED: ['ADMIN', 'EDITOR', 'VIEWER', 'ANONYMOUS'],
+	// Every role must be able to land here - a role missing from this list is
+	// redirected to /un-authorized and then redirected off it again, looping.
+	UN_AUTHORIZED: ['ADMIN', 'EDITOR', 'VIEWER', 'ANONYMOUS', 'AUTHOR'],
 	USAGE_EXPLORER: ['ADMIN', 'EDITOR', 'VIEWER'],
 	VERSION: ['ADMIN', 'EDITOR', 'VIEWER'],
 	LOGS: ['ADMIN', 'EDITOR', 'VIEWER'],
@@ -95,12 +107,12 @@ export const routePermission: Record<keyof typeof ROUTES, ROLES[]> = {
 	GET_STARTED_WITH_CLOUD: ['ADMIN', 'EDITOR'],
 	WORKSPACE_LOCKED: ['ADMIN', 'EDITOR', 'VIEWER'],
 	WORKSPACE_SUSPENDED: ['ADMIN', 'EDITOR', 'VIEWER'],
-	ROLES_SETTINGS: ['ADMIN', 'EDITOR', 'VIEWER', 'ANONYMOUS'],
-	ROLE_CREATE: ['ADMIN', 'EDITOR', 'VIEWER', 'ANONYMOUS'],
-	ROLE_DETAILS: ['ADMIN', 'EDITOR', 'VIEWER', 'ANONYMOUS'],
-	ROLE_EDIT: ['ADMIN', 'EDITOR', 'VIEWER', 'ANONYMOUS'],
+	ROLES_SETTINGS: ['ADMIN', 'EDITOR', 'VIEWER'],
+	ROLE_CREATE: ['ADMIN', 'EDITOR', 'VIEWER'],
+	ROLE_DETAILS: ['ADMIN', 'EDITOR', 'VIEWER'],
+	ROLE_EDIT: ['ADMIN', 'EDITOR', 'VIEWER'],
 	MEMBERS_SETTINGS: ['ADMIN'],
-	SERVICE_ACCOUNTS_SETTINGS: ['ADMIN', 'EDITOR', 'VIEWER', 'ANONYMOUS'],
+	SERVICE_ACCOUNTS_SETTINGS: ['ADMIN', 'EDITOR', 'VIEWER'],
 	BILLING: ['ADMIN'],
 	SUPPORT: ['ADMIN', 'EDITOR', 'VIEWER', 'ANONYMOUS'],
 	SOMETHING_WENT_WRONG: ['ADMIN', 'EDITOR', 'VIEWER'],
@@ -141,3 +153,34 @@ export const routePermission: Record<keyof typeof ROUTES, ROLES[]> = {
 	AI_OBSERVABILITY_OVERVIEW: ['ADMIN', 'EDITOR', 'VIEWER'],
 	AI_OBSERVABILITY_CONFIGURATION: ['ADMIN', 'EDITOR', 'VIEWER'],
 };
+
+/**
+ * Any route that will start be supported under AuthZ should be added here.
+ * This will help correctly identify when fallback to show the page
+ * or just return unauthorized.
+ *
+ * This prevents us from adding `ANONYMOUS` on the `routePermission`
+ */
+export const routeWithInitialAuthZSupport = {
+	MY_SETTINGS: true,
+	SETTINGS: true,
+	TRACES_EXPLORER: true,
+	TRACE: true,
+	TRACE_DETAIL: true,
+	TRACE_DETAIL_OLD: true,
+	LOGS: true,
+	LOGS_EXPLORER: true,
+	LIVE_LOGS: true,
+	ROLES_SETTINGS: true,
+	ROLE_CREATE: true,
+	ROLE_DETAILS: true,
+	ROLE_EDIT: true,
+	SERVICE_ACCOUNTS_SETTINGS: true,
+	SUPPORT: true,
+	OLD_LOGS_EXPLORER: true,
+	METRICS_EXPLORER: true,
+	METRICS_EXPLORER_EXPLORER: true,
+	METRICS_EXPLORER_VOLUME_CONTROL: true,
+	METER_EXPLORER: true,
+	METER: true,
+} as const satisfies Partial<Record<keyof typeof ROUTES, true>>;

frontend/vite.config.ts

@@ -143,6 +143,12 @@ export default defineConfig(({ mode }): UserConfig => {
 		plugins,
 		resolve: {
 			alias: {
+				// @grafana/data imports bare CJS `lodash`, whose UMD footer checks for an
+				// AMD loader before assigning module.exports. Any third-party script that
+				// defines window.define.amd first leaves the bundled namespace empty, so
+				// every lodash method reached through it is undefined at runtime. lodash-es
+				// is the same version, real ESM, and tree-shakes.
+				lodash: 'lodash-es',
 				'@': resolve(__dirname, './src'),
 				utils: resolve(__dirname, './src/utils'),
 				types: resolve(__dirname, './src/types'),

go.mod

@@ -4,7 +4,7 @@ go 1.25.7
 
 require (
 	dario.cat/mergo v1.0.2
-	github.com/AfterShip/clickhouse-sql-parser v0.5.2
+	github.com/AfterShip/clickhouse-sql-parser v0.5.3
 	github.com/ClickHouse/clickhouse-go/v2 v2.44.0
 	github.com/DATA-DOG/go-sqlmock v1.5.2
 	github.com/SigNoz/clickhouse-go-mock v0.14.0

go.sum

@@ -66,8 +66,8 @@ dario.cat/mergo v1.0.2/go.mod h1:E/hbnu0NxMFBjpMIE34DRGLWqDy0g5FuKDhCb31ngxA=
 dmitri.shuralyov.com/gpu/mtl v0.0.0-20190408044501-666a987793e9/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
 filippo.io/edwards25519 v1.2.0 h1:crnVqOiS4jqYleHd9vaKZ+HKtHfllngJIiOpNpoJsjo=
 filippo.io/edwards25519 v1.2.0/go.mod h1:xzAOLCNug/yB62zG1bQ8uziwrIqIuxhctzJT18Q77mc=
-github.com/AfterShip/clickhouse-sql-parser v0.5.2 h1:KCxdmvuVawVF4yl0ZS33q7olgmLZwvZG5BjWHp6o414=
-github.com/AfterShip/clickhouse-sql-parser v0.5.2/go.mod h1:Qi3qvPTfZb/aFwI5V4WFOahgjsLJa4MzVijIAfwOhDw=
+github.com/AfterShip/clickhouse-sql-parser v0.5.3 h1:6iap8XGjuSjD3w7r1UNrg66ljBugcv2P39s4eo/ZLRw=
+github.com/AfterShip/clickhouse-sql-parser v0.5.3/go.mod h1:Qi3qvPTfZb/aFwI5V4WFOahgjsLJa4MzVijIAfwOhDw=
 github.com/Azure/azure-sdk-for-go v68.0.0+incompatible h1:fcYLmCpyNYRnvJbPerq7U0hS+6+I79yEDJBqVNcqUzU=
 github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.0 h1:fou+2+WFTib47nS+nz/ozhEBnvU96bKHy6LjRsY4E28=
 github.com/Azure/azure-sdk-for-go/sdk/azcore v1.21.0/go.mod h1:t76Ruy8AHvUAC8GfMWJMa0ElSbuIcO03NLpynfbgsPA=

pkg/flagger/registry.go

@@ -14,8 +14,6 @@ var (
 	FeatureEnableAIObservability  = featuretypes.MustNewName("enable_ai_observability")
 	FeatureEnableMetricsReduction = featuretypes.MustNewName("enable_metrics_reduction")
 	FeatureUseInfraMonitoringV2   = featuretypes.MustNewName("use_infra_monitoring_v2")
-
-	FeatureUsePrometheusClickhouseV2 = featuretypes.MustNewName("use_prometheus_clickhouse_v2")
 )
 
 func MustNewRegistry() featuretypes.Registry {
@@ -108,14 +106,6 @@ func MustNewRegistry() featuretypes.Registry {
 			DefaultVariant: featuretypes.MustNewName("disabled"),
 			Variants:       featuretypes.NewBooleanVariants(),
 		},
-		&featuretypes.Feature{
-			Name:           FeatureUsePrometheusClickhouseV2,
-			Kind:           featuretypes.KindBoolean,
-			Stage:          featuretypes.StageExperimental,
-			Description:    "Runs PromQL queries on the clickhousev2 provider alongside the served engine result and logs any difference; serving is unaffected.",
-			DefaultVariant: featuretypes.MustNewName("disabled"),
-			Variants:       featuretypes.NewBooleanVariants(),
-		},
 	)
 	if err != nil {
 		panic(err)

pkg/modules/cloudintegration/implcloudintegration/fs/definitions/gcp/computeengine/icon.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="24px" height="24px" viewBox="0 0 24 24"><defs><style>.cls-1{fill:#aecbfa;}.cls-2{fill:#669df6;}.cls-3{fill:#4285f4;}</style></defs><title>Icon_24px_ComputeEngine_Color</title><g data-name="Product Icons"><rect class="cls-1" x="9" y="9" width="6" height="6"/><rect class="cls-2" x="11" y="2" width="2" height="4"/><rect class="cls-2" x="7" y="2" width="2" height="4"/><rect class="cls-2" x="15" y="2" width="2" height="4"/><rect class="cls-3" x="11" y="18" width="2" height="4"/><rect class="cls-3" x="7" y="18" width="2" height="4"/><rect class="cls-3" x="15" y="18" width="2" height="4"/><rect class="cls-3" x="19" y="10" width="2" height="4" transform="translate(8 32) rotate(-90)"/><rect class="cls-3" x="19" y="14" width="2" height="4" transform="translate(4 36) rotate(-90)"/><rect class="cls-3" x="19" y="6" width="2" height="4" transform="translate(12 28) rotate(-90)"/><rect class="cls-2" x="3" y="10" width="2" height="4" transform="translate(-8 16) rotate(-90)"/><rect class="cls-2" x="3" y="14" width="2" height="4" transform="translate(-12 20) rotate(-90)"/><rect class="cls-2" x="3" y="6" width="2" height="4" transform="translate(-4 12) rotate(-90)"/><path class="cls-1" d="M5,5V19H19V5ZM17,17H7V7H17Z"/><polygon class="cls-2" points="9 15 15 15 12 12 9 15"/><polygon class="cls-3" points="12 12 15 15 15 9 12 12"/></g></svg>

pkg/modules/cloudintegration/implcloudintegration/fs/definitions/gcp/computeengine/integration.json

@@ -0,0 +1,124 @@
+{
+  "id": "computeengine",
+  "title": "GCP Compute Engine",
+  "icon": "file://icon.svg",
+  "overview": "file://overview.md",
+  "supportedSignals": {
+    "metrics": true,
+    "logs": true
+  },
+  "dataCollected": {
+    "metrics": [
+      {
+        "name": "compute.googleapis.com/instance/uptime_total",
+        "unit": "Seconds",
+        "type": "Gauge",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/cpu/utilization",
+        "unit": "Percent",
+        "type": "Gauge",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/guest/memory/bytes_used",
+        "unit": "Bytes",
+        "type": "Gauge",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/guest/memory/percent_used",
+        "unit": "Percent",
+        "type": "Gauge",
+        "description": ""
+      },
+      {
+        "name": "agent.googleapis.com/memory/percent_used",
+        "unit": "Percent",
+        "type": "Gauge",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/disk/average_io_latency",
+        "unit": "Microseconds",
+        "type": "Gauge",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/disk/read_bytes_count",
+        "unit": "Bytes",
+        "type": "Sum",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/disk/write_bytes_count",
+        "unit": "Bytes",
+        "type": "Sum",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/disk/read_ops_count",
+        "unit": "Count",
+        "type": "Sum",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/disk/write_ops_count",
+        "unit": "Count",
+        "type": "Sum",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/disk/performance_status",
+        "unit": "None",
+        "type": "Gauge",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/network/received_bytes_count",
+        "unit": "Bytes",
+        "type": "Sum",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/network/sent_bytes_count",
+        "unit": "Bytes",
+        "type": "Sum",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/network/received_packets_count",
+        "unit": "Count",
+        "type": "Sum",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/instance/network/sent_packets_count",
+        "unit": "Count",
+        "type": "Sum",
+        "description": ""
+      },
+      {
+        "name": "compute.googleapis.com/firewall/dropped_packets_count",
+        "unit": "Count",
+        "type": "Sum",
+        "description": ""
+      }
+    ],
+    "logs": []
+  },
+  "telemetryCollectionStrategy": {
+    "gcp": {}
+  },
+  "assets": {
+    "dashboards": [
+      {
+        "id": "overview",
+        "title": "GCP Compute Engine Overview",
+        "description": "Overview of GCP Compute Engine metrics",
+        "definition": "file://assets/dashboards/overview.json"
+      }
+    ]
+  }
+}

pkg/modules/cloudintegration/implcloudintegration/fs/definitions/gcp/computeengine/overview.md

@@ -0,0 +1,3 @@
+### Monitor GCP Compute Engine with SigNoz
+
+Collect key GCP Compute Engine metrics and view them with an out of the box dashboard.

pkg/modules/inframonitoring/implinframonitoring/collect.go

@@ -5,14 +5,14 @@ import (
 	"fmt"
 
 	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
 	"github.com/SigNoz/signoz/pkg/valuer"
 )
 
 func (m *module) Collect(ctx context.Context, _ valuer.UUID) (map[string]any, error) {
 	stats := make(map[string]any)
 
-	metadataTable := fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName)
+	metadataTable := fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.AttributesMetadataTableName)
 	var (
 		systemMetricCount uint64
 		k8sMetricCount    uint64

pkg/modules/inframonitoring/implinframonitoring/containers.go

@@ -7,7 +7,7 @@ import (
 	"strings"
 
 	"github.com/SigNoz/signoz/pkg/querybuilder"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
 	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/valuer"
@@ -281,7 +281,7 @@ func (m *module) getPerGroupContainerStatusCounts(
 	mergedFilterExpr := mergeFilterExpressions(userFilterExpr, buildPageGroupsFilterExpr(pageGroups))
 
 	samplesStartMs, flooredEndMs, tsAdjustedStart, _, localTimeSeriesTable, distributedSamplesTable, _ := alignedMetricWindow(start, end)
-	valueCol := telemetrymetrics.ValueColumnForSamplesTable(distributedSamplesTable)
+	valueCol := metricstelemetryschema.ValueColumnForSamplesTable(distributedSamplesTable)
 
 	// Built once; identical across the two fps CTEs (buildFilterClause hits the
 	// metadata store + parses the expression). AddWhereClause only reads it.
@@ -310,7 +310,7 @@ func (m *module) getPerGroupContainerStatusCounts(
 		)
 	}
 	stateFps.Select(stateFpsCols...)
-	stateFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	stateFps.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTimeSeriesTable))
 	stateFps.Where(
 		stateFps.E("metric_name", containerStatusStateMetricName),
 		stateFps.GE("unix_milli", tsAdjustedStart),
@@ -342,7 +342,7 @@ func (m *module) getPerGroupContainerStatusCounts(
 	containerState.Select(containerStateCols...)
 	containerState.From(fmt.Sprintf(
 		"%s.%s AS samples INNER JOIN state_fps AS fps ON samples.fingerprint = fps.fingerprint",
-		telemetrymetrics.DBName, distributedSamplesTable,
+		metricstelemetryschema.DBName, distributedSamplesTable,
 	))
 	containerState.Where(
 		containerState.E("samples.metric_name", containerStatusStateMetricName),
@@ -361,7 +361,7 @@ func (m *module) getPerGroupContainerStatusCounts(
 		fmt.Sprintf("JSONExtractString(labels, %s) AS container_name", reasonFps.Var(containerNameAttrKey)),
 		fmt.Sprintf("JSONExtractString(labels, %s) AS reason", reasonFps.Var(containerStatusReasonAttrKey)),
 	)
-	reasonFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	reasonFps.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTimeSeriesTable))
 	reasonFps.Where(
 		reasonFps.E("metric_name", containerStatusReasonMetricName),
 		reasonFps.GE("unix_milli", tsAdjustedStart),
@@ -391,7 +391,7 @@ func (m *module) getPerGroupContainerStatusCounts(
 	)
 	reasonInner.From(fmt.Sprintf(
 		"%s.%s AS samples INNER JOIN reason_fps AS fps ON samples.fingerprint = fps.fingerprint",
-		telemetrymetrics.DBName, distributedSamplesTable,
+		metricstelemetryschema.DBName, distributedSamplesTable,
 	))
 	reasonInner.Where(
 		reasonInner.E("samples.metric_name", containerStatusReasonMetricName),
@@ -546,7 +546,7 @@ func (m *module) getPerGroupContainerRestartCounts(
 	mergedFilterExpr := mergeFilterExpressions(userFilterExpr, buildPageGroupsFilterExpr(pageGroups))
 
 	samplesStartMs, flooredEndMs, tsAdjustedStart, _, localTimeSeriesTable, distributedSamplesTable, _ := alignedMetricWindow(start, end)
-	valueCol := telemetrymetrics.ValueColumnForSamplesTable(distributedSamplesTable)
+	valueCol := metricstelemetryschema.ValueColumnForSamplesTable(distributedSamplesTable)
 
 	var (
 		filterClause *sqlbuilder.WhereClause
@@ -572,7 +572,7 @@ func (m *module) getPerGroupContainerRestartCounts(
 		)
 	}
 	restartFps.Select(restartFpsCols...)
-	restartFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	restartFps.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTimeSeriesTable))
 	restartFps.Where(
 		restartFps.E("metric_name", containerRestartsMetricName),
 		restartFps.GE("unix_milli", tsAdjustedStart),
@@ -602,7 +602,7 @@ func (m *module) getPerGroupContainerRestartCounts(
 	containerRestarts.Select(containerRestartsCols...)
 	containerRestarts.From(fmt.Sprintf(
 		"%s.%s AS samples INNER JOIN restart_fps AS fps ON samples.fingerprint = fps.fingerprint",
-		telemetrymetrics.DBName, distributedSamplesTable,
+		metricstelemetryschema.DBName, distributedSamplesTable,
 	))
 	containerRestarts.Where(
 		containerRestarts.E("samples.metric_name", containerRestartsMetricName),
@@ -690,7 +690,7 @@ func (m *module) getPerGroupContainerReadyCounts(
 	mergedFilterExpr := mergeFilterExpressions(userFilterExpr, buildPageGroupsFilterExpr(pageGroups))
 
 	samplesStartMs, flooredEndMs, tsAdjustedStart, _, localTimeSeriesTable, distributedSamplesTable, _ := alignedMetricWindow(start, end)
-	valueCol := telemetrymetrics.ValueColumnForSamplesTable(distributedSamplesTable)
+	valueCol := metricstelemetryschema.ValueColumnForSamplesTable(distributedSamplesTable)
 
 	var (
 		filterClause *sqlbuilder.WhereClause
@@ -716,7 +716,7 @@ func (m *module) getPerGroupContainerReadyCounts(
 		)
 	}
 	readyFps.Select(readyFpsCols...)
-	readyFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	readyFps.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTimeSeriesTable))
 	readyFps.Where(
 		readyFps.E("metric_name", containerReadyMetricName),
 		readyFps.GE("unix_milli", tsAdjustedStart),
@@ -746,7 +746,7 @@ func (m *module) getPerGroupContainerReadyCounts(
 	containerReady.Select(containerReadyCols...)
 	containerReady.From(fmt.Sprintf(
 		"%s.%s AS samples INNER JOIN ready_fps AS fps ON samples.fingerprint = fps.fingerprint",
-		telemetrymetrics.DBName, distributedSamplesTable,
+		metricstelemetryschema.DBName, distributedSamplesTable,
 	))
 	containerReady.Where(
 		containerReady.E("samples.metric_name", containerReadyMetricName),

pkg/modules/inframonitoring/implinframonitoring/helpers.go

@@ -9,7 +9,7 @@ import (
 	"github.com/SigNoz/signoz/pkg/errors"
 	"github.com/SigNoz/signoz/pkg/flagger"
 	"github.com/SigNoz/signoz/pkg/querybuilder"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
 	"github.com/SigNoz/signoz/pkg/types/featuretypes"
 	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
 	"github.com/SigNoz/signoz/pkg/types/metrictypes"
@@ -344,11 +344,11 @@ func alignedMetricWindow(startMs, endMs int64) (
 		flooredEndMs = flooredEndMs - (flooredEndMs % (adjustStep * 1000))
 	}
 
-	tsAdjustedStartMs, _, distributedTSTable, localTSTable := telemetrymetrics.WhichTSTableToUse(
+	tsAdjustedStartMs, _, distributedTSTable, localTSTable := metricstelemetryschema.WhichTSTableToUse(
 		samplesAdjustedStartMs, flooredEndMs, false, nil,
 	)
 
-	distributedSamplesTable, localSamplesTable := telemetrymetrics.WhichSamplesTableToUse(
+	distributedSamplesTable, localSamplesTable := metricstelemetryschema.WhichSamplesTableToUse(
 		samplesAdjustedStartMs, flooredEndMs,
 		metrictypes.UnspecifiedType, metrictypes.TimeAggregationUnspecified, false, nil,
 	)
@@ -362,7 +362,7 @@ func alignedMetricWindow(startMs, endMs int64) (
 func (m *module) buildSamplesTblFingerprintSubQuery(metricNames []string, samplesTable string, flooredStart, flooredEnd uint64) *sqlbuilder.SelectBuilder {
 	fpSB := sqlbuilder.NewSelectBuilder()
 	fpSB.Select("DISTINCT fingerprint")
-	fpSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, samplesTable))
+	fpSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, samplesTable))
 	fpSB.Where(
 		fpSB.In("metric_name", sqlbuilder.List(metricNames)),
 		fpSB.GE("unix_milli", flooredStart),
@@ -376,7 +376,7 @@ func (m *module) buildSamplesTblFingerprintSubQuery(metricNames []string, sample
 func (m *module) buildReducedSamplesTblFingerprintSubQuery(metricNames []string, flooredStart, flooredEnd uint64) *sqlbuilder.SelectBuilder {
 	lastSB := sqlbuilder.NewSelectBuilder()
 	lastSB.Select("reduced_fingerprint")
-	lastSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.SamplesV4ReducedLastTableName))
+	lastSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.SamplesV4ReducedLastTableName))
 	lastSB.Where(
 		lastSB.In("metric_name", sqlbuilder.List(metricNames)),
 		lastSB.GE("unix_milli", flooredStart),
@@ -385,7 +385,7 @@ func (m *module) buildReducedSamplesTblFingerprintSubQuery(metricNames []string,
 
 	sumSB := sqlbuilder.NewSelectBuilder()
 	sumSB.Select("reduced_fingerprint")
-	sumSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.SamplesV4ReducedSumTableName))
+	sumSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.SamplesV4ReducedSumTableName))
 	sumSB.Where(
 		sumSB.In("metric_name", sqlbuilder.List(metricNames)),
 		sumSB.GE("unix_milli", flooredStart),
@@ -478,7 +478,7 @@ func (m *module) getEarliestMetricTime(ctx context.Context, metricNames []string
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("min(first_reported_unix_milli) AS min_first_reported")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.AttributesMetadataTableName))
 	sb.Where(sb.In("metric_name", sqlbuilder.List(metricNames)))
 
 	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
@@ -504,7 +504,7 @@ func (m *module) getMetricsExistence(ctx context.Context, metricNames []string)
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("metric_name", "count(*) AS cnt")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.AttributesMetadataTableName))
 	sb.Where(sb.In("metric_name", sqlbuilder.List(metricNames)))
 	sb.GroupBy("metric_name")
 
@@ -549,7 +549,7 @@ func (m *module) getAttributesExistence(ctx context.Context, metricNames, attrNa
 	}
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("attr_name", "count(*) AS cnt")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.AttributesMetadataTableName))
 	sb.Where(
 		sb.In("metric_name", sqlbuilder.List(metricNames)),
 		sb.In("attr_name", sqlbuilder.List(attrNames)),
@@ -656,7 +656,7 @@ func (m *module) getMetadata(
 
 		rawSrc := sqlbuilder.NewSelectBuilder()
 		rawSrc.Select("labels", "unix_milli")
-		rawSrc.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTableName))
+		rawSrc.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTableName))
 		rawSrc.Where(
 			rawSrc.In("metric_name", sqlbuilder.List(metricNames)),
 			rawSrc.GE("unix_milli", tsAdjustedStartMs),
@@ -669,7 +669,7 @@ func (m *module) getMetadata(
 
 		reducedSrc := sqlbuilder.NewSelectBuilder()
 		reducedSrc.Select("labels", "unix_milli")
-		reducedSrc.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4ReducedTableName))
+		reducedSrc.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4ReducedTableName))
 		reducedSrc.Where(
 			reducedSrc.In("metric_name", sqlbuilder.List(metricNames)),
 			reducedSrc.GE("unix_milli", tsAdjustedStartMs),
@@ -683,7 +683,7 @@ func (m *module) getMetadata(
 		// Inner query reads over the union of raw + reduced series.
 		innerSB.From(innerSB.BuilderAs(sqlbuilder.UnionAll(rawSrc, reducedSrc), "series"))
 	} else {
-		innerSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTableName))
+		innerSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTableName))
 		innerSB.Where(
 			innerSB.In("metric_name", sqlbuilder.List(metricNames)),
 			innerSB.GE("unix_milli", tsAdjustedStartMs),
@@ -870,7 +870,7 @@ func (m *module) getPerGroupDistinctCounts(
 
 		rawSrc := sqlbuilder.NewSelectBuilder()
 		rawSrc.Select("labels")
-		rawSrc.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTimeSeriesTbl))
+		rawSrc.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTimeSeriesTbl))
 		rawSrc.Where(
 			rawSrc.In("metric_name", sqlbuilder.List(metricNames)),
 			rawSrc.GE("unix_milli", tsAdjustedStartMs),
@@ -883,7 +883,7 @@ func (m *module) getPerGroupDistinctCounts(
 
 		reducedSrc := sqlbuilder.NewSelectBuilder()
 		reducedSrc.Select("labels")
-		reducedSrc.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4ReducedTableName))
+		reducedSrc.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4ReducedTableName))
 		reducedSrc.Where(
 			reducedSrc.In("metric_name", sqlbuilder.List(metricNames)),
 			reducedSrc.GE("unix_milli", tsAdjustedStartMs),
@@ -896,7 +896,7 @@ func (m *module) getPerGroupDistinctCounts(
 
 		sb.From(sb.BuilderAs(sqlbuilder.UnionAll(rawSrc, reducedSrc), "series"))
 	} else {
-		sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTimeSeriesTbl))
+		sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTimeSeriesTbl))
 		sb.Where(
 			sb.In("metric_name", sqlbuilder.List(metricNames)),
 			sb.GE("unix_milli", tsAdjustedStartMs),

pkg/modules/inframonitoring/implinframonitoring/hosts.go

@@ -7,7 +7,7 @@ import (
 	"strings"
 
 	"github.com/SigNoz/signoz/pkg/flagger"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
 	"github.com/SigNoz/signoz/pkg/types/featuretypes"
 	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
@@ -72,7 +72,7 @@ func (m *module) getPerGroupHostStatusCounts(
 
 		rawSrc := sqlbuilder.NewSelectBuilder()
 		rawSrc.Select("labels")
-		rawSrc.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTimeSeriesTableName))
+		rawSrc.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTimeSeriesTableName))
 		rawSrc.Where(
 			rawSrc.In("metric_name", sqlbuilder.List(metricNames)),
 			rawSrc.GE("unix_milli", tsAdjustedStartMs),
@@ -85,7 +85,7 @@ func (m *module) getPerGroupHostStatusCounts(
 
 		reducedSrc := sqlbuilder.NewSelectBuilder()
 		reducedSrc.Select("labels")
-		reducedSrc.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4ReducedTableName))
+		reducedSrc.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4ReducedTableName))
 		reducedSrc.Where(
 			reducedSrc.In("metric_name", sqlbuilder.List(metricNames)),
 			reducedSrc.GE("unix_milli", tsAdjustedStartMs),
@@ -101,7 +101,7 @@ func (m *module) getPerGroupHostStatusCounts(
 
 		fpSB := m.buildSamplesTblFingerprintSubQuery(metricNames, localSamplesTable, samplesStartMs, flooredEndMs)
 
-		sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTimeSeriesTableName))
+		sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTimeSeriesTableName))
 		sb.Where(
 			sb.In("metric_name", sqlbuilder.List(metricNames)),
 			sb.GE("unix_milli", tsAdjustedStartMs),
@@ -357,7 +357,7 @@ func (m *module) getActiveHostsQuery(metricNames []string, hostNameAttr string,
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Distinct()
 	sb.Select("attr_string_value")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.AttributesMetadataTableName))
 	sb.Where(
 		sb.In("metric_name", sqlbuilder.List(metricNames)),
 		sb.E("attr_name", hostNameAttr),

pkg/modules/inframonitoring/implinframonitoring/module.go

@@ -9,7 +9,7 @@ import (
 	"github.com/SigNoz/signoz/pkg/flagger"
 	"github.com/SigNoz/signoz/pkg/modules/inframonitoring"
 	"github.com/SigNoz/signoz/pkg/querier"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
 	"github.com/SigNoz/signoz/pkg/telemetrystore"
 	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
 	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
@@ -40,8 +40,8 @@ func NewModule(
 	providerSettings factory.ProviderSettings,
 	cfg inframonitoring.Config,
 ) inframonitoring.Module {
-	fieldMapper := telemetrymetrics.NewFieldMapper()
-	condBuilder := telemetrymetrics.NewConditionBuilder(fieldMapper)
+	fieldMapper := metricstelemetryschema.NewFieldMapper()
+	condBuilder := metricstelemetryschema.NewConditionBuilder(fieldMapper)
 	return &module{
 		telemetryStore:         telemetryStore,
 		telemetryMetadataStore: telemetryMetadataStore,

pkg/modules/inframonitoring/implinframonitoring/nodes.go

@@ -7,7 +7,7 @@ import (
 	"strings"
 
 	"github.com/SigNoz/signoz/pkg/querybuilder"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
 	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/valuer"
@@ -186,7 +186,7 @@ func (m *module) getPerGroupNodeConditionCounts(
 
 	// Step-floor bounds + resolve tables in one shot to match QB v5 querier.
 	samplesStartMs, flooredEndMs, tsAdjustedStartMs, _, localTimeSeriesTable, distributedSamplesTable, _ := alignedMetricWindow(start, end)
-	valueCol := telemetrymetrics.ValueColumnForSamplesTable(distributedSamplesTable)
+	valueCol := metricstelemetryschema.ValueColumnForSamplesTable(distributedSamplesTable)
 
 	// ----- timeSeriesFPs -----
 	timeSeriesFPs := sqlbuilder.NewSelectBuilder()
@@ -200,7 +200,7 @@ func (m *module) getPerGroupNodeConditionCounts(
 		)
 	}
 	timeSeriesFPs.Select(timeSeriesFPsSelectCols...)
-	timeSeriesFPs.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	timeSeriesFPs.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTimeSeriesTable))
 	timeSeriesFPs.Where(
 		timeSeriesFPs.E("metric_name", nodeConditionMetricName),
 		timeSeriesFPs.GE("unix_milli", tsAdjustedStartMs),
@@ -237,7 +237,7 @@ func (m *module) getPerGroupNodeConditionCounts(
 	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, distributedSamplesTable,
+		metricstelemetryschema.DBName, distributedSamplesTable,
 	))
 	latestConditionPerNode.Where(
 		latestConditionPerNode.E("samples.metric_name", nodeConditionMetricName),

pkg/modules/inframonitoring/implinframonitoring/pods.go

@@ -8,7 +8,7 @@ import (
 	"time"
 
 	"github.com/SigNoz/signoz/pkg/querybuilder"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
 	"github.com/SigNoz/signoz/pkg/types/inframonitoringtypes"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/valuer"
@@ -284,7 +284,7 @@ func (m *module) getPerGroupPodStatusCounts(
 	mergedFilterExpr := mergeFilterExpressions(userFilterExpr, buildPageGroupsFilterExpr(pageGroups))
 
 	samplesStartMs, flooredEndMs, tsAdjustedStart, _, localTimeSeriesTable, distributedSamplesTable, _ := alignedMetricWindow(start, end)
-	valueCol := telemetrymetrics.ValueColumnForSamplesTable(distributedSamplesTable)
+	valueCol := metricstelemetryschema.ValueColumnForSamplesTable(distributedSamplesTable)
 
 	// Build the merged filter clause once; it's identical across the three fps
 	// CTEs, and buildFilterClause hits the metadata store + parses the
@@ -313,7 +313,7 @@ func (m *module) getPerGroupPodStatusCounts(
 		)
 	}
 	phaseFps.Select(phaseFpsCols...)
-	phaseFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	phaseFps.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTimeSeriesTable))
 	phaseFps.Where(
 		phaseFps.E("metric_name", podPhaseMetricName),
 		phaseFps.GE("unix_milli", tsAdjustedStart),
@@ -340,7 +340,7 @@ func (m *module) getPerGroupPodStatusCounts(
 	phasePerPod.Select(phasePerPodCols...)
 	phasePerPod.From(fmt.Sprintf(
 		"%s.%s AS samples INNER JOIN phase_fps AS fps ON samples.fingerprint = fps.fingerprint",
-		telemetrymetrics.DBName, distributedSamplesTable,
+		metricstelemetryschema.DBName, distributedSamplesTable,
 	))
 	phasePerPod.Where(
 		phasePerPod.E("samples.metric_name", podPhaseMetricName),
@@ -357,7 +357,7 @@ func (m *module) getPerGroupPodStatusCounts(
 		"fingerprint",
 		fmt.Sprintf("JSONExtractString(labels, %s) AS pod_uid", podReasonFps.Var(podUIDAttrKey)),
 	)
-	podReasonFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	podReasonFps.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTimeSeriesTable))
 	podReasonFps.Where(
 		podReasonFps.E("metric_name", podStatusReasonMetricName),
 		podReasonFps.GE("unix_milli", tsAdjustedStart),
@@ -377,7 +377,7 @@ func (m *module) getPerGroupPodStatusCounts(
 	)
 	podReasonPerPod.From(fmt.Sprintf(
 		"%s.%s AS samples INNER JOIN pod_reason_fps AS fps ON samples.fingerprint = fps.fingerprint",
-		telemetrymetrics.DBName, distributedSamplesTable,
+		metricstelemetryschema.DBName, distributedSamplesTable,
 	))
 	podReasonPerPod.Where(
 		podReasonPerPod.E("samples.metric_name", podStatusReasonMetricName),
@@ -396,7 +396,7 @@ func (m *module) getPerGroupPodStatusCounts(
 		fmt.Sprintf("JSONExtractString(labels, %s) AS container_name", containerReasonFps.Var(containerNameAttrKey)),
 		fmt.Sprintf("JSONExtractString(labels, %s) AS reason", containerReasonFps.Var(containerStatusReasonAttrKey)),
 	)
-	containerReasonFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	containerReasonFps.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTimeSeriesTable))
 	containerReasonFps.Where(
 		containerReasonFps.E("metric_name", containerStatusReasonMetricName),
 		containerReasonFps.GE("unix_milli", tsAdjustedStart),
@@ -432,7 +432,7 @@ func (m *module) getPerGroupPodStatusCounts(
 	)
 	containerInner.From(fmt.Sprintf(
 		"%s.%s AS samples INNER JOIN container_reason_fps AS fps ON samples.fingerprint = fps.fingerprint",
-		telemetrymetrics.DBName, distributedSamplesTable,
+		metricstelemetryschema.DBName, distributedSamplesTable,
 	))
 	containerInner.Where(
 		containerInner.E("samples.metric_name", containerStatusReasonMetricName),
@@ -611,7 +611,7 @@ func (m *module) getPerGroupPodRestartCounts(
 	mergedFilterExpr := mergeFilterExpressions(userFilterExpr, buildPageGroupsFilterExpr(pageGroups))
 
 	samplesStartMs, flooredEndMs, tsAdjustedStart, _, localTimeSeriesTable, distributedSamplesTable, _ := alignedMetricWindow(start, end)
-	valueCol := telemetrymetrics.ValueColumnForSamplesTable(distributedSamplesTable)
+	valueCol := metricstelemetryschema.ValueColumnForSamplesTable(distributedSamplesTable)
 
 	var (
 		filterClause *sqlbuilder.WhereClause
@@ -637,7 +637,7 @@ func (m *module) getPerGroupPodRestartCounts(
 		)
 	}
 	restartFps.Select(restartFpsCols...)
-	restartFps.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTimeSeriesTable))
+	restartFps.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTimeSeriesTable))
 	restartFps.Where(
 		restartFps.E("metric_name", containerRestartsMetricName),
 		restartFps.GE("unix_milli", tsAdjustedStart),
@@ -667,7 +667,7 @@ func (m *module) getPerGroupPodRestartCounts(
 	containerRestarts.Select(containerRestartsCols...)
 	containerRestarts.From(fmt.Sprintf(
 		"%s.%s AS samples INNER JOIN restart_fps AS fps ON samples.fingerprint = fps.fingerprint",
-		telemetrymetrics.DBName, distributedSamplesTable,
+		metricstelemetryschema.DBName, distributedSamplesTable,
 	))
 	containerRestarts.Where(
 		containerRestarts.E("samples.metric_name", containerRestartsMetricName),

pkg/modules/llmpricingrule/impllmpricingrule/module.go

@@ -213,18 +213,18 @@ func (module *module) discoverModels(ctx context.Context, orgID valuer.UUID) ([]
 					Spec: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
 						Name:   "A",
 						Signal: telemetrytypes.SignalTraces,
-						Filter: &qbtypes.Filter{Expression: fmt.Sprintf("%s EXISTS", llmpricingruletypes.GenAIRequestModel)},
+						Filter: &qbtypes.Filter{Expression: fmt.Sprintf("%s EXISTS", telemetrytypes.GenAIRequestModel)},
 						Aggregations: []qbtypes.TraceAggregation{
 							{Expression: "count()", Alias: "spanCount"},
 						},
 						GroupBy: []qbtypes.GroupByKey{
 							{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-								Name:          llmpricingruletypes.GenAIRequestModel,
+								Name:          telemetrytypes.GenAIRequestModel,
 								FieldContext:  telemetrytypes.FieldContextSpan,
 								FieldDataType: telemetrytypes.FieldDataTypeString,
 							}},
 							{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-								Name:          llmpricingruletypes.GenAIProviderName,
+								Name:          telemetrytypes.GenAIProviderName,
 								FieldContext:  telemetrytypes.FieldContextSpan,
 								FieldDataType: telemetrytypes.FieldDataTypeString,
 							}},
@@ -254,9 +254,9 @@ func (module *module) discoverModels(ctx context.Context, orgID valuer.UUID) ([]
 		switch c.Type {
 		case qbtypes.ColumnTypeGroup:
 			switch c.Name {
-			case llmpricingruletypes.GenAIRequestModel:
+			case telemetrytypes.GenAIRequestModel:
 				modelIdx = i
-			case llmpricingruletypes.GenAIProviderName:
+			case telemetrytypes.GenAIProviderName:
 				providerIdx = i
 			}
 		case qbtypes.ColumnTypeAggregation:

pkg/modules/metricsexplorer/implmetricsexplorer/module.go

@@ -19,8 +19,8 @@ import (
 	"github.com/SigNoz/signoz/pkg/modules/dashboard"
 	"github.com/SigNoz/signoz/pkg/modules/metricsexplorer"
 	"github.com/SigNoz/signoz/pkg/querybuilder"
-	"github.com/SigNoz/signoz/pkg/telemetrymeter"
-	"github.com/SigNoz/signoz/pkg/telemetrymetrics"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metertelemetryschema"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/metricstelemetryschema"
 	"github.com/SigNoz/signoz/pkg/telemetrystore"
 	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
 	"github.com/SigNoz/signoz/pkg/types/dashboardtypes"
@@ -49,8 +49,8 @@ type module struct {
 
 // NewModule constructs the metrics module with the provided dependencies.
 func NewModule(ts telemetrystore.TelemetryStore, telemetryMetadataStore telemetrytypes.MetadataStore, cache cache.Cache, ruleStore ruletypes.RuleStore, dashboardModule dashboard.Module, fl flagger.Flagger, providerSettings factory.ProviderSettings, cfg metricsexplorer.Config) metricsexplorer.Module {
-	fieldMapper := telemetrymetrics.NewFieldMapper()
-	condBuilder := telemetrymetrics.NewConditionBuilder(fieldMapper)
+	fieldMapper := metricstelemetryschema.NewFieldMapper()
+	condBuilder := metricstelemetryschema.NewConditionBuilder(fieldMapper)
 	return &module{
 		telemetryStore:         ts,
 		fieldMapper:            fieldMapper,
@@ -89,7 +89,7 @@ func (m *module) listMeterMetrics(ctx context.Context, params *metricsexplorerty
 		"argMax(temporality, unix_milli) AS temporality",
 		"argMax(is_monotonic, unix_milli) AS is_monotonic",
 	)
-	sb.From(fmt.Sprintf("%s.%s", telemetrymeter.DBName, telemetrymeter.SamplesTableName))
+	sb.From(fmt.Sprintf("%s.%s", metertelemetryschema.DBName, metertelemetryschema.SamplesTableName))
 
 	if params.Start != nil && params.End != nil {
 		sb.Where(sb.Between("unix_milli", *params.Start, *params.End))
@@ -160,11 +160,11 @@ func (m *module) listMetrics(ctx context.Context, orgID valuer.UUID, params *met
 	hasRange := params.Start != nil && params.End != nil
 	if hasRange {
 		var distributedTsTable string
-		rangeStart, rangeEnd, distributedTsTable, _ = telemetrymetrics.WhichTSTableToUse(uint64(*params.Start), uint64(*params.End), false, nil)
-		rawSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTsTable))
+		rangeStart, rangeEnd, distributedTsTable, _ = metricstelemetryschema.WhichTSTableToUse(uint64(*params.Start), uint64(*params.End), false, nil)
+		rawSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTsTable))
 		rawSB.Where(rawSB.Between("unix_milli", rangeStart, rangeEnd))
 	} else {
-		rawSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV41weekTableName))
+		rawSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV41weekTableName))
 	}
 
 	applyListFilters(rawSB)
@@ -174,7 +174,7 @@ func (m *module) listMetrics(ctx context.Context, orgID valuer.UUID, params *met
 	if reductionEnabled {
 		reducedSB := sqlbuilder.NewSelectBuilder()
 		reducedSB.Select("DISTINCT metric_name")
-		reducedSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4ReducedTableName))
+		reducedSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4ReducedTableName))
 		if hasRange {
 			reducedSB.Where(reducedSB.Between("unix_milli", rangeStart, rangeEnd))
 		}
@@ -512,7 +512,7 @@ func (m *module) CheckMetricExists(ctx context.Context, orgID valuer.UUID, metri
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("count(*) > 0 as metricExists")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.AttributesMetadataTableName))
 	sb.Where(sb.E("metric_name", metricName))
 
 	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
@@ -534,7 +534,7 @@ func (m *module) HasNonSigNozMetrics(ctx context.Context) (bool, error) {
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("count(*) > 0")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV41weekTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV41weekTableName))
 	sb.Where("metric_name NOT LIKE 'signoz_%'")
 
 	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
@@ -570,10 +570,10 @@ func (m *module) InspectMetrics(
 		return nil, err
 	}
 
-	tsStart, _, tsTable, _ := telemetrymetrics.WhichTSTableToUse(start, end, false, nil)
+	tsStart, _, tsTable, _ := metricstelemetryschema.WhichTSTableToUse(start, end, false, nil)
 	tsSb := sqlbuilder.NewSelectBuilder()
 	tsSb.Select("fingerprint", "labels")
-	tsSb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, tsTable))
+	tsSb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, tsTable))
 	tsSb.Where(
 		tsSb.E("metric_name", req.MetricName),
 		tsSb.GE("unix_milli", tsStart),
@@ -625,7 +625,7 @@ func (m *module) InspectMetrics(
 
 	samplesSb := sqlbuilder.NewSelectBuilder()
 	samplesSb.Select("fingerprint", "unix_milli", "value")
-	samplesSb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.SamplesV4TableName))
+	samplesSb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.SamplesV4TableName))
 	samplesSb.Where(
 		samplesSb.In("fingerprint", fingerprints...),
 		samplesSb.E("metric_name", req.MetricName),
@@ -717,7 +717,7 @@ func (m *module) fetchUpdatedMetadata(ctx context.Context, orgID valuer.UUID, me
 		"argMax(temporality, created_at) AS temporality",
 		"argMax(is_monotonic, created_at) AS is_monotonic",
 	)
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.UpdatedMetadataTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.UpdatedMetadataTableName))
 	sb.Where(sb.In("metric_name", args...))
 	sb.GroupBy("metric_name")
 
@@ -777,7 +777,7 @@ func (m *module) fetchTimeseriesMetadata(ctx context.Context, orgID valuer.UUID,
 		"anyLast(temporality) AS temporality",
 		"argMax(is_monotonic, unix_milli) AS is_monotonic",
 	)
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4TableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4TableName))
 	sb.Where(sb.In("metric_name", args...))
 	sb.GroupBy("metric_name")
 
@@ -891,7 +891,7 @@ func (m *module) checkForLabelInMetric(ctx context.Context, metricName string, l
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("count(*) > 0 AS has_label")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.AttributesMetadataTableName))
 	sb.Where(sb.E("metric_name", metricName))
 	sb.Where(sb.E("attr_name", label))
 	sb.Limit(1)
@@ -914,7 +914,7 @@ func (m *module) insertMetricsMetadata(ctx context.Context, orgID valuer.UUID, r
 	createdAt := time.Now().UnixMilli()
 
 	ib := sqlbuilder.NewInsertBuilder()
-	ib.InsertInto(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.UpdatedMetadataTableName))
+	ib.InsertInto(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.UpdatedMetadataTableName))
 	ib.Cols("metric_name", "temporality", "is_monotonic", "type", "description", "unit", "created_at")
 	ib.Values(
 		req.MetricName,
@@ -1016,9 +1016,9 @@ func (m *module) fetchMetricsStatsWithSamples(
 		}
 	}
 
-	start, end, distributedTsTable, localTsTable := telemetrymetrics.WhichTSTableToUse(uint64(req.Start), uint64(req.End), false, nil)
-	distributedSamplesTable, _ := telemetrymetrics.WhichSamplesTableToUse(uint64(req.Start), uint64(req.End), metrictypes.UnspecifiedType, metrictypes.TimeAggregationUnspecified, false, nil)
-	countExp := telemetrymetrics.CountExpressionForSamplesTable(distributedSamplesTable)
+	start, end, distributedTsTable, localTsTable := metricstelemetryschema.WhichTSTableToUse(uint64(req.Start), uint64(req.End), false, nil)
+	distributedSamplesTable, _ := metricstelemetryschema.WhichSamplesTableToUse(uint64(req.Start), uint64(req.End), metrictypes.UnspecifiedType, metrictypes.TimeAggregationUnspecified, false, nil)
+	countExp := metricstelemetryschema.CountExpressionForSamplesTable(distributedSamplesTable)
 
 	// Timeseries counts per metric
 	tsSB := sqlbuilder.NewSelectBuilder()
@@ -1026,7 +1026,7 @@ func (m *module) fetchMetricsStatsWithSamples(
 		"metric_name",
 		"uniq(fingerprint) AS timeseries",
 	)
-	tsSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTsTable))
+	tsSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTsTable))
 	tsSB.Where(tsSB.Between("unix_milli", start, end))
 	tsSB.Where("NOT startsWith(metric_name, 'signoz')")
 	if filterWhereClause != nil {
@@ -1040,7 +1040,7 @@ func (m *module) fetchMetricsStatsWithSamples(
 		"metric_name",
 		fmt.Sprintf("%s AS samples", countExp),
 	)
-	samplesSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedSamplesTable))
+	samplesSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedSamplesTable))
 	samplesSB.Where(samplesSB.Between("unix_milli", req.Start, req.End))
 	samplesSB.Where("NOT startsWith(metric_name, 'signoz')")
 
@@ -1053,7 +1053,7 @@ func (m *module) fetchMetricsStatsWithSamples(
 	if filterWhereClause != nil {
 		fingerprintSB := sqlbuilder.NewSelectBuilder()
 		fingerprintSB.Select("fingerprint")
-		fingerprintSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTsTable))
+		fingerprintSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTsTable))
 		fingerprintSB.Where(fingerprintSB.Between("unix_milli", start, end))
 		fingerprintSB.Where("NOT startsWith(metric_name, 'signoz')")
 		fingerprintSB.AddWhereClause(sqlbuilder.CopyWhereClause(filterWhereClause))
@@ -1064,7 +1064,7 @@ func (m *module) fetchMetricsStatsWithSamples(
 	} else {
 		metricNamesSB := sqlbuilder.NewSelectBuilder()
 		metricNamesSB.Select("DISTINCT metric_name")
-		metricNamesSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTsTable))
+		metricNamesSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTsTable))
 		metricNamesSB.Where(metricNamesSB.Between("unix_milli", start, end))
 		metricNamesSB.Where("NOT startsWith(metric_name, 'signoz')")
 
@@ -1090,18 +1090,18 @@ func (m *module) fetchMetricsStatsWithSamples(
 		// the data lands either of the _reduced_last/_reduced_sum tables
 		reducedLastSB := sqlbuilder.NewSelectBuilder()
 		reducedLastSB.Select("metric_name", "uniq(reduced_fingerprint, unix_milli) AS cnt")
-		reducedLastSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.SamplesV4ReducedLastTableName))
+		reducedLastSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.SamplesV4ReducedLastTableName))
 		reducedLastSB.Where(reducedLastSB.Between("unix_milli", req.Start, req.End))
 		reducedLastSB.Where("NOT startsWith(metric_name, 'signoz')")
 
 		reducedSumSB := sqlbuilder.NewSelectBuilder()
 		reducedSumSB.Select("metric_name", "uniq(reduced_fingerprint, unix_milli) AS cnt")
-		reducedSumSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.SamplesV4ReducedSumTableName))
+		reducedSumSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.SamplesV4ReducedSumTableName))
 		reducedSumSB.Where(reducedSumSB.Between("unix_milli", req.Start, req.End))
 		reducedSumSB.Where("NOT startsWith(metric_name, 'signoz')")
 
 		// separate query for reduced series counts
-		reducedTsSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4ReducedTableName))
+		reducedTsSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4ReducedTableName))
 		reducedTsSB.Where(reducedTsSB.Between("unix_milli", start, end))
 		reducedTsSB.Where("NOT startsWith(metric_name, 'signoz')")
 		reducedTsSB.GroupBy("metric_name")
@@ -1112,7 +1112,7 @@ func (m *module) fetchMetricsStatsWithSamples(
 			// samples uses a separate cte with local table
 			reducedFpSB := sqlbuilder.NewSelectBuilder()
 			reducedFpSB.Select("fingerprint")
-			reducedFpSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4ReducedLocalTableName))
+			reducedFpSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4ReducedLocalTableName))
 			reducedFpSB.Where(reducedFpSB.Between("unix_milli", start, end))
 			reducedFpSB.Where("NOT startsWith(metric_name, 'signoz')")
 			reducedFpSB.AddWhereClause(sqlbuilder.CopyWhereClause(filterWhereClause))
@@ -1220,11 +1220,11 @@ func (m *module) computeTimeseriesTreemap(ctx context.Context, orgID valuer.UUID
 		}
 	}
 
-	start, end, distributedTsTable, _ := telemetrymetrics.WhichTSTableToUse(uint64(req.Start), uint64(req.End), false, nil)
+	start, end, distributedTsTable, _ := metricstelemetryschema.WhichTSTableToUse(uint64(req.Start), uint64(req.End), false, nil)
 
 	totalTSBuilder := sqlbuilder.NewSelectBuilder()
 	totalTSBuilder.Select("uniq(fingerprint) AS total_time_series")
-	totalTSBuilder.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTsTable))
+	totalTSBuilder.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTsTable))
 	totalTSBuilder.Where(totalTSBuilder.Between("unix_milli", start, end))
 
 	metricsSB := sqlbuilder.NewSelectBuilder()
@@ -1232,7 +1232,7 @@ func (m *module) computeTimeseriesTreemap(ctx context.Context, orgID valuer.UUID
 		"metric_name",
 		"uniq(fingerprint) AS total_value",
 	)
-	metricsSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTsTable))
+	metricsSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTsTable))
 	metricsSB.Where(metricsSB.Between("unix_milli", start, end))
 	metricsSB.Where("NOT startsWith(metric_name, 'signoz')")
 	if filterWhereClause != nil {
@@ -1244,7 +1244,7 @@ func (m *module) computeTimeseriesTreemap(ctx context.Context, orgID valuer.UUID
 	if reductionEnabled {
 		reducedTotalTSBuilder := sqlbuilder.NewSelectBuilder()
 		reducedTotalTSBuilder.Select("uniq(fingerprint) AS total_time_series")
-		reducedTotalTSBuilder.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4ReducedTableName))
+		reducedTotalTSBuilder.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4ReducedTableName))
 		reducedTotalTSBuilder.Where(reducedTotalTSBuilder.Between("unix_milli", start, end))
 
 		reducedMetricsSB := sqlbuilder.NewSelectBuilder()
@@ -1252,7 +1252,7 @@ func (m *module) computeTimeseriesTreemap(ctx context.Context, orgID valuer.UUID
 			"metric_name",
 			"uniq(fingerprint) AS total_value",
 		)
-		reducedMetricsSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4ReducedTableName))
+		reducedMetricsSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4ReducedTableName))
 		reducedMetricsSB.Where(reducedMetricsSB.Between("unix_milli", start, end))
 		reducedMetricsSB.Where("NOT startsWith(metric_name, 'signoz')")
 		if filterWhereClause != nil {
@@ -1338,15 +1338,15 @@ func (m *module) computeSamplesTreemap(ctx context.Context, orgID valuer.UUID, r
 		}
 	}
 
-	start, end, distributedTsTable, localTsTable := telemetrymetrics.WhichTSTableToUse(uint64(req.Start), uint64(req.End), false, nil)
-	distributedSamplesTable, _ := telemetrymetrics.WhichSamplesTableToUse(uint64(req.Start), uint64(req.End), metrictypes.UnspecifiedType, metrictypes.TimeAggregationUnspecified, false, nil)
-	countExp := telemetrymetrics.CountExpressionForSamplesTable(distributedSamplesTable)
+	start, end, distributedTsTable, localTsTable := metricstelemetryschema.WhichTSTableToUse(uint64(req.Start), uint64(req.End), false, nil)
+	distributedSamplesTable, _ := metricstelemetryschema.WhichSamplesTableToUse(uint64(req.Start), uint64(req.End), metrictypes.UnspecifiedType, metrictypes.TimeAggregationUnspecified, false, nil)
+	countExp := metricstelemetryschema.CountExpressionForSamplesTable(distributedSamplesTable)
 
 	candidateLimit := req.Limit + 50
 
 	metricCandidatesSB := sqlbuilder.NewSelectBuilder()
 	metricCandidatesSB.Select("metric_name")
-	metricCandidatesSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedTsTable))
+	metricCandidatesSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedTsTable))
 	metricCandidatesSB.Where("NOT startsWith(metric_name, 'signoz')")
 	metricCandidatesSB.Where(metricCandidatesSB.Between("unix_milli", start, end))
 	if filterWhereClause != nil {
@@ -1364,7 +1364,7 @@ func (m *module) computeSamplesTreemap(ctx context.Context, orgID valuer.UUID, r
 	if reductionEnabled {
 		reducedCandidatesSB = sqlbuilder.NewSelectBuilder()
 		reducedCandidatesSB.Select("metric_name")
-		reducedCandidatesSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4ReducedTableName))
+		reducedCandidatesSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4ReducedTableName))
 		reducedCandidatesSB.Where("NOT startsWith(metric_name, 'signoz')")
 		reducedCandidatesSB.Where(reducedCandidatesSB.Between("unix_milli", start, end))
 		if filterWhereClause != nil {
@@ -1379,7 +1379,7 @@ func (m *module) computeSamplesTreemap(ctx context.Context, orgID valuer.UUID, r
 
 	totalSamplesSB := sqlbuilder.NewSelectBuilder()
 	totalSamplesSB.Select(fmt.Sprintf("%s AS total_samples", countExp))
-	totalSamplesSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedSamplesTable))
+	totalSamplesSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedSamplesTable))
 	totalSamplesSB.Where(totalSamplesSB.Between("unix_milli", req.Start, req.End))
 
 	sampleCountsSB := sqlbuilder.NewSelectBuilder()
@@ -1387,7 +1387,7 @@ func (m *module) computeSamplesTreemap(ctx context.Context, orgID valuer.UUID, r
 		"metric_name",
 		fmt.Sprintf("%s AS samples", countExp),
 	)
-	sampleCountsSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, distributedSamplesTable))
+	sampleCountsSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, distributedSamplesTable))
 	sampleCountsSB.Where(sampleCountsSB.Between("unix_milli", req.Start, req.End))
 	sampleCountsSB.Where("metric_name GLOBAL IN (SELECT metric_name FROM __metric_candidates)")
 
@@ -1397,13 +1397,13 @@ func (m *module) computeSamplesTreemap(ctx context.Context, orgID valuer.UUID, r
 	if reductionEnabled {
 		reducedLastSB = sqlbuilder.NewSelectBuilder()
 		reducedLastSB.Select("metric_name", "uniq(reduced_fingerprint, unix_milli) AS cnt")
-		reducedLastSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.SamplesV4ReducedLastTableName))
+		reducedLastSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.SamplesV4ReducedLastTableName))
 		reducedLastSB.Where(reducedLastSB.Between("unix_milli", req.Start, req.End))
 		reducedLastSB.Where("metric_name GLOBAL IN (SELECT metric_name FROM __reduced_metric_candidates)")
 
 		reducedSumSB = sqlbuilder.NewSelectBuilder()
 		reducedSumSB.Select("metric_name", "uniq(reduced_fingerprint, unix_milli) AS cnt")
-		reducedSumSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.SamplesV4ReducedSumTableName))
+		reducedSumSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.SamplesV4ReducedSumTableName))
 		reducedSumSB.Where(reducedSumSB.Between("unix_milli", req.Start, req.End))
 		reducedSumSB.Where("metric_name GLOBAL IN (SELECT metric_name FROM __reduced_metric_candidates)")
 	}
@@ -1411,7 +1411,7 @@ func (m *module) computeSamplesTreemap(ctx context.Context, orgID valuer.UUID, r
 	if filterWhereClause != nil {
 		fingerprintSB := sqlbuilder.NewSelectBuilder()
 		fingerprintSB.Select("fingerprint")
-		fingerprintSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, localTsTable))
+		fingerprintSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, localTsTable))
 		fingerprintSB.Where(fingerprintSB.Between("unix_milli", start, end))
 		fingerprintSB.Where("NOT startsWith(metric_name, 'signoz')")
 		fingerprintSB.AddWhereClause(sqlbuilder.CopyWhereClause(filterWhereClause))
@@ -1423,7 +1423,7 @@ func (m *module) computeSamplesTreemap(ctx context.Context, orgID valuer.UUID, r
 		if reductionEnabled {
 			reducedFingerprintSB := sqlbuilder.NewSelectBuilder()
 			reducedFingerprintSB.Select("fingerprint")
-			reducedFingerprintSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4ReducedLocalTableName))
+			reducedFingerprintSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4ReducedLocalTableName))
 			reducedFingerprintSB.Where(reducedFingerprintSB.Between("unix_milli", start, end))
 			reducedFingerprintSB.Where("NOT startsWith(metric_name, 'signoz')")
 			reducedFingerprintSB.AddWhereClause(sqlbuilder.CopyWhereClause(filterWhereClause))
@@ -1457,12 +1457,12 @@ func (m *module) computeSamplesTreemap(ctx context.Context, orgID valuer.UUID, r
 		// Grand total includes reduced sample volume so percentages stay consistent.
 		reducedTotalLastSB := sqlbuilder.NewSelectBuilder()
 		reducedTotalLastSB.Select("uniq(reduced_fingerprint, unix_milli) AS cnt")
-		reducedTotalLastSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.SamplesV4ReducedLastTableName))
+		reducedTotalLastSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.SamplesV4ReducedLastTableName))
 		reducedTotalLastSB.Where(reducedTotalLastSB.Between("unix_milli", req.Start, req.End))
 
 		reducedTotalSumSB := sqlbuilder.NewSelectBuilder()
 		reducedTotalSumSB.Select("uniq(reduced_fingerprint, unix_milli) AS cnt")
-		reducedTotalSumSB.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.SamplesV4ReducedSumTableName))
+		reducedTotalSumSB.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.SamplesV4ReducedSumTableName))
 		reducedTotalSumSB.Where(reducedTotalSumSB.Between("unix_milli", req.Start, req.End))
 
 		reducedTotalSamplesSB := sqlbuilder.NewSelectBuilder()
@@ -1552,7 +1552,7 @@ func (m *module) getMetricDataPoints(ctx context.Context, metricName string) (ui
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("sum(count) AS data_points")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.SamplesV4Agg30mTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.SamplesV4Agg30mTableName))
 	sb.Where(sb.E("metric_name", metricName))
 
 	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
@@ -1574,7 +1574,7 @@ func (m *module) getMetricLastReceived(ctx context.Context, metricName string) (
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("MAX(last_reported_unix_milli) AS last_received_time")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.AttributesMetadataTableName))
 	sb.Where(sb.E("metric_name", metricName))
 	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
 
@@ -1599,7 +1599,7 @@ func (m *module) getTotalTimeSeriesForMetricName(ctx context.Context, metricName
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("uniq(fingerprint) AS time_series_count")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV41weekTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV41weekTableName))
 	sb.Where(sb.E("metric_name", metricName))
 
 	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
@@ -1623,7 +1623,7 @@ func (m *module) getActiveTimeSeriesForMetricName(ctx context.Context, metricNam
 
 	sb := sqlbuilder.NewSelectBuilder()
 	sb.Select("uniq(fingerprint) AS active_time_series")
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.TimeseriesV4TableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.TimeseriesV4TableName))
 	sb.Where(sb.E("metric_name", metricName))
 	sb.Where(sb.GTE("unix_milli", milli))
 
@@ -1649,7 +1649,7 @@ func (m *module) fetchMetricAttributes(ctx context.Context, metricName string, s
 		"groupUniqArray(1000)(attr_string_value) AS values",
 		"uniq(attr_string_value) AS valueCount",
 	)
-	sb.From(fmt.Sprintf("%s.%s", telemetrymetrics.DBName, telemetrymetrics.AttributesMetadataTableName))
+	sb.From(fmt.Sprintf("%s.%s", metricstelemetryschema.DBName, metricstelemetryschema.AttributesMetadataTableName))
 	sb.Where(sb.E("metric_name", metricName))
 	sb.Where("NOT startsWith(attr_name, '__')")
 

pkg/modules/promote/implpromote/module.go

@@ -9,7 +9,7 @@ import (
 	schemamigrator "github.com/SigNoz/signoz-otel-collector/cmd/signozschemamigrator/schema_migrator"
 	"github.com/SigNoz/signoz/pkg/errors"
 	"github.com/SigNoz/signoz/pkg/modules/promote"
-	"github.com/SigNoz/signoz/pkg/telemetrylogs"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/logstelemetryschema"
 	"github.com/SigNoz/signoz/pkg/telemetrystore"
 	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
 	"github.com/SigNoz/signoz/pkg/types/instrumentationtypes"
@@ -52,7 +52,7 @@ func (m *module) ListPromotedAndIndexedPaths(ctx context.Context) ([]promotetype
 
 	response := []promotetypes.PromotePath{}
 	for _, path := range promotedPaths {
-		fullPath := telemetrylogs.BodyPromotedColumnPrefix + path
+		fullPath := logstelemetryschema.BodyPromotedColumnPrefix + path
 		path = telemetrytypes.BodyJSONStringSearchPrefix + path
 		item := promotetypes.PromotePath{
 			Path:    path,
@@ -68,7 +68,7 @@ func (m *module) ListPromotedAndIndexedPaths(ctx context.Context) ([]promotetype
 
 	// add the paths that are not promoted but have indexes
 	for path, indexes := range aggr {
-		path := strings.TrimPrefix(path, telemetrylogs.BodyV2ColumnPrefix)
+		path := strings.TrimPrefix(path, logstelemetryschema.BodyV2ColumnPrefix)
 		path = telemetrytypes.BodyJSONStringSearchPrefix + path
 		response = append(response, promotetypes.PromotePath{
 			Path:    path,
@@ -108,8 +108,8 @@ func (m *module) createIndexes(ctx context.Context, indexes []schemamigrator.Ind
 
 	for _, index := range indexes {
 		alterStmt := schemamigrator.AlterTableAddIndex{
-			Database: telemetrylogs.DBName,
-			Table:    telemetrylogs.LogsV2LocalTableName,
+			Database: logstelemetryschema.DBName,
+			Table:    logstelemetryschema.LogsV2LocalTableName,
 			Index:    index,
 		}
 		op := alterStmt.OnCluster(m.telemetryStore.Cluster())
@@ -153,10 +153,10 @@ func (m *module) PromoteAndIndexPaths(
 			}
 		}
 		if len(it.Indexes) > 0 {
-			parentColumn := telemetrylogs.LogsV2BodyV2Column
+			parentColumn := logstelemetryschema.LogsV2BodyV2Column
 			// if the path is already promoted or is being promoted, add it to the promoted column
 			if _, promoted := existingPromotedPaths[it.Path]; promoted || it.Promote {
-				parentColumn = telemetrylogs.LogsV2BodyPromotedColumn
+				parentColumn = logstelemetryschema.LogsV2BodyPromotedColumn
 			}
 
 			for _, index := range it.Indexes {

pkg/modules/services/implservices/module.go

@@ -11,8 +11,8 @@ import (
 	"github.com/SigNoz/signoz/pkg/errors"
 	"github.com/SigNoz/signoz/pkg/modules/services"
 	"github.com/SigNoz/signoz/pkg/querier"
+	"github.com/SigNoz/signoz/pkg/telemetryschema/tracestelemetryschema"
 	"github.com/SigNoz/signoz/pkg/telemetrystore"
-	"github.com/SigNoz/signoz/pkg/telemetrytraces"
 	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
 	"github.com/SigNoz/signoz/pkg/types/instrumentationtypes"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
@@ -39,7 +39,7 @@ func (m *module) FetchTopLevelOperations(ctx context.Context, start time.Time, s
 	ctx = m.withServicesContext(ctx, "FetchTopLevelOperations")
 
 	db := m.TelemetryStore.ClickhouseDB()
-	query := fmt.Sprintf("SELECT name, serviceName, max(time) as ts FROM %s.%s WHERE time >= @start", telemetrytraces.DBName, telemetrytraces.TopLevelOperationsTableName)
+	query := fmt.Sprintf("SELECT name, serviceName, max(time) as ts FROM %s.%s WHERE time >= @start", tracestelemetryschema.DBName, tracestelemetryschema.TopLevelOperationsTableName)
 	args := []any{clickhouse.Named("start", start)}
 	if len(services) > 0 {
 		query += " AND serviceName IN @services"

pkg/prometheus/clickhouseprometheusv2/capture.go

@@ -1,85 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"context"
-	"sync"
-
-	"github.com/SigNoz/signoz/pkg/prometheus"
-	"github.com/prometheus/prometheus/model/labels"
-	"github.com/prometheus/prometheus/storage"
-	"github.com/prometheus/prometheus/util/annotations"
-)
-
-// statementRecorder collects the statements a PromQL evaluation would run.
-// Safe for concurrent use: the engine may Select selectors concurrently.
-type statementRecorder struct {
-	mu         sync.Mutex
-	statements []prometheus.CapturedStatement
-}
-
-func (r *statementRecorder) record(query string, args []any) {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	r.statements = append(r.statements, prometheus.CapturedStatement{Query: query, Args: args})
-}
-
-func (r *statementRecorder) Statements() []prometheus.CapturedStatement {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	out := make([]prometheus.CapturedStatement, len(r.statements))
-	copy(out, r.statements)
-	return out
-}
-
-type captureQueryable struct {
-	client   *client
-	recorder *statementRecorder
-}
-
-func (c *captureQueryable) Querier(mint, maxt int64) (storage.Querier, error) {
-	return &captureQuerier{
-		querier:  querier{mint: mint, maxt: maxt, client: c.client},
-		recorder: c.recorder,
-	}, nil
-}
-
-// captureQuerier builds the same SQL as the live querier but records it and
-// returns no data. The fingerprint filter always takes the subquery form:
-// without executing the series lookup, the inline literal set is unknown.
-type captureQuerier struct {
-	querier
-	recorder *statementRecorder
-}
-
-func (c *captureQuerier) Select(ctx context.Context, _ bool, hints *storage.SelectHints, matchers ...*labels.Matcher) storage.SeriesSet {
-
-	start, end := c.window(hints)
-
-	samplesQuery, args, err := buildSamplesQuery(start, end, metricNamesFromMatchers(matchers), matchers, c.lastSamplePerStepFor(ctx, hints))
-	if err != nil {
-		return storage.ErrSeriesSet(err)
-	}
-	c.recorder.record(samplesQuery, args)
-
-	return storage.EmptySeriesSet()
-}
-
-func (c *captureQuerier) LabelValues(context.Context, string, *storage.LabelHints, ...*labels.Matcher) ([]string, annotations.Annotations, error) {
-	return nil, nil, nil
-}
-
-func (c *captureQuerier) LabelNames(context.Context, *storage.LabelHints, ...*labels.Matcher) ([]string, annotations.Annotations, error) {
-	return nil, nil, nil
-}
-
-// metricNamesFromMatchers extracts the statically known metric name, if any.
-// The live path derives names from the matched series; the capture path has
-// no execution results, so only a __name__ equality contributes.
-func metricNamesFromMatchers(matchers []*labels.Matcher) []string {
-	for _, m := range matchers {
-		if m.Name == metricNameLabel && m.Type == labels.MatchEqual && m.Value != "" {
-			return []string{m.Value}
-		}
-	}
-	return nil
-}

pkg/prometheus/clickhouseprometheusv2/classification_golden_test.go

@@ -1,119 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"encoding/json"
-	"flag"
-	"os"
-	"path/filepath"
-	"sort"
-	"testing"
-
-	"github.com/prometheus/prometheus/promql/parser"
-	"github.com/stretchr/testify/require"
-)
-
-var updateGolden = flag.Bool("update", false, "rewrite the classification golden file")
-
-const goldenFile = "testdata/classification_golden.json"
-
-// corpusFile is the conformance corpus the integration suite replays; the
-// golden freezes how the classifier routes every one of its expressions.
-const corpusFile = "../../../tests/integration/testdata/promqltestcorpus/corpus.json"
-
-type goldenEntry struct {
-	Expr    string `json:"expr"`
-	StartMs int64  `json:"start_ms"`
-	EndMs   int64  `json:"end_ms"`
-	StepMs  int64  `json:"step_ms"`
-	// Plan is the routing decision: "full" (whole query in ClickHouse),
-	// "hybrid" (units substituted, engine on top), "fallback" (engine over
-	// the native querier).
-	Plan string `json:"plan"`
-	// Units is the substituted-unit count for hybrid plans.
-	Units int `json:"units,omitempty"`
-	// Reason is the coarse fallback bucket (fallbackShape).
-	Reason string `json:"reason,omitempty"`
-}
-
-// TestClassificationGolden freezes the classifier's routing decision for
-// every (expression, grid) of the conformance corpus. Routing is a
-// correctness surface of its own: a change that silently sends rate() to the
-// engine path costs the pushdown, and one that silently starts transpiling a
-// shape never proven equivalent risks wrong numbers — both must show up in
-// review as a diff of this file, with the corpus suite's clickhousev2 leg
-// judging whether the new routing still returns the reference answers.
-//
-// Regenerate after intentional classifier changes:
-//
-//	go test ./pkg/prometheus/clickhouseprometheusv2 -run TestClassificationGolden -update
-func TestClassificationGolden(t *testing.T) {
-	raw, err := os.ReadFile(corpusFile)
-	require.NoError(t, err)
-
-	var corpus struct {
-		Cases []struct {
-			Expr    string `json:"expr"`
-			StartMs int64  `json:"start_ms"`
-			EndMs   int64  `json:"end_ms"`
-			StepMs  int64  `json:"step_ms"`
-		} `json:"cases"`
-	}
-	require.NoError(t, json.Unmarshal(raw, &corpus))
-	require.NotEmpty(t, corpus.Cases)
-
-	promParser := parser.NewParser(parser.Options{})
-	seen := map[goldenEntry]bool{}
-	var entries []goldenEntry
-	for _, c := range corpus.Cases {
-		key := goldenEntry{Expr: c.Expr, StartMs: c.StartMs, EndMs: c.EndMs, StepMs: c.StepMs}
-		if seen[key] {
-			continue
-		}
-		seen[key] = true
-
-		expr, err := promParser.ParseExpr(c.Expr)
-		require.NoError(t, err, "corpus expression must parse: %q", c.Expr)
-
-		entry := key
-		plan, ok := classify(expr, gridContext{startMs: c.StartMs, endMs: c.EndMs, stepMs: c.StepMs})
-		switch {
-		case ok && plan.full:
-			entry.Plan = "full"
-		case ok:
-			entry.Plan = "hybrid"
-			entry.Units = len(plan.units)
-		default:
-			entry.Plan = "fallback"
-			entry.Reason = fallbackShape(expr)
-		}
-		entries = append(entries, entry)
-	}
-	sort.Slice(entries, func(i, j int) bool {
-		a, b := entries[i], entries[j]
-		if a.Expr != b.Expr {
-			return a.Expr < b.Expr
-		}
-		if a.StartMs != b.StartMs {
-			return a.StartMs < b.StartMs
-		}
-		if a.EndMs != b.EndMs {
-			return a.EndMs < b.EndMs
-		}
-		return a.StepMs < b.StepMs
-	})
-
-	got, err := json.MarshalIndent(entries, "", "  ")
-	require.NoError(t, err)
-	got = append(got, '\n')
-
-	if *updateGolden {
-		require.NoError(t, os.MkdirAll(filepath.Dir(goldenFile), 0o755))
-		require.NoError(t, os.WriteFile(goldenFile, got, 0o644))
-		return
-	}
-
-	want, err := os.ReadFile(goldenFile)
-	require.NoError(t, err, "golden missing — generate it with -update")
-	require.Equal(t, string(want), string(got),
-		"classification routing changed; if intentional, regenerate with -update and justify the diff in review")
-}

pkg/prometheus/clickhouseprometheusv2/client.go

@@ -1,180 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"context"
-	"encoding/json"
-	"log/slog"
-	"math"
-	"slices"
-
-	"github.com/SigNoz/signoz/pkg/factory"
-	"github.com/SigNoz/signoz/pkg/prometheus"
-	"github.com/SigNoz/signoz/pkg/telemetrystore"
-	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
-	"github.com/SigNoz/signoz/pkg/types/instrumentationtypes"
-	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
-	"github.com/prometheus/prometheus/model/labels"
-	promValue "github.com/prometheus/prometheus/model/value"
-)
-
-// seriesLookup holds a series lookup's result: matched fingerprints with
-// their labels, and the distinct metric names seen on them.
-type seriesLookup struct {
-	fingerprints map[uint64]labels.Labels
-	metricNames  []string
-}
-
-// client executes the series, samples and raw queries against ClickHouse.
-type client struct {
-	settings       factory.ScopedProviderSettings
-	telemetryStore telemetrystore.TelemetryStore
-	lookbackMs     int64
-}
-
-func newClient(settings factory.ScopedProviderSettings, telemetryStore telemetrystore.TelemetryStore, cfg prometheus.Config) *client {
-	lookback := cfg.LookbackDelta
-	if lookback <= 0 {
-		// Mirror the engine: promql defaults an unset lookback to 5m.
-		lookback = defaultLookbackDelta
-	}
-	return &client{
-		settings:       settings,
-		telemetryStore: telemetryStore,
-		lookbackMs:     lookback.Milliseconds(),
-	}
-}
-
-func (c *client) withContext(ctx context.Context, functionName string) context.Context {
-	return ctxtypes.NewContextWithCommentVals(ctx, map[string]string{
-		instrumentationtypes.TelemetrySignal:  telemetrytypes.SignalMetrics.StringValue(),
-		instrumentationtypes.CodeNamespace:    "clickhouse-prometheus-v2",
-		instrumentationtypes.CodeFunctionName: functionName,
-	})
-}
-
-func (c *client) selectSeries(ctx context.Context, query string, args []any) (*seriesLookup, error) {
-	ctx = c.withContext(ctx, "selectSeries")
-	rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
-	if err != nil {
-		return nil, err
-	}
-	defer rows.Close()
-
-	lookup := &seriesLookup{fingerprints: make(map[uint64]labels.Labels)}
-	names := make(map[string]struct{})
-
-	var fingerprint uint64
-	var labelsJSON string
-	for rows.Next() {
-		if err := rows.Scan(&fingerprint, &labelsJSON); err != nil {
-			return nil, err
-		}
-		lset, err := unmarshalLabels(labelsJSON)
-		if err != nil {
-			return nil, err
-		}
-		lookup.fingerprints[fingerprint] = lset
-		if name := lset.Get(metricNameLabel); name != "" {
-			names[name] = struct{}{}
-		}
-	}
-	if err := rows.Err(); err != nil {
-		return nil, err
-	}
-
-	for name := range names {
-		lookup.metricNames = append(lookup.metricNames, name)
-	}
-	slices.Sort(lookup.metricNames)
-
-	return lookup, nil
-}
-
-// unmarshalLabels parses the labels JSON column, dropping empty-valued
-// labels: empty means "absent" in Prometheus, but stored attribute JSON can
-// carry them.
-func unmarshalLabels(s string) (labels.Labels, error) {
-	m := make(map[string]string)
-	if err := json.Unmarshal([]byte(s), &m); err != nil {
-		return labels.EmptyLabels(), err
-	}
-	builder := labels.NewScratchBuilder(len(m))
-	for k, v := range m {
-		if v == "" {
-			continue
-		}
-		builder.Add(k, v)
-	}
-	builder.Sort()
-	return builder.Labels(), nil
-}
-
-// selectSamples assembles per-series sample slices from a samples query (raw
-// or last-sample-per-step; same column shape), whose rows arrive ordered by
-// (fingerprint, unix_milli). Fingerprints missing from the lookup are skipped:
-// the samples query's semi-join re-runs the series predicates and can match
-// series registered after the lookup ran — the lookup is the read snapshot.
-// Stale flags map to the engine's StaleNaN. Duplicate
-// timestamps pass through: uniqueness is ingest's job, and v1 feeds them to
-// the engine as-is over the same dirty data.
-func (c *client) selectSamples(ctx context.Context, query string, args []any, lookup *seriesLookup) ([]*series, error) {
-	ctx = c.withContext(ctx, "selectSamples")
-	rows, err := c.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
-	if err != nil {
-		return nil, err
-	}
-	defer rows.Close()
-
-	var (
-		result       []*series
-		current      *series
-		fingerprint  uint64
-		prevFp       uint64
-		timestampMs  int64
-		val          float64
-		flags        uint32
-		first        = true
-		haveCurrent  bool
-		staleMarker  = math.Float64frombits(promValue.StaleNaN)
-		unknownCount int
-	)
-
-	for rows.Next() {
-		if err := rows.Scan(&fingerprint, &timestampMs, &val, &flags); err != nil {
-			return nil, err
-		}
-
-		if first || fingerprint != prevFp {
-			first = false
-			prevFp = fingerprint
-			lset, ok := lookup.fingerprints[fingerprint]
-			if !ok {
-				unknownCount++
-				haveCurrent = false
-				continue
-			}
-			current = &series{lset: lset}
-			result = append(result, current)
-			haveCurrent = true
-		}
-		if !haveCurrent {
-			continue
-		}
-
-		if flags&1 == 1 {
-			val = staleMarker
-		}
-		current.ts = append(current.ts, timestampMs)
-		current.vs = append(current.vs, val)
-	}
-	if err := rows.Err(); err != nil {
-		return nil, err
-	}
-
-	if unknownCount > 0 {
-		c.settings.Logger().DebugContext(ctx, "skipped samples of fingerprints missing from series lookup",
-			slog.Int("unknown_fingerprints", unknownCount))
-	}
-
-	return result, nil
-}

pkg/prometheus/clickhouseprometheusv2/doc.go

@@ -1,337 +0,0 @@
-// Package clickhouseprometheusv2 is the second-generation ClickHouse-backed
-// Prometheus provider. It exists because the v1 provider fetches every raw
-// sample of a query's union window through the remote-read protobuf layer
-// and hands it to the engine — the cost is a function of ingested data, not
-// of the question asked, which is how a dashboard of PromQL panels takes an
-// instance down.
-//
-// Every query runs in one of two ways, decided per query:
-//
-//   - Transpiled: the query is evaluated entirely inside ClickHouse and only
-//     final (or near-final) per-group grid arrays come back, built on the
-//     timeSeries*ToGrid aggregate functions (the supported ClickHouse floor
-//     is >= 25.6, so they are assumed available).
-//   - Engine: the stock promql engine evaluates over this package's native
-//     storage.Querier. This is the path for everything not transpilable.
-//
-// Correctness is the constraint that shaped both paths: a PromQL result that
-// differs from upstream Prometheus is a lost user, so anything that cannot
-// reproduce engine semantics exactly falls back rather than approximate.
-// The rest of this comment is the PromQL -> SQL story, because that mapping
-// is where correctness is won or lost.
-//
-// # The evaluation model the SQL must reproduce
-//
-// A PromQL range query is an instant query evaluated at every grid point
-// t_i = start + i*step, i = 0..(end-start)/step. At each t_i:
-//
-//   - an instant selector resolves to the latest sample in the left-open
-//     lookback window (t_i - lookback, t_i], and to nothing when that latest
-//     sample is a stale marker — even if older real samples sit inside the
-//     window;
-//   - a range selector [r] collects every sample in (t_i - r, t_i], stale
-//     markers excluded;
-//   - offset d shifts both windows to (t_i - d - w, t_i - d].
-//
-// The transpilation invariant follows from this: every transpiled construct
-// produces, per output series, one array with exactly one slot per grid
-// point — slot i holds the value at t_i, NULL means absent. This is what
-// makes composition correct, not just convenient: the engine evaluates
-// these operators independently per t_i, so any representation that gets
-// every slot right gets the whole query right, and spatial aggregation over
-// arrays is sound because it combines values that belong to the same t_i by
-// construction. Slot index i maps back to t_i = start + i*step at scan time
-// (toMatrix). Everything below is about filling those slots with exactly
-// the numbers the engine would compute — and each equivalence was validated
-// against the vendored engine on live data before its shape entered the
-// allowlist; anything unproven stays on the engine path.
-//
-// # Classification: finding what a statement can answer
-//
-// classify walks the parsed AST looking for "core units" — maximal subtrees
-// of the shape
-//
-//	[agg by/without (...)] [fn(] selector[range] [offset d] [)] [op scalar]...
-//
-// classifyCore peels that chain from the outside in: an optional
-// sum/min/max/avg/count aggregation, then one of the allowlisted functions
-// or a bare instant selector, then the selector with its offset; on the way
-// out it accumulates number-literal arithmetic, comparisons (including
-// bool) and unary minus into a scalar-op pipeline. A node qualifies only if
-// its type, arguments and children are in the proven set — an allowlist, so
-// an overlooked construct becomes a fallback instead of a wrong number.
-//
-// Three unit kinds come out of this, each with its own SQL form:
-// unitRange (rate, irate, increase, delta, idelta over a range selector),
-// unitInstant (instant vector selection, bare or comparison-filtered) and
-// unitOverTime (avg/min/max/sum/count/last _over_time).
-//
-// If the entire tree is one unit, the plan is "full": the statement's rows
-// are the query result. Otherwise every maximal unit is cut out and replaced
-// in the expression with a synthetic selector __signoz_transpiled_N__, and
-// the rewritten expression runs in the engine over the units' materialized
-// results ("hybrid") — histogram_quantile, topk, or/and/unless and vector
-// matching keep exact engine semantics while their expensive inputs were
-// aggregated server-side.
-//
-// Classification refuses when exact semantics cannot be guaranteed
-// server-side: the @ modifier anywhere and default-resolution subqueries
-// (their resolution is a server runtime setting the transpiler cannot see);
-// duration expressions (offset step(), [range()], ...) anywhere — they are
-// resolved into the selector's static fields only at evaluation time, so at
-// classification time those fields still hold their zero values and
-// transpiling would silently use the wrong offset or range;
-// steps or ranges that are not whole seconds (the grid functions take
-// whole-second parameters); grouping by or matching on __name__ in hybrid
-// plans (the synthetic name would leak into results); name-keeping units —
-// bare/comparison instant selectors and last_over_time keep their real
-// __name__ (keepsName), which substitution would replace, so they transpile
-// only as full plans; and every function outside the allowlist (changes,
-// resets, quantile_over_time, absent, native-histogram functions, ...).
-//
-// Units inside a fixed-resolution subquery evaluate on the subquery's own
-// grid instead of the query grid: epoch-aligned multiples of the resolution
-// strictly after outerStart - offset - range, ending at outer end - offset —
-// the exact derivation the engine uses, because a grid shifted by one step
-// changes which samples every window sees.
-//
-// # From one unit to one statement
-//
-// buildUnitSQL renders each unit as a single statement. For
-// sum by (pod) (rate(m{job="api"}[5m])) the skeleton is:
-//
-//	SELECT gkey, sumForEach(grid) AS grid FROM (
-//	    SELECT series.gkey AS gkey,
-//	           timeSeriesRateToGrid(<start>, <end>, <step>, <range>)(fromUnixTimestamp64Milli(unix_milli), value) AS grid
-//	    FROM signoz_metrics.distributed_samples_v4 AS points
-//	    INNER JOIN (
-//	        SELECT fingerprint, <group key expr> AS gkey
-//	        FROM signoz_metrics.time_series_v4
-//	        WHERE <series predicates>
-//	        GROUP BY fingerprint, gkey
-//	    ) AS series ON points.fingerprint = series.fingerprint
-//	    WHERE metric_name = ? AND temporality IN ['Cumulative', 'Unspecified']
-//	      AND points.fingerprint IN (<matched fingerprints>)
-//	      AND unix_milli > <start - range> AND unix_milli <= <end>
-//	      AND bitAnd(flags, 1) = 0
-//	    GROUP BY points.fingerprint, series.gkey
-//	) GROUP BY gkey
-//	SETTINGS allow_experimental_ts_to_grid_aggregate_function = 1
-//
-// Reading it inside out:
-//
-// The time window is the selector's semantics verbatim: strict > on the
-// lower bound and <= on the upper is the left-open (t - w, t] rule, with the
-// whole window shifted by the offset. bitAnd(flags, 1) = 0 drops stale
-// markers, which PromQL excludes from range vectors.
-//
-// The inner GROUP BY computes one grid array per series.
-// timeSeriesRateToGrid(start, end, step, range) is a parametric aggregate:
-// fed (timestamp, value) pairs it produces Array(Nullable(Float64)) with one
-// slot per grid point. Correct because it implements the engine's
-// extrapolatedRate decision for decision — counter resets, the zero-point
-// clamp, the extrapolation thresholds, the >= 2 samples rule, the left-open
-// window — verified by feeding identical samples to both and comparing
-// slot for slot: the only difference ever observed is the last bit
-// (ClickHouse's C++ and Go round the same formula differently), which is
-// the floating-point floor, not a semantic gap. irate/delta/idelta map to
-// their own timeSeries*ToGrid functions with the same verification;
-// increase has no function of its own and is emitted as
-// arrayMap(x -> x * <range seconds>, <rate expr>), exact by definition —
-// extrapolatedRate computes the same extrapolated delta for both and
-// divides by the range only when isRate, so multiplying it back is the
-// identity, not an approximation. The grid parameters are rendered as
-// literals, not bound args — they are aggregate-function parameters — and
-// the experimental gate rides as a SETTINGS clause on the statement itself
-// so telemetrystore hooks cannot clobber it.
-//
-// The join annotates each series with its group key, in one of two forms.
-// by (...) extracts each listed label as a plain column
-// (JSONExtractString(labels, 'pod') AS g0) and groups on the columns
-// directly: the projection is a known short list and the label names live
-// in Go, so building, sorting and stringifying every label pair per row
-// would be waste. Correct because column-tuple equality is label-set
-// equality on the projection, and an extracted '' is the label being
-// absent — Prometheus semantics for by() over missing labels, and empties
-// are skipped when the columns turn back into labels. without and
-// no-aggregation project a label SET that varies per series, so they get
-// the canonical key: toJSONString of the sorted [label, value] pairs the
-// unit projects (without excludes the listed labels plus __name__; no
-// aggregation keeps everything, the name coming off in Go per the engine's
-// name-dropping rules). There the sort is load-bearing — stored JSON key
-// order is not canonical across fingerprints, and two orderings of the same
-// labels must land in one group — empty values are filtered for the same
-// absent-label reason, and the same string parses back into the output
-// label set (labelsFromGroupKey).
-//
-// The outer GROUP BY is the spatial aggregation: sum/min/max/avg/count
-// by/without become the -ForEach combinators. Element-wise aggregation over
-// grid arrays is the engine's per-t_i aggregation, because slot i of every
-// input array refers to the same t_i; the combinators skip NULLs, which is
-// the engine aggregating only the series present at t_i, and an index where
-// every series is absent stays NULL. Two edges need explicit handling:
-// countForEach wraps in a mapping of 0 back to NULL, because a count over
-// an all-absent index is an absent point, not 0; and a unit without
-// aggregation still passes through maxForEach — the identity for the common
-// one-fingerprint group, and a deterministic NULL-skipping merge when a
-// regex __name__ selector collapses distinct metrics onto one projected
-// label set. One caveat is inherent: summation order over series differs
-// from the engine's, so spatial aggregates can differ in the last ULP —
-// float addition is not associative; no ordering reproduces the engine's
-// bit-exactly from inside a GROUP BY.
-//
-// # Instant selectors: staleness needs two aggregates
-//
-// unitInstant uses window = lookback and must reproduce the shadowing rule:
-// the point is absent when the latest in-window sample is a stale marker.
-// timeSeriesLastToGrid alone cannot express that — skipping stale rows in
-// WHERE would resurrect the older real sample the marker was written to
-// bury. So stale rows stay in the scan for this kind only, and the grid
-// expression compares three aggregates per slot:
-//
-//	arrayMap((tall, tok, vok) -> if(tall IS NULL OR tok IS NULL OR tall != tok, NULL, vok),
-//	         timeSeriesLastToGrid(...)(ts, toFloat64(unix_milli)),                           -- last sample overall
-//	         timeSeriesLastToGridIf(...)(ts, toFloat64(unix_milli), bitAnd(flags, 1) = 0),   -- last non-stale, its timestamp
-//	         timeSeriesLastToGridIf(...)(ts, value, bitAnd(flags, 1) = 0))                   -- last non-stale, its value
-//
-// Correct by cases on a slot's window. No samples at all: both timestamp
-// aggregates are NULL, the slot is NULL — absent, as the engine says. Latest
-// sample non-stale: it is the latest overall and the latest non-stale, the
-// timestamps agree, the slot takes its value — the engine's pick. Latest
-// sample stale: the last-overall timestamp is the marker's, the
-// last-non-stale timestamp is older (or NULL when only markers are in
-// window), they disagree, the slot is NULL — the marker shadows, exactly
-// the engine's rule. Timestamps are unique per series (ingest dedups), so
-// timestamp equality identifies "the same sample" without ambiguity. The
-// -If combinator's applicability to these experimental aggregates was
-// probed before being trusted, not assumed.
-//
-// # Windowed *_over_time: whole buckets instead of a grid function
-//
-// avg/min/max/sum/count _over_time aggregate every raw sample in the window,
-// and no timeSeries*ToGrid function computes them. (last_over_time is the
-// exception: the last sample of a range vector — stale markers excluded from
-// range vectors by PromQL, excluded here in WHERE — is exactly
-// timeSeriesLastToGrid.) These transpile only when the range is a whole
-// multiple of the step, and then the window needs no per-sample fan-out at
-// all: with W = range/step, the window (t_k - range, t_k] is exactly the
-// union of W step buckets — both are left-open on the same boundaries — so
-// bucket membership fully determines window membership. Each sample lands
-// in exactly one bucket by a plain GROUP BY:
-//
-//	intDiv(unix_milli - <start> + <range> - 1, <step>) AS jj
-//
-// (ceil((ts - start)/step) shifted by W-1 so the earliest in-window sample
-// sits at 0; slot k's window is buckets jj in [k, k+W-1]). The alternative —
-// fanning each sample into all W windows that cover it — multiplies rows by
-// W, which for a long range over a short step is a row explosion measured
-// in billions; the bucketed form's row count is series x buckets, the size
-// of the output, regardless of W.
-//
-// The shard level aggregates per (series, group key, bucket): a bucket
-// count plus the function's value aggregate (sum for sum/avg, min, max).
-// The assembly level places the partials into dense arrays
-// (groupArrayInsertAt — positions are unique, one row per bucket; counts
-// and sums default to 0, which contributes nothing) and slides: slot k
-// combines its at-most-W bucket partials by direct aggregation, so window
-// sums are added the way the engine adds them — no prefix-sum differencing,
-// whose large-minus-large cancellation would drift past the shadow
-// tolerance on counter-sized values. Correct per slot because the bucket
-// union is the exact window multiset and avg/min/max/sum/count are
-// order-insensitive on a multiset (sum/avg up to summation order, the float
-// caveat above). A slot with zero window count is absent; min/max filter
-// their slices on the bucket counts, so an empty bucket's default can never
-// be mistaken for a value — a real sample can legitimately be +Inf.
-//
-// Ranges that don't divide the step, and windows wider than
-// maxWindowBuckets buckets (the slide costs W combines per slot), fall back
-// to the engine path, which is exact.
-//
-// # Scalar ops, full plans, hybrid plans
-//
-// The scalar-op pipeline applies in Go to the returned arrays
-// (applyScalarOps), slot by slot: arithmetic operators compute, comparisons
-// filter (the slot keeps the vector-side value or becomes NULL) or return
-// 0/1 under bool. Correct trivially: it is the same float64 operation the
-// engine would apply to the same slot value, in the same operator order the
-// AST dictates — running it in Go instead of another SQL layer changes
-// where, not what.
-//
-// A full plan's arrays map straight to the result matrix. A hybrid plan
-// materializes each unit's arrays as synthetic series under its
-// __signoz_transpiled_N__ name and evaluates the rewritten expression over
-// a storage that serves synthetic names from memory and everything else
-// live. Substitution is sound because a unit's output is a plain instant
-// vector to the engine — same values at same timestamps under a different
-// name, and the name cannot matter: plans that group by or match on
-// __name__ were refused at classification, and name-keeping units are never
-// substituted. One subtlety makes it exact: stale markers are written at
-// absent grid points, because the engine's lookback would otherwise
-// resurrect a point from up to lookback earlier — the marker encodes
-// "absent here" the way the engine itself encodes it. Units evaluate
-// concurrently; each is one series lookup plus one grid statement. A step
-// of 0 is an instant query: a single evaluation at end.
-//
-// # Series lookup
-//
-// Both paths resolve matchers the same way, once per selector
-// (selectSeries), against the series tables holding one row per
-// (fingerprint, bucket) at 1h/6h/1d/1w granularities; timeSeriesTableFor
-// picks the table whose bucket fits the window and rounds the window start
-// down to the bucket boundary. How matchers become SQL, and why regexes are
-// anchored, is documented at applySeriesConditions. Empty-valued labels come
-// off at this boundary: an empty value means "label absent" in Prometheus,
-// but stored attribute JSON can carry them.
-//
-// # The engine path
-//
-// Queries that do not transpile run in the stock engine over this package's
-// storage.Querier, which is still not the v1 path. Samples are fetched per
-// selector using the engine's per-selector hints, not the query-wide union
-// window, so foo / foo offset 1d reads two narrow windows instead of the
-// widest one twice. Instant selectors of subquery-free queries fetch only
-// the last sample per step bucket (lastSamplePerStep): buckets anchor at the
-// selector's first evaluation timestamp — recovered from the hints as
-// hints.Start + lookback - 1ms, the inverse of how the engine derives
-// hints.Start — so bucket boundaries coincide with evaluation timestamps and
-// a non-final sample of a bucket can never be the latest sample in
-// (t - lookback, t] for any grid t. Real timestamps are preserved, so the
-// engine's own lookback and staleness handling stay exact. Range selectors
-// always fetch raw — every sample feeds the range function — and the
-// subquery-free proof travels in the context as prometheus.QueryTraits,
-// because subquery selectors evaluate at the subquery's step while the
-// hints carry the top-level step. Row assembly maps stale flags to the
-// engine's StaleNaN and merges series with identical label sets
-// (sortAndMerge) — the engine assumes storages never emit duplicates.
-//
-// # Sharding
-//
-// samples_v4 and time_series_v4 (and all their rollups) shard on the same
-// key — cityHash64(env, temporality, metric_name, fingerprint) — so a
-// series' samples and catalog rows live on the same shard. The transpiled
-// statement above exploits that: the distributed samples table at the
-// top-level FROM makes ClickHouse rewrite the whole inner query per shard,
-// where the join against the shard-local series table and the per-series
-// grid aggregation run next to the data; the initiator only merges
-// aggregate states and applies the spatial -ForEach step. Same layout as
-// the telemetrymetrics statement builder. The group-key join alone
-// restricts the transpiled scan to the matched series; the engine path's
-// samples fetch restricts by the same predicates as a shard-local
-// semi-join, not a GLOBAL broadcast of the matched set. The temporality
-// filter on every
-// samples statement is a semantic no-op — the matched fingerprints already
-// come from those temporalities — that engages the leading samples
-// primary-key column. Delta-temporality series stay invisible to PromQL
-// here exactly as they are in v1: the rollout gate is parity with v1, and
-// making Delta visible is its own change with its own semantics to design —
-// a Delta stream fed to rate() as-if-cumulative would be wrong, not just
-// new.
-//
-// # Observability
-//
-// Every statement carries a log_comment with
-// code.namespace=clickhouse-prometheus-v2 and code.function.name naming the
-// call site (selectSeries, selectSamples, transpiledUnit, LabelValues,
-// LabelNames), so this provider's work is attributable in system.query_log
-// without guessing from query text.
-package clickhouseprometheusv2

pkg/prometheus/clickhouseprometheusv2/provider.go

@@ -1,84 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"context"
-	"time"
-
-	"github.com/SigNoz/signoz/pkg/factory"
-	"github.com/SigNoz/signoz/pkg/prometheus"
-	"github.com/SigNoz/signoz/pkg/telemetrystore"
-	"github.com/prometheus/prometheus/promql"
-	"github.com/prometheus/prometheus/storage"
-)
-
-// Provider ties the package together: its own engine and parser, the
-// ClickHouse client behind the native storage.Querier, and the transpiler
-// executor. See the package documentation for what runs where and why. It is
-// exported as a concrete type — pkg/querier holds it directly for shadow
-// comparison and pinned serving, and an interface with a single
-// implementation would only hide that dependency.
-type Provider struct {
-	settings factory.ScopedProviderSettings
-	engine   *prometheus.Engine
-	parser   prometheus.Parser
-	client   *client
-	executor *executor
-}
-
-var (
-	_ prometheus.Prometheus        = (*Provider)(nil)
-	_ prometheus.StatementCapturer = (*Provider)(nil)
-)
-
-func NewFactory(telemetryStore telemetrystore.TelemetryStore) factory.ProviderFactory[prometheus.Prometheus, prometheus.Config] {
-	return factory.NewProviderFactory(factory.MustNewName("clickhousev2"), func(ctx context.Context, providerSettings factory.ProviderSettings, config prometheus.Config) (prometheus.Prometheus, error) {
-		return New(ctx, providerSettings, config, telemetryStore)
-	})
-}
-
-func New(_ context.Context, providerSettings factory.ProviderSettings, config prometheus.Config, telemetryStore telemetrystore.TelemetryStore) (*Provider, error) {
-	settings := factory.NewScopedProviderSettings(providerSettings, "github.com/SigNoz/signoz/pkg/prometheus/clickhouseprometheusv2")
-
-	engine := prometheus.NewEngine(settings.Logger(), config)
-	parser := prometheus.NewParser()
-	client := newClient(settings, telemetryStore, config)
-
-	return &Provider{
-		settings: settings,
-		engine:   engine,
-		parser:   parser,
-		client:   client,
-		executor: &executor{client: client, engine: engine, parser: parser},
-	}, nil
-}
-
-// TryExecuteRange evaluates transpilable query shapes directly in ClickHouse
-// (see transpiler.go). ok=false means the shape is not transpilable and the
-// caller should evaluate through Engine over Storage instead.
-func (p *Provider) TryExecuteRange(ctx context.Context, query string, start, end time.Time, step time.Duration) (promql.Matrix, bool, error) {
-	return p.executor.TryExecuteRange(ctx, query, start, end, step)
-}
-
-func (p *Provider) Engine() *prometheus.Engine {
-	return p.engine
-}
-
-func (p *Provider) Parser() prometheus.Parser {
-	return p.parser
-}
-
-func (p *Provider) Storage() storage.Queryable {
-	return p
-}
-
-func (p *Provider) Querier(mint, maxt int64) (storage.Querier, error) {
-	return &querier{mint: mint, maxt: maxt, client: p.client}, nil
-}
-
-// CapturingStorage implements prometheus.StatementCapturer: a storage that
-// records each selector's SQL without executing it, for the preview path.
-// A fresh recorder per call keeps concurrent dry-runs isolated.
-func (p *Provider) CapturingStorage() (storage.Queryable, prometheus.StatementRecorder) {
-	recorder := &statementRecorder{}
-	return &captureQueryable{client: p.client, recorder: recorder}, recorder
-}

pkg/prometheus/clickhouseprometheusv2/querier.go

@@ -1,170 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"context"
-	"fmt"
-	"slices"
-	"time"
-
-	"github.com/SigNoz/signoz/pkg/prometheus"
-	"github.com/huandu/go-sqlbuilder"
-	"github.com/prometheus/prometheus/model/labels"
-	"github.com/prometheus/prometheus/storage"
-	"github.com/prometheus/prometheus/util/annotations"
-)
-
-// defaultLookbackDelta mirrors promql's default when the config leaves the
-// lookback unset; the engine and the storage must agree on it for
-// last-sample-per-step bucket anchoring.
-const defaultLookbackDelta = 5 * time.Minute
-
-// querier is a native storage.Querier over ClickHouse: Select builds SQL
-// directly from the matchers and hints, with no remote-read protobuf layer.
-type querier struct {
-	mint, maxt int64
-	client     *client
-}
-
-var _ storage.Querier = (*querier)(nil)
-
-func (q *querier) Select(ctx context.Context, sortSeries bool, hints *storage.SelectHints, matchers ...*labels.Matcher) storage.SeriesSet {
-	start, end := q.window(hints)
-
-	seriesQuery, seriesArgs, err := buildSeriesQuery(start, end, matchers)
-	if err != nil {
-		return storage.ErrSeriesSet(err)
-	}
-	lookup, err := q.client.selectSeries(ctx, seriesQuery, seriesArgs)
-	if err != nil {
-		return storage.ErrSeriesSet(err)
-	}
-	if len(lookup.fingerprints) == 0 {
-		return storage.EmptySeriesSet()
-	}
-
-	list, err := q.fetchSamples(ctx, start, end, matchers, lookup, q.lastSamplePerStepFor(ctx, hints))
-	if err != nil {
-		return storage.ErrSeriesSet(err)
-	}
-
-	// The engine assumes storages never emit duplicate label sets.
-	list = sortAndMerge(list)
-	return newSeriesSet(list)
-}
-
-func (q *querier) LabelValues(ctx context.Context, name string, hints *storage.LabelHints, matchers ...*labels.Matcher) ([]string, annotations.Annotations, error) {
-	sb := sqlbuilder.NewSelectBuilder()
-	if name == metricNameLabel {
-		sb.Select("DISTINCT metric_name AS value")
-	} else {
-		sb.Select(fmt.Sprintf("DISTINCT JSONExtractString(labels, %s) AS value", sb.Var(name)))
-	}
-	adjustedStart, table := timeSeriesTableFor(q.mint, q.maxt)
-	sb.From(fmt.Sprintf("%s.%s", databaseName, table))
-	if err := applySeriesConditions(sb, adjustedStart, q.maxt, matchers); err != nil {
-		return nil, nil, err
-	}
-	sb.Where("value != ''")
-	if hints != nil && hints.Limit > 0 {
-		sb.Limit(hints.Limit)
-	}
-
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	values, err := q.selectStrings(ctx, "LabelValues", query, args)
-	if err != nil {
-		return nil, nil, err
-	}
-	slices.Sort(values)
-	return values, nil, nil
-}
-
-func (q *querier) LabelNames(ctx context.Context, hints *storage.LabelHints, matchers ...*labels.Matcher) ([]string, annotations.Annotations, error) {
-	sb := sqlbuilder.NewSelectBuilder()
-	sb.Select("DISTINCT arrayJoin(JSONExtractKeys(labels)) AS name")
-	adjustedStart, table := timeSeriesTableFor(q.mint, q.maxt)
-	sb.From(fmt.Sprintf("%s.%s", databaseName, table))
-	if err := applySeriesConditions(sb, adjustedStart, q.maxt, matchers); err != nil {
-		return nil, nil, err
-	}
-	if hints != nil && hints.Limit > 0 {
-		sb.Limit(hints.Limit)
-	}
-
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	names, err := q.selectStrings(ctx, "LabelNames", query, args)
-	if err != nil {
-		return nil, nil, err
-	}
-	slices.Sort(names)
-	return names, nil, nil
-}
-
-func (q *querier) Close() error {
-	return nil
-}
-
-// window returns the per-selector fetch window from the hints (already
-// adjusted for offset, @, range and lookback); mint/maxt span the union of
-// all selectors and are the fallback.
-func (q *querier) window(hints *storage.SelectHints) (int64, int64) {
-	if hints != nil && hints.Start != 0 && hints.End != 0 && hints.Start <= hints.End {
-		return hints.Start, hints.End
-	}
-	return q.mint, q.maxt
-}
-
-// lastSamplePerStepFor decides whether the fetch can keep only the last
-// sample per step bucket (see lastSamplePerStep). Only instant selectors
-// (hints.Range == 0) of subquery-free queries qualify: range selectors need
-// every raw sample, and subquery selectors evaluate at the subquery's own
-// step while hints carry the top-level step — the subquery-free proof
-// arrives as QueryTraits in the context. The first evaluation timestamp is
-// recovered as hints.Start + lookback - 1ms, inverting how the engine
-// derives hints.Start.
-func (q *querier) lastSamplePerStepFor(ctx context.Context, hints *storage.SelectHints) *lastSamplePerStep {
-	if hints == nil || hints.Range != 0 || hints.Start <= 0 {
-		return nil
-	}
-	traits, ok := prometheus.QueryTraitsFromContext(ctx)
-	if !ok || !traits.SubqueryFree {
-		return nil
-	}
-	firstEval := hints.Start + q.client.lookbackMs - 1
-	if firstEval > hints.End {
-		// Defensive: never anchor a bucket past the window.
-		firstEval = hints.End
-	}
-	return &lastSamplePerStep{firstEvalMs: firstEval, stepMs: hints.Step}
-}
-
-// fetchSamples runs the samples query for the matched series (see
-// buildSamplesQuery).
-func (q *querier) fetchSamples(ctx context.Context, start, end int64, matchers []*labels.Matcher, lookup *seriesLookup, lastPerStep *lastSamplePerStep) ([]*series, error) {
-	query, args, err := buildSamplesQuery(start, end, lookup.metricNames, matchers, lastPerStep)
-	if err != nil {
-		return nil, err
-	}
-	return q.client.selectSamples(ctx, query, args, lookup)
-}
-
-func (q *querier) selectStrings(ctx context.Context, fn, query string, args []any) ([]string, error) {
-	ctx = q.client.withContext(ctx, fn)
-	rows, err := q.client.telemetryStore.ClickhouseDB().Query(ctx, query, args...)
-	if err != nil {
-		return nil, err
-	}
-	defer rows.Close()
-
-	var out []string
-	var v string
-	for rows.Next() {
-		if err := rows.Scan(&v); err != nil {
-			return nil, err
-		}
-		out = append(out, v)
-	}
-	if err := rows.Err(); err != nil {
-		return nil, err
-	}
-	return out, nil
-}

pkg/prometheus/clickhouseprometheusv2/seriesset.go

@@ -1,184 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"sort"
-
-	"github.com/prometheus/prometheus/model/histogram"
-	"github.com/prometheus/prometheus/model/labels"
-	"github.com/prometheus/prometheus/storage"
-	"github.com/prometheus/prometheus/tsdb/chunkenc"
-	"github.com/prometheus/prometheus/util/annotations"
-)
-
-// series is one time series with samples as parallel slices ordered by
-// timestamp. Deliberately not storage.NewListSeries: that boxes every sample
-// as an interface value, a per-sample allocation this fetch path exists to
-// avoid.
-type series struct {
-	lset labels.Labels
-	ts   []int64
-	vs   []float64
-}
-
-var _ storage.Series = (*series)(nil)
-
-func (s *series) Labels() labels.Labels {
-	return s.lset
-}
-
-func (s *series) Iterator(it chunkenc.Iterator) chunkenc.Iterator {
-	if fit, ok := it.(*floatIterator); ok {
-		fit.reset(s)
-		return fit
-	}
-	fit := &floatIterator{}
-	fit.reset(s)
-	return fit
-}
-
-// floatIterator implements chunkenc.Iterator over a series' sample slices.
-type floatIterator struct {
-	s *series
-	i int
-}
-
-var _ chunkenc.Iterator = (*floatIterator)(nil)
-
-func (it *floatIterator) reset(s *series) {
-	it.s = s
-	it.i = -1
-}
-
-func (it *floatIterator) Next() chunkenc.ValueType {
-	it.i++
-	if it.i >= len(it.s.ts) {
-		return chunkenc.ValNone
-	}
-	return chunkenc.ValFloat
-}
-
-func (it *floatIterator) Seek(t int64) chunkenc.ValueType { //nolint:govet // stdmethods flags io.Seeker; this is chunkenc.Iterator's Seek
-	if it.i < 0 {
-		it.i = 0
-	}
-	if it.i >= len(it.s.ts) {
-		return chunkenc.ValNone
-	}
-	// The current position, once valid, must not move backwards.
-	if it.s.ts[it.i] >= t {
-		return chunkenc.ValFloat
-	}
-	it.i += sort.Search(len(it.s.ts)-it.i, func(j int) bool {
-		return it.s.ts[it.i+j] >= t
-	})
-	if it.i >= len(it.s.ts) {
-		return chunkenc.ValNone
-	}
-	return chunkenc.ValFloat
-}
-
-func (it *floatIterator) At() (int64, float64) {
-	return it.s.ts[it.i], it.s.vs[it.i]
-}
-
-func (it *floatIterator) AtHistogram(*histogram.Histogram) (int64, *histogram.Histogram) {
-	return 0, nil
-}
-
-func (it *floatIterator) AtFloatHistogram(*histogram.FloatHistogram) (int64, *histogram.FloatHistogram) {
-	return 0, nil
-}
-
-func (it *floatIterator) AtT() int64 {
-	return it.s.ts[it.i]
-}
-
-// AtST returns the current start timestamp; not tracked by this storage.
-func (it *floatIterator) AtST() int64 {
-	return 0
-}
-
-func (it *floatIterator) Err() error {
-	return nil
-}
-
-// seriesSet iterates a fully materialized, label-sorted list of series.
-type seriesSet struct {
-	series []*series
-	i      int
-}
-
-var _ storage.SeriesSet = (*seriesSet)(nil)
-
-func newSeriesSet(list []*series) *seriesSet {
-	return &seriesSet{series: list, i: -1}
-}
-
-func (s *seriesSet) Next() bool {
-	s.i++
-	return s.i < len(s.series)
-}
-
-func (s *seriesSet) At() storage.Series {
-	return s.series[s.i]
-}
-
-func (s *seriesSet) Err() error {
-	return nil
-}
-
-func (s *seriesSet) Warnings() annotations.Annotations {
-	return nil
-}
-
-// sortAndMerge orders series by label set and merges identical label sets
-// by timestamp (first sample wins ties): distinct fingerprints can carry
-// identical label sets, and the engine assumes storages never emit
-// duplicates.
-func sortAndMerge(list []*series) []*series {
-	if len(list) < 2 {
-		return list
-	}
-	sort.Slice(list, func(i, j int) bool {
-		return labels.Compare(list[i].lset, list[j].lset) < 0
-	})
-	out := list[:1]
-	for _, s := range list[1:] {
-		last := out[len(out)-1]
-		if labels.Compare(last.lset, s.lset) != 0 {
-			out = append(out, s)
-			continue
-		}
-		merged := mergeSamples(last, s)
-		out[len(out)-1] = merged
-	}
-	return out
-}
-
-func mergeSamples(a, b *series) *series {
-	ts := make([]int64, 0, len(a.ts)+len(b.ts))
-	vs := make([]float64, 0, len(a.ts)+len(b.ts))
-	i, j := 0, 0
-	for i < len(a.ts) && j < len(b.ts) {
-		switch {
-		case a.ts[i] < b.ts[j]:
-			ts = append(ts, a.ts[i])
-			vs = append(vs, a.vs[i])
-			i++
-		case a.ts[i] > b.ts[j]:
-			ts = append(ts, b.ts[j])
-			vs = append(vs, b.vs[j])
-			j++
-		default:
-			ts = append(ts, a.ts[i])
-			vs = append(vs, a.vs[i])
-			i++
-			j++
-		}
-	}
-	ts = append(ts, a.ts[i:]...)
-	vs = append(vs, a.vs[i:]...)
-	ts = append(ts, b.ts[j:]...)
-	vs = append(vs, b.vs[j:]...)
-	return &series{lset: a.lset, ts: ts, vs: vs}
-}

pkg/prometheus/clickhouseprometheusv2/sql.go

@@ -1,164 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"fmt"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/huandu/go-sqlbuilder"
-	"github.com/prometheus/prometheus/model/labels"
-)
-
-// buildSeriesQuery renders the series lookup: one row per matched fingerprint
-// with its labels.
-func buildSeriesQuery(start, end int64, matchers []*labels.Matcher) (string, []any, error) {
-	adjustedStart, table := timeSeriesTableFor(start, end)
-	sb := sqlbuilder.NewSelectBuilder()
-	sb.Select("fingerprint", "any(labels)")
-	sb.From(fmt.Sprintf("%s.%s", databaseName, table))
-	if err := applySeriesConditions(sb, adjustedStart, end, matchers); err != nil {
-		return "", nil, err
-	}
-	sb.GroupBy("fingerprint")
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	return query, args, nil
-}
-
-// buildSamplesQuery renders the samples fetch for the matched series: a
-// semi-join re-runs the series predicates against the shard-local series
-// table (complete by fingerprint co-locality, see localTimeSeriesTable — a
-// GLOBAL broadcast would ship the matched set to every shard, and ClickHouse
-// materializes the subquery's set per shard before the scan, so it still
-// engages the fingerprint primary-key column). metricNames (observed on the
-// matched series when the selector had no __name__ equality) narrows the
-// primary-key scan. A non-nil lastPerStep groups to the last sample per
-// step bucket.
-func buildSamplesQuery(start, end int64, metricNames []string, matchers []*labels.Matcher, lastPerStep *lastSamplePerStep) (string, []any, error) {
-	sb := sqlbuilder.NewSelectBuilder()
-	if lastPerStep != nil {
-		// Aliases must not shadow source columns: ClickHouse resolves aliases
-		// in WHERE too, and "max(unix_milli) AS unix_milli" would put an
-		// aggregate into the WHERE clause (error 184).
-		sb.Select("fingerprint", "max(unix_milli) AS ts", "argMax(value, unix_milli) AS val", "argMax(flags, unix_milli) AS fl")
-	} else {
-		sb.Select("fingerprint", "unix_milli", "value", "flags")
-	}
-	sb.From(fmt.Sprintf("%s.%s", databaseName, distributedSamplesV4))
-
-	switch len(metricNames) {
-	case 0:
-		// No name constraint derivable; the primary-key prefix goes unused.
-	case 1:
-		sb.Where(sb.EQ("metric_name", metricNames[0]))
-	default:
-		sb.Where(sb.In("metric_name", sqlbuilder.List(metricNames)))
-	}
-	// Semantically redundant (the fingerprints already come from these
-	// temporalities) but engages the leading primary-key column.
-	sb.Where("temporality IN ['Cumulative', 'Unspecified']")
-	sub := sqlbuilder.NewSelectBuilder()
-	sub.Select("fingerprint")
-	adjustedStart, table := timeSeriesTableFor(start, end)
-	sub.From(fmt.Sprintf("%s.%s", databaseName, localTimeSeriesTable(table)))
-	if err := applySeriesConditions(sub, adjustedStart, end, matchers); err != nil {
-		return "", nil, err
-	}
-	sb.Where(sb.In("fingerprint", sub))
-	sb.Where(sb.GTE("unix_milli", start), sb.LTE("unix_milli", end))
-
-	if lastPerStep != nil {
-		sb.GroupBy("fingerprint")
-		if expr := lastPerStep.bucketExpr(); expr != "" {
-			sb.GroupBy(expr)
-		}
-		sb.OrderBy("fingerprint", "ts")
-	} else {
-		sb.OrderBy("fingerprint", "unix_milli")
-	}
-
-	query, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-	return query, args, nil
-}
-
-// applySeriesConditions adds the WHERE conditions of a series table scan:
-// __name__ matchers (all four types) translate to the metric_name column,
-// every other matcher to a JSONExtractString condition on the labels column.
-// An equality matcher against "" matches series without the label, mirroring
-// PromQL, because JSONExtractString returns "" for missing keys. Regexes are
-// anchored: PromQL matchers match the whole value, ClickHouse match()
-// searches for a substring.
-func applySeriesConditions(sb *sqlbuilder.SelectBuilder, start, end int64, matchers []*labels.Matcher) error {
-	for _, m := range matchers {
-		if m.Name != metricNameLabel {
-			continue
-		}
-		switch m.Type {
-		case labels.MatchEqual:
-			sb.Where(sb.EQ("metric_name", m.Value))
-		case labels.MatchNotEqual:
-			sb.Where(sb.NE("metric_name", m.Value))
-		case labels.MatchRegexp:
-			sb.Where(fmt.Sprintf("match(metric_name, %s)", sb.Var(anchorRegex(m.Value))))
-		case labels.MatchNotRegexp:
-			sb.Where(fmt.Sprintf("NOT match(metric_name, %s)", sb.Var(anchorRegex(m.Value))))
-		default:
-			return errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported matcher type %q for __name__", m.Type)
-		}
-	}
-
-	sb.Where("temporality IN ['Cumulative', 'Unspecified']")
-	// Inclusive upper bound: registration rows are hour-floored (and 6h/1d/1w
-	// for the rollup tables) by the exporter, so a series first registered in
-	// the bucket starting exactly at `end` would otherwise be invisible while
-	// its samples (<= end) are in range.
-	sb.Where(sb.GTE("unix_milli", start), sb.LTE("unix_milli", end))
-
-	for _, m := range matchers {
-		if m.Name == metricNameLabel {
-			continue
-		}
-		switch m.Type {
-		case labels.MatchEqual:
-			sb.Where(fmt.Sprintf("JSONExtractString(labels, %s) = %s", sb.Var(m.Name), sb.Var(m.Value)))
-		case labels.MatchNotEqual:
-			sb.Where(fmt.Sprintf("JSONExtractString(labels, %s) != %s", sb.Var(m.Name), sb.Var(m.Value)))
-		case labels.MatchRegexp:
-			sb.Where(fmt.Sprintf("match(JSONExtractString(labels, %s), %s)", sb.Var(m.Name), sb.Var(anchorRegex(m.Value))))
-		case labels.MatchNotRegexp:
-			sb.Where(fmt.Sprintf("NOT match(JSONExtractString(labels, %s), %s)", sb.Var(m.Name), sb.Var(anchorRegex(m.Value))))
-		default:
-			return errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported matcher type %q", m.Type)
-		}
-	}
-
-	return nil
-}
-
-// anchorRegex turns a PromQL regex into its fully-anchored form (see
-// applySeriesConditions).
-func anchorRegex(v string) string {
-	return "^(?:" + v + ")$"
-}
-
-// lastSamplePerStep reduces an instant-selector fetch to the last sample of
-// each step bucket: bucket 0 is (start, firstEval], bucket i is
-// (firstEval+(i-1)·step, firstEval+i·step]. Anchoring buckets at the first
-// evaluation timestamp makes every bucket boundary an evaluation timestamp,
-// so a non-final sample of a bucket can never be the latest sample in any
-// (t-lookback, t] the engine resolves — the reduction is lossless. Real
-// timestamps are preserved, so the engine's own lookback and staleness
-// handling remain exact.
-type lastSamplePerStep struct {
-	firstEvalMs int64
-	stepMs      int64
-}
-
-func (t *lastSamplePerStep) bucketExpr() string {
-	if t.stepMs <= 0 {
-		// Instant query: a single evaluation at firstEval; one bucket.
-		return ""
-	}
-	return fmt.Sprintf(
-		"if(unix_milli <= %d, 0, intDiv(unix_milli - %d - 1, %d) + 1)",
-		t.firstEvalMs, t.firstEvalMs, t.stepMs,
-	)
-}

pkg/prometheus/clickhouseprometheusv2/sql_test.go

@@ -1,139 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"testing"
-	"time"
-
-	"github.com/prometheus/prometheus/model/labels"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-func mustMatcher(t *testing.T, mt labels.MatchType, name, value string) *labels.Matcher {
-	t.Helper()
-	m, err := labels.NewMatcher(mt, name, value)
-	require.NoError(t, err)
-	return m
-}
-
-func TestTimeSeriesTableFor(t *testing.T) {
-	base := time.Date(2026, 7, 10, 3, 27, 0, 0, time.UTC).UnixMilli()
-
-	tests := []struct {
-		name      string
-		span      time.Duration
-		wantTable string
-		roundTo   time.Duration
-	}{
-		{"under 6h uses hourly table", 2 * time.Hour, distributedTimeSeriesV4, time.Hour},
-		{"under 1d uses 6h table", 12 * time.Hour, distributedTimeSeriesV46hrs, 6 * time.Hour},
-		{"under 1w uses 1d table", 3 * 24 * time.Hour, distributedTimeSeriesV41day, 24 * time.Hour},
-		{"over 1w uses 1w table", 10 * 24 * time.Hour, distributedTimeSeriesV41week, 7 * 24 * time.Hour},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			start, table := timeSeriesTableFor(base, base+tt.span.Milliseconds())
-			assert.Equal(t, tt.wantTable, table)
-			assert.Zero(t, start%tt.roundTo.Milliseconds())
-			assert.LessOrEqual(t, start, base)
-		})
-	}
-}
-
-func TestBuildSeriesQuery(t *testing.T) {
-	start := int64(1_700_000_000_000)
-	end := start + time.Hour.Milliseconds()
-	// The series table window rounds down to the table's bucket boundary.
-	adjustedStart := start - (start % time.Hour.Milliseconds())
-
-	t.Run("equality name and label matchers", func(t *testing.T) {
-		query, args, err := buildSeriesQuery(start, end, []*labels.Matcher{
-			mustMatcher(t, labels.MatchEqual, "__name__", "http_requests_total"),
-			mustMatcher(t, labels.MatchEqual, "job", "api"),
-		})
-		require.NoError(t, err)
-		assert.Equal(t,
-			"SELECT fingerprint, any(labels) FROM signoz_metrics.distributed_time_series_v4 WHERE metric_name = ? AND temporality IN ['Cumulative', 'Unspecified'] AND unix_milli >= ? AND unix_milli <= ? AND JSONExtractString(labels, ?) = ? GROUP BY fingerprint",
-			query,
-		)
-		assert.Equal(t, []any{"http_requests_total", adjustedStart, end, "job", "api"}, args)
-	})
-
-	t.Run("regex matchers are anchored", func(t *testing.T) {
-		_, args, err := buildSeriesQuery(start, end, []*labels.Matcher{
-			mustMatcher(t, labels.MatchEqual, "__name__", "up"),
-			mustMatcher(t, labels.MatchRegexp, "instance", "prod.*"),
-			mustMatcher(t, labels.MatchNotRegexp, "env", "dev|test"),
-		})
-		require.NoError(t, err)
-		assert.Equal(t, []any{"up", adjustedStart, end, "instance", "^(?:prod.*)$", "env", "^(?:dev|test)$"}, args)
-	})
-
-	t.Run("regex name matcher uses metric_name column", func(t *testing.T) {
-		query, args, err := buildSeriesQuery(start, end, []*labels.Matcher{
-			mustMatcher(t, labels.MatchRegexp, "__name__", "node_cpu.*|node_memory.*"),
-		})
-		require.NoError(t, err)
-		assert.Contains(t, query, "match(metric_name, ?)")
-		assert.NotContains(t, query, "JSONExtractString")
-		assert.Equal(t, []any{"^(?:node_cpu.*|node_memory.*)$", adjustedStart, end}, args)
-	})
-
-	t.Run("no name matcher omits metric_name condition", func(t *testing.T) {
-		query, _, err := buildSeriesQuery(start, end, []*labels.Matcher{
-			mustMatcher(t, labels.MatchEqual, "job", "api"),
-		})
-		require.NoError(t, err)
-		assert.NotContains(t, query, "metric_name")
-	})
-}
-
-func TestBuildSamplesQuery(t *testing.T) {
-	start := int64(1_700_000_000_000)
-	end := start + time.Hour.Milliseconds()
-	adjustedStart := start - (start % time.Hour.Milliseconds())
-	matchers := []*labels.Matcher{
-		mustMatcher(t, labels.MatchEqual, "__name__", "up"),
-		mustMatcher(t, labels.MatchEqual, "job", "api"),
-	}
-
-	t.Run("raw fetch filters by a shard-local semi-join", func(t *testing.T) {
-		query, args, err := buildSamplesQuery(start, end, []string{"up"}, matchers, nil)
-		require.NoError(t, err)
-		assert.Contains(t, query, "fingerprint IN (SELECT fingerprint FROM signoz_metrics.time_series_v4 WHERE ")
-		assert.NotContains(t, query, "GLOBAL IN")
-		assert.Contains(t, query, "ORDER BY fingerprint, unix_milli")
-		// Args follow placeholder order: samples metric name, the semi-join's
-		// series predicates, then the samples window bounds.
-		assert.Equal(t, []any{"up", "up", adjustedStart, end, "job", "api", start, end}, args)
-	})
-
-	t.Run("last-sample-per-step groups by step bucket anchored at first eval", func(t *testing.T) {
-		lastPerStep := &lastSamplePerStep{firstEvalMs: start + 299_999, stepMs: 60_000}
-		query, _, err := buildSamplesQuery(start, end, []string{"up"}, matchers, lastPerStep)
-		require.NoError(t, err)
-		assert.Contains(t, query, "argMax(value, unix_milli) AS val")
-		assert.Contains(t, query, "argMax(flags, unix_milli) AS fl")
-		assert.Contains(t, query, "GROUP BY fingerprint, if(unix_milli <= 1700000299999, 0, intDiv(unix_milli - 1700000299999 - 1, 60000) + 1)")
-		assert.Contains(t, query, "ORDER BY fingerprint, ts")
-		// Aliases must not shadow the source columns referenced in WHERE.
-		assert.NotContains(t, query, "AS unix_milli")
-		assert.NotContains(t, query, "AS value")
-		assert.NotContains(t, query, "AS flags")
-	})
-
-	t.Run("instant query keeps one bucket", func(t *testing.T) {
-		lastPerStep := &lastSamplePerStep{firstEvalMs: end, stepMs: 0}
-		query, _, err := buildSamplesQuery(start, end, []string{"up"}, matchers, lastPerStep)
-		require.NoError(t, err)
-		assert.Contains(t, query, "GROUP BY fingerprint ORDER BY fingerprint, ts")
-		assert.NotContains(t, query, "intDiv")
-	})
-
-	t.Run("multiple metric names from regex selector", func(t *testing.T) {
-		query, args, err := buildSamplesQuery(start, end, []string{"node_cpu", "node_memory"}, matchers, nil)
-		require.NoError(t, err)
-		assert.Contains(t, query, "metric_name IN (?, ?)")
-		assert.Equal(t, []any{"node_cpu", "node_memory", "up", adjustedStart, end, "job", "api", start, end}, args)
-	})
-}

pkg/prometheus/clickhouseprometheusv2/tables.go

@@ -1,70 +0,0 @@
-package clickhouseprometheusv2
-
-import "time"
-
-// TODO(srikanthccv): consolidate the metrics table names and the
-// window-to-table selection across the query builders (telemetrymetrics)
-// and the prometheus providers instead of each package carrying its own
-// copy.
-
-const (
-	// metricNameLabel is the reserved PromQL label holding the metric name.
-	metricNameLabel string = "__name__"
-
-	databaseName                 string = "signoz_metrics"
-	distributedTimeSeriesV4      string = "distributed_time_series_v4"
-	distributedTimeSeriesV46hrs  string = "distributed_time_series_v4_6hrs"
-	distributedTimeSeriesV41day  string = "distributed_time_series_v4_1day"
-	distributedTimeSeriesV41week string = "distributed_time_series_v4_1week"
-	distributedSamplesV4         string = "distributed_samples_v4"
-
-	localTimeSeriesV4      string = "time_series_v4"
-	localTimeSeriesV46hrs  string = "time_series_v4_6hrs"
-	localTimeSeriesV41day  string = "time_series_v4_1day"
-	localTimeSeriesV41week string = "time_series_v4_1week"
-)
-
-// localTimeSeriesTable maps a distributed time series table to its shard-local
-// table. Samples and time series shard on the same key
-// (cityHash64(env, temporality, metric_name, fingerprint)), so a query whose
-// top-level FROM is the distributed samples table can join or semi-join the
-// local time series table inside each shard: the shard rewrite runs the
-// subquery against the shard's own series rows, which are exactly the series
-// of the shard's samples. No broadcast, no initiator-side join.
-func localTimeSeriesTable(distributed string) string {
-	switch distributed {
-	case distributedTimeSeriesV46hrs:
-		return localTimeSeriesV46hrs
-	case distributedTimeSeriesV41day:
-		return localTimeSeriesV41day
-	case distributedTimeSeriesV41week:
-		return localTimeSeriesV41week
-	default:
-		return localTimeSeriesV4
-	}
-}
-
-var (
-	oneHourInMilliseconds  = time.Hour.Milliseconds()
-	sixHoursInMilliseconds = time.Hour.Milliseconds() * 6
-	oneDayInMilliseconds   = time.Hour.Milliseconds() * 24
-	oneWeekInMilliseconds  = time.Hour.Milliseconds() * 24 * 7
-)
-
-// timeSeriesTableFor returns the adjusted start and the time series table for
-// the window. Time series tables hold one row per (fingerprint, bucket), with
-// bucket granularities of 1h, 6h, 1d and 1w; the start is rounded down to the
-// bucket boundary so a window beginning mid-bucket still matches the bucket's
-// row.
-func timeSeriesTableFor(start, end int64) (int64, string) {
-	switch {
-	case end-start < sixHoursInMilliseconds:
-		return start - (start % oneHourInMilliseconds), distributedTimeSeriesV4
-	case end-start < oneDayInMilliseconds:
-		return start - (start % sixHoursInMilliseconds), distributedTimeSeriesV46hrs
-	case end-start < oneWeekInMilliseconds:
-		return start - (start % oneDayInMilliseconds), distributedTimeSeriesV41day
-	default:
-		return start - (start % oneWeekInMilliseconds), distributedTimeSeriesV41week
-	}
-}

pkg/prometheus/clickhouseprometheusv2/transpiler.go

@@ -1,492 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"fmt"
-	"strings"
-
-	"github.com/prometheus/prometheus/model/labels"
-	"github.com/prometheus/prometheus/promql/parser"
-)
-
-// The compiler turns PromQL subtrees into single ClickHouse queries built on
-// the timeSeries*ToGrid aggregate functions (CH >= 25.6), whose semantics
-// were verified against this repo's vendored engine: exact extrapolatedRate
-// behavior including counter resets, the counter zero-point clamp, the
-// 1.1x-average extrapolation threshold, left-open windows, the >= 2 samples
-// rule, stale-marker shadowing, and millisecond grid starts. Sample rows
-// never leave ClickHouse: one row per output series comes back, holding the
-// whole grid as an array.
-//
-// Scope (the allowlist): an optional sum/min/max/avg/count by/without
-// aggregation over a core unit — a rate/increase/delta/irate/idelta range
-// selection, an instant vector selection, or an avg/min/max/sum/count/last
-// _over_time window — plus number-literal arithmetic/comparisons and unary
-// minus on top. Units inside fixed-resolution subqueries evaluate on the
-// subquery's own grid. Everything else either falls back to the engine over
-// this package's querier, or — when a transpilable subtree sits under a
-// non-transpilable node — runs hybrid: the subtree's grids are computed in
-// ClickHouse and substituted into the engine as synthetic series (see
-// compiler_exec.go). See doc.go for the fallback list and the reasons behind
-// each entry.
-
-// rangeFn is a transpilable range-vector function.
-type rangeFn string
-
-const (
-	fnRate     rangeFn = "rate"
-	fnIncrease rangeFn = "increase"
-	fnDelta    rangeFn = "delta"
-	fnIRate    rangeFn = "irate"
-	fnIDelta   rangeFn = "idelta"
-)
-
-var gridFunction = map[rangeFn]string{
-	fnRate:     "timeSeriesRateToGrid",
-	fnIncrease: "timeSeriesRateToGrid", // increase == rate * range seconds, exactly (same factor algebra)
-	fnDelta:    "timeSeriesDeltaToGrid",
-	fnIRate:    "timeSeriesInstantRateToGrid",
-	fnIDelta:   "timeSeriesInstantDeltaToGrid",
-}
-
-// scalarOp is one number-literal arithmetic or comparison applied to a
-// compiled vector, evaluated in Go during assembly with the same float64
-// operations the engine uses.
-type scalarOp struct {
-	op           parser.ItemType
-	scalar       float64
-	scalarOnLeft bool
-	returnBool   bool
-}
-
-// isComparison reports whether the op is a filtering/bool comparison, which
-// preserves the metric name (arithmetic drops it).
-func (o scalarOp) isComparison() bool {
-	return o.op.IsComparisonOperator()
-}
-
-// unitKind is the selector shape at the bottom of a core unit.
-type unitKind int
-
-const (
-	// unitRange: rate/increase/delta/irate/idelta over a matrix selector.
-	unitRange unitKind = iota
-	// unitInstant: a plain vector selector resolved per grid point with
-	// lookback and stale-marker shadowing.
-	unitInstant
-	// unitOverTime: avg/min/max/sum/count/last_over_time over a matrix
-	// selector (aggregation over the window's samples, stale rows excluded).
-	unitOverTime
-)
-
-// coreUnit is one transpilable subtree: selector [-> range function] ->
-// optional aggregation -> scalar op pipeline.
-type coreUnit struct {
-	kind     unitKind
-	matchers []*labels.Matcher
-	offsetMs int64
-	fn       rangeFn // unitRange
-	overFn   string  // unitOverTime: avg|min|max|sum|count|last
-	rangeMs  int64   // unitRange/unitOverTime window
-
-	hasAgg   bool
-	aggOp    parser.ItemType // SUM MIN MAX AVG COUNT
-	by       bool
-	grouping []string
-
-	ops []scalarOp
-}
-
-// keepsName reports whether the unit's output series keep their real
-// __name__: bare/comparison-filtered instant selectors and last_over_time do
-// (it returns the raw sample, name included); range functions, the other
-// *_over_time functions, aggregations, arithmetic and bool comparisons all
-// drop it — a bool comparison returns 0/1, not the sample, so the engine
-// drops the name there too. Units that keep the name cannot be substituted
-// as synthetic series in hybrid plans — the synthetic name would replace
-// the real one — but transpile fine as full plans, where assembly emits the
-// real names.
-func (u *coreUnit) keepsName() bool {
-	nameKeepingSelector := u.kind == unitInstant || (u.kind == unitOverTime && u.overFn == "last")
-	if !nameKeepingSelector || u.hasAgg {
-		return false
-	}
-	for _, op := range u.ops {
-		if !op.isComparison() || op.returnBool {
-			return false
-		}
-	}
-	return true
-}
-
-// gridContext is the evaluation grid a unit computes on. The query grid for
-// top-level units; for units inside subqueries, the subquery's own grid:
-// epoch-aligned multiples of its resolution covering the subquery window,
-// exactly as the engine derives it (engine.go, *parser.SubqueryExpr case).
-type gridContext struct {
-	startMs int64
-	endMs   int64
-	stepMs  int64
-}
-
-// subqueryGrid derives the inner grid for a subquery evaluated on outer:
-// interval S, end = outer end − offset, start = first multiple of S strictly
-// greater than outer start − offset − range.
-func subqueryGrid(outer gridContext, rangeMs, stepMs, offsetMs int64) gridContext {
-	lower := outer.startMs - offsetMs - rangeMs
-	start := stepMs * (lower / stepMs)
-	if start <= lower {
-		start += stepMs
-	}
-	return gridContext{startMs: start, endMs: outer.endMs - offsetMs, stepMs: stepMs}
-}
-
-// transpiledUnit is a coreUnit scheduled for execution, named for hybrid
-// substitution, carrying the grid it evaluates on.
-type transpiledUnit struct {
-	core coreUnit
-	name string // __signoz_transpiled_<n>__
-	grid gridContext
-}
-
-// transpilePlan is the outcome of classifying a query.
-type transpilePlan struct {
-	units []*transpiledUnit
-	grid  gridContext // the query's top-level grid
-	// full is set when the entire query is units[0]; otherwise rewritten
-	// holds the query with each unit replaced by a synthetic selector, to be
-	// evaluated by the engine over a hybrid storage.
-	full      bool
-	rewritten string
-}
-
-const syntheticNamePrefix = "__signoz_transpiled_"
-
-func syntheticName(i int) string {
-	return fmt.Sprintf("%s%d__", syntheticNamePrefix, i)
-}
-
-// classifyCore matches a subtree against the transpilable core shape.
-// stepMs gates second-granularity: the grid functions take whole-second step
-// and window parameters (grid *starts* are millisecond-precise).
-func classifyCore(node parser.Expr, stepMs int64) (*coreUnit, bool) {
-	unit := &coreUnit{}
-
-	expr := node
-	// Peel scalar ops and parens off the top, outermost first; ops apply in
-	// evaluation order, so prepend while peeling.
-	for {
-		switch n := expr.(type) {
-		case *parser.ParenExpr:
-			expr = n.Expr
-			continue
-		case *parser.UnaryExpr:
-			if n.Op != parser.SUB {
-				expr = n.Expr // unary '+' is a no-op
-				continue
-			}
-			// -x == -1 * x for every float64 (incl. NaN and signed zero).
-			unit.ops = append([]scalarOp{{op: parser.MUL, scalar: -1}}, unit.ops...)
-			expr = n.Expr
-			continue
-		case *parser.StepInvariantExpr:
-			// @-pinned expressions evaluate on a different grid.
-			return nil, false
-		case *parser.BinaryExpr:
-			lit, litOnLeft, ok := numberLiteralSide(n)
-			if !ok {
-				return nil, false
-			}
-			if !n.Op.IsOperator() && !n.Op.IsComparisonOperator() {
-				return nil, false
-			}
-			if n.Op == parser.ATAN2 {
-				// atan2 is arithmetic in PromQL but rarely used; keep the
-				// allowlist tight.
-				return nil, false
-			}
-			returnBool := n.ReturnBool
-			unit.ops = append([]scalarOp{{op: n.Op, scalar: lit, scalarOnLeft: litOnLeft, returnBool: returnBool}}, unit.ops...)
-			if litOnLeft {
-				expr = n.RHS
-			} else {
-				expr = n.LHS
-			}
-			continue
-		}
-		break
-	}
-
-	// Optional aggregation.
-	if agg, ok := expr.(*parser.AggregateExpr); ok {
-		switch agg.Op {
-		case parser.SUM, parser.MIN, parser.MAX, parser.AVG, parser.COUNT:
-		default:
-			return nil, false
-		}
-		for _, g := range agg.Grouping {
-			if g == metricNameLabel {
-				// by(__name__)/without(__name__) over synthetic or compiled
-				// output needs name bookkeeping the compiler doesn't do.
-				return nil, false
-			}
-		}
-		unit.hasAgg = true
-		unit.aggOp = agg.Op
-		unit.by = !agg.Without
-		unit.grouping = agg.Grouping
-		expr = agg.Expr
-		for {
-			if p, ok := expr.(*parser.ParenExpr); ok {
-				expr = p.Expr
-				continue
-			}
-			break
-		}
-	}
-
-	// The grid functions take whole-second steps; stepMs == 0 is an instant
-	// query (single-point grid).
-	if stepMs < 0 || stepMs%1000 != 0 {
-		return nil, false
-	}
-
-	// Bare instant selector: resolved per grid point with lookback and
-	// stale-marker shadowing (see compiler_sql.go).
-	if vs, ok := expr.(*parser.VectorSelector); ok {
-		// A duration expression (offset step(), offset range()*2, ...) is
-		// resolved into OriginalOffset only at evaluation time; at
-		// classification time the field still holds its zero value, so
-		// transpiling would silently use the wrong offset.
-		if vs.Timestamp != nil || vs.StartOrEnd != 0 || vs.Anchored || vs.Smoothed || vs.OriginalOffsetExpr != nil {
-			return nil, false
-		}
-		offsetMs := vs.OriginalOffset.Milliseconds()
-		if offsetMs < 0 {
-			return nil, false
-		}
-		unit.kind = unitInstant
-		unit.offsetMs = offsetMs
-		unit.matchers = vs.LabelMatchers
-		return unit, true
-	}
-
-	// Range or *_over_time function over a plain matrix selector.
-	call, ok := expr.(*parser.Call)
-	if !ok {
-		return nil, false
-	}
-	var fn rangeFn
-	var overFn string
-	switch call.Func.Name {
-	case "rate":
-		fn = fnRate
-	case "increase":
-		fn = fnIncrease
-	case "delta":
-		fn = fnDelta
-	case "irate":
-		fn = fnIRate
-	case "idelta":
-		fn = fnIDelta
-	case "avg_over_time", "min_over_time", "max_over_time", "sum_over_time", "count_over_time", "last_over_time":
-		overFn = strings.TrimSuffix(call.Func.Name, "_over_time")
-	default:
-		return nil, false
-	}
-	if len(call.Args) != 1 {
-		return nil, false
-	}
-	ms, ok := call.Args[0].(*parser.MatrixSelector)
-	if !ok {
-		return nil, false
-	}
-	vs, ok := ms.VectorSelector.(*parser.VectorSelector)
-	if !ok {
-		return nil, false
-	}
-	// Duration expressions resolve at evaluation time (see the instant
-	// selector case above); Range/OriginalOffset would be read as zero here.
-	if vs.Timestamp != nil || vs.StartOrEnd != 0 || vs.Anchored || vs.Smoothed || vs.OriginalOffsetExpr != nil || ms.RangeExpr != nil {
-		return nil, false
-	}
-
-	rangeMs := ms.Range.Milliseconds()
-	offsetMs := vs.OriginalOffset.Milliseconds()
-	if rangeMs <= 0 || rangeMs%1000 != 0 || offsetMs < 0 {
-		return nil, false
-	}
-
-	if overFn != "" {
-		unit.kind = unitOverTime
-		unit.overFn = overFn
-	} else {
-		unit.kind = unitRange
-		unit.fn = fn
-	}
-	unit.rangeMs = rangeMs
-	unit.offsetMs = offsetMs
-	unit.matchers = vs.LabelMatchers
-	return unit, true
-}
-
-// numberLiteralSide returns the number literal on one side of a binary
-// expression (peeling parens and unary minus), and which side it is on.
-func numberLiteralSide(b *parser.BinaryExpr) (float64, bool, bool) {
-	if v, ok := literalValue(b.LHS); ok {
-		return v, true, true
-	}
-	if v, ok := literalValue(b.RHS); ok {
-		return v, false, true
-	}
-	return 0, false, false
-}
-
-func literalValue(e parser.Expr) (float64, bool) {
-	neg := false
-	for {
-		switch n := e.(type) {
-		case *parser.ParenExpr:
-			e = n.Expr
-			continue
-		case *parser.StepInvariantExpr:
-			e = n.Expr
-			continue
-		case *parser.UnaryExpr:
-			if n.Op == parser.SUB {
-				neg = !neg
-			}
-			e = n.Expr
-			continue
-		case *parser.NumberLiteral:
-			if neg {
-				return -n.Val, true
-			}
-			return n.Val, true
-		default:
-			return 0, false
-		}
-	}
-}
-
-// classify builds the compile plan for a query: full when the root is a core
-// unit, hybrid when core units sit strictly below the root (including inside
-// fixed-resolution subqueries, computed on the subquery grid), none
-// otherwise.
-func classify(root parser.Expr, grid gridContext) (*transpilePlan, bool) {
-	if unit, ok := classifyCore(root, grid.stepMs); ok {
-		return &transpilePlan{
-			units: []*transpiledUnit{{core: *unit, name: syntheticName(0), grid: grid}},
-			grid:  grid,
-			full:  true,
-		}, true
-	}
-
-	plan := &transpilePlan{grid: grid}
-	rewritten := rewrite(root, grid, plan, false)
-	if len(plan.units) == 0 {
-		return nil, false
-	}
-	plan.rewritten = rewritten.String()
-	return plan, true
-}
-
-// rewrite walks top-down replacing maximal transpilable subtrees with synthetic
-// vector selectors. nameSensitive marks scopes where an ancestor's semantics
-// depend on __name__ (grouping or vector matching on it): synthetic series
-// carry a synthetic __name__, so substitution there would change results.
-// Fixed-resolution subqueries recurse with the subquery's own grid; scopes
-// whose evaluation grid is unknowable (@-pinned, default-resolution
-// subqueries) are not entered.
-func rewrite(node parser.Expr, grid gridContext, plan *transpilePlan, nameSensitive bool) parser.Expr {
-	if node == nil {
-		return nil
-	}
-
-	if !nameSensitive {
-		// Units whose output keeps the real __name__ (bare instant selectors)
-		// cannot be substituted: the synthetic name would replace it in the
-		// engine's output. They still compile as full plans.
-		if unit, ok := classifyCore(node, grid.stepMs); ok && !unit.keepsName() {
-			cu := &transpiledUnit{core: *unit, name: syntheticName(len(plan.units)), grid: grid}
-			plan.units = append(plan.units, cu)
-			return &parser.VectorSelector{
-				Name: cu.name,
-				LabelMatchers: []*labels.Matcher{
-					labels.MustNewMatcher(labels.MatchEqual, metricNameLabel, cu.name),
-				},
-				PosRange: node.PositionRange(),
-			}
-		}
-	}
-
-	switch n := node.(type) {
-	case *parser.ParenExpr:
-		n.Expr = rewrite(n.Expr, grid, plan, nameSensitive)
-	case *parser.UnaryExpr:
-		n.Expr = rewrite(n.Expr, grid, plan, nameSensitive)
-	case *parser.AggregateExpr:
-		sensitive := nameSensitive || groupingUsesName(n.Grouping)
-		n.Expr = rewrite(n.Expr, grid, plan, sensitive)
-		// n.Param is a scalar/string; nothing transpilable inside for our core.
-	case *parser.Call:
-		for i, arg := range n.Args {
-			n.Args[i] = rewrite(arg, grid, plan, nameSensitive)
-		}
-	case *parser.BinaryExpr:
-		sensitive := nameSensitive || vectorMatchingUsesName(n.VectorMatching)
-		n.LHS = rewrite(n.LHS, grid, plan, sensitive)
-		n.RHS = rewrite(n.RHS, grid, plan, sensitive)
-	case *parser.SubqueryExpr:
-		// The alert-smoothing idiom fn_over_time((expr)[R:S]) dominates real
-		// rule fleets; inner units evaluate on the subquery grid, and the
-		// engine does the smoothing over the synthetic series. Requires an
-		// explicit whole-second resolution (S == 0 needs the engine's
-		// default-interval function) and no @ pinning.
-		stepMs := n.Step.Milliseconds()
-		rangeMs := n.Range.Milliseconds()
-		offsetMs := n.OriginalOffset.Milliseconds()
-		if n.Timestamp == nil && n.StartOrEnd == 0 &&
-			n.RangeExpr == nil && n.StepExpr == nil && n.OriginalOffsetExpr == nil &&
-			stepMs > 0 && stepMs%1000 == 0 && rangeMs%1000 == 0 && offsetMs >= 0 {
-			inner := subqueryGrid(grid, rangeMs, stepMs, offsetMs)
-			n.Expr = rewrite(n.Expr, inner, plan, nameSensitive)
-		}
-	case *parser.StepInvariantExpr, *parser.MatrixSelector,
-		*parser.VectorSelector, *parser.NumberLiteral, *parser.StringLiteral:
-		// Leaves, or scopes substitution must not enter.
-	}
-	return node
-}
-
-func groupingUsesName(grouping []string) bool {
-	for _, g := range grouping {
-		if g == metricNameLabel {
-			return true
-		}
-	}
-	return false
-}
-
-func vectorMatchingUsesName(vm *parser.VectorMatching) bool {
-	if vm == nil {
-		return false
-	}
-	for _, l := range append(append([]string{}, vm.MatchingLabels...), vm.Include...) {
-		if l == metricNameLabel {
-			return true
-		}
-	}
-	// Default (all-labels) matching ignores __name__, and by()/ignoring()
-	// lists were checked above.
-	return false
-}
-
-// isSyntheticSelector reports whether matchers target a compiled unit.
-func isSyntheticSelector(matchers []*labels.Matcher) (string, bool) {
-	for _, m := range matchers {
-		if m.Name == metricNameLabel && m.Type == labels.MatchEqual && strings.HasPrefix(m.Value, syntheticNamePrefix) {
-			return m.Value, true
-		}
-	}
-	return "", false
-}

pkg/prometheus/clickhouseprometheusv2/transpiler_corpus_test.go

@@ -1,161 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"bufio"
-	"encoding/json"
-	"fmt"
-	"os"
-	"regexp"
-	"sort"
-	"strings"
-	"testing"
-
-	"github.com/prometheus/prometheus/promql/parser"
-	"github.com/stretchr/testify/require"
-)
-
-// TestClassifyCorpus measures real-workload compiler coverage: it classifies
-// every query of a JSON-lines corpus (one JSON-encoded PromQL string per
-// line) with the live classifier and reports full / hybrid / fallback
-// shares. Skipped unless PROMQL_CORPUS points to one or more files
-// (comma-separated). Dashboard template variables are substituted with
-// placeholder values before parsing, mirroring the production render step.
-//
-//	PROMQL_CORPUS=corpus-a.jsonl,corpus-b.jsonl go test -run TestClassifyCorpus -v
-func TestClassifyCorpus(t *testing.T) {
-	corpus := os.Getenv("PROMQL_CORPUS")
-	if corpus == "" {
-		t.Skip("PROMQL_CORPUS not set")
-	}
-
-	varRe := regexp.MustCompile(`\{\{\s*\.?[\w.]+\s*\}\}|\[\[\s*[\w.]+\s*\]\]|\$[\w.]+`)
-	promParser := parser.NewParser(parser.Options{})
-
-	for _, path := range strings.Split(corpus, ",") {
-		f, err := os.Open(path)
-		require.NoError(t, err)
-
-		var full, hybrid, fallbackInstant, fallbackOther, parseErrs int
-		fallbackReasons := map[string]int{}
-
-		scanner := bufio.NewScanner(f)
-		scanner.Buffer(make([]byte, 1024*1024), 1024*1024)
-		for scanner.Scan() {
-			var query string
-			require.NoError(t, json.Unmarshal(scanner.Bytes(), &query))
-			query = varRe.ReplaceAllString(query, "placeholder")
-
-			expr, err := promParser.ParseExpr(query)
-			if err != nil {
-				parseErrs++
-				continue
-			}
-
-			plan, ok := classify(expr, gridContext{startMs: 1_700_000_000_000, endMs: 1_700_007_200_000, stepMs: 60_000})
-			switch {
-			case ok && plan.full:
-				full++
-			case ok:
-				hybrid++
-			default:
-				reason := fallbackShape(expr)
-				fallbackReasons[reason]++
-				if reason == "instant-selector shape (last-sample-per-step engine path)" {
-					fallbackInstant++
-				} else {
-					fallbackOther++
-				}
-			}
-		}
-		require.NoError(t, scanner.Err())
-		_ = f.Close()
-
-		total := full + hybrid + fallbackInstant + fallbackOther
-		if total == 0 {
-			t.Logf("%s: no parseable queries (%d parse errors)", path, parseErrs)
-			continue
-		}
-		t.Logf("%s: %d queries — full=%d (%.0f%%) hybrid=%d (%.0f%%) fallback=%d (%.0f%%; instant-shape=%d) parse_errors=%d",
-			path, total,
-			full, 100*float64(full)/float64(total),
-			hybrid, 100*float64(hybrid)/float64(total),
-			fallbackInstant+fallbackOther, 100*float64(fallbackInstant+fallbackOther)/float64(total),
-			fallbackInstant, parseErrs)
-
-		reasons := make([]string, 0, len(fallbackReasons))
-		for r := range fallbackReasons {
-			reasons = append(reasons, r)
-		}
-		sort.Slice(reasons, func(i, j int) bool { return fallbackReasons[reasons[i]] > fallbackReasons[reasons[j]] })
-		for _, r := range reasons {
-			t.Logf("  fallback %4d  %s", fallbackReasons[r], r)
-		}
-	}
-}
-
-// fallbackShape buckets a non-transpilable query by why it stays on the engine
-// path, to separate "already served well" (instant selectors on the last-sample-per-step
-// path) from genuine compiler gaps.
-func fallbackShape(expr parser.Expr) string {
-	var hasMatrix, hasSubquery, hasAt, hasDurationExpr, overTime bool
-	rangeFns := map[string]bool{"rate": true, "increase": true, "delta": true, "irate": true, "idelta": true}
-	var unsupportedFns []string
-	parser.Inspect(expr, func(node parser.Node, _ []parser.Node) error {
-		switch n := node.(type) {
-		case *parser.MatrixSelector:
-			hasMatrix = true
-			if n.RangeExpr != nil {
-				hasDurationExpr = true
-			}
-		case *parser.SubqueryExpr:
-			hasSubquery = true
-			if n.RangeExpr != nil || n.StepExpr != nil || n.OriginalOffsetExpr != nil {
-				hasDurationExpr = true
-			}
-		case *parser.VectorSelector:
-			if n.Timestamp != nil || n.StartOrEnd != 0 {
-				hasAt = true
-			}
-			if n.OriginalOffsetExpr != nil {
-				hasDurationExpr = true
-			}
-		case *parser.Call:
-			if strings.HasSuffix(n.Func.Name, "_over_time") {
-				overTime = true
-			} else if !rangeFns[n.Func.Name] {
-				unsupportedFns = append(unsupportedFns, n.Func.Name)
-			}
-		}
-		return nil
-	})
-
-	switch {
-	case hasDurationExpr:
-		return "duration expression (resolved only at evaluation time)"
-	case hasSubquery:
-		return "subquery"
-	case hasAt:
-		return "@ modifier"
-	case overTime:
-		return "*_over_time range function"
-	case !hasMatrix:
-		return "instant-selector shape (last-sample-per-step engine path)"
-	case len(unsupportedFns) > 0:
-		return fmt.Sprintf("range shape with unsupported function(s): %s", strings.Join(dedupe(unsupportedFns), ",")) //nolint:makezero
-	default:
-		return "other range shape"
-	}
-}
-
-func dedupe(in []string) []string {
-	seen := map[string]bool{}
-	var out []string
-	for _, s := range in {
-		if !seen[s] {
-			seen[s] = true
-			out = append(out, s)
-		}
-	}
-	sort.Strings(out)
-	return out
-}

pkg/prometheus/clickhouseprometheusv2/transpiler_exec.go

@@ -1,550 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"context"
-	"encoding/json"
-	"math"
-	"sort"
-	"time"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/SigNoz/signoz/pkg/prometheus"
-	"github.com/prometheus/prometheus/model/labels"
-	promValue "github.com/prometheus/prometheus/model/value"
-	"github.com/prometheus/prometheus/promql"
-	"github.com/prometheus/prometheus/promql/parser"
-	"github.com/prometheus/prometheus/storage"
-	"golang.org/x/sync/errgroup"
-)
-
-// executor evaluates transpilable PromQL directly in ClickHouse, falling
-// back (ok=false) whenever the query shape or the step doesn't qualify. The
-// timeSeries*ToGrid functions it builds on are assumed available: the
-// supported ClickHouse floor is >= 25.6.
-type executor struct {
-	client *client
-	engine *prometheus.Engine
-	parser prometheus.Parser
-}
-
-// maxWindowBuckets caps range/step for the windowed *_over_time form: every
-// grid slot combines that many bucket partials, and the fleet's windows sit
-// well under it ([1m]..[17m] at 30-60s steps) — anything larger is a
-// long-range query whose step a dashboard scales up anyway, and the engine
-// path serves the rest.
-const maxWindowBuckets = 64
-
-// TryExecuteRange transpiles and runs the query in ClickHouse when its shape
-// is in the allowlist. ok=false means "not transpilable" and carries no
-// error; the caller runs the engine path.
-func (e *executor) TryExecuteRange(ctx context.Context, qs string, start, end time.Time, step time.Duration) (promql.Matrix, bool, error) {
-	expr, err := e.parser.ParseExpr(qs)
-	if err != nil {
-		// Let the engine path produce the (enhanced) parse error.
-		return nil, false, nil
-	}
-
-	plan, ok := classify(expr, queryGrid(start, end, step))
-	if !ok {
-		return nil, false, nil
-	}
-
-	// timeSeriesLastToGrid widens its window to max(window, step) — probed: a
-	// sample aged (window, step] still fills the slot — while the rate/delta
-	// family enforces the window strictly. The Last-style kinds used to fall
-	// back when window < step because of that widening; the window-sliver
-	// filter (see samplesConditions) makes the widening harmless there:
-	// samples exist only inside (t_k - window, t_k] slivers, so the widened
-	// window intersected with the data IS the lookback window — and if a
-	// future ClickHouse stops widening, the unwidened window is the sliver
-	// too. Correct either way. A non-positive window still falls back: the
-	// sliver argument needs a real window to filter to.
-	//
-	// The windowed *_over_time form gates only the range >= step regime: it
-	// decomposes the window into whole step buckets (see windowedInner),
-	// which is exact only when the range is a multiple of the step, and its
-	// per-slot slide costs range/step bucket combines — bounded by
-	// maxWindowBuckets so a long-range short-step query cannot turn the
-	// slide into the bottleneck. range < step needs neither gate: the
-	// windows are disjoint slivers, aggregated one slot each with no slide.
-	// Every miss falls back to the engine path, which is exact.
-	for _, unit := range plan.units {
-		stepMs := unit.grid.stepMs
-		if stepMs == 0 {
-			stepMs = 1000
-		}
-		switch {
-		case unit.core.kind == unitInstant || (unit.core.kind == unitOverTime && unit.core.overFn == "last"):
-			windowMs := unit.core.rangeMs
-			if unit.core.kind == unitInstant {
-				windowMs = e.client.lookbackMs
-			}
-			if windowMs <= 0 {
-				return nil, false, nil
-			}
-		case unit.core.kind == unitOverTime:
-			if unit.core.rangeMs < unit.grid.stepMs {
-				// Disjoint slivers: no divisibility or width requirement.
-				continue
-			}
-			if unit.core.rangeMs%stepMs != 0 || unit.core.rangeMs/stepMs > maxWindowBuckets {
-				return nil, false, nil
-			}
-		}
-	}
-
-	// Evaluate every unit concurrently on its own grid (the query grid, or a
-	// subquery grid); each is one series lookup plus one grid query.
-	results := make([][]transpiledSeries, len(plan.units))
-	eg, egCtx := errgroup.WithContext(ctx)
-	for i, unit := range plan.units {
-		eg.Go(func() error {
-			res, err := e.executeUnit(egCtx, &unit.core, unit.grid)
-			if err != nil {
-				return err
-			}
-			results[i] = res
-			return nil
-		})
-	}
-	if err := eg.Wait(); err != nil {
-		return nil, true, err
-	}
-
-	if plan.full {
-		g := plan.units[0].grid
-		return toMatrix(results[0], g.startMs, g.stepMs), true, nil
-	}
-
-	matrix, err := e.executeHybrid(ctx, plan, results)
-	if err != nil {
-		return nil, true, err
-	}
-	return matrix, true, nil
-}
-
-// queryGrid derives the top-level evaluation grid; step 0 is an instant
-// query: a single evaluation at end, whatever start was.
-func queryGrid(start, end time.Time, step time.Duration) gridContext {
-	startMs, endMs, stepMs := start.UnixMilli(), end.UnixMilli(), step.Milliseconds()
-	if stepMs == 0 {
-		startMs = endMs
-	}
-	return gridContext{startMs: startMs, endMs: endMs, stepMs: stepMs}
-}
-
-// transpiledSeries is one output series of a unit: projected labels and one
-// value pointer per grid point (nil = absent).
-type transpiledSeries struct {
-	lset   labels.Labels
-	values []*float64
-}
-
-// executeUnit runs one core unit on its grid: series lookup (budgets,
-// fingerprints, metric names), then the single grid query, then the
-// scalar-op pipeline.
-func (e *executor) executeUnit(ctx context.Context, unit *coreUnit, grid gridContext) ([]transpiledSeries, error) {
-	startMs, endMs, stepMs := grid.startMs, grid.endMs, grid.stepMs
-	windowMs := unit.rangeMs
-	if unit.kind == unitInstant {
-		windowMs = e.client.lookbackMs
-	}
-	dataStart := startMs - unit.offsetMs - windowMs
-	dataEnd := endMs - unit.offsetMs
-
-	seriesQuery, seriesArgs, err := buildSeriesQuery(dataStart, dataEnd, unit.matchers)
-	if err != nil {
-		return nil, err
-	}
-	lookup, err := e.client.selectSeries(ctx, seriesQuery, seriesArgs)
-	if err != nil {
-		return nil, err
-	}
-	if len(lookup.fingerprints) == 0 {
-		return nil, nil
-	}
-
-	query, args, err := buildUnitSQL(unit, lookup.metricNames, dataStart, dataEnd, startMs, endMs, stepMs, e.client.lookbackMs)
-	if err != nil {
-		return nil, err
-	}
-
-	rows, err := e.client.telemetryStore.ClickhouseDB().Query(e.client.withContext(ctx, "transpiledUnit"), query, args...)
-	if err != nil {
-		return nil, err
-	}
-	defer rows.Close()
-
-	// Name-dropping units keep __name__ in the SQL group key so distinct
-	// metrics never merge server-side; the name comes off here. Two metrics
-	// can then share a labelset — the engine merges their samples into one
-	// series when they never overlap in time (a selector spanning metrics
-	// whose series alternate across lookback windows) and raises the
-	// duplicate-labelset error only when two samples land on the same
-	// evaluation timestamp. mergeSameLabelsetSeries reproduces exactly that.
-	stripName := !unit.hasAgg && !unit.keepsName()
-
-	// by (...) units return one plain column per grouped label; everything
-	// else returns the single canonical JSON key (see groupKeyColumns).
-	keyNames := groupKeyColumns(unit)
-	keyVals := make([]string, max(len(keyNames), 1))
-	targets := make([]any, 0, len(keyVals)+1)
-	for i := range keyVals {
-		targets = append(targets, &keyVals[i])
-	}
-	var gridValues []*float64
-	targets = append(targets, &gridValues)
-
-	var out []transpiledSeries
-	for rows.Next() {
-		if err := rows.Scan(targets...); err != nil {
-			return nil, err
-		}
-		var lset labels.Labels
-		if keyNames != nil {
-			builder := labels.NewScratchBuilder(len(keyNames))
-			for i, name := range keyNames {
-				// An empty extracted value is the label being absent.
-				if keyVals[i] != "" {
-					builder.Add(name, keyVals[i])
-				}
-			}
-			builder.Sort()
-			lset = builder.Labels()
-		} else {
-			lset, err = labelsFromGroupKey(keyVals[0])
-			if err != nil {
-				return nil, err
-			}
-		}
-		if stripName {
-			lset = labels.NewBuilder(lset).Del(metricNameLabel).Labels()
-		}
-		values := make([]*float64, len(gridValues))
-		copy(values, gridValues)
-		applyScalarOps(unit.ops, values)
-		out = append(out, transpiledSeries{lset: lset, values: values})
-	}
-	if err := rows.Err(); err != nil {
-		return nil, err
-	}
-
-	if stripName {
-		if out, err = mergeSameLabelsetSeries(out); err != nil {
-			return nil, err
-		}
-	}
-	sort.Slice(out, func(i, j int) bool { return labels.Compare(out[i].lset, out[j].lset) < 0 })
-	return out, nil
-}
-
-// mergeSameLabelsetSeries combines series left with identical labelsets by a
-// name strip, slot by slot: the engine assembles its result matrix by
-// labelset, so post-strip twins whose points interleave in time are one
-// series to it, and two values on the same evaluation timestamp are its
-// duplicate-labelset error — v1 would have errored there too, so silently
-// picking one value would be a divergence.
-func mergeSameLabelsetSeries(in []transpiledSeries) ([]transpiledSeries, error) {
-	index := make(map[uint64]int, len(in))
-	out := in[:0]
-	for _, s := range in {
-		hash := s.lset.Hash()
-		idx, ok := index[hash]
-		if ok && labels.Equal(out[idx].lset, s.lset) {
-			dst := out[idx].values
-			for k, v := range s.values {
-				if v == nil {
-					continue
-				}
-				if dst[k] != nil {
-					return nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "vector cannot contain metrics with the same labelset")
-				}
-				dst[k] = v
-			}
-			continue
-		}
-		index[hash] = len(out)
-		out = append(out, s)
-	}
-	return out, nil
-}
-
-// labelsFromGroupKey parses the toJSONString'd sorted [key, value] pairs.
-func labelsFromGroupKey(gkey string) (labels.Labels, error) {
-	var pairs [][]string
-	if err := json.Unmarshal([]byte(gkey), &pairs); err != nil {
-		return labels.EmptyLabels(), errors.WrapInternalf(err, errors.CodeInternal, "malformed compiled group key %q", gkey)
-	}
-	builder := labels.NewScratchBuilder(len(pairs))
-	for _, p := range pairs {
-		if len(p) != 2 {
-			return labels.EmptyLabels(), errors.NewInternalf(errors.CodeInternal, "malformed compiled group key pair %q", gkey)
-		}
-		builder.Add(p[0], p[1])
-	}
-	builder.Sort()
-	return builder.Labels(), nil
-}
-
-// applyScalarOps applies the number-literal op pipeline in place, with the
-// same float64 arithmetic and comparison-filter semantics as the engine.
-func applyScalarOps(ops []scalarOp, values []*float64) {
-	for _, op := range ops {
-		for i, v := range values {
-			if v == nil {
-				continue
-			}
-			lhs, rhs := *v, op.scalar
-			if op.scalarOnLeft {
-				lhs, rhs = op.scalar, *v
-			}
-			switch op.op {
-			case parser.ADD:
-				res := lhs + rhs
-				values[i] = &res
-			case parser.SUB:
-				res := lhs - rhs
-				values[i] = &res
-			case parser.MUL:
-				res := lhs * rhs
-				values[i] = &res
-			case parser.DIV:
-				res := lhs / rhs
-				values[i] = &res
-			case parser.MOD:
-				res := math.Mod(lhs, rhs)
-				values[i] = &res
-			case parser.POW:
-				res := math.Pow(lhs, rhs)
-				values[i] = &res
-			default:
-				keep := compare(op.op, lhs, rhs)
-				switch {
-				case op.returnBool:
-					res := 0.0
-					if keep {
-						res = 1.0
-					}
-					values[i] = &res
-				case keep:
-					// Filter comparisons keep the vector-side value.
-					vec := *v
-					values[i] = &vec
-				default:
-					values[i] = nil
-				}
-			}
-		}
-	}
-}
-
-func compare(op parser.ItemType, lhs, rhs float64) bool {
-	switch op {
-	case parser.EQLC:
-		return lhs == rhs
-	case parser.NEQ:
-		return lhs != rhs
-	case parser.GTR:
-		return lhs > rhs
-	case parser.LSS:
-		return lhs < rhs
-	case parser.GTE:
-		return lhs >= rhs
-	case parser.LTE:
-		return lhs <= rhs
-	}
-	return false
-}
-
-// toMatrix converts a unit result to a promql matrix on the query grid.
-func toMatrix(series []transpiledSeries, startMs, stepMs int64) promql.Matrix {
-	matrix := make(promql.Matrix, 0, len(series))
-	for _, s := range series {
-		var floats []promql.FPoint
-		for i, v := range s.values {
-			if v == nil {
-				continue
-			}
-			floats = append(floats, promql.FPoint{T: startMs + int64(i)*stepMs, F: *v})
-		}
-		if len(floats) == 0 {
-			continue
-		}
-		matrix = append(matrix, promql.Series{Metric: s.lset, Floats: floats})
-	}
-	return matrix
-}
-
-// executeHybrid substitutes each unit's grids into the engine as synthetic
-// series and evaluates the rewritten query over a storage that serves
-// synthetic selectors from memory and everything else from the live querier.
-// Absent grid points become stale markers so the engine's lookback cannot
-// resurrect the previous grid point. Each unit's synthetic samples sit on its
-// own grid (query grid, or subquery grid for units inside subqueries).
-func (e *executor) executeHybrid(ctx context.Context, plan *transpilePlan, results [][]transpiledSeries) (promql.Matrix, error) {
-	synthetic := make(map[string][]*series, len(plan.units))
-	staleMarker := math.Float64frombits(promValue.StaleNaN)
-
-	queryGrid := plan.grid
-
-	for i, unit := range plan.units {
-		g := unit.grid
-		gridLen := 1
-		if g.stepMs > 0 {
-			gridLen = int((g.endMs-g.startMs)/g.stepMs) + 1
-		}
-		list := make([]*series, 0, len(results[i]))
-		for _, cs := range results[i] {
-			builder := labels.NewBuilder(cs.lset)
-			builder.Set(metricNameLabel, unit.name)
-			s := &series{lset: builder.Labels()}
-			s.ts = make([]int64, 0, gridLen)
-			s.vs = make([]float64, 0, gridLen)
-			for idx := 0; idx < gridLen; idx++ {
-				t := g.startMs + int64(idx)*g.stepMs
-				var v float64
-				if idx < len(cs.values) && cs.values[idx] != nil {
-					v = *cs.values[idx]
-				} else {
-					v = staleMarker
-				}
-				s.ts = append(s.ts, t)
-				s.vs = append(s.vs, v)
-			}
-			list = append(list, s)
-		}
-		synthetic[unit.name] = list
-	}
-
-	hybrid := &hybridQueryable{client: e.client, synthetic: synthetic}
-
-	var qry promql.Query
-	var err error
-	if queryGrid.stepMs == 0 {
-		qry, err = e.engine.NewInstantQuery(ctx, hybrid, nil, plan.rewritten, time.UnixMilli(queryGrid.endMs))
-	} else {
-		qry, err = e.engine.NewRangeQuery(ctx, hybrid, nil, plan.rewritten, time.UnixMilli(queryGrid.startMs), time.UnixMilli(queryGrid.endMs), time.Duration(queryGrid.stepMs)*time.Millisecond)
-	}
-	if err != nil {
-		return nil, err
-	}
-	defer qry.Close()
-
-	res := qry.Exec(ctx)
-	if res.Err != nil {
-		return nil, res.Err
-	}
-
-	matrix, err := resultToMatrix(res)
-	if err != nil {
-		return nil, err
-	}
-
-	// Deep-copy before Close returns the result's slices to the engine pool,
-	// and drop the synthetic __name__ that filter comparisons preserve.
-	out := make(promql.Matrix, 0, len(matrix))
-	for _, s := range matrix {
-		lset := s.Metric
-		if name := lset.Get(metricNameLabel); len(name) >= len(syntheticNamePrefix) && name[:len(syntheticNamePrefix)] == syntheticNamePrefix {
-			builder := labels.NewBuilder(lset)
-			builder.Del(metricNameLabel)
-			lset = builder.Labels()
-		}
-		floats := make([]promql.FPoint, len(s.Floats))
-		copy(floats, s.Floats)
-		out = append(out, promql.Series{Metric: lset.Copy(), Floats: floats})
-	}
-	// The strip can leave twins: two units' outputs distinguishable only by
-	// their synthetic names (e.g. -metric_a or -metric_b, both {} to the
-	// engine's real evaluation once names dropped). The engine assembles its
-	// matrix by labelset, merging such temporally-disjoint elements into one
-	// series; reproduce that, with its duplicate error on same-timestamp
-	// overlap.
-	out, err = mergeMatrixByLabelset(out)
-	if err != nil {
-		return nil, err
-	}
-	sort.Slice(out, func(i, j int) bool { return labels.Compare(out[i].Metric, out[j].Metric) < 0 })
-	return out, nil
-}
-
-// mergeMatrixByLabelset merges series sharing a labelset by interleaving
-// their points in timestamp order; a timestamp present in both is the
-// engine's duplicate-labelset error.
-func mergeMatrixByLabelset(matrix promql.Matrix) (promql.Matrix, error) {
-	index := make(map[uint64]int, len(matrix))
-	out := matrix[:0]
-	for _, s := range matrix {
-		hash := s.Metric.Hash()
-		idx, ok := index[hash]
-		if ok && labels.Equal(out[idx].Metric, s.Metric) {
-			merged := make([]promql.FPoint, 0, len(out[idx].Floats)+len(s.Floats))
-			a, b := out[idx].Floats, s.Floats
-			for len(a) > 0 && len(b) > 0 {
-				switch {
-				case a[0].T < b[0].T:
-					merged, a = append(merged, a[0]), a[1:]
-				case b[0].T < a[0].T:
-					merged, b = append(merged, b[0]), b[1:]
-				default:
-					return nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "vector cannot contain metrics with the same labelset")
-				}
-			}
-			out[idx].Floats = append(append(merged, a...), b...)
-			continue
-		}
-		index[hash] = len(out)
-		out = append(out, s)
-	}
-	return out, nil
-}
-
-func resultToMatrix(res *promql.Result) (promql.Matrix, error) {
-	switch v := res.Value.(type) {
-	case promql.Matrix:
-		return v, nil
-	case promql.Vector:
-		matrix := make(promql.Matrix, 0, len(v))
-		for _, s := range v {
-			matrix = append(matrix, promql.Series{Metric: s.Metric, Floats: []promql.FPoint{{T: s.T, F: s.F}}})
-		}
-		return matrix, nil
-	case promql.Scalar:
-		return promql.Matrix{{Metric: labels.EmptyLabels(), Floats: []promql.FPoint{{T: v.T, F: v.V}}}}, nil
-	default:
-		return nil, errors.NewInternalf(errors.CodeInternal, "unexpected hybrid result type %T", res.Value)
-	}
-}
-
-// hybridQueryable serves synthetic (compiled) selectors from memory and
-// everything else from the live storage.
-type hybridQueryable struct {
-	client    *client
-	synthetic map[string][]*series
-}
-
-func (h *hybridQueryable) Querier(mint, maxt int64) (storage.Querier, error) {
-	return &hybridQuerier{
-		querier:   querier{mint: mint, maxt: maxt, client: h.client},
-		synthetic: h.synthetic,
-	}, nil
-}
-
-type hybridQuerier struct {
-	querier
-	synthetic map[string][]*series
-}
-
-func (h *hybridQuerier) Select(ctx context.Context, sortSeries bool, hints *storage.SelectHints, matchers ...*labels.Matcher) storage.SeriesSet {
-	if name, ok := isSyntheticSelector(matchers); ok {
-		list := h.synthetic[name]
-		if sortSeries {
-			sorted := make([]*series, len(list))
-			copy(sorted, list)
-			sort.Slice(sorted, func(i, j int) bool { return labels.Compare(sorted[i].lset, sorted[j].lset) < 0 })
-			list = sorted
-		}
-		return newSeriesSet(list)
-	}
-	return h.querier.Select(ctx, sortSeries, hints, matchers...)
-}

pkg/prometheus/clickhouseprometheusv2/transpiler_sql.go

@@ -1,412 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"fmt"
-	"strings"
-
-	"github.com/huandu/go-sqlbuilder"
-)
-
-// experimental gate for the timeSeries*ToGrid aggregate functions; attached
-// as a SETTINGS clause so telemetrystore hooks cannot clobber it.
-const gridFunctionsSetting = "SETTINGS allow_experimental_ts_to_grid_aggregate_function = 1"
-
-var aggForEach = map[string]string{
-	"sum":   "sumForEach",
-	"min":   "minForEach",
-	"max":   "maxForEach",
-	"avg":   "avgForEach",
-	"count": "countForEach",
-}
-
-// buildUnitSQL renders the single ClickHouse query evaluating a core unit
-// over the [startMs, endMs] / stepMs evaluation grid: per-series grids via a
-// timeSeries*ToGrid aggregate (or a windowed aggregation for *_over_time),
-// then spatial aggregation with -ForEach combinators grouped by a canonical
-// JSON key of the projected label pairs.
-//
-// The heavy level is shaped to run on the shards: the top-level FROM is the
-// distributed samples table and the group-key join partner is a subquery on
-// the shard-local time series table, so the shard rewrite executes the join
-// and the per-(fingerprint, group key) aggregation next to the data —
-// complete by fingerprint co-locality (see localTimeSeriesTable) — and the
-// initiator only merges the per-series states and applies the spatial
-// -ForEach step. Same layout as the telemetrymetrics statement builder.
-// The windowed *_over_time form shares the frame but aggregates per
-// (series, group key, step bucket) instead of straight to grids
-// (see windowedInner).
-//
-// The selector's data window is offset-shifted; the resulting grid indices
-// map 1:1 onto the query grid (output ts = startMs + i*stepMs). Grid
-// parameters are rendered as literals — they are aggregate-function
-// parameters, not bindable values.
-//
-// Statements nest builder-rendered SQL as text, so the returned args must be
-// ordered by where each fragment lands in the final statement: ClickHouse
-// binds ? placeholders by position. A JOIN renders before WHERE, so a joined
-// subquery's args precede the outer query's own condition args.
-//
-// Row shape: the group-key columns (see groupKeyColumns) followed by
-// grid Array(Nullable(Float64)); NULL grid points are absent points (the
-// engine's "no value here"), which the -ForEach combinators preserve: an
-// index where every series is NULL aggregates to NULL, and countForEach's 0
-// is mapped back to NULL.
-func buildUnitSQL(unit *coreUnit, metricNames []string, dataStart, dataEnd int64, startMs, endMs, stepMs, lookbackMs int64) (string, []any, error) {
-	selStart := startMs - unit.offsetMs
-	selEnd := endMs - unit.offsetMs
-	stepSec := stepMs / 1000
-	if stepSec == 0 {
-		// Instant query: start == end, so the grid has one point for any
-		// positive step.
-		stepSec = 1
-	}
-	windowMs := unit.rangeMs
-	if unit.kind == unitInstant {
-		windowMs = lookbackMs
-	}
-	windowSec := windowMs / 1000
-
-	adjustedTsStart, tsTable := timeSeriesTableFor(dataStart, dataEnd)
-	keyNames := groupKeyColumns(unit)
-
-	// seriesSub computes fingerprint -> group key columns. It reads the
-	// local series table when it rides inside the shard-rewritten samples
-	// query, and the distributed one when it joins at the initiator
-	// (windowed form).
-	seriesSub := func(table string) (string, []any, error) {
-		sub := sqlbuilder.NewSelectBuilder()
-		selects := []string{"fingerprint"}
-		if keyNames == nil {
-			selects = append(selects, groupKeyExpr(unit)+" AS gkey")
-		} else {
-			// by (...) grouping extracts exactly the listed labels as plain
-			// columns: no reason to build, sort and stringify every label
-			// pair per row when the projection is a known short list and
-			// the label names live in Go anyway.
-			for i, name := range keyNames {
-				selects = append(selects, fmt.Sprintf("JSONExtractString(labels, %s) AS g%d", sub.Var(name), i))
-			}
-		}
-		sub.Select(selects...)
-		sub.From(fmt.Sprintf("%s.%s", databaseName, table))
-		if err := applySeriesConditions(sub, adjustedTsStart, dataEnd, unit.matchers); err != nil {
-			return "", nil, err
-		}
-		sub.GroupBy(append([]string{"fingerprint"}, keyColumnAliases(keyNames)...)...)
-		q, args := sub.BuildWithFlavor(sqlbuilder.ClickHouse)
-		return q, args, nil
-	}
-
-	// samplesConditions adds the samples-side WHERE. The group-key join
-	// restricts to the matched series; no fingerprint condition is added
-	// here.
-	samplesConditions := func(sb *sqlbuilder.SelectBuilder, excludeStale bool) {
-		switch len(metricNames) {
-		case 0:
-			// No name constraint derivable; correct but unable to use the
-			// metric_name primary-key prefix.
-		case 1:
-			sb.Where(sb.EQ("metric_name", metricNames[0]))
-		default:
-			sb.Where(sb.In("metric_name", sqlbuilder.List(metricNames)))
-		}
-		// temporality precedes metric_name in the samples primary key; the
-		// fingerprints already come from these temporalities, so this only
-		// helps granule pruning.
-		sb.Where("temporality IN ['Cumulative', 'Unspecified']")
-		// When the window is narrower than the step, the grid windows
-		// (t_k − window, t_k] cover only window/step of the selector's
-		// timeline; a sample in a gap belongs to no window and cannot move
-		// any grid point, but the grid aggregate buffers every row it is
-		// fed. Keeping only in-window rows cut a 36k-series 1w rate from
-		// 74s/28GiB to 16s/4.3GiB on fleet data — the read stays the same,
-		// the aggregate input shrinks by the coverage ratio. The lattice
-		// anchors at selStart (end may sit off-lattice on unaligned grids),
-		// positiveModulo because samples above selStart make the dividend
-		// negative, and the upper bound tightens to the last grid point —
-		// rows past it are equally windowless. window >= step tiles the
-		// timeline and keeps today's plain bounds.
-		sliver := stepMs > 0 && windowMs > 0 && windowMs < stepMs
-		upper := selEnd
-		if sliver {
-			upper = selStart + (selEnd-selStart)/stepMs*stepMs
-		}
-		// Left-open window: a sample exactly at the window's lower boundary
-		// is never used (range selectors and lookback are both left-open).
-		sb.Where(sb.GT("unix_milli", selStart-windowMs), sb.LTE("unix_milli", upper))
-		if sliver {
-			sb.Where(fmt.Sprintf("positiveModulo(%s - unix_milli, %s) < %s",
-				sb.Var(selStart), sb.Var(stepMs), sb.Var(windowMs)))
-		}
-		if excludeStale {
-			// PromQL excludes stale markers from range vectors. Instant
-			// selectors need the stale rows for shadowing instead.
-			sb.Where("bitAnd(flags, 1) = 0")
-		}
-	}
-
-	keyCols := keyColumnAliases(keyNames)
-
-	// joinedInner builds the shard-side SELECT for the single-pass kinds:
-	// grid expression per (fingerprint, group key), group-key join against
-	// the local series table.
-	joinedInner := func(gridExpr string, excludeStale bool) (string, []any, error) {
-		seriesSQL, seriesArgs, err := seriesSub(localTimeSeriesTable(tsTable))
-		if err != nil {
-			return "", nil, err
-		}
-		sb := sqlbuilder.NewSelectBuilder()
-		selects := make([]string, 0, len(keyCols)+1)
-		// A fingerprint is the hash of one labelset, so every group-key
-		// column is functionally dependent on it: any() is exact, and
-		// grouping by the fingerprint alone spares hashing the joined
-		// string per sample row — measured -10-13% on a 1.9B-row rate.
-		for _, col := range keyCols {
-			selects = append(selects, fmt.Sprintf("any(series.%s) AS %s", col, col))
-		}
-		sb.Select(append(selects, gridExpr+" AS grid")...)
-		sb.From(fmt.Sprintf("%s.%s AS points", databaseName, distributedSamplesV4))
-		sb.JoinWithOption(sqlbuilder.InnerJoin, fmt.Sprintf("(%s) AS series", seriesSQL), "points.fingerprint = series.fingerprint")
-		samplesConditions(sb, excludeStale)
-		sb.GroupBy("points.fingerprint")
-		q, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
-		// The join text renders before WHERE: its args come first.
-		return q, append(seriesArgs, args...), nil
-	}
-
-	var inner string
-	var innerArgs []any
-	var err error
-	switch unit.kind {
-	case unitInstant:
-		// Instant selection with stale shadowing: the grid value is the last
-		// non-stale sample in (t-lookback, t], absent when the overall last
-		// sample in that window is a stale marker (verified semantics: the
-		// -If combinator applies to the grid aggregates, and NULL comparisons
-		// make a stale-latest point absent).
-		gridParams := fmt.Sprintf("(fromUnixTimestamp64Milli(%d), fromUnixTimestamp64Milli(%d), %d, %d)", selStart, selEnd, stepSec, windowSec)
-		gridExpr := fmt.Sprintf(
-			"arrayMap((tall, tok, vok) -> if(tall IS NULL OR tok IS NULL OR tall != tok, NULL, vok), timeSeriesLastToGrid%s(fromUnixTimestamp64Milli(unix_milli), toFloat64(unix_milli)), timeSeriesLastToGridIf%s(fromUnixTimestamp64Milli(unix_milli), toFloat64(unix_milli), bitAnd(flags, 1) = 0), timeSeriesLastToGridIf%s(fromUnixTimestamp64Milli(unix_milli), value, bitAnd(flags, 1) = 0))",
-			gridParams, gridParams, gridParams,
-		)
-		inner, innerArgs, err = joinedInner(gridExpr, false)
-	case unitOverTime:
-		if unit.overFn == "last" {
-			// last_over_time == last non-stale sample in the window: the
-			// stale rows are already excluded in WHERE.
-			gridExpr := fmt.Sprintf(
-				"timeSeriesLastToGrid(fromUnixTimestamp64Milli(%d), fromUnixTimestamp64Milli(%d), %d, %d)(fromUnixTimestamp64Milli(unix_milli), value)",
-				selStart, selEnd, stepSec, windowSec,
-			)
-			inner, innerArgs, err = joinedInner(gridExpr, true)
-			break
-		}
-		inner, innerArgs, err = windowedInner(unit, samplesConditions, seriesSub, keyCols, localTimeSeriesTable(tsTable), selStart, selEnd, stepMs, windowMs)
-	default: // unitRange
-		gridExpr := fmt.Sprintf(
-			"%s(fromUnixTimestamp64Milli(%d), fromUnixTimestamp64Milli(%d), %d, %d)(fromUnixTimestamp64Milli(unix_milli), value)",
-			gridFunction[unit.fn], selStart, selEnd, stepSec, windowSec,
-		)
-		if unit.fn == fnIncrease {
-			// increase == rate * range-seconds, exactly: extrapolatedRate
-			// divides by the range only when isRate.
-			gridExpr = fmt.Sprintf("arrayMap(x -> x * %d, %s)", windowSec, gridExpr)
-		}
-		inner, innerArgs, err = joinedInner(gridExpr, true)
-	}
-	if err != nil {
-		return "", nil, err
-	}
-
-	spatial := "maxForEach(grid)"
-	switch {
-	case !unit.hasAgg:
-		// Per-series output: one row per (labels-minus-__name__) group.
-		// Distinct fingerprints can collapse onto the same projected label
-		// set only via a regex __name__ selector over metrics with identical
-		// other labels; maxForEach is a deterministic NULL-skipping merge and
-		// the identity for the overwhelmingly common one-fingerprint group.
-	case unit.aggOp.String() == "count":
-		// count over an all-absent index is an absent point, not 0.
-		spatial = "arrayMap(c -> if(c = 0, NULL, toFloat64(c)), countForEach(grid))"
-	default:
-		spatial = fmt.Sprintf("%s(grid)", aggForEach[unit.aggOp.String()])
-	}
-
-	keyList := strings.Join(keyCols, ", ")
-	query := fmt.Sprintf("SELECT %s, %s AS grid FROM (%s) GROUP BY %s %s", keyList, spatial, inner, keyList, gridFunctionsSetting)
-	return query, innerArgs, nil
-}
-
-// groupKeyColumns returns the label names to extract as plain group-key
-// columns, or nil when the unit needs the canonical JSON key instead. Only
-// by (...) grouping qualifies: its projection is a known short list, so
-// extracting each label directly beats building, sorting and stringifying
-// every label pair per row. without and no-aggregation project a label SET
-// that varies per series — there the sorted-JSON key is load-bearing: the
-// sort is what makes two fingerprints with different stored JSON key order
-// land in one group, and the string carries the labels back out.
-func groupKeyColumns(unit *coreUnit) []string {
-	if unit.hasAgg && unit.by && len(unit.grouping) > 0 {
-		return unit.grouping
-	}
-	return nil
-}
-
-// keyColumnAliases names the group-key columns in every SELECT level: g0..gN
-// for direct extraction, the single canonical gkey otherwise.
-func keyColumnAliases(keyNames []string) []string {
-	if keyNames == nil {
-		return []string{"gkey"}
-	}
-	cols := make([]string, len(keyNames))
-	for i := range keyNames {
-		cols[i] = fmt.Sprintf("g%d", i)
-	}
-	return cols
-}
-
-// windowedInner builds the avg/min/max/sum/count _over_time form without
-// fanning samples out. It runs only when the range is a whole multiple of
-// the step (see the transpile gate), because then the window
-// (t_k - range, t_k] is exactly the union of W = range/step step buckets —
-// both are left-open on the same boundaries — so bucket membership fully
-// determines window membership. Fanning each sample into all W windows it
-// covers (ARRAY JOIN) multiplies rows by W, which at long ranges over short
-// steps is a row explosion measured in billions.
-//
-// The bucketing itself is the -Resample combinator: one group per (series,
-// group key) whose state is a fixed array of per-bucket aggregates, updated
-// in place per sample. Grouping by (series, bucket) instead — measured on a
-// 100k-series x 371-bucket workload — creates a 37M-entry hash aggregation
-// whose per-thread partial tables scale memory WITH max_threads (12 -> 48
-// GiB from 2 to 8 threads, dead at 16) and ships one row per group to the
-// initiator; the Resample form carries the same numbers in 100k compact
-// array states, like every other unit kind.
-//
-// The wrapper level slides the window: slot k combines buckets k..k+W-1 by
-// direct aggregation over at most W partials — no prefix-sum tricks, so no
-// large-minus-large cancellation against the engine's directly-summed
-// windows. A slot with zero window count is absent, which also keeps
-// min/max honest: their slices filter on the bucket counts, so an empty
-// bucket's zero-fill can never be mistaken for a value (a real sample can
-// legitimately be 0 or +Inf).
-func windowedInner(unit *coreUnit, samplesConditions func(*sqlbuilder.SelectBuilder, bool), seriesSub func(string) (string, []any, error), keyCols []string, localSeriesTable string, selStart, selEnd, stepMs, windowMs int64) (string, []any, error) {
-	effStepMs := stepMs
-	if effStepMs == 0 {
-		effStepMs = 1000
-	}
-	lastIdx := (selEnd - selStart) / effStepMs
-	gridLen := lastIdx + 1
-	w := windowMs / effStepMs
-	bucketLen := gridLen + w
-
-	// A window narrower than the step makes the windows (t_k - range, t_k]
-	// pairwise disjoint: there is nothing to slide, each slot reads exactly
-	// its own window's aggregate. This is exact ONLY over sliver-filtered
-	// rows (samplesConditions adds the window<step predicate): the index
-	// below assigns every gap sample to the window above it, and the filter
-	// is what removes them. Requires a real step — instant queries carry no
-	// sliver filter, so they keep the tiled form and its gates.
-	disjoint := stepMs > 0 && windowMs < stepMs
-	if disjoint {
-		w = 1
-		bucketLen = gridLen
-	}
-
-	seriesSQL, seriesArgs, err := seriesSub(localSeriesTable)
-	if err != nil {
-		return "", nil, err
-	}
-
-	// Bucket index, shifted so the earliest in-window sample lands at 0:
-	// jj = ceil((ts - selStart)/step) + W - 1, folded into one intDiv. Slot
-	// k's window is then buckets jj in [k, k+W-1]. In the disjoint form the
-	// same ceil lands each in-window sample directly on its slot (W = 1),
-	// and the numerator stays positive: the fetch floor is
-	// selStart - range > selStart - step.
-	jjShift := windowMs
-	if disjoint {
-		jjShift = effStepMs
-	}
-	jj := fmt.Sprintf("intDiv(unix_milli - %d + %d - 1, %d)", selStart, jjShift, effStepMs)
-	buckets := sqlbuilder.NewSelectBuilder()
-	selects := make([]string, 0, len(keyCols)+2)
-	// any() over the group key: exact because the key is functionally
-	// dependent on the fingerprint (see joinedInner).
-	for _, col := range keyCols {
-		selects = append(selects, fmt.Sprintf("any(series.%s) AS %s", col, col))
-	}
-	selects = append(selects, fmt.Sprintf("countResample(0, %d, 1)(value, %s) AS cnts", bucketLen, jj))
-	if unit.overFn != "count" {
-		selects = append(selects, fmt.Sprintf("%sResample(0, %d, 1)(value, %s) AS vals", map[string]string{
-			"avg": "sum",
-			"sum": "sum",
-			"min": "min",
-			"max": "max",
-		}[unit.overFn], bucketLen, jj))
-	}
-	buckets.Select(selects...)
-	buckets.From(fmt.Sprintf("%s.%s AS points", databaseName, distributedSamplesV4))
-	buckets.JoinWithOption(sqlbuilder.InnerJoin, fmt.Sprintf("(%s) AS series", seriesSQL), "points.fingerprint = series.fingerprint")
-	samplesConditions(buckets, true)
-	buckets.GroupBy("points.fingerprint")
-	bucketsSQL, bucketsArgs := buckets.BuildWithFlavor(sqlbuilder.ClickHouse)
-
-	windowCnt := fmt.Sprintf("arraySum(arraySlice(cnts, k + 1, %d))", w)
-	var slot string
-	switch unit.overFn {
-	case "count":
-		slot = fmt.Sprintf("if(%s = 0, NULL, toFloat64(%s))", windowCnt, windowCnt)
-	case "sum":
-		slot = fmt.Sprintf("if(%s = 0, NULL, arraySum(arraySlice(vals, k + 1, %d)))", windowCnt, w)
-	case "avg":
-		slot = fmt.Sprintf("if(%s = 0, NULL, arraySum(arraySlice(vals, k + 1, %d)) / %s)", windowCnt, w, windowCnt)
-	case "min":
-		slot = fmt.Sprintf("if(%s = 0, NULL, arrayMin(arrayFilter((v, c) -> c > 0, arraySlice(vals, k + 1, %d), arraySlice(cnts, k + 1, %d))))", windowCnt, w, w)
-	case "max":
-		slot = fmt.Sprintf("if(%s = 0, NULL, arrayMax(arrayFilter((v, c) -> c > 0, arraySlice(vals, k + 1, %d), arraySlice(cnts, k + 1, %d))))", windowCnt, w, w)
-	}
-
-	keyList := strings.Join(keyCols, ", ")
-	inner := fmt.Sprintf(
-		"SELECT %s, arrayMap(k -> %s, range(toUInt64(%d))) AS grid FROM (%s)",
-		keyList, slot, gridLen, bucketsSQL,
-	)
-	return inner, append(seriesArgs, bucketsArgs...), nil
-}
-
-// groupKeyExpr renders the canonical JSON group key for the units whose
-// projected label SET varies per series (see groupKeyColumns): the sorted
-// [key, value] pairs of the projected labels, JSON-encoded.
-//   - by () with no labels: one constant group;
-//   - without (a, b): keep everything except the listed labels and __name__;
-//   - no aggregation: keep everything including __name__ — even when the
-//     unit drops the name from its OUTPUT, the key must keep it so distinct
-//     metrics never merge in SQL; executeUnit strips the name afterwards and
-//     turns a post-strip collision into the engine's duplicate-labelset
-//     error instead of a silently invented merge.
-func groupKeyExpr(unit *coreUnit) string {
-	// An empty label value means "label absent" in Prometheus; the stored
-	// labels JSON can carry empty attribute values, which must not become
-	// output labels or group keys.
-	pairs := "arraySort(JSONExtractKeysAndValues(labels, 'String'))"
-	if !unit.hasAgg {
-		return fmt.Sprintf("toJSONString(arrayFilter(p -> p.2 != '', %s))", pairs)
-	}
-	if unit.by {
-		// Non-empty by (...) never reaches here; groupKeyColumns extracts
-		// those labels as plain columns instead.
-		return "'[]'"
-	}
-	excluded := append([]string{metricNameLabel}, unit.grouping...)
-	return fmt.Sprintf("toJSONString(arrayFilter(p -> p.2 != '' AND p.1 NOT IN (%s), %s))", quotedList(excluded), pairs)
-}
-
-func quotedList(items []string) string {
-	quoted := make([]string, len(items))
-	for i, s := range items {
-		quoted[i] = "'" + strings.ReplaceAll(s, "'", "\\'") + "'"
-	}
-	return strings.Join(quoted, ", ")
-}

pkg/prometheus/clickhouseprometheusv2/transpiler_test.go

@@ -1,751 +0,0 @@
-package clickhouseprometheusv2
-
-import (
-	"context"
-	"testing"
-	"time"
-
-	"github.com/DATA-DOG/go-sqlmock"
-	cmock "github.com/SigNoz/clickhouse-go-mock"
-	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/SigNoz/signoz/pkg/factory"
-	"github.com/SigNoz/signoz/pkg/instrumentation/instrumentationtest"
-	"github.com/SigNoz/signoz/pkg/prometheus"
-	"github.com/SigNoz/signoz/pkg/telemetrystore"
-	"github.com/SigNoz/signoz/pkg/telemetrystore/telemetrystoretest"
-	"github.com/prometheus/prometheus/model/labels"
-	"github.com/prometheus/prometheus/promql"
-	"github.com/prometheus/prometheus/promql/parser"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-func newTestClient(t *testing.T) (*client, *telemetrystoretest.Provider) {
-	t.Helper()
-	store := telemetrystoretest.New(telemetrystore.Config{Provider: "clickhouse"}, sqlmock.QueryMatcherRegexp)
-	settings := factory.NewScopedProviderSettings(instrumentationtest.New().ToProviderSettings(), "clickhouseprometheusv2_test")
-	return newClient(settings, store, prometheus.Config{}), store
-}
-
-var seriesCols = []cmock.ColumnType{
-	{Name: "fingerprint", Type: "UInt64"},
-	{Name: "labels", Type: "String"},
-}
-
-func parse(t *testing.T, q string) parser.Expr {
-	t.Helper()
-	expr, err := parser.NewParser(parser.Options{}).ParseExpr(q)
-	require.NoError(t, err)
-	return expr
-}
-
-func TestClassifyFullShapes(t *testing.T) {
-	tests := []struct {
-		name  string
-		query string
-		check func(t *testing.T, u *coreUnit)
-	}{
-		{
-			name:  "sum by rate",
-			query: `sum by (pod) (rate(http_requests_total{job="api"}[5m]))`,
-			check: func(t *testing.T, u *coreUnit) {
-				assert.Equal(t, fnRate, u.fn)
-				assert.Equal(t, int64(300_000), u.rangeMs)
-				assert.True(t, u.hasAgg)
-				assert.True(t, u.by)
-				assert.Equal(t, []string{"pod"}, u.grouping)
-			},
-		},
-		{
-			name:  "bare increase with offset",
-			query: `increase(errors_total[10m] offset 30m)`,
-			check: func(t *testing.T, u *coreUnit) {
-				assert.Equal(t, fnIncrease, u.fn)
-				assert.Equal(t, int64(1_800_000), u.offsetMs)
-				assert.False(t, u.hasAgg)
-			},
-		},
-		{
-			name:  "avg without over delta",
-			query: `avg without (instance) (delta(gauge_metric[15m]))`,
-			check: func(t *testing.T, u *coreUnit) {
-				assert.Equal(t, fnDelta, u.fn)
-				assert.True(t, u.hasAgg)
-				assert.False(t, u.by)
-			},
-		},
-		{
-			name:  "scalar pipeline with comparison",
-			query: `sum(rate(x[5m])) * 100 > 5`,
-			check: func(t *testing.T, u *coreUnit) {
-				require.Len(t, u.ops, 2)
-				assert.Equal(t, parser.ItemType(parser.MUL), u.ops[0].op)
-				assert.Equal(t, 100.0, u.ops[0].scalar)
-				assert.Equal(t, parser.ItemType(parser.GTR), u.ops[1].op)
-			},
-		},
-		{
-			name:  "scalar on left with unary minus",
-			query: `-1 * sum(rate(x[5m]))`,
-			check: func(t *testing.T, u *coreUnit) {
-				require.Len(t, u.ops, 1)
-				assert.True(t, u.ops[0].scalarOnLeft)
-				assert.Equal(t, -1.0, u.ops[0].scalar)
-			},
-		},
-		{
-			name:  "bool comparison",
-			query: `sum(rate(x[5m])) >= bool 0.5`,
-			check: func(t *testing.T, u *coreUnit) {
-				require.Len(t, u.ops, 1)
-				assert.True(t, u.ops[0].returnBool)
-			},
-		},
-		{
-			name:  "irate utf8 name",
-			query: `sum by ("k8s.pod.name") (irate({"k8s.container.cpu.time"}[2m]))`,
-			check: func(t *testing.T, u *coreUnit) {
-				assert.Equal(t, fnIRate, u.fn)
-				assert.Equal(t, []string{"k8s.pod.name"}, u.grouping)
-			},
-		},
-		{
-			name:  "bare instant selector keeps name",
-			query: `up{job="api"}`,
-			check: func(t *testing.T, u *coreUnit) {
-				assert.Equal(t, unitInstant, u.kind)
-				assert.True(t, u.keepsName())
-			},
-		},
-		{
-			name:  "gauge aggregation",
-			query: `sum by (pod) (container_memory offset 5m)`,
-			check: func(t *testing.T, u *coreUnit) {
-				assert.Equal(t, unitInstant, u.kind)
-				assert.Equal(t, int64(300_000), u.offsetMs)
-				assert.True(t, u.hasAgg)
-				assert.False(t, u.keepsName())
-			},
-		},
-		{
-			name:  "gauge comparison keeps name",
-			query: `container_memory > 100`,
-			check: func(t *testing.T, u *coreUnit) {
-				assert.Equal(t, unitInstant, u.kind)
-				assert.True(t, u.keepsName())
-			},
-		},
-		{
-			name:  "gauge arithmetic drops name",
-			query: `container_memory / 1024`,
-			check: func(t *testing.T, u *coreUnit) {
-				assert.Equal(t, unitInstant, u.kind)
-				assert.False(t, u.keepsName())
-			},
-		},
-		{
-			name:  "avg_over_time",
-			query: `max by (node) (avg_over_time(load1[10m]))`,
-			check: func(t *testing.T, u *coreUnit) {
-				assert.Equal(t, unitOverTime, u.kind)
-				assert.Equal(t, "avg", u.overFn)
-				assert.Equal(t, int64(600_000), u.rangeMs)
-			},
-		},
-		{
-			name:  "last_over_time keeps name",
-			query: `last_over_time(load1[10m])`,
-			check: func(t *testing.T, u *coreUnit) {
-				assert.Equal(t, unitOverTime, u.kind)
-				assert.Equal(t, "last", u.overFn)
-				assert.True(t, u.keepsName())
-			},
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			plan, ok := classify(parse(t, tt.query), testGrid(60_000))
-			require.True(t, ok, "expected transpilable")
-			require.True(t, plan.full, "expected full compilation")
-			require.Len(t, plan.units, 1)
-			tt.check(t, &plan.units[0].core)
-		})
-	}
-}
-
-func TestClassifyFallbackShapes(t *testing.T) {
-	queries := []struct {
-		name  string
-		query string
-		step  int64
-	}{
-		{"default-resolution subquery", `max_over_time(rate(x[5m])[30m:])`, 60_000},
-		{"at modifier", `sum(rate(x[5m] @ 1609746000))`, 60_000},
-		{"at modifier on gauge", `sum(container_memory @ 1609746000)`, 60_000},
-		{"sub-second step", `sum(rate(x[5m]))`, 500},
-		{"sub-second range", `sum(rate(x[1500ms]))`, 60_000},
-		{"by __name__ full", `sum by (__name__) (rate({__name__=~"a|b"}[5m]))`, 60_000},
-		{"quantile_over_time unsupported", `quantile_over_time(0.9, load1[10m])`, 60_000},
-		// Duration expressions resolve into the selectors' static fields only
-		// at evaluation time; classification reads those fields as zero, so
-		// transpiling would silently use the wrong offset (caught by the
-		// conformance corpus' duration_expression.test cases). Offset
-		// expressions parse without the experimental-parser flag, so they do
-		// reach the transpiler; range-position expressions are rejected at
-		// parse (the RangeExpr/StepExpr guards are defense-in-depth).
-		{"duration expression offset on instant", `x offset step()`, 60_000},
-		{"duration expression offset arithmetic", `x offset -step()*2`, 60_000},
-		{"duration expression offset on range", `sum(rate(x[5m] offset max(3s, step())))`, 60_000},
-		{"duration expression subquery step", `max_over_time(rate(x[5m])[30m:step()])`, 60_000},
-	}
-	for _, tt := range queries {
-		t.Run(tt.name, func(t *testing.T) {
-			_, ok := classify(parse(t, tt.query), testGrid(tt.step))
-			assert.False(t, ok, "expected fallback for %s", tt.query)
-		})
-	}
-}
-
-func TestClassifyHybridShapes(t *testing.T) {
-	tests := []struct {
-		name          string
-		query         string
-		wantUnits     int
-		wantRewritten string
-	}{
-		{
-			name:          "histogram quantile",
-			query:         `histogram_quantile(0.95, sum by (le) (rate(http_bucket[5m])))`,
-			wantUnits:     1,
-			wantRewritten: `histogram_quantile(0.95, __signoz_transpiled_0__)`,
-		},
-		{
-			name:          "topk over compiled",
-			query:         `topk(5, sum by (pod) (rate(x[5m])))`,
-			wantUnits:     1,
-			wantRewritten: `topk(5, __signoz_transpiled_0__)`,
-		},
-		{
-			name:          "ratio of compiled units",
-			query:         `sum(rate(a[5m])) / sum(rate(b[5m]))`,
-			wantUnits:     2,
-			wantRewritten: `__signoz_transpiled_0__ / __signoz_transpiled_1__`,
-		},
-		{
-			name:          "or vector zero",
-			query:         `sum(rate(a[5m])) or vector(0)`,
-			wantUnits:     1,
-			wantRewritten: `__signoz_transpiled_0__ or vector(0)`,
-		},
-		{
-			name:          "quantile agg over compiled rate",
-			query:         `quantile(0.9, rate(x[5m]))`,
-			wantUnits:     1,
-			wantRewritten: `quantile(0.9, __signoz_transpiled_0__)`,
-		},
-		{
-			name:          "non-literal scalar side stays engine-side",
-			query:         `sum(rate(x[5m])) * scalar(y)`,
-			wantUnits:     1,
-			wantRewritten: `__signoz_transpiled_0__ * scalar(y)`,
-		},
-		{
-			name:          "compiled mixed with raw selector",
-			query:         `sum by (pod) (rate(a[5m])) / on (pod) group_left () b`,
-			wantUnits:     1,
-			wantRewritten: `__signoz_transpiled_0__ / on (pod) group_left () b`,
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			plan, ok := classify(parse(t, tt.query), testGrid(60_000))
-			require.True(t, ok)
-			assert.False(t, plan.full)
-			assert.Len(t, plan.units, tt.wantUnits)
-			assert.Equal(t, tt.wantRewritten, plan.rewritten)
-		})
-	}
-}
-
-func TestClassifyHybridGuards(t *testing.T) {
-	t.Run("no substitution under on(__name__)", func(t *testing.T) {
-		plan, ok := classify(parse(t, `sum(rate(a[5m])) * on (__name__) b`), testGrid(60_000))
-		_ = plan
-		assert.False(t, ok, "matching on __name__ must not see synthetic names")
-	})
-	t.Run("no substitution inside @-pinned subquery", func(t *testing.T) {
-		_, ok := classify(parse(t, `max_over_time(rate(x[5m])[30m:1m] @ 1609746000)`), testGrid(60_000))
-		assert.False(t, ok)
-	})
-}
-
-// The alert-smoothing idiom: units inside a fixed-resolution subquery
-// evaluate on the subquery grid — epoch-aligned multiples of the resolution,
-// starting strictly after (outer start - range), exactly as the engine
-// derives it.
-func TestClassifySubqueryUnits(t *testing.T) {
-	grid := gridContext{startMs: 1_700_000_030_000, endMs: 1_700_007_200_000, stepMs: 60_000}
-
-	plan, ok := classify(parse(t, `min_over_time((sum by (ns) (increase(x[5m])))[10m:5m]) > 0`), grid)
-	require.True(t, ok)
-	require.False(t, plan.full)
-	require.Len(t, plan.units, 1)
-	assert.Equal(t, `min_over_time(__signoz_transpiled_0__[10m:5m]) > 0`, plan.rewritten)
-
-	unit := plan.units[0]
-	// lower bound = outer start - range = 1_699_999_430_000; first multiple
-	// of 300_000 strictly greater is 1_699_999_500_000.
-	assert.Equal(t, int64(1_699_999_500_000), unit.grid.startMs)
-	assert.Equal(t, grid.endMs, unit.grid.endMs)
-	assert.Equal(t, int64(300_000), unit.grid.stepMs)
-	assert.Equal(t, fnIncrease, unit.core.fn)
-
-	t.Run("subquery offset shifts the grid", func(t *testing.T) {
-		plan, ok := classify(parse(t, `max_over_time((sum(rate(x[5m])))[10m:5m] offset 30m)`), grid)
-		require.True(t, ok)
-		require.Len(t, plan.units, 1)
-		// lower = start - offset - range = 1_699_997_630_000 -> first
-		// multiple of 300_000 above = 1_699_997_700_000; end shifts too.
-		assert.Equal(t, int64(1_699_997_700_000), plan.units[0].grid.startMs)
-		assert.Equal(t, grid.endMs-1_800_000, plan.units[0].grid.endMs)
-	})
-
-	t.Run("mollusk ratio-inside-subquery idiom", func(t *testing.T) {
-		q := `min_over_time(((sum by (a) (rate(m1[5m]))) / (avg by (a) (m2)))[5m:1m])`
-		plan, ok := classify(parse(t, q), grid)
-		require.True(t, ok)
-		// Both sides compile on the subquery grid: the rate side and the
-		// gauge aggregation side; the engine joins them and smooths.
-		require.Len(t, plan.units, 2)
-		assert.Equal(t, int64(60_000), plan.units[0].grid.stepMs)
-		assert.Equal(t, unitInstant, plan.units[1].core.kind)
-		assert.Contains(t, plan.rewritten, `__signoz_transpiled_0__ / __signoz_transpiled_1__`)
-	})
-}
-
-func TestBuildUnitSQL(t *testing.T) {
-	unit := &coreUnit{
-		fn:       fnRate,
-		rangeMs:  300_000,
-		hasAgg:   true,
-		aggOp:    parser.SUM,
-		by:       true,
-		grouping: []string{"pod"},
-		matchers: []*labels.Matcher{mustMatcher(t, labels.MatchEqual, "__name__", "http_requests_total")},
-	}
-	sql, args, err := buildUnitSQL(unit, []string{"http_requests_total"}, 1_699_999_700_000, 1_700_003_600_000, 1_700_000_000_000, 1_700_003_600_000, 60_000, 300_000)
-	require.NoError(t, err)
-
-	assert.Contains(t, sql, "timeSeriesRateToGrid(fromUnixTimestamp64Milli(1700000000000), fromUnixTimestamp64Milli(1700003600000), 60, 300)(fromUnixTimestamp64Milli(unix_milli), value)")
-	assert.Contains(t, sql, "unix_milli > ? AND unix_milli <= ?")
-	assert.Contains(t, sql, "bitAnd(flags, 1) = 0")
-	assert.Contains(t, sql, "sumForEach(grid)")
-	// The group-key join rides inside the shard query: distributed samples
-	// at the top level, the local series table in the join subquery, the
-	// grid aggregation grouped per (fingerprint, group key) shard-side.
-	assert.Contains(t, sql, "FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint,")
-	assert.Contains(t, sql, "FROM signoz_metrics.time_series_v4 WHERE")
-	// The group key is functionally dependent on the fingerprint (one
-	// labelset per fingerprint): any() is exact and the per-row hash key
-	// shrinks to the fingerprint alone.
-	assert.Contains(t, sql, "any(series.g0) AS g0")
-	assert.Contains(t, sql, "GROUP BY points.fingerprint)")
-	// No samples-side fingerprint condition: the group-key join restricts.
-	assert.NotContains(t, sql, "points.fingerprint IN (")
-	// by (pod) extracts the grouped label directly — no per-row JSON
-	// build/sort/stringify for a known projection.
-	assert.Contains(t, sql, "JSONExtractString(labels, ?) AS g0")
-	assert.NotContains(t, sql, "toJSONString")
-	assert.Contains(t, sql, "SETTINGS allow_experimental_ts_to_grid_aggregate_function = 1")
-	// Args follow placeholder order: the joined series subquery renders
-	// before the samples WHERE, and its select list ('pod') renders before
-	// its own conditions.
-	assert.Equal(t, []any{"pod", "http_requests_total", int64(1_699_999_200_000), int64(1_700_003_600_000), "http_requests_total", int64(1_699_999_700_000), int64(1_700_003_600_000)}, args)
-}
-
-func TestBuildUnitSQLIncreaseAndOffset(t *testing.T) {
-	unit := &coreUnit{
-		fn:       fnIncrease,
-		rangeMs:  600_000,
-		offsetMs: 1_800_000,
-		matchers: []*labels.Matcher{mustMatcher(t, labels.MatchEqual, "__name__", "errors_total")},
-	}
-	sql, _, err := buildUnitSQL(unit, nil, 1_699_997_600_000, 1_700_001_800_000, 1_700_000_000_000, 1_700_003_600_000, 60_000, 300_000)
-	require.NoError(t, err)
-
-	// Grid and window shift by the offset; increase multiplies rate by the
-	// range in seconds.
-	assert.Contains(t, sql, "fromUnixTimestamp64Milli(1699998200000), fromUnixTimestamp64Milli(1700001800000)")
-	assert.Contains(t, sql, "arrayMap(x -> x * 600, timeSeriesRateToGrid")
-	assert.Contains(t, sql, "maxForEach(grid)")
-}
-
-func TestBuildUnitSQLOverLimitJoinOnly(t *testing.T) {
-	// Past the inline limit no fingerprint filter is rendered: the series
-	// join restricts to the matched fingerprints on its own.
-	unit := &coreUnit{
-		fn:       fnRate,
-		rangeMs:  300_000,
-		hasAgg:   true,
-		aggOp:    parser.SUM,
-		by:       true,
-		matchers: []*labels.Matcher{mustMatcher(t, labels.MatchEqual, "__name__", "http_requests_total")},
-	}
-	sql, _, err := buildUnitSQL(unit, []string{"http_requests_total"}, 1_699_999_700_000, 1_700_003_600_000, 1_700_000_000_000, 1_700_003_600_000, 60_000, 300_000)
-	require.NoError(t, err)
-
-	assert.NotContains(t, sql, "points.fingerprint IN")
-	assert.Contains(t, sql, "INNER JOIN (SELECT fingerprint,")
-	assert.Contains(t, sql, "FROM signoz_metrics.time_series_v4 WHERE")
-}
-
-func TestBuildUnitSQLWindowSliver(t *testing.T) {
-	// rate[5m] on a 30m grid evaluates only a 5m sliver before each grid
-	// point — samples in the gaps belong to no window and would only be
-	// buffered by the grid aggregate. The WHERE must keep exactly the
-	// in-window rows: positiveModulo anchored at the selector start (end
-	// can sit off-lattice on unaligned grids, and samples above the start
-	// make the plain modulo dividend negative), and the scan capped at the
-	// last grid point — rows past it are equally windowless.
-	unit := &coreUnit{
-		fn:       fnRate,
-		rangeMs:  300_000,
-		hasAgg:   true,
-		aggOp:    parser.SUM,
-		by:       true,
-		grouping: []string{"pod"},
-		matchers: []*labels.Matcher{mustMatcher(t, labels.MatchEqual, "__name__", "http_requests_total")},
-	}
-	sql, args, err := buildUnitSQL(unit, []string{"http_requests_total"}, 1_699_999_700_000, 1_700_003_600_000, 1_700_000_000_000, 1_700_003_600_000, 1_800_000, 300_000)
-	require.NoError(t, err)
-
-	assert.Contains(t, sql, "positiveModulo(? - unix_milli, ?) < ?")
-	assert.Equal(t, []any{"pod", "http_requests_total", int64(1_699_999_200_000), int64(1_700_003_600_000), "http_requests_total", int64(1_699_999_700_000), int64(1_700_003_600_000), int64(1_700_000_000_000), int64(1_800_000), int64(300_000)}, args)
-
-	t.Run("off-lattice end caps the scan at the last grid point", func(t *testing.T) {
-		// end - start = 50m at a 30m step: the only grid points are start
-		// and start+30m; samples in the trailing 20m serve no window.
-		_, args, err := buildUnitSQL(unit, []string{"http_requests_total"}, 1_699_999_700_000, 1_700_003_000_000, 1_700_000_000_000, 1_700_003_000_000, 1_800_000, 300_000)
-		require.NoError(t, err)
-		assert.Contains(t, args, int64(1_700_001_800_000))
-	})
-
-	t.Run("window covering the step keeps plain bounds", func(t *testing.T) {
-		sql, _, err := buildUnitSQL(unit, []string{"http_requests_total"}, 1_699_999_700_000, 1_700_003_600_000, 1_700_000_000_000, 1_700_003_600_000, 60_000, 300_000)
-		require.NoError(t, err)
-		assert.NotContains(t, sql, "positiveModulo")
-	})
-}
-
-func TestBuildUnitSQLWindowedBucketsWithoutFanOut(t *testing.T) {
-	// The window is W = range/step whole buckets, so each sample lands in
-	// exactly one bucket via GROUP BY and the window slides over bucket
-	// partials — fanning samples into every covered window (ARRAY JOIN)
-	// multiplies rows by W, a row explosion at long ranges.
-	unit := &coreUnit{
-		kind:     unitOverTime,
-		overFn:   "avg",
-		rangeMs:  600_000,
-		matchers: []*labels.Matcher{mustMatcher(t, labels.MatchEqual, "__name__", "node_load1")},
-	}
-	sql, _, err := buildUnitSQL(unit, []string{"node_load1"}, 1_699_999_400_000, 1_700_003_600_000, 1_700_000_000_000, 1_700_003_600_000, 60_000, 600_000)
-	require.NoError(t, err)
-
-	assert.NotContains(t, sql, "ARRAY JOIN")
-	// One group per series with fixed per-bucket arrays (-Resample); the
-	// bucket index jj = ceil((ts - start)/step) + W - 1 folded into a single
-	// intDiv. Grouping by (series, bucket) instead measured 37M hash groups
-	// whose per-thread partials scale memory with max_threads.
-	assert.Contains(t, sql, "countResample(0, 71, 1)(value, intDiv(unix_milli - 1700000000000 + 600000 - 1, 60000)) AS cnts")
-	assert.Contains(t, sql, "sumResample(0, 71, 1)(value, intDiv(unix_milli - 1700000000000 + 600000 - 1, 60000)) AS vals")
-	assert.Contains(t, sql, "any(series.gkey) AS gkey")
-	assert.Contains(t, sql, "GROUP BY points.fingerprint)")
-	assert.NotContains(t, sql, "jj) AS jj")
-	assert.Contains(t, sql, "INNER JOIN (SELECT fingerprint,")
-	assert.Contains(t, sql, "FROM signoz_metrics.time_series_v4 WHERE")
-	// Slide: W = 10 buckets per slot, absent when the window count is 0.
-	assert.Contains(t, sql, "arraySum(arraySlice(cnts, k + 1, 10))")
-	assert.Contains(t, sql, "arraySum(arraySlice(vals, k + 1, 10))")
-}
-
-func TestBuildUnitSQLDisjointOverTime(t *testing.T) {
-	// avg_over_time[5m] on a 30m grid: the windows are pairwise disjoint,
-	// so there is no slide — one Resample bucket per grid slot, read
-	// directly. Exact only together with the window-sliver predicate, which
-	// removes the gap samples the ceil index would otherwise assign to the
-	// window above them.
-	unit := &coreUnit{
-		kind:     unitOverTime,
-		overFn:   "avg",
-		rangeMs:  300_000,
-		matchers: []*labels.Matcher{mustMatcher(t, labels.MatchEqual, "__name__", "node_load1")},
-	}
-	sql, _, err := buildUnitSQL(unit, []string{"node_load1"}, 1_699_999_700_000, 1_700_003_600_000, 1_700_000_000_000, 1_700_003_600_000, 1_800_000, 300_000)
-	require.NoError(t, err)
-
-	assert.NotContains(t, sql, "ARRAY JOIN")
-	// gridLen = 3 slots, bucket array the same length — no W tail.
-	assert.Contains(t, sql, "countResample(0, 3, 1)(value, intDiv(unix_milli - 1700000000000 + 1800000 - 1, 1800000)) AS cnts")
-	assert.Contains(t, sql, "sumResample(0, 3, 1)(value, intDiv(unix_milli - 1700000000000 + 1800000 - 1, 1800000)) AS vals")
-	// Single-bucket window: the slide degenerates to reading one slot.
-	assert.Contains(t, sql, "arraySum(arraySlice(cnts, k + 1, 1))")
-	// The sliver predicate is the correctness precondition of this form.
-	assert.Contains(t, sql, "positiveModulo(? - unix_milli, ?) < ?")
-}
-
-// TestDisjointWindowLattice brute-forces the disjoint-form arithmetic: a
-// sample survives the sliver predicate exactly when some grid window
-// contains it, and the ceil bucket index then lands it on that window's
-// slot. This is the pure-Go mirror of the SQL expressions — the predicate
-// in samplesConditions and jj in windowedInner — over random lattices,
-// including off-lattice ends and samples beyond the last grid point.
-func TestDisjointWindowLattice(t *testing.T) {
-	rng := func(seed *uint64) int64 {
-		*seed = *seed*6364136223846793005 + 1442695040888963407
-		return int64(*seed >> 33)
-	}
-	seed := uint64(42)
-	for trial := 0; trial < 2000; trial++ {
-		stepMs := 1_000 * (1 + rng(&seed)%3600)
-		windowMs := 1 + rng(&seed)%(stepMs-1) // strictly below the step
-		selStart := 1_700_000_000_000 + rng(&seed)%1_000_000
-		selEnd := selStart + rng(&seed)%(50*stepMs) // end may sit off-lattice
-		lastIdx := (selEnd - selStart) / stepMs
-		upper := selStart + lastIdx*stepMs
-
-		for i := 0; i < 50; i++ {
-			u := selStart - windowMs - stepMs + rng(&seed)%(selEnd-selStart+3*stepMs)
-
-			// Oracle: is u inside any window (t_k - window, t_k]?
-			inWindow := false
-			var slot int64 = -1
-			for k := int64(0); k <= lastIdx; k++ {
-				tk := selStart + k*stepMs
-				if u > tk-windowMs && u <= tk {
-					inWindow = true
-					slot = k
-					break
-				}
-			}
-
-			// The SQL: fetch bounds, then the sliver predicate
-			// positiveModulo(selStart - u, step) < window.
-			kept := u > selStart-windowMs && u <= upper
-			if kept {
-				pmod := (selStart - u) % stepMs
-				if pmod < 0 {
-					pmod += stepMs
-				}
-				kept = pmod < windowMs
-			}
-
-			require.Equal(t, inWindow, kept,
-				"sliver keep mismatch: u=%d selStart=%d step=%d window=%d", u, selStart, stepMs, windowMs)
-			if !kept {
-				continue
-			}
-			// jj = ceil((u - selStart)/step) via one intDiv; numerator is
-			// positive because u > selStart - window > selStart - step.
-			jj := (u - selStart + stepMs - 1) / stepMs
-			require.Equal(t, slot, jj,
-				"slot mismatch: u=%d selStart=%d step=%d window=%d", u, selStart, stepMs, windowMs)
-		}
-	}
-}
-
-func TestTryExecuteRange_WindowedGateFallsBack(t *testing.T) {
-	c, store := newTestClient(t)
-	e := &executor{client: c, parser: prometheus.NewParser()}
-
-	start := time.UnixMilli(1_700_000_000_000)
-	end := time.UnixMilli(1_700_003_600_000)
-
-	// 10m range at 90s step: the window is not a whole number of buckets.
-	_, ok, err := e.TryExecuteRange(context.Background(), `avg_over_time(up[10m])`, start, end, 90*time.Second)
-	require.NoError(t, err)
-	assert.False(t, ok, "range not divisible by step must not transpile")
-
-	// 1d range at 60s step: 1440 bucket combines per slot, over the cap.
-	_, ok, err = e.TryExecuteRange(context.Background(), `avg_over_time(up[1d])`, start, end, time.Minute)
-	require.NoError(t, err)
-	assert.False(t, ok, "range/step above maxWindowBuckets must not transpile")
-
-	// 1m range at 5m step: the windows are disjoint slivers — no
-	// divisibility or width requirement, so this transpiles.
-	store.Mock().ExpectQuery("SELECT fingerprint, any\\(labels\\)").WithArgs("up", int64(1_699_999_200_000), int64(1_700_003_600_000)).WillReturnRows(cmock.NewRows(seriesCols, [][]any{}))
-	_, ok, err = e.TryExecuteRange(context.Background(), `avg_over_time(up[1m])`, start, end, 5*time.Minute)
-	require.NoError(t, err)
-	assert.True(t, ok, "range below step is the disjoint form and must transpile")
-}
-
-func TestApplyScalarOps(t *testing.T) {
-	f := func(v float64) *float64 { return &v }
-
-	t.Run("arithmetic chain", func(t *testing.T) {
-		values := []*float64{f(2), nil, f(4)}
-		applyScalarOps([]scalarOp{{op: parser.MUL, scalar: 100}, {op: parser.ADD, scalar: 1}}, values)
-		require.NotNil(t, values[0])
-		assert.Equal(t, 201.0, *values[0])
-		assert.Nil(t, values[1])
-		assert.Equal(t, 401.0, *values[2])
-	})
-
-	t.Run("comparison filters points", func(t *testing.T) {
-		values := []*float64{f(1), f(10)}
-		applyScalarOps([]scalarOp{{op: parser.GTR, scalar: 5}}, values)
-		assert.Nil(t, values[0])
-		require.NotNil(t, values[1])
-		assert.Equal(t, 10.0, *values[1], "filter comparisons keep the original value")
-	})
-
-	t.Run("bool comparison emits 0/1", func(t *testing.T) {
-		values := []*float64{f(1), f(10)}
-		applyScalarOps([]scalarOp{{op: parser.GTR, scalar: 5, returnBool: true}}, values)
-		assert.Equal(t, 0.0, *values[0])
-		assert.Equal(t, 1.0, *values[1])
-	})
-
-	t.Run("scalar on left division", func(t *testing.T) {
-		values := []*float64{f(4)}
-		applyScalarOps([]scalarOp{{op: parser.DIV, scalar: 100, scalarOnLeft: true}}, values)
-		assert.Equal(t, 25.0, *values[0])
-	})
-}
-
-func TestLabelsFromGroupKey(t *testing.T) {
-	lset, err := labelsFromGroupKey(`[["pod","api-0"],["ns","prod"]]`)
-	require.NoError(t, err)
-	assert.Equal(t, "api-0", lset.Get("pod"))
-	assert.Equal(t, "prod", lset.Get("ns"))
-
-	empty, err := labelsFromGroupKey(`[]`)
-	require.NoError(t, err)
-	assert.True(t, empty.IsEmpty())
-}
-
-// testGrid is a 2h query grid ending on a round timestamp.
-func testGrid(stepMs int64) gridContext {
-	return gridContext{startMs: 1_700_000_000_000, endMs: 1_700_007_200_000, stepMs: stepMs}
-}
-
-// A bool comparison returns 0/1, not the sample, so the engine drops
-// __name__; keeping it would change downstream vector matching.
-func TestKeepsName_BoolComparisonDropsName(t *testing.T) {
-	plan, ok := classify(parse(t, `up > bool 0`), testGrid(60_000))
-	require.True(t, ok)
-	assert.False(t, plan.units[0].core.keepsName())
-
-	plan, ok = classify(parse(t, `up > 0`), testGrid(60_000))
-	require.True(t, ok)
-	assert.True(t, plan.units[0].core.keepsName())
-}
-
-// timeSeriesLastToGrid widens its window to max(window, step) — probed on
-// 25.12 — so Last-style units at window < step must fall back or they would
-// resurrect samples the engine's lookback already dropped.
-func TestTryExecuteRange_LastStyleWindowBelowStepTranspiles(t *testing.T) {
-	// These used to fall back because timeSeriesLastToGrid widens its window
-	// to max(window, step). Over sliver-filtered rows the widening is
-	// harmless — the widened window intersected with the data IS the
-	// lookback window — so the gate is gone and both shapes transpile. The
-	// mock returns no series: the point here is the routing, the value
-	// semantics are the parity suite's job.
-	c, store := newTestClient(t)
-	e := &executor{client: c, parser: prometheus.NewParser()}
-
-	start := time.UnixMilli(1_700_000_000_000)
-	end := time.UnixMilli(1_700_003_600_000)
-
-	store.Mock().ExpectQuery("SELECT fingerprint, any\\(labels\\)").WithArgs("up", int64(1_699_999_200_000), int64(1_700_003_600_000)).WillReturnRows(cmock.NewRows(seriesCols, [][]any{}))
-	_, ok, err := e.TryExecuteRange(context.Background(), `sum by (pod) (up)`, start, end, time.Hour)
-	require.NoError(t, err)
-	assert.True(t, ok, "instant selection at step > lookback must transpile")
-
-	store.Mock().ExpectQuery("SELECT fingerprint, any\\(labels\\)").WithArgs("up", int64(1_699_999_200_000), int64(1_700_003_600_000)).WillReturnRows(cmock.NewRows(seriesCols, [][]any{}))
-	_, ok, err = e.TryExecuteRange(context.Background(), `last_over_time(up[10m])`, start, end, time.Hour)
-	require.NoError(t, err)
-	assert.True(t, ok, "last_over_time at range < step must transpile")
-}
-
-// Two metrics collapsing onto one labelset after the name drop, with values
-// on the same grid slot, is the engine's duplicate-labelset error; merging
-// them would invent a series no engine would produce. (Temporally disjoint
-// twins merge instead — see TestMergeSameLabelsetSeries.)
-func TestExecuteUnit_NameCollisionErrors(t *testing.T) {
-	c, store := newTestClient(t)
-	e := &executor{client: c, parser: prometheus.NewParser()}
-
-	store.Mock().ExpectQuery("SELECT fingerprint, any\\(labels\\)").WithArgs("^(?:a|b)$", int64(1_699_999_200_000), int64(1_700_003_600_000)).WillReturnRows(cmock.NewRows(seriesCols, [][]any{
-		{uint64(1), `{"__name__":"a","job":"x"}`},
-		{uint64(2), `{"__name__":"b","job":"x"}`},
-	}))
-	store.Mock().ExpectQuery("SELECT gkey").
-		WithArgs("^(?:a|b)$", int64(1_699_999_200_000), int64(1_700_003_600_000), "a", "b", int64(1_699_999_700_000), int64(1_700_003_600_000)).
-		WillReturnRows(cmock.NewRows(gkeyCols, [][]any{
-			{`[["__name__","a"],["job","x"]]`, []*float64{f64(1)}},
-			{`[["__name__","b"],["job","x"]]`, []*float64{f64(2)}},
-		}))
-
-	plan, ok := classify(parse(t, `rate({__name__=~"a|b"}[5m])`), gridContext{startMs: 1_700_000_000_000, endMs: 1_700_003_600_000, stepMs: 60_000})
-	require.True(t, ok)
-
-	_, err := e.executeUnit(context.Background(), &plan.units[0].core, plan.units[0].grid)
-	require.Error(t, err)
-	assert.Contains(t, err.Error(), "vector cannot contain metrics with the same labelset")
-}
-
-var gkeyCols = []cmock.ColumnType{
-	{Name: "gkey", Type: "String"},
-	{Name: "grid", Type: "Array(Nullable(Float64))"},
-}
-
-func f64(v float64) *float64 { return &v }
-
-// A nameless selector can span metrics whose series alternate in time (one
-// dies inside the lookback before the other appears); after the name drop
-// the engine merges them into ONE series and errors only when two samples
-// share an evaluation timestamp. Pinned by conformance cases
-// operators.test:994/997 (-{job="api"} over http_requests/http_errors).
-func TestMergeSameLabelsetSeries(t *testing.T) {
-	f := func(v float64) *float64 { return &v }
-	api := labels.FromStrings("job", "api")
-
-	out, err := mergeSameLabelsetSeries([]transpiledSeries{
-		{lset: api, values: []*float64{f(-2), nil}},
-		{lset: api, values: []*float64{nil, f(-4)}},
-		{lset: labels.FromStrings("job", "web"), values: []*float64{f(7), nil}},
-	})
-	require.NoError(t, err)
-	require.Len(t, out, 2)
-	assert.Equal(t, []*float64{f(-2), f(-4)}, out[0].values, "temporally disjoint twins must merge into one series")
-
-	_, err = mergeSameLabelsetSeries([]transpiledSeries{
-		{lset: api, values: []*float64{f(1), nil}},
-		{lset: api, values: []*float64{f(2), nil}},
-	})
-	require.Error(t, err, "two values on one evaluation timestamp is the engine's duplicate error")
-	assert.True(t, errors.Ast(err, errors.TypeInvalidInput))
-}
-
-// Hybrid twin case: stripping the synthetic __name__ can leave two engine
-// output series distinguishable only by those names (-metric_a or -metric_b:
-// both {} once real names are dropped). Pinned by conformance cases
-// name_label_dropping.test:137 and operators.test:1016.
-func TestMergeMatrixByLabelset(t *testing.T) {
-	empty := labels.EmptyLabels()
-
-	out, err := mergeMatrixByLabelset(promql.Matrix{
-		{Metric: empty, Floats: []promql.FPoint{{T: 0, F: -1}}},
-		{Metric: empty, Floats: []promql.FPoint{{T: 600_000, F: -4}}},
-	})
-	require.NoError(t, err)
-	require.Len(t, out, 1)
-	assert.Equal(t, []promql.FPoint{{T: 0, F: -1}, {T: 600_000, F: -4}}, out[0].Floats)
-
-	_, err = mergeMatrixByLabelset(promql.Matrix{
-		{Metric: empty, Floats: []promql.FPoint{{T: 0, F: -1}}},
-		{Metric: empty, Floats: []promql.FPoint{{T: 0, F: -3}}},
-	})
-	require.Error(t, err)
-	assert.True(t, errors.Ast(err, errors.TypeInvalidInput))
-}

pkg/prometheus/config.go

@@ -24,10 +24,6 @@ type Config struct {
 
 	// Timeout is the maximum time a query is allowed to run before being aborted.
 	Timeout time.Duration `mapstructure:"timeout"`
-
-	// ProviderName selects the storage provider: "clickhouse" (default) or
-	// "clickhousev2".
-	ProviderName string `mapstructure:"provider"`
 }
 
 func NewConfigFactory() factory.ConfigFactory {
@@ -41,8 +37,7 @@ func newConfig() factory.Config {
 			Path:          "",
 			MaxConcurrent: 20,
 		},
-		Timeout:      2 * time.Minute,
-		ProviderName: "clickhouse",
+		Timeout: 2 * time.Minute,
 	}
 }
 
@@ -50,15 +45,9 @@ func (c Config) Validate() error {
 	if c.Timeout <= 0 {
 		return errors.Newf(errors.TypeInvalidInput, errors.CodeInvalidInput, "prometheus::timeout must be greater than 0")
 	}
-	if c.ProviderName != "" && c.ProviderName != "clickhouse" && c.ProviderName != "clickhousev2" {
-		return errors.Newf(errors.TypeInvalidInput, errors.CodeInvalidInput, "prometheus::provider must be one of [clickhouse, clickhousev2], got %q", c.ProviderName)
-	}
 	return nil
 }
 
 func (c Config) Provider() string {
-	if c.ProviderName == "" {
-		return "clickhouse"
-	}
-	return c.ProviderName
+	return "clickhouse"
 }

pkg/prometheus/prometheus.go

@@ -35,9 +35,3 @@ type StatementRecorder interface {
 type StatementCapturer interface {
 	CapturingStorage() (storage.Queryable, StatementRecorder)
 }
-
-// ProviderClickhouseV2 is the clickhousev2 provider name: the factory
-// registration, the prometheus::provider config value and the
-// X-SigNoz-PromQL-Provider request header all use it, so they cannot drift
-// apart.
-const ProviderClickhouseV2 = "clickhousev2"

pkg/prometheus/traits.go

@@ -1,49 +0,0 @@
-package prometheus
-
-import (
-	"context"
-
-	"github.com/prometheus/prometheus/promql/parser"
-)
-
-type queryTraitsKey struct{}
-
-// QueryTraits carries per-query facts a storage implementation cannot derive
-// from SelectHints alone. Call sites that parse the PromQL expression attach
-// traits to the context before handing it to the engine; storages treat a
-// missing traits value as "unknown" and stay conservative.
-type QueryTraits struct {
-	// SubqueryFree is true when the query contains no subquery expression.
-	// Subquery selectors are evaluated at the subquery's own step, but
-	// SelectHints.Step always carries the top-level step, so step-aligned
-	// storage optimizations (e.g. keeping only the last sample per step
-	// bucket) are safe only when this is true.
-	SubqueryFree bool
-}
-
-// DetectQueryTraits derives QueryTraits from a parsed PromQL expression.
-func DetectQueryTraits(expr parser.Expr) QueryTraits {
-	subqueryFree := true
-	parser.Inspect(expr, func(node parser.Node, _ []parser.Node) error {
-		if _, ok := node.(*parser.SubqueryExpr); ok {
-			subqueryFree = false
-		}
-		return nil
-	})
-	return QueryTraits{SubqueryFree: subqueryFree}
-}
-
-// NewContextWithQueryTraits returns a context carrying the given traits.
-func NewContextWithQueryTraits(ctx context.Context, traits QueryTraits) context.Context {
-	return context.WithValue(ctx, queryTraitsKey{}, traits)
-}
-
-// QueryTraitsFromContext returns the traits attached to ctx, if any.
-//
-// Context is used here, unlike for backend selection, because traits must
-// cross the promql engine to reach storage.Querier.Select, and the engine's
-// interfaces offer no other channel; the alternative is a Prometheus fork.
-func QueryTraitsFromContext(ctx context.Context) (QueryTraits, bool) {
-	traits, ok := ctx.Value(queryTraitsKey{}).(QueryTraits)
-	return traits, ok
-}