chore: go lint fix

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

@@ -190,7 +190,7 @@ services:
       # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
   signoz:
     !!merge <<: *db-depend
-    image: signoz/signoz:v0.116.1
+    image: signoz/signoz:v0.116.0
     ports:
       - "8080:8080" # signoz port
     #   - "6060:6060"     # pprof port

deploy/docker-swarm/docker-compose.yaml

@@ -117,7 +117,7 @@ services:
       # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
   signoz:
     !!merge <<: *db-depend
-    image: signoz/signoz:v0.116.1
+    image: signoz/signoz:v0.116.0
     ports:
       - "8080:8080" # signoz port
     volumes:

deploy/docker/docker-compose.ha.yaml

@@ -181,7 +181,7 @@ services:
       # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
   signoz:
     !!merge <<: *db-depend
-    image: signoz/signoz:${VERSION:-v0.116.1}
+    image: signoz/signoz:${VERSION:-v0.116.0}
     container_name: signoz
     ports:
       - "8080:8080" # signoz port

deploy/docker/docker-compose.yaml

@@ -109,7 +109,7 @@ services:
       # - ../common/clickhouse/storage.xml:/etc/clickhouse-server/config.d/storage.xml
   signoz:
     !!merge <<: *db-depend
-    image: signoz/signoz:${VERSION:-v0.116.1}
+    image: signoz/signoz:${VERSION:-v0.116.0}
     container_name: signoz
     ports:
       - "8080:8080" # signoz port

go.mod

@@ -11,6 +11,7 @@ require (
 	github.com/SigNoz/signoz-otel-collector v0.144.2
 	github.com/antlr4-go/antlr/v4 v4.13.1
 	github.com/antonmedv/expr v1.15.3
+	github.com/bytedance/sonic v1.14.1
 	github.com/cespare/xxhash/v2 v2.3.0
 	github.com/coreos/go-oidc/v3 v3.17.0
 	github.com/dgraph-io/ristretto/v2 v2.3.0
@@ -105,7 +106,6 @@ require (
 	github.com/aws/aws-sdk-go-v2/service/sts v1.41.6 // indirect
 	github.com/aws/smithy-go v1.24.0 // indirect
 	github.com/bytedance/gopkg v0.1.3 // indirect
-	github.com/bytedance/sonic v1.14.1 // indirect
 	github.com/bytedance/sonic/loader v0.3.0 // indirect
 	github.com/cloudwego/base64x v0.1.6 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.8 // indirect

pkg/http/middleware/authz.go

@@ -9,6 +9,7 @@ import (
 	"github.com/SigNoz/signoz/pkg/http/render"
 	"github.com/SigNoz/signoz/pkg/modules/organization"
 	"github.com/SigNoz/signoz/pkg/types/authtypes"
+	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
 	"github.com/SigNoz/signoz/pkg/valuer"
 	"github.com/gorilla/mux"
 )
@@ -40,7 +41,9 @@ func (middleware *AuthZ) ViewAccess(next http.HandlerFunc) http.HandlerFunc {
 			return
 		}
 
-		if claims.IdentNProvider == authtypes.IdentNProviderAPIkey.StringValue() {
+		commentCtx := ctxtypes.CommentFromContext(ctx)
+		authtype, ok := commentCtx.Map()["auth_type"]
+		if ok && (authtype == authtypes.IdentNProviderAPIkey.StringValue()) {
 			if err := claims.IsViewer(); err != nil {
 				middleware.logger.WarnContext(ctx, authzDeniedMessage, "claims", claims)
 				render.Error(rw, err)
@@ -90,7 +93,9 @@ func (middleware *AuthZ) EditAccess(next http.HandlerFunc) http.HandlerFunc {
 			return
 		}
 
-		if claims.IdentNProvider == authtypes.IdentNProviderAPIkey.StringValue() {
+		commentCtx := ctxtypes.CommentFromContext(ctx)
+		authtype, ok := commentCtx.Map()["auth_type"]
+		if ok && (authtype == authtypes.IdentNProviderAPIkey.StringValue()) {
 			if err := claims.IsEditor(); err != nil {
 				middleware.logger.WarnContext(ctx, authzDeniedMessage, "claims", claims)
 				render.Error(rw, err)
@@ -139,7 +144,9 @@ func (middleware *AuthZ) AdminAccess(next http.HandlerFunc) http.HandlerFunc {
 			return
 		}
 
-		if claims.IdentNProvider == authtypes.IdentNProviderAPIkey.StringValue() {
+		commentCtx := ctxtypes.CommentFromContext(ctx)
+		authtype, ok := commentCtx.Map()["auth_type"]
+		if ok && (authtype == authtypes.IdentNProviderAPIkey.StringValue()) {
 			if err := claims.IsAdmin(); err != nil {
 				middleware.logger.WarnContext(ctx, authzDeniedMessage, "claims", claims)
 				render.Error(rw, err)

pkg/identn/apikeyidentn/identn.go

@@ -101,8 +101,13 @@ func (provider *provider) GetIdentity(req *http.Request) (*authtypes.Identity, e
 		return nil, err
 	}
 
-	identity := authtypes.NewIdentity(user.ID, user.OrgID, user.Email, apiKey.Role, provider.Name())
-	return identity, nil
+	identity := authtypes.Identity{
+		UserID: user.ID,
+		Role:   apiKey.Role,
+		Email:  user.Email,
+		OrgID:  user.OrgID,
+	}
+	return &identity, nil
 }
 
 func (provider *provider) Post(ctx context.Context, _ *http.Request, _ authtypes.Claims) {

pkg/modules/cloudintegration/cloudintegration.go

@@ -1,65 +0,0 @@
-package cloudintegration
-
-import (
-	"context"
-	"net/http"
-
-	citypes "github.com/SigNoz/signoz/pkg/types/cloudintegrationtypes"
-	"github.com/SigNoz/signoz/pkg/types/dashboardtypes"
-	"github.com/SigNoz/signoz/pkg/valuer"
-)
-
-type Module interface {
-	CreateAccount(ctx context.Context, account *citypes.Account) error
-
-	// GetAccount returns cloud integration account
-	GetAccount(ctx context.Context, orgID, accountID valuer.UUID) (*citypes.Account, error)
-
-	// ListAccounts lists accounts where agent is connected
-	ListAccounts(ctx context.Context, orgID valuer.UUID) ([]*citypes.Account, error)
-
-	// UpdateAccount updates the cloud integration account for a specific organization.
-	UpdateAccount(ctx context.Context, account *citypes.Account) error
-
-	// DisconnectAccount soft deletes/removes a cloud integration account.
-	DisconnectAccount(ctx context.Context, orgID, accountID valuer.UUID) error
-
-	// GetConnectionArtifact returns cloud provider specific connection information,
-	// client side handles how this information is shown
-	GetConnectionArtifact(ctx context.Context, account *citypes.Account, req *citypes.ConnectionArtifactRequest) (*citypes.ConnectionArtifact, error)
-
-	// ListServicesMetadata returns the list of services metadata for a cloud provider attached with the integrationID.
-	// This just returns a summary of the service and not the whole service definition
-	ListServicesMetadata(ctx context.Context, orgID valuer.UUID, integrationID *valuer.UUID) ([]*citypes.ServiceMetadata, error)
-
-	// GetService returns service definition details for a serviceID. This returns config and
-	// other details required to show in service details page on web client.
-	GetService(ctx context.Context, orgID valuer.UUID, integrationID *valuer.UUID, serviceID string) (*citypes.Service, error)
-
-	// UpdateService updates cloud integration service
-	UpdateService(ctx context.Context, orgID valuer.UUID, service *citypes.CloudIntegrationService) error
-
-	// AgentCheckIn is called by agent to heartbeat and get latest config in response.
-	AgentCheckIn(ctx context.Context, orgID valuer.UUID, req *citypes.AgentCheckInRequest) (*citypes.AgentCheckInResponse, error)
-
-	// GetDashboardByID returns dashboard JSON for a given dashboard id.
-	// this only returns the dashboard when the service (embedded in dashboard id) is enabled
-	// in the org for any cloud integration account
-	GetDashboardByID(ctx context.Context, orgID valuer.UUID, id string) (*dashboardtypes.Dashboard, error)
-
-	// ListDashboards returns list of dashboards across all connected cloud integration accounts
-	// for enabled services in the org. This list gets added to dashboard list page
-	ListDashboards(ctx context.Context, orgID valuer.UUID) ([]*dashboardtypes.Dashboard, error)
-}
-
-type Handler interface {
-	GetConnectionArtifact(http.ResponseWriter, *http.Request)
-	ListAccounts(http.ResponseWriter, *http.Request)
-	GetAccount(http.ResponseWriter, *http.Request)
-	UpdateAccount(http.ResponseWriter, *http.Request)
-	DisconnectAccount(http.ResponseWriter, *http.Request)
-	ListServicesMetadata(http.ResponseWriter, *http.Request)
-	GetService(http.ResponseWriter, *http.Request)
-	UpdateService(http.ResponseWriter, *http.Request)
-	AgentCheckIn(http.ResponseWriter, *http.Request)
-}

pkg/modules/promote/implpromote/module.go

@@ -78,7 +78,7 @@ 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, telemetrylogs.BodyJSONColumnPrefix)
 		path = telemetrytypes.BodyJSONStringSearchPrefix + path
 		response = append(response, promotetypes.PromotePath{
 			Path:    path,
@@ -163,7 +163,7 @@ func (m *module) PromoteAndIndexPaths(
 			}
 		}
 		if len(it.Indexes) > 0 {
-			parentColumn := telemetrylogs.LogsV2BodyV2Column
+			parentColumn := telemetrylogs.LogsV2BodyJSONColumn
 			// 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

pkg/querier/builder_query.go

@@ -10,11 +10,13 @@ import (
 
 	"github.com/ClickHouse/clickhouse-go/v2"
 	"github.com/SigNoz/signoz/pkg/errors"
+	"github.com/SigNoz/signoz/pkg/telemetrylogs"
 	"github.com/SigNoz/signoz/pkg/telemetrystore"
 	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
 	"github.com/SigNoz/signoz/pkg/types/instrumentationtypes"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
+	"github.com/bytedance/sonic"
 )
 
 type builderQuery[T any] struct {
@@ -260,6 +262,40 @@ func (q *builderQuery[T]) executeWithContext(ctx context.Context, query string,
 		return nil, err
 	}
 
+	// merge body_json and promoted into body
+	if q.spec.Signal == telemetrytypes.SignalLogs {
+		switch typedPayload := payload.(type) {
+		case *qbtypes.RawData:
+			for _, rr := range typedPayload.Rows {
+				seeder := func() error {
+					body, ok := rr.Data[telemetrylogs.LogsV2BodyJSONColumn].(map[string]any)
+					if !ok {
+						return nil
+					}
+					promoted, ok := rr.Data[telemetrylogs.LogsV2BodyPromotedColumn].(map[string]any)
+					if !ok {
+						return nil
+					}
+					seed(promoted, body)
+					str, err := sonic.MarshalString(body)
+					if err != nil {
+						return errors.Wrapf(err, errors.TypeInternal, errors.CodeInternal, "failed to marshal body")
+					}
+					rr.Data["body"] = str
+					return nil
+				}
+				err := seeder()
+				if err != nil {
+					return nil, err
+				}
+
+				delete(rr.Data, telemetrylogs.LogsV2BodyJSONColumn)
+				delete(rr.Data, telemetrylogs.LogsV2BodyPromotedColumn)
+			}
+			payload = typedPayload
+		}
+	}
+
 	return &qbtypes.Result{
 		Type:  q.kind,
 		Value: payload,
@@ -387,3 +423,18 @@ func decodeCursor(cur string) (int64, error) {
 	}
 	return strconv.ParseInt(string(b), 10, 64)
 }
+
+func seed(promoted map[string]any, body map[string]any) {
+	for key, fromValue := range promoted {
+		if toValue, ok := body[key]; !ok {
+			body[key] = fromValue
+		} else {
+			if fromValue, ok := fromValue.(map[string]any); ok {
+				if toValue, ok := toValue.(map[string]any); ok {
+					seed(fromValue, toValue)
+					body[key] = toValue
+				}
+			}
+		}
+	}
+}

pkg/querier/consume.go

@@ -14,6 +14,7 @@ import (
 	"github.com/ClickHouse/clickhouse-go/v2/lib/driver"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
+	"github.com/bytedance/sonic"
 )
 
 var (
@@ -68,6 +69,7 @@ func readAsTimeSeries(rows driver.Rows, queryWindow *qbtypes.TimeRange, step qbt
 		key string // deterministic join of label values
 	}
 	seriesMap := map[sKey]*qbtypes.TimeSeries{}
+	var keyOrder []sKey // preserves ClickHouse row-arrival order
 
 	stepMs := uint64(step.Duration.Milliseconds())
 
@@ -218,6 +220,7 @@ func readAsTimeSeries(rows driver.Rows, queryWindow *qbtypes.TimeRange, step qbt
 			if !ok {
 				series = &qbtypes.TimeSeries{Labels: lblObjs}
 				seriesMap[key] = series
+				keyOrder = append(keyOrder, key)
 			}
 			series.Values = append(series.Values, &qbtypes.TimeSeriesValue{
 				Timestamp: ts,
@@ -249,8 +252,8 @@ func readAsTimeSeries(rows driver.Rows, queryWindow *qbtypes.TimeRange, step qbt
 			Alias: "__result_" + strconv.Itoa(i),
 		}
 	}
-	for k, s := range seriesMap {
-		buckets[k.agg].Series = append(buckets[k.agg].Series, s)
+	for _, k := range keyOrder {
+		buckets[k.agg].Series = append(buckets[k.agg].Series, seriesMap[k])
 	}
 
 	var nonEmpty []*qbtypes.AggregationBucket
@@ -393,11 +396,17 @@ func readAsRaw(rows driver.Rows, queryName string) (*qbtypes.RawData, error) {
 
 			// de-reference the typed pointer to any
 			val := reflect.ValueOf(cellPtr).Elem().Interface()
-			// Post-process JSON columns: normalize into String value
+
+			// Post-process JSON columns: normalize into structured values
 			if strings.HasPrefix(strings.ToUpper(colTypes[i].DatabaseTypeName()), "JSON") {
 				switch x := val.(type) {
 				case []byte:
-					val = string(x)
+					if len(x) > 0 {
+						var v any
+						if err := sonic.Unmarshal(x, &v); err == nil {
+							val = v
+						}
+					}
 				default:
 					// already a structured type (map[string]any, []any, etc.)
 				}

pkg/querier/postprocess.go

@@ -185,22 +185,6 @@ func postProcessMetricQuery(
 	query qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation],
 	req *qbtypes.QueryRangeRequest,
 ) *qbtypes.Result {
-
-	config := query.Aggregations[0]
-	spaceAggOrderBy := fmt.Sprintf("%s(%s)", config.SpaceAggregation.StringValue(), config.MetricName)
-	timeAggOrderBy := fmt.Sprintf("%s(%s)", config.TimeAggregation.StringValue(), config.MetricName)
-	timeSpaceAggOrderBy := fmt.Sprintf("%s(%s(%s))", config.SpaceAggregation.StringValue(), config.TimeAggregation.StringValue(), config.MetricName)
-
-	for idx := range query.Order {
-		if query.Order[idx].Key.Name == spaceAggOrderBy ||
-			query.Order[idx].Key.Name == timeAggOrderBy ||
-			query.Order[idx].Key.Name == timeSpaceAggOrderBy {
-			query.Order[idx].Key.Name = qbtypes.DefaultOrderByKey
-		}
-	}
-
-	result = q.applySeriesLimit(result, query.Limit, query.Order)
-
 	if len(query.Functions) > 0 {
 		step := query.StepInterval.Duration.Milliseconds()
 		functions := q.prepareFillZeroArgsWithStep(query.Functions, req, step)

pkg/query-service/rules/prom_rule_task.go

@@ -7,14 +7,12 @@ import (
 	"sync"
 	"time"
 
-	"log/slog"
-
-	"github.com/SigNoz/signoz/pkg/types/authtypes"
 	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
 	ruletypes "github.com/SigNoz/signoz/pkg/types/ruletypes"
 	"github.com/SigNoz/signoz/pkg/valuer"
 	opentracing "github.com/opentracing/opentracing-go"
 	plabels "github.com/prometheus/prometheus/model/labels"
+	"log/slog"
 )
 
 // PromRuleTask is a promql rule executor
@@ -373,7 +371,7 @@ func (g *PromRuleTask) Eval(ctx context.Context, ts time.Time) {
 
 			comment := ctxtypes.CommentFromContext(ctx)
 			comment.Set("rule_id", rule.ID())
-			comment.Set("identn_provider", authtypes.IdentNProviderInternal.StringValue())
+			comment.Set("auth_type", "internal")
 			ctx = ctxtypes.NewContextWithComment(ctx, comment)
 
 			_, err := rule.Eval(ctx, ts)

pkg/query-service/rules/rule_task.go

@@ -10,7 +10,6 @@ import (
 	"log/slog"
 
 	"github.com/SigNoz/signoz/pkg/query-service/utils/labels"
-	"github.com/SigNoz/signoz/pkg/types/authtypes"
 	"github.com/SigNoz/signoz/pkg/types/ctxtypes"
 	ruletypes "github.com/SigNoz/signoz/pkg/types/ruletypes"
 	"github.com/SigNoz/signoz/pkg/valuer"
@@ -359,7 +358,7 @@ func (g *RuleTask) Eval(ctx context.Context, ts time.Time) {
 
 			comment := ctxtypes.CommentFromContext(ctx)
 			comment.Set("rule_id", rule.ID())
-			comment.Set("identn_provider", authtypes.IdentNProviderInternal.StringValue())
+			comment.Set("auth_type", "internal")
 			ctx = ctxtypes.NewContextWithComment(ctx, comment)
 
 			_, err := rule.Eval(ctx, ts)

pkg/querybuilder/fallback_expr.go

@@ -219,6 +219,7 @@ func DataTypeCollisionHandledFieldName(key *telemetrytypes.TelemetryFieldKey, va
 			// we don't have a toBoolOrNull in ClickHouse, so we need to convert the bool to a string
 			value = fmt.Sprintf("%t", v)
 		}
+
 	case telemetrytypes.FieldDataTypeInt64,
 		telemetrytypes.FieldDataTypeArrayInt64,
 		telemetrytypes.FieldDataTypeNumber,

pkg/querybuilder/where_clause_visitor.go

@@ -313,30 +313,37 @@ func (v *filterExpressionVisitor) VisitPrimary(ctx *grammar.PrimaryContext) any
 			return ""
 		}
 		child := ctx.GetChild(0)
-		var searchText string
 		if keyCtx, ok := child.(*grammar.KeyContext); ok {
 			// create a full text search condition on the body field
-			searchText = keyCtx.GetText()
+
+			keyText := keyCtx.GetText()
+			cond, err := v.conditionBuilder.ConditionFor(context.Background(), v.fullTextColumn, qbtypes.FilterOperatorRegexp, FormatFullTextSearch(keyText), v.builder, v.startNs, v.endNs)
+			if err != nil {
+				v.errors = append(v.errors, fmt.Sprintf("failed to build full text search condition: %s", err.Error()))
+				return ""
+			}
+			return cond
 		} else if valCtx, ok := child.(*grammar.ValueContext); ok {
+			var text string
 			if valCtx.QUOTED_TEXT() != nil {
-				searchText = trimQuotes(valCtx.QUOTED_TEXT().GetText())
+				text = trimQuotes(valCtx.QUOTED_TEXT().GetText())
 			} else if valCtx.NUMBER() != nil {
-				searchText = valCtx.NUMBER().GetText()
+				text = valCtx.NUMBER().GetText()
 			} else if valCtx.BOOL() != nil {
-				searchText = valCtx.BOOL().GetText()
+				text = valCtx.BOOL().GetText()
 			} else if valCtx.KEY() != nil {
-				searchText = valCtx.KEY().GetText()
+				text = valCtx.KEY().GetText()
 			} else {
 				v.errors = append(v.errors, fmt.Sprintf("unsupported value type: %s", valCtx.GetText()))
 				return ""
 			}
+			cond, err := v.conditionBuilder.ConditionFor(context.Background(), v.fullTextColumn, qbtypes.FilterOperatorRegexp, FormatFullTextSearch(text), v.builder, v.startNs, v.endNs)
+			if err != nil {
+				v.errors = append(v.errors, fmt.Sprintf("failed to build full text search condition: %s", err.Error()))
+				return ""
+			}
+			return cond
 		}
-		cond, err := v.conditionBuilder.ConditionFor(context.Background(), v.fullTextColumn, qbtypes.FilterOperatorRegexp, FormatFullTextSearch(searchText), v.builder, v.startNs, v.endNs)
-		if err != nil {
-			v.errors = append(v.errors, fmt.Sprintf("failed to build full text search condition: %s", err.Error()))
-			return ""
-		}
-		return cond
 	}
 
 	return "" // Should not happen with valid input
@@ -376,7 +383,6 @@ func (v *filterExpressionVisitor) VisitComparison(ctx *grammar.ComparisonContext
 		for _, key := range keys {
 			condition, err := v.conditionBuilder.ConditionFor(context.Background(), key, op, nil, v.builder, v.startNs, v.endNs)
 			if err != nil {
-				v.errors = append(v.errors, fmt.Sprintf("failed to build condition: %s", err.Error()))
 				return ""
 			}
 			conds = append(conds, condition)
@@ -642,6 +648,7 @@ func (v *filterExpressionVisitor) VisitValueList(ctx *grammar.ValueListContext)
 
 // VisitFullText handles standalone quoted strings for full-text search
 func (v *filterExpressionVisitor) VisitFullText(ctx *grammar.FullTextContext) any {
+
 	if v.skipFullTextFilter {
 		return ""
 	}
@@ -663,7 +670,6 @@ func (v *filterExpressionVisitor) VisitFullText(ctx *grammar.FullTextContext) an
 		v.errors = append(v.errors, fmt.Sprintf("failed to build full text search condition: %s", err.Error()))
 		return ""
 	}
-
 	return cond
 }
 

pkg/telemetrylogs/condition_builder.go

@@ -3,12 +3,14 @@ package telemetrylogs
 import (
 	"context"
 	"fmt"
+	"slices"
 
 	schema "github.com/SigNoz/signoz-otel-collector/cmd/signozschemamigrator/schema_migrator"
 	"github.com/SigNoz/signoz/pkg/errors"
 	"github.com/SigNoz/signoz/pkg/querybuilder"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
+	"golang.org/x/exp/maps"
 
 	"github.com/huandu/go-sqlbuilder"
 )
@@ -33,7 +35,7 @@ func (c *conditionBuilder) conditionFor(
 		return "", err
 	}
 
-	if column.Type.GetType() == schema.ColumnTypeEnumJSON && querybuilder.BodyJSONQueryEnabled && key.Name != messageSubField {
+	if column.Type.GetType() == schema.ColumnTypeEnumJSON && querybuilder.BodyJSONQueryEnabled {
 		valueType, value := InferDataType(value, operator, key)
 		cond, err := NewJSONConditionBuilder(key, valueType).buildJSONCondition(operator, value, sb)
 		if err != nil {
@@ -52,14 +54,14 @@ func (c *conditionBuilder) conditionFor(
 	}
 
 	// Check if this is a body JSON search - either by FieldContext
-	if key.FieldContext == telemetrytypes.FieldContextBody && !querybuilder.BodyJSONQueryEnabled {
+	if key.FieldContext == telemetrytypes.FieldContextBody {
 		tblFieldName, value = GetBodyJSONKey(ctx, key, operator, value)
 	}
 
 	tblFieldName, value = querybuilder.DataTypeCollisionHandledFieldName(key, value, tblFieldName, operator)
 
 	// make use of case insensitive index for body
-	if tblFieldName == "body" || tblFieldName == messageSubColumn {
+	if tblFieldName == "body" {
 		switch operator {
 		case qbtypes.FilterOperatorLike:
 			return sb.ILike(tblFieldName, value), nil
@@ -106,6 +108,7 @@ func (c *conditionBuilder) conditionFor(
 		return sb.ILike(tblFieldName, fmt.Sprintf("%%%s%%", value)), nil
 	case qbtypes.FilterOperatorNotContains:
 		return sb.NotILike(tblFieldName, fmt.Sprintf("%%%s%%", value)), nil
+
 	case qbtypes.FilterOperatorRegexp:
 		// Note: Escape $$ to $$$$ to avoid sqlbuilder interpreting materialized $ signs
 		// Only needed because we are using sprintf instead of sb.Match (not implemented in sqlbuilder)
@@ -175,8 +178,9 @@ func (c *conditionBuilder) conditionFor(
 		case schema.ColumnTypeEnumJSON:
 			if operator == qbtypes.FilterOperatorExists {
 				return sb.IsNotNull(tblFieldName), nil
+			} else {
+				return sb.IsNull(tblFieldName), nil
 			}
-			return sb.IsNull(tblFieldName), nil
 		case schema.ColumnTypeEnumLowCardinality:
 			switch elementType := column.Type.(schema.LowCardinalityColumnType).ElementType; elementType.GetType() {
 			case schema.ColumnTypeEnumString:
@@ -243,30 +247,19 @@ func (c *conditionBuilder) ConditionFor(
 		return "", err
 	}
 
-	// Skip adding exists filter for intrinsic fields i.e. Table level log context fields
-	buildExistCondition := operator.AddDefaultExistsFilter()
-	switch key.FieldContext {
-	case telemetrytypes.FieldContextLog, telemetrytypes.FieldContextScope:
-		// pass; No need to build exist condition for top level columns
-		// immediately return
-		return condition, nil
-	case telemetrytypes.FieldContextResource, telemetrytypes.FieldContextAttribute:
-		// build exist condition for resource and attribute fields based on filter operator
-	case telemetrytypes.FieldContextBody:
-		// Querying JSON fields already account for Nullability of fields
-		// so additional exists checks are not needed
-		if querybuilder.BodyJSONQueryEnabled {
+	if !(key.FieldContext == telemetrytypes.FieldContextBody && querybuilder.BodyJSONQueryEnabled) && operator.AddDefaultExistsFilter() {
+		// skip adding exists filter for intrinsic fields
+		// with an exception for body json search
+		field, _ := c.fm.FieldFor(ctx, key)
+		if slices.Contains(maps.Keys(IntrinsicFields), field) && key.FieldContext != telemetrytypes.FieldContextBody {
 			return condition, nil
 		}
-	}
 
-	if buildExistCondition {
 		existsCondition, err := c.conditionFor(ctx, key, qbtypes.FilterOperatorExists, nil, sb)
 		if err != nil {
 			return "", err
 		}
 		return sb.And(condition, existsCondition), nil
 	}
-
 	return condition, nil
 }

pkg/telemetrylogs/condition_builder_test.go

@@ -127,8 +127,7 @@ func TestConditionFor(t *testing.T) {
 		{
 			name: "Contains operator - body",
 			key: telemetrytypes.TelemetryFieldKey{
-				Name:         "body",
-				FieldContext: telemetrytypes.FieldContextLog,
+				Name: "body",
 			},
 			operator:      qbtypes.FilterOperatorContains,
 			value:         521509198310,

pkg/telemetrylogs/const.go

@@ -1,10 +1,7 @@
 package telemetrylogs
 
 import (
-	"fmt"
-
 	"github.com/SigNoz/signoz-otel-collector/constants"
-	"github.com/SigNoz/signoz/pkg/querybuilder"
 	qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
 	"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
 )
@@ -20,7 +17,7 @@ const (
 	LogsV2TimestampColumn         = "timestamp"
 	LogsV2ObservedTimestampColumn = "observed_timestamp"
 	LogsV2BodyColumn              = "body"
-	LogsV2BodyV2Column            = constants.BodyV2Column
+	LogsV2BodyJSONColumn          = constants.BodyV2Column
 	LogsV2BodyPromotedColumn      = constants.BodyPromotedColumn
 	LogsV2TraceIDColumn           = "trace_id"
 	LogsV2SpanIDColumn            = "span_id"
@@ -37,14 +34,8 @@ const (
 	LogsV2ResourcesStringColumn  = "resources_string"
 	LogsV2ScopeStringColumn      = "scope_string"
 
-	BodyV2ColumnPrefix       = constants.BodyV2ColumnPrefix
+	BodyJSONColumnPrefix     = constants.BodyV2ColumnPrefix
 	BodyPromotedColumnPrefix = constants.BodyPromotedColumnPrefix
-
-	// messageSubColumn is the ClickHouse sub-column that body searches map to
-	// when BodyJSONQueryEnabled is true.
-	messageSubField          = "message"
-	messageSubColumn         = "body_v2.message"
-	bodySearchDefaultWarning = "body searches default to `body.message:string`. Use `body.<key>` to search a different field inside body"
 )
 
 var (
@@ -127,11 +118,3 @@ var (
 		},
 	}
 )
-
-func bodyAliasExpression() string {
-	if !querybuilder.BodyJSONQueryEnabled {
-		return LogsV2BodyColumn
-	}
-
-	return fmt.Sprintf("%s as body", LogsV2BodyV2Column)
-}

pkg/telemetrylogs/field_mapper.go

@@ -30,8 +30,7 @@ var (
 		"severity_text":      {Name: "severity_text", Type: schema.LowCardinalityColumnType{ElementType: schema.ColumnTypeString}},
 		"severity_number":    {Name: "severity_number", Type: schema.ColumnTypeUInt8},
 		"body":               {Name: "body", Type: schema.ColumnTypeString},
-		messageSubColumn:     {Name: messageSubColumn, Type: schema.ColumnTypeString},
-		LogsV2BodyV2Column: {Name: LogsV2BodyV2Column, Type: schema.JSONColumnType{
+		LogsV2BodyJSONColumn: {Name: LogsV2BodyJSONColumn, Type: schema.JSONColumnType{
 			MaxDynamicTypes: utils.ToPointer(uint(32)),
 			MaxDynamicPaths: utils.ToPointer(uint(0)),
 		}},
@@ -89,26 +88,21 @@ func (m *fieldMapper) getColumn(_ context.Context, key *telemetrytypes.Telemetry
 			return logsV2Columns["attributes_bool"], nil
 		}
 	case telemetrytypes.FieldContextBody:
-		// Body context is for JSON body fields. Use body_v2 if feature flag is enabled.
+		// Body context is for JSON body fields
+		// Use body_json if feature flag is enabled
 		if querybuilder.BodyJSONQueryEnabled {
-			if key.Name == messageSubField {
-				return logsV2Columns[messageSubColumn], nil
-			}
-			return logsV2Columns[LogsV2BodyV2Column], nil
+			return logsV2Columns[LogsV2BodyJSONColumn], nil
 		}
 		// Fall back to legacy body column
 		return logsV2Columns["body"], nil
 	case telemetrytypes.FieldContextLog, telemetrytypes.FieldContextUnspecified:
-		if key.Name == LogsV2BodyColumn && querybuilder.BodyJSONQueryEnabled {
-			return logsV2Columns[messageSubColumn], nil
-		}
 		col, ok := logsV2Columns[key.Name]
 		if !ok {
 			// check if the key has body JSON search
 			if strings.HasPrefix(key.Name, telemetrytypes.BodyJSONStringSearchPrefix) {
-				// Use body_v2 if feature flag is enabled and we have a body condition builder
+				// Use body_json if feature flag is enabled and we have a body condition builder
 				if querybuilder.BodyJSONQueryEnabled {
-					return logsV2Columns[LogsV2BodyV2Column], nil
+					return logsV2Columns[LogsV2BodyJSONColumn], nil
 				}
 				// Fall back to legacy body column
 				return logsV2Columns["body"], nil
@@ -144,10 +138,6 @@ func (m *fieldMapper) FieldFor(ctx context.Context, key *telemetrytypes.Telemetr
 			}
 			return fmt.Sprintf("multiIf(%s.`%s` IS NOT NULL, %s.`%s`::String, mapContains(%s, '%s'), %s, NULL)", column.Name, key.Name, column.Name, key.Name, oldColumn.Name, key.Name, oldKeyName), nil
 		case telemetrytypes.FieldContextBody:
-			if key.Name == messageSubField {
-				return messageSubColumn, nil
-			}
-
 			if key.JSONDataType == nil {
 				return "", qbtypes.ErrColumnNotFound
 			}
@@ -256,37 +246,34 @@ func (m *fieldMapper) buildFieldForJSON(key *telemetrytypes.TelemetryFieldKey) (
 		node := plan[0]
 
 		expr := fmt.Sprintf("dynamicElement(%s, '%s')", node.FieldPath(), node.TerminalConfig.ElemType.StringValue())
-		// TODO(Piyush): Promoted path logic commented out. Materialized now means type hint
-		// promotion will be extracted from key field evolution
-		// (direct sub-column access), not a promoted body_promoted.* column.
-		// if key.Materialized {
-		// 	if len(plan) < 2 {
-		// 		return "", errors.Newf(errors.TypeUnexpected, CodePromotedPlanMissing,
-		// 			"plan length is less than 2 for promoted path: %s", key.Name)
-		// 	}
+		if key.Materialized {
+			if len(plan) < 2 {
+				return "", errors.Newf(errors.TypeUnexpected, CodePromotedPlanMissing,
+					"plan length is less than 2 for promoted path: %s", key.Name)
+			}
 
-		// 	node := plan[1]
-		// 	promotedExpr := fmt.Sprintf(
-		// 		"dynamicElement(%s, '%s')",
-		// 		node.FieldPath(),
-		// 		node.TerminalConfig.ElemType.StringValue(),
-		// 	)
+			node := plan[1]
+			promotedExpr := fmt.Sprintf(
+				"dynamicElement(%s, '%s')",
+				node.FieldPath(),
+				node.TerminalConfig.ElemType.StringValue(),
+			)
 
-		// 	// dynamicElement returns NULL for scalar types or an empty array for array types.
-		// 	if node.TerminalConfig.ElemType.IsArray {
-		// 		expr = fmt.Sprintf(
-		// 			"if(length(%s) > 0, %s, %s)",
-		// 			promotedExpr,
-		// 			promotedExpr,
-		// 			expr,
-		// 		)
-		// 	} else {
-		// 		// promoted column first then body_json column
-		// 		// TODO(Piyush): Change this in future for better performance
-		// 		expr = fmt.Sprintf("coalesce(%s, %s)", promotedExpr, expr)
-		// 	}
+			// dynamicElement returns NULL for scalar types or an empty array for array types.
+			if node.TerminalConfig.ElemType.IsArray {
+				expr = fmt.Sprintf(
+					"if(length(%s) > 0, %s, %s)",
+					promotedExpr,
+					promotedExpr,
+					expr,
+				)
+			} else {
+				// promoted column first then body_json column
+				// TODO(Piyush): Change this in future for better performance
+				expr = fmt.Sprintf("coalesce(%s, %s)", promotedExpr, expr)
+			}
 
-		// }
+		}
 
 		return expr, nil
 	}

pkg/telemetrylogs/json_condition_builder.go

@@ -30,7 +30,7 @@ func NewJSONConditionBuilder(key *telemetrytypes.TelemetryFieldKey, valueType te
 	return &jsonConditionBuilder{key: key, valueType: telemetrytypes.MappingFieldDataTypeToJSONDataType[valueType]}
 }
 
-// BuildCondition builds the full WHERE condition for body_v2 JSON paths
+// BuildCondition builds the full WHERE condition for body_json JSON paths
 func (c *jsonConditionBuilder) buildJSONCondition(operator qbtypes.FilterOperator, value any, sb *sqlbuilder.SelectBuilder) (string, error) {
 	conditions := []string{}
 	for _, node := range c.key.JSONPlan {
@@ -40,7 +40,6 @@ func (c *jsonConditionBuilder) buildJSONCondition(operator qbtypes.FilterOperato
 		}
 		conditions = append(conditions, condition)
 	}
-
 	return sb.Or(conditions...), nil
 }
 
@@ -289,9 +288,9 @@ func (c *jsonConditionBuilder) applyOperator(sb *sqlbuilder.SelectBuilder, field
 		}
 		return sb.NotIn(fieldExpr, values...), nil
 	case qbtypes.FilterOperatorExists:
-		return sb.IsNotNull(fieldExpr), nil
+		return fmt.Sprintf("%s IS NOT NULL", fieldExpr), nil
 	case qbtypes.FilterOperatorNotExists:
-		return sb.IsNull(fieldExpr), nil
+		return fmt.Sprintf("%s IS NULL", fieldExpr), nil
 	// between and not between
 	case qbtypes.FilterOperatorBetween, qbtypes.FilterOperatorNotBetween:
 		values, ok := value.([]any)

pkg/telemetrylogs/statement_builder.go

@@ -65,7 +65,7 @@ func (b *logQueryStatementBuilder) Build(
 	start = querybuilder.ToNanoSecs(start)
 	end = querybuilder.ToNanoSecs(end)
 
-	keySelectors, warnings := getKeySelectors(query)
+	keySelectors := getKeySelectors(query)
 	keys, _, err := b.metadataStore.GetKeysMulti(ctx, keySelectors)
 	if err != nil {
 		return nil, err
@@ -76,29 +76,20 @@ func (b *logQueryStatementBuilder) Build(
 	// Create SQL builder
 	q := sqlbuilder.NewSelectBuilder()
 
-	var stmt *qbtypes.Statement
 	switch requestType {
 	case qbtypes.RequestTypeRaw, qbtypes.RequestTypeRawStream:
-		stmt, err = b.buildListQuery(ctx, q, query, start, end, keys, variables)
+		return b.buildListQuery(ctx, q, query, start, end, keys, variables)
 	case qbtypes.RequestTypeTimeSeries:
-		stmt, err = b.buildTimeSeriesQuery(ctx, q, query, start, end, keys, variables)
+		return b.buildTimeSeriesQuery(ctx, q, query, start, end, keys, variables)
 	case qbtypes.RequestTypeScalar:
-		stmt, err = b.buildScalarQuery(ctx, q, query, start, end, keys, false, variables)
-	default:
-		return nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported request type: %s", requestType)
+		return b.buildScalarQuery(ctx, q, query, start, end, keys, false, variables)
 	}
 
-	if err != nil {
-		return nil, err
-	}
-
-	stmt.Warnings = append(stmt.Warnings, warnings...)
-	return stmt, nil
+	return nil, errors.NewInvalidInputf(errors.CodeInvalidInput, "unsupported request type: %s", requestType)
 }
 
-func getKeySelectors(query qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]) ([]*telemetrytypes.FieldKeySelector, []string) {
+func getKeySelectors(query qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]) []*telemetrytypes.FieldKeySelector {
 	var keySelectors []*telemetrytypes.FieldKeySelector
-	var warnings []string
 
 	for idx := range query.Aggregations {
 		aggExpr := query.Aggregations[idx]
@@ -145,19 +136,7 @@ func getKeySelectors(query qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]) ([
 		keySelectors[idx].SelectorMatchType = telemetrytypes.FieldSelectorMatchTypeExact
 	}
 
-	// When the new JSON body experience is enabled, warn the user if they use the bare
-	// "body" key in the filter — queries on plain "body" default to body.message:string.
-	// TODO(Piyush): Setup better for coming FTS support.
-	if querybuilder.BodyJSONQueryEnabled {
-		for _, sel := range keySelectors {
-			if sel.Name == LogsV2BodyColumn {
-				warnings = append(warnings, bodySearchDefaultWarning)
-				break
-			}
-		}
-	}
-
-	return keySelectors, warnings
+	return keySelectors
 }
 
 func (b *logQueryStatementBuilder) adjustKeys(ctx context.Context, keys map[string][]*telemetrytypes.TelemetryFieldKey, query qbtypes.QueryBuilderQuery[qbtypes.LogAggregation], requestType qbtypes.RequestType) qbtypes.QueryBuilderQuery[qbtypes.LogAggregation] {
@@ -224,6 +203,7 @@ func (b *logQueryStatementBuilder) adjustKeys(ctx context.Context, keys map[stri
 }
 
 func (b *logQueryStatementBuilder) adjustKey(key *telemetrytypes.TelemetryFieldKey, keys map[string][]*telemetrytypes.TelemetryFieldKey) []string {
+
 	// First check if it matches with any intrinsic fields
 	var intrinsicOrCalculatedField telemetrytypes.TelemetryFieldKey
 	if _, ok := IntrinsicFields[key.Name]; ok {
@@ -232,6 +212,7 @@ func (b *logQueryStatementBuilder) adjustKey(key *telemetrytypes.TelemetryFieldK
 	}
 
 	return querybuilder.AdjustKey(key, keys, nil)
+
 }
 
 // buildListQuery builds a query for list panel type
@@ -268,7 +249,11 @@ func (b *logQueryStatementBuilder) buildListQuery(
 		sb.SelectMore(LogsV2SeverityNumberColumn)
 		sb.SelectMore(LogsV2ScopeNameColumn)
 		sb.SelectMore(LogsV2ScopeVersionColumn)
-		sb.SelectMore(bodyAliasExpression())
+		sb.SelectMore(LogsV2BodyColumn)
+		if querybuilder.BodyJSONQueryEnabled {
+			sb.SelectMore(LogsV2BodyJSONColumn)
+			sb.SelectMore(LogsV2BodyPromotedColumn)
+		}
 		sb.SelectMore(LogsV2AttributesStringColumn)
 		sb.SelectMore(LogsV2AttributesNumberColumn)
 		sb.SelectMore(LogsV2AttributesBoolColumn)

pkg/telemetrylogs/stmt_builder_test.go

@@ -5,7 +5,6 @@ import (
 	"testing"
 	"time"
 
-	"github.com/SigNoz/signoz/pkg/errors"
 	"github.com/SigNoz/signoz/pkg/instrumentation/instrumentationtest"
 	"github.com/SigNoz/signoz/pkg/querybuilder"
 	"github.com/SigNoz/signoz/pkg/querybuilder/resourcefilter"
@@ -887,246 +886,3 @@ func TestAdjustKey(t *testing.T) {
 		})
 	}
 }
-
-func TestStmtBuilderBodyField(t *testing.T) {
-	cases := []struct {
-		name                string
-		requestType         qbtypes.RequestType
-		query               qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]
-		enableBodyJSONQuery bool
-		expected            qbtypes.Statement
-		expectedErr         error
-	}{
-		{
-			name:        "body_exists",
-			requestType: qbtypes.RequestTypeRaw,
-			query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
-				Signal: telemetrytypes.SignalLogs,
-				Filter: &qbtypes.Filter{Expression: "body Exists"},
-				Limit:  10,
-			},
-			enableBodyJSONQuery: true,
-			expected: qbtypes.Statement{
-				Query:    "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body_v2 as body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND body_v2.message <> ? AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
-				Args:     []any{uint64(1747945619), uint64(1747983448), "", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
-				Warnings: []string{bodySearchDefaultWarning},
-			},
-			expectedErr: nil,
-		},
-		{
-			name:        "body_exists_disabled",
-			requestType: qbtypes.RequestTypeRaw,
-			query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
-				Signal: telemetrytypes.SignalLogs,
-				Filter: &qbtypes.Filter{Expression: "body Exists"},
-				Limit:  10,
-			},
-			enableBodyJSONQuery: false,
-			expected: qbtypes.Statement{
-				Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND body <> ? AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
-				Args:  []any{uint64(1747945619), uint64(1747983448), "", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
-			},
-			expectedErr: nil,
-		},
-		{
-			name:        "body_empty",
-			requestType: qbtypes.RequestTypeRaw,
-			query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
-				Signal: telemetrytypes.SignalLogs,
-				Filter: &qbtypes.Filter{Expression: "body == ''"},
-				Limit:  10,
-			},
-			enableBodyJSONQuery: true,
-			expected: qbtypes.Statement{
-				Query:    "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body_v2 as body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND body_v2.message = ? AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
-				Args:     []any{uint64(1747945619), uint64(1747983448), "", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
-				Warnings: []string{bodySearchDefaultWarning},
-			},
-			expectedErr: nil,
-		},
-		{
-			name:        "body_empty_disabled",
-			requestType: qbtypes.RequestTypeRaw,
-			query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
-				Signal: telemetrytypes.SignalLogs,
-				Filter: &qbtypes.Filter{Expression: "body == ''"},
-				Limit:  10,
-			},
-			enableBodyJSONQuery: false,
-			expected: qbtypes.Statement{
-				Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND body = ? AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
-				Args:  []any{uint64(1747945619), uint64(1747983448), "", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
-			},
-			expectedErr: nil,
-		},
-		{
-			name:        "body_contains",
-			requestType: qbtypes.RequestTypeRaw,
-			query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
-				Signal: telemetrytypes.SignalLogs,
-				Filter: &qbtypes.Filter{Expression: "body CONTAINS 'error'"},
-				Limit:  10,
-			},
-			enableBodyJSONQuery: true,
-			expected: qbtypes.Statement{
-				Query:    "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body_v2 as body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND LOWER(body_v2.message) LIKE LOWER(?) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
-				Args:     []any{uint64(1747945619), uint64(1747983448), "%error%", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
-				Warnings: []string{bodySearchDefaultWarning},
-			},
-			expectedErr: nil,
-		},
-		{
-			name:        "body_contains_disabled",
-			requestType: qbtypes.RequestTypeRaw,
-			query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
-				Signal: telemetrytypes.SignalLogs,
-				Filter: &qbtypes.Filter{Expression: "body CONTAINS 'error'"},
-				Limit:  10,
-			},
-			enableBodyJSONQuery: false,
-			expected: qbtypes.Statement{
-				Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND LOWER(body) LIKE LOWER(?) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
-				Args:  []any{uint64(1747945619), uint64(1747983448), "%error%", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
-			},
-			expectedErr: nil,
-		},
-	}
-
-	fm := NewFieldMapper()
-	cb := NewConditionBuilder(fm)
-
-	enable, disable := jsonQueryTestUtil(t)
-	defer disable()
-	for _, c := range cases {
-		t.Run(c.name, func(t *testing.T) {
-			if c.enableBodyJSONQuery {
-				enable()
-			} else {
-				disable()
-			}
-			// build the key map after enabling/disabling body JSON query
-			mockMetadataStore := telemetrytypestest.NewMockMetadataStore()
-			for _, field := range IntrinsicFields {
-				f := field
-				mockMetadataStore.KeysMap[field.Name] = append(mockMetadataStore.KeysMap[field.Name], &f)
-			}
-			aggExprRewriter := querybuilder.NewAggExprRewriter(instrumentationtest.New().ToProviderSettings(), nil, fm, cb, nil)
-			resourceFilterStmtBuilder := resourceFilterStmtBuilder()
-			statementBuilder := NewLogQueryStatementBuilder(
-				instrumentationtest.New().ToProviderSettings(),
-				mockMetadataStore,
-				fm,
-				cb,
-				resourceFilterStmtBuilder,
-				aggExprRewriter,
-				DefaultFullTextColumn,
-				GetBodyJSONKey,
-			)
-
-			q, err := statementBuilder.Build(context.Background(), 1747947419000, 1747983448000, c.requestType, c.query, nil)
-			if c.expectedErr != nil {
-				require.Error(t, err)
-				require.Contains(t, err.Error(), c.expectedErr.Error())
-			} else {
-				if err != nil {
-					_, _, _, _, _, add := errors.Unwrapb(err)
-					t.Logf("error additionals: %v", add)
-				}
-				require.NoError(t, err)
-				require.Equal(t, c.expected.Query, q.Query)
-				require.Equal(t, c.expected.Args, q.Args)
-				require.Equal(t, c.expected.Warnings, q.Warnings)
-			}
-		})
-	}
-}
-
-func TestStmtBuilderBodyFullTextSearch(t *testing.T) {
-	cases := []struct {
-		name                string
-		requestType         qbtypes.RequestType
-		query               qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]
-		enableBodyJSONQuery bool
-		expected            qbtypes.Statement
-		expectedErr         error
-	}{
-		{
-			name:        "body_contains",
-			requestType: qbtypes.RequestTypeRaw,
-			query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
-				Signal: telemetrytypes.SignalLogs,
-				Filter: &qbtypes.Filter{Expression: "'error'"},
-				Limit:  10,
-			},
-			enableBodyJSONQuery: true,
-			expected: qbtypes.Statement{
-				Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body_v2 as body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND match(LOWER(body_v2.message), LOWER(?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
-				Args:  []any{uint64(1747945619), uint64(1747983448), "error", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
-			},
-			expectedErr: nil,
-		},
-		{
-			name:        "body_contains_disabled",
-			requestType: qbtypes.RequestTypeRaw,
-			query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
-				Signal: telemetrytypes.SignalLogs,
-				Filter: &qbtypes.Filter{Expression: "'error'"},
-				Limit:  10,
-			},
-			enableBodyJSONQuery: false,
-			expected: qbtypes.Statement{
-				Query: "WITH __resource_filter AS (SELECT fingerprint FROM signoz_logs.distributed_logs_v2_resource WHERE true AND seen_at_ts_bucket_start >= ? AND seen_at_ts_bucket_start <= ?) SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter) AND match(LOWER(body), LOWER(?)) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
-				Args:  []any{uint64(1747945619), uint64(1747983448), "error", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
-			},
-			expectedErr: nil,
-		},
-	}
-
-	fm := NewFieldMapper()
-	cb := NewConditionBuilder(fm)
-
-	enable, disable := jsonQueryTestUtil(t)
-	defer disable()
-	for _, c := range cases {
-		t.Run(c.name, func(t *testing.T) {
-			if c.enableBodyJSONQuery {
-				enable()
-			} else {
-				disable()
-			}
-			// build the key map after enabling/disabling body JSON query
-			mockMetadataStore := telemetrytypestest.NewMockMetadataStore()
-			for _, field := range IntrinsicFields {
-				f := field
-				mockMetadataStore.KeysMap[field.Name] = append(mockMetadataStore.KeysMap[field.Name], &f)
-			}
-			aggExprRewriter := querybuilder.NewAggExprRewriter(instrumentationtest.New().ToProviderSettings(), nil, fm, cb, nil)
-			resourceFilterStmtBuilder := resourceFilterStmtBuilder()
-			statementBuilder := NewLogQueryStatementBuilder(
-				instrumentationtest.New().ToProviderSettings(),
-				mockMetadataStore,
-				fm,
-				cb,
-				resourceFilterStmtBuilder,
-				aggExprRewriter,
-				DefaultFullTextColumn,
-				GetBodyJSONKey,
-			)
-
-			q, err := statementBuilder.Build(context.Background(), 1747947419000, 1747983448000, c.requestType, c.query, nil)
-			if c.expectedErr != nil {
-				require.Error(t, err)
-				require.Contains(t, err.Error(), c.expectedErr.Error())
-			} else {
-				if err != nil {
-					_, _, _, _, _, add := errors.Unwrapb(err)
-					t.Logf("error additionals: %v", add)
-				}
-				require.NoError(t, err)
-				require.Equal(t, c.expected.Query, q.Query)
-				require.Equal(t, c.expected.Args, q.Args)
-				require.Equal(t, c.expected.Warnings, q.Warnings)
-			}
-		})
-	}
-}

pkg/telemetrylogs/test_data.go

@@ -27,6 +27,13 @@ func buildCompleteFieldKeyMap() map[string][]*telemetrytypes.TelemetryFieldKey {
 				FieldDataType: telemetrytypes.FieldDataTypeString,
 			},
 		},
+		"body": {
+			{
+				Name:          "body",
+				FieldContext:  telemetrytypes.FieldContextLog,
+				FieldDataType: telemetrytypes.FieldDataTypeString,
+			},
+		},
 		"http.status_code": {
 			{
 				Name:          "http.status_code",
@@ -931,13 +938,6 @@ func buildCompleteFieldKeyMap() map[string][]*telemetrytypes.TelemetryFieldKey {
 				Materialized:  true,
 			},
 		},
-		"body": {
-			{
-				Name:          "body",
-				FieldContext:  telemetrytypes.FieldContextLog,
-				FieldDataType: telemetrytypes.FieldDataTypeString,
-			},
-		},
 	}
 
 	for _, keys := range keysMap {
@@ -945,7 +945,6 @@ func buildCompleteFieldKeyMap() map[string][]*telemetrytypes.TelemetryFieldKey {
 			key.Signal = telemetrytypes.SignalLogs
 		}
 	}
-
 	return keysMap
 }
 

pkg/telemetrymetadata/body_json_metadata.go

@@ -54,7 +54,6 @@ func (t *telemetryMetaStore) fetchBodyJSONPaths(ctx context.Context,
 		instrumentationtypes.CodeNamespace:    "metadata",
 		instrumentationtypes.CodeFunctionName: "fetchBodyJSONPaths",
 	})
-
 	query, args, limit := buildGetBodyJSONPathsQuery(fieldKeySelectors)
 	rows, err := t.telemetrystore.ClickhouseDB().Query(ctx, query, args...)
 	if err != nil {
@@ -185,6 +184,7 @@ func buildGetBodyJSONPathsQuery(fieldKeySelectors []*telemetrytypes.FieldKeySele
 		limit += fieldKeySelector.Limit
 	}
 	sb.Where(sb.Or(orClauses...))
+
 	// Group by path to get unique paths with aggregated types
 	sb.GroupBy("path")
 
@@ -319,7 +319,7 @@ func (t *telemetryMetaStore) ListJSONValues(ctx context.Context, path string, li
 	if promoted {
 		path = telemetrylogs.BodyPromotedColumnPrefix + path
 	} else {
-		path = telemetrylogs.BodyV2ColumnPrefix + path
+		path = telemetrylogs.BodyJSONColumnPrefix + path
 	}
 
 	from := fmt.Sprintf("%s.%s", telemetrylogs.DBName, telemetrylogs.LogsV2TableName)
@@ -522,7 +522,7 @@ func (t *telemetryMetaStore) GetPromotedPaths(ctx context.Context, paths ...stri
 // TODO(Piyush): Remove this function
 func CleanPathPrefixes(path string) string {
 	path = strings.TrimPrefix(path, telemetrytypes.BodyJSONStringSearchPrefix)
-	path = strings.TrimPrefix(path, telemetrylogs.BodyV2ColumnPrefix)
+	path = strings.TrimPrefix(path, telemetrylogs.BodyJSONColumnPrefix)
 	path = strings.TrimPrefix(path, telemetrylogs.BodyPromotedColumnPrefix)
 	return path
 }

pkg/telemetrymetadata/metadata.go

@@ -102,7 +102,7 @@ func NewTelemetryMetaStore(
 		jsonColumnMetadata: map[telemetrytypes.Signal]map[telemetrytypes.FieldContext]telemetrytypes.JSONColumnMetadata{
 			telemetrytypes.SignalLogs: {
 				telemetrytypes.FieldContextBody: telemetrytypes.JSONColumnMetadata{
-					BaseColumn:     telemetrylogs.LogsV2BodyV2Column,
+					BaseColumn:     telemetrylogs.LogsV2BodyJSONColumn,
 					PromotedColumn: telemetrylogs.LogsV2BodyPromotedColumn,
 				},
 			},

pkg/telemetrymeter/stmt_builder_test.go

@@ -51,7 +51,7 @@ func TestStatementBuilder(t *testing.T) {
 				},
 			},
 			expected: qbtypes.Statement{
-				Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(86400)) AS ts, JSONExtractString(labels, 'service.name') AS `service.name`, max(value) AS per_series_value FROM signoz_meter.distributed_samples AS points WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? AND JSONExtractString(labels, 'service.name') = ? AND LOWER(temporality) LIKE LOWER(?) GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `service.name`, ts",
+				Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(86400)) AS ts, JSONExtractString(labels, 'service.name') AS `service.name`, max(value) AS per_series_value FROM signoz_meter.distributed_samples AS points WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? AND JSONExtractString(labels, 'service.name') = ? AND LOWER(temporality) LIKE LOWER(?) GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte WHERE (`service.name`) IN (SELECT `service.name` FROM __spatial_aggregation_cte GROUP BY `service.name` ORDER BY avg(value) DESC LIMIT 10) ORDER BY avg(value) OVER (PARTITION BY `service.name`) DESC, `service.name`, ts ASC",
 				Args:  []any{"signoz_calls_total", uint64(1747785600000), uint64(1747983420000), "cartservice", "cumulative", 0},
 			},
 			expectedErr: nil,
@@ -84,7 +84,7 @@ func TestStatementBuilder(t *testing.T) {
 				},
 			},
 			expected: qbtypes.Statement{
-				Query: "WITH __spatial_aggregation_cte AS (SELECT toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(86400)) AS ts, JSONExtractString(labels, 'service.name') AS `service.name`, sum(value)/86400 AS value FROM signoz_meter.distributed_samples AS points WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? AND JSONExtractString(labels, 'service.name') = ? AND LOWER(temporality) LIKE LOWER(?) GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `service.name`, ts",
+				Query: "WITH __spatial_aggregation_cte AS (SELECT toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(86400)) AS ts, JSONExtractString(labels, 'service.name') AS `service.name`, sum(value)/86400 AS value FROM signoz_meter.distributed_samples AS points WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? AND JSONExtractString(labels, 'service.name') = ? AND LOWER(temporality) LIKE LOWER(?) GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte WHERE (`service.name`) IN (SELECT `service.name` FROM __spatial_aggregation_cte GROUP BY `service.name` ORDER BY avg(value) DESC LIMIT 10) ORDER BY avg(value) OVER (PARTITION BY `service.name`) DESC, `service.name`, ts ASC",
 				Args:  []any{"signoz_calls_total", uint64(1747872000000), uint64(1747983420000), "cartservice", "delta"},
 			},
 			expectedErr: nil,
@@ -117,7 +117,7 @@ func TestStatementBuilder(t *testing.T) {
 				},
 			},
 			expected: qbtypes.Statement{
-				Query: "WITH __temporal_aggregation_cte AS (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(86400)) AS ts, JSONExtractString(labels, 'service.name') AS `service.name`, sum(value)/86400 AS per_series_value FROM signoz_meter.distributed_samples AS points WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? AND JSONExtractString(labels, 'service.name') = ? AND LOWER(temporality) LIKE LOWER(?) GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts), __spatial_aggregation_cte AS (SELECT ts, `service.name`, avg(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `service.name`, ts",
+				Query: "WITH __temporal_aggregation_cte AS (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(86400)) AS ts, JSONExtractString(labels, 'service.name') AS `service.name`, sum(value)/86400 AS per_series_value FROM signoz_meter.distributed_samples AS points WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? AND JSONExtractString(labels, 'service.name') = ? AND LOWER(temporality) LIKE LOWER(?) GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts), __spatial_aggregation_cte AS (SELECT ts, `service.name`, avg(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte WHERE (`service.name`) IN (SELECT `service.name` FROM __spatial_aggregation_cte GROUP BY `service.name` ORDER BY avg(value) DESC LIMIT 10) ORDER BY avg(value) OVER (PARTITION BY `service.name`) DESC, `service.name`, ts ASC",
 				Args:  []any{"signoz_calls_total", uint64(1747872000000), uint64(1747983420000), "cartservice", "delta", 0},
 			},
 			expectedErr: nil,
@@ -150,7 +150,7 @@ func TestStatementBuilder(t *testing.T) {
 				},
 			},
 			expected: qbtypes.Statement{
-				Query: "WITH __temporal_aggregation_cte AS (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(86400)) AS ts, JSONExtractString(labels, 'host.name') AS `host.name`, avg(value) AS per_series_value FROM signoz_meter.distributed_samples AS points WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? AND JSONExtractString(labels, 'host.name') = ? AND LOWER(temporality) LIKE LOWER(?) GROUP BY fingerprint, ts, `host.name` ORDER BY fingerprint, ts), __spatial_aggregation_cte AS (SELECT ts, `host.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `host.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `host.name`, ts",
+				Query: "WITH __temporal_aggregation_cte AS (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(86400)) AS ts, JSONExtractString(labels, 'host.name') AS `host.name`, avg(value) AS per_series_value FROM signoz_meter.distributed_samples AS points WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? AND JSONExtractString(labels, 'host.name') = ? AND LOWER(temporality) LIKE LOWER(?) GROUP BY fingerprint, ts, `host.name` ORDER BY fingerprint, ts), __spatial_aggregation_cte AS (SELECT ts, `host.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `host.name`) SELECT * FROM __spatial_aggregation_cte WHERE (`host.name`) IN (SELECT `host.name` FROM __spatial_aggregation_cte GROUP BY `host.name` ORDER BY avg(value) DESC LIMIT 10) ORDER BY avg(value) OVER (PARTITION BY `host.name`) DESC, `host.name`, ts ASC",
 				Args:  []any{"system.memory.usage", uint64(1747872000000), uint64(1747983420000), "big-data-node-1", "unspecified", 0},
 			},
 			expectedErr: nil,

pkg/telemetrymetrics/statement_builder.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"fmt"
 	"log/slog"
+	"strings"
 
 	"github.com/SigNoz/signoz/pkg/factory"
 	"github.com/SigNoz/signoz/pkg/flagger"
@@ -539,6 +540,13 @@ func (b *MetricQueryStatementBuilder) buildSpatialAggregationCTE(
 	return fmt.Sprintf("__spatial_aggregation_cte AS (%s)", q), args
 }
 
+func isMetricAggOrderByKey(key string, config qbtypes.MetricAggregation) bool {
+	spaceAggOrderBy := fmt.Sprintf("%s(%s)", config.SpaceAggregation.StringValue(), config.MetricName)
+	timeAggOrderBy := fmt.Sprintf("%s(%s)", config.TimeAggregation.StringValue(), config.MetricName)
+	timeSpaceAggOrderBy := fmt.Sprintf("%s(%s(%s))", config.SpaceAggregation.StringValue(), config.TimeAggregation.StringValue(), config.MetricName)
+	return key == spaceAggOrderBy || key == timeAggOrderBy || key == timeSpaceAggOrderBy
+}
+
 func (b *MetricQueryStatementBuilder) BuildFinalSelect(
 	cteFragments []string,
 	cteArgs [][]any,
@@ -546,73 +554,159 @@ func (b *MetricQueryStatementBuilder) BuildFinalSelect(
 ) (*qbtypes.Statement, error) {
 	metricType := query.Aggregations[0].Type
 	spaceAgg := query.Aggregations[0].SpaceAggregation
+	finalCTE := "__spatial_aggregation_cte"
+	if metricType == metrictypes.HistogramType {
+		histogramCTE, histogramCTEArgs, err := b.buildHistogramCTE(query)
+		if err != nil {
+			return nil, err
+		}
+		cteFragments = append(cteFragments, histogramCTE)
+		cteArgs = append(cteArgs, histogramCTEArgs)
+		finalCTE = "__histogram_cte"
+	}
+
+	groupByKeys := querybuilder.GroupByKeys(query.GroupBy)
+	hasGroupBy := len(groupByKeys) > 0
+
+	if hasGroupBy {
+		cteWithAvgColumn := b.buildCTEWithAvgColumn(query, finalCTE)
+		cteFragments = append(cteFragments, cteWithAvgColumn)
+
+		cteWithGroupRankColumn := b.buildCTEWithGroupRank(query)
+		cteFragments = append(cteFragments, cteWithGroupRankColumn)
+		finalCTE = "__with_group_rank_cte"
+	}
 
 	combined := querybuilder.CombineCTEs(cteFragments)
-
 	var args []any
 	for _, a := range cteArgs {
 		args = append(args, a...)
 	}
 
 	sb := sqlbuilder.NewSelectBuilder()
+	sb.Select("ts")
+	if metricType == metrictypes.HistogramType && spaceAgg == metrictypes.SpaceAggregationCount && query.Aggregations[0].ComparisonSpaceAggregationParam == nil {
+		sb.SelectMore("le")
+	}
+	sb.SelectMore(groupByKeys...)
+	sb.SelectMore("value")
+	sb.From(finalCTE)
+	if query.Having != nil && query.Having.Expression != "" {
+		rewriter := querybuilder.NewHavingExpressionRewriter()
+		rewrittenExpr := rewriter.RewriteForMetrics(query.Having.Expression, query.Aggregations)
+		sb.Where(rewrittenExpr)
+	}
 
-	if metricType == metrictypes.HistogramType && spaceAgg.IsPercentile() {
-		quantile := query.Aggregations[0].SpaceAggregation.Percentile()
-		sb.Select("ts")
-		for _, g := range query.GroupBy {
-			sb.SelectMore(fmt.Sprintf("`%s`", g.TelemetryFieldKey.Name))
-		}
-		sb.SelectMore(fmt.Sprintf(
-			"histogramQuantile(arrayMap(x -> toFloat64(x), groupArray(le)), groupArray(value), %.3f) AS value",
-			quantile,
-		))
-		sb.From("__spatial_aggregation_cte")
-		sb.GroupBy(querybuilder.GroupByKeys(query.GroupBy)...)
-		sb.GroupBy("ts")
-		if query.Having != nil && query.Having.Expression != "" {
-			rewriter := querybuilder.NewHavingExpressionRewriter()
-			rewrittenExpr := rewriter.RewriteForMetrics(query.Having.Expression, query.Aggregations)
-			sb.Having(rewrittenExpr)
-		}
-	} else if metricType == metrictypes.HistogramType && spaceAgg == metrictypes.SpaceAggregationCount && query.Aggregations[0].ComparisonSpaceAggregationParam != nil {
-		sb.Select("ts")
-
-		for _, g := range query.GroupBy {
-			sb.SelectMore(fmt.Sprintf("`%s`", g.TelemetryFieldKey.Name))
-		}
-
-		aggQuery, err := AggregationQueryForHistogramCountWithParams(query.Aggregations[0].ComparisonSpaceAggregationParam)
-		if err != nil {
-			return nil, err
-		}
-		sb.SelectMore(aggQuery)
-
-		sb.From("__spatial_aggregation_cte")
-
-		sb.GroupBy(querybuilder.GroupByKeys(query.GroupBy)...)
-		sb.GroupBy("ts")
-
-		if query.Having != nil && query.Having.Expression != "" {
-			rewriter := querybuilder.NewHavingExpressionRewriter()
-			rewrittenExpr := rewriter.RewriteForMetrics(query.Having.Expression, query.Aggregations)
-			sb.Having(rewrittenExpr)
-		}
-	} else {
-		// for count aggregation on histograms with no params, the exact result of spatial aggregation can be sent forward
-		sb.Select("*")
-		sb.From("__spatial_aggregation_cte")
-		if query.Having != nil && query.Having.Expression != "" {
-			rewriter := querybuilder.NewHavingExpressionRewriter()
-			rewrittenExpr := rewriter.RewriteForMetrics(query.Having.Expression, query.Aggregations)
-			sb.Where(rewrittenExpr)
+	if hasGroupBy {
+		sb.OrderBy("group_rank")
+		if query.Limit > 0 {
+			sb.Where(fmt.Sprintf("group_rank <= %d", query.Limit))
 		}
 	}
-	sb.OrderBy(querybuilder.GroupByKeys(query.GroupBy)...)
-	sb.OrderBy("ts")
 	if metricType == metrictypes.HistogramType && spaceAgg == metrictypes.SpaceAggregationCount && query.Aggregations[0].ComparisonSpaceAggregationParam == nil {
 		sb.OrderBy("toFloat64(le)")
 	}
+	sb.OrderBy("ts ASC")
 
 	q, a := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
 	return &qbtypes.Statement{Query: combined + q, Args: append(args, a...)}, nil
 }
+
+func (b *MetricQueryStatementBuilder) buildHistogramCTE(
+	query qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation],
+) (string, []any, error) {
+	spaceAgg := query.Aggregations[0].SpaceAggregation
+	histogramCTEQueryBuilder := sqlbuilder.NewSelectBuilder()
+	if spaceAgg.IsPercentile() {
+		histogramCTEQueryBuilder.Select("ts")
+		for _, g := range query.GroupBy {
+			histogramCTEQueryBuilder.SelectMore(fmt.Sprintf("`%s`", g.TelemetryFieldKey.Name))
+		}
+		quantile := spaceAgg.Percentile()
+		histogramCTEQueryBuilder.SelectMore(fmt.Sprintf(
+			"histogramQuantile(arrayMap(x -> toFloat64(x), groupArray(le)), groupArray(value), %.3f) AS value",
+			quantile,
+		))
+		histogramCTEQueryBuilder.From("__spatial_aggregation_cte")
+		histogramCTEQueryBuilder.GroupBy(querybuilder.GroupByKeys(query.GroupBy)...)
+		histogramCTEQueryBuilder.GroupBy("ts")
+	} else if spaceAgg == metrictypes.SpaceAggregationCount && query.Aggregations[0].ComparisonSpaceAggregationParam != nil {
+		histogramCTEQueryBuilder.Select("ts")
+		for _, g := range query.GroupBy {
+			histogramCTEQueryBuilder.SelectMore(fmt.Sprintf("`%s`", g.TelemetryFieldKey.Name))
+		}
+		aggQuery, err := AggregationQueryForHistogramCountWithParams(query.Aggregations[0].ComparisonSpaceAggregationParam)
+		if err != nil {
+			return "", nil, err
+		}
+		histogramCTEQueryBuilder.SelectMore(aggQuery)
+		histogramCTEQueryBuilder.From("__spatial_aggregation_cte")
+		histogramCTEQueryBuilder.GroupBy(querybuilder.GroupByKeys(query.GroupBy)...)
+		histogramCTEQueryBuilder.GroupBy("ts")
+	} else {
+		// for count aggregation on histograms with no params, the exact result of spatial aggregation can be sent forward
+		histogramCTEQueryBuilder.Select("*")
+		histogramCTEQueryBuilder.From("__spatial_aggregation_cte")
+	}
+	histogramQueryCTE, histogramQueryCTEArgs := histogramCTEQueryBuilder.BuildWithFlavor(sqlbuilder.ClickHouse)
+	histogramCTE := fmt.Sprintf("__histogram_cte AS (%s)", histogramQueryCTE)
+
+	return histogramCTE, histogramQueryCTEArgs, nil
+}
+
+/*
+this receives a CTE (__spatial_aggregation_cte or __histogram_cte) that has columns ts, value, and a column each for all the group by keys
+it creates a CTE (__with_avg_cte) that adds a column avg_val which has the avg value for the group the row belongs in
+*/
+func (b *MetricQueryStatementBuilder) buildCTEWithAvgColumn(
+	query qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation],
+	latestCTE string,
+) string {
+	withAvgCTEBuilder := sqlbuilder.NewSelectBuilder()
+	withAvgCTEBuilder.Select("*")
+	groupByKeys := querybuilder.GroupByKeys(query.GroupBy)
+	withAvgCTEBuilder.SelectMore(fmt.Sprintf("avgIf(value, isNaN(value) = 0) OVER (PARTITION BY %s) AS avg_val", strings.Join(groupByKeys, ",")))
+	withAvgCTEBuilder.From(latestCTE)
+	withAvgCTEQuery, _ := withAvgCTEBuilder.BuildWithFlavor(sqlbuilder.ClickHouse) // no args so second return param is ignored
+	withAvgCTE := fmt.Sprintf("__with_avg_cte AS (%s)", withAvgCTEQuery)
+	return withAvgCTE
+}
+
+/*
+this receives the __with_avg_cte that has columns ts, value, a column each for all the group by keys, and avg_val which has the avg value for the group the row belongs in
+it creates a CTE (__with_group_rank_cte) that adds a column group_rank that ranks each group based on the order by keys (or by avg val if there are none)
+*/
+func (b *MetricQueryStatementBuilder) buildCTEWithGroupRank(
+	query qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation],
+) string {
+	withGroupByCTEBuilder := sqlbuilder.NewSelectBuilder()
+	withGroupByCTEBuilder.Select("*")
+
+	windowOrder := []string{}
+	orderedKeys := map[string]struct{}{} // this will be used to add the remaining keys as tie breakers in the end
+	if len(query.Order) > 0 {
+		for _, o := range query.Order {
+			key := o.Key.Name
+			if isMetricAggOrderByKey(key, query.Aggregations[0]) {
+				windowOrder = append(windowOrder, fmt.Sprintf("avg_val %s", o.Direction.StringValue()))
+			} else {
+				windowOrder = append(windowOrder, fmt.Sprintf("`%s` %s", key, o.Direction.StringValue()))
+				orderedKeys[fmt.Sprintf("`%s`", key)] = struct{}{}
+			}
+		}
+	} else {
+		windowOrder = append(windowOrder, "avg_val DESC")
+	}
+	groupByKeys := querybuilder.GroupByKeys(query.GroupBy)
+	for _, gk := range groupByKeys { // keys that haven't been added via order by keys will be added at the end as tie breakers
+		if _, ok := orderedKeys[gk]; !ok {
+			windowOrder = append(windowOrder, fmt.Sprintf("%s ASC", gk))
+		}
+	}
+	withGroupByCTEBuilder.SelectMore(fmt.Sprintf("dense_rank() OVER (ORDER BY %s) AS group_rank", strings.Join(windowOrder, ",")))
+
+	withGroupByCTEBuilder.From("__with_avg_cte")
+	withGroupRankCTEQuery, _ := withGroupByCTEBuilder.BuildWithFlavor(sqlbuilder.ClickHouse) // no args so second return param is ignored
+	withGroupRankCTE := fmt.Sprintf("__with_group_rank_cte AS (%s)", withGroupRankCTEQuery)
+	return withGroupRankCTE
+}

pkg/telemetrymetrics/stmt_builder_test.go

@@ -15,16 +15,17 @@ import (
 )
 
 func TestStatementBuilder(t *testing.T) {
-	cases := []struct {
-		name        string
-		requestType qbtypes.RequestType
-		query       qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]
-		expected    qbtypes.Statement
-		expectedErr error
-	}{
+	type baseQuery struct {
+		name     string
+		query    qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]
+		orderKey string
+		args     []any
+		cte      string
+	}
+
+	bases := []baseQuery{
 		{
-			name:        "test_cumulative_rate_sum",
-			requestType: qbtypes.RequestTypeTimeSeries,
+			name: "cumulative_rate_sum",
 			query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
 				Signal:       telemetrytypes.SignalMetrics,
 				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
@@ -40,24 +41,16 @@ func TestStatementBuilder(t *testing.T) {
 				Filter: &qbtypes.Filter{
 					Expression: "service.name = 'cartservice'",
 				},
-				Limit: 10,
 				GroupBy: []qbtypes.GroupByKey{
-					{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "service.name",
-						},
-					},
+					{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "service.name"}},
 				},
 			},
-			expected: qbtypes.Statement{
-				Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, max(value) AS per_series_value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND JSONExtractString(labels, 'service.name') = ? GROUP BY fingerprint, `service.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `service.name`, ts",
-				Args:  []any{"signoz_calls_total", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "cartservice", "signoz_calls_total", uint64(1747947360000), uint64(1747983420000), 0},
-			},
-			expectedErr: nil,
+			orderKey: "service.name",
+			args:     []any{"signoz_calls_total", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "cartservice", "signoz_calls_total", uint64(1747947360000), uint64(1747983420000), 0},
+			cte:      "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, max(value) AS per_series_value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND JSONExtractString(labels, 'service.name') = ? GROUP BY fingerprint, `service.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`)",
 		},
 		{
-			name:        "test_cumulative_rate_sum_with_mat_column",
-			requestType: qbtypes.RequestTypeTimeSeries,
+			name: "cumulative_rate_sum_with_mat_column",
 			query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
 				Signal:       telemetrytypes.SignalMetrics,
 				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
@@ -73,24 +66,16 @@ func TestStatementBuilder(t *testing.T) {
 				Filter: &qbtypes.Filter{
 					Expression: "materialized.key.name REGEXP 'cartservice' OR service.name = 'cartservice'",
 				},
-				Limit: 10,
 				GroupBy: []qbtypes.GroupByKey{
-					{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "service.name",
-						},
-					},
+					{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "service.name"}},
 				},
 			},
-			expected: qbtypes.Statement{
-				Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, max(value) AS per_series_value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND (match(JSONExtractString(labels, 'materialized.key.name'), ?) OR JSONExtractString(labels, 'service.name') = ?) GROUP BY fingerprint, `service.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `service.name`, ts",
-				Args:  []any{"signoz_calls_total", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "cartservice", "cartservice", "signoz_calls_total", uint64(1747947360000), uint64(1747983420000), 0},
-			},
-			expectedErr: nil,
+			orderKey: "service.name",
+			args:     []any{"signoz_calls_total", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "cartservice", "cartservice", "signoz_calls_total", uint64(1747947360000), uint64(1747983420000), 0},
+			cte:      "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, max(value) AS per_series_value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND (match(JSONExtractString(labels, 'materialized.key.name'), ?) OR JSONExtractString(labels, 'service.name') = ?) GROUP BY fingerprint, `service.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`)",
 		},
 		{
-			name:        "test_delta_rate_sum",
-			requestType: qbtypes.RequestTypeTimeSeries,
+			name: "delta_rate_sum",
 			query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
 				Signal:       telemetrytypes.SignalMetrics,
 				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
@@ -106,24 +91,16 @@ func TestStatementBuilder(t *testing.T) {
 				Filter: &qbtypes.Filter{
 					Expression: "service.name = 'cartservice'",
 				},
-				Limit: 10,
 				GroupBy: []qbtypes.GroupByKey{
-					{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "service.name",
-						},
-					},
+					{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "service.name"}},
 				},
 			},
-			expected: qbtypes.Statement{
-				Query: "WITH __spatial_aggregation_cte AS (SELECT toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, sum(value)/30 AS value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND JSONExtractString(labels, 'service.name') = ? GROUP BY fingerprint, `service.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `service.name`, ts",
-				Args:  []any{"signoz_calls_total", uint64(1747936800000), uint64(1747983420000), "delta", false, "cartservice", "signoz_calls_total", uint64(1747947390000), uint64(1747983420000)},
-			},
-			expectedErr: nil,
+			orderKey: "service.name",
+			args:     []any{"signoz_calls_total", uint64(1747936800000), uint64(1747983420000), "delta", false, "cartservice", "signoz_calls_total", uint64(1747947390000), uint64(1747983420000)},
+			cte:      "WITH __spatial_aggregation_cte AS (SELECT toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, sum(value)/30 AS value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND JSONExtractString(labels, 'service.name') = ? GROUP BY fingerprint, `service.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY ts, `service.name`)",
 		},
 		{
-			name:        "test_histogram_percentile1",
-			requestType: qbtypes.RequestTypeTimeSeries,
+			name: "histogram_percentile1",
 			query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
 				Signal:       telemetrytypes.SignalMetrics,
 				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
@@ -139,24 +116,38 @@ func TestStatementBuilder(t *testing.T) {
 				Filter: &qbtypes.Filter{
 					Expression: "service.name = 'cartservice'",
 				},
-				Limit: 10,
 				GroupBy: []qbtypes.GroupByKey{
-					{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "service.name",
-						},
-					},
+					{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "service.name"}},
 				},
 			},
-			expected: qbtypes.Statement{
-				Query: "WITH __spatial_aggregation_cte AS (SELECT toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, `le`, sum(value)/30 AS value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name`, JSONExtractString(labels, 'le') AS `le` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND JSONExtractString(labels, 'service.name') = ? GROUP BY fingerprint, `service.name`, `le`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY ts, `service.name`, `le`) SELECT ts, `service.name`, histogramQuantile(arrayMap(x -> toFloat64(x), groupArray(le)), groupArray(value), 0.950) AS value FROM __spatial_aggregation_cte GROUP BY `service.name`, ts ORDER BY `service.name`, ts",
-				Args:  []any{"signoz_latency", uint64(1747936800000), uint64(1747983420000), "delta", false, "cartservice", "signoz_latency", uint64(1747947390000), uint64(1747983420000)},
-			},
-			expectedErr: nil,
+			orderKey: "service.name",
+			args:     []any{"signoz_latency", uint64(1747936800000), uint64(1747983420000), "delta", false, "cartservice", "signoz_latency", uint64(1747947390000), uint64(1747983420000)},
+			cte:      "WITH __spatial_aggregation_cte AS (SELECT toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, `le`, sum(value)/30 AS value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name`, JSONExtractString(labels, 'le') AS `le` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND JSONExtractString(labels, 'service.name') = ? GROUP BY fingerprint, `service.name`, `le`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY ts, `service.name`, `le`), __histogram_cte AS (SELECT ts, `service.name`, histogramQuantile(arrayMap(x -> toFloat64(x), groupArray(le)), groupArray(value), 0.950) AS value FROM __spatial_aggregation_cte GROUP BY `service.name`, ts)",
 		},
 		{
-			name:        "test_gauge_avg_sum",
-			requestType: qbtypes.RequestTypeTimeSeries,
+			name: "histogram_percentile2",
+			query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
+				Signal:       telemetrytypes.SignalMetrics,
+				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
+				Aggregations: []qbtypes.MetricAggregation{
+					{
+						MetricName:       "http_server_duration_bucket",
+						Type:             metrictypes.HistogramType,
+						Temporality:      metrictypes.Cumulative,
+						TimeAggregation:  metrictypes.TimeAggregationRate,
+						SpaceAggregation: metrictypes.SpaceAggregationPercentile95,
+					},
+				},
+				GroupBy: []qbtypes.GroupByKey{
+					{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "service.name"}},
+				},
+			},
+			orderKey: "service.name",
+			args:     []any{"http_server_duration_bucket", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "http_server_duration_bucket", uint64(1747947360000), uint64(1747983420000), 0},
+			cte:      "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, `le`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, `le`, max(value) AS per_series_value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name`, JSONExtractString(labels, 'le') AS `le` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? GROUP BY fingerprint, `service.name`, `le`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `service.name`, `le` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, `le`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`, `le`), __histogram_cte AS (SELECT ts, `service.name`, histogramQuantile(arrayMap(x -> toFloat64(x), groupArray(le)), groupArray(value), 0.950) AS value FROM __spatial_aggregation_cte GROUP BY `service.name`, ts)",
+		},
+		{
+			name: "gauge_avg_sum",
 			query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
 				Signal:       telemetrytypes.SignalMetrics,
 				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
@@ -172,53 +163,83 @@ func TestStatementBuilder(t *testing.T) {
 				Filter: &qbtypes.Filter{
 					Expression: "host.name = 'big-data-node-1'",
 				},
-				Limit: 10,
 				GroupBy: []qbtypes.GroupByKey{
-					{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "host.name",
-						},
-					},
+					{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "host.name"}},
 				},
 			},
-			expected: qbtypes.Statement{
-				Query: "WITH __temporal_aggregation_cte AS (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `host.name`, avg(value) AS per_series_value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'host.name') AS `host.name` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND JSONExtractString(labels, 'host.name') = ? GROUP BY fingerprint, `host.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `host.name` ORDER BY fingerprint, ts), __spatial_aggregation_cte AS (SELECT ts, `host.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `host.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `host.name`, ts",
-				Args:  []any{"system.memory.usage", uint64(1747936800000), uint64(1747983420000), "unspecified", false, "big-data-node-1", "system.memory.usage", uint64(1747947390000), uint64(1747983420000), 0},
-			},
-			expectedErr: nil,
-		},
-		{
-			name:        "test_histogram_percentile2",
-			requestType: qbtypes.RequestTypeTimeSeries,
-			query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
-				Signal:       telemetrytypes.SignalMetrics,
-				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
-				Aggregations: []qbtypes.MetricAggregation{
-					{
-						MetricName:       "http_server_duration_bucket",
-						Type:             metrictypes.HistogramType,
-						Temporality:      metrictypes.Cumulative,
-						TimeAggregation:  metrictypes.TimeAggregationRate,
-						SpaceAggregation: metrictypes.SpaceAggregationPercentile95,
-					},
-				},
-				Limit: 10,
-				GroupBy: []qbtypes.GroupByKey{
-					{
-						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
-							Name: "service.name",
-						},
-					},
-				},
-			},
-			expected: qbtypes.Statement{
-				Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, `le`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, `le`, max(value) AS per_series_value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name`, JSONExtractString(labels, 'le') AS `le` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? GROUP BY fingerprint, `service.name`, `le`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `service.name`, `le` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, `le`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`, `le`) SELECT ts, `service.name`, histogramQuantile(arrayMap(x -> toFloat64(x), groupArray(le)), groupArray(value), 0.950) AS value FROM __spatial_aggregation_cte GROUP BY `service.name`, ts ORDER BY `service.name`, ts",
-				Args:  []any{"http_server_duration_bucket", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "http_server_duration_bucket", uint64(1747947360000), uint64(1747983420000), 0},
-			},
-			expectedErr: nil,
+			orderKey: "host.name",
+			args:     []any{"system.memory.usage", uint64(1747936800000), uint64(1747983420000), "unspecified", false, "big-data-node-1", "system.memory.usage", uint64(1747947390000), uint64(1747983420000), 0},
+			cte:      "WITH __temporal_aggregation_cte AS (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `host.name`, avg(value) AS per_series_value FROM signoz_metrics.distributed_samples_v4 AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'host.name') AS `host.name` FROM signoz_metrics.time_series_v4_6hrs WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND LOWER(temporality) LIKE LOWER(?) AND __normalized = ? AND JSONExtractString(labels, 'host.name') = ? GROUP BY fingerprint, `host.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `host.name` ORDER BY fingerprint, ts), __spatial_aggregation_cte AS (SELECT ts, `host.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `host.name`)",
 		},
 	}
 
+	type variant struct {
+		name     string
+		limit    int
+		hasOrder bool
+	}
+
+	variants := []variant{
+		{"with_limits", 10, false},
+		{"without_limits", 0, false},
+		{"with_order_by", 0, true},
+		{"with_order_by_and_limits", 10, true},
+	}
+
+	sumMetricsFinalSelects := map[string]string{
+		"with_limits":              " SELECT * FROM __spatial_aggregation_cte WHERE (`service.name`) IN (SELECT `service.name` FROM __spatial_aggregation_cte GROUP BY `service.name` ORDER BY avg(value) DESC LIMIT 10) ORDER BY avg(value) OVER (PARTITION BY `service.name`) DESC, `service.name`, ts ASC",
+		"without_limits":           " SELECT * FROM __spatial_aggregation_cte ORDER BY avg(value) OVER (PARTITION BY `service.name`) DESC, `service.name`, ts ASC",
+		"with_order_by":            " SELECT * FROM __spatial_aggregation_cte ORDER BY `service.name` asc, ts ASC",
+		"with_order_by_and_limits": " SELECT * FROM __spatial_aggregation_cte WHERE (`service.name`) IN (SELECT `service.name` FROM __spatial_aggregation_cte GROUP BY `service.name` ORDER BY `service.name` asc LIMIT 10) ORDER BY `service.name` asc, ts ASC",
+	}
+
+	histogramMetricsFinalSelects := map[string]string{
+		"with_limits":              " SELECT * FROM __histogram_cte WHERE (`service.name`) IN (SELECT `service.name` FROM __histogram_cte GROUP BY `service.name` ORDER BY avg(value) DESC LIMIT 10) ORDER BY avg(value) OVER (PARTITION BY `service.name`) DESC, `service.name`, ts ASC",
+		"without_limits":           " SELECT * FROM __histogram_cte ORDER BY avg(value) OVER (PARTITION BY `service.name`) DESC, `service.name`, ts ASC",
+		"with_order_by":            " SELECT * FROM __histogram_cte ORDER BY `service.name` asc, ts ASC",
+		"with_order_by_and_limits": " SELECT * FROM __histogram_cte WHERE (`service.name`) IN (SELECT `service.name` FROM __histogram_cte GROUP BY `service.name` ORDER BY `service.name` asc LIMIT 10) ORDER BY `service.name` asc, ts ASC",
+	}
+
+	// expectedFinalSelects maps "base/variant" to the final SELECT portion after the CTE.
+	// The full expected query is: base.cte + expectedFinalSelects[name]
+	expectedFinalSelects := map[string]string{
+		// cumulative_rate_sum
+		"cumulative_rate_sum/with_limits":              sumMetricsFinalSelects["with_limits"],
+		"cumulative_rate_sum/without_limits":           sumMetricsFinalSelects["without_limits"],
+		"cumulative_rate_sum/with_order_by":            sumMetricsFinalSelects["with_order_by"],
+		"cumulative_rate_sum/with_order_by_and_limits": sumMetricsFinalSelects["with_order_by_and_limits"],
+
+		// cumulative_rate_sum_with_mat_column
+		"cumulative_rate_sum_with_mat_column/with_limits":              sumMetricsFinalSelects["with_limits"],
+		"cumulative_rate_sum_with_mat_column/without_limits":           sumMetricsFinalSelects["without_limits"],
+		"cumulative_rate_sum_with_mat_column/with_order_by":            sumMetricsFinalSelects["with_order_by"],
+		"cumulative_rate_sum_with_mat_column/with_order_by_and_limits": sumMetricsFinalSelects["with_order_by_and_limits"],
+
+		// delta_rate_sum
+		"delta_rate_sum/with_limits":              sumMetricsFinalSelects["with_limits"],
+		"delta_rate_sum/without_limits":           sumMetricsFinalSelects["without_limits"],
+		"delta_rate_sum/with_order_by":            sumMetricsFinalSelects["with_order_by"],
+		"delta_rate_sum/with_order_by_and_limits": sumMetricsFinalSelects["with_order_by_and_limits"],
+
+		// histogram_percentile1
+		"histogram_percentile1/with_limits":              histogramMetricsFinalSelects["with_limits"],
+		"histogram_percentile1/without_limits":           histogramMetricsFinalSelects["without_limits"],
+		"histogram_percentile1/with_order_by":            histogramMetricsFinalSelects["with_order_by"],
+		"histogram_percentile1/with_order_by_and_limits": histogramMetricsFinalSelects["with_order_by_and_limits"],
+
+		// histogram_percentile2
+		"histogram_percentile2/with_limits":              histogramMetricsFinalSelects["with_limits"],
+		"histogram_percentile2/without_limits":           histogramMetricsFinalSelects["without_limits"],
+		"histogram_percentile2/with_order_by":            histogramMetricsFinalSelects["with_order_by"],
+		"histogram_percentile2/with_order_by_and_limits": histogramMetricsFinalSelects["with_order_by_and_limits"],
+
+		// gauge_avg_sum
+		"gauge_avg_sum/with_limits":              " SELECT * FROM __spatial_aggregation_cte WHERE (`host.name`) IN (SELECT `host.name` FROM __spatial_aggregation_cte GROUP BY `host.name` ORDER BY avg(value) DESC LIMIT 10) ORDER BY avg(value) OVER (PARTITION BY `host.name`) DESC, `host.name`, ts ASC",
+		"gauge_avg_sum/without_limits":           " SELECT * FROM __spatial_aggregation_cte ORDER BY avg(value) OVER (PARTITION BY `host.name`) DESC, `host.name`, ts ASC",
+		"gauge_avg_sum/with_order_by":            " SELECT * FROM __spatial_aggregation_cte ORDER BY `host.name` asc, ts ASC",
+		"gauge_avg_sum/with_order_by_and_limits": " SELECT * FROM __spatial_aggregation_cte WHERE (`host.name`) IN (SELECT `host.name` FROM __spatial_aggregation_cte GROUP BY `host.name` ORDER BY `host.name` asc LIMIT 10) ORDER BY `host.name` asc, ts ASC",
+	}
+
 	fm := NewFieldMapper()
 	cb := NewConditionBuilder(fm)
 	mockMetadataStore := telemetrytypestest.NewMockMetadataStore()
@@ -227,15 +248,13 @@ func TestStatementBuilder(t *testing.T) {
 		t.Fatalf("failed to load field keys: %v", err)
 	}
 	mockMetadataStore.KeysMap = keys
-	// NOTE: LoadFieldKeysFromJSON doesn't set Materialized field
-	// for keys, so we have to set it manually here for testing
 	if _, ok := mockMetadataStore.KeysMap["materialized.key.name"]; ok {
 		if len(mockMetadataStore.KeysMap["materialized.key.name"]) > 0 {
 			mockMetadataStore.KeysMap["materialized.key.name"][0].Materialized = true
 		}
 	}
 
-	flagger, err := flagger.New(context.Background(), instrumentationtest.New().ToProviderSettings(), flagger.Config{}, flagger.MustNewRegistry())
+	fl, err := flagger.New(context.Background(), instrumentationtest.New().ToProviderSettings(), flagger.Config{}, flagger.MustNewRegistry())
 	if err != nil {
 		t.Fatalf("failed to create flagger: %v", err)
 	}
@@ -245,23 +264,30 @@ func TestStatementBuilder(t *testing.T) {
 		mockMetadataStore,
 		fm,
 		cb,
-		flagger,
+		fl,
 	)
 
-	for _, c := range cases {
-		t.Run(c.name, func(t *testing.T) {
+	for _, b := range bases {
+		for _, v := range variants {
+			name := b.name + "/" + v.name
+			t.Run(name, func(t *testing.T) {
+				q := b.query
+				q.Limit = v.limit
+				if v.hasOrder {
+					q.Order = []qbtypes.OrderBy{
+						{
+							Key:       qbtypes.OrderByKey{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: b.orderKey}},
+							Direction: qbtypes.OrderDirectionAsc,
+						},
+					}
+				}
 
-			q, err := statementBuilder.Build(context.Background(), 1747947419000, 1747983448000, c.requestType, c.query, nil)
+				result, err := statementBuilder.Build(context.Background(), 1747947419000, 1747983448000, qbtypes.RequestTypeTimeSeries, q, nil)
 
-			if c.expectedErr != nil {
-				require.Error(t, err)
-				require.Contains(t, err.Error(), c.expectedErr.Error())
-			} else {
 				require.NoError(t, err)
-				require.Equal(t, c.expected.Query, q.Query)
-				require.Equal(t, c.expected.Args, q.Args)
-				require.Equal(t, c.expected.Warnings, q.Warnings)
-			}
-		})
+				require.Equal(t, b.cte+expectedFinalSelects[name], result.Query)
+				require.Equal(t, b.args, result.Args)
+			})
+		}
 	}
 }

pkg/types/authtypes/identn.go

@@ -6,7 +6,6 @@ var (
 	IdentNProviderTokenizer = IdentNProvider{valuer.NewString("tokenizer")}
 	IdentNProviderAPIkey    = IdentNProvider{valuer.NewString("api_key")}
 	IdentNProviderAnonymous = IdentNProvider{valuer.NewString("anonymous")}
-	IdentNProviderInternal  = IdentNProvider{valuer.NewString("internal")}
 )
 
 type IdentNProvider struct{ valuer.String }

pkg/types/cloudintegrationtypes/account.go

@@ -1,43 +0,0 @@
-package cloudintegrationtypes
-
-import (
-	"time"
-
-	"github.com/SigNoz/signoz/pkg/types"
-	"github.com/SigNoz/signoz/pkg/valuer"
-)
-
-type Account struct {
-	types.Identifiable
-	types.TimeAuditable
-	ProviderAccountId *string           `json:"providerAccountID,omitempty"`
-	Provider          CloudProviderType `json:"provider"`
-	RemovedAt         *time.Time        `json:"removedAt,omitempty"`
-	AgentReport       *AgentReport      `json:"agentReport,omitempty"`
-	OrgID             valuer.UUID       `json:"orgID"`
-	Config            *AccountConfig    `json:"config,omitempty"`
-}
-
-// AgentReport represents heartbeats sent by the agent.
-type AgentReport struct {
-	TimestampMillis int64          `json:"timestampMillis"`
-	Data            map[string]any `json:"data"`
-}
-
-type GettableAccounts struct {
-	Accounts []*Account `json:"accounts"`
-}
-
-type GettableAccount = Account
-
-type UpdatableAccount struct {
-	Config *AccountConfig `json:"config"`
-}
-
-type AccountConfig struct {
-	AWS *AWSAccountConfig `json:"aws,omitempty"`
-}
-
-type AWSAccountConfig struct {
-	Regions []string `json:"regions"`
-}

pkg/types/cloudintegrationtypes/cloudintegration.go

@@ -1,80 +0,0 @@
-package cloudintegrationtypes
-
-import (
-	"database/sql/driver"
-	"encoding/json"
-	"time"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/uptrace/bun"
-
-	"github.com/SigNoz/signoz/pkg/types"
-	"github.com/SigNoz/signoz/pkg/valuer"
-)
-
-var (
-	ErrCodeCloudIntegrationNotFound = errors.MustNewCode("cloud_integration_not_found")
-)
-
-// StorableCloudIntegration represents a cloud integration stored in the database.
-// This is also referred as "Account" in the context of cloud integrations.
-type StorableCloudIntegration struct {
-	bun.BaseModel `bun:"table:cloud_integration"`
-	types.Identifiable
-	types.TimeAuditable
-
-	Provider        CloudProviderType    `bun:"provider,type:text"`
-	Config          string               `bun:"config,type:text"` // Config is provider-specific data in JSON string format
-	AccountID       *string              `bun:"account_id,type:text"`
-	LastAgentReport *StorableAgentReport `bun:"last_agent_report,type:text"`
-	RemovedAt       *time.Time           `bun:"removed_at,type:timestamp,nullzero"`
-	OrgID           valuer.UUID          `bun:"org_id,type:text"`
-}
-
-// StorableAgentReport represents the last heartbeat and arbitrary data sent by the agent
-// as of now there is no use case for Data field, but keeping it for backwards compatibility with older structure.
-type StorableAgentReport struct {
-	TimestampMillis int64          `json:"timestamp_millis"` // backward compatibility
-	Data            map[string]any `json:"data"`
-}
-
-// StorableCloudIntegrationService is to store service config for a cloud integration, which is a cloud provider specific configuration.
-type StorableCloudIntegrationService struct {
-	bun.BaseModel `bun:"table:cloud_integration_service,alias:cis"`
-	types.Identifiable
-	types.TimeAuditable
-
-	Type               ServiceID   `bun:"type,type:text,notnull"` // Keeping Type field name as is, but it is a service id
-	Config             string      `bun:"config,type:text"`       // Config is cloud provider's service specific data in JSON string format
-	CloudIntegrationID valuer.UUID `bun:"cloud_integration_id,type:text"`
-}
-
-// Scan scans value from DB.
-func (r *StorableAgentReport) Scan(src any) error {
-	var data []byte
-	switch v := src.(type) {
-	case []byte:
-		data = v
-	case string:
-		data = []byte(v)
-	default:
-		return errors.NewInternalf(errors.CodeInternal, "tried to scan from %T instead of string or bytes", src)
-	}
-	return json.Unmarshal(data, r)
-}
-
-// Value creates value to be stored in DB.
-func (r *StorableAgentReport) Value() (driver.Value, error) {
-	if r == nil {
-		return nil, errors.NewInternalf(errors.CodeInternal, "agent report is nil")
-	}
-
-	serialized, err := json.Marshal(r)
-	if err != nil {
-		return nil, errors.WrapInternalf(
-			err, errors.CodeInternal, "couldn't serialize agent report to JSON",
-		)
-	}
-	// Return as string instead of []byte to ensure PostgreSQL stores as text, not bytes
-	return string(serialized), nil
-}

pkg/types/cloudintegrationtypes/cloudprovider.go

@@ -1,41 +0,0 @@
-package cloudintegrationtypes
-
-import (
-	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/SigNoz/signoz/pkg/valuer"
-)
-
-// CloudProviderType type alias.
-type CloudProviderType struct{ valuer.String }
-
-var (
-	// cloud providers.
-	CloudProviderTypeAWS   = CloudProviderType{valuer.NewString("aws")}
-	CloudProviderTypeAzure = CloudProviderType{valuer.NewString("azure")}
-
-	// errors.
-	ErrCodeCloudProviderInvalidInput = errors.MustNewCode("invalid_cloud_provider")
-
-	AWSIntegrationUserEmail   = valuer.MustNewEmail("aws-integration@signoz.io")
-	AzureIntegrationUserEmail = valuer.MustNewEmail("azure-integration@signoz.io")
-)
-
-// CloudIntegrationUserEmails is the list of valid emails for Cloud One Click integrations.
-// This is used for validation and restrictions in different contexts, across codebase.
-var CloudIntegrationUserEmails = []valuer.Email{
-	AWSIntegrationUserEmail,
-	AzureIntegrationUserEmail,
-}
-
-// NewCloudProvider returns a new CloudProviderType from a string.
-// It validates the input and returns an error if the input is not valid cloud provider.
-func NewCloudProvider(provider string) (CloudProviderType, error) {
-	switch provider {
-	case CloudProviderTypeAWS.StringValue():
-		return CloudProviderTypeAWS, nil
-	case CloudProviderTypeAzure.StringValue():
-		return CloudProviderTypeAzure, nil
-	default:
-		return CloudProviderType{}, errors.NewInvalidInputf(ErrCodeCloudProviderInvalidInput, "invalid cloud provider: %s", provider)
-	}
-}

pkg/types/cloudintegrationtypes/connection.go

@@ -1,88 +0,0 @@
-package cloudintegrationtypes
-
-import "github.com/SigNoz/signoz/pkg/types/integrationtypes"
-
-type ConnectionArtifactRequest struct {
-	Aws *AWSConnectionArtifactRequest `json:"aws"`
-}
-
-type AWSConnectionArtifactRequest struct {
-	DeploymentRegion string   `json:"deploymentRegion"`
-	Regions          []string `json:"regions"`
-}
-
-type PostableConnectionArtifact = ConnectionArtifactRequest
-
-type ConnectionArtifact struct {
-	Aws *AWSConnectionArtifact `json:"aws"`
-}
-
-type AWSConnectionArtifact struct {
-	ConnectionUrl string `json:"connectionURL"`
-}
-
-type GettableConnectionArtifact = ConnectionArtifact
-
-type AccountStatus struct {
-	Id                string                         `json:"id"`
-	ProviderAccountId *string                        `json:"providerAccountID,omitempty"`
-	Status            integrationtypes.AccountStatus `json:"status"`
-}
-
-type GettableAccountStatus = AccountStatus
-
-type AgentCheckInRequest struct {
-	// older backward compatible fields are mapped to new fields
-	// CloudIntegrationId string `json:"cloudIntegrationId"`
-	// AccountId          string `json:"accountId"`
-
-	// New fields
-	ProviderAccountId string `json:"providerAccountId"`
-	CloudAccountId    string `json:"cloudAccountId"`
-
-	Data map[string]any `json:"data,omitempty"`
-}
-
-type PostableAgentCheckInRequest struct {
-	AgentCheckInRequest
-	// following are backward compatible fields for older running agents
-	// which gets mapped to new fields in AgentCheckInRequest
-	CloudIntegrationId string `json:"cloud_integration_id"`
-	CloudAccountId     string `json:"cloud_account_id"`
-}
-
-type GettableAgentCheckInResponse struct {
-	AgentCheckInResponse
-
-	// For backward compatibility
-	CloudIntegrationId string `json:"cloud_integration_id"`
-	AccountId          string `json:"account_id"`
-}
-
-type AgentCheckInResponse struct {
-	// Older fields for backward compatibility are mapped to new fields below
-	// CloudIntegrationId string `json:"cloud_integration_id"`
-	// AccountId          string `json:"account_id"`
-
-	// New fields
-	ProviderAccountId string `json:"providerAccountId"`
-	CloudAccountId    string `json:"cloudAccountId"`
-
-	// IntegrationConfig populates data related to integration that is required for an agent
-	// to start collecting telemetry data
-	// keeping JSON key snake_case for backward compatibility
-	IntegrationConfig *IntegrationConfig `json:"integration_config,omitempty"`
-}
-
-type IntegrationConfig struct {
-	EnabledRegions []string               `json:"enabledRegions"`      // backward compatible
-	Telemetry      *AWSCollectionStrategy `json:"telemetry,omitempty"` // backward compatible
-
-	// new fields
-	AWS *AWSIntegrationConfig `json:"aws,omitempty"`
-}
-
-type AWSIntegrationConfig struct {
-	EnabledRegions []string               `json:"enabledRegions"`
-	Telemetry      *AWSCollectionStrategy `json:"telemetry,omitempty"`
-}

pkg/types/cloudintegrationtypes/regions.go

@@ -1,103 +0,0 @@
-package cloudintegrationtypes
-
-import (
-	"github.com/SigNoz/signoz/pkg/errors"
-)
-
-var (
-	ErrCodeInvalidCloudRegion    = errors.MustNewCode("invalid_cloud_region")
-	ErrCodeMismatchCloudProvider = errors.MustNewCode("cloud_provider_mismatch")
-)
-
-// List of all valid cloud regions on Amazon Web Services.
-var ValidAWSRegions = map[string]struct{}{
-	"af-south-1":     {}, // Africa (Cape Town).
-	"ap-east-1":      {}, // Asia Pacific (Hong Kong).
-	"ap-northeast-1": {}, // Asia Pacific (Tokyo).
-	"ap-northeast-2": {}, // Asia Pacific (Seoul).
-	"ap-northeast-3": {}, // Asia Pacific (Osaka).
-	"ap-south-1":     {}, // Asia Pacific (Mumbai).
-	"ap-south-2":     {}, // Asia Pacific (Hyderabad).
-	"ap-southeast-1": {}, // Asia Pacific (Singapore).
-	"ap-southeast-2": {}, // Asia Pacific (Sydney).
-	"ap-southeast-3": {}, // Asia Pacific (Jakarta).
-	"ap-southeast-4": {}, // Asia Pacific (Melbourne).
-	"ca-central-1":   {}, // Canada (Central).
-	"ca-west-1":      {}, // Canada West (Calgary).
-	"eu-central-1":   {}, // Europe (Frankfurt).
-	"eu-central-2":   {}, // Europe (Zurich).
-	"eu-north-1":     {}, // Europe (Stockholm).
-	"eu-south-1":     {}, // Europe (Milan).
-	"eu-south-2":     {}, // Europe (Spain).
-	"eu-west-1":      {}, // Europe (Ireland).
-	"eu-west-2":      {}, // Europe (London).
-	"eu-west-3":      {}, // Europe (Paris).
-	"il-central-1":   {}, // Israel (Tel Aviv).
-	"me-central-1":   {}, // Middle East (UAE).
-	"me-south-1":     {}, // Middle East (Bahrain).
-	"sa-east-1":      {}, // South America (Sao Paulo).
-	"us-east-1":      {}, // US East (N. Virginia).
-	"us-east-2":      {}, // US East (Ohio).
-	"us-west-1":      {}, // US West (N. California).
-	"us-west-2":      {}, // US West (Oregon).
-}
-
-// List of all valid cloud regions for Microsoft Azure.
-var ValidAzureRegions = map[string]struct{}{
-	"australiacentral":   {}, // Australia Central
-	"australiacentral2":  {}, // Australia Central 2
-	"australiaeast":      {}, // Australia East
-	"australiasoutheast": {}, // Australia Southeast
-	"austriaeast":        {}, // Austria East
-	"belgiumcentral":     {}, // Belgium Central
-	"brazilsouth":        {}, // Brazil South
-	"brazilsoutheast":    {}, // Brazil Southeast
-	"canadacentral":      {}, // Canada Central
-	"canadaeast":         {}, // Canada East
-	"centralindia":       {}, // Central India
-	"centralus":          {}, // Central US
-	"chilecentral":       {}, // Chile Central
-	"denmarkeast":        {}, // Denmark East
-	"eastasia":           {}, // East Asia
-	"eastus":             {}, // East US
-	"eastus2":            {}, // East US 2
-	"francecentral":      {}, // France Central
-	"francesouth":        {}, // France South
-	"germanynorth":       {}, // Germany North
-	"germanywestcentral": {}, // Germany West Central
-	"indonesiacentral":   {}, // Indonesia Central
-	"israelcentral":      {}, // Israel Central
-	"italynorth":         {}, // Italy North
-	"japaneast":          {}, // Japan East
-	"japanwest":          {}, // Japan West
-	"koreacentral":       {}, // Korea Central
-	"koreasouth":         {}, // Korea South
-	"malaysiawest":       {}, // Malaysia West
-	"mexicocentral":      {}, // Mexico Central
-	"newzealandnorth":    {}, // New Zealand North
-	"northcentralus":     {}, // North Central US
-	"northeurope":        {}, // North Europe
-	"norwayeast":         {}, // Norway East
-	"norwaywest":         {}, // Norway West
-	"polandcentral":      {}, // Poland Central
-	"qatarcentral":       {}, // Qatar Central
-	"southafricanorth":   {}, // South Africa North
-	"southafricawest":    {}, // South Africa West
-	"southcentralus":     {}, // South Central US
-	"southindia":         {}, // South India
-	"southeastasia":      {}, // Southeast Asia
-	"spaincentral":       {}, // Spain Central
-	"swedencentral":      {}, // Sweden Central
-	"switzerlandnorth":   {}, // Switzerland North
-	"switzerlandwest":    {}, // Switzerland West
-	"uaecentral":         {}, // UAE Central
-	"uaenorth":           {}, // UAE North
-	"uksouth":            {}, // UK South
-	"ukwest":             {}, // UK West
-	"westcentralus":      {}, // West Central US
-	"westeurope":         {}, // West Europe
-	"westindia":          {}, // West India
-	"westus":             {}, // West US
-	"westus2":            {}, // West US 2
-	"westus3":            {}, // West US 3
-}

pkg/types/cloudintegrationtypes/service.go

@@ -1,248 +0,0 @@
-package cloudintegrationtypes
-
-import (
-	"fmt"
-	"time"
-
-	"github.com/SigNoz/signoz/pkg/errors"
-	"github.com/SigNoz/signoz/pkg/types"
-	"github.com/SigNoz/signoz/pkg/types/dashboardtypes"
-	"github.com/SigNoz/signoz/pkg/valuer"
-)
-
-var (
-	S3Sync = valuer.NewString("s3sync")
-	// ErrCodeInvalidServiceID is the error code for invalid service id.
-	ErrCodeInvalidServiceID = errors.MustNewCode("invalid_service_id")
-)
-
-type ServiceID struct{ valuer.String }
-
-type CloudIntegrationService struct {
-	types.Identifiable
-	types.TimeAuditable
-	Type               ServiceID      `json:"type"`
-	Config             *ServiceConfig `json:"config"`
-	CloudIntegrationID valuer.UUID    `json:"cloudIntegrationID"`
-}
-
-// ServiceMetadata helps to quickly list available services and whether it is enabled or not.
-// As getting complete service definition is a heavy operation and the response is also large,
-// initial integration page load can be very slow.
-type ServiceMetadata struct {
-	ServiceDefinitionMetadata
-	// if the service is enabled for the account
-	Enabled bool `json:"enabled"`
-}
-
-type GettableServicesMetadata struct {
-	Services []*ServiceMetadata `json:"services"`
-}
-
-type Service struct {
-	ServiceDefinition
-	ServiceConfig *ServiceConfig `json:"serviceConfig"`
-}
-
-type GettableService = Service
-
-type UpdatableService struct {
-	Config *ServiceConfig `json:"config"`
-}
-
-type ServiceConfig struct {
-	AWS *AWSServiceConfig `json:"aws,omitempty"`
-}
-
-type AWSServiceConfig struct {
-	Logs    *AWSServiceLogsConfig    `json:"logs"`
-	Metrics *AWSServiceMetricsConfig `json:"metrics"`
-}
-
-// AWSServiceLogsConfig is AWS specific logs config for a service
-// NOTE: the JSON keys are snake case for backward compatibility with existing agents.
-type AWSServiceLogsConfig struct {
-	Enabled   bool                `json:"enabled"`
-	S3Buckets map[string][]string `json:"s3_buckets,omitempty"`
-}
-
-type AWSServiceMetricsConfig struct {
-	Enabled bool `json:"enabled"`
-}
-
-// ServiceDefinitionMetadata represents service definition metadata. This is useful for showing service tab in frontend.
-type ServiceDefinitionMetadata struct {
-	Id    string `json:"id"`
-	Title string `json:"title"`
-	Icon  string `json:"icon"`
-}
-
-type ServiceDefinition struct {
-	ServiceDefinitionMetadata
-	Overview         string              `json:"overview"` // markdown
-	Assets           Assets              `json:"assets"`
-	SupportedSignals SupportedSignals    `json:"supported_signals"`
-	DataCollected    DataCollected       `json:"dataCollected"`
-	Strategy         *CollectionStrategy `json:"telemetryCollectionStrategy"`
-}
-
-// CollectionStrategy is cloud provider specific configuration for signal collection,
-// this is used by agent to understand the nitty-gritty for collecting telemetry for the cloud provider.
-type CollectionStrategy struct {
-	AWS *AWSCollectionStrategy `json:"aws,omitempty"`
-}
-
-// Assets represents the collection of dashboards.
-type Assets struct {
-	Dashboards []Dashboard `json:"dashboards"`
-}
-
-// SupportedSignals for cloud provider's service.
-type SupportedSignals struct {
-	Logs    bool `json:"logs"`
-	Metrics bool `json:"metrics"`
-}
-
-// DataCollected is curated static list of metrics and logs, this is shown as part of service overview.
-type DataCollected struct {
-	Logs    []CollectedLogAttribute `json:"logs"`
-	Metrics []CollectedMetric       `json:"metrics"`
-}
-
-// CollectedLogAttribute represents a log attribute that is present in all log entries for a service,
-// this is shown as part of service overview.
-type CollectedLogAttribute struct {
-	Name string `json:"name"`
-	Path string `json:"path"`
-	Type string `json:"type"`
-}
-
-// CollectedMetric represents a metric that is collected for a service, this is shown as part of service overview.
-type CollectedMetric struct {
-	Name        string `json:"name"`
-	Type        string `json:"type"`
-	Unit        string `json:"unit"`
-	Description string `json:"description"`
-}
-
-// AWSCollectionStrategy represents signal collection strategy for AWS services.
-// this is AWS specific.
-// NOTE: this structure is still using snake case, for backward compatibility,
-// with existing agents.
-type AWSCollectionStrategy struct {
-	Metrics   *AWSMetricsStrategy `json:"aws_metrics,omitempty"`
-	Logs      *AWSLogsStrategy    `json:"aws_logs,omitempty"`
-	S3Buckets map[string][]string `json:"s3_buckets,omitempty"` // Only available in S3 Sync Service Type in AWS
-}
-
-// AWSMetricsStrategy represents metrics collection strategy for AWS services.
-// this is AWS specific.
-// NOTE: this structure is still using snake case, for backward compatibility,
-// with existing agents.
-type AWSMetricsStrategy struct {
-	// to be used as https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-cloudwatch-metricstream.html#cfn-cloudwatch-metricstream-includefilters
-	StreamFilters []struct {
-		// json tags here are in the shape expected by AWS API as detailed at
-		// https://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-properties-cloudwatch-metricstream-metricstreamfilter.html
-		Namespace   string   `json:"Namespace"`
-		MetricNames []string `json:"MetricNames,omitempty"`
-	} `json:"cloudwatch_metric_stream_filters"`
-}
-
-// AWSLogsStrategy represents logs collection strategy for AWS services.
-// this is AWS specific.
-// NOTE: this structure is still using snake case, for backward compatibility,
-// with existing agents.
-type AWSLogsStrategy struct {
-	Subscriptions []struct {
-		// subscribe to all logs groups with specified prefix.
-		// eg: `/aws/rds/`
-		LogGroupNamePrefix string `json:"log_group_name_prefix"`
-
-		// https://docs.aws.amazon.com/AmazonCloudWatch/latest/logs/FilterAndPatternSyntax.html
-		// "" implies no filtering is required.
-		FilterPattern string `json:"filter_pattern"`
-	} `json:"cloudwatch_logs_subscriptions"`
-}
-
-// Dashboard represents a dashboard definition for cloud integration.
-// This is used to show available pre-made dashboards for a service,
-// hence has additional fields like id, title and description
-type Dashboard struct {
-	Id          string                               `json:"id"`
-	Title       string                               `json:"title"`
-	Description string                               `json:"description"`
-	Definition  dashboardtypes.StorableDashboardData `json:"definition,omitempty"`
-}
-
-// SupportedServices is the map of supported services for each cloud provider.
-var SupportedServices = map[CloudProviderType][]ServiceID{
-	CloudProviderTypeAWS: {
-		{valuer.NewString("alb")},
-		{valuer.NewString("api-gateway")},
-		{valuer.NewString("dynamodb")},
-		{valuer.NewString("ec2")},
-		{valuer.NewString("ecs")},
-		{valuer.NewString("eks")},
-		{valuer.NewString("elasticache")},
-		{valuer.NewString("lambda")},
-		{valuer.NewString("msk")},
-		{valuer.NewString("rds")},
-		{valuer.NewString("s3sync")},
-		{valuer.NewString("sns")},
-		{valuer.NewString("sqs")},
-	},
-}
-
-// NewServiceID returns a new ServiceID from a string, validated against the supported services for the given cloud provider.
-func NewServiceID(provider CloudProviderType, service string) (ServiceID, error) {
-	services, ok := SupportedServices[provider]
-	if !ok {
-		return ServiceID{}, errors.NewInvalidInputf(ErrCodeInvalidServiceID, "no services defined for cloud provider: %s", provider)
-	}
-	for _, s := range services {
-		if s.StringValue() == service {
-			return s, nil
-		}
-	}
-	return ServiceID{}, errors.NewInvalidInputf(ErrCodeInvalidServiceID, "invalid service id %q for cloud provider %s", service, provider)
-}
-
-// UTILS
-
-// GetCloudIntegrationDashboardID returns the dashboard id for a cloud integration, given the cloud provider, service id, and dashboard id.
-// This is used to generate unique dashboard ids for cloud integration, and also to parse the dashboard id to get the cloud provider and service id when needed.
-func GetCloudIntegrationDashboardID(cloudProvider CloudProviderType, svcId, dashboardId string) string {
-	return fmt.Sprintf("cloud-integration--%s--%s--%s", cloudProvider, svcId, dashboardId)
-}
-
-// GetDashboardsFromAssets returns the list of dashboards for the cloud provider service from definition.
-func GetDashboardsFromAssets(
-	svcId string,
-	orgID valuer.UUID,
-	cloudProvider CloudProviderType,
-	createdAt time.Time,
-	assets Assets,
-) []*dashboardtypes.Dashboard {
-	dashboards := make([]*dashboardtypes.Dashboard, 0)
-
-	for _, d := range assets.Dashboards {
-		author := fmt.Sprintf("%s-integration", cloudProvider)
-		dashboards = append(dashboards, &dashboardtypes.Dashboard{
-			ID:     GetCloudIntegrationDashboardID(cloudProvider, svcId, d.Id),
-			Locked: true,
-			OrgID:  orgID,
-			Data:   d.Definition,
-			TimeAuditable: types.TimeAuditable{
-				CreatedAt: createdAt,
-				UpdatedAt: createdAt,
-			},
-			UserAuditable: types.UserAuditable{
-				CreatedBy: author,
-				UpdatedBy: author,
-			},
-		})
-	}
-
-	return dashboards
-}

pkg/types/cloudintegrationtypes/store.go

@@ -1,41 +0,0 @@
-package cloudintegrationtypes
-
-import (
-	"context"
-
-	"github.com/SigNoz/signoz/pkg/valuer"
-)
-
-type Store interface {
-	// GetAccountByID returns a cloud integration account by id
-	GetAccountByID(ctx context.Context, orgID, id valuer.UUID, provider CloudProviderType) (*StorableCloudIntegration, error)
-
-	// CreateAccount creates a new cloud integration account
-	CreateAccount(ctx context.Context, account *StorableCloudIntegration) (*StorableCloudIntegration, error)
-
-	// UpdateAccount updates an existing cloud integration account
-	UpdateAccount(ctx context.Context, account *StorableCloudIntegration) error
-
-	// RemoveAccount marks a cloud integration account as removed by setting the RemovedAt field
-	RemoveAccount(ctx context.Context, orgID, id valuer.UUID, provider CloudProviderType) error
-
-	// ListConnectedAccounts returns all the cloud integration accounts for the org and cloud provider
-	ListConnectedAccounts(ctx context.Context, orgID valuer.UUID, provider CloudProviderType) ([]*StorableCloudIntegration, error)
-
-	// GetConnectedAccount for a given provider
-	GetConnectedAccount(ctx context.Context, orgID valuer.UUID, provider CloudProviderType, providerAccountID string) (*StorableCloudIntegration, error)
-
-	// cloud_integration_service related methods
-
-	// GetServiceByServiceID returns the cloud integration service for the given cloud integration id and service id
-	GetServiceByServiceID(ctx context.Context, cloudIntegrationID valuer.UUID, serviceID ServiceID) (*StorableCloudIntegrationService, error)
-
-	// CreateService creates a new cloud integration service
-	CreateService(ctx context.Context, service *StorableCloudIntegrationService) (*StorableCloudIntegrationService, error)
-
-	// UpdateService updates an existing cloud integration service
-	UpdateService(ctx context.Context, service *StorableCloudIntegrationService) error
-
-	// ListServices returns all the cloud integration services for the given cloud integration id
-	ListServices(ctx context.Context, cloudIntegrationID valuer.UUID) ([]*StorableCloudIntegrationService, error)
-}

pkg/types/telemetrytypes/json_access_plan.go

@@ -40,7 +40,7 @@ type JSONAccessNode struct {
 	// Node information
 	Name       string
 	IsTerminal bool
-	isRoot     bool // marked true for only body_v2 and body_promoted
+	isRoot     bool // marked true for only body_json and body_json_promoted
 
 	// Precomputed type information (single source of truth)
 	AvailableTypes []JSONDataType

pkg/types/telemetrytypes/json_access_plan_test.go

@@ -1,19 +1,12 @@
 package telemetrytypes
 
 import (
-	"fmt"
 	"testing"
 
-	otelconstants "github.com/SigNoz/signoz-otel-collector/constants"
 	"github.com/stretchr/testify/require"
 	"gopkg.in/yaml.v3"
 )
 
-const (
-	bodyV2Column       = otelconstants.BodyV2Column
-	bodyPromotedColumn = otelconstants.BodyPromotedColumn
-)
-
 // ============================================================================
 // Helper Functions for Test Data Creation
 // ============================================================================
@@ -116,8 +109,8 @@ func TestNode_Alias(t *testing.T) {
 	}{
 		{
 			name:     "Root node returns name as-is",
-			node:     NewRootJSONAccessNode(bodyV2Column, 32, 0),
-			expected: bodyV2Column,
+			node:     NewRootJSONAccessNode("body_json", 32, 0),
+			expected: "body_json",
 		},
 		{
 			name: "Node without parent returns backticked name",
@@ -131,9 +124,9 @@ func TestNode_Alias(t *testing.T) {
 			name: "Node with root parent uses dot separator",
 			node: &JSONAccessNode{
 				Name:   "age",
-				Parent: NewRootJSONAccessNode(bodyV2Column, 32, 0),
+				Parent: NewRootJSONAccessNode("body_json", 32, 0),
 			},
-			expected: "`" + bodyV2Column + ".age`",
+			expected: "`" + "body_json" + ".age`",
 		},
 		{
 			name: "Node with non-root parent uses array separator",
@@ -141,10 +134,10 @@ func TestNode_Alias(t *testing.T) {
 				Name: "name",
 				Parent: &JSONAccessNode{
 					Name:   "education",
-					Parent: NewRootJSONAccessNode(bodyV2Column, 32, 0),
+					Parent: NewRootJSONAccessNode("body_json", 32, 0),
 				},
 			},
-			expected: "`" + bodyV2Column + ".education[].name`",
+			expected: "`" + "body_json" + ".education[].name`",
 		},
 		{
 			name: "Nested array path with multiple levels",
@@ -154,11 +147,11 @@ func TestNode_Alias(t *testing.T) {
 					Name: "awards",
 					Parent: &JSONAccessNode{
 						Name:   "education",
-						Parent: NewRootJSONAccessNode(bodyV2Column, 32, 0),
+						Parent: NewRootJSONAccessNode("body_json", 32, 0),
 					},
 				},
 			},
-			expected: "`" + bodyV2Column + ".education[].awards[].type`",
+			expected: "`" + "body_json" + ".education[].awards[].type`",
 		},
 	}
 
@@ -180,18 +173,18 @@ func TestNode_FieldPath(t *testing.T) {
 			name: "Simple field path from root",
 			node: &JSONAccessNode{
 				Name:   "user",
-				Parent: NewRootJSONAccessNode(bodyV2Column, 32, 0),
+				Parent: NewRootJSONAccessNode("body_json", 32, 0),
 			},
 			// FieldPath() always wraps the field name in backticks
-			expected: bodyV2Column + ".`user`",
+			expected: "body_json" + ".`user`",
 		},
 		{
 			name: "Field path with backtick-required key",
 			node: &JSONAccessNode{
 				Name:   "user-name", // requires backtick
-				Parent: NewRootJSONAccessNode(bodyV2Column, 32, 0),
+				Parent: NewRootJSONAccessNode("body_json", 32, 0),
 			},
-			expected: bodyV2Column + ".`user-name`",
+			expected: "body_json" + ".`user-name`",
 		},
 		{
 			name: "Nested field path",
@@ -199,11 +192,11 @@ func TestNode_FieldPath(t *testing.T) {
 				Name: "age",
 				Parent: &JSONAccessNode{
 					Name:   "user",
-					Parent: NewRootJSONAccessNode(bodyV2Column, 32, 0),
+					Parent: NewRootJSONAccessNode("body_json", 32, 0),
 				},
 			},
 			// FieldPath() always wraps the field name in backticks
-			expected: "`" + bodyV2Column + ".user`.`age`",
+			expected: "`" + "body_json" + ".user`.`age`",
 		},
 		{
 			name: "Array element field path",
@@ -211,11 +204,11 @@ func TestNode_FieldPath(t *testing.T) {
 				Name: "name",
 				Parent: &JSONAccessNode{
 					Name:   "education",
-					Parent: NewRootJSONAccessNode(bodyV2Column, 32, 0),
+					Parent: NewRootJSONAccessNode("body_json", 32, 0),
 				},
 			},
 			// FieldPath() always wraps the field name in backticks
-			expected: "`" + bodyV2Column + ".education`.`name`",
+			expected: "`" + "body_json" + ".education`.`name`",
 		},
 	}
 
@@ -243,36 +236,36 @@ func TestPlanJSON_BasicStructure(t *testing.T) {
 		{
 			name: "Simple path not promoted",
 			key:  makeKey("user.name", String, false),
-			expectedYAML: fmt.Sprintf(`
+			expectedYAML: `
 - name: user.name
-  column: %s
+  column: body_json
   availableTypes:
     - String
   maxDynamicTypes: 16
   isTerminal: true
   elemType: String
-`, bodyV2Column),
+`,
 		},
 		{
 			name: "Simple path promoted",
 			key:  makeKey("user.name", String, true),
-			expectedYAML: fmt.Sprintf(`
+			expectedYAML: `
 - name: user.name
-  column: %s
+  column: body_json
   availableTypes:
     - String
   maxDynamicTypes: 16
   isTerminal: true
   elemType: String
 - name: user.name
-  column: %s
+  column: body_json_promoted
   availableTypes:
     - String
   maxDynamicTypes: 16
   maxDynamicPaths: 256
   isTerminal: true
   elemType: String
-`, bodyV2Column, bodyPromotedColumn),
+`,
 		},
 		{
 			name:         "Empty path returns error",
@@ -285,8 +278,8 @@ func TestPlanJSON_BasicStructure(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			err := tt.key.SetJSONAccessPlan(JSONColumnMetadata{
-				BaseColumn:     bodyV2Column,
-				PromotedColumn: bodyPromotedColumn,
+				BaseColumn:     "body_json",
+				PromotedColumn: "body_json_promoted",
 			}, types)
 			if tt.expectErr {
 				require.Error(t, err)
@@ -311,9 +304,9 @@ func TestPlanJSON_ArrayPaths(t *testing.T) {
 		{
 			name: "Single array level - JSON branch only",
 			path: "education[].name",
-			expectedYAML: fmt.Sprintf(`
+			expectedYAML: `
 - name: education
-  column: %s
+  column: body_json
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
@@ -325,14 +318,14 @@ func TestPlanJSON_ArrayPaths(t *testing.T) {
       maxDynamicTypes: 8
       isTerminal: true
       elemType: String
-`, bodyV2Column),
+`,
 		},
 		{
 			name: "Single array level - both JSON and Dynamic branches",
 			path: "education[].awards[].type",
-			expectedYAML: fmt.Sprintf(`
+			expectedYAML: `
 - name: education
-  column: %s
+  column: body_json
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
@@ -359,14 +352,14 @@ func TestPlanJSON_ArrayPaths(t *testing.T) {
           maxDynamicPaths: 256
           isTerminal: true
           elemType: String
-`, bodyV2Column),
+`,
 		},
 		{
 			name: "Deeply nested array path",
 			path: "interests[].entities[].reviews[].entries[].metadata[].positions[].name",
-			expectedYAML: fmt.Sprintf(`
+			expectedYAML: `
 - name: interests
-  column: %s
+  column: body_json
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
@@ -406,14 +399,14 @@ func TestPlanJSON_ArrayPaths(t *testing.T) {
                             - String
                           isTerminal: true
                           elemType: String
-`, bodyV2Column),
+`,
 		},
 		{
 			name: "ArrayAnyIndex replacement [*] to []",
 			path: "education[*].name",
-			expectedYAML: fmt.Sprintf(`
+			expectedYAML: `
 - name: education
-  column: %s
+  column: body_json
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
@@ -425,7 +418,7 @@ func TestPlanJSON_ArrayPaths(t *testing.T) {
       maxDynamicTypes: 8
       isTerminal: true
       elemType: String
-`, bodyV2Column),
+`,
 		},
 	}
 
@@ -433,8 +426,8 @@ func TestPlanJSON_ArrayPaths(t *testing.T) {
 		t.Run(tt.name, func(t *testing.T) {
 			key := makeKey(tt.path, String, false)
 			err := key.SetJSONAccessPlan(JSONColumnMetadata{
-				BaseColumn:     bodyV2Column,
-				PromotedColumn: bodyPromotedColumn,
+				BaseColumn:     "body_json",
+				PromotedColumn: "body_json_promoted",
 			}, types)
 			require.NoError(t, err)
 			require.NotNil(t, key.JSONPlan)
@@ -452,15 +445,15 @@ func TestPlanJSON_PromotedVsNonPromoted(t *testing.T) {
 	t.Run("Non-promoted plan", func(t *testing.T) {
 		key := makeKey(path, String, false)
 		err := key.SetJSONAccessPlan(JSONColumnMetadata{
-			BaseColumn:     bodyV2Column,
-			PromotedColumn: bodyPromotedColumn,
+			BaseColumn:     "body_json",
+			PromotedColumn: "body_json_promoted",
 		}, types)
 		require.NoError(t, err)
 		require.Len(t, key.JSONPlan, 1)
 
-		expectedYAML := fmt.Sprintf(`
+		expectedYAML := `
 - name: education
-  column: %s
+  column: body_json
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
@@ -487,7 +480,7 @@ func TestPlanJSON_PromotedVsNonPromoted(t *testing.T) {
           maxDynamicPaths: 256
           isTerminal: true
           elemType: String
-`, bodyV2Column)
+`
 		got := plansToYAML(t, key.JSONPlan)
 		require.YAMLEq(t, expectedYAML, got)
 	})
@@ -495,15 +488,15 @@ func TestPlanJSON_PromotedVsNonPromoted(t *testing.T) {
 	t.Run("Promoted plan", func(t *testing.T) {
 		key := makeKey(path, String, true)
 		err := key.SetJSONAccessPlan(JSONColumnMetadata{
-			BaseColumn:     bodyV2Column,
-			PromotedColumn: bodyPromotedColumn,
+			BaseColumn:     "body_json",
+			PromotedColumn: "body_json_promoted",
 		}, types)
 		require.NoError(t, err)
 		require.Len(t, key.JSONPlan, 2)
 
-		expectedYAML := fmt.Sprintf(`
+		expectedYAML := `
 - name: education
-  column: %s
+  column: body_json
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
@@ -531,7 +524,7 @@ func TestPlanJSON_PromotedVsNonPromoted(t *testing.T) {
           isTerminal: true
           elemType: String
 - name: education
-  column: %s
+  column: body_json_promoted
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
@@ -561,7 +554,7 @@ func TestPlanJSON_PromotedVsNonPromoted(t *testing.T) {
           maxDynamicPaths: 256
           isTerminal: true
           elemType: String
-`, bodyV2Column, bodyPromotedColumn)
+`
 		got := plansToYAML(t, key.JSONPlan)
 		require.YAMLEq(t, expectedYAML, got)
 	})
@@ -582,11 +575,11 @@ func TestPlanJSON_EdgeCases(t *testing.T) {
 			expectErr: true,
 		},
 		{
-			name: "Very deep nesting - validates progression doesn't go negative",
-			path: "interests[].entities[].reviews[].entries[].metadata[].positions[].name",
-			expectedYAML: fmt.Sprintf(`
+			name:  "Very deep nesting - validates progression doesn't go negative",
+			path:  "interests[].entities[].reviews[].entries[].metadata[].positions[].name",
+			expectedYAML: `
 - name: interests
-  column: %s
+  column: body_json
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
@@ -626,14 +619,14 @@ func TestPlanJSON_EdgeCases(t *testing.T) {
                             - String
                           isTerminal: true
                           elemType: String
-`, bodyV2Column),
+`,
 		},
 		{
-			name: "Path with mixed scalar and array types",
-			path: "education[].type",
-			expectedYAML: fmt.Sprintf(`
+			name:  "Path with mixed scalar and array types",
+			path:  "education[].type",
+			expectedYAML: `
 - name: education
-  column: %s
+  column: body_json
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
@@ -646,20 +639,20 @@ func TestPlanJSON_EdgeCases(t *testing.T) {
       maxDynamicTypes: 8
       isTerminal: true
       elemType: String
-`, bodyV2Column),
+`,
 		},
 		{
-			name: "Exists with only array types available",
-			path: "education",
-			expectedYAML: fmt.Sprintf(`
+			name:  "Exists with only array types available",
+			path:  "education",
+			expectedYAML: `
 - name: education
-  column: %s
+  column: body_json
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
   isTerminal: true
   elemType: Array(JSON)
-`, bodyV2Column),
+`,
 		},
 	}
 
@@ -675,8 +668,8 @@ func TestPlanJSON_EdgeCases(t *testing.T) {
 			}
 			key := makeKey(tt.path, keyType, false)
 			err := key.SetJSONAccessPlan(JSONColumnMetadata{
-				BaseColumn:     bodyV2Column,
-				PromotedColumn: bodyPromotedColumn,
+				BaseColumn:     "body_json",
+				PromotedColumn: "body_json_promoted",
 			}, types)
 			if tt.expectErr {
 				require.Error(t, err)
@@ -694,15 +687,15 @@ func TestPlanJSON_TreeStructure(t *testing.T) {
 	path := "education[].awards[].participated[].team[].branch"
 	key := makeKey(path, String, false)
 	err := key.SetJSONAccessPlan(JSONColumnMetadata{
-		BaseColumn:     bodyV2Column,
-		PromotedColumn: bodyPromotedColumn,
+		BaseColumn:     "body_json",
+		PromotedColumn: "body_json_promoted",
 	}, types)
 	require.NoError(t, err)
 	require.Len(t, key.JSONPlan, 1)
 
-	expectedYAML := fmt.Sprintf(`
+	expectedYAML := `
 - name: education
-  column: %s
+  column: body_json
   availableTypes:
     - Array(JSON)
   maxDynamicTypes: 16
@@ -787,7 +780,7 @@ func TestPlanJSON_TreeStructure(t *testing.T) {
                   maxDynamicPaths: 64
                   isTerminal: true
                   elemType: String
-`, bodyV2Column)
+`
 
 	got := plansToYAML(t, key.JSONPlan)
 	require.YAMLEq(t, expectedYAML, got)

pkg/types/telemetrytypes/telemetrytypestest/metadata_store.go

@@ -20,11 +20,9 @@ type MockMetadataStore struct {
 	PromotedPathsMap   map[string]bool
 	LogsJSONIndexesMap map[string][]schemamigrator.Index
 	LookupKeysMap      map[telemetrytypes.MetricMetadataLookupKey]int64
-	// StaticFields holds signal-specific intrinsic field definitions (e.g. telemetrylogs.IntrinsicFields).
-	StaticFields map[string]telemetrytypes.TelemetryFieldKey
 }
 
-// NewMockMetadataStore creates a new instance of MockMetadataStore with initialized maps.
+// NewMockMetadataStore creates a new instance of MockMetadataStore with initialized maps
 func NewMockMetadataStore() *MockMetadataStore {
 	return &MockMetadataStore{
 		KeysMap:            make(map[string][]*telemetrytypes.TelemetryFieldKey),
@@ -35,20 +33,12 @@ func NewMockMetadataStore() *MockMetadataStore {
 		PromotedPathsMap:   make(map[string]bool),
 		LogsJSONIndexesMap: make(map[string][]schemamigrator.Index),
 		LookupKeysMap:      make(map[telemetrytypes.MetricMetadataLookupKey]int64),
-		StaticFields:       make(map[string]telemetrytypes.TelemetryFieldKey),
 	}
 }
 
-// SetStaticFields sets the static fields for the mock metadata store.
-// Pass the signal-specific intrinsic fields (e.g. telemetrylogs.IntrinsicFields) so the mock
-// mirrors what the real metadata store does when injecting those definitions into key results.
-func (m *MockMetadataStore) SetStaticFields(intrinsicFields map[string]telemetrytypes.TelemetryFieldKey) {
-	m.StaticFields = intrinsicFields
-}
-
 // GetKeys returns a map of field keys types.TelemetryFieldKey by name
 func (m *MockMetadataStore) GetKeys(ctx context.Context, fieldKeySelector *telemetrytypes.FieldKeySelector) (map[string][]*telemetrytypes.TelemetryFieldKey, bool, error) {
-	setOfKeys := make(map[string]*telemetrytypes.TelemetryFieldKey)
+
 	result := make(map[string][]*telemetrytypes.TelemetryFieldKey)
 
 	// If selector is nil, return all keys
@@ -56,30 +46,18 @@ func (m *MockMetadataStore) GetKeys(ctx context.Context, fieldKeySelector *telem
 		return m.KeysMap, true, nil
 	}
 
-	// Apply selector logic from KeysMap
+	// Apply selector logic
 	for name, keys := range m.KeysMap {
+		// Check if name matches
 		if matchesName(fieldKeySelector, name) {
+			filteredKeys := []*telemetrytypes.TelemetryFieldKey{}
 			for _, key := range keys {
 				if matchesKey(fieldKeySelector, key) {
-					if _, exists := setOfKeys[key.Text()]; !exists {
-						result[name] = append(result[name], key)
-						setOfKeys[key.Text()] = key
-					}
+					filteredKeys = append(filteredKeys, key)
 				}
 			}
-		}
-	}
-
-	// StaticFields (e.g. IntrinsicFields), mirroring the real metadata store.
-	for key, field := range m.StaticFields {
-		if !matchesName(fieldKeySelector, key) {
-			continue
-		}
-
-		if matchesKey(fieldKeySelector, &field) {
-			if _, exists := setOfKeys[field.Text()]; !exists {
-				result[field.Name] = append(result[field.Name], &field)
-				setOfKeys[field.Text()] = &field
+			if len(filteredKeys) > 0 {
+				result[name] = filteredKeys
 			}
 		}
 	}
@@ -130,7 +108,7 @@ func (m *MockMetadataStore) GetKey(ctx context.Context, fieldKeySelector *teleme
 
 	result := []*telemetrytypes.TelemetryFieldKey{}
 
-	// Find keys matching the selector from KeysMap
+	// Find keys matching the selector
 	for name, keys := range m.KeysMap {
 		if matchesName(fieldKeySelector, name) {
 			for _, key := range keys {
@@ -141,17 +119,6 @@ func (m *MockMetadataStore) GetKey(ctx context.Context, fieldKeySelector *teleme
 		}
 	}
 
-	// Add matching StaticFields (e.g. IntrinsicFields), same as the real metadata store does
-	for key, field := range m.StaticFields {
-		if !matchesName(fieldKeySelector, key) {
-			continue
-		}
-
-		if matchesKey(fieldKeySelector, &field) {
-			result = append(result, &field)
-		}
-	}
-
 	return result, nil
 }
 

tests/integration/fixtures/querier.py

@@ -58,6 +58,8 @@ def build_builder_query(
     step_interval: int = DEFAULT_STEP_INTERVAL,
     group_by: Optional[List[str]] = None,
     filter_expression: Optional[str] = None,
+    order_by: Optional[List[Dict]] = None,
+    limit: Optional[int] = None,
     functions: Optional[List[Dict]] = None,
     disabled: bool = False,
 ) -> Dict:
@@ -93,6 +95,12 @@ def build_builder_query(
     if filter_expression:
         spec["filter"] = {"expression": filter_expression}
 
+    if order_by:
+        spec["order"] = order_by
+
+    if limit is not None:
+        spec["limit"] = limit
+
     if functions:
         spec["functions"] = functions
 

tests/integration/src/passwordauthn/03_apikey.py

@@ -61,55 +61,3 @@ def test_api_key(signoz: types.SigNoz, get_token: Callable[[str, str], str]) ->
     assert found_pat["userId"] == found_user["id"]
     assert found_pat["name"] == "admin"
     assert found_pat["role"] == "ADMIN"
-
-
-def test_api_key_role(signoz: types.SigNoz, get_token: Callable[[str, str], str]) -> None:
-    admin_token = get_token("admin@integration.test", "password123Z$")
-
-    response = requests.post(
-        signoz.self.host_configs["8080"].get("/api/v1/pats"),
-        headers={"Authorization": f"Bearer {admin_token}"},
-        json={
-            "name": "viewer",
-            "role": "VIEWER",
-            "expiresInDays": 1,
-        },
-        timeout=2,
-    )
-
-    assert response.status_code == HTTPStatus.CREATED
-    pat_response = response.json()
-    assert "data" in pat_response
-    assert "token" in pat_response["data"]
-
-    response = requests.get(
-        signoz.self.host_configs["8080"].get("/api/v1/user"),
-        timeout=2,
-        headers={"SIGNOZ-API-KEY": f"{pat_response["data"]["token"]}"},
-    )
-
-    assert response.status_code == HTTPStatus.FORBIDDEN
-
-    response = requests.post(
-        signoz.self.host_configs["8080"].get("/api/v1/pats"),
-        headers={"Authorization": f"Bearer {admin_token}"},
-        json={
-            "name": "editor",
-            "role": "EDITOR",
-            "expiresInDays": 1,
-        },
-        timeout=2,
-    )
-
-    assert response.status_code == HTTPStatus.CREATED
-    pat_response = response.json()
-    assert "data" in pat_response
-    assert "token" in pat_response["data"]
-
-    response = requests.get(
-        signoz.self.host_configs["8080"].get("/api/v1/user"),
-        timeout=2,
-        headers={"SIGNOZ-API-KEY": f"{pat_response["data"]["token"]}"},
-    )
-
-    assert response.status_code == HTTPStatus.FORBIDDEN

tests/integration/src/querier/05_metrics_rate_cumulative_counter.py

@@ -2,16 +2,20 @@
 Look at the cumulative_counters_1h.jsonl file for the relevant data
 """
 
+import logging
 import os
 from datetime import datetime, timedelta, timezone
 from http import HTTPStatus
-from typing import Any, Callable, List
+from typing import Any, Callable, List, Optional, Union
+
+import pytest
 
 from fixtures import types
 from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.metrics import Metrics
 from fixtures.querier import (
     build_builder_query,
+    build_order_by,
     get_all_series,
     get_series_values,
     make_query_request,
@@ -71,16 +75,200 @@ def test_rate_with_steady_values_and_reset(
         assert v["value"] >= 0, f"Rate should not be negative: {v['value']}"
 
 
+def _assert_endpoint_rate_values(endpoint_values: dict) -> None:
+    # /health: 60 data points (t01-t60), steady +10/min
+    # rate = 10/60 = 0.167
+    if "/health" in endpoint_values:
+        health_values = endpoint_values["/health"]
+        assert (
+            len(health_values) >= 58
+        ), f"Expected >= 58 values for /health, got {len(health_values)}"
+        count_steady_health = sum(1 for v in health_values if v["value"] == 0.167)
+        assert (
+            count_steady_health >= 57
+        ), f"Expected >= 57 steady rate values (0.167) for /health, got {count_steady_health}"
+        # all /health rates should be 0.167 except possibly first/last due to boundaries
+        for v in health_values[1:-1]:
+            assert v["value"] == 0.167, f"Expected /health rate 0.167, got {v['value']}"
+
+    # /products: 51 data points with 10-minute gap (t20-t29 missing), steady +20/min
+    # rate = 20/60 = 0.333, gap causes lower averaged rate at boundary
+    if "/products" in endpoint_values:
+        products_values = endpoint_values["/products"]
+        assert (
+            len(products_values) >= 49
+        ), f"Expected >= 49 values for /products, got {len(products_values)}"
+        count_steady_products = sum(1 for v in products_values if v["value"] == 0.333)
+        # most values should be 0.333, some boundary values differ due to 10-min gap
+        assert (
+            count_steady_products >= 46
+        ), f"Expected >= 46 steady rate values (0.333) for /products, got {count_steady_products}"
+        # check that non-0.333 values are due to gap averaging (should be lower)
+        gap_boundary_values = [v["value"] for v in products_values if v["value"] != 0.333]
+        for val in gap_boundary_values:
+            assert (
+                0 < val < 0.333
+            ), f"Gap boundary values should be between 0 and 0.333, got {val}"
+
+    # /checkout: 61 data points (t00-t60), +1/min normal, +50/min spike at t40-t44
+    # normal rate = 1/60 = 0.0167, spike rate = 50/60 = 0.833
+    if "/checkout" in endpoint_values:
+        checkout_values = endpoint_values["/checkout"]
+        assert (
+            len(checkout_values) >= 59
+        ), f"Expected >= 59 values for /checkout, got {len(checkout_values)}"
+        count_steady_checkout = sum(1 for v in checkout_values if v["value"] == 0.0167)
+        assert (
+            count_steady_checkout >= 53
+        ), f"Expected >= 53 steady rate values (0.0167) for /checkout, got {count_steady_checkout}"
+        # check that spike values exist (traffic spike +50/min at t40-t44)
+        count_spike_checkout = sum(1 for v in checkout_values if v["value"] == 0.833)
+        assert (
+            count_spike_checkout >= 4
+        ), f"Expected >= 4 spike rate values (0.833) for /checkout, got {count_spike_checkout}"
+        # spike values should be consecutive
+        spike_indices = [
+            i for i, v in enumerate[Any](checkout_values) if v["value"] == 0.833
+        ]
+        assert len(spike_indices) >= 4, f"Expected >= 4 spike indices, got {spike_indices}"
+        for i in range(1, len(spike_indices)):
+            assert (
+                spike_indices[i] == spike_indices[i - 1] + 1
+            ), f"Spike indices should be consecutive, got {spike_indices}"
+
+    # /orders: 60 data points (t00-t60) with gap at t30, counter reset at t31 (150->2)
+    # rate = 5/60 = 0.0833
+    # reset at t31 causes: rate at t30 includes gap (lower), t31 has high rate after reset
+    if "/orders" in endpoint_values:
+        orders_values = endpoint_values["/orders"]
+        assert (
+            len(orders_values) >= 58
+        ), f"Expected >= 58 values for /orders, got {len(orders_values)}"
+        count_steady_orders = sum(1 for v in orders_values if v["value"] == 0.0833)
+        assert (
+            count_steady_orders >= 55
+        ), f"Expected >= 55 steady rate values (0.0833) for /orders, got {count_steady_orders}"
+        # check for counter reset effects - there should be some non-standard values
+        non_standard_orders = [v["value"] for v in orders_values if v["value"] != 0.0833]
+        assert (
+            len(non_standard_orders) >= 2
+        ), f"Expected >= 2 non-standard values due to counter reset, got {non_standard_orders}"
+        # post-reset value should be higher (new counter value / interval)
+        high_rate_orders = [v for v in non_standard_orders if v > 0.0833]
+        assert (
+            len(high_rate_orders) >= 1
+        ), f"Expected at least one high rate value after counter reset, got {non_standard_orders}"
+
+    # /users: 56 data points (t05-t60), sparse +1 every 5 minutes
+    # Rate = 1/60 = 0.0167 during increment, 0 during flat periods
+    if "/users" in endpoint_values:
+        users_values = endpoint_values["/users"]
+        assert (
+            len(users_values) >= 54
+        ), f"Expected >= 54 values for /users, got {len(users_values)}"
+        count_zero_users = sum(1 for v in users_values if v["value"] == 0)
+        # most values should be 0 (flat periods between increments)
+        assert (
+            count_zero_users >= 40
+        ), f"Expected >= 40 zero rate values for /users (sparse data), got {count_zero_users}"
+        # non-zero values should be 0.0167 (1/60 increment rate)
+        non_zero_users = [v["value"] for v in users_values if v["value"] != 0]
+        count_increment_rate = sum(1 for v in non_zero_users if v == 0.0167)
+        assert (
+            count_increment_rate >= 8
+        ), f"Expected >= 8 increment rate values (0.0167) for /users, got {count_increment_rate}"
+
+
+@pytest.mark.parametrize(
+    "metric_suffix,order_by,limit,expected_count,expected_endpoints",
+    [
+        (
+            "no_order",
+            None, # this is equivalent to sum(metric_name)
+            None,
+            5,
+            ["/products", "/health", "/checkout", "/orders", "/users"],
+        ),
+        (
+            "only_limit",
+            None, # this is equivalent to sum(metric_name)
+            3,
+            3,
+            ["/products", "/health", "/checkout"],
+        ),
+        (
+            "asc",
+            [build_order_by("endpoint", "asc")],
+            None,
+            5,
+            ["/checkout", "/health", "/orders", "/products", "/users"],
+        ),
+        (
+            "asc_lim3",
+            [build_order_by("endpoint", "asc")],
+            3,
+            3,
+            ["/checkout", "/health", "/orders"],
+        ),
+        (
+            "desc",
+            [build_order_by("endpoint", "desc")],
+            None,
+            5,
+            ["/users", "/products", "/orders", "/health", "/checkout"],
+        ),
+        (
+            "desc_lim3",
+            [build_order_by("endpoint", "desc")],
+            3,
+            3,
+            ["/users", "/products", "/orders"],
+        ),
+        (
+            "asc_metric_name",
+            [build_order_by("sum(test_rate_groupby_asc_metric_name)", "asc")],
+            None,
+            5,
+            ["/users", "/orders", "/checkout", "/health", "/products"],
+        ),
+        (
+            "asc_metric_name_lim3",
+            [build_order_by("sum(test_rate_groupby_asc_metric_name_lim3)", "asc")],
+            3,
+            3,
+            ["/users", "/orders", "/checkout"],
+        ),
+        (
+            "desc_metric_name",
+            [build_order_by("sum(test_rate_groupby_desc_metric_name)", "desc")],
+            None,
+            5,
+            ["/products", "/health", "/checkout", "/orders", "/users"],
+        ),
+        (
+            "desc_metric_name_lim3",
+            [build_order_by("sum(test_rate_groupby_desc_metric_name_lim3)", "desc")],
+            3,
+            3,
+            ["/products", "/health", "/checkout"],
+        ),
+    ],
+)
 def test_rate_group_by_endpoint(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token: Callable[[str, str], str],
     insert_metrics: Callable[[List[Metrics]], None],
+    metric_suffix: str,
+    order_by: Optional[List],
+    limit: Optional[int],
+    expected_count: int,
+    expected_endpoints: Union[set, List[str]],
 ) -> None:
     now = datetime.now(tz=timezone.utc).replace(second=0, microsecond=0)
     start_ms = int((now - timedelta(minutes=65)).timestamp() * 1000)
     end_ms = int(now.timestamp() * 1000)
-    metric_name = "test_rate_groupby"
+    metric_name = f"test_rate_groupby_{metric_suffix}"
 
     metrics = Metrics.load_from_file(
         CUMULATIVE_COUNTERS_FILE,
@@ -97,6 +285,8 @@ def test_rate_group_by_endpoint(
         "sum",
         temporality="cumulative",
         group_by=["endpoint"],
+        order_by=order_by,
+        limit=limit,
     )
 
     response = make_query_request(signoz, token, start_ms, end_ms, [query])
@@ -105,10 +295,23 @@ def test_rate_group_by_endpoint(
     data = response.json()
     all_series = get_all_series(data, "A")
 
-    # Should have 5 different endpoints
     assert (
-        len(all_series) == 5
-    ), f"Expected 5 series for 5 endpoints, got {len(all_series)}"
+        len(all_series) == expected_count
+    ), f"Expected {expected_count} series, got {len(all_series)}"
+
+    endpoint_labels = [
+        series.get("labels", [{}])[0].get("value", "unknown")
+        for series in all_series
+    ]
+
+    if isinstance(expected_endpoints, set):
+        assert (
+            set(endpoint_labels) == expected_endpoints
+        ), f"Expected endpoints {expected_endpoints}, got {set(endpoint_labels)}"
+    else:
+        assert endpoint_labels == expected_endpoints, (
+            f"Expected endpoints {expected_endpoints}, got {endpoint_labels}"
+        )
 
     # endpoint -> values
     endpoint_values = {}
@@ -117,11 +320,6 @@ def test_rate_group_by_endpoint(
         values = sorted(series.get("values", []), key=lambda x: x["timestamp"])
         endpoint_values[endpoint] = values
 
-    expected_endpoints = {"/products", "/health", "/checkout", "/orders", "/users"}
-    assert (
-        set(endpoint_values.keys()) == expected_endpoints
-    ), f"Expected endpoints {expected_endpoints}, got {set(endpoint_values.keys())}"
-
     # at no point rate should be negative
     for endpoint, values in endpoint_values.items():
         for v in values:
@@ -129,103 +327,4 @@ def test_rate_group_by_endpoint(
                 v["value"] >= 0
             ), f"Rate for {endpoint} should not be negative: {v['value']}"
 
-    # /health: 60 data points (t01-t60), steady +10/min
-    # rate = 10/60 = 0.167
-    health_values = endpoint_values["/health"]
-    assert (
-        len(health_values) >= 58
-    ), f"Expected >= 58 values for /health, got {len(health_values)}"
-    count_steady_health = sum(1 for v in health_values if v["value"] == 0.167)
-    assert (
-        count_steady_health >= 57
-    ), f"Expected >= 57 steady rate values (0.167) for /health, got {count_steady_health}"
-    # all /health rates should be 0.167 except possibly first/last due to boundaries
-    for v in health_values[1:-1]:
-        assert v["value"] == 0.167, f"Expected /health rate 0.167, got {v['value']}"
-
-    # /products: 51 data points with 10-minute gap (t20-t29 missing), steady +20/min
-    # rate = 20/60 = 0.333, gap causes lower averaged rate at boundary
-    products_values = endpoint_values["/products"]
-    assert (
-        len(products_values) >= 49
-    ), f"Expected >= 49 values for /products, got {len(products_values)}"
-    count_steady_products = sum(1 for v in products_values if v["value"] == 0.333)
-
-    # most values should be 0.333, some boundary values differ due to 10-min gap
-    assert (
-        count_steady_products >= 46
-    ), f"Expected >= 46 steady rate values (0.333) for /products, got {count_steady_products}"
-
-    # check that non-0.333 values are due to gap averaging (should be lower)
-    gap_boundary_values = [v["value"] for v in products_values if v["value"] != 0.333]
-    for val in gap_boundary_values:
-        assert (
-            0 < val < 0.333
-        ), f"Gap boundary values should be between 0 and 0.333, got {val}"
-
-    # /checkout: 61 data points (t00-t60), +1/min normal, +50/min spike at t40-t44
-    # normal rate = 1/60 = 0.0167, spike rate = 50/60 = 0.833
-    checkout_values = endpoint_values["/checkout"]
-    assert (
-        len(checkout_values) >= 59
-    ), f"Expected >= 59 values for /checkout, got {len(checkout_values)}"
-    count_steady_checkout = sum(1 for v in checkout_values if v["value"] == 0.0167)
-    assert (
-        count_steady_checkout >= 53
-    ), f"Expected >= 53 steady rate values (0.0167) for /checkout, got {count_steady_checkout}"
-    # check that spike values exist (traffic spike +50/min at t40-t44)
-    count_spike_checkout = sum(1 for v in checkout_values if v["value"] == 0.833)
-    assert (
-        count_spike_checkout >= 4
-    ), f"Expected >= 4 spike rate values (0.833) for /checkout, got {count_spike_checkout}"
-
-    # spike values should be consecutive
-    spike_indices = [
-        i for i, v in enumerate[Any](checkout_values) if v["value"] == 0.833
-    ]
-    assert len(spike_indices) >= 4, f"Expected >= 4 spike indices, got {spike_indices}"
-    # consecutiveness
-    for i in range(1, len(spike_indices)):
-        assert (
-            spike_indices[i] == spike_indices[i - 1] + 1
-        ), f"Spike indices should be consecutive, got {spike_indices}"
-
-    # /orders: 60 data points (t00-t60) with gap at t30, counter reset at t31 (150->2)
-    # rate = 5/60 = 0.0833
-    # reset at t31 causes: rate at t30 includes gap (lower), t31 has high rate after reset
-    orders_values = endpoint_values["/orders"]
-    assert (
-        len(orders_values) >= 58
-    ), f"Expected >= 58 values for /orders, got {len(orders_values)}"
-    count_steady_orders = sum(1 for v in orders_values if v["value"] == 0.0833)
-    assert (
-        count_steady_orders >= 55
-    ), f"Expected >= 55 steady rate values (0.0833) for /orders, got {count_steady_orders}"
-    # check for counter reset effects - there should be some non-standard values
-    non_standard_orders = [v["value"] for v in orders_values if v["value"] != 0.0833]
-    assert (
-        len(non_standard_orders) >= 2
-    ), f"Expected >= 2 non-standard values due to counter reset, got {non_standard_orders}"
-    # post-reset value should be higher (new counter value / interval)
-    high_rate_orders = [v for v in non_standard_orders if v > 0.0833]
-    assert (
-        len(high_rate_orders) >= 1
-    ), f"Expected at least one high rate value after counter reset, got {non_standard_orders}"
-
-    # /users: 56 data points (t05-t60), sparse +1 every 5 minutes
-    # Rate = 1/60 = 0.0167 during increment, 0 during flat periods
-    users_values = endpoint_values["/users"]
-    assert (
-        len(users_values) >= 54
-    ), f"Expected >= 54 values for /users, got {len(users_values)}"
-    count_zero_users = sum(1 for v in users_values if v["value"] == 0)
-    # most values should be 0 (flat periods between increments)
-    assert (
-        count_zero_users >= 40
-    ), f"Expected >= 40 zero rate values for /users (sparse data), got {count_zero_users}"
-    # non-zero values should be 0.0167 (1/60 increment rate)
-    non_zero_users = [v["value"] for v in users_values if v["value"] != 0]
-    count_increment_rate = sum(1 for v in non_zero_users if v == 0.0167)
-    assert (
-        count_increment_rate >= 8
-    ), f"Expected >= 8 increment rate values (0.0167) for /users, got {count_increment_rate}"
+    _assert_endpoint_rate_values(endpoint_values)

tests/integration/src/querier/07_metrics_multi_temporality.py

@@ -5,7 +5,7 @@ Look at the multi_temporality_counters_1h.jsonl file for the relevant data
 import random
 from datetime import datetime, timedelta, timezone
 from http import HTTPStatus
-from typing import Callable, List
+from typing import Callable, List, Optional, Union
 
 import pytest
 
@@ -14,6 +14,7 @@ from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.metrics import Metrics
 from fixtures.querier import (
     build_builder_query,
+    build_order_by,
     get_all_series,
     get_series_values,
     make_query_request,
@@ -91,6 +92,198 @@ def test_with_steady_values_and_reset(
         ), f"{time_aggregation} should not be negative: {v['value']}"
 
 
+def _assert_endpoint_group_values(  # pylint: disable=too-many-arguments
+    endpoint_values: dict,
+    stable_health_value: float,
+    stable_products_value: float,
+    stable_checkout_value: float,
+    spike_checkout_value: float,
+    stable_orders_value: float,
+    spike_users_value: float,
+    time_aggregation: str,
+) -> None:
+    # /health: 60 data points (t01-t60), steady +10/min
+    if "/health" in endpoint_values:
+        health_values = endpoint_values["/health"]
+        assert (
+            len(health_values) >= 58
+        ), f"Expected >= 58 values for /health, got {len(health_values)}"
+        count_steady_health = sum(
+            1 for v in health_values if v["value"] == stable_health_value
+        )
+        assert (
+            count_steady_health >= 57
+        ), f"Expected >= 57 steady rate values ({stable_health_value}) for /health, got {count_steady_health}"
+        # all /health rates should be stable except possibly first/last due to boundaries
+        for v in health_values[1:-1]:
+            assert (
+                v["value"] == stable_health_value
+            ), f"Expected /health rate {stable_health_value}, got {v['value']}"
+
+    # /products: 51 data points with 10-minute gap (t20-t29 missing), steady +20/min
+    if "/products" in endpoint_values:
+        products_values = endpoint_values["/products"]
+        assert (
+            len(products_values) >= 49
+        ), f"Expected >= 49 values for /products, got {len(products_values)}"
+        count_steady_products = sum(
+            1 for v in products_values if v["value"] == stable_products_value
+        )
+        # most values should be stable, some boundary values differ due to 10-min gap
+        assert (
+            count_steady_products >= 46
+        ), f"Expected >= 46 steady rate values ({stable_products_value}) for /products, got {count_steady_products}"
+        # check that non-stable values are due to gap averaging (should be lower)
+        gap_boundary_values = [
+            v["value"] for v in products_values if v["value"] != stable_products_value
+        ]
+        for val in gap_boundary_values:
+            assert (
+                0 < val < stable_products_value
+            ), f"Gap boundary values should be between 0 and {stable_products_value}, got {val}"
+
+    # /checkout: 61 data points (t00-t60), +1/min normal, +50/min spike at t40-t44
+    if "/checkout" in endpoint_values:
+        checkout_values = endpoint_values["/checkout"]
+        assert (
+            len(checkout_values) >= 59
+        ), f"Expected >= 59 values for /checkout, got {len(checkout_values)}"
+        count_steady_checkout = sum(
+            1 for v in checkout_values if v["value"] == stable_checkout_value
+        )
+        assert (
+            count_steady_checkout >= 53
+        ), f"Expected >= 53 steady {time_aggregation} values ({stable_checkout_value}) for /checkout, got {count_steady_checkout}"
+        # check that spike values exist (traffic spike +50/min at t40-t44)
+        count_spike_checkout = sum(
+            1 for v in checkout_values if v["value"] == spike_checkout_value
+        )
+        assert (
+            count_spike_checkout >= 4
+        ), f"Expected >= 4 spike {time_aggregation} values ({spike_checkout_value}) for /checkout, got {count_spike_checkout}"
+        # spike values should be consecutive
+        spike_indices = [
+            i for i, v in enumerate(checkout_values) if v["value"] == spike_checkout_value
+        ]
+        assert len(spike_indices) >= 4, f"Expected >= 4 spike indices, got {spike_indices}"
+        for i in range(1, len(spike_indices)):
+            assert (
+                spike_indices[i] == spike_indices[i - 1] + 1
+            ), f"Spike indices should be consecutive, got {spike_indices}"
+
+    # /orders: 60 data points (t00-t60) with gap at t30, counter reset at t31 (150->2)
+    # reset at t31 causes: rate/increase at t30 includes gap (lower), t31 has high rate after reset
+    if "/orders" in endpoint_values:
+        orders_values = endpoint_values["/orders"]
+        assert (
+            len(orders_values) >= 58
+        ), f"Expected >= 58 values for /orders, got {len(orders_values)}"
+        count_steady_orders = sum(
+            1 for v in orders_values if v["value"] == stable_orders_value
+        )
+        assert (
+            count_steady_orders >= 55
+        ), f"Expected >= 55 steady {time_aggregation} values ({stable_orders_value}) for /orders, got {count_steady_orders}"
+        # check for counter reset effects - there should be some non-standard values
+        non_standard_orders = [
+            v["value"] for v in orders_values if v["value"] != stable_orders_value
+        ]
+        assert (
+            len(non_standard_orders) >= 2
+        ), f"Expected >= 2 non-standard values due to counter reset, got {non_standard_orders}"
+        # post-reset value should be higher (new counter value / interval)
+        high_rate_orders = [v for v in non_standard_orders if v > stable_orders_value]
+        assert (
+            len(high_rate_orders) >= 1
+        ), f"Expected at least one high {time_aggregation} value after counter reset, got {non_standard_orders}"
+
+    # /users: 56 data points (t05-t60), sparse +1 every 5 minutes
+    if "/users" in endpoint_values:
+        users_values = endpoint_values["/users"]
+        assert (
+            len(users_values) >= 54
+        ), f"Expected >= 54 values for /users, got {len(users_values)}"
+        count_zero_users = sum(1 for v in users_values if v["value"] == 0)
+        # most values should be 0 (flat periods between increments)
+        assert (
+            count_zero_users >= 40
+        ), f"Expected >= 40 zero {time_aggregation} values for /users (sparse data), got {count_zero_users}"
+        # non-zero values should be stable increment rate
+        non_zero_users = [v["value"] for v in users_values if v["value"] != 0]
+        count_increment_rate = sum(1 for v in non_zero_users if v == spike_users_value)
+        assert (
+            count_increment_rate >= 8
+        ), f"Expected >= 8 increment {time_aggregation} values ({spike_users_value}) for /users, got {count_increment_rate}"
+
+
+@pytest.mark.parametrize(
+    "order_suffix,order_by_spec,limit,expected_count,expected_endpoints",
+    [
+        (
+            "no_order",
+            None,
+            None,
+            5,
+            ["/products", "/health", "/checkout", "/orders", "/users"],
+        ),
+        (
+            "asc",
+            ("endpoint", "asc"),
+            None,
+            5,
+            ["/checkout", "/health", "/orders", "/products", "/users"],
+        ),
+        (
+            "asc_lim3",
+            ("endpoint", "asc"),
+            3,
+            3,
+            ["/checkout", "/health", "/orders"],
+        ),
+        (
+            "desc",
+            ("endpoint", "desc"),
+            None,
+            5,
+            ["/users", "/products", "/orders", "/health", "/checkout"],
+        ),
+        (
+            "desc_lim3",
+            ("endpoint", "desc"),
+            3,
+            3,
+            ["/users", "/products", "/orders"],
+        ),
+        (
+            "asc_metric_name",
+            ("sum_metric", "asc"),
+            None,
+            5,
+            ["/users", "/orders", "/checkout", "/health", "/products"],
+        ),
+        (
+            "asc_metric_name_lim3",
+            ("sum_metric", "asc"),
+            3,
+            3,
+            ["/users", "/orders", "/checkout"],
+        ),
+        (
+            "desc_metric_name",
+            ("sum_metric", "desc"),
+            None,
+            5,
+            ["/products", "/health", "/checkout", "/orders", "/users"],
+        ),
+        (
+            "desc_metric_name_lim3",
+            ("sum_metric", "desc"),
+            3,
+            3,
+            ["/products", "/health", "/checkout"],
+        ),
+    ],
+)
 @pytest.mark.parametrize(
     "time_aggregation, stable_health_value, stable_products_value, stable_checkout_value, spike_checkout_value, stable_orders_value, spike_users_value",
     [
@@ -110,11 +303,24 @@ def test_group_by_endpoint(
     spike_checkout_value: float,
     stable_orders_value: float,
     spike_users_value: float,
+    order_suffix: str,
+    order_by_spec: Optional[tuple],
+    limit: Optional[int],
+    expected_count: int,
+    expected_endpoints: Union[set, List[str]],
 ) -> None:
     now = datetime.now(tz=timezone.utc).replace(second=0, microsecond=0)
     start_ms = int((now - timedelta(minutes=65)).timestamp() * 1000)
     end_ms = int(now.timestamp() * 1000)
-    metric_name = f"test_{time_aggregation}_groupby"
+    metric_name = f"test_{time_aggregation}_groupby_{order_suffix}"
+
+    # Build order_by at runtime so metric name reflects actual time_aggregation
+    order_by = None
+    if order_by_spec is not None:
+        key, direction = order_by_spec
+        if key == "sum_metric":
+            key = f"sum({metric_name})"
+        order_by = [build_order_by(key, direction)]
 
     metrics = Metrics.load_from_file(
         MULTI_TEMPORALITY_FILE,
@@ -130,6 +336,8 @@ def test_group_by_endpoint(
         time_aggregation,
         "sum",
         group_by=["endpoint"],
+        order_by=order_by,
+        limit=limit,
     )
 
     response = make_query_request(signoz, token, start_ms, end_ms, [query])
@@ -137,10 +345,23 @@ def test_group_by_endpoint(
 
     data = response.json()
     all_series = get_all_series(data, "A")
-    # Should have 5 different endpoints
     assert (
-        len(all_series) == 5
-    ), f"Expected 5 series for 5 endpoints, got {len(all_series)}"
+        len(all_series) == expected_count
+    ), f"Expected {expected_count} series, got {len(all_series)}"
+
+    endpoint_labels = [
+        series.get("labels", [{}])[0].get("value", "unknown")
+        for series in all_series
+    ]
+
+    if isinstance(expected_endpoints, set):
+        assert (
+            set(endpoint_labels) == expected_endpoints
+        ), f"Expected endpoints {expected_endpoints}, got {set(endpoint_labels)}"
+    else:
+        assert endpoint_labels == expected_endpoints, (
+            f"Expected endpoints {expected_endpoints}, got {endpoint_labels}"
+        )
 
     # endpoint -> values
     endpoint_values = {}
@@ -149,11 +370,6 @@ def test_group_by_endpoint(
         values = sorted(series.get("values", []), key=lambda x: x["timestamp"])
         endpoint_values[endpoint] = values
 
-    expected_endpoints = {"/products", "/health", "/checkout", "/orders", "/users"}
-    assert (
-        set(endpoint_values.keys()) == expected_endpoints
-    ), f"Expected endpoints {expected_endpoints}, got {set(endpoint_values.keys())}"
-
     # at no point rate should be negative
     for endpoint, values in endpoint_values.items():
         for v in values:
@@ -161,117 +377,16 @@ def test_group_by_endpoint(
                 v["value"] >= 0
             ), f"Rate for {endpoint} should not be negative: {v['value']}"
 
-    # /health: 60 data points (t01-t60), steady +10/min
-    health_values = endpoint_values["/health"]
-    assert (
-        len(health_values) >= 58
-    ), f"Expected >= 58 values for /health, got {len(health_values)}"
-    count_steady_health = sum(
-        1 for v in health_values if v["value"] == stable_health_value
+    _assert_endpoint_group_values(
+        endpoint_values,
+        stable_health_value,
+        stable_products_value,
+        stable_checkout_value,
+        spike_checkout_value,
+        stable_orders_value,
+        spike_users_value,
+        time_aggregation,
     )
-    assert (
-        count_steady_health >= 57
-    ), f"Expected >= 57 steady rate values ({stable_health_value}) for /health, got {count_steady_health}"
-    # all /health rates should be state except possibly first/last due to boundaries
-    for v in health_values[1:-1]:
-        assert (
-            v["value"] == stable_health_value
-        ), f"Expected /health rate {stable_health_value}, got {v['value']}"
-
-    # /products: 51 data points with 10-minute gap (t20-t29 missing), steady +20/min
-    products_values = endpoint_values["/products"]
-    assert (
-        len(products_values) >= 49
-    ), f"Expected >= 49 values for /products, got {len(products_values)}"
-    count_steady_products = sum(
-        1 for v in products_values if v["value"] == stable_products_value
-    )
-
-    # most values should be stable, some boundary values differ due to 10-min gap
-    assert (
-        count_steady_products >= 46
-    ), f"Expected >= 46 steady rate values ({stable_products_value}) for /products, got {count_steady_products}"
-
-    # check that non-stable values are due to gap averaging (should be lower)
-    gap_boundary_values = [
-        v["value"] for v in products_values if v["value"] != stable_products_value
-    ]
-    for val in gap_boundary_values:
-        assert (
-            0 < val < stable_products_value
-        ), f"Gap boundary values should be between 0 and {stable_products_value}, got {val}"
-
-    # /checkout: 61 data points (t00-t60), +1/min normal, +50/min spike at t40-t44
-    checkout_values = endpoint_values["/checkout"]
-    assert (
-        len(checkout_values) >= 59
-    ), f"Expected >= 59 values for /checkout, got {len(checkout_values)}"
-    count_steady_checkout = sum(
-        1 for v in checkout_values if v["value"] == stable_checkout_value
-    )
-    assert (
-        count_steady_checkout >= 53
-    ), f"Expected >= 53 steady {time_aggregation} values ({stable_checkout_value}) for /checkout, got {count_steady_checkout}"
-    # check that spike values exist (traffic spike +50/min at t40-t44)
-    count_spike_checkout = sum(
-        1 for v in checkout_values if v["value"] == spike_checkout_value
-    )
-    assert (
-        count_spike_checkout >= 4
-    ), f"Expected >= 4 spike {time_aggregation} values ({spike_checkout_value}) for /checkout, got {count_spike_checkout}"
-
-    # spike values should be consecutive
-    spike_indices = [
-        i for i, v in enumerate(checkout_values) if v["value"] == spike_checkout_value
-    ]
-    assert len(spike_indices) >= 4, f"Expected >= 4 spike indices, got {spike_indices}"
-    # consecutiveness
-    for i in range(1, len(spike_indices)):
-        assert (
-            spike_indices[i] == spike_indices[i - 1] + 1
-        ), f"Spike indices should be consecutive, got {spike_indices}"
-
-    # /orders: 60 data points (t00-t60) with gap at t30, counter reset at t31 (150->2)
-    # reset at t31 causes: rate/increase at t30 includes gap (lower), t31 has high rate after reset
-    orders_values = endpoint_values["/orders"]
-    assert (
-        len(orders_values) >= 58
-    ), f"Expected >= 58 values for /orders, got {len(orders_values)}"
-    count_steady_orders = sum(
-        1 for v in orders_values if v["value"] == stable_orders_value
-    )
-    assert (
-        count_steady_orders >= 55
-    ), f"Expected >= 55 steady {time_aggregation} values ({stable_orders_value}) for /orders, got {count_steady_orders}"
-    # check for counter reset effects - there should be some non-standard values
-    non_standard_orders = [
-        v["value"] for v in orders_values if v["value"] != stable_orders_value
-    ]
-    assert (
-        len(non_standard_orders) >= 2
-    ), f"Expected >= 2 non-standard values due to counter reset, got {non_standard_orders}"
-    # post-reset value should be higher (new counter value / interval)
-    high_rate_orders = [v for v in non_standard_orders if v > stable_orders_value]
-    assert (
-        len(high_rate_orders) >= 1
-    ), f"Expected at least one high {time_aggregation} value after counter reset, got {non_standard_orders}"
-
-    # /users: 56 data points (t05-t60), sparse +1 every 5 minutes
-    users_values = endpoint_values["/users"]
-    assert (
-        len(users_values) >= 54
-    ), f"Expected >= 54 values for /users, got {len(users_values)}"
-    count_zero_users = sum(1 for v in users_values if v["value"] == 0)
-    # most values should be 0 (flat periods between increments)
-    assert (
-        count_zero_users >= 40
-    ), f"Expected >= 40 zero {time_aggregation} values for /users (sparse data), got {count_zero_users}"
-    # non-zero values should be 0.0167 (1/60 increment rate)
-    non_zero_users = [v["value"] for v in users_values if v["value"] != 0]
-    count_increment_rate = sum(1 for v in non_zero_users if v == spike_users_value)
-    assert (
-        count_increment_rate >= 8
-    ), f"Expected >= 8 increment {time_aggregation} values ({spike_users_value}) for /users, got {count_increment_rate}"
 
 
 @pytest.mark.parametrize(

tests/integration/src/querier/08_metrics_histogram.py

@@ -4,7 +4,7 @@ Look at the histogram_data_1h.jsonl file for the relevant data
 
 from datetime import datetime, timedelta, timezone
 from http import HTTPStatus
-from typing import Callable, List
+from typing import Callable, List, Optional, Union
 
 import pytest
 
@@ -13,13 +13,16 @@ from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.metrics import Metrics
 from fixtures.querier import (
     build_builder_query,
+    build_order_by,
     get_all_series,
     get_series_values,
     make_query_request,
 )
 from fixtures.utils import get_testdata_file_path
 
+
 FILE = get_testdata_file_path("histogram_data_1h.jsonl")
+FILE_WITH_MANY_GROUPS = get_testdata_file_path("histogram_data_1h_many_groups.jsonl")
 
 
 @pytest.mark.parametrize(
@@ -521,4 +524,564 @@ def test_histogram_percentile_for_delta_service(
     assert len(result_values) == 60
     assert result_values[0]["value"] == zeroth_value
     assert result_values[1]["value"] == first_value
-    assert result_values[-1]["value"] == last_value
+    assert result_values[-1]["value"] == last_value
+
+
+def _assert_series_endpoint_labels(
+    series: list,
+    expected_endpoints: Union[set, List[str]],
+    prefix: str,
+) -> None:
+    labels = [s.get("labels", [{}])[0].get("value", "unknown") for s in series]
+    if isinstance(expected_endpoints, set):
+        assert (
+            set(labels) == expected_endpoints
+        ), f"Expected {prefix} endpoints {expected_endpoints}, got {set(labels)}"
+    else:
+        assert labels == expected_endpoints, (
+            f"Expected {prefix} endpoints in order {expected_endpoints}, got {labels}"
+        )
+
+
+@pytest.mark.parametrize(
+    "order_suffix,order_by,limit,expected_count,expected_endpoints",
+    [
+        (
+            "no_order",
+            None,
+            None,
+            3,
+            ["/checkout", "/health", "/orders"],
+        ),
+        (
+            "asc",
+            [build_order_by("endpoint", "asc")],
+            None,
+            3,
+            ["/checkout", "/health", "/orders"],
+        ),
+        (
+            "asc_lim2",
+            [build_order_by("endpoint", "asc")],
+            2,
+            2,
+            ["/checkout", "/health"],
+        ),
+        (
+            "desc",
+            [build_order_by("endpoint", "desc")],
+            None,
+            3,
+            ["/orders", "/health", "/checkout"],
+        ),
+        (
+            "desc_lim2",
+            [build_order_by("endpoint", "desc")],
+            2,
+            2,
+            ["/orders", "/health"],
+        ),
+        (
+            "asc_metric_name",
+            [build_order_by("count(test_histogram_count_groupby_asc_metric_name)", "asc")],
+            None,
+            3,
+            ["/health", "/orders", "/checkout"], ## health and orders have the same size so they are then sorted endpoint as a tiebreaker
+        ),
+        (
+            "asc_metric_name_lim2",
+            [build_order_by("count(test_histogram_count_groupby_asc_metric_name_lim2)", "asc")],
+            2,
+            2,
+            ["/health", "/orders"],
+        ),
+        (
+            "desc_metric_name",
+            [build_order_by("count(test_histogram_count_groupby_desc_metric_name)", "desc")],
+            None,
+            3,
+            ["/checkout", "/health", "/orders"], ## health and orders have the same size so they are then sorted endpoint as a tiebreaker
+        ),
+        (
+            "desc_metric_name_lim2",
+            [build_order_by("count(test_histogram_count_groupby_desc_metric_name_lim2)", "desc")],
+            2,
+            2,
+            ["/checkout", "/health"],
+        ),
+    ],
+)
+def test_histogram_count_group_by_endpoint(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    insert_metrics: Callable[[List[Metrics]], None],
+    order_suffix: str,
+    order_by: Optional[List],
+    limit: Optional[int],
+    expected_count: int,
+    expected_endpoints: Union[set, List[str]],
+) -> None:
+    now = datetime.now(tz=timezone.utc).replace(second=0, microsecond=0)
+    start_ms = int((now - timedelta(minutes=65)).timestamp() * 1000)
+    end_ms = int(now.timestamp() * 1000)
+    metric_name = f"test_histogram_count_groupby_{order_suffix}"
+
+    metrics = Metrics.load_from_file(
+        FILE,
+        base_time=now - timedelta(minutes=60),
+        metric_name_override=metric_name,
+    )
+    insert_metrics(metrics)
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    query_count = build_builder_query(
+        "A",
+        metric_name,
+        "increase",
+        "count",
+        comparisonSpaceAggregationParam={"threshold": 1000, "operator": "<="},
+        group_by=["endpoint"],
+        order_by=order_by,
+        limit=limit,
+    )
+
+    response = make_query_request(signoz, token, start_ms, end_ms, [query_count])
+    assert response.status_code == HTTPStatus.OK
+
+    data = response.json()
+    count_all_series = get_all_series(data, "A")
+
+    assert (
+        len(count_all_series) == expected_count
+    ), f"Expected {expected_count} series, got {len(count_all_series)}"
+
+    _assert_series_endpoint_labels(count_all_series, expected_endpoints, "count")
+
+    count_values = {}
+    for series in count_all_series:
+        endpoint = series.get("labels", [{}])[0].get("value", "unknown")
+        count_values[endpoint] = sorted(
+            series.get("values", []), key=lambda x: x["timestamp"]
+        )
+
+    for endpoint, values in count_values.items():
+        for v in values:
+            assert v["value"] >= 0, f"Count for {endpoint} should not be negative: {v['value']}"
+
+    # /health (cumulative, service=api): 59 points, increase starts at 11/min → 69/min
+    if "/health" in count_values:
+        vals = count_values["/health"]
+        assert vals[0]["value"] == 11, f"Expected /health count first=11, got {vals[0]['value']}"
+        assert vals[-1]["value"] == 69, f"Expected /health count last=69, got {vals[-1]['value']}"
+
+    # /orders (cumulative, service=api): same distribution as /health
+    if "/orders" in count_values:
+        vals = count_values["/orders"]
+        assert vals[0]["value"] == 11, f"Expected /orders count first=11, got {vals[0]['value']}"
+        assert vals[-1]["value"] == 69, f"Expected /orders count last=69, got {vals[-1]['value']}"
+
+    # /checkout (delta, service=web): 60 points, zeroth=12345 (raw delta), then 11/min → 69/min
+    if "/checkout" in count_values:
+        vals = count_values["/checkout"]
+        assert vals[0]["value"] == 12345, f"Expected /checkout count zeroth=12345, got {vals[0]['value']}"
+        assert vals[1]["value"] == 11, f"Expected /checkout count first=11, got {vals[1]['value']}"
+        assert vals[-1]["value"] == 69, f"Expected /checkout count last=69, got {vals[-1]['value']}"
+
+
+@pytest.mark.parametrize(
+    "order_suffix,order_by,limit,expected_count,expected_endpoints",
+    [
+        (
+            "no_order",
+            None,
+            None,
+            4,
+            [ "/checkout", "/health", "/orders", "/coupon"],
+        ),
+        (
+            "only_limit",
+            None,
+            1,
+            1,
+            [ "/checkout"], ##health and checkout have the same size so they are then sorted endpoint as a tiebreaker, and only checkout makes the limit
+        ),
+        (
+            "asc",
+            [build_order_by("endpoint", "asc")],
+            None,
+            4,
+            [ "/checkout", "/coupon", "/health", "/orders"],
+        ),
+        (
+            "asc_lim2",
+            [build_order_by("endpoint", "asc")],
+            2,
+            2,
+            ["/checkout", "/coupon"],
+        ),
+        (
+            "desc",
+            [build_order_by("endpoint", "desc")],
+            None,
+            4,
+            ["/orders", "/health", "/coupon", "/checkout"],
+        ),
+        (
+            "desc_lim2",
+            [build_order_by("endpoint", "desc")],
+            2,
+            2,
+            ["/orders", "/health"],
+        ),
+        (
+            "asc_metric_name",
+            [build_order_by("p75(test_histogram_p75_groupby_asc_metric_name)", "asc")],
+            None,
+            4,
+            ["/coupon", "/orders", "/checkout", "/health"], ## health and checkout have the same size so they are then sorted endpoint as a tiebreaker
+        ),
+        (
+            "asc_metric_name_lim2",
+            [build_order_by("p75(test_histogram_p75_groupby_asc_metric_name_lim2)", "asc")],
+            2,
+            2,
+            ["/coupon", "/orders"],
+        ),
+        (
+            "asc_metric_name_lim3",
+            [build_order_by("p75(test_histogram_p75_groupby_asc_metric_name_lim3)", "asc")],
+            3,
+            3,
+            ["/coupon", "/orders", "/checkout"], ##health and checkout have the same size so they are then sorted endpoint as a tiebreaker, and only checkout makes the limit
+        ),
+        (
+            "desc_metric_name",
+            [build_order_by("p75(test_histogram_p75_groupby_desc_metric_name)", "desc")],
+            None,
+            4,
+            [ "/checkout", "/health", "/orders", "/coupon"],
+        ),
+        (
+            "desc_metric_name_lim2",
+            [build_order_by("p75(test_histogram_p75_groupby_desc_metric_name_lim2)", "desc")],
+            2,
+            2,
+            [ "/checkout", "/health"],
+        ),
+        (
+            "desc_metric_name_lim2",
+            [build_order_by("p75(test_histogram_p75_groupby_desc_metric_name_lim2)", "desc")],
+            1,
+            1,
+            [ "/checkout"], ##health and checkout have the same size so they are then sorted endpoint as a tiebreaker, and only checkout makes the limit
+        ),
+    ],
+)
+def test_histogram_percentile_group_by_endpoint(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    insert_metrics: Callable[[List[Metrics]], None],
+    order_suffix: str,
+    order_by: Optional[List],
+    limit: Optional[int],
+    expected_count: int,
+    expected_endpoints: Union[set, List[str]],
+) -> None:
+    now = datetime.now(tz=timezone.utc).replace(second=0, microsecond=0)
+    start_ms = int((now - timedelta(minutes=65)).timestamp() * 1000)
+    end_ms = int(now.timestamp() * 1000)
+    metric_name = f"test_histogram_p75_groupby_{order_suffix}"
+
+    metrics = Metrics.load_from_file(
+        FILE_WITH_MANY_GROUPS,
+        base_time=now - timedelta(minutes=60),
+        metric_name_override=metric_name,
+    )
+    insert_metrics(metrics)
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    query_p75 = build_builder_query(
+        "A",
+        metric_name,
+        "doesnotreallymatter",
+        "p75",
+        group_by=["endpoint"],
+        order_by=order_by,
+        limit=limit,
+    )
+
+    response = make_query_request(signoz, token, start_ms, end_ms, [query_p75])
+    assert response.status_code == HTTPStatus.OK
+
+    data = response.json()
+    p75_series = get_all_series(data, "A")
+
+    for series in p75_series:
+        endpoint = series.get("labels", [{}])[0].get("value", "unknown")
+
+    assert (
+        len(p75_series) == expected_count
+    ), f"Expected {expected_count} p75 series, got {len(p75_series)}"
+
+    _assert_series_endpoint_labels(p75_series, expected_endpoints, "p75")
+
+    p75_values = {}
+    for series in p75_series:
+        endpoint = series.get("labels", [{}])[0].get("value", "unknown")
+        p75_values[endpoint] = sorted(
+            series.get("values", []), key=lambda x: x["timestamp"]
+        )
+
+    for endpoint, values in p75_values.items():
+        for v in values:
+            assert v["value"] >= 0, f"p75 for {endpoint} should not be negative: {v['value']}"
+
+    # /health (cumulative, service=api)
+    if "/health" in p75_values:
+        vals = p75_values["/health"]
+        assert vals[0]["value"] == 6000, f"Expected /health p75 first=6000, got {vals[0]['value']}"
+        assert vals[-1]["value"] == 6000, f"Expected /health p75 last=6000, got {vals[-1]['value']}"
+
+    # /orders (cumulative, service=api): same distribution as /health
+    if "/orders" in p75_values:
+        vals = p75_values["/orders"]
+        assert vals[0]["value"] == 4500, f"Expected /orders p75 first=4500, got {vals[0]['value']}"
+        assert vals[-1]["value"] == 4500, f"Expected /orders p75 last=4500, got {vals[-1]['value']}"
+
+    # /checkout (delta, service=web): 60 points
+    if "/checkout" in p75_values:
+        vals = p75_values["/checkout"]
+        assert vals[0]["value"] == 6000, f"Expected /checkout p75 zeroth=6000, got {vals[0]['value']}"
+        assert vals[1]["value"] == 6000, f"Expected /checkout p75 first=6000, got {vals[1]['value']}"
+        assert vals[-1]["value"] == 6000, f"Expected /checkout p75 last=6000, got {vals[-1]['value']}"
+
+    # /coupon (delta, service=web): 60 points
+    if "/coupon" in p75_values:
+        vals = p75_values["/coupon"]
+        assert vals[0]["value"] == 1125, f"Expected /coupon p75 zeroth=1125, got {vals[0]['value']}"
+        assert vals[1]["value"] == 1125, f"Expected /coupon p75 first=1125, got {vals[1]['value']}"
+        assert vals[-1]["value"] == 1125, f"Expected /coupon p75 last=1125, got {vals[-1]['value']}"
+
+
+@pytest.mark.parametrize(
+    "order_suffix,order_by,limit,expected_count,expected_endpoints, expected_status_codes",
+    [
+        (
+            "no_order",
+            None,
+            None,
+            5,
+            [ "/checkout", "/health", "/orders", "/coupon", "/coupon"], ## coupon has 200 and 500 status codes so it will appear twice
+            [ "200", "200", "200", "200", "500"],
+        ),
+        (
+            "only_limit",
+            None,
+            1,
+            1,
+            [ "/checkout"], ##health and checkout have the same size so they are then sorted endpoint as a tiebreaker, and only checkout makes the limit
+            [ "200"]
+        ),
+        (
+            "asc_endpoint",
+            [build_order_by("endpoint", "asc")],
+            None,
+            5,
+            [ "/checkout", "/coupon", "/coupon", "/health", "/orders"],
+            [ "200", "200", "500", "200", "200"],
+        ),
+        (
+            "asc_endpoint_status_code",
+            [build_order_by("endpoint", "asc"), build_order_by("status_code", "asc")],
+            None,
+            5,
+            [ "/checkout", "/coupon", "/coupon", "/health", "/orders"],
+            [ "200", "200", "500", "200", "200"],
+        ),
+        (
+            "asc_status_code_endpoint",
+            [build_order_by("status_code", "asc"), build_order_by("endpoint", "asc")],
+            None,
+            5,
+            [ "/checkout", "/coupon", "/health", "/orders", "/coupon"],
+            [ "200", "200", "200", "200", "500"],
+        ),
+        (
+            "asc_endpoint_limit_2",
+            [build_order_by("endpoint", "asc")],
+            2,
+            2,
+            [ "/checkout", "/coupon"],
+            [ "200", "200"],
+        ),
+        (
+            "asc_endpoint_status_code_limit_2",
+            [build_order_by("endpoint", "asc"), build_order_by("status_code", "asc")],
+            2,
+            2,
+            [ "/checkout", "/coupon"],
+            [ "200", "200"],
+        ),
+        (
+            "asc_status_code_endpoint_limit_4",
+            [build_order_by("status_code", "asc"), build_order_by("endpoint", "asc")],
+            4,
+            4,
+            [ "/checkout", "/coupon", "/health", "/orders"],
+            [ "200", "200", "200", "200"],
+        ),
+        (
+            "desc_endpoint",
+            [build_order_by("endpoint", "desc")],
+            None,
+            5,
+            ["/orders", "/health", "/coupon", "/coupon", "/checkout"],
+            [ "200", "200", "200", "500", "200"],
+        ),
+        (
+            "desc_endpoint_status_code",
+            [build_order_by("endpoint", "desc"), build_order_by("status_code", "desc")],
+            None,
+            5,
+            ["/orders", "/health", "/coupon", "/coupon", "/checkout"],
+            [ "200", "200", "500", "200", "200"],
+        ),
+        (
+            "desc_status_code_endpoint",
+            [build_order_by("status_code", "desc"), build_order_by("endpoint", "desc")],
+            None,
+            5,
+            ["/coupon", "/orders", "/health", "/coupon", "/checkout"],
+            [ "500", "200", "200", "200", "200"],
+        ),
+        (
+            "desc_endpoint_limit2",
+            [build_order_by("endpoint", "desc")],
+            3,
+            3,
+            ["/orders", "/health", "/coupon"],
+            [ "200", "200", "200"],
+        ),
+        (
+            "desc_endpoint_status_code_limit3",
+            [build_order_by("endpoint", "desc"), build_order_by("status_code", "desc")],
+            3,
+            3,
+            ["/orders", "/health", "/coupon"],
+            [ "200", "200", "500"],
+        ),
+        (
+            "desc_status_code_endpoint_limit2",
+            [build_order_by("status_code", "desc"), build_order_by("endpoint", "desc")],
+            2,
+            2,
+            ["/coupon", "/orders"],
+            [ "500", "200"],
+        ),
+    ],
+)
+def test_histogram_percentile_group_by_endpoint_and_status_code(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    insert_metrics: Callable[[List[Metrics]], None],
+    order_suffix: str,
+    order_by: Optional[List],
+    limit: Optional[int],
+    expected_count: int,
+    expected_endpoints: Union[set, List[str]],
+    expected_status_codes: Union[set, List[str]],
+) -> None:
+    now = datetime.now(tz=timezone.utc).replace(second=0, microsecond=0)
+    start_ms = int((now - timedelta(minutes=65)).timestamp() * 1000)
+    end_ms = int(now.timestamp() * 1000)
+    metric_name = f"test_histogram_p75_groupby_{order_suffix}"
+
+    metrics = Metrics.load_from_file(
+        FILE_WITH_MANY_GROUPS,
+        base_time=now - timedelta(minutes=60),
+        metric_name_override=metric_name,
+    )
+    insert_metrics(metrics)
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    query_p75 = build_builder_query(
+        "A",
+        metric_name,
+        "doesnotreallymatter",
+        "p75",
+        group_by=["endpoint", "status_code"],
+        order_by=order_by,
+        limit=limit,
+    )
+
+    response = make_query_request(signoz, token, start_ms, end_ms, [query_p75])
+    assert response.status_code == HTTPStatus.OK
+
+    data = response.json()
+    p75_series = get_all_series(data, "A")
+
+    for series in p75_series:
+        endpoint = series.get("labels", [{}])[0].get("value", "unknown")
+        status_code = series.get("labels", [{}])[1].get("value", "unknown")
+
+    assert (
+        len(p75_series) == expected_count
+    ), f"Expected {expected_count} p75 series, got {len(p75_series)}"
+
+    _assert_series_endpoint_labels(p75_series, expected_endpoints, "p75")
+    
+    endpoints = [s.get("labels", [{}])[0].get("value", "unknown") for s in p75_series]
+    assert endpoints == expected_endpoints, (
+        f"Expected p75 endpoints in order {expected_endpoints}, got {endpoints}"
+    )
+    status_codes = [s.get("labels", [{}])[1].get("value", "unknown") for s in p75_series]
+    assert status_codes == expected_status_codes, (
+        f"Expected p75 endpoints in order {expected_status_codes}, got {status_codes}"
+    )
+
+    p75_values = {}
+    for series in p75_series:
+        endpoint = series.get("labels", [{}])[0].get("value", "unknown")
+        status_code = series.get("labels", [{}])[1].get("value", "unknown")
+        p75_values[endpoint+status_code] = sorted(
+            series.get("values", []), key=lambda x: x["timestamp"]
+        )
+
+    for endpoint, values in p75_values.items():
+        for v in values:
+            assert v["value"] >= 0, f"p75 for {endpoint} should not be negative: {v['value']}"
+
+    # /health (cumulative, service=api)
+    if "/health200" in p75_values:
+        vals = p75_values["/health200"]
+        assert vals[0]["value"] == 6000, f"Expected /health p75 first=6000, got {vals[0]['value']}"
+        assert vals[-1]["value"] == 6000, f"Expected /health p75 last=6000, got {vals[-1]['value']}"
+
+    # /orders (cumulative, service=api): same distribution as /health
+    if "/orders200" in p75_values:
+        vals = p75_values["/orders200"]
+        assert vals[0]["value"] == 4500, f"Expected /orders p75 first=4500, got {vals[0]['value']}"
+        assert vals[-1]["value"] == 4500, f"Expected /orders p75 last=4500, got {vals[-1]['value']}"
+
+    # /checkout (delta, service=web): 60 points
+    if "/checkout200" in p75_values:
+        vals = p75_values["/checkout200"]
+        assert vals[0]["value"] == 6000, f"Expected /checkout p75 zeroth=6000, got {vals[0]['value']}"
+        assert vals[1]["value"] == 6000, f"Expected /checkout p75 first=6000, got {vals[1]['value']}"
+        assert vals[-1]["value"] == 6000, f"Expected /checkout p75 last=6000, got {vals[-1]['value']}"
+
+    # /coupon (delta, service=web): 60 points
+    if "/coupon200" in p75_values:
+        vals = p75_values["/coupon200"]
+        assert vals[0]["value"] == 1250, f"Expected /coupon200 p75 zeroth=1250, got {vals[0]['value']}"
+        assert vals[1]["value"] == 1250, f"Expected /coupon200 p75 first=1250, got {vals[1]['value']}"
+        assert vals[-1]["value"] == 1250, f"Expected /coupon200 p75 last=1250, got {vals[-1]['value']}"
+
+    if "/coupon500" in p75_values:
+        vals = p75_values["/coupon500"]
+        assert vals[0]["value"] == 750, f"Expected /coupon500 p75 zeroth=750, got {vals[0]['value']}"
+        assert vals[1]["value"] == 750, f"Expected /coupon500 p75 first=750, got {vals[1]['value']}"
+        assert vals[-1]["value"] == 750, f"Expected /coupon500 p75 last=750, got {vals[-1]['value']}"

tests/integration/src/querier/09_metrics_gauge.py

@@ -1,6 +1,6 @@
 from datetime import datetime, timedelta, timezone
 from http import HTTPStatus
-from typing import Callable, List
+from typing import Callable, List, Optional, Union
 
 import pytest
 
@@ -9,6 +9,8 @@ from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.metrics import Metrics
 from fixtures.querier import (
     build_builder_query,
+    build_order_by,
+    get_all_series,
     get_series_values,
     make_query_request,
 )
@@ -139,3 +141,137 @@ def test_for_multiple_aggregations(
     assert result_values[19]["value"] == twentieth_min_val
     assert result_values[20]["value"] == twenty_first_min_val
     assert result_values[30]["value"] == thirty_first_min_val
+
+
+@pytest.mark.parametrize(
+    "metric_suffix,order_by,limit,expected_count,expected_services",
+    [
+        (
+            "no_order",
+            None,  # default ordering: desc by avg of all metric values for a group
+            None,
+            3,
+            ["lab", "web", "api"],  # sum of all values: lab=42000, api=36000, web=34000. avg of all sums: lab=700, api=600, web=680
+        ),
+        (
+            "only_limit",
+            None,
+            2,
+            2,
+            ["lab", "web"],  # top 2 by default desc: lab=42000, api=36000
+        ),
+        (
+            "asc",
+            [build_order_by("service", "asc")],
+            None,
+            3,
+            ["api", "lab", "web"],
+        ),
+        (
+            "asc_lim2",
+            [build_order_by("service", "asc")],
+            2,
+            2,
+            ["api", "lab"],
+        ),
+        (
+            "desc",
+            [build_order_by("service", "desc")],
+            None,
+            3,
+            ["web", "lab", "api"],
+        ),
+        (
+            "desc_lim2",
+            [build_order_by("service", "desc")],
+            2,
+            2,
+            ["web", "lab"],
+        ),
+        (
+            "asc_metric_name",
+            [build_order_by("sum(test_gauge_groupby_asc_metric_name)", "asc")],
+            None,
+            3,
+            ["api", "web", "lab"],
+        ),
+        (
+            "asc_metric_name_lim2",
+            [build_order_by("sum(test_gauge_groupby_asc_metric_name_lim2)", "asc")],
+            2,
+            2,
+            ["api", "web"],
+        ),
+        (
+            "desc_metric_name",
+            [build_order_by("sum(test_gauge_groupby_desc_metric_name)", "desc")],
+            None,
+            3,
+            ["lab", "web", "api"], 
+        ),
+        (
+            "desc_metric_name_lim2",
+            [build_order_by("sum(test_gauge_groupby_desc_metric_name_lim2)", "desc")],
+            2,
+            2,
+            ["lab", "web"],
+        ),
+    ],
+)
+def test_gauge_group_by_service(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    insert_metrics: Callable[[List[Metrics]], None],
+    metric_suffix: str,
+    order_by: Optional[List],
+    limit: Optional[int],
+    expected_count: int,
+    expected_services: Union[set, List[str]],
+) -> None:
+    now = datetime.now(tz=timezone.utc).replace(second=0, microsecond=0)
+    start_ms = int((now - timedelta(minutes=65)).timestamp() * 1000)
+    end_ms = int(now.timestamp() * 1000)
+    metric_name = f"test_gauge_groupby_{metric_suffix}"
+
+    metrics = Metrics.load_from_file(
+        FILE,
+        base_time=now - timedelta(minutes=60),
+        metric_name_override=metric_name,
+    )
+    insert_metrics(metrics)
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    query = build_builder_query(
+        "A",
+        metric_name,
+        "max",
+        "sum",
+        group_by=["service"],
+        order_by=order_by,
+        limit=limit,
+    )
+
+    response = make_query_request(signoz, token, start_ms, end_ms, [query])
+    assert response.status_code == HTTPStatus.OK
+
+    data = response.json()
+    all_series = get_all_series(data, "A")
+
+    assert (
+        len(all_series) == expected_count
+    ), f"Expected {expected_count} series, got {len(all_series)}"
+
+    service_labels = [
+        series.get("labels", [{}])[0].get("value", "unknown")
+        for series in all_series
+    ]
+
+    if isinstance(expected_services, set):
+        assert (
+            set(service_labels) == expected_services
+        ), f"Expected services {expected_services}, got {set(service_labels)}"
+    else:
+        assert service_labels == expected_services, (
+            f"Expected services {expected_services}, got {service_labels}"
+        )

tests/integration/src/querier/10_metrics_rate_delta_counter.py

@@ -5,13 +5,16 @@ Look at the delta_counters_1h.jsonl file for the relevant data
 import os
 from datetime import datetime, timedelta, timezone
 from http import HTTPStatus
-from typing import Any, Callable, List
+from typing import Any, Callable, List, Optional, Union
+
+import pytest
 
 from fixtures import types
 from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.metrics import Metrics
 from fixtures.querier import (
     build_builder_query,
+    build_order_by,
     get_all_series,
     get_series_values,
     make_query_request,
@@ -69,16 +72,61 @@ def test_rate_with_steady_values_and_reset(
         assert v["value"] >= 0, f"Rate should not be negative: {v['value']}"
 
 
+@pytest.mark.parametrize(
+    "order_suffix,order_by,limit,expected_count,expected_endpoints",
+    [
+        (
+            "no_order",
+            None,
+            None,
+            5,
+            {"/products", "/health", "/checkout", "/orders", "/users"},
+        ),
+        (
+            "asc",
+            [build_order_by("endpoint", "asc")],
+            None,
+            5,
+            ["/checkout", "/health", "/orders", "/products", "/users"],
+        ),
+        (
+            "asc_lim3",
+            [build_order_by("endpoint", "asc")],
+            3,
+            3,
+            ["/checkout", "/health", "/orders"],
+        ),
+        (
+            "desc",
+            [build_order_by("endpoint", "desc")],
+            None,
+            5,
+            ["/users", "/products", "/orders", "/health", "/checkout"],
+        ),
+        (
+            "desc_lim3",
+            [build_order_by("endpoint", "desc")],
+            3,
+            3,
+            ["/users", "/products", "/orders"],
+        ),
+    ],
+)
 def test_rate_group_by_endpoint(
     signoz: types.SigNoz,
     create_user_admin: None,  # pylint: disable=unused-argument
     get_token: Callable[[str, str], str],
     insert_metrics: Callable[[List[Metrics]], None],
+    order_suffix: str,
+    order_by: Optional[List],
+    limit: Optional[int],
+    expected_count: int,
+    expected_endpoints: Union[set, List[str]],
 ) -> None:
     now = datetime.now(tz=timezone.utc).replace(second=0, microsecond=0)
     start_ms = int((now - timedelta(minutes=65)).timestamp() * 1000)
     end_ms = int(now.timestamp() * 1000)
-    metric_name = "test_rate_groupby"
+    metric_name = f"test_rate_groupby_{order_suffix}"
 
     metrics = Metrics.load_from_file(
         DELTA_COUNTERS_FILE,
@@ -94,6 +142,8 @@ def test_rate_group_by_endpoint(
         "rate",
         "sum",
         group_by=["endpoint"],
+        order_by=order_by,
+        limit=limit,
     )
 
     response = make_query_request(signoz, token, start_ms, end_ms, [query])
@@ -102,10 +152,23 @@ def test_rate_group_by_endpoint(
     data = response.json()
     all_series = get_all_series(data, "A")
 
-    # Should have 5 different endpoints
     assert (
-        len(all_series) == 5
-    ), f"Expected 5 series for 5 endpoints, got {len(all_series)}"
+        len(all_series) == expected_count
+    ), f"Expected {expected_count} series, got {len(all_series)}"
+
+    endpoint_labels = [
+        series.get("labels", [{}])[0].get("value", "unknown")
+        for series in all_series
+    ]
+
+    if isinstance(expected_endpoints, set):
+        assert (
+            set(endpoint_labels) == expected_endpoints
+        ), f"Expected endpoints {expected_endpoints}, got {set(endpoint_labels)}"
+    else:
+        assert endpoint_labels == expected_endpoints, (
+            f"Expected endpoints {expected_endpoints}, got {endpoint_labels}"
+        )
 
     # endpoint -> values
     endpoint_values = {}
@@ -114,11 +177,6 @@ def test_rate_group_by_endpoint(
         values = sorted(series.get("values", []), key=lambda x: x["timestamp"])
         endpoint_values[endpoint] = values
 
-    expected_endpoints = {"/products", "/health", "/checkout", "/orders", "/users"}
-    assert (
-        set(endpoint_values.keys()) == expected_endpoints
-    ), f"Expected endpoints {expected_endpoints}, got {set(endpoint_values.keys())}"
-
     # at no point rate should be negative
     for endpoint, values in endpoint_values.items():
         for v in values:
@@ -128,93 +186,95 @@ def test_rate_group_by_endpoint(
 
     # /health: 60 data points (t01-t60), steady +10/min
     # rate = 10/60 = 0.167
-    health_values = endpoint_values["/health"]
-    assert (
-        len(health_values) == 60
-    ), f"Expected 60 values for /health, got {len(health_values)}"
-    count_steady_health = sum(1 for v in health_values if v["value"] == 0.167)
-    assert (
-        count_steady_health == 60
-    ), f"Expected == 60 steady rate values (0.167) for /health, got {count_steady_health}"
-    # all /health rates should be 0.167 except possibly first/last due to boundaries
-    for v in health_values[1:-1]:
-        assert v["value"] == 0.167, f"Expected /health rate 0.167, got {v['value']}"
+    if "/health" in endpoint_values:
+        health_values = endpoint_values["/health"]
+        assert (
+            len(health_values) == 60
+        ), f"Expected 60 values for /health, got {len(health_values)}"
+        count_steady_health = sum(1 for v in health_values if v["value"] == 0.167)
+        assert (
+            count_steady_health == 60
+        ), f"Expected == 60 steady rate values (0.167) for /health, got {count_steady_health}"
+        # all /health rates should be 0.167 except possibly first/last due to boundaries
+        for v in health_values[1:-1]:
+            assert v["value"] == 0.167, f"Expected /health rate 0.167, got {v['value']}"
 
     # /products: 51 data points with 10-minute gap (t20-t29 missing), steady +20/min
     # rate = 20/60 = 0.333, gap causes lower averaged rate at boundary
-    products_values = endpoint_values["/products"]
-    assert (
-        len(products_values) == 51
-    ), f"Expected 51 values for /products, got {len(products_values)}"
-    count_steady_products = sum(1 for v in products_values if v["value"] == 0.333)
-
-    assert (
-        count_steady_products == 51
-    ), f"Expected 51 steady rate values (0.333) for /products, got {count_steady_products}"
+    if "/products" in endpoint_values:
+        products_values = endpoint_values["/products"]
+        assert (
+            len(products_values) == 51
+        ), f"Expected 51 values for /products, got {len(products_values)}"
+        count_steady_products = sum(1 for v in products_values if v["value"] == 0.333)
+        assert (
+            count_steady_products == 51
+        ), f"Expected 51 steady rate values (0.333) for /products, got {count_steady_products}"
 
     # /checkout: 61 data points (t00-t60), +1/min normal, +50/min spike at t40-t44
     # normal rate = 1/60 = 0.0167, spike rate = 50/60 = 0.833
-    checkout_values = endpoint_values["/checkout"]
-    assert (
-        len(checkout_values) == 61
-    ), f"Expected 61 values for /checkout, got {len(checkout_values)}"
-    count_steady_checkout = sum(1 for v in checkout_values if v["value"] == 0.0167)
-    assert (
-        count_steady_checkout == 56
-    ), f"Expected 56 steady rate values (0.0167) for /checkout, got {count_steady_checkout}"
-    # check that spike values exist (traffic spike +50/min at t40-t44)
-    count_spike_checkout = sum(1 for v in checkout_values if v["value"] == 0.833)
-    assert (
-        count_spike_checkout == 5
-    ), f"Expected 5 spike rate values (0.833) for /checkout, got {count_spike_checkout}"
-
-    # spike values should be consecutive
-    spike_indices = [
-        i for i, v in enumerate[Any](checkout_values) if v["value"] == 0.833
-    ]
-    assert len(spike_indices) == 5, f"Expected 5 spike indices, got {spike_indices}"
-    # consecutiveness
-    for i in range(1, len(spike_indices)):
+    if "/checkout" in endpoint_values:
+        checkout_values = endpoint_values["/checkout"]
         assert (
-            spike_indices[i] == spike_indices[i - 1] + 1
-        ), f"Spike indices should be consecutive, got {spike_indices}"
+            len(checkout_values) == 61
+        ), f"Expected 61 values for /checkout, got {len(checkout_values)}"
+        count_steady_checkout = sum(1 for v in checkout_values if v["value"] == 0.0167)
+        assert (
+            count_steady_checkout == 56
+        ), f"Expected 56 steady rate values (0.0167) for /checkout, got {count_steady_checkout}"
+        # check that spike values exist (traffic spike +50/min at t40-t44)
+        count_spike_checkout = sum(1 for v in checkout_values if v["value"] == 0.833)
+        assert (
+            count_spike_checkout == 5
+        ), f"Expected 5 spike rate values (0.833) for /checkout, got {count_spike_checkout}"
+        # spike values should be consecutive
+        spike_indices = [
+            i for i, v in enumerate[Any](checkout_values) if v["value"] == 0.833
+        ]
+        assert len(spike_indices) == 5, f"Expected 5 spike indices, got {spike_indices}"
+        for i in range(1, len(spike_indices)):
+            assert (
+                spike_indices[i] == spike_indices[i - 1] + 1
+            ), f"Spike indices should be consecutive, got {spike_indices}"
 
     # /orders: 60 data points (t00-t60) with gap at t30, counter reset at t31 (150->2)
     # rate = 5/60 = 0.0833
     # reset at t31 causes: rate at t30 includes gap (lower), t31 has high rate after reset
-    orders_values = endpoint_values["/orders"]
-    assert (
-        len(orders_values) == 60
-    ), f"Expected 59 values for /orders, got {len(orders_values)}"
-    count_steady_orders = sum(1 for v in orders_values if v["value"] == 0.0833)
-    assert (
-        count_steady_orders == 58
-    ), f"Expected 58 steady rate values (0.0833) for /orders, got {count_steady_orders}"
-    # check for counter reset effects - there should be some non-standard values
-    non_standard_orders = [v["value"] for v in orders_values if v["value"] != 0.0833]
-    assert (
-        len(non_standard_orders) == 2
-    ), f"Expected 2 non-standard values due to counter reset, got {non_standard_orders}"
-    # post-reset value should be higher (new counter value / interval)
-    high_rate_orders = [v for v in non_standard_orders if v > 0.0833]
-    assert (
-        len(high_rate_orders) == 1
-    ), f"Expected one high rate value after counter reset, got {non_standard_orders}"
+    if "/orders" in endpoint_values:
+        orders_values = endpoint_values["/orders"]
+        assert (
+            len(orders_values) == 60
+        ), f"Expected 60 values for /orders, got {len(orders_values)}"
+        count_steady_orders = sum(1 for v in orders_values if v["value"] == 0.0833)
+        assert (
+            count_steady_orders == 58
+        ), f"Expected 58 steady rate values (0.0833) for /orders, got {count_steady_orders}"
+        # check for counter reset effects - there should be some non-standard values
+        non_standard_orders = [v["value"] for v in orders_values if v["value"] != 0.0833]
+        assert (
+            len(non_standard_orders) == 2
+        ), f"Expected 2 non-standard values due to counter reset, got {non_standard_orders}"
+        # post-reset value should be higher (new counter value / interval)
+        high_rate_orders = [v for v in non_standard_orders if v > 0.0833]
+        assert (
+            len(high_rate_orders) == 1
+        ), f"Expected one high rate value after counter reset, got {non_standard_orders}"
 
     # /users: 56 data points (t05-t60), sparse +1 every 5 minutes (12 of them)
     # Rate = 1/60 = 0.0167 during increment, 0 during flat periods
-    users_values = endpoint_values["/users"]
-    assert (
-        len(users_values) == 56
-    ), f"Expected 56 values for /users, got {len(users_values)}"
-    count_zero_users = sum(1 for v in users_values if v["value"] == 0)
-    # most values should be 0 (flat periods between increments)
-    assert (
-        count_zero_users == 44
-    ), f"Expected 44 zero rate values for /users (sparse data), got {count_zero_users}"
-    # non-zero values should be 0.0167 (1/60 increment rate)
-    non_zero_users = [v["value"] for v in users_values if v["value"] != 0]
-    count_increment_rate = sum(1 for v in non_zero_users if v == 0.0167)
-    assert (
-        count_increment_rate == 12
-    ), f"Expected 12 increment rate values (0.0167) for /users, got {count_increment_rate}"
+    if "/users" in endpoint_values:
+        users_values = endpoint_values["/users"]
+        assert (
+            len(users_values) == 56
+        ), f"Expected 56 values for /users, got {len(users_values)}"
+        count_zero_users = sum(1 for v in users_values if v["value"] == 0)
+        # most values should be 0 (flat periods between increments)
+        assert (
+            count_zero_users == 44
+        ), f"Expected 44 zero rate values for /users (sparse data), got {count_zero_users}"
+        # non-zero values should be 0.0167 (1/60 increment rate)
+        non_zero_users = [v["value"] for v in users_values if v["value"] != 0]
+        count_increment_rate = sum(1 for v in non_zero_users if v == 0.0167)
+        assert (
+            count_increment_rate == 12
+        ), f"Expected 12 increment rate values (0.0167) for /users, got {count_increment_rate}"