Merge remote-tracking branch 'origin/main' into ns/scope

Otherwise it will be impossible to query if scope attribute also
exists with same name - name and version

.gitignore

@@ -231,4 +231,5 @@ cython_debug/
 # LSP config files
 pyrightconfig.json
 
-
+# agents
+.claude/settings.local.json

pkg/querybuilder/query_to_keys.go

@@ -56,6 +56,17 @@ func QueryStringToKeysSelectors(query string) []*telemetrytypes.FieldKeySelector
 					FieldDataType: key.FieldDataType,
 				})
 			}
+
+			// todo(tushar): consider reverting changes done to this method in below PR to avoid scope specific checks
+			// https://github.com/SigNoz/signoz/issues/11374
+			if key.FieldContext == telemetrytypes.FieldContextScope {
+				keys = append(keys, &telemetrytypes.FieldKeySelector{
+					Name:          key.FieldContext.StringValue() + "." + key.Name,
+					Signal:        key.Signal,
+					FieldContext:  telemetrytypes.FieldContextUnspecified, // this allows 'scope.' prefix for keys with other context as well
+					FieldDataType: key.FieldDataType,
+				})
+			}
 		}
 	}
 

pkg/querybuilder/query_to_keys_test.go

@@ -72,6 +72,23 @@ func TestQueryToKeys(t *testing.T) {
 				},
 			},
 		},
+		{
+			query: `scope.version = '1.0.0'`,
+			expectedKeys: []telemetrytypes.FieldKeySelector{
+				{
+					Name:          "version",
+					Signal:        telemetrytypes.SignalUnspecified,
+					FieldContext:  telemetrytypes.FieldContextScope,
+					FieldDataType: telemetrytypes.FieldDataTypeUnspecified,
+				},
+				{
+					Name:          "scope.version",
+					Signal:        telemetrytypes.SignalUnspecified,
+					FieldContext:  telemetrytypes.FieldContextUnspecified,
+					FieldDataType: telemetrytypes.FieldDataTypeUnspecified,
+				},
+			},
+		},
 	}
 
 	for _, testCase := range testCases {

pkg/telemetrymetadata/metadata.go

@@ -200,7 +200,7 @@ func (t *telemetryMetaStore) getTracesKeys(ctx context.Context, fieldKeySelector
 		`CASE
 			// WHEN tagType = 'spanfield' THEN 1
 			WHEN tagType = 'resource' THEN 2
-			// WHEN tagType = 'scope' THEN 3
+			WHEN tagType = 'scope' THEN 3
 			WHEN tagType = 'tag' THEN 4
 			ELSE 5
 		END as priority`,

pkg/telemetrytraces/field_mapper.go

@@ -51,6 +51,7 @@ var (
 			ValueType: schema.ColumnTypeString,
 		}},
 		"resource": {Name: "resource", Type: schema.JSONColumnType{}},
+		"scope":    {Name: "scope", Type: schema.JSONColumnType{}},
 
 		"events": {Name: "events", Type: schema.ArrayColumnType{
 			ElementType: schema.ColumnTypeString,
@@ -176,7 +177,7 @@ func (m *defaultFieldMapper) getColumn(
 	case telemetrytypes.FieldContextResource:
 		return []*schema.Column{indexV3Columns["resources_string"], indexV3Columns["resource"]}, nil
 	case telemetrytypes.FieldContextScope:
-		return []*schema.Column{}, qbtypes.ErrColumnNotFound
+		return []*schema.Column{indexV3Columns["scope"]}, nil
 	case telemetrytypes.FieldContextAttribute:
 		switch key.FieldDataType {
 		case telemetrytypes.FieldDataTypeString:
@@ -278,14 +279,24 @@ func (m *defaultFieldMapper) FieldFor(
 
 		switch column.Type.GetType() {
 		case schema.ColumnTypeEnumJSON:
-			// json is only supported for resource context as of now
-			if key.FieldContext != telemetrytypes.FieldContextResource {
-				return "", errors.Newf(errors.TypeInvalidInput, errors.CodeInvalidInput, "only resource context fields are supported for json columns, got %s", key.FieldContext.String)
-			}
 			// have to add ::string as clickHouse throws an error :- data types Variant/Dynamic are not allowed in GROUP BY
 			// once clickHouse dependency is updated, we need to check if we can remove it.
-			exprs = append(exprs, fmt.Sprintf("%s.`%s`::String", columnName, key.Name))
-			existExpr = append(existExpr, fmt.Sprintf("%s.`%s` IS NOT NULL", columnName, key.Name))
+			switch key.FieldContext {
+			case telemetrytypes.FieldContextResource:
+				exprs = append(exprs, fmt.Sprintf("%s.`%s`::String", columnName, key.Name))
+				existExpr = append(existExpr, fmt.Sprintf("%s.`%s` IS NOT NULL", columnName, key.Name))
+			case telemetrytypes.FieldContextScope:
+				switch key.Name {
+				case "scope.name", "scope.version":
+					exprs = append(exprs, fmt.Sprintf("%s::String", key.Name))
+					existExpr = append(existExpr, fmt.Sprintf("%s IS NOT NULL", key.Name))
+				default:
+					exprs = append(exprs, fmt.Sprintf("%s.attributes.`%s`::String", columnName, key.Name))
+					existExpr = append(existExpr, fmt.Sprintf("%s.attributes.`%s` IS NOT NULL", columnName, key.Name))
+				}
+			default:
+				return "", errors.Newf(errors.TypeInvalidInput, errors.CodeInvalidInput, "only resource and scope context fields are supported for json columns, got %s", key.FieldContext.String)
+			}
 		case schema.ColumnTypeEnumString,
 			schema.ColumnTypeEnumUInt64,
 			schema.ColumnTypeEnumUInt32,

pkg/telemetrytraces/field_mapper_test.go

@@ -82,6 +82,33 @@ func TestGetFieldKeyName(t *testing.T) {
 			expectedResult: "multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, `resource_string_deployment$$environment_exists`==true, `resource_string_deployment$$environment`, NULL)",
 			expectedError:  nil,
 		},
+		{
+			name: "Scope field - scope.name",
+			key: telemetrytypes.TelemetryFieldKey{
+				Name:         "scope.name",
+				FieldContext: telemetrytypes.FieldContextScope,
+			},
+			expectedResult: "scope.name::String",
+			expectedError:  nil,
+		},
+		{
+			name: "Scope field - scope.version",
+			key: telemetrytypes.TelemetryFieldKey{
+				Name:         "scope.version",
+				FieldContext: telemetrytypes.FieldContextScope,
+			},
+			expectedResult: "scope.version::String",
+			expectedError:  nil,
+		},
+		{
+			name: "Scope field - custom attribute",
+			key: telemetrytypes.TelemetryFieldKey{
+				Name:         "custom.attr",
+				FieldContext: telemetrytypes.FieldContextScope,
+			},
+			expectedResult: "scope.attributes.`custom.attr`::String",
+			expectedError:  nil,
+		},
 		{
 			// Query like `attribute.attribute_string:string` should resolve to `attributes_string['attribute_string']`.
 			name: "Attribute key whose name collides with contextual map column resolves as a map lookup",

pkg/telemetrytraces/stmt_builder_test.go

@@ -370,6 +370,94 @@ func TestStatementBuilder(t *testing.T) {
 			},
 			expectedErr: nil,
 		},
+		{
+			name:        "scope.name filter and group by",
+			requestType: qbtypes.RequestTypeTimeSeries,
+			query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
+				Signal:       telemetrytypes.SignalTraces,
+				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
+				Aggregations: []qbtypes.TraceAggregation{
+					{
+						Expression: "count()",
+					},
+				},
+				Filter: &qbtypes.Filter{
+					Expression: "scope.name = 'opentelemetry-io'",
+				},
+				Limit: 10,
+				GroupBy: []qbtypes.GroupByKey{
+					{
+						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
+							Name:         "scope.name",
+							FieldContext: telemetrytypes.FieldContextScope,
+						},
+					},
+				},
+			},
+			expected: qbtypes.Statement{
+				Query: "WITH __limit_cte AS (SELECT toString(multiIf(scope.name::String IS NOT NULL, scope.name::String, NULL)) AS `scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.name::String = ? AND scope.name::String IS NOT NULL) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `scope.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(scope.name::String IS NOT NULL, scope.name::String, NULL)) AS `scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.name::String = ? AND scope.name::String IS NOT NULL) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`scope.name`) GLOBAL IN (SELECT `scope.name` FROM __limit_cte) GROUP BY ts, `scope.name`",
+				Args:  []any{"opentelemetry-io", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "opentelemetry-io", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
+			},
+			expectedErr: nil,
+		},
+		{
+			name:        "scope.version filter with scope.name group by",
+			requestType: qbtypes.RequestTypeTimeSeries,
+			query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
+				Signal:       telemetrytypes.SignalTraces,
+				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
+				Aggregations: []qbtypes.TraceAggregation{
+					{
+						Expression: "count()",
+					},
+				},
+				Filter: &qbtypes.Filter{
+					Expression: "scope.version = '1.0.0'",
+				},
+				Limit: 10,
+				GroupBy: []qbtypes.GroupByKey{
+					{
+						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
+							Name:         "scope.name",
+							FieldContext: telemetrytypes.FieldContextScope,
+						},
+					},
+				},
+			},
+			expected: qbtypes.Statement{
+				Query: "WITH __limit_cte AS (SELECT toString(multiIf(scope.name::String IS NOT NULL, scope.name::String, NULL)) AS `scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String IS NOT NULL) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `scope.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(scope.name::String IS NOT NULL, scope.name::String, NULL)) AS `scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String IS NOT NULL) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`scope.name`) GLOBAL IN (SELECT `scope.name` FROM __limit_cte) GROUP BY ts, `scope.name`",
+				Args:  []any{"1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
+			},
+			expectedErr: nil,
+		},
+		{
+			name:        "scope.version filter only (no scope field in group by)",
+			requestType: qbtypes.RequestTypeTimeSeries,
+			query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
+				Signal:       telemetrytypes.SignalTraces,
+				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
+				Aggregations: []qbtypes.TraceAggregation{
+					{
+						Expression: "count()",
+					},
+				},
+				Filter: &qbtypes.Filter{
+					Expression: "scope.version = '1.0.0'",
+				},
+				Limit: 10,
+				GroupBy: []qbtypes.GroupByKey{
+					{
+						TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
+							Name: "service.name",
+						},
+					},
+				},
+			},
+			expected: qbtypes.Statement{
+				Query: "WITH __limit_cte AS (SELECT toString(multiIf(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL, multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL), NULL)) AS `service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String IS NOT NULL) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `service.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL) IS NOT NULL, multiIf(resource.`service.name` IS NOT NULL, resource.`service.name`::String, mapContains(resources_string, 'service.name'), resources_string['service.name'], NULL), NULL)) AS `service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String IS NOT NULL) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`service.name`) GLOBAL IN (SELECT `service.name` FROM __limit_cte) GROUP BY ts, `service.name`",
+				Args:  []any{"1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
+			},
+		},
 	}
 
 	fm := NewFieldMapper()
@@ -793,6 +881,32 @@ func TestStatementBuilderListQueryWithCorruptData(t *testing.T) {
 			},
 			expectedErr: nil,
 		},
+		{
+			name:        "List query with scope filter only (no scope in select or group by)",
+			requestType: qbtypes.RequestTypeRaw,
+			keysMap: map[string][]*telemetrytypes.TelemetryFieldKey{
+				"scope.version": {
+					{
+						Name:          "scope.version",
+						Signal:        telemetrytypes.SignalTraces,
+						FieldContext:  telemetrytypes.FieldContextScope,
+						FieldDataType: telemetrytypes.FieldDataTypeString,
+					},
+				},
+			},
+			query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
+				Signal:       telemetrytypes.SignalTraces,
+				StepInterval: qbtypes.Step{Duration: 30 * time.Second},
+				Filter: &qbtypes.Filter{
+					Expression: "scope.version = '1.0.0'",
+				},
+				Limit: 10,
+			},
+			expected: qbtypes.Statement{
+				Query: "SELECT timestamp AS `timestamp`, trace_id AS `trace_id`, span_id AS `span_id`, trace_state AS `trace_state`, parent_span_id AS `parent_span_id`, flags AS `flags`, name AS `name`, kind AS `kind`, kind_string AS `kind_string`, duration_nano AS `duration_nano`, status_code AS `status_code`, status_message AS `status_message`, status_code_string AS `status_code_string`, events AS `events`, links AS `links`, response_status_code AS `response_status_code`, external_http_url AS `external_http_url`, http_url AS `http_url`, external_http_method AS `external_http_method`, http_method AS `http_method`, http_host AS `http_host`, db_name AS `db_name`, db_operation AS `db_operation`, has_error AS `has_error`, is_remote AS `is_remote`, attributes_string, attributes_number, attributes_bool, resources_string FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String IS NOT NULL) AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
+				Args:  []any{"1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
+			},
+		},
 	}
 
 	for _, c := range cases {

pkg/telemetrytraces/test_data.go

@@ -113,6 +113,20 @@ func buildCompleteFieldKeyMap(releaseTime time.Time) map[string][]*telemetrytype
 				FieldDataType: telemetrytypes.FieldDataTypeBool,
 			},
 		},
+		"scope.name": {
+			{
+				Name:          "scope.name",
+				FieldContext:  telemetrytypes.FieldContextScope,
+				FieldDataType: telemetrytypes.FieldDataTypeString,
+			},
+		},
+		"scope.version": {
+			{
+				Name:          "scope.version",
+				FieldContext:  telemetrytypes.FieldContextScope,
+				FieldDataType: telemetrytypes.FieldDataTypeString,
+			},
+		},
 	}
 	for _, keys := range keysMap {
 		for _, key := range keys {