Compare commits

...

4 Commits

Author SHA1 Message Date
nityanandagohain
d90f025875 fix: support for related values in ai field values 2026-08-28 13:21:40 +05:30
Vikrant Gupta
1b8155fea9 chore(featureflag): make features endpoint open access (#12704)
#### Description

- Changes `GET /api/v1/features` from `ViewAccess` to `OpenAccess` in
both editions so every authenticated user, including those on custom
roles, can read feature flags.
- Feature flags describe the org's plan, not the caller's privileges,
and the frontend needs them to boot. With #12700 making the active
license readable by every authenticated user, the flags must be readable
too — otherwise custom-role users load the license but hang on the flags
fetch.
- Applies the same change to the flagger endpoint `GET /api/v2/features`
so the v2 client behaves identically when the frontend migrates to it.

#### Issues closed by this PR

Closes: https://github.com/SigNoz/platform-pod/issues/2653
2026-08-27 09:58:46 +00:00
Nikhil Soni
dac406eb93 feat: add support for quering scope fields in traces (#10920)
### 📄 Summary


Add support for instrumentation scope for traces. PR on collector -
https://github.com/SigNoz/signoz-otel-collector/pull/811


#### Screenshots / Screen Recordings (if applicable)

<img width="468" height="298" alt="image"
src="https://github.com/user-attachments/assets/03335ca3-a1c5-428b-9bfa-cd1796f735df"
/>

#### Issues closed by this PR

https://github.com/SigNoz/signoz/issues/5319
2026-08-27 09:55:43 +00:00
Gaurav Tewari
f69bce998a feat: add useBarChart instead of graph (#12517)
#### Description

- The logs frequency chart now draws with the uPlotV2 `BarChart` instead
of the Chart.js `Graph`, putting it on the same chart stack as the rest
of the product. Covers both Logs Explorer and Live Logs, which share the
component.
- Chart setup moves into a `useLogsExplorerChartConfig` hook built on
the shared `buildBaseConfig`. Severity colours, labels, drag-to-zoom and
timezone handling all behave as before; stacking goes through
`stack`/`StackMode`.
- Timestamps now convert ns → s, since uPlot's x scale is in seconds
where Chart.js wanted ms.
- Removes the `.ant-card-body` rules from three stylesheets. They
stopped matching anything when #8904 dropped the antd Card wrapper.
- Unblocked by #12627, which removed the last-minute trim from the time
scale. My earlier attempt at that (#12528) is closed.

#### Issues closed by this PR

Closes -
https://github.com/orgs/SigNoz/projects/39/views/20?pane=issue&itemId=128310734&issue=SigNoz%7Csignoz%7C9059

#### Screenshots / Screen Recordings



https://github.com/user-attachments/assets/b27f75ae-085d-410b-a5b8-491bac590fd0


#### Additional Information

---------

Co-authored-by: Gaurav Tewari <tewarig@users.noreply.github.com>
2026-08-27 07:09:12 +00:00
34 changed files with 1296 additions and 174 deletions

View File

@@ -8801,6 +8801,7 @@ components:
- span
- trace
- resource
- scope
- attribute
- body
- ""
@@ -9221,6 +9222,10 @@ paths:
name: name
schema:
type: string
- in: query
name: existingQuery
schema:
type: string
responses:
"200":
content:
@@ -15468,10 +15473,8 @@ paths:
$ref: '#/components/schemas/RenderErrorResponse'
description: Internal Server Error
security:
- api_key:
- VIEWER
- tokenizer:
- VIEWER
- api_key: []
- tokenizer: []
summary: Get features
tags:
- features

View File

@@ -67,7 +67,7 @@ func (ah *APIHandler) RegisterRoutes(router *mux.Router, am *middleware.AuthZ) {
// note: add ee override methods first
// routes available only in ee version
router.HandleFunc("/api/v1/features", am.ViewAccess(ah.getFeatureFlags)).Methods(http.MethodGet)
router.HandleFunc("/api/v1/features", am.OpenAccess(ah.getFeatureFlags)).Methods(http.MethodGet)
// base overrides
router.HandleFunc("/api/v1/version", am.OpenAccess(ah.getVersion)).Methods(http.MethodGet)

View File

@@ -3492,6 +3492,7 @@ export enum TelemetrytypesFieldContextDTO {
span = 'span',
trace = 'trace',
resource = 'resource',
scope = 'scope',
attribute = 'attribute',
body = 'body',
'' = '',
@@ -10247,6 +10248,11 @@ export type GetAIObservabilityFieldsValuesParams = {
* @description undefined
*/
name?: string;
/**
* @type string
* @description undefined
*/
existingQuery?: string;
};
export type GetAIObservabilityFieldsValues200 = {

View File

@@ -10,6 +10,7 @@ const fieldContextToSuggestionMap: Record<
[TelemetrytypesFieldContextDTO.attribute]: 'attribute',
// no maps for the following values on suggestion context
[TelemetrytypesFieldContextDTO.trace]: undefined,
[TelemetrytypesFieldContextDTO.scope]: undefined,
[TelemetrytypesFieldContextDTO.body]: undefined,
[TelemetrytypesFieldContextDTO.metric]: undefined,
[TelemetrytypesFieldContextDTO.log]: undefined,

View File

@@ -4,13 +4,6 @@
padding: 0px 8px;
.logs-frequency-chart {
.ant-card-body {
height: 140px;
min-height: 140px;
padding: 0 16px 22px 16px;
font-family: 'Geist Mono';
}
margin-bottom: 0px;
}
}

View File

@@ -3,13 +3,6 @@
min-height: 200px;
border-bottom: 1px solid var(--l1-border);
.ant-card-body {
height: 200px;
min-height: 200px;
padding: 0 16px 16px 16px;
font-family: 'Geist Mono';
}
.logs-frequency-chart-loading {
height: 100%;
display: flex;

View File

@@ -1,25 +1,29 @@
import { memo, useCallback, useMemo } from 'react';
import { memo, useCallback, useMemo, useRef } from 'react';
// eslint-disable-next-line no-restricted-imports
import { useDispatch, useSelector } from 'react-redux';
import { useLocation } from 'react-router-dom';
import Graph from 'components/Graph';
import Spinner from 'components/Spinner';
import { QueryParams } from 'constants/query';
import { themeColors } from 'constants/theme';
import BarChart from 'container/DashboardContainer/visualization/charts/BarChart/BarChart';
import { useResizeObserver } from 'hooks/useDimensions';
import { useSafeNavigate } from 'hooks/useSafeNavigate';
import useUrlQuery from 'hooks/useUrlQuery';
import getChartData, { GetChartDataProps } from 'lib/getChartData';
import GetMinMax from 'lib/getMinMax';
import { colors } from 'lib/getRandomColor';
import { LegendPosition } from 'lib/uPlotV2/components/types';
import { StackMode } from 'lib/uPlotV2/config/types';
import { useTimezone } from 'providers/Timezone';
import { UpdateTimeInterval } from 'store/actions';
import { AppState } from 'store/reducers';
import { GlobalReducer } from 'types/reducer/globalTime';
import { LogsExplorerChartProps } from './LogsExplorerChart.interfaces';
import { getColorsForSeverityLabels } from './utils';
import { useLogsExplorerChartConfig } from './useLogsExplorerChartConfig';
import './LogsExplorerChart.styles.scss';
// Axis and tooltip format separately; both need this or only one abbreviates.
const Y_AXIS_UNIT = 'short';
function LogsExplorerChart({
data,
isLoading,
@@ -37,24 +41,6 @@ function LogsExplorerChart({
const { minTime, maxTime } = useSelector<AppState, GlobalReducer>(
(state) => state.globalTime,
);
const handleCreateDatasets: Required<GetChartDataProps>['createDataset'] =
useCallback(
(element, index, allLabels) => ({
data: element,
backgroundColor: isLogsExplorerViews
? getColorsForSeverityLabels(allLabels[index], index)
: colors[index % colors.length] || themeColors.red,
borderColor: isLogsExplorerViews
? getColorsForSeverityLabels(allLabels[index], index)
: colors[index % colors.length] || themeColors.red,
...(isLabelEnabled
? {
label: allLabels[index],
}
: {}),
}),
[isLabelEnabled, isLogsExplorerViews],
);
const onDragSelect = useCallback(
(start: number, end: number): void => {
@@ -86,44 +72,47 @@ function LogsExplorerChart({
[dispatch, location.pathname, safeNavigate, urlQuery, isShowingLiveLogs],
);
const graphData = useMemo(
() =>
getChartData({
queryData: [
{
queryData: data,
},
],
createDataset: handleCreateDatasets,
}),
[data, handleCreateDatasets],
);
// Convert nanosecond timestamps to milliseconds for Chart.js
const { chartMinTime, chartMaxTime } = useMemo(
// uPlot plots the series on a seconds-based x scale
const { minTimeScale, maxTimeScale } = useMemo(
() => ({
chartMinTime: minTime ? Math.floor(minTime / 1e6) : undefined,
chartMaxTime: maxTime ? Math.floor(maxTime / 1e6) : undefined,
minTimeScale: minTime ? Math.floor(minTime / 1e9) : undefined,
maxTimeScale: maxTime ? Math.floor(maxTime / 1e9) : undefined,
}),
[minTime, maxTime],
);
const { timezone } = useTimezone();
const graphRef = useRef<HTMLDivElement>(null);
const dimensions = useResizeObserver(graphRef);
const { config, chartData } = useLogsExplorerChartConfig({
data,
isLogsExplorerViews,
isLabelEnabled,
onDragSelect,
minTimeScale,
maxTimeScale,
yAxisUnit: Y_AXIS_UNIT,
});
return (
<div className={`${className} logs-frequency-chart-container`}>
<div ref={graphRef} className={`${className} logs-frequency-chart-container`}>
{isLoading ? (
<div className="logs-frequency-chart-loading">
<Spinner size="default" height="100%" />
</div>
) : (
<Graph
name="logsExplorerChart"
data={graphData.data}
isStacked={isLogsExplorerViews}
type="bar"
animate
onDragSelect={onDragSelect}
minTime={chartMinTime}
maxTime={chartMaxTime}
<BarChart
config={config}
data={chartData}
width={dimensions.width}
height={dimensions.height}
stack={isLogsExplorerViews ? StackMode.Normal : StackMode.None}
showLegend={isLabelEnabled}
legendConfig={{ position: LegendPosition.BOTTOM }}
timezone={timezone}
data-testid="logs-frequency-chart"
yAxisUnit={Y_AXIS_UNIT}
/>
)}
</div>

View File

@@ -0,0 +1,105 @@
import { useMemo } from 'react';
import { PANEL_TYPES } from 'constants/queryBuilder';
import { themeColors } from 'constants/theme';
import { buildBaseConfig } from 'container/DashboardContainer/visualization/panels/utils/baseConfigBuilder';
import { useIsDarkMode } from 'hooks/useDarkMode';
import getLabelName from 'lib/getLabelName';
import { colors } from 'lib/getRandomColor';
import { getUPlotChartData } from 'lib/uPlotLib/utils/getUplotChartData';
import { DrawStyle } from 'lib/uPlotV2/config/types';
import { UPlotConfigBuilder } from 'lib/uPlotV2/config/UPlotConfigBuilder';
import { useTimezone } from 'providers/Timezone';
import { MetricRangePayloadProps } from 'types/api/metrics/getQueryRange';
import { QueryData } from 'types/api/widgets/getQuery';
import uPlot from 'uplot';
import { getColorsForSeverityLabels } from './utils';
export interface UseLogsExplorerChartConfigParams {
data: QueryData[];
isLogsExplorerViews?: boolean;
isLabelEnabled?: boolean;
onDragSelect: (start: number, end: number) => void;
minTimeScale?: number;
maxTimeScale?: number;
yAxisUnit?: string;
}
export interface UseLogsExplorerChartConfigResult {
config: UPlotConfigBuilder;
chartData: uPlot.AlignedData;
}
export function useLogsExplorerChartConfig({
data,
isLogsExplorerViews = false,
isLabelEnabled = true,
onDragSelect,
minTimeScale,
maxTimeScale,
yAxisUnit,
}: UseLogsExplorerChartConfigParams): UseLogsExplorerChartConfigResult {
const isDarkMode = useIsDarkMode();
const { timezone } = useTimezone();
// getUPlotChartData / buildBaseConfig both consume the legacy query-range payload
// shape, so the raw series list is wrapped instead of being plotted directly.
const apiResponse = useMemo(
() =>
({
data: { result: data, resultType: '' },
}) as unknown as MetricRangePayloadProps,
[data],
);
const chartData = useMemo(() => getUPlotChartData(apiResponse), [apiResponse]);
const config = useMemo(() => {
const builder = buildBaseConfig({
id: 'logs-explorer-frequency-chart',
isDarkMode,
onDragSelect,
timezone,
minTimeScale,
maxTimeScale,
yAxisUnit,
panelType: PANEL_TYPES.BAR,
});
data.forEach((series, index) => {
const label = getLabelName(
series.metric,
series.queryName || '',
series.legend || '',
);
const color = isLogsExplorerViews
? getColorsForSeverityLabels(label, index)
: colors[index % colors.length] || themeColors.red;
builder.addSeries({
scaleKey: 'y',
drawStyle: DrawStyle.Bar,
// No group-by yields query name "A"; use ' ' not '' so uPlot does not default the label to "Value".
label: isLabelEnabled && label.trim() ? label : ' ',
lineColor: color,
colorMapping: {},
isDarkMode,
});
});
return builder;
}, [
data,
isDarkMode,
isLabelEnabled,
isLogsExplorerViews,
maxTimeScale,
minTimeScale,
onDragSelect,
timezone,
yAxisUnit,
]);
return { config, chartData };
}

View File

@@ -217,13 +217,6 @@
padding: 0px 8px;
.logs-frequency-chart {
.ant-card-body {
height: 140px;
min-height: 140px;
padding: 0 16px 22px 16px;
font-family: 'Geist Mono';
}
margin-bottom: 0px;
}
}

View File

@@ -4,13 +4,12 @@ import (
"net/http"
"github.com/SigNoz/signoz/pkg/http/handler"
"github.com/SigNoz/signoz/pkg/types"
"github.com/SigNoz/signoz/pkg/types/featuretypes"
"github.com/gorilla/mux"
)
func (provider *provider) addFlaggerRoutes(router *mux.Router) error {
if err := router.Handle("/api/v2/features", handler.New(provider.authzMiddleware.ViewAccess(provider.flaggerHandler.GetFeatures), handler.OpenAPIDef{
if err := router.Handle("/api/v2/features", handler.New(provider.authzMiddleware.OpenAccess(provider.flaggerHandler.GetFeatures), handler.OpenAPIDef{
ID: "GetFeatures",
Tags: []string{"features"},
Summary: "Get features",
@@ -22,7 +21,7 @@ func (provider *provider) addFlaggerRoutes(router *mux.Router) error {
SuccessStatusCode: http.StatusOK,
ErrorStatusCodes: []int{},
Deprecated: false,
SecuritySchemes: newSecuritySchemes(types.RoleViewer),
SecuritySchemes: newScopedSecuritySchemes(nil),
})).Methods(http.MethodGet).GetError(); err != nil {
return err
}

View File

@@ -5,7 +5,6 @@ import (
"net/http"
"time"
"github.com/SigNoz/signoz/pkg/errors"
"github.com/SigNoz/signoz/pkg/http/binding"
"github.com/SigNoz/signoz/pkg/http/render"
"github.com/SigNoz/signoz/pkg/modules/aiobservability"
@@ -66,13 +65,6 @@ func (handler *handler) GetFieldsValues(rw http.ResponseWriter, req *http.Reques
ctx, cancel := context.WithTimeout(req.Context(), 10*time.Second)
defer cancel()
// binding ignores query params the struct does not declare, so an unsupported
// existingQuery would silently return values it did not narrow
if req.URL.Query().Has("existingQuery") {
render.Error(rw, errors.New(errors.TypeInvalidInput, errors.CodeInvalidInput, "existingQuery is not supported"))
return
}
var params aiobservabilitytypes.PostableFieldValueParams
if err := binding.Query.BindQuery(req.URL.Query(), &params); err != nil {
render.Error(rw, err)
@@ -84,18 +76,29 @@ func (handler *handler) GetFieldsValues(rw http.ResponseWriter, req *http.Reques
render.Error(rw, err)
return
}
orgID := valuer.MustNewUUID(claims.OrgID)
params.ExistingQuery = aitelemetryschema.ScopedExistingQuery(params.ExistingQuery)
fieldValueSelector := aiobservabilitytypes.NewFieldValueSelectorFromPostableFieldValueParams(params)
values := &telemetrytypes.TelemetryFieldValues{}
complete := true
// the trace context names the computed per-trace aggregates, which are never ingested
if fieldValueSelector.FieldContext != telemetrytypes.FieldContextTrace {
values, complete, err = handler.telemetryMetadataStore.GetAllValues(ctx, valuer.MustNewUUID(claims.OrgID), fieldValueSelector)
values, complete, err = handler.telemetryMetadataStore.GetAllValues(ctx, orgID, fieldValueSelector)
if err != nil {
render.Error(rw, err)
return
}
// related values are best-effort: on failure the plain values still serve
// the filter bar
relatedValues, relatedComplete, err := handler.telemetryMetadataStore.GetRelatedValues(ctx, orgID, fieldValueSelector)
if err != nil {
relatedValues = []string{}
}
values.RelatedValues = relatedValues
complete = complete && relatedComplete
}
render.Success(rw, http.StatusOK, &telemetrytypes.GettableFieldValues{

View File

@@ -439,7 +439,7 @@ func (aH *APIHandler) RegisterRoutes(router *mux.Router, am *middleware.AuthZ) {
router.HandleFunc("/api/v2/traces/fields", am.EditAccess(aH.updateTraceField)).Methods(http.MethodPost)
router.HandleFunc("/api/v1/version", am.OpenAccess(aH.getVersion)).Methods(http.MethodGet)
router.HandleFunc("/api/v1/features", am.ViewAccess(aH.getFeatureFlags)).Methods(http.MethodGet)
router.HandleFunc("/api/v1/features", am.OpenAccess(aH.getFeatureFlags)).Methods(http.MethodGet)
router.HandleFunc("/api/v1/health", am.OpenAccess(aH.getHealth)).Methods(http.MethodGet)
router.HandleFunc("/api/v1/listErrors", am.ViewAccess(aH.listErrors)).Methods(http.MethodPost)
@@ -1497,7 +1497,7 @@ func (aH *APIHandler) getFeatureFlags(w http.ResponseWriter, r *http.Request) {
claims, err := authtypes.ClaimsFromContext(r.Context())
if err != nil {
aH.HandleError(w, err, http.StatusInternalServerError)
aH.HandleError(w, err, http.StatusUnauthorized)
return
}

View File

@@ -107,8 +107,8 @@ func SynthesizeKeys(field *telemetrytypes.TelemetryFieldKey, value any) []*telem
fieldContext = telemetrytypes.FieldContextAttribute
}
fieldDataType := field.FieldDataType
// Resource values are strings; pin the type so operand coercion applies.
if fieldContext == telemetrytypes.FieldContextResource &&
// Resource and scope values are strings; pin the type so operand coercion applies.
if (fieldContext == telemetrytypes.FieldContextResource || fieldContext == telemetrytypes.FieldContextScope) &&
fieldDataType == telemetrytypes.FieldDataTypeUnspecified {
fieldDataType = telemetrytypes.FieldDataTypeString
}

View File

@@ -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,
})
}
}
}

View File

@@ -72,6 +72,44 @@ 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,
},
},
},
{
// A scope attribute whose own name carries a `scope.` prefix. `scope.prefixed`
// normalizes to {prefixed, scope}; the second selector re-adds the prefix so the
// metadata fetch can target the attribute's exact key `scope.prefixed` rather than
// relying on the broad `%prefixed%` match.
query: `scope.prefixed = 'x'`,
expectedKeys: []telemetrytypes.FieldKeySelector{
{
Name: "prefixed",
Signal: telemetrytypes.SignalUnspecified,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeUnspecified,
},
{
Name: "scope.prefixed",
Signal: telemetrytypes.SignalUnspecified,
FieldContext: telemetrytypes.FieldContextUnspecified,
FieldDataType: telemetrytypes.FieldDataTypeUnspecified,
},
},
},
}
for _, testCase := range testCases {

View File

@@ -1,8 +1,6 @@
package aistatementbuilder
import (
"strings"
"github.com/SigNoz/signoz/pkg/factory"
"github.com/SigNoz/signoz/pkg/flagger"
"github.com/SigNoz/signoz/pkg/statementbuilder"
@@ -27,11 +25,8 @@ func NewFactory(
// Scope describes gen_ai for the scoped trace builder: an AI trace has >=1 gen_ai
// LLM, tool, or agent span, and its list adds AI/LLM per-trace metrics.
func Scope() scopedtraces.TraceScope {
gateKeyNames := []string{aiobservabilitytypes.GenAIRequestModel, aiobservabilitytypes.GenAIToolName, aiobservabilitytypes.GenAIAgentName}
gateExprs := make([]string, 0, len(gateKeyNames))
gateKeys := make([]*telemetrytypes.TelemetryFieldKey, 0, len(gateKeyNames))
for _, name := range gateKeyNames {
gateExprs = append(gateExprs, name+" EXISTS")
gateKeys := make([]*telemetrytypes.TelemetryFieldKey, 0, len(aiobservabilitytypes.GenAISpanGateKeys))
for _, name := range aiobservabilitytypes.GenAISpanGateKeys {
gateKeys = append(gateKeys, &telemetrytypes.TelemetryFieldKey{
Name: name,
Signal: telemetrytypes.SignalTraces,
@@ -79,7 +74,7 @@ func Scope() scopedtraces.TraceScope {
}
return scopedtraces.TraceScope{
FilterExpression: strings.Join(gateExprs, " OR "),
FilterExpression: aiobservabilitytypes.GenAISpanFilterExpression(),
FieldKeys: gateKeys,
Columns: columns,
DefaultOrderAlias: "last_activity_time",

View File

@@ -204,31 +204,15 @@ func getKeySelectors(query qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation])
}
for idx := range query.GroupBy {
groupBy := query.GroupBy[idx]
keySelectors = append(keySelectors, &telemetrytypes.FieldKeySelector{
Name: groupBy.Name,
Signal: telemetrytypes.SignalTraces,
FieldContext: groupBy.FieldContext,
FieldDataType: groupBy.FieldDataType,
})
keySelectors = append(keySelectors, keySelectorsForField(query.GroupBy[idx].TelemetryFieldKey)...)
}
for idx := range query.SelectFields {
keySelectors = append(keySelectors, &telemetrytypes.FieldKeySelector{
Name: query.SelectFields[idx].Name,
Signal: telemetrytypes.SignalTraces,
FieldContext: query.SelectFields[idx].FieldContext,
FieldDataType: query.SelectFields[idx].FieldDataType,
})
keySelectors = append(keySelectors, keySelectorsForField(query.SelectFields[idx])...)
}
for idx := range query.Order {
keySelectors = append(keySelectors, &telemetrytypes.FieldKeySelector{
Name: query.Order[idx].Key.Name,
Signal: telemetrytypes.SignalTraces,
FieldContext: query.Order[idx].Key.FieldContext,
FieldDataType: query.Order[idx].Key.FieldDataType,
})
keySelectors = append(keySelectors, keySelectorsForField(query.Order[idx].Key.TelemetryFieldKey)...)
}
for idx := range keySelectors {
@@ -239,6 +223,26 @@ func getKeySelectors(query qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation])
return keySelectors
}
func keySelectorsForField(key telemetrytypes.TelemetryFieldKey) []*telemetrytypes.FieldKeySelector {
selectors := []*telemetrytypes.FieldKeySelector{
{
Name: key.Name,
Signal: telemetrytypes.SignalTraces,
FieldContext: key.FieldContext,
FieldDataType: key.FieldDataType,
},
}
if key.FieldContext != telemetrytypes.FieldContextUnspecified {
selectors = append(selectors, &telemetrytypes.FieldKeySelector{
Name: key.FieldContext.StringValue() + "." + key.Name,
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextUnspecified,
FieldDataType: key.FieldDataType,
})
}
return selectors
}
// mergeDeprecatedTraceKeys prepends deprecated intrinsic/calculated trace field
// definitions to the keys map. We do this during statement building, not at
// metadata fetch time, because:
@@ -310,20 +314,14 @@ func adjustTraceKey(key *telemetrytypes.TelemetryFieldKey, keys map[string][]*te
For example: trace_id (intrinsic), response_status_code (calculated).
*/
// Resolve against the context-qualified name first, then the bare name since that can be instrinsic field e.g. scope.name.
var isIntrinsicOrCalculatedField bool
var intrinsicOrCalculatedField telemetrytypes.TelemetryFieldKey
if _, ok := tracestelemetryschema.IntrinsicFields[key.Name]; ok {
isIntrinsicOrCalculatedField = true
intrinsicOrCalculatedField = tracestelemetryschema.IntrinsicFields[key.Name]
} else if _, ok := tracestelemetryschema.CalculatedFields[key.Name]; ok {
isIntrinsicOrCalculatedField = true
intrinsicOrCalculatedField = tracestelemetryschema.CalculatedFields[key.Name]
} else if _, ok := tracestelemetryschema.IntrinsicFieldsDeprecated[key.Name]; ok {
isIntrinsicOrCalculatedField = true
intrinsicOrCalculatedField = tracestelemetryschema.IntrinsicFieldsDeprecated[key.Name]
} else if _, ok := tracestelemetryschema.CalculatedFieldsDeprecated[key.Name]; ok {
isIntrinsicOrCalculatedField = true
intrinsicOrCalculatedField = tracestelemetryschema.CalculatedFieldsDeprecated[key.Name]
if key.FieldContext != telemetrytypes.FieldContextUnspecified {
intrinsicOrCalculatedField, isIntrinsicOrCalculatedField = lookupIntrinsicOrCalculatedField(key.FieldContext.StringValue() + "." + key.Name)
}
if !isIntrinsicOrCalculatedField {
intrinsicOrCalculatedField, isIntrinsicOrCalculatedField = lookupIntrinsicOrCalculatedField(key.Name)
}
if isIntrinsicOrCalculatedField {
@@ -335,6 +333,24 @@ func adjustTraceKey(key *telemetrytypes.TelemetryFieldKey, keys map[string][]*te
return actions
}
// lookupIntrinsicOrCalculatedField returns the intrinsic or calculated field registered under
// name, across the current and deprecated tables.
func lookupIntrinsicOrCalculatedField(name string) (telemetrytypes.TelemetryFieldKey, bool) {
if f, ok := tracestelemetryschema.IntrinsicFields[name]; ok {
return f, true
}
if f, ok := tracestelemetryschema.CalculatedFields[name]; ok {
return f, true
}
if f, ok := tracestelemetryschema.IntrinsicFieldsDeprecated[name]; ok {
return f, true
}
if f, ok := tracestelemetryschema.CalculatedFieldsDeprecated[name]; ok {
return f, true
}
return telemetrytypes.TelemetryFieldKey{}, false
}
// buildListQuery builds a query for list panel type.
func (b *traceQueryStatementBuilder) buildListQuery(
ctx context.Context,

View File

@@ -374,6 +374,94 @@ 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 <> '', scope.name::String, NULL)) AS `__GROUP_BY_KEY_0_scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.name::String = ? AND scope.name::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_scope.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(scope.name::String <> '', scope.name::String, NULL)) AS `__GROUP_BY_KEY_0_scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.name::String = ? AND scope.name::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_scope.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_scope.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_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 <> '', scope.name::String, NULL)) AS `__GROUP_BY_KEY_0_scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_scope.name` ORDER BY __result_0 DESC LIMIT ?) SELECT toStartOfInterval(timestamp, INTERVAL 30 SECOND) AS ts, toString(multiIf(scope.name::String <> '', scope.name::String, NULL)) AS `__GROUP_BY_KEY_0_scope.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_scope.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_scope.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_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 `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? GROUP BY `__GROUP_BY_KEY_0_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 `__GROUP_BY_KEY_0_service.name`, count() AS __result_0 FROM signoz_traces.distributed_signoz_index_v3 WHERE (scope.version::String = ? AND scope.version::String <> '') AND timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? AND (`__GROUP_BY_KEY_0_service.name`) GLOBAL IN (SELECT `__GROUP_BY_KEY_0_service.name` FROM __limit_cte) GROUP BY ts, `__GROUP_BY_KEY_0_service.name`",
Args: []any{"1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10, "1.0.0", "1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448)},
},
},
}
fl := flaggertest.New(t)
@@ -800,6 +888,143 @@ 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 `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, trace_state AS `__SELECT_KEY_3_trace_state`, parent_span_id AS `__SELECT_KEY_4_parent_span_id`, flags AS `__SELECT_KEY_5_flags`, name AS `__SELECT_KEY_6_name`, kind AS `__SELECT_KEY_7_kind`, kind_string AS `__SELECT_KEY_8_kind_string`, duration_nano AS `__SELECT_KEY_9_duration_nano`, status_code AS `__SELECT_KEY_10_status_code`, status_message AS `__SELECT_KEY_11_status_message`, status_code_string AS `__SELECT_KEY_12_status_code_string`, events AS `__SELECT_KEY_13_events`, links AS `__SELECT_KEY_14_links`, response_status_code AS `__SELECT_KEY_15_response_status_code`, external_http_url AS `__SELECT_KEY_16_external_http_url`, http_url AS `__SELECT_KEY_17_http_url`, external_http_method AS `__SELECT_KEY_18_external_http_method`, http_method AS `__SELECT_KEY_19_http_method`, http_host AS `__SELECT_KEY_20_http_host`, db_name AS `__SELECT_KEY_21_db_name`, db_operation AS `__SELECT_KEY_22_db_operation`, has_error AS `__SELECT_KEY_23_has_error`, is_remote AS `__SELECT_KEY_24_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 <> '') 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},
},
},
{
// Regression test: scope.version in selectFields with no metadata (isColumn=true filters it out)
// must still produce scope.version::String, not scope.attributes.version::String
name: "scope.version in selectFields only, no metadata (intrinsic field fallback)",
requestType: qbtypes.RequestTypeRaw,
keysMap: map[string][]*telemetrytypes.TelemetryFieldKey{},
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Filter: &qbtypes.Filter{},
SelectFields: []telemetrytypes.TelemetryFieldKey{
{Name: "scope.version", FieldContext: telemetrytypes.FieldContextUnspecified},
},
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, multiIf(scope.version::String <> '', scope.version::String, NULL) AS `__SELECT_KEY_3_scope.version` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},
{
// A scope attribute whose own name literally carries a `scope.` prefix (`scope.prefixed`,
// normalized to {prefixed, scope}) resolves to that attribute in a SELECT even without a
// filter: getKeySelectors emits the reconstructed `scope.prefixed` selector so the metadata
// fetch surfaces it and AdjustKey recovers the full name. Without it the `scope.` prefix is
// lost and it wrongly reads `scope.attributes.prefixed`.
name: "scope-prefixed attribute in selectFields resolves without a filter",
requestType: qbtypes.RequestTypeRaw,
keysMap: map[string][]*telemetrytypes.TelemetryFieldKey{
"scope.prefixed": {
{
Name: "scope.prefixed",
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{},
SelectFields: []telemetrytypes.TelemetryFieldKey{
{Name: "prefixed", FieldContext: telemetrytypes.FieldContextScope},
},
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, multiIf(scope.attributes.`scope.prefixed` IS NOT NULL, scope.attributes.`scope.prefixed`::String, NULL) AS `__SELECT_KEY_3_scope.prefixed` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},
{
// A scope-context key whose name matches a declared scope path resolves to that
// declared path (scope.name), not the span `name` column and not an undeclared
// scope attribute. getTracesKeys surfaces the declared path as an intrinsic key
// (metadata.go), which shadows the same-named span intrinsic.
name: "scope-context name resolves to the declared scope path",
requestType: qbtypes.RequestTypeRaw,
keysMap: map[string][]*telemetrytypes.TelemetryFieldKey{
"scope.name": {
{
Name: "scope.name",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
"name": {
{
Name: "name",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextSpan,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
},
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Filter: &qbtypes.Filter{},
SelectFields: []telemetrytypes.TelemetryFieldKey{
{Name: "name", FieldContext: telemetrytypes.FieldContextScope},
},
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, multiIf(scope.name::String <> '', scope.name::String, NULL) AS `__SELECT_KEY_3_name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},
{
// span.scope.name (span context, name "scope.name") resolves to the declared
// scope path scope.name, not a span attribute literally named scope.name.
name: "span-context scope.name in selectFields resolves to the declared scope path",
requestType: qbtypes.RequestTypeRaw,
keysMap: map[string][]*telemetrytypes.TelemetryFieldKey{},
query: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Signal: telemetrytypes.SignalTraces,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Filter: &qbtypes.Filter{},
SelectFields: []telemetrytypes.TelemetryFieldKey{
{Name: "scope.name", FieldContext: telemetrytypes.FieldContextSpan},
},
Limit: 10,
},
expected: qbtypes.Statement{
Query: "SELECT timestamp AS `__SELECT_KEY_0_timestamp`, trace_id AS `__SELECT_KEY_1_trace_id`, span_id AS `__SELECT_KEY_2_span_id`, multiIf(scope.name::String <> '', scope.name::String, NULL) AS `__SELECT_KEY_3_scope.name` FROM signoz_traces.distributed_signoz_index_v3 WHERE timestamp >= ? AND timestamp < ? AND ts_bucket_start >= ? AND ts_bucket_start <= ? LIMIT ?",
Args: []any{"1747947419000000000", "1747983448000000000", uint64(1747945619), uint64(1747983448), 10},
},
},
}
for _, c := range cases {

View File

@@ -180,7 +180,7 @@ 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`,

View File

@@ -0,0 +1,36 @@
package aitelemetryschema
import (
"github.com/SigNoz/signoz/pkg/querybuilder"
"github.com/SigNoz/signoz/pkg/types/aiobservabilitytypes"
)
var (
traceAggregateNames = func() map[string]struct{} {
names := make(map[string]struct{}, len(TraceAggregateFields))
for name := range TraceAggregateFields {
names[name] = struct{}{}
}
return names
}()
genAISpanGate = "(" + aiobservabilitytypes.GenAISpanFilterExpression() + ")"
)
// ScopedExistingQuery narrows value suggestions to gen_ai spans: the caller's
// filter minus its per-trace aggregate atoms (never ingested, so nothing can
// narrow on them), ANDed with the gen_ai span gate. An unparseable filter is
// dropped, matching how the metadata store treats it downstream.
func ScopedExistingQuery(existingQuery string) string {
spanExpr := ""
if existingQuery != "" {
if expr, _, err := querybuilder.SplitFilterForAggregates(existingQuery, traceAggregateNames); err == nil {
spanExpr = expr
}
}
if spanExpr == "" {
return genAISpanGate
}
return genAISpanGate + " AND (" + spanExpr + ")"
}

View File

@@ -0,0 +1,94 @@
package aitelemetryschema
import (
"testing"
"github.com/stretchr/testify/assert"
)
func TestScopedExistingQuery(t *testing.T) {
gate := "(gen_ai.request.model EXISTS OR gen_ai.tool.name EXISTS OR gen_ai.agent.name EXISTS)"
testCases := []struct {
name string
existingQuery string
expected string
}{
{
name: "empty query returns the gate alone",
existingQuery: "",
expected: gate,
},
{
name: "span filter is preserved under the gate",
existingQuery: "service.name = 'checkout'",
expected: gate + " AND (service.name = 'checkout')",
},
{
name: "trace aggregate filter is stripped",
existingQuery: "llm_call_count > 5",
expected: gate,
},
{
name: "mixed filter keeps only the span part",
existingQuery: "llm_call_count > 5 AND gen_ai.request.model = 'gpt-4'",
expected: gate + " AND (gen_ai.request.model = 'gpt-4')",
},
{
name: "trace context filter is stripped",
existingQuery: "trace.total_tokens > 100 AND service.name = 'checkout'",
expected: gate + " AND (service.name = 'checkout')",
},
{
name: "unparseable filter is dropped",
existingQuery: "service.name = ",
expected: gate,
},
{
name: "multiple span conditions survive as one AND chain",
existingQuery: "service.name = 'checkout' AND gen_ai.request.model = 'gpt-4' AND llm_call_count > 5",
expected: gate + " AND (service.name = 'checkout' AND gen_ai.request.model = 'gpt-4')",
},
{
name: "span OR group is kept whole and parenthesized against the AND join",
existingQuery: "service.name = 'a' OR service.name = 'b'",
expected: gate + " AND ((service.name = 'a' OR service.name = 'b'))",
},
{
name: "parenthesized span OR group ANDed with an aggregate keeps only the group",
existingQuery: "(service.name = 'a' OR service.name = 'b') AND llm_call_count > 5",
expected: gate + " AND ((service.name = 'a' OR service.name = 'b'))",
},
{
name: "OR group of trace aggregates is stripped whole",
existingQuery: "llm_call_count > 5 OR total_tokens > 100",
expected: gate,
},
{
name: "OR mixing aggregate and span atoms drops the whole filter",
existingQuery: "llm_call_count > 5 OR service.name = 'checkout'",
expected: gate,
},
{
name: "parenthesized AND group is split, not routed whole",
existingQuery: "(llm_call_count > 5 AND service.name = 'checkout') AND gen_ai.request.model = 'gpt-4'",
expected: gate + " AND (service.name = 'checkout' AND gen_ai.request.model = 'gpt-4')",
},
{
name: "NOT over an aggregate group is stripped",
existingQuery: "NOT (llm_call_count > 5) AND service.name = 'checkout'",
expected: gate + " AND (service.name = 'checkout')",
},
{
name: "NOT over a span group is kept",
existingQuery: "NOT (service.name = 'checkout')",
expected: gate + " AND (NOT (service.name = 'checkout'))",
},
}
for _, testCase := range testCases {
t.Run(testCase.name, func(t *testing.T) {
assert.Equal(t, testCase.expected, ScopedExistingQuery(testCase.existingQuery))
})
}
}

View File

@@ -391,6 +391,96 @@ func TestConditionForResourceWithEvolution(t *testing.T) {
}
}
// TestConditionForScopeIntrinsicFields covers the scope.name/scope.version intrinsic
// fields against the "scope" JSON column. These are *declared* String paths on that
// column, so a row without a scope reads as ” and never NULL: presence must be an
// empty-string check, since "IS NOT NULL" would hold for every row. That also rules
// out treating them as nested attribute keys under scope.attributes, which are
// undeclared (Dynamic) paths and genuinely NULL when absent.
func TestConditionForScopeIntrinsicFields(t *testing.T) {
ctx := context.Background()
fm := NewFieldMapper(flaggertest.New(t))
conditionBuilder := NewConditionBuilder(fm, flaggertest.New(t))
testCases := []struct {
name string
key telemetrytypes.TelemetryFieldKey
operator qbtypes.FilterOperator
value any
expectedSQL string
}{
{
name: "Equal - scope.name",
key: telemetrytypes.TelemetryFieldKey{
Name: "scope.name",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorEqual,
value: "io.signoz.payment",
expectedSQL: "(scope.name::String = ? AND scope.name::String <> '')",
},
{
name: "Equal - scope.version",
key: telemetrytypes.TelemetryFieldKey{
Name: "scope.version",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorEqual,
value: "2.3.1",
expectedSQL: "(scope.version::String = ? AND scope.version::String <> '')",
},
{
name: "Exists - scope.name",
key: telemetrytypes.TelemetryFieldKey{
Name: "scope.name",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorExists,
value: nil,
expectedSQL: "scope.name::String <> ''",
},
{
name: "NotExists - scope.version",
key: telemetrytypes.TelemetryFieldKey{
Name: "scope.version",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorNotExists,
value: nil,
expectedSQL: "scope.version::String = ''",
},
{
// `scope.attribute.name` (normalized to {attribute.name, scope}) addresses the scope
// attribute named `name` — the declared `scope.name` path is never reached this way.
name: "Equal - scope.attribute.name reaches the named scope attribute",
key: telemetrytypes.TelemetryFieldKey{
Name: "attribute.name",
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
operator: qbtypes.FilterOperatorEqual,
value: "io.signoz.checkout",
expectedSQL: "(scope.attributes.`name`::String = ? AND scope.attributes.`name` IS NOT NULL)",
},
}
for _, tc := range testCases {
sb := sqlbuilder.NewSelectBuilder()
t.Run(tc.name, func(t *testing.T) {
conds, _, err := conditionBuilder.ConditionFor(ctx, valuer.UUID{}, 0, 0, &tc.key, map[string][]*telemetrytypes.TelemetryFieldKey{tc.key.Name: {&tc.key}}, qbtypes.ConditionBuilderOptions{}, tc.operator, tc.value, sb)
require.NoError(t, err)
sb.Where(conds...)
sql, _ := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
assert.Contains(t, sql, tc.expectedSQL)
assert.NotContains(t, sql, "scope.`scope.", "must not double-prefix the scope JSON path")
})
}
}
// TestConditionForSynthesizedKeys covers the KeyNotFound fallback: when a
// referenced attribute key has no metadata match, the builder synthesizes key(s) from
// user input and queries anyway, emitting a warning instead of failing.
@@ -414,6 +504,20 @@ func TestConditionForSynthesizedKeys(t *testing.T) {
assert.Contains(t, args, "timeout")
})
t.Run("scope context with no metadata -> scope attribute", func(t *testing.T) {
sb := sqlbuilder.NewSelectBuilder()
key := telemetrytypes.TelemetryFieldKey{Name: "custom.attr", FieldContext: telemetrytypes.FieldContextScope}
conds, warnings, err := cb.ConditionFor(ctx, valuer.UUID{}, 0, 0, &key, noMatches, qbtypes.ConditionBuilderOptions{}, qbtypes.FilterOperatorEqual, "v", sb)
assert.NoError(t, err, "an undeclared scope attribute must still be filterable")
assert.NotEmpty(t, warnings)
sb.Where(conds...)
sql, _ := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
assert.Contains(t, sql, "scope.attributes.`custom.attr`")
// `scope.` can be part of the attribute's own name, so the literal spelling is a
// candidate too — the caller ORs the two.
assert.Contains(t, sql, "scope.attributes.`scope.custom.attr`")
})
t.Run("bare key with number operand -> attribute number", func(t *testing.T) {
sb := sqlbuilder.NewSelectBuilder()
key := telemetrytypes.TelemetryFieldKey{Name: "http.status"}

View File

@@ -121,6 +121,20 @@ var (
FieldContext: telemetrytypes.FieldContextSpan,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
"scope.name": {
Name: "scope.name",
Description: "Instrumentation scope name",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
"scope.version": {
Name: "scope.version",
Description: "Instrumentation scope version",
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
}
IntrinsicFieldsDeprecated = map[string]telemetrytypes.TelemetryFieldKey{
"traceID": {

View File

@@ -53,6 +53,7 @@ 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,
@@ -181,7 +182,7 @@ func (m *fieldMapper) getColumn(
case telemetrytypes.FieldContextResource:
return []*schema.Column{indexV3Columns["resource"], indexV3Columns["resources_string"]}, nil
case telemetrytypes.FieldContextScope:
return []*schema.Column{}, qbtypes.ErrColumnNotFound
return []*schema.Column{indexV3Columns["scope"]}, nil
case telemetrytypes.FieldContextAttribute:
switch key.FieldDataType {
case telemetrytypes.FieldDataTypeString:
@@ -292,14 +293,25 @@ func (m *fieldMapper) resolveColumnExprs(
switch column.Type.GetType() {
case schema.ColumnTypeEnumJSON:
// json is only supported for resource context as of now
if key.FieldContext != telemetrytypes.FieldContextResource {
return nil, nil, nil, 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))
existExprs = append(existExprs, 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))
existExprs = append(existExprs, fmt.Sprintf("%s.`%s` IS NOT NULL", columnName, key.Name))
case telemetrytypes.FieldContextScope:
if f, ok := IntrinsicFields[key.Name]; ok && f.FieldContext == telemetrytypes.FieldContextScope {
// declared String paths on the scope column read '' for the missing case
exprs = append(exprs, fmt.Sprintf("%s::String", key.Name))
existExprs = append(existExprs, fmt.Sprintf("%s <> ''", key.Name))
} else {
attributeName := strings.TrimPrefix(key.Name, "attribute.") // literal "attribute" prefix in attribute keys needs double prefix
exprs = append(exprs, fmt.Sprintf("%s.attributes.%s::String", columnName, querybuilder.ClickHouseIdentifier(attributeName)))
existExprs = append(existExprs, fmt.Sprintf("%s.attributes.%s IS NOT NULL", columnName, querybuilder.ClickHouseIdentifier(attributeName)))
}
default:
return nil, nil, nil, errors.NewInternalf(errors.CodeInternal, "only resource and scope context fields are supported for json columns, got %s", key.FieldContext.String)
}
case schema.ColumnTypeEnumString,
schema.ColumnTypeEnumUInt64,
schema.ColumnTypeEnumUInt32,
@@ -341,20 +353,6 @@ func (m *fieldMapper) resolveColumnExprs(
return exprs, existExprs, columns, nil
}
// logicalForResolvedColumn upgrades a directly-resolvable key (the FieldFor
// probe succeeded) to its family when the metadata map proves membership;
// otherwise the key stays a single-member logical field.
func (m *fieldMapper) logicalForResolvedColumn(ctx context.Context, orgID valuer.UUID, field *telemetrytypes.TelemetryFieldKey, keys map[string][]*telemetrytypes.TelemetryFieldKey) *telemetrytypes.LogicalField {
for _, logical := range querybuilder.MatchingLogicalFields(ctx, orgID, m.fl, field, keys) {
if logical.IsFamily() &&
logical.FieldContext == field.FieldContext &&
(field.FieldDataType == telemetrytypes.FieldDataTypeUnspecified || logical.FieldDataType == field.FieldDataType) {
return logical
}
}
return telemetrytypes.SingleLogicalField(field.Name, field)
}
// upgradeToFamilies swaps single-member candidates for their family when the
// metadata map proves membership. Candidate order and every non-family
// candidate stay exactly as the legacy flow produced them; sibling candidates
@@ -419,9 +417,11 @@ func (m *fieldMapper) ColumnExpressionFor(
var candidates []*telemetrytypes.LogicalField
switch _, err := m.FieldFor(ctx, orgID, startNs, endNs, field); {
case err == nil:
// A directly-resolvable key upgrades to its family when the metadata
// map proves membership; otherwise it stays single-member.
candidates = []*telemetrytypes.LogicalField{m.logicalForResolvedColumn(ctx, orgID, field, keys)}
// Every match from metadata is kept, similar to the filter path.
candidates = querybuilder.MatchingLogicalFields(ctx, orgID, m.fl, field, keys)
if len(candidates) == 0 {
candidates = []*telemetrytypes.LogicalField{telemetrytypes.SingleLogicalField(field.Name, field)}
}
case errors.Is(err, qbtypes.ErrColumnNotFound):
// The legacy candidate flow, unchanged: column (when the bare name is
// one) plus metadata matches, else synthesized type-variant keys. The
@@ -595,15 +595,37 @@ func (m *fieldMapper) CandidateKeys(ctx context.Context, _ valuer.UUID, field *t
// honored as-is: the stripped name lives in the attribute maps
stripped := telemetrytypes.NewTelemetryFieldKey(field.Name, telemetrytypes.FieldContextUnspecified, field.FieldDataType)
return querybuilder.SynthesizeKeys(stripped, value)
case telemetrytypes.FieldContextAttribute, telemetrytypes.FieldContextResource:
case telemetrytypes.FieldContextAttribute, telemetrytypes.FieldContextResource, telemetrytypes.FieldContextScope:
// strict context honored as-is: stripped interpretation first, literal spelling second
literal := telemetrytypes.NewTelemetryFieldKey(field.FieldContext.StringValue()+"."+field.Name, field.FieldContext, field.FieldDataType)
return append(querybuilder.SynthesizeKeys(field, value), querybuilder.SynthesizeKeys(literal, value)...)
}
// contexts that don't exist on spans (log, body, scope, …) have nothing to synthesize
// contexts that don't exist on spans (log, body, …) have nothing to synthesize
return nil
}
// scopeJSONExistsExpression renders the existence predicate for the scope JSON column, the one
// signal-specific case the generic querybuilder.ExistsExpression must not carry.
func scopeJSONExistsExpression(key *telemetrytypes.TelemetryFieldKey, fieldExpression string, exists bool) (string, bool) {
if key.FieldContext != telemetrytypes.FieldContextScope {
return "", false
}
// Declared String paths are non-Nullable (absent reads '' not NULL).
if f, ok := IntrinsicFields[key.Name]; ok && f.FieldContext == telemetrytypes.FieldContextScope {
if exists {
return fieldExpression + " <> ''", true
}
return fieldExpression + " = ''", true
}
// Scope attribute: the value expression casts the JSON path to String, which folds a missing
// key's NULL to '', so presence must test the raw path — drop the ::String cast.
path := strings.TrimSuffix(fieldExpression, "::String")
if exists {
return path + " IS NOT NULL", true
}
return path + " IS NULL", true
}
// ExistsFor implements the per-key existence primitive of qbtypes.FieldMapper.
func (m *fieldMapper) ExistsFor(
ctx context.Context,
@@ -620,5 +642,8 @@ func (m *fieldMapper) ExistsFor(
if err != nil {
return "", err
}
if expr, ok := scopeJSONExistsExpression(key, fieldExpression, exists); ok {
return expr, nil
}
return querybuilder.ExistsExpression(columns, key, tsStart, tsEnd, fieldExpression, exists)
}

View File

@@ -84,6 +84,45 @@ func TestGetFieldKeyName(t *testing.T) {
expectedResult: "multiIf(resource.`deployment.environment` IS NOT NULL, resource.`deployment.environment`::String, `resource_string_deployment$$environment_exists`, `resource_string_deployment$$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,
},
{
// `scope.attribute.name` normalizes to {attribute.name, scope}; the literal
// `attribute.` prefix is dropped so it addresses the scope attribute named `name`
// (which the declared `scope.name` path deliberately does not).
name: "Scope field - attribute prefix addresses the named scope attribute",
key: telemetrytypes.TelemetryFieldKey{
Name: "attribute.name",
FieldContext: telemetrytypes.FieldContextScope,
},
expectedResult: "scope.attributes.`name`::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",
@@ -304,3 +343,99 @@ func TestColumnExpressionForTimestampAttributeCollision(t *testing.T) {
assert.Contains(t, result, "attributes_number['timestamp']")
})
}
// TestColumnExpressionForScopeDeclaredPath covers select-side resolution of scope names that
// collide with a declared scope path. A short name under scope context (or the bare
// `scope.<x>` spelling that normalizes to it) names both homes and coalesces them when
// metadata knows a same-named scope attribute, and binds to the declared path alone when it
// does not. The full `scope.<x>` name under explicit scope context addresses the declared
// path alone; the explicit `scope.attribute.` prefix addresses the attribute alone.
func TestColumnExpressionForScopeDeclaredPath(t *testing.T) {
ctx := context.Background()
scopeKey := func(name string) *telemetrytypes.TelemetryFieldKey {
return &telemetrytypes.TelemetryFieldKey{
Name: name,
Signal: telemetrytypes.SignalTraces,
FieldContext: telemetrytypes.FieldContextScope,
FieldDataType: telemetrytypes.FieldDataTypeString,
}
}
declaredOnly := map[string][]*telemetrytypes.TelemetryFieldKey{
"scope.name": {scopeKey("scope.name")},
"scope.version": {scopeKey("scope.version")},
}
withAttr := map[string][]*telemetrytypes.TelemetryFieldKey{
"scope.name": {scopeKey("scope.name")},
"scope.version": {scopeKey("scope.version")},
"name": {scopeKey("name")},
"version": {scopeKey("version")},
}
testCases := []struct {
name string
key telemetrytypes.TelemetryFieldKey
keys map[string][]*telemetrytypes.TelemetryFieldKey
expectedResult string
}{
{
name: "short name under scope context binds to the declared path",
key: telemetrytypes.TelemetryFieldKey{Name: "version", FieldContext: telemetrytypes.FieldContextScope},
keys: declaredOnly,
expectedResult: "multiIf(scope.version::String <> '', scope.version::String, NULL)",
},
{
name: "full scope.version name under scope context addresses the declared path alone",
key: telemetrytypes.TelemetryFieldKey{Name: "scope.version", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.version::String <> '', scope.version::String, NULL)",
},
{
name: "full scope.name name under scope context addresses the declared path alone",
key: telemetrytypes.TelemetryFieldKey{Name: "scope.name", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.name::String <> '', scope.name::String, NULL)",
},
{
// `scope.attribute.name` normalizes to {attribute.name, scope}; the `attribute.`
// prefix is dropped so it addresses the scope attribute named `name` — the only
// way to reach it, since `scope.name` is reserved for the declared path.
name: "attribute prefix reaches the named scope attribute",
key: telemetrytypes.TelemetryFieldKey{Name: "attribute.name", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.attributes.`name` IS NOT NULL, scope.attributes.`name`::String, NULL)",
},
{
// the caller supplied the context, so `scope.` is part of the name rather than a
// prefix to strip: this addresses a scope attribute literally named
// `scope.testing.env`, not the attribute `testing.env`
name: "explicit context keeps a scope-prefixed name intact",
key: telemetrytypes.TelemetryFieldKey{Name: "scope.testing.env", FieldContext: telemetrytypes.FieldContextScope},
keys: declaredOnly,
expectedResult: "multiIf(scope.attributes.`scope.testing.env` IS NOT NULL, scope.attributes.`scope.testing.env`::String, NULL)",
},
{
// metadata knows both homes under this name, so the short spelling coalesces
// them instead of being rejected as ambiguous
name: "short name coalesces a known scope attribute with the declared path",
key: telemetrytypes.TelemetryFieldKey{Name: "name", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.attributes.`name` IS NOT NULL, toString(scope.attributes.`name`::String), scope.name::String <> '', toString(scope.name::String), NULL)",
},
{
name: "short version coalesces a known scope attribute with the declared path",
key: telemetrytypes.TelemetryFieldKey{Name: "version", FieldContext: telemetrytypes.FieldContextScope},
keys: withAttr,
expectedResult: "multiIf(scope.attributes.`version` IS NOT NULL, toString(scope.attributes.`version`::String), scope.version::String <> '', toString(scope.version::String), NULL)",
},
}
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
fm := NewFieldMapper(flaggertest.New(t))
result, err := fm.ColumnExpressionFor(ctx, valuer.UUID{}, 0, 0, &tc.key, telemetrytypes.FieldDataTypeUnspecified, tc.keys)
require.NoError(t, err)
assert.Equal(t, tc.expectedResult, result)
})
}
}

View File

@@ -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,
},
},
// both spellings of an enabled semantic-convention family
"deployment.environment.name": {
{

View File

@@ -15,11 +15,12 @@ type PostableFieldKeysParams struct {
Limit int `query:"limit"`
}
// existingQuery is unsupported until the computed per-trace aggregates it may
// reference can be narrowed on.
// existingQuery may reference the computed per-trace aggregates, which are
// never ingested; those filters are stripped before narrowing values.
type PostableFieldValueParams struct {
PostableFieldKeysParams
Name string `query:"name"`
Name string `query:"name"`
ExistingQuery string `query:"existingQuery"`
}
func NewFieldKeySelectorFromPostableFieldKeysParams(params PostableFieldKeysParams) *telemetrytypes.FieldKeySelector {
@@ -30,6 +31,7 @@ func NewFieldValueSelectorFromPostableFieldValueParams(params PostableFieldValue
return telemetrytypes.NewFieldValueSelectorFromPostableFieldValueParams(telemetrytypes.PostableFieldValueParams{
PostableFieldKeysParams: params.telemetryParams(),
Name: params.Name,
ExistingQuery: params.ExistingQuery,
})
}

View File

@@ -1,5 +1,7 @@
package aiobservabilitytypes
import "strings"
// OpenTelemetry gen_ai semantic-convention attribute keys. Single source of truth
// shared by the AI query builder and the LLM pricing pipeline.
const (
@@ -18,6 +20,20 @@ const (
GenAIOutputMessages = "gen_ai.output.messages"
)
// GenAISpanGateKeys mark a span as gen_ai: an LLM call, a tool call, or an
// agent span. A trace belongs to the AI explorer when any span carries one.
var GenAISpanGateKeys = []string{GenAIRequestModel, GenAIToolName, GenAIAgentName}
// GenAISpanFilterExpression renders the gate as a query-builder filter
// expression: each gate key ORed on EXISTS.
func GenAISpanFilterExpression() string {
exprs := make([]string, 0, len(GenAISpanGateKeys))
for _, key := range GenAISpanGateKeys {
exprs = append(exprs, key+" EXISTS")
}
return strings.Join(exprs, " OR ")
}
// Per-span costs the SigNoz LLM pricing processor attaches; not OTel semconv.
const (
SignozGenAICostInput = "_signoz.gen_ai.cost_input"

View File

@@ -18,7 +18,7 @@ import (
// - Use `scope.` prefix to explicitly indicate and enforce scope context. Example
// - `scope.name`
// - `scope.version`
// - `scope.my.custom.attribute` and `scope.attribute.my.custom.attribute` resolve to same attribute
// - `scope.my.custom.attribute` resolves to the `my.custom.attribute` scope attribute
//
// - Use `attribute.` to explicitly indicate and enforce attribute context. Example
// - `attribute.http.method`
@@ -190,7 +190,7 @@ func (FieldContext) Enum() []any {
FieldContextSpan,
FieldContextTrace,
FieldContextResource,
// FieldContextScope,
FieldContextScope,
FieldContextAttribute,
// FieldContextEvent,
FieldContextBody,

View File

@@ -294,6 +294,17 @@ func TestNormalize(t *testing.T) {
FieldDataType: FieldDataTypeString,
},
},
{
name: "Normalize keeps a prefix that does not match the set context",
input: TelemetryFieldKey{
Name: "scope.name",
FieldContext: FieldContextAttribute,
},
expected: TelemetryFieldKey{
Name: "scope.name",
FieldContext: FieldContextAttribute,
},
},
{
name: "Normalize body field",
input: TelemetryFieldKey{

View File

@@ -999,6 +999,8 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"cloud.provider": "integration",
"cloud.account.id": "000",
"trace_id": "corrupt_data",
"scope_name": "corrupt_data",
"scope.scope.name": "corrupt_data",
},
attributes={
"net.transport": "IP.TCP",
@@ -1007,7 +1009,10 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"http.request.method": "POST",
"http.response.status_code": "200",
"timestamp": "corrupt_data",
"version": "1.0.0",
"scope.scope.version": "1.0.0",
},
scope={"name": "io.signoz.http.server", "version": "2.0.0"},
),
Traces(
timestamp=now - timedelta(seconds=3.5),
@@ -1027,12 +1032,24 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"cloud.provider": "integration",
"cloud.account.id": "000",
"timestamp": "corrupt_data",
"scope.attributes.name": "corrupt_data",
},
attributes={
"db.name": "integration",
"db.operation": "SELECT",
"db.statement": "SELECT * FROM integration",
"trace_d": "corrupt_data",
"scope.attributes.version": "corrupt_data",
},
scope={
"name": "io.opentelemetry.contrib.http",
"version": "1.0.0",
"attributes": {
"telemetry.sdk.language": "cpp",
"name": "not-the-real-name",
"version": "not-the-real-version",
"attributes": "literally-a-key-named-attributes",
},
},
),
Traces(
@@ -1053,12 +1070,15 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"cloud.provider": "integration",
"cloud.account.id": "000",
"duration_nano": "corrupt_data",
"scope.scope.attributes.version": "corrupt_data",
},
attributes={
"http.request.method": "PATCH",
"http.status_code": "404",
"id": "1",
"scope.scope.version": "corrupt_data",
},
scope={"name": "io.signoz.http.client", "version": "2.0.0"},
),
Traces(
timestamp=now - timedelta(seconds=1),
@@ -1077,6 +1097,7 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"host.name": "linux-001",
"cloud.provider": "integration",
"cloud.account.id": "001",
"scope.scope.version": "corrupt_data",
},
attributes={
"message.type": "SENT",
@@ -1084,7 +1105,10 @@ def generate_traces_with_corrupt_metadata() -> list[Traces]:
"messaging.message.id": "001",
"duration_nano": "corrupt_data",
"id": 1,
"scope": "corrupt_data",
"scope.attributes.name": "corrupt_data",
},
scope={"name": "io.signoz.messaging", "version": "3.0.0"},
),
]

View File

@@ -302,6 +302,7 @@ class Traces(ABC):
db_operation: str
has_error: bool
is_remote: str
scope_json: dict[str, Any]
resource: list[TracesResource]
tag_attributes: list[TracesTagAttributes]
@@ -327,6 +328,7 @@ class Traces(ABC):
links: list[TracesLink] = [],
trace_state: str = "",
flags: np.uint32 = 0,
scope: dict[str, Any] = {},
resource_write_mode: Literal["legacy_only", "dual_write"] = "dual_write",
) -> None:
if timestamp is None:
@@ -408,6 +410,33 @@ class Traces(ABC):
# Calculate resource fingerprint
self.resource_fingerprint = LogsOrTracesFingerprint(self.resources_string).calculate()
# Process scope mirroring the InstrumentationScope on the OTLP span.
scope_name = scope.get("name", "")
scope_version = scope.get("version", "")
scope_string = {k: str(v) for k, v in scope.get("attributes", {}).items()}
self.scope_json = {
"name": scope_name,
"version": scope_version,
"attributes": scope_string,
}
scope_keys = {"scope.name": scope_name, "scope.version": scope_version}
scope_keys.update(scope_string)
for k, v in scope_keys.items():
if v == "":
continue
self.tag_attributes.append(
TracesTagAttributes(
timestamp=timestamp,
tag_key=k,
tag_type="scope",
tag_data_type="string",
string_value=v,
number_value=None,
)
)
self.attribute_keys.append(TracesResourceOrAttributeKeys(name=k, datatype="string", tag_type="scope"))
# Process attributes by type and populate custom fields
self.attribute_string = {}
self.attributes_number = {}
@@ -659,6 +688,7 @@ class Traces(ABC):
self.has_error,
self.is_remote,
self.resource_json,
self.scope_json,
],
dtype=object,
)
@@ -689,6 +719,7 @@ class Traces(ABC):
attributes=data.get("attributes", {}),
trace_state=data.get("trace_state", ""),
flags=data.get("flags", 0),
scope=data.get("scope", {}),
)
@classmethod
@@ -828,6 +859,7 @@ def insert_traces_to_clickhouse(conn, traces: list[Traces]) -> None:
"has_error",
"is_remote",
"resource",
"scope",
],
data=[trace.np_arr() for trace in traces],
)

View File

@@ -2,10 +2,12 @@ from collections.abc import Callable
from datetime import UTC, datetime
from http import HTTPStatus
import pytest
from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.metadata import get_field_keys, get_field_values
from fixtures.querierai import ai_trace
from fixtures.metadata import AttributesMetadata, get_field_keys, get_field_values
from fixtures.querierai import ai_trace, ai_trace_mixed_spans
from fixtures.traces import Traces
AI_KEYS_PATH = "/api/v1/ai_observability/fields/keys"
@@ -106,20 +108,94 @@ def test_ai_field_values_suggests_ingested_attribute_values(
assert values["stringValues"] == ["gpt-it-values"], values
def test_ai_field_values_reject_existing_query(
@pytest.mark.parametrize(
"existing_query,search_text,expected",
[
pytest.param(None, "", {"ai-rel-a", "ai-rel-b", "ai-rel-c"}, id="no_query_scopes_to_gen_ai_spans"),
pytest.param("gen_ai.user.id = 'alice'", "", {"ai-rel-a"}, id="span_filter_narrows_under_the_gate"),
pytest.param("llm_call_count > 0", "", {"ai-rel-a", "ai-rel-b", "ai-rel-c"}, id="pure_trace_aggregate_filter_is_stripped"),
pytest.param("llm_call_count > 0 AND gen_ai.user.id = 'alice'", "", {"ai-rel-a"}, id="mixed_filter_keeps_only_the_span_part"),
pytest.param(
"llm_call_count > 0 OR gen_ai.user.id = 'alice'",
"",
{"ai-rel-a", "ai-rel-b", "ai-rel-c"},
id="class_mixing_or_drops_the_filter_not_the_request",
),
pytest.param(
"gen_ai.user.id = ",
"",
{"ai-rel-a", "ai-rel-b", "ai-rel-c"},
id="unparseable_filter_falls_back_to_the_gate",
),
pytest.param(None, "ai-rel-a", {"ai-rel-a"}, id="search_text_narrows_related_values"),
# http.request.method lives on the root span's metadata row, gen_ai.* on
# the LLM/tool/agent rows; rows are per span-shape, so the gate AND a
# cross-span attribute filter can match no single row
pytest.param("http.request.method = 'POST'", "", set(), id="cross_span_attribute_filter_matches_no_row"),
],
)
def test_ai_field_values_related_values(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
insert_traces: Callable[[list[Traces]], None],
insert_attributes_metadata: Callable[[list[AttributesMetadata]], None],
existing_query: str | None,
search_text: str,
expected: set[str],
) -> None:
now = datetime.now(tz=UTC).replace(second=0, microsecond=0)
# existingQuery key resolution reads the trace keys tables, not
# attributes_metadata; a mixed trace registers the gate keys (model/tool/
# agent) plus gen_ai.user.id and http.request.method
insert_traces(ai_trace_mixed_spans(now=now, service="ai-rel-a", user="alice"))
# related values are served from attributes_metadata; one row per gate key,
# the traces row without any gate attribute and the logs row (wrong
# data_source, gate attribute present) must never surface
insert_attributes_metadata(
[
AttributesMetadata(
data_source="traces",
resource_attributes={"service.name": "ai-rel-a"},
attributes={"gen_ai.request.model": "gpt-rel", "gen_ai.user.id": "alice"},
),
AttributesMetadata(
data_source="traces",
resource_attributes={"service.name": "ai-rel-b"},
attributes={"gen_ai.tool.name": "get_weather", "gen_ai.user.id": "bob"},
),
AttributesMetadata(
data_source="traces",
resource_attributes={"service.name": "ai-rel-c"},
attributes={"gen_ai.agent.name": "chat-agent"},
),
AttributesMetadata(
data_source="traces",
resource_attributes={"service.name": "plain-rel"},
attributes={"http.request.method": "POST"},
),
AttributesMetadata(
data_source="logs",
resource_attributes={"service.name": "ai-rel-logs"},
attributes={"gen_ai.request.model": "gpt-rel"},
),
]
)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = get_field_values(
signoz,
token,
{"name": "gen_ai.request.model", "existingQuery": "service.name = 'ai-it-values'"},
AI_VALUES_PATH,
)
assert response.status_code == HTTPStatus.BAD_REQUEST, response.text
params = {"name": "service.name", "searchText": search_text}
if existing_query is not None:
params["existingQuery"] = existing_query
response = get_field_values(signoz, token, params, AI_VALUES_PATH)
assert response.status_code == HTTPStatus.OK, response.text
assert response.json()["status"] == "success"
related = response.json()["data"]["values"].get("relatedValues") or []
assert set(related) == expected, related
def test_ai_field_values_of_computed_aggregate_are_empty(

View File

@@ -1240,6 +1240,13 @@ def test_traces_list_span_scope(
lambda x: {"duration_nano": int(x[1].duration_nano), "span_id": x[1].span_id, "timestamp": format_timestamp(x[1].timestamp), "trace_id": x[1].trace_id},
id="select_attribute_duration_order_intrinsic",
),
# Case 9: filter on the intrinsic scope.version. Only x[1] should match.
pytest.param(
BuilderQuery(signal="traces", name="A", select_fields=[TelemetryFieldKey("timestamp")], filter_expression="scope.version = '1.0.0'", limit=1),
HTTPStatus.OK,
lambda x: {"span_id": x[1].span_id, "timestamp": format_timestamp(x[1].timestamp), "trace_id": x[1].trace_id},
id="filter_scope_version",
),
],
)
def test_traces_list_with_corrupt_data(
@@ -1283,6 +1290,168 @@ def test_traces_list_with_corrupt_data(
assert get_rows(response)[0]["data"] == expected(traces)
@pytest.mark.parametrize(
"filter_expression,expected_indices",
[
# Intrinsic scope.name / scope.version resolve to the JSON sub-columns.
pytest.param("scope.name = 'io.signoz.payment'", [1], id="intrinsic_scope_name"),
pytest.param("scope.version = '2.3.1'", [0], id="intrinsic_scope_version"),
# A scope attribute resolves against the scope JSON column's attributes.
pytest.param("scope.telemetry.sdk.language = 'python'", [1], id="scope_attribute"),
# A scope attribute whose own name carries a `scope.` prefix. `scope.prefixed`
# normalizes to {prefixed, scope} and must still resolve to the attribute.
pytest.param("scope.prefixed = 'prefixed-val'", [0], id="scope_prefixed_attribute"),
# `env.tier` is a span attribute on span 0 and a scope attribute on
# span 1. Unprefixed -> no explicit context, so it is checked in every
# applicable context (attribute OR scope) and both spans match.
pytest.param("env.tier = 'gold'", [0, 1], id="bare_cross_context"),
# The explicit `scope.` prefix forces scope context only, so span 0's
# span attribute is ignored — only span 1 matches.
pytest.param("scope.env.tier = 'gold'", [1], id="scope_prefixed_cross_context"),
# `scope.name` names both homes it can resolve to: the declared scope.name field
# (span 0) and a same-named `name` scope attribute (span 1), the same way any
# other name colliding across contexts unions. `scope.attribute.name` addresses
# the attribute alone.
pytest.param("scope.name = 'io.signoz.checkout'", [0, 1], id="scope_name_unions_attribute"),
# The `scope.name` spelling is also a real stored key: span 2 carries a span
# attribute literally named `scope.name`, so it matches too.
pytest.param("scope.name = 'attr-scope-name'", [2], id="scope_name_matches_stored_spelling"),
# The explicit `scope.attribute.` prefix addresses the scope attribute alone, without
# the declared path. Span 1 has a `name` scope attribute = 'io.signoz.checkout'.
pytest.param("scope.attribute.name = 'io.signoz.checkout'", [1], id="scope_attribute_name"),
# `version` as a scope attribute: no span carries one (span 1's 4.5.6 is the declared
# scope.version, not a scope attribute), so this matches nothing.
pytest.param("scope.attribute.version = '4.5.6'", [], id="scope_attribute_version_none"),
# An unprefixed `name` is checked in every applicable context: the span `name`
# column (span 2) and a `name` scope attribute (span 1). It does not reach the
# declared scope.name field (span 0), which only the `scope.` prefix addresses.
pytest.param("name = 'io.signoz.checkout'", [1, 2], id="bare_name_unions_scope_attribute"),
# A value that no resolvable key holds (scope.name/scope.version field,
# a `name`/`version` scope attribute, or a same-named attribute/resource)
# returns nothing.
pytest.param("scope.version = 'corrupt_data'", [], id="scope_version_no_match"),
pytest.param("scope.name = 'corrupt_data'", [], id="scope_name_no_match"),
],
)
def test_traces_list_with_scope_filter(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
insert_traces: Callable[[list[Traces]], None],
filter_expression: str,
expected_indices: list[int],
) -> None:
"""
Setup three spans with different scope key resolution:
- x[0]: scope.name/version 'io.signoz.checkout'/'2.3.1'; span attribute
env.tier='gold'.
- x[1]: scope.name/version 'io.signoz.payment'/'4.5.6'; scope attributes
telemetry.sdk.language='python', env.tier='gold', and a `name` scope
attribute colliding with x[0]'s scope.name value.
- x[2]: span name 'io.signoz.checkout' (colliding with x[0]'s scope.name
value) and a span attribute literally named `scope.name`.
Tests:
- Filtering on scope.name / scope.version / a scope attribute.
- An unprefixed key is resolved across contexts (scope checked alongside
attribute / intrinsic), while a `scope.`-prefixed key is scope-only.
- `scope.name`/`scope.version` name every home they resolve to: the declared JSON
sub-column and a same-named `name`/`version` scope attribute. The explicit
`scope.attribute.` prefix addresses the attribute alone.
- a bare `name` reaches the span `name` column and a `name` scope attribute, but
never the declared scope.name field.
"""
now = datetime.now(tz=UTC).replace(microsecond=0)
trace_id = TraceIdGenerator.trace_id()
span_ids = [TraceIdGenerator.span_id() for _ in range(3)]
traces = [
Traces(
timestamp=now - timedelta(seconds=4),
duration=timedelta(seconds=2),
trace_id=trace_id,
span_id=span_ids[0],
parent_span_id="",
name="GET /checkout",
kind=TracesKind.SPAN_KIND_SERVER,
status_code=TracesStatusCode.STATUS_CODE_OK,
resources={"service.name": "checkout"},
attributes={"http.request.method": "GET", "env.tier": "gold"},
scope={
"name": "io.signoz.checkout",
"version": "2.3.1",
# a scope attribute whose own name carries a `scope.` prefix
"attributes": {"telemetry.sdk.language": "go", "scope.prefixed": "prefixed-val"},
},
),
Traces(
timestamp=now - timedelta(seconds=2),
duration=timedelta(seconds=1),
trace_id=trace_id,
span_id=span_ids[1],
parent_span_id="",
name="POST /pay",
kind=TracesKind.SPAN_KIND_SERVER,
status_code=TracesStatusCode.STATUS_CODE_OK,
resources={"service.name": "payment"},
attributes={"http.request.method": "POST"},
# env.tier is a scope attribute here (cross-context with span 0);
# `name` is a scope attribute colliding with span 0's scope.name.
scope={
"name": "io.signoz.payment",
"version": "4.5.6",
"attributes": {
"telemetry.sdk.language": "python",
"env.tier": "gold",
"name": "io.signoz.checkout",
},
},
),
Traces(
timestamp=now - timedelta(seconds=1),
duration=timedelta(seconds=1),
trace_id=trace_id,
span_id=span_ids[2],
parent_span_id="",
# span name collides with span 0's scope.name value
name="io.signoz.checkout",
kind=TracesKind.SPAN_KIND_SERVER,
status_code=TracesStatusCode.STATUS_CODE_OK,
resources={"service.name": "probe"},
# a span attribute named `scope.name`
attributes={"scope.name": "attr-scope-name"},
scope={"name": "span-gamma", "version": "9.9.9"},
),
]
insert_traces(traces)
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
start_ms = int((now - timedelta(minutes=1)).timestamp() * 1000)
end_ms = int((now + timedelta(seconds=1)).timestamp() * 1000)
response = make_query_request(
signoz,
token,
start_ms=start_ms,
end_ms=end_ms,
request_type=RequestType.RAW,
queries=[
BuilderQuery(
signal="traces",
name="A",
select_fields=[TelemetryFieldKey("timestamp")],
filter_expression=filter_expression,
limit=10,
).to_dict()
],
)
assert response.status_code == HTTPStatus.OK, response.text
got_span_ids = {row["data"]["span_id"] for row in get_rows(response)}
expected_span_ids = {traces[i].span_id for i in expected_indices}
assert got_span_ids == expected_span_ids
@pytest.mark.parametrize("surface", ["filter", "select", "order"])
def test_traces_list_unknown_span_context_synthesizes(
signoz: types.SigNoz,