Compare commits

..

1 Commits

Author SHA1 Message Date
srikanthccv
38a1711ee8 test(querier): pin explicit context resolution under ambiguous names
One name can exist in more than one place. `name` is a span column and a
span attribute. `severity_text` is a log column and a log attribute. An
attribute can have two data types. `service.name` is a resource attribute
and a span or log attribute. These tests record what the query builder
does for each shape in a filter, EXISTS, a group by, an order by, an
aggregation argument, and a raw select. A change to name resolution then
fails here first.

- A key with an explicit context reads that context only. A bare key with
  more than one reading returns an ambiguity warning. An `attribute.` key
  returns the warning when the attribute has two data types.
- A bare key that is a column and an attribute reads both in a filter. It
  orders, groups, and counts by the column only. A string operand matches
  a number attribute through a text cast.
- A bare key that is a resource attribute and an attribute reads the
  resource attribute in a filter and in a raw select. The filter returns a
  warning.
- An `attribute.` key in an order by sorts by the attribute on traces and
  by the column on logs.
- A key under the signal's own context that exists only as an attribute
  reads the attribute. On logs it also reads the body JSON path. A
  `scope.` key on logs resolves through metadata only. When metadata does
  not report the key, the query fails with "key not found". This is also
  true for the declared path `scope.name`.

Assisted-by: Claude Fable 5.1
Claude-Session: https://claude.ai/code/session_01RSnZFLSfyi5S4QYQDcxHeW
2026-09-09 14:48:32 +05:30
23 changed files with 535 additions and 428 deletions

View File

@@ -8349,8 +8349,6 @@ components:
$ref: '#/components/schemas/RuletypesAlertState'
overallStateChanged:
type: boolean
relatedAITracesLink:
type: string
relatedLogsLink:
type: string
relatedTracesLink:
@@ -8394,8 +8392,6 @@ components:
$ref: '#/components/schemas/Querybuildertypesv5Label'
nullable: true
type: array
relatedAITracesLink:
type: string
relatedLogsLink:
type: string
relatedTracesLink:
@@ -8501,7 +8497,6 @@ components:
- TRACES_BASED_ALERT
- LOGS_BASED_ALERT
- EXCEPTIONS_BASED_ALERT
- AI_TRACES_BASED_ALERT
type: string
RuletypesBasicRuleThreshold:
properties:

View File

@@ -9610,10 +9610,6 @@ export interface RulestatehistorytypesGettableRuleStateHistoryDTO {
* @type boolean
*/
overallStateChanged: boolean;
/**
* @type string
*/
relatedAITracesLink?: string;
/**
* @type string
*/
@@ -9662,10 +9658,6 @@ export interface RulestatehistorytypesGettableRuleStateHistoryContributorDTO {
* @type array,null
*/
labels: Querybuildertypesv5LabelDTO[] | null;
/**
* @type string
*/
relatedAITracesLink?: string;
/**
* @type string
*/
@@ -9761,7 +9753,6 @@ export enum RuletypesAlertTypeDTO {
TRACES_BASED_ALERT = 'TRACES_BASED_ALERT',
LOGS_BASED_ALERT = 'LOGS_BASED_ALERT',
EXCEPTIONS_BASED_ALERT = 'EXCEPTIONS_BASED_ALERT',
AI_TRACES_BASED_ALERT = 'AI_TRACES_BASED_ALERT',
}
export enum RuletypesMatchTypeDTO {
at_least_once = 'at_least_once',

View File

@@ -12,32 +12,25 @@ import (
// PrepareParamsForTracesV5 returns the traces explorer query params for the
// given range and filter; the traces explorer writes its time params in
// nanoseconds. queryType is builder_ai_query for the AI observability explorer.
func PrepareParamsForTracesV5(start, end time.Time, whereClause string, queryType qbtypes.QueryType) url.Values {
return prepareExplorerParams("traces", queryType, start.UnixNano(), end.UnixNano(), whereClause)
// nanoseconds.
func PrepareParamsForTracesV5(start, end time.Time, whereClause string) url.Values {
return prepareExplorerParams("traces", start.UnixNano(), end.UnixNano(), whereClause)
}
// PrepareParamsForLogsV5 returns the logs explorer query params for the given
// range and filter; the logs explorer writes its time params in milliseconds.
func PrepareParamsForLogsV5(start, end time.Time, whereClause string) url.Values {
return prepareExplorerParams("logs", qbtypes.QueryTypeBuilder, start.UnixMilli(), end.UnixMilli(), whereClause)
return prepareExplorerParams("logs", start.UnixMilli(), end.UnixMilli(), whereClause)
}
// The end link is double encoded because otherwise a filter expression with `%` somewhere in it breaks.
func prepareExplorerParams(dataSource string, queryType qbtypes.QueryType, start, end int64, whereClause string) url.Values {
// builder_query is the explorer default, so it is left out to keep existing links unchanged
builderQueryType := ""
if queryType != qbtypes.QueryTypeBuilder {
builderQueryType = queryType.StringValue()
}
func prepareExplorerParams(dataSource string, start, end int64, whereClause string) url.Values {
urlData := URLShareableCompositeQuery{
QueryType: "builder",
Builder: URLShareableBuilderQuery{
QueryData: []LinkQuery{{
DataSource: dataSource,
BuilderQueryType: builderQueryType,
Filter: &FilterExpression{Expression: whereClause},
DataSource: dataSource,
Filter: &FilterExpression{Expression: whereClause},
}},
QueryFormulas: make([]string, 0),
},
@@ -54,8 +47,7 @@ func prepareExplorerParams(dataSource string, queryType qbtypes.QueryType, start
// BuilderQueryForSignal returns the filter expression and group-by keys of the
// builder query for the given signal, or found=false when the composite query
// has no builder query for it (e.g. PromQL or ClickHouse SQL alerts). AI trace
// queries (builder_ai_query) count as trace builder queries.
// has no builder query for it (e.g. PromQL or ClickHouse SQL alerts).
// TODO(srikanthccv): re-visit this and support multiple queries.
func BuilderQueryForSignal(queries []qbtypes.QueryEnvelope, signal telemetrytypes.Signal) (string, []qbtypes.GroupByKey, bool) {
switch signal {
@@ -71,7 +63,7 @@ func builderQueryForSignal[T any](queries []qbtypes.QueryEnvelope, signal teleme
var q qbtypes.QueryBuilderQuery[T]
found := false
for _, query := range queries {
if query.Type != qbtypes.QueryTypeBuilder && query.Type != qbtypes.QueryTypeBuilderAI {
if query.Type != qbtypes.QueryTypeBuilder {
continue
}
if spec, ok := query.Spec.(qbtypes.QueryBuilderQuery[T]); ok {

View File

@@ -30,15 +30,6 @@ func TestBuilderQueryForSignal(t *testing.T) {
Type: qbtypes.QueryTypePromQL,
Spec: qbtypes.PromQuery{Name: "C"},
}
aiTraceQuery := qbtypes.QueryEnvelope{
Type: qbtypes.QueryTypeBuilderAI,
Spec: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Name: "D",
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{Expression: "trace.input_tokens > 1000"},
GroupBy: []qbtypes.GroupByKey{{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "session.id"}}},
},
}
t.Run("logs query among mixed queries", func(t *testing.T) {
filterExpr, groupBy, found := BuilderQueryForSignal([]qbtypes.QueryEnvelope{promQuery, logQuery, traceQuery}, telemetrytypes.SignalLogs)
@@ -55,14 +46,6 @@ func TestBuilderQueryForSignal(t *testing.T) {
assert.Empty(t, groupBy)
})
t.Run("ai trace query counts as traces", func(t *testing.T) {
filterExpr, groupBy, found := BuilderQueryForSignal([]qbtypes.QueryEnvelope{logQuery, aiTraceQuery}, telemetrytypes.SignalTraces)
require.True(t, found)
assert.Equal(t, "trace.input_tokens > 1000", filterExpr)
require.Len(t, groupBy, 1)
assert.Equal(t, "session.id", groupBy[0].Name)
})
t.Run("no builder query for signal", func(t *testing.T) {
_, _, found := BuilderQueryForSignal([]qbtypes.QueryEnvelope{traceQuery}, telemetrytypes.SignalLogs)
assert.False(t, found)

View File

@@ -13,9 +13,8 @@ type FilterExpression struct {
// LinkQuery carries the only fields the explorer pages read from a shared
// link; the frontend fills in the rest of the query shape with defaults.
type LinkQuery struct {
DataSource string `json:"dataSource"`
BuilderQueryType string `json:"builderQueryType,omitempty"`
Filter *FilterExpression `json:"filter,omitempty"`
DataSource string `json:"dataSource"`
Filter *FilterExpression `json:"filter,omitempty"`
}
type URLShareableBuilderQuery struct {

View File

@@ -114,7 +114,6 @@ func (h *handler) GetRuleHistoryTimeline(w http.ResponseWriter, r *http.Request)
Fingerprint: item.Fingerprint,
Value: item.Value,
RelatedTracesLink: item.RelatedTracesLink,
RelatedAITracesLink: item.RelatedAITracesLink,
RelatedLogsLink: item.RelatedLogsLink,
})
}
@@ -152,12 +151,11 @@ func (h *handler) GetRuleHistoryContributors(w http.ResponseWriter, r *http.Requ
converted := make([]rulestatehistorytypes.GettableRuleStateHistoryContributor, 0, len(res))
for _, item := range res {
converted = append(converted, rulestatehistorytypes.GettableRuleStateHistoryContributor{
Fingerprint: item.Fingerprint,
Labels: item.Labels.ToQBLabels(),
Count: item.Count,
RelatedTracesLink: item.RelatedTracesLink,
RelatedAITracesLink: item.RelatedAITracesLink,
RelatedLogsLink: item.RelatedLogsLink,
Fingerprint: item.Fingerprint,
Labels: item.Labels.ToQBLabels(),
Count: item.Count,
RelatedTracesLink: item.RelatedTracesLink,
RelatedLogsLink: item.RelatedLogsLink,
})
}
render.Success(w, http.StatusOK, converted)

View File

@@ -41,8 +41,7 @@ func (m *module) relatedLinkBuilderForRule(ctx context.Context, orgID valuer.UUI
return nil
}
signal, ok := relatedLinkSignal(rule.AlertType)
if !ok {
if rule.AlertType != ruletypes.AlertTypeLogs && rule.AlertType != ruletypes.AlertTypeTraces {
return nil
}
if rule.RuleCondition == nil || rule.RuleCondition.CompositeQuery == nil {
@@ -63,6 +62,10 @@ func (m *module) relatedLinkBuilderForRule(ctx context.Context, orgID valuer.UUI
builder.evaluation = ruletypes.RollingWindow{EvalWindow: evalWindow}
}
signal := telemetrytypes.SignalLogs
if rule.AlertType == ruletypes.AlertTypeTraces {
signal = telemetrytypes.SignalTraces
}
// links are still built from the labels alone when the rule has no builder
// query for the signal (e.g. ClickHouse SQL alerts)
builder.filterExpr, builder.groupBy, _ = contextlinks.BuilderQueryForSignal(rule.RuleCondition.CompositeQuery.Queries, signal)
@@ -81,35 +84,21 @@ func (b *relatedLinkBuilder) queryWindow(unixMilli int64) (time.Time, time.Time)
return start.Add(-3 * time.Minute), end
}
// links returns the explorer query params for the given entry labels and time
// range.
func (b *relatedLinkBuilder) links(labels rulestatehistorytypes.LabelsString, start, end time.Time) rulestatehistorytypes.RelatedLinks {
// links returns the encoded logs and traces explorer query params for the
// given entry labels and time range; at most one of the two is non-empty.
func (b *relatedLinkBuilder) links(labels rulestatehistorytypes.LabelsString, start, end time.Time) (string, string) {
lbls := map[string]string{}
if err := json.Unmarshal([]byte(labels), &lbls); err != nil {
return rulestatehistorytypes.RelatedLinks{}
return "", ""
}
whereClause := contextlinks.PrepareFilterExpression(lbls, b.filterExpr, b.groupBy)
switch b.alertType {
case ruletypes.AlertTypeLogs:
return rulestatehistorytypes.RelatedLinks{RelatedLogsLink: contextlinks.PrepareParamsForLogsV5(start, end, whereClause).Encode()}
return contextlinks.PrepareParamsForLogsV5(start, end, whereClause).Encode(), ""
case ruletypes.AlertTypeTraces:
return rulestatehistorytypes.RelatedLinks{RelatedTracesLink: contextlinks.PrepareParamsForTracesV5(start, end, whereClause, qbtypes.QueryTypeBuilder).Encode()}
case ruletypes.AlertTypeAITraces:
return rulestatehistorytypes.RelatedLinks{RelatedAITracesLink: contextlinks.PrepareParamsForTracesV5(start, end, whereClause, qbtypes.QueryTypeBuilderAI).Encode()}
return "", contextlinks.PrepareParamsForTracesV5(start, end, whereClause).Encode()
}
return rulestatehistorytypes.RelatedLinks{}
}
// relatedLinkSignal returns the explorer signal that related links open for
// the alert type, or ok=false when the alert type has none (e.g. metrics).
func relatedLinkSignal(alertType ruletypes.AlertType) (telemetrytypes.Signal, bool) {
switch alertType {
case ruletypes.AlertTypeLogs:
return telemetrytypes.SignalLogs, true
case ruletypes.AlertTypeTraces, ruletypes.AlertTypeAITraces:
return telemetrytypes.SignalTraces, true
}
return telemetrytypes.SignalUnspecified, false
return "", ""
}

View File

@@ -34,7 +34,7 @@ func (m *module) GetHistoryTimeline(ctx context.Context, orgID valuer.UUID, rule
if builder := m.relatedLinkBuilderForRule(ctx, orgID, ruleID); builder != nil {
for idx := range items {
start, end := builder.queryWindow(items[idx].UnixMilli)
items[idx].RelatedLinks = builder.links(items[idx].Labels, start, end)
items[idx].RelatedLogsLink, items[idx].RelatedTracesLink = builder.links(items[idx].Labels, start, end)
}
}
@@ -60,7 +60,7 @@ func (m *module) GetHistoryContributors(ctx context.Context, orgID valuer.UUID,
// span it too instead of a single evaluation window
start, end := time.UnixMilli(query.Start), time.UnixMilli(query.End)
for idx := range contributors {
contributors[idx].RelatedLinks = builder.links(contributors[idx].Labels, start, end)
contributors[idx].RelatedLogsLink, contributors[idx].RelatedTracesLink = builder.links(contributors[idx].Labels, start, end)
}
}

View File

@@ -830,12 +830,12 @@ func (aH *APIHandler) getRuleStateHistory(w http.ResponseWriter, r *http.Request
whereClause := contextlinks.PrepareFilterExpression(lbls, filterExpr, q.GroupBy)
res.Items[idx].RelatedLogsLink = contextlinks.PrepareParamsForLogsV5(start, end, whereClause).Encode()
} else if rule.AlertType == ruletypes.AlertTypeTraces || rule.AlertType == ruletypes.AlertTypeAITraces {
} else if rule.AlertType == ruletypes.AlertTypeTraces {
// TODO(srikanthccv): re-visit this and support multiple queries
var q qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]
for _, query := range rule.RuleCondition.CompositeQuery.Queries {
if query.Type == qbtypes.QueryTypeBuilder || query.Type == qbtypes.QueryTypeBuilderAI {
if query.Type == qbtypes.QueryTypeBuilder {
switch spec := query.Spec.(type) {
case qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]:
q = spec
@@ -849,7 +849,7 @@ func (aH *APIHandler) getRuleStateHistory(w http.ResponseWriter, r *http.Request
}
whereClause := contextlinks.PrepareFilterExpression(lbls, filterExpr, q.GroupBy)
res.Items[idx].RelatedTracesLink = contextlinks.PrepareParamsForTracesV5(start, end, whereClause, rule.AlertType.BuilderQueryType()).Encode()
res.Items[idx].RelatedTracesLink = contextlinks.PrepareParamsForTracesV5(start, end, whereClause).Encode()
}
}
}

View File

@@ -420,7 +420,7 @@ func (r *BaseRule) ShouldSkipNewGroups() bool {
func (r *BaseRule) isFilterNewSeriesSupported() bool {
if r.ruleCondition.CompositeQuery.QueryType == ruletypes.QueryTypeBuilder {
for _, query := range r.ruleCondition.CompositeQuery.Queries {
if query.Type != qbtypes.QueryTypeBuilder && query.Type != qbtypes.QueryTypeBuilderAI {
if query.Type != qbtypes.QueryTypeBuilder {
continue
}
switch query.Spec.(type) {

View File

@@ -7,7 +7,6 @@ import (
"testing"
"time"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/SigNoz/signoz/pkg/instrumentation/instrumentationtest"
@@ -165,24 +164,6 @@ type filterNewSeriesTestCase struct {
expectError bool
}
func TestBaseRule_IsFilterNewSeriesSupported(t *testing.T) {
postableRule := createPostableRule(&ruletypes.AlertCompositeQuery{
QueryType: ruletypes.QueryTypeBuilder,
Queries: []qbtypes.QueryEnvelope{{
Type: qbtypes.QueryTypeBuilderAI,
Spec: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Name: "A",
Signal: telemetrytypes.SignalTraces,
Aggregations: []qbtypes.TraceAggregation{{Expression: "max(trace.total_tokens)"}},
},
}},
})
rule, err := NewBaseRule("test-rule", valuer.GenerateUUID(), &postableRule, mustParseURL(t, "http://localhost:8080"), WithLogger(instrumentationtest.New().Logger()))
require.NoError(t, err)
assert.False(t, rule.isFilterNewSeriesSupported())
}
func TestBaseRule_FilterNewSeries(t *testing.T) {
defaultEvalTime := time.Unix(1700000000, 0)
defaultNewGroupEvalDelay := valuer.MustParseTextDuration("2m")

View File

@@ -9,7 +9,6 @@ import (
"github.com/SigNoz/signoz/pkg/instrumentation/instrumentationtest"
"github.com/SigNoz/signoz/pkg/querier"
"github.com/SigNoz/signoz/pkg/statementbuilder"
"github.com/SigNoz/signoz/pkg/statementbuilder/aistatementbuilder"
"github.com/SigNoz/signoz/pkg/statementbuilder/logsstatementbuilder"
"github.com/SigNoz/signoz/pkg/statementbuilder/metricsstatementbuilder"
"github.com/SigNoz/signoz/pkg/statementbuilder/tracesstatementbuilder"
@@ -128,40 +127,3 @@ func prepareQuerierForTraces(t *testing.T, telemetryStore telemetrystore.Telemet
0, // maxConcurrentQueries (0 means default)
)
}
func prepareQuerierForAITraces(t *testing.T, telemetryStore telemetrystore.TelemetryStore, keysMap map[string][]*telemetrytypes.TelemetryFieldKey) querier.Querier {
t.Helper()
providerSettings := instrumentationtest.New().ToProviderSettings()
metadataStore := telemetrytypestest.NewMockMetadataStore()
for _, keys := range keysMap {
for _, key := range keys {
key.Signal = telemetrytypes.SignalTraces
}
}
metadataStore.KeysMap = keysMap
fl := flaggertest.New(t)
aiTraceStmtBuilder, err := aistatementbuilder.NewFactory(telemetryStore, metadataStore, fl).New(context.Background(), providerSettings, statementbuilder.Config{})
require.NoError(t, err)
return querier.New(
providerSettings,
telemetryStore,
metadataStore,
nil, // prometheus
nil, // promV2
nil, // traceStmtBuilder
aiTraceStmtBuilder,
nil, // logStmtBuilder
nil, // auditStmtBuilder
nil, // metricStmtBuilder
nil, // meterStmtBuilder
nil, // traceOperatorStmtBuilder
nil, // bucketCache
fl,
0,
0, // maxConcurrentQueries (0 means default)
)
}

View File

@@ -132,7 +132,7 @@ func (r *ThresholdRule) prepareParamsForTraces(ctx context.Context, ts time.Time
whereClause := contextlinks.PrepareFilterExpression(lbls.Map(), filterExpr, groupBy)
return contextlinks.PrepareParamsForTracesV5(start, end, whereClause, r.typ.BuilderQueryType())
return contextlinks.PrepareParamsForTracesV5(start, end, whereClause)
}
func (r *ThresholdRule) buildAndRunQuery(ctx context.Context, orgID valuer.UUID, ts time.Time) (ruletypes.Vector, error) {
@@ -308,14 +308,10 @@ func (r *ThresholdRule) Eval(ctx context.Context, ts time.Time) (int, error) {
// is used alert grouping, and we want to group alerts with the same
// label set, but different timestamps, together.
switch r.typ {
case ruletypes.AlertTypeTraces, ruletypes.AlertTypeAITraces:
case ruletypes.AlertTypeTraces:
params := r.prepareParamsForTraces(ctx, ts, smpl.Metric)
if len(params) > 0 {
explorerPath := "traces-explorer"
if r.typ == ruletypes.AlertTypeAITraces {
explorerPath = "ai-observability/explorer"
}
link := r.ExternalURL(explorerPath, params)
link := r.ExternalURL("traces-explorer", params)
r.logger.InfoContext(ctx, "adding traces link to annotations", slog.String("annotation.link", link))
annotations = append(annotations, ruletypes.Label{Name: ruletypes.AnnotationRelatedTraces, Value: link})
}

View File

@@ -916,104 +916,6 @@ func TestThresholdRuleTracesLink(t *testing.T) {
}
}
func TestThresholdRuleAITracesLink(t *testing.T) {
postableRule := ruletypes.PostableRule{
AlertName: "AI traces link test",
AlertType: ruletypes.AlertTypeAITraces,
RuleType: ruletypes.RuleTypeThreshold,
Evaluation: &ruletypes.EvaluationEnvelope{Kind: ruletypes.RollingEvaluation, Spec: ruletypes.RollingWindow{
EvalWindow: valuer.MustParseTextDuration("5m"),
Frequency: valuer.MustParseTextDuration("1m"),
}},
RuleCondition: &ruletypes.RuleCondition{
CompositeQuery: &ruletypes.AlertCompositeQuery{
QueryType: ruletypes.QueryTypeBuilder,
Queries: []qbtypes.QueryEnvelope{{
Type: qbtypes.QueryTypeBuilderAI,
Spec: qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
Name: "A",
StepInterval: qbtypes.Step{Duration: time.Minute},
Aggregations: []qbtypes.TraceAggregation{{
Expression: "count()",
}},
Signal: telemetrytypes.SignalTraces,
Filter: &qbtypes.Filter{
Expression: "service.name = 'llm-gateway'",
},
},
}},
},
},
}
cols := make([]cmock.ColumnType, 0)
cols = append(cols, cmock.ColumnType{Name: "value", Type: "Float64"})
cols = append(cols, cmock.ColumnType{Name: "attr", Type: "String"})
cols = append(cols, cmock.ColumnType{Name: "timestamp", Type: "DateTime"})
keysMap := map[string][]*telemetrytypes.TelemetryFieldKey{
"service.name": {
{
Name: "service.name",
FieldContext: telemetrytypes.FieldContextResource,
FieldDataType: telemetrytypes.FieldDataTypeString,
},
},
}
logger := instrumentationtest.New().Logger()
for idx, c := range testCases {
telemetryStore := telemetrystoretest.New(telemetrystore.Config{}, &queryMatcherAny{})
rows := cmock.NewRows(cols, c.values)
telemetryStore.Mock().
ExpectQuery("SELECT any").
WithArgs(nil, nil, nil, nil, nil, nil, nil, nil, nil, nil).
WillReturnRows(rows)
querier := prepareQuerierForAITraces(t, telemetryStore, keysMap)
postableRule.RuleCondition.CompareOperator = c.compareOperator
postableRule.RuleCondition.MatchType = c.matchType
postableRule.RuleCondition.Target = &c.target
postableRule.RuleCondition.CompositeQuery.Unit = c.yAxisUnit
postableRule.RuleCondition.TargetUnit = c.targetUnit
postableRule.RuleCondition.Thresholds = &ruletypes.RuleThresholdData{
Kind: ruletypes.BasicThresholdKind,
Spec: ruletypes.BasicRuleThresholds{
{
Name: postableRule.AlertName,
TargetValue: &c.target,
TargetUnit: c.targetUnit,
MatchType: c.matchType,
CompareOperator: c.compareOperator,
},
},
}
postableRule.Annotations = map[string]string{
"description": "This alert is fired when the defined metric (current value: {{$value}}) crosses the threshold ({{$threshold}})",
"summary": "The rule threshold is set to {{$threshold}}, and the observed metric value is {{$value}}",
}
externalURL := mustParseURL(t, "http://localhost:8080")
rule, err := NewThresholdRule("69", valuer.GenerateUUID(), &postableRule, querier, logger, externalURL)
require.NoError(t, err, "case %d", idx)
alertsFound, err := rule.Eval(context.Background(), time.Now())
require.NoError(t, err, "case %d", idx)
assert.Equal(t, c.expectAlerts, alertsFound, "case %d", idx)
for _, item := range rule.Active {
link := item.Annotations.Map()[ruletypes.AnnotationRelatedTraces]
assert.True(t, strings.HasPrefix(link, "http://localhost:8080/ai-observability/explorer?"), "case %d: %s", idx, link)
assert.Contains(t, link, "builder_ai_query", "case %d", idx)
assert.Contains(t, link, "llm-gateway", "case %d", idx)
}
}
}
func TestThresholdRuleLogsLink(t *testing.T) {
postableRule := ruletypes.PostableRule{
AlertName: "Logs link test",

View File

@@ -23,17 +23,15 @@ type GettableRuleStateHistory struct {
Fingerprint uint64 `json:"fingerprint" required:"true"`
Value float64 `json:"value" required:"true"`
RelatedTracesLink string `json:"relatedTracesLink,omitempty"`
RelatedAITracesLink string `json:"relatedAITracesLink,omitempty"`
RelatedLogsLink string `json:"relatedLogsLink,omitempty"`
}
type GettableRuleStateHistoryContributor struct {
Fingerprint uint64 `json:"fingerprint" required:"true"`
Labels []*qbtypes.Label `json:"labels" required:"true"`
Count uint64 `json:"count" required:"true"`
RelatedTracesLink string `json:"relatedTracesLink,omitempty"`
RelatedAITracesLink string `json:"relatedAITracesLink,omitempty"`
RelatedLogsLink string `json:"relatedLogsLink,omitempty"`
Fingerprint uint64 `json:"fingerprint" required:"true"`
Labels []*qbtypes.Label `json:"labels" required:"true"`
Count uint64 `json:"count" required:"true"`
RelatedTracesLink string `json:"relatedTracesLink,omitempty"`
RelatedLogsLink string `json:"relatedLogsLink,omitempty"`
}
type GettableRuleStateWindow struct {

View File

@@ -77,23 +77,16 @@ type RuleStateHistory struct {
Fingerprint uint64 `ch:"fingerprint"`
Value float64 `ch:"value"`
RelatedLinks
RelatedTracesLink string
RelatedLogsLink string
}
type RuleStateHistoryContributor struct {
Fingerprint uint64 `ch:"fingerprint"`
Labels LabelsString `ch:"labels"`
Count uint64 `ch:"count"`
RelatedLinks
}
// RelatedLinks holds the encoded explorer query params for a history entry;
// at most one field is non-empty.
type RelatedLinks struct {
RelatedTracesLink string
RelatedAITracesLink string
RelatedLogsLink string
Fingerprint uint64 `ch:"fingerprint"`
Labels LabelsString `ch:"labels"`
Count uint64 `ch:"count"`
RelatedTracesLink string
RelatedLogsLink string
}
type Store interface {

View File

@@ -24,7 +24,6 @@ const (
AlertTypeTraces AlertType = "TRACES_BASED_ALERT"
AlertTypeLogs AlertType = "LOGS_BASED_ALERT"
AlertTypeExceptions AlertType = "EXCEPTIONS_BASED_ALERT"
AlertTypeAITraces AlertType = "AI_TRACES_BASED_ALERT"
)
// Enum implements jsonschema.Enum; returns the acceptable values for AlertType.
@@ -34,19 +33,9 @@ func (AlertType) Enum() []any {
AlertTypeTraces,
AlertTypeLogs,
AlertTypeExceptions,
AlertTypeAITraces,
}
}
// BuilderQueryType returns the query type the alert type's builder queries
// carry; only AI trace alerts use builder_ai_query.
func (t AlertType) BuilderQueryType() qbtypes.QueryType {
if t == AlertTypeAITraces {
return qbtypes.QueryTypeBuilderAI
}
return qbtypes.QueryTypeBuilder
}
const (
DefaultSchemaVersion = "v1"
SchemaVersionV2Alpha1 = "v2alpha1"
@@ -417,11 +406,11 @@ func (r *PostableRule) Validate() error {
if r.AlertType != "" {
switch r.AlertType {
case AlertTypeMetric, AlertTypeTraces, AlertTypeLogs, AlertTypeExceptions, AlertTypeAITraces:
case AlertTypeMetric, AlertTypeTraces, AlertTypeLogs, AlertTypeExceptions:
default:
errs = append(errs, errors.NewInvalidInputf(errors.CodeInvalidInput,
"alertType: unsupported value %q; must be one of %q, %q, %q, %q, %q",
r.AlertType, AlertTypeMetric, AlertTypeTraces, AlertTypeLogs, AlertTypeExceptions, AlertTypeAITraces))
"alertType: unsupported value %q; must be one of %q, %q, %q, %q",
r.AlertType, AlertTypeMetric, AlertTypeTraces, AlertTypeLogs, AlertTypeExceptions))
}
}

View File

@@ -209,10 +209,6 @@ func TestValidate_PostableRule_Common(t *testing.T) {
name: "valid alertType EXCEPTIONS_BASED_ALERT",
json: patchJSON(validV1Builder(), `{"alertType": "EXCEPTIONS_BASED_ALERT"}`),
},
{
name: "valid alertType AI_TRACES_BASED_ALERT",
json: patchJSON(validV1Builder(), `{"alertType": "AI_TRACES_BASED_ALERT"}`),
},
{
name: "empty alertType is ok (optional)",
json: removeField(validV1Builder(), "alertType"),

View File

@@ -1,4 +1,4 @@
"""Seed data for the queriercommon keyless-semantics tests.
"""Seed data for the queriercommon keyless-semantics and explicit-context tests.
Three identities exist in every signal. GOLD and SILVER carry the test keys.
NONE carries no key at all. The tests assert which identities a filter
@@ -8,6 +8,7 @@ The attribute names are outside every semantic-convention family, so the
seeded data pins base behavior with any semconv overlay state.
"""
import json
from collections.abc import Callable, Generator
from datetime import UTC, datetime, timedelta
@@ -122,3 +123,103 @@ def keyless_series(insert_metrics: Callable[[list[Metrics]], None]) -> Generator
]
)
yield start, start + points * 60
EXPLICIT_PREFIX = "explicit-ctx"
# String attribute that identifies the row. It has one context only. Each
# assertion reads it back.
IDENTITY_KEY = "probe.id"
# Attribute with no column of the same name. It tests a key under the
# signal's own context that metadata does not know. On logs, the rows without
# the attribute have the value nested in the body JSON.
ATTRIBUTE_ONLY_KEY = "route.tag"
CONTESTED_VALUE = "checkout"
# Row identities. Each row shows where the contested value is:
# - COLUMN_ONLY: in the column (`name` on spans, `severity_text` on logs).
# - ATTRIBUTE_ONLY: in the string attribute with the same name.
# - BOTH: in the column and in the string attribute.
# - NEITHER: in none of them.
# - NUMBER_ATTRIBUTE: in a number attribute with the same name. Its data
# type is different from the column.
COLUMN_ONLY = f"{EXPLICIT_PREFIX}-column"
ATTRIBUTE_ONLY = f"{EXPLICIT_PREFIX}-attribute"
BOTH = f"{EXPLICIT_PREFIX}-both"
NEITHER = f"{EXPLICIT_PREFIX}-neither"
NUMBER_ATTRIBUTE = f"{EXPLICIT_PREFIX}-number"
NUMBER_VALUE = 42
# (identity, value in the column, value in the string attribute, value in
# the number attribute, resource service.name, attribute service.name,
# has route.tag, insert offset in seconds)
ROWS = [
(COLUMN_ONLY, True, False, False, "svc-a", None, True, 1),
(ATTRIBUTE_ONLY, False, True, False, "svc-b", "svc-a", False, 2),
(BOTH, True, True, False, "svc-a", "svc-a", True, 3),
(NEITHER, False, False, False, "svc-b", "svc-b", False, 4),
(NUMBER_ATTRIBUTE, False, False, True, "svc-b", None, False, 5),
]
# Logs only. The scope name is a declared path. A scope attribute also has
# the name `name`. A second scope attribute has a plain name.
SCOPE_NAME = "scope-a"
SCOPE_ATTRIBUTE_KEY = "env"
SCOPE_ATTRIBUTE_VALUE = "prod"
@pytest.fixture(name="ambiguous_rows", scope="function")
def ambiguous_rows(
insert_logs: Callable[[list[Logs]], None],
insert_traces: Callable[[list[Traces]], None],
) -> Generator[datetime]:
"""Inserts one span and one log for each identity. Every row has a
resource `service.name`. Some rows also have a span or log attribute
`service.name` with a different value. On logs, the rows without the
`route.tag` attribute have the value in the body JSON. Logs with the
column value have the scope name. Logs with the attribute value have the
scope attributes. Yields the base timestamp."""
now = datetime.now(tz=UTC).replace(microsecond=0) - timedelta(minutes=1)
insert_traces(
[
Traces(
timestamp=now - timedelta(seconds=offset),
duration=timedelta(milliseconds=10),
trace_id=TraceIdGenerator.trace_id(),
span_id=TraceIdGenerator.span_id(),
name=CONTESTED_VALUE if column else "other",
kind=TracesKind.SPAN_KIND_SERVER,
status_code=TracesStatusCode.STATUS_CODE_OK,
resources={"service.name": resource_service},
attributes={
IDENTITY_KEY: identity,
**({"name": CONTESTED_VALUE} if attribute else {}),
**({"name": NUMBER_VALUE} if number else {}),
**({"service.name": attribute_service} if attribute_service else {}),
**({ATTRIBUTE_ONLY_KEY: CONTESTED_VALUE} if tagged else {}),
},
)
for identity, column, attribute, number, resource_service, attribute_service, tagged, offset in ROWS
]
)
insert_logs(
[
Logs(
timestamp=now - timedelta(seconds=offset),
body=json.dumps({} if tagged else {"route": {"tag": CONTESTED_VALUE}}),
severity_text="ERROR" if column else "INFO",
scope_name=SCOPE_NAME if column else "",
scope_attributes={"name": CONTESTED_VALUE, SCOPE_ATTRIBUTE_KEY: SCOPE_ATTRIBUTE_VALUE} if attribute else {},
resources={"service.name": resource_service},
attributes={
IDENTITY_KEY: identity,
**({"severity_text": "ERROR"} if attribute else {}),
**({"severity_text": NUMBER_VALUE} if number else {}),
**({"service.name": attribute_service} if attribute_service else {}),
**({ATTRIBUTE_ONLY_KEY: CONTESTED_VALUE} if tagged else {}),
},
)
for identity, column, attribute, number, resource_service, attribute_service, tagged, offset in ROWS
]
)
yield now

View File

@@ -1,16 +0,0 @@
{"timestamp": "2026-01-29T10:00:00.000000Z", "duration": "PT2.5S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f601", "span_id": "c1b2c3d4e5f6a701", "parent_span_id": "", "name": "POST /chat", "kind": 2, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"http.request.method": "POST", "http.response.status_code": "200", "http.request.path": "/chat"}}
{"timestamp": "2026-01-29T10:00:00.200000Z", "duration": "PT2S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f601", "span_id": "d1b2c3d4e5f6a701", "parent_span_id": "c1b2c3d4e5f6a701", "name": "chat gpt-4o-mini", "kind": 3, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"gen_ai.system": "openai", "gen_ai.request.model": "gpt-4o-mini", "gen_ai.user.id": "user-0", "gen_ai.usage.input_tokens": 300, "gen_ai.usage.output_tokens": 120, "_signoz.gen_ai.total_cost": 0.02}}
{"timestamp": "2026-01-29T10:00:30.000000Z", "duration": "PT2.5S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f602", "span_id": "c1b2c3d4e5f6a702", "parent_span_id": "", "name": "POST /chat", "kind": 2, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"http.request.method": "POST", "http.response.status_code": "200", "http.request.path": "/chat"}}
{"timestamp": "2026-01-29T10:00:30.200000Z", "duration": "PT2S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f602", "span_id": "d1b2c3d4e5f6a702", "parent_span_id": "c1b2c3d4e5f6a702", "name": "chat gpt-4o-mini", "kind": 3, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"gen_ai.system": "openai", "gen_ai.request.model": "gpt-4o-mini", "gen_ai.user.id": "user-1", "gen_ai.usage.input_tokens": 310, "gen_ai.usage.output_tokens": 125, "_signoz.gen_ai.total_cost": 0.02}}
{"timestamp": "2026-01-29T10:01:00.000000Z", "duration": "PT2.5S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f603", "span_id": "c1b2c3d4e5f6a703", "parent_span_id": "", "name": "POST /chat", "kind": 2, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"http.request.method": "POST", "http.response.status_code": "200", "http.request.path": "/chat"}}
{"timestamp": "2026-01-29T10:01:00.200000Z", "duration": "PT2S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f603", "span_id": "d1b2c3d4e5f6a703", "parent_span_id": "c1b2c3d4e5f6a703", "name": "chat gpt-4o-mini", "kind": 3, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"gen_ai.system": "openai", "gen_ai.request.model": "gpt-4o-mini", "gen_ai.user.id": "user-0", "gen_ai.usage.input_tokens": 320, "gen_ai.usage.output_tokens": 130, "_signoz.gen_ai.total_cost": 0.02}}
{"timestamp": "2026-01-29T10:01:30.000000Z", "duration": "PT2.5S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f604", "span_id": "c1b2c3d4e5f6a704", "parent_span_id": "", "name": "POST /chat", "kind": 2, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"http.request.method": "POST", "http.response.status_code": "200", "http.request.path": "/chat"}}
{"timestamp": "2026-01-29T10:01:30.200000Z", "duration": "PT2S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f604", "span_id": "d1b2c3d4e5f6a704", "parent_span_id": "c1b2c3d4e5f6a704", "name": "chat gpt-4o-mini", "kind": 3, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"gen_ai.system": "openai", "gen_ai.request.model": "gpt-4o-mini", "gen_ai.user.id": "user-1", "gen_ai.usage.input_tokens": 330, "gen_ai.usage.output_tokens": 135, "_signoz.gen_ai.total_cost": 0.02}}
{"timestamp": "2026-01-29T10:02:00.000000Z", "duration": "PT2.5S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f605", "span_id": "c1b2c3d4e5f6a705", "parent_span_id": "", "name": "POST /chat", "kind": 2, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"http.request.method": "POST", "http.response.status_code": "200", "http.request.path": "/chat"}}
{"timestamp": "2026-01-29T10:02:00.200000Z", "duration": "PT2S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f605", "span_id": "d1b2c3d4e5f6a705", "parent_span_id": "c1b2c3d4e5f6a705", "name": "chat gpt-4o-mini", "kind": 3, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"gen_ai.system": "openai", "gen_ai.request.model": "gpt-4o-mini", "gen_ai.user.id": "user-0", "gen_ai.usage.input_tokens": 340, "gen_ai.usage.output_tokens": 140, "_signoz.gen_ai.total_cost": 0.02}}
{"timestamp": "2026-01-29T10:02:30.000000Z", "duration": "PT2.5S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f606", "span_id": "c1b2c3d4e5f6a706", "parent_span_id": "", "name": "POST /chat", "kind": 2, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"http.request.method": "POST", "http.response.status_code": "200", "http.request.path": "/chat"}}
{"timestamp": "2026-01-29T10:02:30.200000Z", "duration": "PT2S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f606", "span_id": "d1b2c3d4e5f6a706", "parent_span_id": "c1b2c3d4e5f6a706", "name": "chat gpt-4o-mini", "kind": 3, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"gen_ai.system": "openai", "gen_ai.request.model": "gpt-4o-mini", "gen_ai.user.id": "user-1", "gen_ai.usage.input_tokens": 350, "gen_ai.usage.output_tokens": 145, "_signoz.gen_ai.total_cost": 0.02}}
{"timestamp": "2026-01-29T10:03:00.000000Z", "duration": "PT2.5S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f607", "span_id": "c1b2c3d4e5f6a707", "parent_span_id": "", "name": "POST /chat", "kind": 2, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"http.request.method": "POST", "http.response.status_code": "200", "http.request.path": "/chat"}}
{"timestamp": "2026-01-29T10:03:00.200000Z", "duration": "PT2S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f607", "span_id": "d1b2c3d4e5f6a707", "parent_span_id": "c1b2c3d4e5f6a707", "name": "chat gpt-4o-mini", "kind": 3, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"gen_ai.system": "openai", "gen_ai.request.model": "gpt-4o-mini", "gen_ai.user.id": "user-0", "gen_ai.usage.input_tokens": 360, "gen_ai.usage.output_tokens": 150, "_signoz.gen_ai.total_cost": 0.02}}
{"timestamp": "2026-01-29T10:03:30.000000Z", "duration": "PT2.5S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f608", "span_id": "c1b2c3d4e5f6a708", "parent_span_id": "", "name": "POST /chat", "kind": 2, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"http.request.method": "POST", "http.response.status_code": "200", "http.request.path": "/chat"}}
{"timestamp": "2026-01-29T10:03:30.200000Z", "duration": "PT2S", "trace_id": "7a1f6d3d6b0a1f9e8a71b2c3d4e5f608", "span_id": "d1b2c3d4e5f6a708", "parent_span_id": "c1b2c3d4e5f6a708", "name": "chat gpt-4o-mini", "kind": 3, "status_code": 1, "status_message": "", "resources": {"deployment.environment": "production", "service.name": "llm-gateway", "os.type": "linux", "host.name": "linux-000"}, "attributes": {"gen_ai.system": "openai", "gen_ai.request.model": "gpt-4o-mini", "gen_ai.user.id": "user-1", "gen_ai.usage.input_tokens": 370, "gen_ai.usage.output_tokens": 155, "_signoz.gen_ai.total_cost": 0.02}}

View File

@@ -1,73 +0,0 @@
{
"alert": "rule_state_history_ai_traces",
"ruleType": "threshold_rule",
"alertType": "AI_TRACES_BASED_ALERT",
"condition": {
"thresholds": {
"kind": "basic",
"spec": [
{
"name": "critical",
"target": 0,
"matchType": "at_least_once",
"op": "above",
"channels": [
"test channel"
]
}
]
},
"compositeQuery": {
"queryType": "builder",
"panelType": "graph",
"queries": [
{
"type": "builder_ai_query",
"spec": {
"name": "A",
"signal": "traces",
"filter": {
"expression": "trace.input_tokens > 100"
},
"groupBy": [
{
"name": "service.name",
"fieldContext": "resource",
"fieldDataType": "string"
}
],
"aggregations": [
{
"expression": "max(trace.total_tokens)"
}
]
}
}
]
},
"selectedQueryName": "A"
},
"evaluation": {
"kind": "rolling",
"spec": {
"evalWindow": "5m0s",
"frequency": "15s"
}
},
"labels": {},
"annotations": {
"description": "This alert is fired when the defined metric (current value: {{$value}}) crosses the threshold ({{$threshold}})",
"summary": "This alert is fired when the defined metric (current value: {{$value}}) crosses the threshold ({{$threshold}})"
},
"notificationSettings": {
"groupBy": [],
"usePolicy": false,
"renotify": {
"enabled": false,
"interval": "30m",
"alertStates": []
}
},
"version": "v5",
"schemaVersion": "v2alpha1"
}

View File

@@ -38,7 +38,6 @@ def test_logs_rule_history_related_links(
assert labels_to_map(item["labels"]).get("service.name") == "payment-service"
assert item.get("relatedTracesLink", "") == ""
assert item.get("relatedAITracesLink", "") == ""
assert item.get("relatedLogsLink", "") != ""
# logs explorer links carry the time range in milliseconds, anchored to the
@@ -53,7 +52,6 @@ def test_logs_rule_history_related_links(
assert len(contributors) == 1
assert contributors[0]["count"] >= 1
assert contributors[0].get("relatedTracesLink", "") == ""
assert contributors[0].get("relatedAITracesLink", "") == ""
assert contributors[0].get("relatedLogsLink", "") != ""
# contributor counts aggregate the whole queried range, so their links span it
@@ -82,7 +80,6 @@ def test_traces_rule_history_related_links(
assert labels_to_map(item["labels"]).get("service.name") == "order-service"
assert item.get("relatedLogsLink", "") == ""
assert item.get("relatedAITracesLink", "") == ""
assert item.get("relatedTracesLink", "") != ""
# traces explorer links carry the time range in nanoseconds, anchored to the
@@ -97,7 +94,6 @@ def test_traces_rule_history_related_links(
assert len(contributors) == 1
assert contributors[0]["count"] >= 1
assert contributors[0].get("relatedLogsLink", "") == ""
assert contributors[0].get("relatedAITracesLink", "") == ""
assert contributors[0].get("relatedTracesLink", "") != ""
# contributor counts aggregate the whole queried range, so their links span it
@@ -105,49 +101,3 @@ def test_traces_rule_history_related_links(
assert contributor_link["start"] == query_start_ms * 1_000_000
assert contributor_link["end"] == query_end_ms * 1_000_000
assert_related_link_query(contributor_link, "traces", ["http.request.path", "/order", "service.name", "order-service"])
def test_ai_traces_rule_history_related_links(
signoz: types.SigNoz,
create_alert_rule_with_channel: Callable[[str], str],
insert_alert_data: Callable[[list[types.AlertData], datetime], None],
get_token: Callable[[str, str], str],
):
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
query_start_ms = int((datetime.now(tz=UTC) - timedelta(minutes=30)).timestamp() * 1000)
insert_alert_data(
[types.AlertData(type="traces", data_path="alerts/test_scenarios/rule_state_history_ai_traces/alert_data.jsonl")],
base_time=datetime.now(tz=UTC) - timedelta(minutes=5),
)
rule_id = create_alert_rule_with_channel("alerts/test_scenarios/rule_state_history_ai_traces/rule.json")
(item, query_end_ms) = wait_for_firing_timeline_entry(signoz, token, rule_id, query_start_ms)
assert labels_to_map(item["labels"]).get("service.name") == "llm-gateway"
assert item.get("relatedLogsLink", "") == ""
assert item.get("relatedTracesLink", "") == ""
assert item.get("relatedAITracesLink", "") != ""
# AI alert links follow the traces explorer shape: a nanosecond range
# anchored to the second-truncated entry timestamp
link = parse_related_link(item["relatedAITracesLink"])
assert link["end"] == (item["unixMilli"] // 1000) * 1_000_000_000
assert link["end"] - link["start"] == RELATED_LINK_WINDOW_SECONDS * 1_000_000_000
assert_related_link_query(link, "traces", ["trace.input_tokens", "100", "service.name", "llm-gateway"])
# the AI explorer only resolves trace.* fields for builder_ai_query
assert link["composite_query"]["builder"]["queryData"][0]["builderQueryType"] == "builder_ai_query"
contributors = get_rule_history_top_contributors(signoz, token, rule_id, query_start_ms, query_end_ms)
contributors = [c for c in contributors if labels_to_map(c["labels"]).get("service.name") == "llm-gateway"]
assert len(contributors) == 1
assert contributors[0]["count"] >= 1
assert contributors[0].get("relatedLogsLink", "") == ""
assert contributors[0].get("relatedTracesLink", "") == ""
assert contributors[0].get("relatedAITracesLink", "") != ""
contributor_link = parse_related_link(contributors[0]["relatedAITracesLink"])
assert contributor_link["start"] == query_start_ms * 1_000_000
assert contributor_link["end"] == query_end_ms * 1_000_000
assert_related_link_query(contributor_link, "traces", ["trace.input_tokens", "100", "service.name", "llm-gateway"])
assert contributor_link["composite_query"]["builder"]["queryData"][0]["builderQueryType"] == "builder_ai_query"

View File

@@ -0,0 +1,381 @@
from collections.abc import Callable
from datetime import datetime, timedelta
from http import HTTPStatus
import pytest
from fixtures import types
from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
from fixtures.querier import (
RequestType,
assert_scalar_value,
build_aggregation,
build_group_by_field,
build_order_by,
build_raw_query,
build_scalar_query,
get_all_warnings,
get_column_data_from_response,
get_scalar_table_data,
make_query_request,
)
from fixtures.queriercommon import (
ATTRIBUTE_ONLY,
BOTH,
COLUMN_ONLY,
EXPLICIT_PREFIX,
IDENTITY_KEY,
NEITHER,
NUMBER_ATTRIBUTE,
)
# One name can exist in more than one place. `name` is a span column and a
# span attribute. `severity_text` is a log column and a log attribute.
# `service.name` is a resource attribute and a span or log attribute.
#
# Rules for a filter:
# - A key with an explicit context reads that context only.
# - A bare key that is a column and an attribute reads both. The query
# returns an ambiguity warning.
# - A bare key that is a resource attribute and an attribute reads the
# resource attribute. The query returns an ambiguity warning.
# - An `attribute.` key returns the warning when the attribute has two data
# types.
# - A string operand matches a number attribute through a text cast.
# - A key under the signal's own context (`span.`, `log.`) that exists only
# as an attribute reads the attribute. On logs it also reads the body JSON
# path.
FILTER_MATRIX = [
pytest.param("{contested} = '{value}'", {COLUMN_ONLY, ATTRIBUTE_ONLY, BOTH}, True, id="bare_column_and_attribute"),
pytest.param("{own}.{contested} = '{value}'", {COLUMN_ONLY, BOTH}, False, id="own_context_column_only"),
pytest.param("attribute.{contested} = '{value}'", {ATTRIBUTE_ONLY, BOTH}, True, id="attribute_context_warns_about_two_types"),
pytest.param("{contested} != '{value}'", {NEITHER, NUMBER_ATTRIBUTE}, True, id="bare_negative_excludes_every_carrier"),
pytest.param("{contested} EXISTS", {COLUMN_ONLY, ATTRIBUTE_ONLY, BOTH, NEITHER, NUMBER_ATTRIBUTE}, True, id="bare_exists_is_the_column"),
pytest.param("{contested} NOT EXISTS", set(), True, id="bare_not_exists_is_never"),
pytest.param("attribute.{contested} EXISTS", {ATTRIBUTE_ONLY, BOTH, NUMBER_ATTRIBUTE}, True, id="attribute_exists_spans_both_types"),
pytest.param("attribute.{contested} NOT EXISTS", {COLUMN_ONLY, NEITHER}, True, id="attribute_not_exists"),
pytest.param("{contested} = '42'", {NUMBER_ATTRIBUTE}, True, id="bare_string_operand_reaches_the_number_attribute"),
pytest.param("attribute.{contested}:string = '{value}'", {ATTRIBUTE_ONLY, BOTH}, False, id="type_suffix_selects_the_string_attribute"),
pytest.param("attribute.{contested}:float64 = 42", {NUMBER_ATTRIBUTE}, False, id="type_suffix_selects_the_number_attribute"),
pytest.param("service.name = 'svc-a'", {COLUMN_ONLY, BOTH}, True, id="bare_resource_wins_with_warning"),
pytest.param("service.name != 'svc-a'", {ATTRIBUTE_ONLY, NEITHER, NUMBER_ATTRIBUTE}, True, id="bare_resource_negative"),
pytest.param("resource.service.name = 'svc-a'", {COLUMN_ONLY, BOTH}, False, id="resource_context_no_warning"),
pytest.param("resource.service.name != 'svc-a'", {ATTRIBUTE_ONLY, NEITHER, NUMBER_ATTRIBUTE}, False, id="resource_context_negative"),
pytest.param("attribute.service.name = 'svc-a'", {ATTRIBUTE_ONLY, BOTH}, False, id="attribute_context_no_warning"),
pytest.param(
"{own}.route.tag = 'checkout'",
{"traces": {COLUMN_ONLY, BOTH}, "logs": {COLUMN_ONLY, ATTRIBUTE_ONLY, BOTH, NEITHER, NUMBER_ATTRIBUTE}},
False,
id="own_context_miss_corrects_to_attribute_and_on_logs_to_body",
),
pytest.param("route.tag = 'checkout'", {COLUMN_ONLY, BOTH}, False, id="bare_attribute_only_key"),
]
SIGNALS = [
pytest.param("traces", "span", "name", "checkout", "other", id="traces"),
pytest.param("logs", "log", "severity_text", "ERROR", "INFO", id="logs"),
]
@pytest.mark.parametrize("expression_template,expected,expects_ambiguity_warning", FILTER_MATRIX)
@pytest.mark.parametrize("signal,own_context,contested,value,other_value", SIGNALS)
def test_filter_resolution(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
signal: str,
own_context: str,
contested: str,
value: str,
other_value: str, # pylint: disable=unused-argument
expression_template: str,
expected: set[str] | dict[str, set[str]],
expects_ambiguity_warning: bool,
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
expression = expression_template.format(own=own_context, contested=contested, value=value)
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.RAW,
queries=[
build_raw_query(
"A",
signal,
limit=100,
filter_expression=expression,
order=[build_order_by("timestamp", "asc")],
select_fields=[{"name": IDENTITY_KEY}],
)
],
)
assert response.status_code == HTTPStatus.OK, response.text
matched = {row for row in get_column_data_from_response(response.json(), IDENTITY_KEY) if row.startswith(EXPLICIT_PREFIX)}
assert matched == (expected[signal] if isinstance(expected, dict) else expected), expression
warnings = [w["message"] for w in get_all_warnings(response.json())]
assert any("ambiguous" in w for w in warnings) == expects_ambiguity_warning, warnings
# Rules for a group by:
# - A bare key that is a column and an attribute groups by the column only.
# - A key with an explicit context groups by that context only.
GROUP_BY_MATRIX = [
pytest.param(None, {"{value}": 2, "{other}": 3}, id="bare_groups_by_the_column"),
pytest.param("own", {"{value}": 2, "{other}": 3}, id="own_context_groups_by_the_column"),
pytest.param("attribute", {"{value}": 2}, id="attribute_context_groups_by_the_attribute"),
]
@pytest.mark.parametrize("context,expected_template", GROUP_BY_MATRIX)
@pytest.mark.parametrize("signal,own_context,contested,value,other_value", SIGNALS)
def test_group_by_resolution(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
signal: str,
own_context: str,
contested: str,
value: str,
other_value: str,
context: str | None,
expected_template: dict[str, int],
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
field_context = own_context if context == "own" else context
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.SCALAR,
queries=[
build_scalar_query(
"A",
signal,
[build_aggregation("count()", "rows")],
group_by=[build_group_by_field(contested, "string", field_context) if field_context else {"name": contested}],
filter_expression=f"{IDENTITY_KEY} LIKE '{EXPLICIT_PREFIX}%'",
)
],
)
assert response.status_code == HTTPStatus.OK, response.text
expected = {key.format(value=value, other=other_value): count for key, count in expected_template.items()}
groups = {row[0]: row[1] for row in get_scalar_table_data(response.json()) if row[0] in expected}
assert groups == expected, get_scalar_table_data(response.json())
# Rule for a raw select of a bare key that is a resource attribute and an
# attribute: each row shows the resource value. This is also true for a row
# where the attribute has a different value.
@pytest.mark.parametrize("signal", ["traces", "logs"])
def test_select_of_ambiguous_name(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
signal: str,
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.RAW,
queries=[
build_raw_query(
"A",
signal,
limit=100,
filter_expression=f"{IDENTITY_KEY} LIKE '{EXPLICIT_PREFIX}%'",
order=[build_order_by("timestamp", "asc")],
select_fields=[{"name": IDENTITY_KEY}, {"name": "service.name"}],
)
],
)
assert response.status_code == HTTPStatus.OK, response.text
rows = response.json()["data"]["data"]["results"][0]["rows"] or []
by_identity = {row["data"][IDENTITY_KEY]: row["data"]["service.name"] for row in rows if row["data"].get(IDENTITY_KEY, "").startswith(EXPLICIT_PREFIX)}
assert by_identity == {
COLUMN_ONLY: "svc-a",
ATTRIBUTE_ONLY: "svc-b",
BOTH: "svc-a",
NEITHER: "svc-b",
NUMBER_ATTRIBUTE: "svc-b",
}
# Rules for an order by, descending, with the timestamp descending as the
# second key:
# - A bare key or a key under the signal's own context sorts by the column
# only.
# - An `attribute.` key sorts by the attribute on traces. The number
# attribute sorts as text. Rows without the attribute come last.
# - An `attribute.` key sorts by the column on logs.
BY_COLUMN = [ATTRIBUTE_ONLY, NEITHER, NUMBER_ATTRIBUTE, COLUMN_ONLY, BOTH]
ORDER_BY_MATRIX = [
pytest.param(None, {"traces": BY_COLUMN, "logs": BY_COLUMN}, id="bare_orders_by_the_column"),
pytest.param("own", {"traces": BY_COLUMN, "logs": BY_COLUMN}, id="own_context_orders_by_the_column"),
pytest.param(
"attribute",
{"traces": [ATTRIBUTE_ONLY, BOTH, NUMBER_ATTRIBUTE, COLUMN_ONLY, NEITHER], "logs": BY_COLUMN},
id="attribute_context_orders_by_the_attribute_on_traces_only",
),
]
@pytest.mark.parametrize("context,expected", ORDER_BY_MATRIX)
@pytest.mark.parametrize("signal,own_context,contested,value,other_value", SIGNALS)
def test_order_by_resolution(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
signal: str,
own_context: str,
contested: str,
value: str, # pylint: disable=unused-argument
other_value: str, # pylint: disable=unused-argument
context: str | None,
expected: dict[str, list[str]],
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
prefix = f"{own_context}." if context == "own" else f"{context}." if context else ""
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.RAW,
queries=[
build_raw_query(
"A",
signal,
limit=100,
filter_expression=f"{IDENTITY_KEY} LIKE '{EXPLICIT_PREFIX}%'",
order=[build_order_by(f"{prefix}{contested}", "desc"), build_order_by("timestamp", "desc")],
select_fields=[{"name": IDENTITY_KEY}],
)
],
)
assert response.status_code == HTTPStatus.OK, response.text
ordered = [row for row in get_column_data_from_response(response.json(), IDENTITY_KEY) if row.startswith(EXPLICIT_PREFIX)]
assert ordered == expected[signal]
# Rules for an aggregation argument:
# - A bare key counts the values of the column only.
# - An `attribute.` key counts the attribute in both data types. The number
# attribute adds one distinct value.
AGGREGATION_MATRIX = [
pytest.param(None, 2, id="bare_counts_the_column"),
pytest.param("own", 2, id="own_context_counts_the_column"),
pytest.param("attribute", 2, id="attribute_context_counts_both_attribute_types"),
]
@pytest.mark.parametrize("context,expected", AGGREGATION_MATRIX)
@pytest.mark.parametrize("signal,own_context,contested,value,other_value", SIGNALS)
def test_aggregation_argument_resolution(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
signal: str,
own_context: str,
contested: str,
value: str, # pylint: disable=unused-argument
other_value: str, # pylint: disable=unused-argument
context: str | None,
expected: int,
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
prefix = f"{own_context}." if context == "own" else f"{context}." if context else ""
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.SCALAR,
queries=[
build_scalar_query(
"A",
signal,
[build_aggregation(f"count_distinct({prefix}{contested})", "distinct")],
filter_expression=f"{IDENTITY_KEY} LIKE '{EXPLICIT_PREFIX}%'",
)
],
)
assert response.status_code == HTTPStatus.OK, response.text
assert_scalar_value(response, "A", expected)
# Rules for logs only:
# - A `body.` key reads the body JSON path. It does not read the attribute
# with the same name.
# - A `log.` key reads the attribute and the body JSON path together. This
# is also true when metadata reports the attribute.
# - A `scope.` key resolves through metadata only. When metadata does not
# report the key, the query fails with "key not found". This is also true
# for the declared path `scope.name` and for rows that have the scope
# data.
LOGS_ONLY_MATRIX = [
pytest.param("body.route.tag = 'checkout'", {ATTRIBUTE_ONLY, NEITHER, NUMBER_ATTRIBUTE}, id="body_context_reads_the_body_json"),
pytest.param("log.route.tag = 'checkout'", {COLUMN_ONLY, ATTRIBUTE_ONLY, BOTH, NEITHER, NUMBER_ATTRIBUTE}, id="log_context_reads_attribute_and_body"),
pytest.param("scope.name = 'scope-a'", "key `name` not found", id="scope_name_needs_metadata"),
pytest.param("scope.env = 'prod'", "key `env` not found", id="scope_attribute_needs_metadata"),
pytest.param("scope.env EXISTS", "key `env` not found", id="scope_attribute_exists_needs_metadata"),
]
@pytest.mark.parametrize("expression,expected", LOGS_ONLY_MATRIX)
def test_logs_body_and_scope_contexts(
signoz: types.SigNoz,
create_user_admin: None, # pylint: disable=unused-argument
get_token: Callable[[str, str], str],
ambiguous_rows: datetime,
expression: str,
expected: set[str] | str,
) -> None:
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
response = make_query_request(
signoz,
token,
start_ms=int((ambiguous_rows - timedelta(minutes=2)).timestamp() * 1000),
end_ms=int((ambiguous_rows + timedelta(minutes=1)).timestamp() * 1000),
request_type=RequestType.RAW,
queries=[
build_raw_query(
"A",
"logs",
limit=100,
filter_expression=expression,
order=[build_order_by("timestamp", "asc")],
select_fields=[{"name": IDENTITY_KEY}],
)
],
)
if isinstance(expected, str):
assert response.status_code == HTTPStatus.BAD_REQUEST, response.text
assert expected in response.text, response.text
return
assert response.status_code == HTTPStatus.OK, response.text
matched = {row for row in get_column_data_from_response(response.json(), IDENTITY_KEY) if row.startswith(EXPLICIT_PREFIX)}
assert matched == expected, expression