mirror of
https://github.com/SigNoz/signoz.git
synced 2026-08-28 15:20:42 +01:00
Compare commits
28 Commits
platform-p
...
issue_5601
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
349ee00df4 | ||
|
|
31372a0bbe | ||
|
|
bde83ff0ff | ||
|
|
0a59a9ef2d | ||
|
|
f0bac9f6be | ||
|
|
2d22cb6374 | ||
|
|
5f3d869058 | ||
|
|
b2c5af428e | ||
|
|
093f9b41c4 | ||
|
|
596e128005 | ||
|
|
2e1da92367 | ||
|
|
1e8d72e8fa | ||
|
|
cce080e1ae | ||
|
|
deca060a4d | ||
|
|
03c7e524e7 | ||
|
|
815dc7d88b | ||
|
|
f50d9199fe | ||
|
|
97c49c870b | ||
|
|
31efe177a4 | ||
|
|
d502d12ac3 | ||
|
|
bd9f15a716 | ||
|
|
813ef988c9 | ||
|
|
40e6799285 | ||
|
|
1caa60a3cd | ||
|
|
3f781f0083 | ||
|
|
6aec05cf7a | ||
|
|
683a52f35a | ||
|
|
e924fa1e62 |
133
pkg/statementbuilder/aistatementbuilder/span_list_test.go
Normal file
133
pkg/statementbuilder/aistatementbuilder/span_list_test.go
Normal file
@@ -0,0 +1,133 @@
|
||||
package aistatementbuilder
|
||||
|
||||
import (
|
||||
"context"
|
||||
"testing"
|
||||
|
||||
qbtypes "github.com/SigNoz/signoz/pkg/types/querybuildertypes/querybuildertypesv5"
|
||||
"github.com/SigNoz/signoz/pkg/types/telemetrytypes"
|
||||
"github.com/SigNoz/signoz/pkg/valuer"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
|
||||
// Mixed filter: the span-level part gates the scan, the trace-level part becomes the
|
||||
// __trace_scope qualification.
|
||||
func TestBuild_FullSQL_SpanList_TraceScoped(t *testing.T) {
|
||||
b := newTestBuilder(t)
|
||||
stmt, err := b.Build(context.Background(), valuer.UUID{}, testStartMs, testEndMs, qbtypes.RequestTypeRaw,
|
||||
qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
|
||||
Signal: telemetrytypes.SignalTraces,
|
||||
Filter: &qbtypes.Filter{Expression: "gen_ai.request.model = 'gpt-4o-mini' AND trace.output_tokens > 1000"},
|
||||
Limit: 10,
|
||||
}, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
assertSQLEqual(t, `
|
||||
WITH __trace_scope AS (
|
||||
SELECT trace_id,
|
||||
sum(multiIf(mapContains(attributes_number, 'gen_ai.usage.output_tokens'), toFloat64(attributes_number['gen_ai.usage.output_tokens']), NULL)) AS output_tokens
|
||||
FROM signoz_traces.distributed_signoz_index_v3
|
||||
WHERE timestamp >= '1747947419000000000'
|
||||
AND timestamp < '1747983448000000000'
|
||||
AND ts_bucket_start >= 1747945619
|
||||
AND ts_bucket_start <= 1747983448
|
||||
AND (mapContains(attributes_string, 'gen_ai.request.model') OR mapContains(attributes_string, 'gen_ai.tool.name') OR mapContains(attributes_string, 'gen_ai.agent.name'))
|
||||
GROUP BY trace_id
|
||||
HAVING output_tokens > 1000
|
||||
)
|
||||
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 trace_id GLOBAL IN (SELECT trace_id FROM __trace_scope)
|
||||
AND (((mapContains(attributes_string, 'gen_ai.request.model')
|
||||
OR mapContains(attributes_string, 'gen_ai.tool.name')
|
||||
OR mapContains(attributes_string, 'gen_ai.agent.name')))
|
||||
AND ((attributes_string['gen_ai.request.model'] = 'gpt-4o-mini'
|
||||
AND mapContains(attributes_string, 'gen_ai.request.model'))))
|
||||
AND timestamp >= '1747947419000000000'
|
||||
AND timestamp < '1747983448000000000'
|
||||
AND ts_bucket_start >= 1747945619
|
||||
AND ts_bucket_start <= 1747983448
|
||||
LIMIT 10
|
||||
`, stmt)
|
||||
}
|
||||
|
||||
// A resource attribute mixed with a trace-level condition: the resource part flows
|
||||
// through the fingerprint machinery, the trace-level part through __trace_scope.
|
||||
func TestBuild_SpanList_ResourcePlusTraceFilter(t *testing.T) {
|
||||
b := newTestBuilder(t)
|
||||
stmt, err := b.Build(context.Background(), valuer.UUID{}, testStartMs, testEndMs, qbtypes.RequestTypeRaw,
|
||||
qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
|
||||
Signal: telemetrytypes.SignalTraces,
|
||||
Filter: &qbtypes.Filter{Expression: "resource.service.name = 'checkout' AND trace.output_tokens > 1000"},
|
||||
Limit: 10,
|
||||
}, nil)
|
||||
require.NoError(t, err)
|
||||
|
||||
got := renderSQL(t, stmt)
|
||||
assert.Contains(t, got, "__resource_filter AS (")
|
||||
assert.Contains(t, got, "resource_fingerprint GLOBAL IN (SELECT fingerprint FROM __resource_filter)")
|
||||
assert.Contains(t, got, "__trace_scope AS (")
|
||||
assert.Contains(t, got, "trace_id GLOBAL IN (SELECT trace_id FROM __trace_scope)")
|
||||
assert.Contains(t, got, "HAVING output_tokens > 1000")
|
||||
}
|
||||
|
||||
// Trace-level order keys are rejected — known aggregate alias or not — while a bare
|
||||
// span column sharing an alias (duration_nano) stays orderable.
|
||||
func TestBuild_SpanList_OrderKeyValidation(t *testing.T) {
|
||||
b := newTestBuilder(t)
|
||||
build := func(q qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]) error {
|
||||
q.Signal = telemetrytypes.SignalTraces
|
||||
_, err := b.Build(context.Background(), valuer.UUID{}, testStartMs, testEndMs, qbtypes.RequestTypeRaw, q, nil)
|
||||
return err
|
||||
}
|
||||
|
||||
err := build(qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
|
||||
Order: []qbtypes.OrderBy{{Key: qbtypes.OrderByKey{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "trace.output_tokens"}}}},
|
||||
})
|
||||
require.ErrorContains(t, err, `ordering the span list by trace-level key "trace.output_tokens" is not supported`)
|
||||
|
||||
err = build(qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
|
||||
Order: []qbtypes.OrderBy{{Key: qbtypes.OrderByKey{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "trace.foo"}}}},
|
||||
})
|
||||
require.ErrorContains(t, err, `trace-level key "trace.foo"`)
|
||||
|
||||
err = build(qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
|
||||
Order: []qbtypes.OrderBy{{Key: qbtypes.OrderByKey{TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{Name: "duration_nano"}}, Direction: qbtypes.OrderDirectionDesc}},
|
||||
Limit: 10,
|
||||
})
|
||||
require.NoError(t, err, "bare duration_nano is a span column, not a trace-level key")
|
||||
}
|
||||
|
||||
// Variables in a trace-level condition resolve through the standard pipeline; a
|
||||
// dynamic __all__ drops the condition (no scope CTE).
|
||||
func TestBuild_SpanList_TraceFilter_Variables(t *testing.T) {
|
||||
b := newTestBuilder(t)
|
||||
build := func(expr string, vars map[string]qbtypes.VariableItem) (*qbtypes.Statement, error) {
|
||||
return b.Build(context.Background(), valuer.UUID{}, testStartMs, testEndMs, qbtypes.RequestTypeRaw,
|
||||
qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]{
|
||||
Signal: telemetrytypes.SignalTraces,
|
||||
Filter: &qbtypes.Filter{Expression: expr},
|
||||
Limit: 10,
|
||||
}, vars)
|
||||
}
|
||||
|
||||
stmt, err := build("trace.output_tokens > $threshold",
|
||||
map[string]qbtypes.VariableItem{"threshold": {Value: 700}})
|
||||
require.NoError(t, err)
|
||||
assert.Contains(t, renderSQL(t, stmt), "HAVING output_tokens > 700")
|
||||
|
||||
stmt, err = build("trace.output_tokens > $threshold",
|
||||
map[string]qbtypes.VariableItem{"threshold": {Type: qbtypes.DynamicVariableType, Value: "__all__"}})
|
||||
require.NoError(t, err)
|
||||
assert.NotContains(t, stmt.Query, "__trace_scope")
|
||||
}
|
||||
@@ -114,6 +114,9 @@ func (b *scopedTraceStatementBuilder) Build(
|
||||
case qbtypes.RequestTypeTrace:
|
||||
return b.buildTraceListQuery(ctx, orgID, querybuilder.ToNanoSecs(start), querybuilder.ToNanoSecs(end), query, variables)
|
||||
case qbtypes.RequestTypeRaw:
|
||||
if err := b.validateRawOrderKeys(query); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return b.buildDelegated(ctx, orgID, start, end, requestType, query, variables)
|
||||
case qbtypes.RequestTypeScalar, qbtypes.RequestTypeTimeSeries:
|
||||
return b.buildAggregation(ctx, orgID, start, end, requestType, query, variables)
|
||||
@@ -122,27 +125,18 @@ func (b *scopedTraceStatementBuilder) Build(
|
||||
}
|
||||
}
|
||||
|
||||
// buildDelegated ANDs the base gate into the user filter and delegates to the
|
||||
// standard trace builder (the span-list / raw path).
|
||||
func (b *scopedTraceStatementBuilder) buildDelegated(
|
||||
ctx context.Context,
|
||||
orgID valuer.UUID,
|
||||
start, end uint64,
|
||||
requestType qbtypes.RequestType,
|
||||
query qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation],
|
||||
variables map[string]qbtypes.VariableItem,
|
||||
) (*qbtypes.Statement, error) {
|
||||
gate := b.scope.FilterExpression
|
||||
expr := gate
|
||||
if query.Filter != nil && strings.TrimSpace(query.Filter.Expression) != "" {
|
||||
expr = fmt.Sprintf("(%s) AND (%s)", gate, query.Filter.Expression)
|
||||
// validateRawOrderKeys rejects trace-level order keys — no per-trace value exists on
|
||||
// span rows. A bare name may be a span column sharing an alias (duration_nano), so it passes.
|
||||
func (b *scopedTraceStatementBuilder) validateRawOrderKeys(query qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation]) error {
|
||||
for _, o := range query.Order {
|
||||
key := o.Key.TelemetryFieldKey
|
||||
key.Normalize()
|
||||
if key.FieldContext == telemetrytypes.FieldContextTrace {
|
||||
return errors.NewInvalidInputf(errors.CodeInvalidInput,
|
||||
"ordering the span list by trace-level key %q is not supported; order by span columns instead (e.g. timestamp, duration_nano)", o.Key.Name)
|
||||
}
|
||||
}
|
||||
|
||||
// shallow copy; only Filter is replaced, caller's query untouched
|
||||
gated := query
|
||||
gated.Filter = &qbtypes.Filter{Expression: expr}
|
||||
|
||||
return b.traceStmtBuilder.Build(ctx, orgID, start, end, requestType, gated, variables)
|
||||
return nil
|
||||
}
|
||||
|
||||
// traceScopedStatementBuilder is the delegate's optional capability of constraining a
|
||||
@@ -153,10 +147,10 @@ type traceScopedStatementBuilder interface {
|
||||
BuildTraceScoped(ctx context.Context, orgID valuer.UUID, start, end uint64, requestType qbtypes.RequestType, query qbtypes.QueryBuilderQuery[qbtypes.TraceAggregation], variables map[string]qbtypes.VariableItem, traceScope, traceScopeResource *qbtypes.Statement) (*qbtypes.Statement, error)
|
||||
}
|
||||
|
||||
// buildDelegatedAggregation serves span-level scalar/time-series through the standard
|
||||
// trace builder, with the gate ANDed into the span-level filter part; a trace-level
|
||||
// part becomes a qualification the delegate constrains trace_id by.
|
||||
func (b *scopedTraceStatementBuilder) buildDelegatedAggregation(
|
||||
// buildDelegated serves the raw span list and span-level scalar/time-series through
|
||||
// the standard trace builder, with the gate ANDed into the span-level filter part; a
|
||||
// trace-level part becomes a qualification the delegate constrains trace_id by.
|
||||
func (b *scopedTraceStatementBuilder) buildDelegated(
|
||||
ctx context.Context,
|
||||
orgID valuer.UUID,
|
||||
start, end uint64,
|
||||
|
||||
@@ -45,7 +45,7 @@ func (b *scopedTraceStatementBuilder) buildAggregation(
|
||||
return nil, err
|
||||
}
|
||||
if len(traceAggs) == 0 {
|
||||
return b.buildDelegatedAggregation(ctx, orgID, start, end, requestType, query, variables)
|
||||
return b.buildDelegated(ctx, orgID, start, end, requestType, query, variables)
|
||||
}
|
||||
return b.buildTraceAggregationQuery(ctx, orgID, querybuilder.ToNanoSecs(start), querybuilder.ToNanoSecs(end), requestType, query, variables, traceAggs)
|
||||
}
|
||||
|
||||
@@ -361,6 +361,11 @@ func (b *traceQueryStatementBuilder) buildListQuery(
|
||||
cteArgs = append(cteArgs, args)
|
||||
}
|
||||
|
||||
if scopeFrags, scopeArgs := b.attachTraceScope(sb, frag != ""); len(scopeFrags) > 0 {
|
||||
cteFragments = append(cteFragments, scopeFrags...)
|
||||
cteArgs = append(cteArgs, scopeArgs...)
|
||||
}
|
||||
|
||||
for i, field := range query.SelectFields {
|
||||
expr, err := b.fm.ColumnExpressionFor(ctx, orgID, start, end, &field, telemetrytypes.FieldDataTypeUnspecified, keys)
|
||||
if err != nil {
|
||||
|
||||
@@ -209,6 +209,52 @@ def test_ai_span_list_excludes_non_gen_ai_spans(
|
||||
assert "POST /api/chat" not in names # root span excluded
|
||||
|
||||
|
||||
def test_ai_span_list_trace_level_filter(
|
||||
signoz: types.SigNoz,
|
||||
create_user_admin: None, # pylint: disable=unused-argument
|
||||
get_token: Callable[[str, str], str],
|
||||
insert_traces: Callable[[list[Traces]], None],
|
||||
) -> None:
|
||||
"""Span list (raw) with a trace-level condition returns only the gen_ai spans
|
||||
of traces whose window-clipped aggregates qualify."""
|
||||
now = datetime.now(tz=UTC).replace(second=0, microsecond=0)
|
||||
service = "ai-it-spanlist-tracefilter"
|
||||
small = ai_trace(now=now, service=service, user="a", in_tokens=10, out_tokens=100)
|
||||
large = ai_trace(now=now, service=service, user="b", in_tokens=30, out_tokens=300)
|
||||
insert_traces(small + large)
|
||||
|
||||
token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
|
||||
start_ms, end_ms = query_window(now)
|
||||
|
||||
query = BuilderQuery(
|
||||
signal="traces",
|
||||
query_type="builder_ai_query",
|
||||
name="A",
|
||||
filter_expression=f"service.name = '{service}' AND trace.output_tokens > 100",
|
||||
limit=10,
|
||||
)
|
||||
response = make_query_request(signoz, token, start_ms, end_ms, [query.to_dict()], request_type=RequestType.RAW)
|
||||
assert response.status_code == HTTPStatus.OK, response.text
|
||||
|
||||
rows = response.json()["data"]["data"]["results"][0]["rows"]
|
||||
assert len(rows) == 1, f"expected only the large trace's LLM span, got {len(rows)} rows"
|
||||
body = json.dumps(rows)
|
||||
assert large[0].trace_id in body
|
||||
assert small[0].trace_id not in body
|
||||
|
||||
# a threshold no trace meets: the empty qualification yields no spans, not an error
|
||||
query = BuilderQuery(
|
||||
signal="traces",
|
||||
query_type="builder_ai_query",
|
||||
name="A",
|
||||
filter_expression=f"service.name = '{service}' AND trace.output_tokens > 1000",
|
||||
limit=10,
|
||||
)
|
||||
response = make_query_request(signoz, token, start_ms, end_ms, [query.to_dict()], request_type=RequestType.RAW)
|
||||
assert response.status_code == HTTPStatus.OK, response.text
|
||||
assert not (response.json()["data"]["data"]["results"][0].get("rows") or [])
|
||||
|
||||
|
||||
def test_ai_list_having_or_aggregates(
|
||||
signoz: types.SigNoz,
|
||||
create_user_admin: None, # pylint: disable=unused-argument
|
||||
|
||||
Reference in New Issue
Block a user