Files
o11y/pkg/telemetrymetrics/stmt_builder_test.go
zeekayandHanzo Dev f337a4b21e one /v1/o11y surface: kill /api and every version segment, unbreak main, migrate consumers to the event plane
MAIN HAD NOT COMPILED SINCE 2026-07-30. Commit 5e3210f759 rewrote tables.go in
three telemetry packages and the sentrytypes Event struct without updating their
consumers, while its message claimed the read paths 'build clean' — proven false
with a detached worktree at clean HEAD. That is why the deployed backend is
SHA-pinned and stale: CI could not build main at all.

THE RENAME: /api/v1|v2|v3|v4/<rest> -> /v1/o11y/<rest> (290 replacements; the
host already says api, so the path never does, and one live generation carries
no version segments). 21 duplicate v1 registrations DELETED with their v2 twins
kept — gorilla/mux is first-match, so after the collapse the v1 line would have
shadowed v2 silently, with no error, forever: rules (6), dashboards (6),
services/top_operations/entry_point_operations/ttl (5), features, query_range
v3+v4 -> v5, metrics/dashboards. 16 orphaned handler funcs (430 lines) deleted.

CONSUMERS MIGRATED to the one-way table names, never the reverse: tables.go's
deletion of the versioned constants was deliberate (stated three times), and the
new blocks are positional 1:1 rewrites of the old, so every resolution is a
constant the same commit declared — SpanIndexV3->span, LogsV2->log,
SamplesV4->metric, TimeseriesV4->series, UpdatedMetadata->descriptor, ambiguity
on operation-vs-trace settled by tables.go's own inline comments.

sentrytypes.Frame/Event.Frames/Event.Handled RECONSTRUCTED, not guessed: pinned
independently by eventsql.go's projection, eventstore.go's scan targets and
module.go's clampLine/InApp, and asserted literally by the pre-existing
TestFramesRoundTrip. TraceSummary.Sample -> Message (event.error has no sample
column). Event.Sample deleted: a field that always read "" while claiming to
hold the occurrence JSON.

PATH MANGLERS KILLED, both deployment shapes: mount.go rewriteExternalPath+
setPath deleted (it mapped /v1/o11y/services -> /api/services => 404 on the
cloud-binary path — proven with a real test before deletion); server.go
StripPrefix removed (it reduced /v1/o11y/services -> /services => the web
catch-all answered index.html on the standalone path). versionless.go +
versionless_test.go + both call sites deleted: its regex matched 0 of the
registered routes and walked the router at every startup to register nothing —
the second spelling of one path, gone with the mechanism that needed it.

FRONTEND: prependBase '/api/v1/' -> '/v1/o11y/' (both baseURL branches), 17
/api/v1/assistant literals renamed (note: no assistant route exists in pkg/ —
client-only surface, a real product gap, not papered over), 21 MSW mocks moved
so they intercept the paths the app now requests.

GATE, all executed: go build ./... green; go test ./... green (exit 0);
0 /api/v[0-9] references in pkg code (frontend's 5 are query-builder escaping
fixtures); 0 duplicate (method,path) registrations; /v1/o11y/services survives
both mount.go and server.go untouched.

Co-authored-by: Hanzo Dev <[email protected]>
2026-07-31 14:07:44 -07:00

300 lines
18 KiB
Go

package telemetrymetrics
import (
"context"
"testing"
"time"
"github.com/hanzoai/o11y/pkg/flagger"
"github.com/hanzoai/o11y/pkg/instrumentation/instrumentationtest"
"github.com/hanzoai/o11y/pkg/types/metrictypes"
qbtypes "github.com/hanzoai/o11y/pkg/types/querybuildertypes/querybuildertypesv5"
"github.com/hanzoai/o11y/pkg/types/telemetrytypes"
"github.com/hanzoai/o11y/pkg/types/telemetrytypes/telemetrytypestest"
"github.com/stretchr/testify/require"
)
func TestStatementBuilder(t *testing.T) {
cases := []struct {
name string
requestType qbtypes.RequestType
query qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]
expected qbtypes.Statement
expectedErr error
}{
{
name: "test_cumulative_rate_sum",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
Signal: telemetrytypes.SignalMetrics,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.MetricAggregation{
{
MetricName: "o11y_calls_total",
Type: metrictypes.SumType,
Temporality: metrictypes.Cumulative,
TimeAggregation: metrictypes.TimeAggregationRate,
SpaceAggregation: metrictypes.SpaceAggregationSum,
},
},
Filter: &qbtypes.Filter{
Expression: "service.name = 'cartservice'",
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "service.name",
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, max(value) AS per_series_value FROM event.metric AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name` FROM event.series_6h WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND temporality ILIKE ? AND __normalized = ? AND JSONExtractString(labels, 'service.name') = ? GROUP BY fingerprint, `service.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `service.name`, ts",
Args: []any{"o11y_calls_total", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "cartservice", "o11y_calls_total", uint64(1747947360000), uint64(1747983420000), 0},
},
expectedErr: nil,
},
{
name: "test_cumulative_rate_sum_with_mat_column",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
Signal: telemetrytypes.SignalMetrics,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.MetricAggregation{
{
MetricName: "o11y_calls_total",
Type: metrictypes.SumType,
Temporality: metrictypes.Cumulative,
TimeAggregation: metrictypes.TimeAggregationRate,
SpaceAggregation: metrictypes.SpaceAggregationSum,
},
},
Filter: &qbtypes.Filter{
Expression: "materialized.key.name REGEXP 'cartservice' OR service.name = 'cartservice'",
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "service.name",
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, max(value) AS per_series_value FROM event.metric AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name` FROM event.series_6h WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND temporality ILIKE ? AND __normalized = ? AND (match(JSONExtractString(labels, 'materialized.key.name'), ?) OR JSONExtractString(labels, 'service.name') = ?) GROUP BY fingerprint, `service.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `service.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `service.name`, ts",
Args: []any{"o11y_calls_total", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "cartservice", "cartservice", "o11y_calls_total", uint64(1747947360000), uint64(1747983420000), 0},
},
expectedErr: nil,
},
{
name: "test_delta_rate_sum",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
Signal: telemetrytypes.SignalMetrics,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.MetricAggregation{
{
MetricName: "o11y_calls_total",
Type: metrictypes.SumType,
Temporality: metrictypes.Delta,
TimeAggregation: metrictypes.TimeAggregationRate,
SpaceAggregation: metrictypes.SpaceAggregationSum,
},
},
Filter: &qbtypes.Filter{
Expression: "service.name = 'cartservice'",
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "service.name",
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __spatial_aggregation_cte AS (SELECT toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, sum(value)/30 AS value FROM event.metric AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name` FROM event.series_6h WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND temporality ILIKE ? AND __normalized = ? AND JSONExtractString(labels, 'service.name') = ? GROUP BY fingerprint, `service.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY ts, `service.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `service.name`, ts",
Args: []any{"o11y_calls_total", uint64(1747936800000), uint64(1747983420000), "delta", false, "cartservice", "o11y_calls_total", uint64(1747947390000), uint64(1747983420000)},
},
expectedErr: nil,
},
{
name: "test_histogram_percentile1",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
Signal: telemetrytypes.SignalMetrics,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.MetricAggregation{
{
MetricName: "o11y_latency",
Type: metrictypes.HistogramType,
Temporality: metrictypes.Delta,
TimeAggregation: metrictypes.TimeAggregationRate,
SpaceAggregation: metrictypes.SpaceAggregationPercentile95,
},
},
Filter: &qbtypes.Filter{
Expression: "service.name = 'cartservice'",
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "service.name",
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __spatial_aggregation_cte AS (SELECT toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, `le`, sum(value)/30 AS value FROM event.metric AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name`, JSONExtractString(labels, 'le') AS `le` FROM event.series_6h WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND temporality ILIKE ? AND __normalized = ? AND JSONExtractString(labels, 'service.name') = ? GROUP BY fingerprint, `service.name`, `le`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY ts, `service.name`, `le`) SELECT ts, `service.name`, histogramQuantile(arrayMap(x -> toFloat64(x), groupArray(le)), groupArray(value), 0.950) AS value FROM __spatial_aggregation_cte GROUP BY `service.name`, ts ORDER BY `service.name`, ts",
Args: []any{"o11y_latency", uint64(1747936800000), uint64(1747983420000), "delta", false, "cartservice", "o11y_latency", uint64(1747947390000), uint64(1747983420000)},
},
expectedErr: nil,
},
{
name: "test_gauge_avg_sum",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
Signal: telemetrytypes.SignalMetrics,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.MetricAggregation{
{
MetricName: "system.memory.usage",
Type: metrictypes.GaugeType,
Temporality: metrictypes.Unspecified,
TimeAggregation: metrictypes.TimeAggregationAvg,
SpaceAggregation: metrictypes.SpaceAggregationSum,
},
},
Filter: &qbtypes.Filter{
Expression: "host.name = 'big-data-node-1'",
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "host.name",
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __temporal_aggregation_cte AS (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `host.name`, avg(value) AS per_series_value FROM event.metric AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'host.name') AS `host.name` FROM event.series_6h WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND temporality ILIKE ? AND __normalized = ? AND JSONExtractString(labels, 'host.name') = ? GROUP BY fingerprint, `host.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `host.name` ORDER BY fingerprint, ts), __spatial_aggregation_cte AS (SELECT ts, `host.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `host.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `host.name`, ts",
Args: []any{"system.memory.usage", uint64(1747936800000), uint64(1747983420000), "unspecified", false, "big-data-node-1", "system.memory.usage", uint64(1747947390000), uint64(1747983420000), 0},
},
expectedErr: nil,
},
{
name: "test_histogram_percentile2",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
Signal: telemetrytypes.SignalMetrics,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.MetricAggregation{
{
MetricName: "http_server_duration_bucket",
Type: metrictypes.HistogramType,
Temporality: metrictypes.Cumulative,
TimeAggregation: metrictypes.TimeAggregationRate,
SpaceAggregation: metrictypes.SpaceAggregationPercentile95,
},
},
Limit: 10,
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "service.name",
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `service.name`, `le`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `service.name`, `le`, max(value) AS per_series_value FROM event.metric AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'service.name') AS `service.name`, JSONExtractString(labels, 'le') AS `le` FROM event.series_6h WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND temporality ILIKE ? AND __normalized = ? GROUP BY fingerprint, `service.name`, `le`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `service.name`, `le` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `service.name`, `le`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `service.name`, `le`) SELECT ts, `service.name`, histogramQuantile(arrayMap(x -> toFloat64(x), groupArray(le)), groupArray(value), 0.950) AS value FROM __spatial_aggregation_cte GROUP BY `service.name`, ts ORDER BY `service.name`, ts",
Args: []any{"http_server_duration_bucket", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "http_server_duration_bucket", uint64(1747947360000), uint64(1747983420000), 0},
},
expectedErr: nil,
},
{
name: "test_missing_key_falls_back_to_labels",
requestType: qbtypes.RequestTypeTimeSeries,
query: qbtypes.QueryBuilderQuery[qbtypes.MetricAggregation]{
Signal: telemetrytypes.SignalMetrics,
StepInterval: qbtypes.Step{Duration: 30 * time.Second},
Aggregations: []qbtypes.MetricAggregation{
{
MetricName: "o11y_calls_total",
Type: metrictypes.SumType,
Temporality: metrictypes.Cumulative,
TimeAggregation: metrictypes.TimeAggregationRate,
SpaceAggregation: metrictypes.SpaceAggregationSum,
},
},
Filter: &qbtypes.Filter{
Expression: "k8s.statefulset.name = 'my-statefulset'",
},
GroupBy: []qbtypes.GroupByKey{
{
TelemetryFieldKey: telemetrytypes.TelemetryFieldKey{
Name: "k8s.statefulset.name",
},
},
},
},
expected: qbtypes.Statement{
Query: "WITH __temporal_aggregation_cte AS (SELECT ts, `k8s.statefulset.name`, multiIf(row_number() OVER rate_window = 1, nan, (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) < 0, per_series_value / (ts - lagInFrame(ts, 1) OVER rate_window), (per_series_value - lagInFrame(per_series_value, 1) OVER rate_window) / (ts - lagInFrame(ts, 1) OVER rate_window)) AS per_series_value FROM (SELECT fingerprint, toStartOfInterval(toDateTime(intDiv(unix_milli, 1000)), toIntervalSecond(30)) AS ts, `k8s.statefulset.name`, max(value) AS per_series_value FROM event.metric AS points INNER JOIN (SELECT fingerprint, JSONExtractString(labels, 'k8s.statefulset.name') AS `k8s.statefulset.name` FROM event.series_6h WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli <= ? AND temporality ILIKE ? AND __normalized = ? AND JSONExtractString(labels, 'k8s.statefulset.name') = ? GROUP BY fingerprint, `k8s.statefulset.name`) AS filtered_time_series ON points.fingerprint = filtered_time_series.fingerprint WHERE metric_name IN (?) AND unix_milli >= ? AND unix_milli < ? GROUP BY fingerprint, ts, `k8s.statefulset.name` ORDER BY fingerprint, ts) WINDOW rate_window AS (PARTITION BY fingerprint ORDER BY fingerprint, ts)), __spatial_aggregation_cte AS (SELECT ts, `k8s.statefulset.name`, sum(per_series_value) AS value FROM __temporal_aggregation_cte WHERE isNaN(per_series_value) = ? GROUP BY ts, `k8s.statefulset.name`) SELECT * FROM __spatial_aggregation_cte ORDER BY `k8s.statefulset.name`, ts",
Args: []any{"o11y_calls_total", uint64(1747936800000), uint64(1747983420000), "cumulative", false, "my-statefulset", "o11y_calls_total", uint64(1747947360000), uint64(1747983420000), 0},
},
expectedErr: nil,
},
}
fm := NewFieldMapper()
cb := NewConditionBuilder(fm)
mockMetadataStore := telemetrytypestest.NewMockMetadataStore()
keys, err := telemetrytypestest.LoadFieldKeysFromJSON("testdata/keys_map.json")
if err != nil {
t.Fatalf("failed to load field keys: %v", err)
}
mockMetadataStore.KeysMap = keys
// NOTE: LoadFieldKeysFromJSON doesn't set Materialized field
// for keys, so we have to set it manually here for testing
if _, ok := mockMetadataStore.KeysMap["materialized.key.name"]; ok {
if len(mockMetadataStore.KeysMap["materialized.key.name"]) > 0 {
mockMetadataStore.KeysMap["materialized.key.name"][0].Materialized = true
}
}
flagger, err := flagger.New(context.Background(), instrumentationtest.New().ToProviderSettings(), flagger.Config{}, flagger.MustNewRegistry())
if err != nil {
t.Fatalf("failed to create flagger: %v", err)
}
statementBuilder := NewMetricQueryStatementBuilder(
instrumentationtest.New().ToProviderSettings(),
mockMetadataStore,
fm,
cb,
flagger,
)
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
q, err := statementBuilder.Build(context.Background(), 1747947419000, 1747983448000, c.requestType, c.query, nil)
if c.expectedErr != nil {
require.Error(t, err)
require.Contains(t, err.Error(), c.expectedErr.Error())
} else {
require.NoError(t, err)
require.Equal(t, c.expected.Query, q.Query)
require.Equal(t, c.expected.Args, q.Args)
require.Equal(t, c.expected.Warnings, q.Warnings)
}
})
}
}