feat(#6458): export eval measurement scores via OTLP #6459
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,207 @@ | ||
| // Command prove-otlp-scores scores a real run-telemetry.jsonl and asserts | ||
| // portable OTLP gen_ai.evaluation.result events arrive at a local sink. | ||
| package main | ||
|
|
||
| import ( | ||
| "bytes" | ||
| "compress/gzip" | ||
| "context" | ||
| "encoding/hex" | ||
| "encoding/json" | ||
| "fmt" | ||
| "io" | ||
| "net/http" | ||
| "net/http/httptest" | ||
| "os" | ||
| "path/filepath" | ||
| "sync" | ||
|
|
||
| coltracepb "go.opentelemetry.io/proto/otlp/collector/trace/v1" | ||
| commonpb "go.opentelemetry.io/proto/otlp/common/v1" | ||
| "google.golang.org/protobuf/proto" | ||
|
|
||
| "github.com/fullsend-ai/fullsend/internal/evalmeasure" | ||
| ) | ||
|
|
||
| func main() { | ||
| if len(os.Args) < 3 { | ||
| fmt.Fprintf(os.Stderr, "usage: %s <run-telemetry.jsonl> <registry.yaml> [out-dir]\n", os.Args[0]) | ||
| fmt.Fprintf(os.Stderr, " out-dir defaults to a fresh temp dir (never the telemetry file's directory).\n") | ||
| os.Exit(2) | ||
| } | ||
| telem := os.Args[1] | ||
| reg := os.Args[2] | ||
| out := "" | ||
| if len(os.Args) > 3 { | ||
| out = os.Args[3] | ||
| } else { | ||
| tmp, err := os.MkdirTemp("", "prove-otlp-scores-*") | ||
| if err != nil { | ||
| fmt.Fprintf(os.Stderr, "temp out-dir: %v\n", err) | ||
| os.Exit(1) | ||
| } | ||
| out = tmp | ||
| fmt.Fprintf(os.Stderr, "using temp out-dir %s\n", out) | ||
| } | ||
| if err := os.MkdirAll(out, 0o755); err != nil { | ||
| fmt.Fprintf(os.Stderr, "out-dir: %v\n", err) | ||
| os.Exit(1) | ||
| } | ||
| if err := ensureCleanScoreOutput(out); err != nil { | ||
| fmt.Fprintf(os.Stderr, "out-dir: %v\n", err) | ||
| os.Exit(1) | ||
| } | ||
|
|
||
| var mu sync.Mutex | ||
| var reqs []*coltracepb.ExportTraceServiceRequest | ||
| srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) { | ||
| raw, err := io.ReadAll(r.Body) | ||
| if err != nil { | ||
| http.Error(w, err.Error(), http.StatusBadRequest) | ||
| return | ||
| } | ||
| if r.Header.Get("Content-Encoding") == "gzip" { | ||
| zr, err := gzip.NewReader(bytes.NewReader(raw)) | ||
| if err != nil { | ||
| http.Error(w, err.Error(), http.StatusBadRequest) | ||
| return | ||
| } | ||
| raw, err = io.ReadAll(zr) | ||
| _ = zr.Close() | ||
| if err != nil { | ||
| http.Error(w, err.Error(), http.StatusBadRequest) | ||
| return | ||
| } | ||
| } | ||
| var req coltracepb.ExportTraceServiceRequest | ||
| if err := proto.Unmarshal(raw, &req); err != nil { | ||
| http.Error(w, err.Error(), http.StatusBadRequest) | ||
| return | ||
| } | ||
| mu.Lock() | ||
| reqs = append(reqs, &req) | ||
| mu.Unlock() | ||
| resp, _ := proto.Marshal(&coltracepb.ExportTraceServiceResponse{}) | ||
| w.Header().Set("Content-Type", "application/x-protobuf") | ||
| _, _ = w.Write(resp) | ||
| })) | ||
| defer srv.Close() | ||
|
|
||
| _ = os.Setenv("OTEL_EXPORTER_OTLP_ENDPOINT", srv.URL) | ||
|
Member
There was a problem hiding this comment. [MEDIUM] The tool deliberately normalizes the OTLP environment before measuring — The suppression gate is now TraceID-scoped, so the false negative needs the ambient Suggestion: Add
Contributor
Author
There was a problem hiding this comment. Fixed in c530e9d.
|
||
| _ = os.Unsetenv("OTEL_EXPORTER_OTLP_TRACES_ENDPOINT") | ||
| _ = os.Unsetenv("OTEL_SDK_DISABLED") | ||
| // Clear ambient W3C parents so an unsampled TRACEPARENT from a prior | ||
| // fullsend run in this shell cannot suppress every score and make the | ||
| // prove tool report a false FAIL. | ||
| _ = os.Unsetenv("TRACEPARENT") | ||
| _ = os.Unsetenv("TRACESTATE") | ||
|
|
||
| results, stats, err := evalmeasure.MeasureAndExport(context.Background(), telem, reg, out, "dev") | ||
| if err != nil { | ||
| fmt.Fprintf(os.Stderr, "measure failed: %v\n", err) | ||
| os.Exit(1) | ||
| } | ||
|
|
||
| mu.Lock() | ||
| reqsCopy := append([]*coltracepb.ExportTraceServiceRequest(nil), reqs...) | ||
| nReqs := len(reqs) | ||
| mu.Unlock() | ||
|
|
||
| events := extractEvents(reqsCopy) | ||
| report := map[string]any{ | ||
| "endpoint": srv.URL, | ||
| "out_dir": out, | ||
| "scores_written": len(results), | ||
| "remote_export_warning": stats.RemoteExportWarning, | ||
| "results": results, | ||
| "otlp_requests": nReqs, | ||
| "events": events, | ||
| } | ||
| enc := json.NewEncoder(os.Stdout) | ||
| enc.SetIndent("", " ") | ||
| _ = enc.Encode(report) | ||
|
|
||
| if len(results) == 0 { | ||
| fmt.Fprintf(os.Stderr, "FAIL: no scores written\n") | ||
| os.Exit(1) | ||
| } | ||
| if nReqs == 0 { | ||
| fmt.Fprintf(os.Stderr, "FAIL: no OTLP requests received\n") | ||
| os.Exit(1) | ||
| } | ||
| if len(events) == 0 { | ||
| fmt.Fprintf(os.Stderr, "FAIL: no gen_ai.evaluation.result events\n") | ||
| os.Exit(1) | ||
| } | ||
| fmt.Fprintf(os.Stderr, "PASS: %d score(s), %d OTLP event(s)\n", len(results), len(events)) | ||
| } | ||
|
|
||
| // ensureCleanScoreOutput rejects an existing score artifact rather than | ||
| // deleting it. The proof tool writes a fresh derived-data pair so it cannot | ||
| // erase or append duplicate measurements in an operator's live run directory. | ||
| func ensureCleanScoreOutput(out string) error { | ||
| for _, name := range []string{evalmeasure.LedgerFile, evalmeasure.MeasurementsFile} { | ||
| path := filepath.Join(out, name) | ||
| if _, err := os.Stat(path); err == nil { | ||
| return fmt.Errorf("%s already exists; choose a fresh out-dir", path) | ||
| } else if !os.IsNotExist(err) { | ||
| return fmt.Errorf("stat %s: %w", path, err) | ||
| } | ||
| } | ||
| return nil | ||
| } | ||
|
|
||
| type eventView struct { | ||
| SpanName string `json:"span_name"` | ||
| TraceID string `json:"trace_id"` | ||
| ParentID string `json:"parent_span_id"` | ||
| EventName string `json:"event_name"` | ||
| Attributes map[string]any `json:"attributes"` | ||
| } | ||
|
|
||
| func extractEvents(reqs []*coltracepb.ExportTraceServiceRequest) []eventView { | ||
| var out []eventView | ||
| for _, req := range reqs { | ||
| for _, rs := range req.GetResourceSpans() { | ||
| for _, ss := range rs.GetScopeSpans() { | ||
| for _, sp := range ss.GetSpans() { | ||
| for _, ev := range sp.GetEvents() { | ||
| if ev.GetName() != evalmeasure.EventGenAIEvaluationResult { | ||
| continue | ||
| } | ||
| attrs := map[string]any{} | ||
| for _, kv := range ev.GetAttributes() { | ||
| attrs[kv.GetKey()] = anyValue(kv.GetValue()) | ||
| } | ||
| out = append(out, eventView{ | ||
| SpanName: sp.GetName(), | ||
| TraceID: hex.EncodeToString(sp.GetTraceId()), | ||
| ParentID: hex.EncodeToString(sp.GetParentSpanId()), | ||
| EventName: ev.GetName(), | ||
| Attributes: attrs, | ||
| }) | ||
| } | ||
| } | ||
| } | ||
| } | ||
| } | ||
| return out | ||
| } | ||
|
|
||
| func anyValue(v *commonpb.AnyValue) any { | ||
| if v == nil { | ||
| return nil | ||
| } | ||
| switch x := v.GetValue().(type) { | ||
| case *commonpb.AnyValue_StringValue: | ||
| return x.StringValue | ||
| case *commonpb.AnyValue_DoubleValue: | ||
| return x.DoubleValue | ||
| case *commonpb.AnyValue_IntValue: | ||
| return x.IntValue | ||
| case *commonpb.AnyValue_BoolValue: | ||
| return x.BoolValue | ||
| default: | ||
| return v.String() | ||
| } | ||
| } | ||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.