Feat/telemetry http exporter (#314)

* feat(telemetry): add OTLP HTTP exporter and print TraceID

- Add HTTP/protobuf exporter support alongside existing gRPC exporter
- Route based on OTEL_EXPORTER_OTLP_PROTOCOL config (http/protobuf vs grpc)
- Print TraceID to stderr when telemetry is enabled for easier correlation
- Add corresponding unit tests

* feat(telemetry): add span coverage for LLM calls, tool execution, plan/filter phases

- Add StartLLMSpan / RecordLLMResult helpers (span.go), symmetric with
  existing StartToolSpan / RecordToolResult
- Wrap LLM completion calls in llmloop.RunPerFile with llm.request spans
- Wrap all three tool execution paths in executeToolCall with
  tool.execute.* spans (dynamic tools, code_comment sync/async, other tools)
- Add plan.execute span around executePlanPhase
- Add main.loop span around RunPerFile call in executeSubtask
- Add review_filter.execute span around executeReviewFilter, with
  comments.before / comments.filtered attributes
- Record llm.error attribute on LLM failures for diagnosability
- Record review.repo / review.from / review.to / review.model on the
  top-level review.run span
- Metrics (RecordLLMRequest / RecordToolCall) are preserved alongside
  the new spans — they serve different purposes (aggregate dashboards
  vs per-run diagnosis)

Verified end-to-end against Sunfire (OTLP HTTP gateway): full span tree
observed for review.run -> subtask.execute -> plan.execute/main.loop/
review_filter.execute -> llm.request/tool.execute.*

* fix(telemetry): address CR findings — span error handling, async span lifecycle, protocol robustness

- Add span.RecordError(err) to RecordLLMResult and RecordToolResult for
  consistency with EndSpan
- Use OTel standard pattern (span.SetStatus + span.RecordError) in error
  paths of review.run, plan.execute, main.loop, review_filter.execute
- Move async code_comment span end into pool.Submit callback so span
  duration reflects actual execution time
- Unify time.Since(startTime) in code_comment error path to a single dur
- Remove http/json from supported OTLP protocols (not actually implemented)
- Add stderr warning when unknown OTLP protocol falls back to gRPC

* feat(telemetry): include trace_id in JSON output, restrict stderr to text format

- Add trace_id as top-level field in jsonOutput struct (omitempty)
- JSON format: trace_id in structured response for programmatic extraction
- Text format: TraceID printed to stderr for human debugging
- Telemetry disabled: trace_id field omitted entirely

* fix: address PR review findings

- loop.go: wrap async span lifecycle in defer to prevent leak on panic
- exporter.go: update parseOTLPEndpoint comment to reflect gRPC+HTTP usage
- scan_cmd.go: align traceID extraction and OTel error handling with review_cmd
- output.go/shared.go: propagate traceID to outputJSONNoFiles for consistency
- agent.go: move comments.filtered attribute before early return so 0 is
  distinguishable from not-executed

* feat(telemetry): address PR review — http/json routing, LLM span coverage, trace_id tests

- Route http/json to HTTP exporter (Go OTel SDK HTTP transport only
  supports protobuf serialization; users need HTTP transport, not JSON encoding)
- Add llm.request spans to executePlanPhase, executeReviewFilter, and
  ReLocateComment with Usage nil-safety consistent with loop.go
- Add trace_id assertions to output helper tests and emitRunResult
  end-to-end tests using real TracerProvider

* docs: add OTLP protocol selection and endpoint format to telemetry section

Sync across all 5 README language versions (en, zh-CN, ja-JP, ko-KR, ru-RU).

* fix: unify time.Since in async code_comment defer to single dur variable
This commit is contained in:
xujiejie 2026-07-08 13:12:21 +08:00 committed by GitHub
parent 14f1c22a60
commit 46dde274d8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 471 additions and 24 deletions

View file

@ -7,6 +7,9 @@ import (
"testing"
"time"
"go.opentelemetry.io/otel"
sdktrace "go.opentelemetry.io/otel/sdk/trace"
"github.com/open-code-review/open-code-review/internal/agent"
"github.com/open-code-review/open-code-review/internal/model"
)
@ -175,3 +178,61 @@ func TestEmitRunResult_NilQuietHandle(t *testing.T) {
})
_ = got
}
func TestEmitRunResult_JSONTraceIDFromContext(t *testing.T) {
tp := sdktrace.NewTracerProvider()
defer tp.Shutdown(context.Background())
otel.SetTracerProvider(tp)
ctx, span := tp.Tracer("test").Start(context.Background(), "test-root")
wantTraceID := span.SpanContext().TraceID().String()
defer span.End()
ag := &mockResultProvider{
filesReviewed: 2,
inputTokens: 10,
outputTokens: 5,
totalTokens: 15,
}
got := captureStdout(t, func() {
err := emitRunResult(ctx, ag, nil, time.Now(), "json", "developer", nil)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
})
var out jsonOutput
if err := json.Unmarshal([]byte(got), &out); err != nil {
t.Fatalf("unmarshal: %v", err)
}
if out.TraceID != wantTraceID {
t.Errorf("trace_id = %q, want %q", out.TraceID, wantTraceID)
}
}
func TestEmitRunResult_JSONNoFilesTraceID(t *testing.T) {
tp := sdktrace.NewTracerProvider()
defer tp.Shutdown(context.Background())
otel.SetTracerProvider(tp)
ctx, span := tp.Tracer("test").Start(context.Background(), "test-root")
wantTraceID := span.SpanContext().TraceID().String()
defer span.End()
ag := &mockResultProvider{filesReviewed: 0}
got := captureStdout(t, func() {
err := emitRunResult(ctx, ag, nil, time.Now(), "json", "developer", nil)
if err != nil {
t.Fatalf("unexpected error: %v", err)
}
})
var out jsonOutput
if err := json.Unmarshal([]byte(got), &out); err != nil {
t.Fatalf("unmarshal: %v", err)
}
if out.Status != "skipped" {
t.Errorf("status = %q, want skipped", out.Status)
}
if out.TraceID != wantTraceID {
t.Errorf("trace_id = %q, want %q", out.TraceID, wantTraceID)
}
}

View file

@ -240,6 +240,7 @@ type jsonToolCalls struct {
type jsonOutput struct {
Status string `json:"status"`
TraceID string `json:"trace_id,omitempty"`
Message string `json:"message,omitempty"`
Summary *jsonSummary `json:"summary,omitempty"`
ToolCalls *jsonToolCalls `json:"tool_calls"`
@ -263,9 +264,10 @@ func outputJSON(comments []model.LlmComment) error {
func outputJSONWithWarnings(comments []model.LlmComment, warnings []agent.AgentWarning,
filesReviewed, inputTokens, outputTokens, totalTokens, cacheReadTokens, cacheWriteTokens int64,
duration time.Duration, projectSummary string, toolCalls map[string]int64) error {
duration time.Duration, projectSummary string, toolCalls map[string]int64, traceID string) error {
out := jsonOutput{
Status: "success",
TraceID: traceID,
Comments: comments,
Summary: &jsonSummary{
FilesReviewed: filesReviewed,
@ -311,9 +313,10 @@ func outputJSONWithWarnings(comments []model.LlmComment, warnings []agent.AgentW
return enc.Encode(out)
}
func outputJSONNoFiles() error {
func outputJSONNoFiles(traceID string) error {
out := jsonOutput{
Status: "skipped",
TraceID: traceID,
Message: "No supported files changed.",
Comments: []model.LlmComment{},
ToolCalls: &jsonToolCalls{

View file

@ -168,8 +168,7 @@ func TestOutputJSONWithWarnings_NoCommentsSubtaskError(t *testing.T) {
os.Stdout = w
warnings := []agent.AgentWarning{{Type: "subtask_error", File: "x.go", Message: "fail"}}
err := outputJSONWithWarnings(nil, warnings, 1, 10, 5, 15, 0, 0, time.Second, "", nil)
err := outputJSONWithWarnings(nil, warnings, 1, 10, 5, 15, 0, 0, time.Second, "", nil, "abc123trace")
w.Close()
os.Stdout = old
@ -188,6 +187,9 @@ func TestOutputJSONWithWarnings_NoCommentsSubtaskError(t *testing.T) {
if !strings.Contains(out.Message, "errors") {
t.Errorf("message = %q, expected to mention errors", out.Message)
}
if out.TraceID != "abc123trace" {
t.Errorf("trace_id = %q, want abc123trace", out.TraceID)
}
}
func TestStatusBadge(t *testing.T) {
@ -275,8 +277,7 @@ func TestOutputJSONWithWarnings(t *testing.T) {
comments := []model.LlmComment{{Path: "b.go", Content: "test"}}
warnings := []agent.AgentWarning{{Type: "subtask_error", File: "c.go", Message: "failed"}}
err := outputJSONWithWarnings(comments, warnings, 5, 100, 50, 150, 10, 5, 3*time.Second, "summary", map[string]int64{"file_read": 3})
err := outputJSONWithWarnings(comments, warnings, 5, 100, 50, 150, 10, 5, 3*time.Second, "summary", map[string]int64{"file_read": 3}, "trace-xyz-789")
w.Close()
os.Stdout = old
@ -301,6 +302,9 @@ func TestOutputJSONWithWarnings(t *testing.T) {
if out.ToolCalls == nil || out.ToolCalls.Total != 3 {
t.Errorf("ToolCalls.Total = %v", out.ToolCalls)
}
if out.TraceID != "trace-xyz-789" {
t.Errorf("trace_id = %q, want trace-xyz-789", out.TraceID)
}
}
func TestOutputJSONWithWarnings_NoCommentsNoErrors(t *testing.T) {
@ -309,8 +313,7 @@ func TestOutputJSONWithWarnings_NoCommentsNoErrors(t *testing.T) {
os.Stdout = w
warnings := []agent.AgentWarning{{Type: "warning", Message: "something"}}
err := outputJSONWithWarnings(nil, warnings, 2, 50, 20, 70, 0, 0, time.Second, "", nil)
err := outputJSONWithWarnings(nil, warnings, 2, 50, 20, 70, 0, 0, time.Second, "", nil, "")
w.Close()
os.Stdout = old
@ -336,7 +339,7 @@ func TestOutputJSONNoFiles(t *testing.T) {
r, w, _ := os.Pipe()
os.Stdout = w
err := outputJSONNoFiles()
err := outputJSONNoFiles("test-trace-id-456")
w.Close()
os.Stdout = old
@ -353,6 +356,9 @@ func TestOutputJSONNoFiles(t *testing.T) {
if out.Status != "skipped" {
t.Errorf("status = %q, want skipped", out.Status)
}
if out.TraceID != "test-trace-id-456" {
t.Errorf("trace_id = %q, want test-trace-id-456", out.TraceID)
}
}
func captureStdout(t *testing.T, fn func()) string {

View file

@ -13,6 +13,8 @@ import (
"github.com/open-code-review/open-code-review/internal/mcp"
"github.com/open-code-review/open-code-review/internal/telemetry"
"github.com/open-code-review/open-code-review/internal/tool"
"go.opentelemetry.io/otel/codes"
)
func runReview(args []string) error {
@ -104,11 +106,23 @@ func runReview(args []string) error {
ctx, span := telemetry.StartSpan(context.Background(), "review.run")
defer span.End()
telemetry.SetAttr(span, "review.repo", cc.RepoDir)
telemetry.SetAttr(span, "review.from", opts.from)
telemetry.SetAttr(span, "review.to", opts.to)
telemetry.SetAttr(span, "review.model", rt.Model)
var traceID string
if telemetry.IsEnabled() {
traceID = telemetry.TraceIDFromContext(ctx)
if opts.outputFormat != "json" {
fmt.Fprintf(os.Stderr, "[ocr] TraceID: %s\n", traceID)
}
}
startTime := time.Now()
comments, err := ag.Run(ctx)
if err != nil {
telemetry.SetAttr(span, "error", err.Error())
span.SetStatus(codes.Error, err.Error())
span.RecordError(err)
return fmt.Errorf("review failed: %w", err)
}

View file

@ -3,6 +3,7 @@ package main
import (
"context"
"fmt"
"os"
"strings"
"time"
@ -11,6 +12,8 @@ import (
"github.com/open-code-review/open-code-review/internal/scan"
"github.com/open-code-review/open-code-review/internal/telemetry"
"github.com/open-code-review/open-code-review/internal/tool"
"go.opentelemetry.io/otel/codes"
)
// scanOptions mirrors reviewOptions for the full-scan subcommand. The two
@ -207,11 +210,19 @@ func runScan(args []string) error {
ctx, span := telemetry.StartSpan(context.Background(), "scan.run")
defer span.End()
var traceID string
if telemetry.IsEnabled() {
traceID = telemetry.TraceIDFromContext(ctx)
if opts.outputFormat != "json" {
fmt.Fprintf(os.Stderr, "[ocr] TraceID: %s\n", traceID)
}
}
startTime := time.Now()
comments, err := ag.Run(ctx)
if err != nil {
telemetry.SetAttr(span, "error", err.Error())
span.SetStatus(codes.Error, err.Error())
span.RecordError(err)
return fmt.Errorf("scan failed: %w", err)
}

View file

@ -276,8 +276,10 @@ func emitRunResult(
telemetry.RecordCommentsGenerated(ctx, int64(len(comments)))
}
traceID := telemetry.TraceIDFromContext(ctx)
if outputFormat == "json" && len(comments) == 0 && ag.FilesReviewed() == 0 {
return outputJSONNoFiles()
return outputJSONNoFiles(traceID)
}
// Agent-text audiences need stdout back before PrintTraceSummary so the
@ -296,7 +298,7 @@ func emitRunResult(
return outputJSONWithWarnings(comments, ag.Warnings(), ag.FilesReviewed(),
ag.TotalInputTokens(), ag.TotalOutputTokens(), ag.TotalTokensUsed(),
ag.TotalCacheReadTokens(), ag.TotalCacheWriteTokens(), duration,
ag.ProjectSummary(), ag.ToolCalls())
ag.ProjectSummary(), ag.ToolCalls(), traceID)
}
outputTextWithWarnings(comments, ag.Warnings())
if summary := ag.ProjectSummary(); summary != "" {