mirror of
https://github.com/alibaba/open-code-review.git
synced 2026-07-09 17:28:58 +00:00
* 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
308 lines
11 KiB
Go
308 lines
11 KiB
Go
package main
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"os"
|
|
"path/filepath"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/open-code-review/open-code-review/internal/agent"
|
|
"github.com/open-code-review/open-code-review/internal/config/rules"
|
|
"github.com/open-code-review/open-code-review/internal/config/template"
|
|
"github.com/open-code-review/open-code-review/internal/config/toolsconfig"
|
|
"github.com/open-code-review/open-code-review/internal/diff"
|
|
"github.com/open-code-review/open-code-review/internal/gitcmd"
|
|
"github.com/open-code-review/open-code-review/internal/llm"
|
|
"github.com/open-code-review/open-code-review/internal/model"
|
|
"github.com/open-code-review/open-code-review/internal/stdout"
|
|
"github.com/open-code-review/open-code-review/internal/telemetry"
|
|
"github.com/open-code-review/open-code-review/internal/tool"
|
|
)
|
|
|
|
// commonContext bundles the state that both `ocr review` and `ocr scan`
|
|
// need to load *before* deciding whether to dispatch a preview or a real
|
|
// LLM session: a validated template, the resolved repo path, review rules,
|
|
// and a shared git subprocess limiter.
|
|
type commonContext struct {
|
|
Template *template.Template
|
|
RepoDir string
|
|
Resolver rules.Resolver
|
|
FileFilter *rules.FileFilter
|
|
GitRunner *gitcmd.Runner
|
|
// IsGitRepo reports whether RepoDir is inside a git repository. Always
|
|
// true when requireGit was set; may be false when scan accepts non-git
|
|
// directories.
|
|
IsGitRepo bool
|
|
}
|
|
|
|
// loadCommonContext validates the working directory, loads the embedded
|
|
// template, raises MaxToolRequestTimes when maxTools exceeds the default,
|
|
// resolves the absolute repo path, loads system review rules, and creates
|
|
// the global git subprocess limiter. Both review and scan callers go
|
|
// through this so the startup sequence stays consistent.
|
|
//
|
|
// requireGit=true fails fast when the directory is not a git repo (review
|
|
// path: diff concept requires git). requireGit=false allows non-git
|
|
// directories (scan path: provider falls back to filepath.Walk).
|
|
func loadCommonContext(repoDirInput, rulePath string, maxTools, maxGitProcs int, requireGit bool) (*commonContext, error) {
|
|
tpl, err := template.LoadDefault()
|
|
if err != nil {
|
|
return nil, fmt.Errorf("load default template: %w", err)
|
|
}
|
|
if maxTools > tpl.MaxToolRequestTimes {
|
|
tpl.MaxToolRequestTimes = maxTools
|
|
}
|
|
if err := tpl.Validate(); err != nil {
|
|
return nil, fmt.Errorf("invalid config: %w", err)
|
|
}
|
|
|
|
repoDir, isGit, err := resolveWorkingDir(repoDirInput, requireGit)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
resolver, fileFilter, err := rules.NewResolver(repoDir, rulePath)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("load rules: %w", err)
|
|
}
|
|
|
|
return &commonContext{
|
|
Template: tpl,
|
|
RepoDir: repoDir,
|
|
Resolver: resolver,
|
|
FileFilter: fileFilter,
|
|
GitRunner: gitcmd.New(maxGitProcs),
|
|
IsGitRepo: isGit,
|
|
}, nil
|
|
}
|
|
|
|
// resolveWorkingDir returns (absPath, isGitRepo, err). When requireGit is
|
|
// true, returns an error if the directory is not a git repo. When false,
|
|
// returns IsGitRepo=false instead of erroring (scan path uses this).
|
|
func resolveWorkingDir(input string, requireGit bool) (string, bool, error) {
|
|
if input == "" {
|
|
wd, err := os.Getwd()
|
|
if err != nil {
|
|
return "", false, fmt.Errorf("get working directory: %w", err)
|
|
}
|
|
input = wd
|
|
}
|
|
absPath, err := filepath.Abs(input)
|
|
if err != nil {
|
|
return "", false, fmt.Errorf("resolve absolute path: %w", err)
|
|
}
|
|
if _, statErr := os.Stat(absPath); statErr != nil {
|
|
return "", false, fmt.Errorf("stat %s: %w", absPath, statErr)
|
|
}
|
|
out, err := runGitCmd(absPath, "rev-parse", "--git-dir")
|
|
isGit := err == nil && len(out) > 0
|
|
if !isGit && requireGit {
|
|
return "", false, fmt.Errorf("%s is not a git repository", absPath)
|
|
}
|
|
// #287: git reports diff and `git show HEAD:<path>` paths relative to the
|
|
// repository root, not the current directory. When `ocr review` runs from a
|
|
// subdirectory of a monorepo, anchor RepoDir at the git top-level so those
|
|
// root-relative paths resolve for both disk reads and git-show reads.
|
|
// requireGit is true only for the review path; scan (requireGit=false) keeps
|
|
// the CWD so its `git ls-files` walk stays scoped to the subdirectory.
|
|
if isGit && requireGit {
|
|
// runGitCmdStdout captures stdout only so git stderr notices can't
|
|
// pollute the resolved path. --show-toplevel fails (or is empty) when
|
|
// there is no work tree — e.g. a bare repo, where --git-dir succeeds so
|
|
// isGit is true. Fail loudly there instead of silently reusing the
|
|
// subdir, which would reproduce the #287 root-relative-path bug.
|
|
top, topErr := runGitCmdStdout(absPath, "rev-parse", "--show-toplevel")
|
|
t := strings.TrimSpace(string(top))
|
|
if topErr != nil || t == "" {
|
|
return "", false, fmt.Errorf("%s is a git repository without a work tree (bare repo?); cannot resolve its top level for review", absPath)
|
|
}
|
|
absPath = t
|
|
}
|
|
return absPath, isGit, nil
|
|
}
|
|
|
|
// llmRuntime bundles the LLM-side state both subcommands need once they've
|
|
// decided to actually run a session: tool definitions, an app-language
|
|
// adjusted template (mutated in place via ApplyLanguage), the LLM client,
|
|
// the resolved model name, and a fresh comment collector.
|
|
type llmRuntime struct {
|
|
Client llm.LLMClient
|
|
Model string
|
|
PlanToolDefs []llm.ToolDef
|
|
MainToolDefs []llm.ToolDef
|
|
Collector *tool.CommentCollector
|
|
AppCfg *Config
|
|
}
|
|
|
|
// loadLLMRuntime loads tool defs from toolConfigPath, reads the app config
|
|
// from the user's default config path (applying the configured language to
|
|
// tpl — defaulting when the config file is absent), resolves the LLM
|
|
// endpoint (honoring modelOverride from --model when non-empty), and
|
|
// returns the runtime bundle. tpl is mutated in place.
|
|
func loadLLMRuntime(tpl *template.Template, toolConfigPath, modelOverride string) (*llmRuntime, error) {
|
|
toolEntries, err := toolsconfig.Load(toolConfigPath)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("load tools: %w", err)
|
|
}
|
|
planToolDefs := agent.BuildToolDefs(toolEntries, true)
|
|
mainToolDefs := agent.BuildToolDefs(toolEntries, false)
|
|
|
|
cfgPath, err := defaultConfigPath()
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
appCfg, err := LoadAppConfig(cfgPath)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("load app config: %w", err)
|
|
}
|
|
// Apply the language directive even when the config file is missing
|
|
// (upstream #fix: ApplyLanguage with empty lang falls back to default).
|
|
var lang string
|
|
if appCfg != nil {
|
|
lang = appCfg.Language
|
|
}
|
|
tpl.ApplyLanguage(lang)
|
|
|
|
ep, err := llm.ResolveEndpointWithModelOverride(cfgPath, modelOverride)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("resolve LLM endpoint: %w", err)
|
|
}
|
|
|
|
return &llmRuntime{
|
|
Client: llm.NewLLMClient(ep),
|
|
Model: ep.Model,
|
|
PlanToolDefs: planToolDefs,
|
|
MainToolDefs: mainToolDefs,
|
|
Collector: tool.NewCommentCollector(),
|
|
AppCfg: appCfg,
|
|
}, nil
|
|
}
|
|
|
|
// applyCLIExcludes appends user-supplied --exclude patterns (already split
|
|
// into a []string) onto cc.FileFilter.Exclude. Creates the FileFilter if
|
|
// none was returned by rule.json layers. Idempotent on empty input.
|
|
func applyCLIExcludes(cc *commonContext, patterns []string) {
|
|
if len(patterns) == 0 {
|
|
return
|
|
}
|
|
if cc.FileFilter == nil {
|
|
cc.FileFilter = &rules.FileFilter{}
|
|
}
|
|
cc.FileFilter.Exclude = append(cc.FileFilter.Exclude, patterns...)
|
|
}
|
|
|
|
// excludeToolDef returns a copy of defs with any entries whose function name
|
|
// matches name removed. Used by `ocr scan` to hide tools that don't make
|
|
// sense in full-scan mode (e.g. file_read_diff).
|
|
func excludeToolDef(defs []llm.ToolDef, name string) []llm.ToolDef {
|
|
out := make([]llm.ToolDef, 0, len(defs))
|
|
for _, d := range defs {
|
|
if d.Function.Name == name {
|
|
continue
|
|
}
|
|
out = append(out, d)
|
|
}
|
|
return out
|
|
}
|
|
|
|
// quietHandle wraps a stdout.Quiet() restorer so callers can `defer
|
|
// q.Restore()` for safety while emitRunResult restores it early when the
|
|
// agent-text audience needs the trace summary on the user's terminal.
|
|
// Restore is idempotent.
|
|
type quietHandle struct {
|
|
fn func()
|
|
}
|
|
|
|
// newQuietHandle silences stdout when outputFormat=="json" or
|
|
// audience=="agent"; otherwise the returned handle is a no-op restorer.
|
|
func newQuietHandle(outputFormat, audience string) *quietHandle {
|
|
h := &quietHandle{}
|
|
if outputFormat == "json" || audience == "agent" {
|
|
h.fn = stdout.Quiet()
|
|
}
|
|
return h
|
|
}
|
|
|
|
// Restore re-enables stdout. Safe to call multiple times.
|
|
func (h *quietHandle) Restore() {
|
|
if h == nil || h.fn == nil {
|
|
return
|
|
}
|
|
h.fn()
|
|
h.fn = nil
|
|
}
|
|
|
|
// ResultProvider abstracts the metadata both internal/agent.Agent and
|
|
// internal/scan.Agent expose post-run, so emitRunResult can finalize
|
|
// either without knowing which kind it has.
|
|
type ResultProvider interface {
|
|
Diffs() []model.Diff
|
|
FilesReviewed() int64
|
|
TotalInputTokens() int64
|
|
TotalOutputTokens() int64
|
|
TotalTokensUsed() int64
|
|
TotalCacheReadTokens() int64
|
|
TotalCacheWriteTokens() int64
|
|
Warnings() []agent.AgentWarning
|
|
// ProjectSummary is the markdown project-level summary produced by
|
|
// scan's PROJECT_SUMMARY_TASK. Empty for review mode and for scans
|
|
// that skipped / failed the summary phase.
|
|
ProjectSummary() string
|
|
ToolCalls() map[string]int64
|
|
}
|
|
|
|
// emitRunResult is the post-LLM-run finalization shared by `ocr review` and
|
|
// `ocr scan`: resolves comment line numbers, records telemetry, restores
|
|
// stdout early for agent-text audiences so the summary is visible, prints
|
|
// the trace summary, and writes the result in the requested format.
|
|
//
|
|
// q is the silencing handle returned by newQuietHandle; pass nil if no
|
|
// silencing was set up (in which case the early restore is a no-op).
|
|
func emitRunResult(
|
|
ctx context.Context,
|
|
ag ResultProvider,
|
|
comments []model.LlmComment,
|
|
startTime time.Time,
|
|
outputFormat, audience string,
|
|
q *quietHandle,
|
|
) error {
|
|
comments = diff.ResolveLineNumbers(comments, ag.Diffs())
|
|
|
|
duration := time.Since(startTime)
|
|
telemetry.RecordReviewDuration(ctx, duration)
|
|
if len(comments) > 0 {
|
|
telemetry.RecordCommentsGenerated(ctx, int64(len(comments)))
|
|
}
|
|
|
|
traceID := telemetry.TraceIDFromContext(ctx)
|
|
|
|
if outputFormat == "json" && len(comments) == 0 && ag.FilesReviewed() == 0 {
|
|
return outputJSONNoFiles(traceID)
|
|
}
|
|
|
|
// Agent-text audiences need stdout back before PrintTraceSummary so the
|
|
// summary line lands on their terminal.
|
|
if audience == "agent" && outputFormat != "json" {
|
|
q.Restore()
|
|
}
|
|
|
|
if outputFormat != "json" {
|
|
telemetry.PrintTraceSummary(ag.FilesReviewed(), int64(len(comments)),
|
|
ag.TotalInputTokens(), ag.TotalOutputTokens(), ag.TotalTokensUsed(),
|
|
ag.TotalCacheReadTokens(), ag.TotalCacheWriteTokens(), duration)
|
|
}
|
|
|
|
if outputFormat == "json" {
|
|
return outputJSONWithWarnings(comments, ag.Warnings(), ag.FilesReviewed(),
|
|
ag.TotalInputTokens(), ag.TotalOutputTokens(), ag.TotalTokensUsed(),
|
|
ag.TotalCacheReadTokens(), ag.TotalCacheWriteTokens(), duration,
|
|
ag.ProjectSummary(), ag.ToolCalls(), traceID)
|
|
}
|
|
outputTextWithWarnings(comments, ag.Warnings())
|
|
if summary := ag.ProjectSummary(); summary != "" {
|
|
fmt.Printf("\n\n──────── Project Summary ────────\n\n%s\n", summary)
|
|
}
|
|
return nil
|
|
}
|