Preserve terminal rejection warnings

This commit is contained in:
2026-08-09 01:19:55 +00:00
parent 14bfae216d
commit 8e669a1f14
7 changed files with 254 additions and 76 deletions

View File

@@ -254,6 +254,9 @@ func (e *laneEngine) startContinuationWorkers() {
}
}
// collect is the sole owner of pending, launch, and completion accounting. It
// must drain closed extract results and one completion for every launched
// continuation, even after cancellation.
func (e *laneEngine) collect() {
resultChannel := (<-chan extractJobResult)(e.results)
for resultChannel != nil || len(e.pending) > 0 || e.completed < e.launched {
@@ -407,20 +410,20 @@ func (r *Runner) runExtractJob(ctx context.Context, input RunInput, doc *source.
var accepted erasedExtractArtifact
var serialized CheckpointArtifact
var acceptedWarnings []contracts.Warning
ok, rejection, err := runWithRetry(ctx, lane.Extract.Retries, func(attempt int) (bool, *contracts.RejectedOutput, error) {
retryResult, err := runWithRetry(ctx, lane.Extract.Retries, func(attempt int) (retryAttemptResult, error) {
started := time.Now().UTC()
attemptPath := path.Join("extract", fileio.EncodePathComponent(lane.ID), fmt.Sprintf("chunk-%06d", chunk.Index+1), fmt.Sprintf("attempt-%02d", attempt))
attemptCtx, llmScope := withDebugLLMScope(ctx, attemptPath)
terminal := newAttemptTerminalRecorder(input.Debug, attemptPath, "extract", llmScope, debugTimedEnvelope{Stage: string(StageExtract), StepID: input.stepID, LaneID: lane.ID, ModuleKey: lane.Extract.Module, Attempt: attempt, StartedAt: started})
requestMetadata, metadataErr := cloneMetadata(input.Metadata)
if metadataErr != nil {
return false, nil, terminal.record(nil, fmt.Errorf("clone extract request metadata: %w", metadataErr))
return retryAttemptResult{}, terminal.record(nil, fmt.Errorf("clone extract request metadata: %w", metadataErr))
}
extractReferences := operationReferenceSet(input, lane.ExtractReferences)
extracted, callErr := typed.extract(attemptCtx, typed.extractor, contracts.TypedExtractionRequest{Source: doc, Chunk: &chunk, SourceInput: chunkInputMaterial(sourceInput, chunk), SessionID: sessionID, References: CloneReferenceSet(extractReferences), LLMProfile: lane.Extract.LLMProfile, Metadata: requestMetadata})
if callErr != nil {
attemptErr := fmt.Errorf("extract lane %q chunk %q with extractor %q: %w", lane.ID, chunk.ID, lane.Extract.Module, callErr)
return false, nil, terminal.record(nil, attemptErr)
return retryAttemptResult{}, terminal.record(nil, attemptErr)
}
artifact := erasedExtractArtifact{LaneID: lane.ID, ExtractorKey: lane.Extract.Module, SourceID: doc.ID, ChunkID: chunk.ID, ChunkIndex: chunk.Index, ChunkRef: chunk.Ref, Value: extracted.Value}
attemptWarnings := cloneWarnings(extracted.Warnings)
@@ -428,31 +431,38 @@ func (r *Runner) runExtractJob(ctx context.Context, input RunInput, doc *source.
if encodeErr != nil {
attemptErr := fmt.Errorf("serialize extract candidate for lane %q chunk %q: %w", lane.ID, chunk.ID, encodeErr)
payload := map[string]any{"warnings": debugWarningEnvelopes(attemptWarnings)}
return false, nil, terminal.record(payload, attemptErr)
return retryAttemptResult{}, terminal.record(payload, attemptErr)
}
serializedCandidate.ChunkID, serializedCandidate.ChunkIndex, serializedCandidate.ChunkRef = artifact.ChunkID, artifact.ChunkIndex, artifact.ChunkRef
warnings, rejected, validateErr := r.validateTypedArtifact(attemptCtx, typed.codec, typedValidationTarget{stage: StageExtract, stepID: input.stepID, laneID: lane.ID, moduleKey: lane.Extract.Module, source: doc, sourceID: doc.ID, sourceInput: chunkInputMaterial(sourceInput, chunk), sessionID: sessionID, references: extractReferences, metadata: input.Metadata, chunk: &chunk, ref: chunk.Ref, value: extracted.Value, candidate: &serializedCandidate}, state.prepared.extractValidators, attempt, input.Debug)
attemptWarnings = append(attemptWarnings, warnings...)
payload := map[string]any{"output": debugCheckpointArtifact(serializedCandidate), "warnings": debugWarningEnvelopes(attemptWarnings), "rejection": debugRejectedOutputPtr(rejected)}
if validateErr != nil || rejected != nil {
return false, rejected, terminal.record(payload, validateErr)
if validateErr != nil {
return retryAttemptResult{}, terminal.record(payload, validateErr)
}
if rejected != nil {
if debugErr := terminal.record(payload, nil); debugErr != nil {
return retryAttemptResult{}, debugErr
}
return retryAttemptResult{rejection: rejected, warnings: attemptWarnings}, nil
}
stored, encodeErr := checkpointArtifact(typed.codec, artifact.LaneID, artifact.ExtractorKey, artifact.SourceID, artifact.Value)
if encodeErr != nil {
attemptErr := fmt.Errorf("serialize accepted extract output for lane %q chunk %q: %w", lane.ID, chunk.ID, encodeErr)
return false, nil, terminal.record(payload, attemptErr)
return retryAttemptResult{}, terminal.record(payload, attemptErr)
}
stored.ChunkID, stored.ChunkIndex, stored.ChunkRef = artifact.ChunkID, artifact.ChunkIndex, artifact.ChunkRef
accepted, serialized = artifact, stored
acceptedWarnings = attemptWarnings
if debugErr := terminal.record(payload, nil); debugErr != nil {
return false, nil, debugErr
return retryAttemptResult{}, debugErr
}
return true, nil, nil
return retryAttemptResult{accepted: true}, nil
})
result.err = err
if err == nil && !ok {
result.rejected = rejection
if err == nil && !retryResult.accepted {
result.rejected = retryResult.rejection
result.warnings = cloneWarnings(retryResult.warnings)
return result
}
result.value, result.serialized, result.warnings = accepted, serialized, acceptedWarnings
@@ -470,6 +480,7 @@ func finalizeLaneExtract(checkpoints CheckpointRecorder, stepID string, state *l
result := state.results[index]
if result.rejected != nil {
state.rejected = append(state.rejected, *result.rejected)
state.warnings = append(state.warnings, result.warnings...)
continue
}
state.values = append(state.values, result.value)