Add stable checkpoint decision diagnostics

This commit is contained in:
2026-07-22 02:13:50 +00:00
parent 5bdd56cfb1
commit 9de399432e
10 changed files with 391 additions and 155 deletions

View File

@@ -100,7 +100,7 @@ func initializeLaneStates(input RunInput, step PreparedPipelineStep, checkpoints
if err := setTypedLaneManifestMetadata(output, prepared.resolved.ID, prepared.typed.extractor, prepared.typed.merger, prepared.typed.normalizer); err != nil {
return nil, err
}
state, err := prepareLaneExtract(input, loader, doc, chunks, i, prepared)
state, err := prepareLaneExtract(input, loader, doc, chunks, i, prepared, output)
if err != nil {
return nil, err
}
@@ -175,6 +175,13 @@ func (r *Runner) runLaneEngine(parent context.Context, input RunInput, checkpoin
}()
}
completedOutputs, runErrors := collectLaneResults(ctx, cancel, input, checkpoints, chunks, states, results, completions, continuations)
close(continuations)
continuationWorkers.Wait()
return completedOutputs, runErrors
}
func collectLaneResults(ctx context.Context, cancel context.CancelFunc, input RunInput, checkpoints CheckpointRecorder, chunks []source.Chunk, states []*laneExtractState, results <-chan extractJobResult, completions <-chan laneCompletion, continuations chan<- *laneExtractState) ([]RunOutput, []orderedRunError) {
completedOutputs := make([]RunOutput, len(states))
var runErrors []orderedRunError
var pendingContinuations []*laneExtractState
@@ -184,7 +191,6 @@ func (r *Runner) runLaneEngine(parent context.Context, input RunInput, checkpoin
pendingContinuations = append(pendingContinuations, state)
}
}
resultChannel := results
for resultChannel != nil || len(pendingContinuations) > 0 || completed < launched {
var continuationChannel chan<- *laneExtractState
@@ -232,8 +238,6 @@ func (r *Runner) runLaneEngine(parent context.Context, input RunInput, checkpoin
}
}
}
close(continuations)
continuationWorkers.Wait()
return completedOutputs, runErrors
}
@@ -246,7 +250,7 @@ func mergeCompletedLanes(output *RunOutput, completedOutputs []RunOutput) error
return nil
}
func prepareLaneExtract(input RunInput, loader CheckpointLoader, doc *source.SourceDocument, chunks []source.Chunk, index int, prepared preparedLaneExecutor) (*laneExtractState, error) {
func prepareLaneExtract(input RunInput, loader CheckpointLoader, doc *source.SourceDocument, chunks []source.Chunk, index int, prepared preparedLaneExecutor, output *RunOutput) (*laneExtractState, error) {
lane, typed := prepared.resolved, prepared.typed
digest, err := joinedChunkDigest(chunks)
if err != nil {
@@ -256,7 +260,7 @@ func prepareLaneExtract(input RunInput, loader CheckpointLoader, doc *source.Sou
deps := append(digestFingerprints("chunks", digest), generatedReferenceDependencies(extractReferences)...)
state := &laneExtractState{index: index, prepared: prepared, deps: normalizeCheckpointFingerprints(deps), remaining: len(chunks), results: make(map[int]extractJobResult, len(chunks))}
cp, decision := loadExtract(loader, input.stepID, lane.ID, lane.Extract.Module, state.deps)
decision, err = resolveCheckpointDecision(nil, loader, input.CheckpointPolicy, StageExtract, input.stepID, lane.ID, lane.Extract.Module, decision, typed.codec, cp.Outputs)
decision, err = resolveCheckpointDecision(output, loader, input.CheckpointPolicy, StageExtract, input.stepID, lane.ID, lane.Extract.Module, decision, typed.codec, cp.Outputs)
if err != nil {
return nil, err
}
@@ -385,7 +389,6 @@ func (r *Runner) continueLane(ctx context.Context, input RunInput, checkpoints C
}
local.Warnings = append(local.Warnings, cloneWarnings(results.warnings)...)
local.Rejected = append(local.Rejected, cloneRejectedOutputs(results.rejected)...)
recordCheckpointEvent(&local, loader, string(StageExtract), input.stepID, lane.ID, lane.Extract.Module, results.decision)
if err := writeDebugTimed(input.Debug, path.Join("extract", debugPathComponent(lane.ID), "input.json"), debugTimedEnvelope{Stage: string(StageExtract), StepID: input.stepID, LaneID: lane.ID, ModuleKey: lane.Extract.Module, StartedAt: time.Now().UTC(), Payload: map[string]any{"reused": results.decision.Reused, "decision": results.decision, "source": debugSourceDocumentEnvelope(doc), "chunks": debugSourceChunkEnvelopes(chunks), "options": redactSensitiveMap(lane.Extract.Options), "metadata": redactSensitiveMap(input.Metadata)}}); err != nil {
return local, &laneRunError{stage: StageExtract, err: err}
}