eric/notarius
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Implement generated artifact handoff and provenance

Browse Source
This commit is contained in:
Eric Rakestraw
2026-07-21 21:39:23 +00:00
parent afb7ed3cf1
commit 22d4f29670
12 changed files with 749 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
internal/framework/pipeline/runner_concurrent.go
View File

@@ -230,7 +230,9 @@ func prepareLaneExtract(input RunInput, loader CheckpointLoader, doc *source.Sou
if err != nil {
return nil, fmt.Errorf("digest chunks for lane %q: %w", lane.ID, err)
}
state := &laneExtractState{index: index, prepared: prepared, deps: digestFingerprints("chunks", digest), remaining: len(chunks), results: make(map[int]extractJobResult, len(chunks))}
extractReferences := operationReferenceSet(input, lane.ExtractReferences)
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, lane.ID, lane.Extract.Module, state.deps)
if decision.Reused {
for _, stored := range cp.Outputs {
@@ -285,7 +287,8 @@ func (r *Runner) runExtractJob(ctx context.Context, input RunInput, doc *source.
if metadataErr != nil {
return false, nil, terminal.record(nil, fmt.Errorf("clone extract request metadata: %w", metadataErr))
}
extracted, callErr := typed.extract(attemptCtx, typed.extractor, contracts.TypedExtractionRequest{Source: doc, Chunk: &chunk, SourceInput: chunkInputMaterial(sourceInput, chunk), SessionID: sessionID, References: CloneReferenceSet(lane.ExtractReferences.ReferenceSet), LLMProfile: lane.Extract.LLMProfile, Metadata: requestMetadata})
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)
@@ -299,7 +302,7 @@ func (r *Runner) runExtractJob(ctx context.Context, input RunInput, doc *source.
return false, nil, 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: lane.ExtractReferences.ReferenceSet, metadata: input.Metadata, chunk: &chunk, ref: chunk.Ref, value: extracted.Value, candidate: &serializedCandidate}, state.prepared.extractValidators, attempt, input.Debug)
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 {
@@ -440,7 +443,7 @@ func mergeLaneOutput(dst *RunOutput, src RunOutput) error {
dst.CheckpointEvents = append(dst.CheckpointEvents, src.CheckpointEvents...)
for i := range dst.Manifest.ArtifactLanes {
for j := range src.Manifest.ArtifactLanes {
if dst.Manifest.ArtifactLanes[i].ID == src.Manifest.ArtifactLanes[j].ID && src.Manifest.ArtifactLanes[j].Metadata != nil {
if dst.Manifest.ArtifactLanes[i].ID == src.Manifest.ArtifactLanes[j].ID && dst.Manifest.ArtifactLanes[i].StepID == src.Manifest.ArtifactLanes[j].StepID && src.Manifest.ArtifactLanes[j].Metadata != nil {
metadata, err := cloneMetadata(src.Manifest.ArtifactLanes[j].Metadata)
if err != nil {
return fmt.Errorf("clone lane %q manifest metadata: %w", dst.Manifest.ArtifactLanes[i].ID, err)