Move chunks into the canonical source model

This commit is contained in:
2026-07-17 05:32:11 +00:00
parent 40709e4ad8
commit 075888c97f
33 changed files with 548 additions and 325 deletions

View File

@@ -173,7 +173,7 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (output RunOutput, err
return failOutput(output), fmt.Errorf("build chunker %q: %w", input.Pipeline.Chunk.Module, err)
}
attachModuleManifestMetadata(&output, "chunker", chunker)
var canonicalChunks []contracts.SourceChunk
var canonicalChunks []source.Chunk
var chunkWarnings []contracts.Warning
chunkCheckpoint, chunkDecision := checkpointLoader.Chunk(chunker.Key(), doc.Digest)
recordCheckpointEvent(&output, checkpointLoader, string(StageChunk), "", chunker.Key(), chunkDecision)
@@ -388,7 +388,7 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (output RunOutput, err
return output, nil
}
func (r *Runner) runLane(ctx context.Context, input RunInput, checkpoints CheckpointRecorder, checkpointLoader CheckpointLoader, doc *source.SourceDocument, sourceInput contracts.LLMInputMaterial, sessionID string, chunks []contracts.SourceChunk, lane ResolvedArtifactLane, output *RunOutput) error {
func (r *Runner) runLane(ctx context.Context, input RunInput, checkpoints CheckpointRecorder, checkpointLoader CheckpointLoader, doc *source.SourceDocument, sourceInput contracts.LLMInputMaterial, sessionID string, chunks []source.Chunk, lane ResolvedArtifactLane, output *RunOutput) error {
extractor, err := r.registries.Extractors.Build(lane.Extract.Module)
if err != nil {
return fmt.Errorf("build extractor %q for lane %q: %w", lane.Extract.Module, lane.ID, err)
@@ -406,7 +406,11 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, checkpoints Checkp
extractOutputs := make([]contracts.ExtractOutput, 0, len(chunks))
extractWarnings := []contracts.Warning{}
extractRejectedStart := len(output.Rejected)
extractDependencies := digestFingerprints("chunks", joinedChunkDigest(chunks))
chunksDigest, err := joinedChunkDigest(chunks)
if err != nil {
return fmt.Errorf("digest chunks for lane %q: %w", lane.ID, err)
}
extractDependencies := digestFingerprints("chunks", chunksDigest)
extractCheckpoint, extractDecision := checkpointLoader.Extract(lane.ID, extractor.Key(), extractDependencies)
recordCheckpointEvent(output, checkpointLoader, string(StageExtract), lane.ID, extractor.Key(), extractDecision)
extractStarted := time.Now().UTC()
@@ -887,8 +891,8 @@ type rawValidationTarget struct {
llmClient contracts.StructuredLLMClient
chunkID string
chunkIndex int
chunk *contracts.SourceChunk
chunks []contracts.SourceChunk
chunk *source.Chunk
chunks []source.Chunk
schema contracts.ResponseSchema
payload contracts.RawPayload
extractOutputs []contracts.ExtractOutput
@@ -946,7 +950,7 @@ func runWithRetry(ctx context.Context, retries int, run func(attempt int) (bool,
return false, lastRejection, nil
}
func (r *Runner) validateChunksRaw(ctx context.Context, doc *source.SourceDocument, moduleKey string, chunks []contracts.SourceChunk, sourceInput contracts.LLMInputMaterial, sessionID string, references contracts.ReferenceSet, llmClient contracts.StructuredLLMClient, metadata map[string]any, chains []ResolvedValidatorChain, attempt int, debug DebugRecorder) ([]contracts.Warning, *contracts.RejectedOutput, error) {
func (r *Runner) validateChunksRaw(ctx context.Context, doc *source.SourceDocument, moduleKey string, chunks []source.Chunk, sourceInput contracts.LLMInputMaterial, sessionID string, references contracts.ReferenceSet, llmClient contracts.StructuredLLMClient, metadata map[string]any, chains []ResolvedValidatorChain, attempt int, debug DebugRecorder) ([]contracts.Warning, *contracts.RejectedOutput, error) {
return r.validateRaw(ctx, rawValidationTarget{
stage: StageChunk,
moduleKey: moduleKey,
@@ -1463,7 +1467,7 @@ func sourceInputMaterial(inputPath string, content []byte) contracts.LLMInputMat
)
}
func chunkInputMaterial(sourceInput contracts.LLMInputMaterial, chunk contracts.SourceChunk) contracts.LLMInputMaterial {
func chunkInputMaterial(sourceInput contracts.LLMInputMaterial, chunk source.Chunk) contracts.LLMInputMaterial {
return contracts.NewLLMInputMaterial(
"source",
chunk.MediaType,
@@ -1537,7 +1541,7 @@ func cloneResponseSchema(schema contracts.ResponseSchema) contracts.ResponseSche
return schema
}
func cloneSourceChunkPtr(chunk *contracts.SourceChunk) *contracts.SourceChunk {
func cloneSourceChunkPtr(chunk *source.Chunk) *source.Chunk {
if chunk == nil {
return nil
}
@@ -1545,18 +1549,18 @@ func cloneSourceChunkPtr(chunk *contracts.SourceChunk) *contracts.SourceChunk {
return &cloned
}
func cloneSourceChunk(chunk contracts.SourceChunk) contracts.SourceChunk {
func cloneSourceChunk(chunk source.Chunk) source.Chunk {
chunk.Content = append([]byte(nil), chunk.Content...)
chunk.Units = cloneSourceUnits(chunk.Units)
chunk.Metadata = cloneMetadata(chunk.Metadata)
return chunk
}
func cloneSourceChunks(chunks []contracts.SourceChunk) []contracts.SourceChunk {
func cloneSourceChunks(chunks []source.Chunk) []source.Chunk {
if len(chunks) == 0 {
return nil
}
out := make([]contracts.SourceChunk, 0, len(chunks))
out := make([]source.Chunk, 0, len(chunks))
for _, chunk := range chunks {
out = append(out, cloneSourceChunk(chunk))
}