Integrate chunk plan caching into the runner

This commit is contained in:
2026-07-18 00:20:56 +00:00
parent ebd449d847
commit 51a36efb6b
15 changed files with 590 additions and 441 deletions

View File

@@ -58,36 +58,6 @@ func (l *WorkspaceLoader) Source(moduleKey string) (pipeline.SourceCheckpoint, p
return pipeline.SourceCheckpoint{Document: &doc}, reusedDecision()
}
func (l *WorkspaceLoader) Chunk(moduleKey string, sourceDigest string) (pipeline.ChunkCheckpoint, pipeline.CheckpointDecision) {
expectedDependencies := digestFingerprints("source_document", sourceDigest)
var manifest coreworkspace.ChunkManifest
if decision := l.readJSON("chunk/manifest.json", &manifest); !decision.Reused {
return pipeline.ChunkCheckpoint{}, decision
}
if decision := l.validateManifest(manifest.StageManifest, coreworkspace.StageChunk, "", moduleKey, coreworkspace.StatusSucceeded, expectedDependencies); !decision.Reused {
return pipeline.ChunkCheckpoint{}, decision
}
var payload chunksEnvelope
if decision := l.readJSON("chunk/chunks.json", &payload); !decision.Reused {
return pipeline.ChunkCheckpoint{}, decision
}
chunks, err := sourceChunksFromEnvelope(payload.Chunks)
if err != nil {
return pipeline.ChunkCheckpoint{}, invalidDecision("chunk checkpoint payload is invalid: %v", err)
}
if len(chunks) == 0 {
return pipeline.ChunkCheckpoint{}, invalidDecision("chunk checkpoint payload has no chunks")
}
outputDigests, err := chunkOutputDigests(chunks)
if err != nil {
return pipeline.ChunkCheckpoint{}, invalidDecision("chunk checkpoint output cannot be digested: %v", err)
}
if !fingerprintsEqual(coreworkspaceToPipelineFingerprints(manifest.OutputDigests), outputDigests) {
return pipeline.ChunkCheckpoint{}, invalidDecision("chunk checkpoint output digests do not match payload")
}
return pipeline.ChunkCheckpoint{Chunks: chunks, Warnings: cloneWarnings(payload.Warnings)}, reusedDecision()
}
func (l *WorkspaceLoader) Extract(laneID, moduleKey string, dependencies []pipeline.CheckpointFingerprint) (pipeline.ExtractCheckpoint, pipeline.CheckpointDecision) {
var manifest coreworkspace.ExtractLaneManifest
if d := l.readJSON(laneManifestPath("extract", laneID), &manifest); !d.Reused {
@@ -232,40 +202,6 @@ func (l *WorkspaceLoader) validateLaneManifest(manifest coreworkspace.StageManif
return reusedDecision()
}
func sourceChunksFromEnvelope(values []chunkEnvelope) ([]source.Chunk, error) {
if len(values) == 0 {
return nil, nil
}
out := make([]source.Chunk, 0, len(values))
for _, value := range values {
content, err := contentFromEnvelope(value.Content)
if err != nil {
return nil, err
}
annotations, err := source.CanonicalizeChunkAnnotations(value.Annotations)
if err != nil {
return nil, fmt.Errorf("canonicalize chunk %q annotations: %w", value.ID, err)
}
planAnnotations, err := source.CanonicalizeChunkAnnotations(value.PlanAnnotations)
if err != nil {
return nil, fmt.Errorf("canonicalize chunk %q plan_annotations: %w", value.ID, err)
}
out = append(out, source.Chunk{
ID: value.ID,
SourceID: value.SourceID,
Index: value.Index,
Ref: value.Ref,
Content: content,
MediaType: value.Content.MediaType,
Units: cloneSourceUnits(value.Units),
Metadata: cloneMetadata(value.Metadata),
Annotations: annotations,
PlanAnnotations: planAnnotations,
})
}
return out, nil
}
func contentFromEnvelope(value binaryEnvelope) ([]byte, error) {
content, err := base64.StdEncoding.DecodeString(value.ContentBase64)
if err != nil {