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

@@ -21,7 +21,7 @@ type CheckpointRecorder interface {
SourceSucceeded(moduleKey string, doc *source.SourceDocument) error
SourceFailed(moduleKey string, err error) error
ChunkRunning(moduleKey string, sourceDigest string) error
ChunkSucceeded(moduleKey string, sourceDigest string, chunks []contracts.SourceChunk, warnings []contracts.Warning) error
ChunkSucceeded(moduleKey string, sourceDigest string, chunks []source.Chunk, warnings []contracts.Warning) error
ChunkRejected(moduleKey string, sourceDigest string, rejected contracts.RejectedOutput) error
ChunkFailed(moduleKey string, sourceDigest string, err error) error
ExtractRunning(laneID string, moduleKey string, dependencies []CheckpointFingerprint) error
@@ -55,7 +55,7 @@ type SourceCheckpoint struct {
}
type ChunkCheckpoint struct {
Chunks []contracts.SourceChunk
Chunks []source.Chunk
Warnings []contracts.Warning
}
@@ -94,7 +94,7 @@ func (noopCheckpointRecorder) SourceRunning(string) error
func (noopCheckpointRecorder) SourceSucceeded(string, *source.SourceDocument) error { return nil }
func (noopCheckpointRecorder) SourceFailed(string, error) error { return nil }
func (noopCheckpointRecorder) ChunkRunning(string, string) error { return nil }
func (noopCheckpointRecorder) ChunkSucceeded(string, string, []contracts.SourceChunk, []contracts.Warning) error {
func (noopCheckpointRecorder) ChunkSucceeded(string, string, []source.Chunk, []contracts.Warning) error {
return nil
}
func (noopCheckpointRecorder) ChunkRejected(string, string, contracts.RejectedOutput) error {
@@ -180,17 +180,21 @@ func digestFingerprints(name string, digest string) []CheckpointFingerprint {
return []CheckpointFingerprint{{Name: name, Value: digest}}
}
func joinedChunkDigest(chunks []contracts.SourceChunk) string {
func joinedChunkDigest(chunks []source.Chunk) (string, error) {
if len(chunks) == 0 {
return ""
return "", nil
}
values := make([]string, 0, len(chunks))
for _, chunk := range chunks {
values = append(values, chunk.ID+"="+checkpointContentDigest(chunk.Content))
digest, err := source.DigestChunk(chunk)
if err != nil {
return "", fmt.Errorf("digest chunk %q: %w", chunk.ID, err)
}
values = append(values, chunk.ID+"="+digest)
}
sort.Strings(values)
sum := sha256.Sum256([]byte(strings.Join(values, "\n")))
return "sha256:" + hex.EncodeToString(sum[:])
return "sha256:" + hex.EncodeToString(sum[:]), nil
}
func normalizeCheckpointFingerprints(values []CheckpointFingerprint) []CheckpointFingerprint {