Write workspace checkpoints during runs

This commit is contained in:
2026-07-08 02:46:38 +00:00
parent f044c00a7c
commit 1d3a444df8
11 changed files with 1258 additions and 9 deletions

View File

@@ -0,0 +1,625 @@
package checkpoint
import (
"crypto/sha256"
"encoding/base64"
"encoding/hex"
"fmt"
"path"
"sort"
"strings"
"time"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
coreworkspace "gitea.maximumdirect.net/eric/notarius/internal/core/workspace"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
type WorkspaceRecorder struct {
root string
now func() time.Time
}
func NewWorkspaceRecorder(settings coreworkspace.Settings, identity coreworkspace.CheckpointIdentity) (pipeline.CheckpointRecorder, error) {
root, err := settings.CheckpointDirectory(identity)
if err != nil {
return nil, err
}
if strings.TrimSpace(root) == "" {
return pipeline.NoopCheckpointRecorder(), nil
}
return &WorkspaceRecorder{root: root, now: time.Now}, nil
}
func (r *WorkspaceRecorder) SourceRunning(moduleKey string) error {
manifest := coreworkspace.NewStageManifest(coreworkspace.StageSource, coreworkspace.StatusRunning)
manifest.ModuleKey = moduleKey
manifest.StartedAt = timePtr(r.timestamp())
return r.writeManifest("source/manifest.json", coreworkspace.SourceManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) SourceSucceeded(moduleKey string, doc *source.SourceDocument) error {
if doc == nil {
return fmt.Errorf("checkpoint source document must not be nil")
}
if err := r.writePayload("source/source-document.json", sourceDocumentEnvelope{Document: cloneSourceDocument(*doc)}); err != nil {
return err
}
manifest := coreworkspace.NewStageManifest(coreworkspace.StageSource, coreworkspace.StatusSucceeded)
manifest.ModuleKey = moduleKey
manifest.OutputDigests = workspaceFingerprints(digestFingerprints("source_document", doc.Digest))
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest("source/manifest.json", coreworkspace.SourceManifest{
StageManifest: manifest,
SourceID: doc.ID,
})
}
func (r *WorkspaceRecorder) SourceFailed(moduleKey string, err error) error {
manifest := coreworkspace.NewStageManifest(coreworkspace.StageSource, coreworkspace.StatusFailed)
manifest.ModuleKey = moduleKey
manifest.CompletedAt = timePtr(r.timestamp())
manifest.Metadata = errorMetadata(err)
return r.writeManifest("source/manifest.json", coreworkspace.SourceManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) ChunkRunning(moduleKey string, sourceDigest string) error {
manifest := coreworkspace.NewStageManifest(coreworkspace.StageChunk, coreworkspace.StatusRunning)
manifest.ModuleKey = moduleKey
manifest.DependencyFingerprints = workspaceFingerprints(digestFingerprints("source_document", sourceDigest))
manifest.StartedAt = timePtr(r.timestamp())
return r.writeManifest("chunk/manifest.json", coreworkspace.ChunkManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) ChunkSucceeded(moduleKey string, sourceDigest string, chunks []contracts.SourceChunk, warnings []contracts.Warning) error {
payload := chunksEnvelope{Chunks: chunkEnvelopes(chunks), Warnings: cloneWarnings(warnings)}
if err := r.writePayload("chunk/chunks.json", payload); err != nil {
return err
}
manifest := coreworkspace.NewStageManifest(coreworkspace.StageChunk, coreworkspace.StatusSucceeded)
manifest.ModuleKey = moduleKey
manifest.DependencyFingerprints = workspaceFingerprints(digestFingerprints("source_document", sourceDigest))
manifest.OutputDigests = workspaceFingerprints(chunkOutputDigests(chunks))
manifest.ValidationStatus = validationStatusString(warnings, nil)
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest("chunk/manifest.json", coreworkspace.ChunkManifest{
StageManifest: manifest,
ChunkCount: len(chunks),
})
}
func (r *WorkspaceRecorder) ChunkRejected(moduleKey string, sourceDigest string, rejected contracts.RejectedOutput) error {
manifest := coreworkspace.NewStageManifest(coreworkspace.StageChunk, coreworkspace.StatusSucceededWithRejections)
manifest.ModuleKey = moduleKey
manifest.DependencyFingerprints = workspaceFingerprints(digestFingerprints("source_document", sourceDigest))
manifest.ValidationStatus = "rejected"
manifest.Rejections = rejectionSummaries([]contracts.RejectedOutput{rejected})
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest("chunk/manifest.json", coreworkspace.ChunkManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) ChunkFailed(moduleKey string, sourceDigest string, err error) error {
manifest := coreworkspace.NewStageManifest(coreworkspace.StageChunk, coreworkspace.StatusFailed)
manifest.ModuleKey = moduleKey
manifest.DependencyFingerprints = workspaceFingerprints(digestFingerprints("source_document", sourceDigest))
manifest.CompletedAt = timePtr(r.timestamp())
manifest.Metadata = errorMetadata(err)
return r.writeManifest("chunk/manifest.json", coreworkspace.ChunkManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) ExtractRunning(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) error {
manifest := laneManifest(coreworkspace.StageExtract, coreworkspace.StatusRunning, laneID, moduleKey, dependencies)
manifest.StartedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("extract", laneID), coreworkspace.ExtractLaneManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) ExtractSucceeded(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, outputs []contracts.ExtractOutput, rejected []contracts.RejectedOutput, warnings []contracts.Warning) error {
payload := extractOutputsEnvelope{
Outputs: extractOutputEnvelopes(outputs),
Rejected: cloneRejectedOutputs(rejected),
Warnings: cloneWarnings(warnings),
}
if err := r.writePayload(lanePayloadPath("extract", laneID, "outputs.json"), payload); err != nil {
return err
}
manifest := laneManifest(coreworkspace.StageExtract, statusForRejected(rejected), laneID, moduleKey, dependencies)
manifest.OutputDigests = workspaceFingerprints(rawOutputDigests(extractPayloads(outputs)))
manifest.ValidationStatus = validationStatusString(warnings, rejected)
manifest.Rejections = rejectionSummaries(rejected)
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("extract", laneID), coreworkspace.ExtractLaneManifest{
StageManifest: manifest,
ChunkCount: len(outputs) + len(rejected),
OutputCount: len(outputs),
})
}
func (r *WorkspaceRecorder) ExtractFailed(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, err error) error {
manifest := laneManifest(coreworkspace.StageExtract, coreworkspace.StatusFailed, laneID, moduleKey, dependencies)
manifest.CompletedAt = timePtr(r.timestamp())
manifest.Metadata = errorMetadata(err)
return r.writeManifest(laneManifestPath("extract", laneID), coreworkspace.ExtractLaneManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) MergeRunning(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) error {
manifest := laneManifest(coreworkspace.StageMerge, coreworkspace.StatusRunning, laneID, moduleKey, dependencies)
manifest.StartedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("merge", laneID), coreworkspace.MergeLaneManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) MergeSucceeded(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, output contracts.MergeOutput, warnings []contracts.Warning) error {
payload := mergeOutputEnvelope{Output: mergeOutputEnvelopeFromOutput(output), Warnings: cloneWarnings(warnings)}
if err := r.writePayload(lanePayloadPath("merge", laneID, "output.json"), payload); err != nil {
return err
}
manifest := laneManifest(coreworkspace.StageMerge, coreworkspace.StatusSucceeded, laneID, moduleKey, dependencies)
manifest.OutputDigests = workspaceFingerprints(rawOutputDigests([]contracts.RawPayload{output.Payload}))
manifest.ValidationStatus = validationStatusString(warnings, nil)
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("merge", laneID), coreworkspace.MergeLaneManifest{
StageManifest: manifest,
InputCount: len(dependencies),
})
}
func (r *WorkspaceRecorder) MergeRejected(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, rejected contracts.RejectedOutput) error {
manifest := laneManifest(coreworkspace.StageMerge, coreworkspace.StatusSucceededWithRejections, laneID, moduleKey, dependencies)
manifest.ValidationStatus = "rejected"
manifest.Rejections = rejectionSummaries([]contracts.RejectedOutput{rejected})
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("merge", laneID), coreworkspace.MergeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
}
func (r *WorkspaceRecorder) MergeFailed(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, err error) error {
manifest := laneManifest(coreworkspace.StageMerge, coreworkspace.StatusFailed, laneID, moduleKey, dependencies)
manifest.CompletedAt = timePtr(r.timestamp())
manifest.Metadata = errorMetadata(err)
return r.writeManifest(laneManifestPath("merge", laneID), coreworkspace.MergeLaneManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) NormalizeRunning(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) error {
manifest := laneManifest(coreworkspace.StageNormalize, coreworkspace.StatusRunning, laneID, moduleKey, dependencies)
manifest.StartedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("normalize", laneID), coreworkspace.NormalizeLaneManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) NormalizeSucceeded(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, output contracts.NormalizeOutput, warnings []contracts.Warning) error {
payload := normalizeOutputEnvelope{Output: normalizeOutputEnvelopeFromOutput(output), Warnings: cloneWarnings(warnings)}
if err := r.writePayload(lanePayloadPath("normalize", laneID, "output.json"), payload); err != nil {
return err
}
manifest := laneManifest(coreworkspace.StageNormalize, coreworkspace.StatusSucceeded, laneID, moduleKey, dependencies)
manifest.OutputDigests = workspaceFingerprints(rawOutputDigests([]contracts.RawPayload{output.Payload}))
manifest.ValidationStatus = validationStatusString(warnings, nil)
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("normalize", laneID), coreworkspace.NormalizeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
}
func (r *WorkspaceRecorder) NormalizeRejected(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, rejected contracts.RejectedOutput) error {
manifest := laneManifest(coreworkspace.StageNormalize, coreworkspace.StatusSucceededWithRejections, laneID, moduleKey, dependencies)
manifest.ValidationStatus = "rejected"
manifest.Rejections = rejectionSummaries([]contracts.RejectedOutput{rejected})
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("normalize", laneID), coreworkspace.NormalizeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
}
func (r *WorkspaceRecorder) NormalizeFailed(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, err error) error {
manifest := laneManifest(coreworkspace.StageNormalize, coreworkspace.StatusFailed, laneID, moduleKey, dependencies)
manifest.CompletedAt = timePtr(r.timestamp())
manifest.Metadata = errorMetadata(err)
return r.writeManifest(laneManifestPath("normalize", laneID), coreworkspace.NormalizeLaneManifest{StageManifest: manifest})
}
func (r *WorkspaceRecorder) writeManifest(name string, payload any) error {
return r.writeJSON(name, payload)
}
func (r *WorkspaceRecorder) writePayload(name string, payload any) error {
return r.writeJSON(name, payload)
}
func (r *WorkspaceRecorder) writeJSON(name string, payload any) error {
if r == nil || strings.TrimSpace(r.root) == "" {
return nil
}
return coreworkspace.WriteJSON(r.root, name, payload)
}
func (r *WorkspaceRecorder) timestamp() time.Time {
if r == nil || r.now == nil {
return time.Now().UTC()
}
return r.now().UTC()
}
func laneManifest(stage coreworkspace.StageName, status coreworkspace.StageStatus, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) coreworkspace.StageManifest {
manifest := coreworkspace.NewStageManifest(stage, status)
manifest.LaneID = laneID
manifest.ModuleKey = moduleKey
manifest.DependencyFingerprints = workspaceFingerprints(dependencies)
return manifest
}
type sourceDocumentEnvelope struct {
Document source.SourceDocument `json:"document"`
}
type chunksEnvelope struct {
Chunks []chunkEnvelope `json:"chunks"`
Warnings []contracts.Warning `json:"warnings,omitempty"`
}
type chunkEnvelope struct {
ID string `json:"id"`
SourceID string `json:"source_id"`
Index int `json:"index"`
StartUnitID int `json:"start_unit_id"`
EndUnitID int `json:"end_unit_id"`
Content binaryEnvelope `json:"content"`
Units []source.SourceUnit `json:"units,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"`
}
type extractOutputsEnvelope struct {
Outputs []extractOutputEnvelope `json:"outputs"`
Rejected []contracts.RejectedOutput `json:"rejected,omitempty"`
Warnings []contracts.Warning `json:"warnings,omitempty"`
}
type extractOutputEnvelope struct {
LaneID string `json:"lane_id"`
ExtractorKey string `json:"extractor_key"`
SourceID string `json:"source_id"`
ChunkID string `json:"chunk_id"`
ChunkIndex int `json:"chunk_index"`
Schema contracts.ResponseSchema `json:"schema,omitempty"`
Payload binaryEnvelope `json:"payload"`
}
type mergeOutputEnvelope struct {
Output mergeOutputPayload `json:"output"`
Warnings []contracts.Warning `json:"warnings,omitempty"`
}
type mergeOutputPayload struct {
LaneID string `json:"lane_id"`
MergerKey string `json:"merger_key"`
SourceID string `json:"source_id,omitempty"`
Schema contracts.ResponseSchema `json:"schema,omitempty"`
Payload binaryEnvelope `json:"payload"`
}
type normalizeOutputEnvelope struct {
Output normalizeOutputPayload `json:"output"`
Warnings []contracts.Warning `json:"warnings,omitempty"`
}
type normalizeOutputPayload struct {
LaneID string `json:"lane_id"`
NormalizerKey string `json:"normalizer_key"`
SourceID string `json:"source_id,omitempty"`
Schema contracts.ResponseSchema `json:"schema,omitempty"`
Payload binaryEnvelope `json:"payload"`
}
type binaryEnvelope struct {
ContentBase64 string `json:"content_base64,omitempty"`
ContentDigest string `json:"content_digest,omitempty"`
MediaType string `json:"media_type,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"`
Warnings []contracts.Warning `json:"warnings,omitempty"`
}
func chunkEnvelopes(chunks []contracts.SourceChunk) []chunkEnvelope {
if len(chunks) == 0 {
return nil
}
out := make([]chunkEnvelope, 0, len(chunks))
for _, chunk := range chunks {
out = append(out, chunkEnvelope{
ID: chunk.ID,
SourceID: chunk.SourceID,
Index: chunk.Index,
StartUnitID: chunk.StartUnitID,
EndUnitID: chunk.EndUnitID,
Content: binaryEnvelopeFromContent(chunk.Content, chunk.MediaType, chunk.Metadata, nil),
Units: cloneSourceUnits(chunk.Units),
Metadata: cloneMetadata(chunk.Metadata),
})
}
return out
}
func extractOutputEnvelopes(outputs []contracts.ExtractOutput) []extractOutputEnvelope {
if len(outputs) == 0 {
return nil
}
out := make([]extractOutputEnvelope, 0, len(outputs))
for _, output := range outputs {
out = append(out, extractOutputEnvelope{
LaneID: output.LaneID,
ExtractorKey: output.ExtractorKey,
SourceID: output.SourceID,
ChunkID: output.ChunkID,
ChunkIndex: output.ChunkIndex,
Schema: schemaEnvelope(output.Schema),
Payload: binaryEnvelopeFromPayload(output.Payload),
})
}
return out
}
func mergeOutputEnvelopeFromOutput(output contracts.MergeOutput) mergeOutputPayload {
return mergeOutputPayload{
LaneID: output.LaneID,
MergerKey: output.MergerKey,
SourceID: output.SourceID,
Schema: schemaEnvelope(output.Schema),
Payload: binaryEnvelopeFromPayload(output.Payload),
}
}
func normalizeOutputEnvelopeFromOutput(output contracts.NormalizeOutput) normalizeOutputPayload {
return normalizeOutputPayload{
LaneID: output.LaneID,
NormalizerKey: output.NormalizerKey,
SourceID: output.SourceID,
Schema: schemaEnvelope(output.Schema),
Payload: binaryEnvelopeFromPayload(output.Payload),
}
}
func schemaEnvelope(schema contracts.ResponseSchema) contracts.ResponseSchema {
schema.JSONSchema = nil
return schema
}
func binaryEnvelopeFromPayload(payload contracts.RawPayload) binaryEnvelope {
return binaryEnvelopeFromContent(payload.Content, payload.MediaType, payload.Metadata, payload.Warnings)
}
func binaryEnvelopeFromContent(content []byte, mediaType string, metadata map[string]any, warnings []contracts.Warning) binaryEnvelope {
return binaryEnvelope{
ContentBase64: base64.StdEncoding.EncodeToString(content),
ContentDigest: contentDigest(content),
MediaType: mediaType,
Metadata: cloneMetadata(metadata),
Warnings: cloneWarnings(warnings),
}
}
func cloneSourceDocument(doc source.SourceDocument) source.SourceDocument {
doc.Units = cloneSourceUnits(doc.Units)
doc.Metadata = cloneMetadata(doc.Metadata)
return doc
}
func cloneSourceUnits(units []source.SourceUnit) []source.SourceUnit {
if len(units) == 0 {
return nil
}
out := make([]source.SourceUnit, 0, len(units))
for _, unit := range units {
out = append(out, source.SourceUnit{
ID: unit.ID,
Kind: unit.Kind,
Text: unit.Text,
Metadata: cloneMetadata(unit.Metadata),
})
}
return out
}
func cloneWarnings(warnings []contracts.Warning) []contracts.Warning {
if len(warnings) == 0 {
return nil
}
return append([]contracts.Warning(nil), warnings...)
}
func cloneRejectedOutputs(rejected []contracts.RejectedOutput) []contracts.RejectedOutput {
if len(rejected) == 0 {
return nil
}
return append([]contracts.RejectedOutput(nil), rejected...)
}
func cloneMetadata(metadata map[string]any) map[string]any {
if len(metadata) == 0 {
return nil
}
out := make(map[string]any, len(metadata))
for key, value := range metadata {
out[key] = value
}
return out
}
func rawOutputDigests(payloads []contracts.RawPayload) []pipeline.CheckpointFingerprint {
values := make([]pipeline.CheckpointFingerprint, 0, len(payloads))
for i, payload := range payloads {
values = append(values, pipeline.CheckpointFingerprint{
Name: fmt.Sprintf("payload[%d]", i),
Value: contentDigest(payload.Content),
})
}
return normalizeFingerprints(values)
}
func extractPayloads(outputs []contracts.ExtractOutput) []contracts.RawPayload {
if len(outputs) == 0 {
return nil
}
payloads := make([]contracts.RawPayload, 0, len(outputs))
for _, output := range outputs {
payloads = append(payloads, output.Payload)
}
return payloads
}
func chunkOutputDigests(chunks []contracts.SourceChunk) []pipeline.CheckpointFingerprint {
values := make([]pipeline.CheckpointFingerprint, 0, len(chunks))
for _, chunk := range chunks {
values = append(values, pipeline.CheckpointFingerprint{
Name: chunk.ID,
Value: contentDigest(chunk.Content),
})
}
return normalizeFingerprints(values)
}
func digestFingerprints(name string, digest string) []pipeline.CheckpointFingerprint {
digest = strings.TrimSpace(digest)
if digest == "" {
return nil
}
return []pipeline.CheckpointFingerprint{{Name: name, Value: digest}}
}
func workspaceFingerprints(values []pipeline.CheckpointFingerprint) []coreworkspace.Fingerprint {
normalized := normalizeFingerprints(values)
if len(normalized) == 0 {
return nil
}
out := make([]coreworkspace.Fingerprint, 0, len(normalized))
for _, value := range normalized {
out = append(out, coreworkspace.Fingerprint{Name: value.Name, Value: value.Value})
}
return out
}
func normalizeFingerprints(values []pipeline.CheckpointFingerprint) []pipeline.CheckpointFingerprint {
if len(values) == 0 {
return nil
}
byName := make(map[string]string, len(values))
for _, value := range values {
name := strings.TrimSpace(value.Name)
fingerprint := strings.TrimSpace(value.Value)
if name == "" || fingerprint == "" {
continue
}
byName[name] = fingerprint
}
if len(byName) == 0 {
return nil
}
names := make([]string, 0, len(byName))
for name := range byName {
names = append(names, name)
}
sort.Strings(names)
out := make([]pipeline.CheckpointFingerprint, 0, len(names))
for _, name := range names {
out = append(out, pipeline.CheckpointFingerprint{Name: name, Value: byName[name]})
}
return out
}
func rejectionSummaries(rejected []contracts.RejectedOutput) []coreworkspace.RejectionSummary {
if len(rejected) == 0 {
return nil
}
type key struct {
validatorName string
reasonCode string
message string
}
counts := make(map[key]int, len(rejected))
for _, item := range rejected {
k := key{validatorName: item.ValidatorName, reasonCode: item.ReasonCode, message: item.Message}
counts[k]++
}
keys := make([]key, 0, len(counts))
for k := range counts {
keys = append(keys, k)
}
sort.Slice(keys, func(i, j int) bool {
if keys[i].validatorName != keys[j].validatorName {
return keys[i].validatorName < keys[j].validatorName
}
if keys[i].reasonCode != keys[j].reasonCode {
return keys[i].reasonCode < keys[j].reasonCode
}
return keys[i].message < keys[j].message
})
out := make([]coreworkspace.RejectionSummary, 0, len(keys))
for _, k := range keys {
out = append(out, coreworkspace.RejectionSummary{
ValidatorName: k.validatorName,
ReasonCode: k.reasonCode,
Message: k.message,
Count: counts[k],
})
}
return out
}
func statusForRejected(rejected []contracts.RejectedOutput) coreworkspace.StageStatus {
if len(rejected) > 0 {
return coreworkspace.StatusSucceededWithRejections
}
return coreworkspace.StatusSucceeded
}
func validationStatusString(warnings []contracts.Warning, rejected []contracts.RejectedOutput) string {
if len(rejected) > 0 {
return "rejected"
}
if len(warnings) > 0 {
return "approved_with_warnings"
}
return "approved"
}
func errorMetadata(err error) map[string]string {
if err == nil {
return nil
}
return map[string]string{"error": err.Error()}
}
func laneManifestPath(stage string, laneID string) string {
return lanePayloadPath(stage, laneID, "manifest.json")
}
func lanePayloadPath(stage string, laneID string, file string) string {
return path.Join(stage, checkpointPathComponent(laneID), file)
}
func checkpointPathComponent(value string) string {
value = strings.TrimSpace(value)
if value == "" {
return "_"
}
var b strings.Builder
for _, r := range value {
switch {
case r >= 'a' && r <= 'z':
b.WriteRune(r)
case r >= 'A' && r <= 'Z':
b.WriteRune(r)
case r >= '0' && r <= '9':
b.WriteRune(r)
case r == '-' || r == '_' || r == '.':
b.WriteRune(r)
default:
b.WriteString(fmt.Sprintf("~%x", r))
}
}
out := b.String()
if out == "." || out == ".." || strings.Contains(out, "..") {
return "_"
}
return out
}
func contentDigest(content []byte) string {
sum := sha256.Sum256(content)
return "sha256:" + hex.EncodeToString(sum[:])
}
func timePtr(t time.Time) *time.Time {
return &t
}

View File

@@ -0,0 +1,195 @@
package checkpoint
import (
"encoding/base64"
"encoding/json"
"os"
"path/filepath"
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
coreworkspace "gitea.maximumdirect.net/eric/notarius/internal/core/workspace"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
)
func TestWorkspaceRecorderWritesSuccessfulCheckpointFiles(t *testing.T) {
root := t.TempDir()
recorder := newTestRecorder(t, root)
doc := &source.SourceDocument{
ID: "source-1",
Kind: "document",
Format: "text/plain",
Digest: "sha256:source",
Units: []source.SourceUnit{{ID: 1, Kind: "line", Text: "hello"}},
}
chunks := []contracts.SourceChunk{
{
ID: "chunk-1",
SourceID: "source-1",
Index: 0,
StartUnitID: 1,
EndUnitID: 1,
Content: []byte("chunk content"),
MediaType: "text/plain",
Units: doc.Units,
},
}
if err := recorder.SourceRunning("seriatim"); err != nil {
t.Fatalf("SourceRunning: %v", err)
}
assertManifestStatus(t, filepath.Join(root, "source", "manifest.json"), coreworkspace.StatusRunning)
if err := recorder.SourceSucceeded("seriatim", doc); err != nil {
t.Fatalf("SourceSucceeded: %v", err)
}
assertManifestStatus(t, filepath.Join(root, "source", "manifest.json"), coreworkspace.StatusSucceeded)
if _, err := os.Stat(filepath.Join(root, "source", "source-document.json")); err != nil {
t.Fatalf("expected source checkpoint payload: %v", err)
}
if err := recorder.ChunkRunning("generic", doc.Digest); err != nil {
t.Fatalf("ChunkRunning: %v", err)
}
if err := recorder.ChunkSucceeded("generic", doc.Digest, chunks, nil); err != nil {
t.Fatalf("ChunkSucceeded: %v", err)
}
assertManifestStatus(t, filepath.Join(root, "chunk", "manifest.json"), coreworkspace.StatusSucceeded)
var chunkPayload struct {
Chunks []struct {
Content struct {
ContentBase64 string `json:"content_base64"`
ContentDigest string `json:"content_digest"`
} `json:"content"`
} `json:"chunks"`
}
readJSON(t, filepath.Join(root, "chunk", "chunks.json"), &chunkPayload)
if len(chunkPayload.Chunks) != 1 {
t.Fatalf("checkpoint chunks = %#v, want one", chunkPayload.Chunks)
}
decoded, err := base64.StdEncoding.DecodeString(chunkPayload.Chunks[0].Content.ContentBase64)
if err != nil {
t.Fatalf("decode chunk content: %v", err)
}
if string(decoded) != "chunk content" {
t.Fatalf("chunk content = %q, want original content", decoded)
}
if got, want := chunkPayload.Chunks[0].Content.ContentDigest, contentDigest([]byte("chunk content")); got != want {
t.Fatalf("content digest = %q, want %q", got, want)
}
}
func TestWorkspaceRecorderRecordsRejectedExtractOutputs(t *testing.T) {
root := t.TempDir()
recorder := newTestRecorder(t, root)
rejected := []contracts.RejectedOutput{
{
Stage: string(pipeline.StageExtract),
LaneID: "spells",
ModuleKey: "dnd/spells",
ChunkID: "chunk-1",
ValidatorName: "shape",
ReasonCode: "invalid_shape",
Message: "bad shape",
},
}
if err := recorder.ExtractRunning("spells", "dnd/spells", []pipeline.CheckpointFingerprint{{Name: "chunks", Value: "sha256:chunks"}}); err != nil {
t.Fatalf("ExtractRunning: %v", err)
}
if err := recorder.ExtractSucceeded("spells", "dnd/spells", nil, nil, rejected, nil); err != nil {
t.Fatalf("ExtractSucceeded: %v", err)
}
var manifest coreworkspace.ExtractLaneManifest
readJSON(t, filepath.Join(root, "extract", "spells", "manifest.json"), &manifest)
if manifest.Status != coreworkspace.StatusSucceededWithRejections || manifest.ValidationStatus != "rejected" {
t.Fatalf("extract manifest status = %q validation=%q", manifest.Status, manifest.ValidationStatus)
}
if len(manifest.Rejections) != 1 || manifest.Rejections[0].Count != 1 || manifest.Rejections[0].ReasonCode != "invalid_shape" {
t.Fatalf("rejections = %#v", manifest.Rejections)
}
var payload struct {
Rejected []contracts.RejectedOutput `json:"rejected"`
}
readJSON(t, filepath.Join(root, "extract", "spells", "outputs.json"), &payload)
if len(payload.Rejected) != 1 || payload.Rejected[0].ChunkID != "chunk-1" {
t.Fatalf("checkpoint rejected payload = %#v", payload.Rejected)
}
}
func TestWorkspaceRecorderRecordsFailedStages(t *testing.T) {
root := t.TempDir()
recorder := newTestRecorder(t, root)
if err := recorder.MergeRunning("spells", "appendorder", nil); err != nil {
t.Fatalf("MergeRunning: %v", err)
}
if err := recorder.MergeFailed("spells", "appendorder", nil, assertErr("merge failed")); err != nil {
t.Fatalf("MergeFailed: %v", err)
}
var manifest coreworkspace.MergeLaneManifest
readJSON(t, filepath.Join(root, "merge", "spells", "manifest.json"), &manifest)
if manifest.Status != coreworkspace.StatusFailed {
t.Fatalf("status = %q, want failed", manifest.Status)
}
if !strings.Contains(manifest.Metadata["error"], "merge failed") {
t.Fatalf("metadata = %#v, want error", manifest.Metadata)
}
}
func TestWorkspaceRecorderRecordsWarningOnlyValidation(t *testing.T) {
root := t.TempDir()
recorder := newTestRecorder(t, root)
output := contracts.NormalizeOutput{
LaneID: "spells",
NormalizerKey: "noop",
SourceID: "source-1",
Payload: contracts.RawPayload{
Content: []byte(`{"ok":true}`),
MediaType: "application/json",
},
}
warnings := []contracts.Warning{{ReasonCode: "note", Message: "warning"}}
if err := recorder.NormalizeSucceeded("spells", "noop", nil, output, warnings); err != nil {
t.Fatalf("NormalizeSucceeded: %v", err)
}
var manifest coreworkspace.NormalizeLaneManifest
readJSON(t, filepath.Join(root, "normalize", "spells", "manifest.json"), &manifest)
if manifest.Status != coreworkspace.StatusSucceeded || manifest.ValidationStatus != "approved_with_warnings" {
t.Fatalf("normalize manifest status = %q validation=%q", manifest.Status, manifest.ValidationStatus)
}
}
func newTestRecorder(t *testing.T, root string) *WorkspaceRecorder {
t.Helper()
return &WorkspaceRecorder{root: root}
}
func assertManifestStatus(t *testing.T, path string, want coreworkspace.StageStatus) {
t.Helper()
var manifest coreworkspace.StageManifest
readJSON(t, path, &manifest)
if manifest.Status != want {
t.Fatalf("%s status = %q, want %q", path, manifest.Status, want)
}
}
func readJSON(t *testing.T, path string, out any) {
t.Helper()
data, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read %q: %v", path, err)
}
if err := json.Unmarshal(data, out); err != nil {
t.Fatalf("decode %q: %v", path, err)
}
}
type assertErr string
func (e assertErr) Error() string { return string(e) }

View File

@@ -0,0 +1,161 @@
package pipeline
import (
"crypto/sha256"
"encoding/hex"
"fmt"
"sort"
"strings"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
)
type CheckpointFingerprint struct {
Name string `json:"name"`
Value string `json:"value"`
}
type CheckpointRecorder interface {
SourceRunning(moduleKey string) error
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
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
ExtractSucceeded(laneID string, moduleKey string, dependencies []CheckpointFingerprint, outputs []contracts.ExtractOutput, rejected []contracts.RejectedOutput, warnings []contracts.Warning) error
ExtractFailed(laneID string, moduleKey string, dependencies []CheckpointFingerprint, err error) error
MergeRunning(laneID string, moduleKey string, dependencies []CheckpointFingerprint) error
MergeSucceeded(laneID string, moduleKey string, dependencies []CheckpointFingerprint, output contracts.MergeOutput, warnings []contracts.Warning) error
MergeRejected(laneID string, moduleKey string, dependencies []CheckpointFingerprint, rejected contracts.RejectedOutput) error
MergeFailed(laneID string, moduleKey string, dependencies []CheckpointFingerprint, err error) error
NormalizeRunning(laneID string, moduleKey string, dependencies []CheckpointFingerprint) error
NormalizeSucceeded(laneID string, moduleKey string, dependencies []CheckpointFingerprint, output contracts.NormalizeOutput, warnings []contracts.Warning) error
NormalizeRejected(laneID string, moduleKey string, dependencies []CheckpointFingerprint, rejected contracts.RejectedOutput) error
NormalizeFailed(laneID string, moduleKey string, dependencies []CheckpointFingerprint, err error) error
}
type noopCheckpointRecorder struct{}
func NoopCheckpointRecorder() CheckpointRecorder { return noopCheckpointRecorder{} }
func (noopCheckpointRecorder) SourceRunning(string) error { return nil }
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 {
return nil
}
func (noopCheckpointRecorder) ChunkRejected(string, string, contracts.RejectedOutput) error {
return nil
}
func (noopCheckpointRecorder) ChunkFailed(string, string, error) error { return nil }
func (noopCheckpointRecorder) ExtractRunning(string, string, []CheckpointFingerprint) error {
return nil
}
func (noopCheckpointRecorder) ExtractSucceeded(string, string, []CheckpointFingerprint, []contracts.ExtractOutput, []contracts.RejectedOutput, []contracts.Warning) error {
return nil
}
func (noopCheckpointRecorder) ExtractFailed(string, string, []CheckpointFingerprint, error) error {
return nil
}
func (noopCheckpointRecorder) MergeRunning(string, string, []CheckpointFingerprint) error { return nil }
func (noopCheckpointRecorder) MergeSucceeded(string, string, []CheckpointFingerprint, contracts.MergeOutput, []contracts.Warning) error {
return nil
}
func (noopCheckpointRecorder) MergeRejected(string, string, []CheckpointFingerprint, contracts.RejectedOutput) error {
return nil
}
func (noopCheckpointRecorder) MergeFailed(string, string, []CheckpointFingerprint, error) error {
return nil
}
func (noopCheckpointRecorder) NormalizeRunning(string, string, []CheckpointFingerprint) error {
return nil
}
func (noopCheckpointRecorder) NormalizeSucceeded(string, string, []CheckpointFingerprint, contracts.NormalizeOutput, []contracts.Warning) error {
return nil
}
func (noopCheckpointRecorder) NormalizeRejected(string, string, []CheckpointFingerprint, contracts.RejectedOutput) error {
return nil
}
func (noopCheckpointRecorder) NormalizeFailed(string, string, []CheckpointFingerprint, error) error {
return nil
}
func rawOutputDigests(payloads []contracts.RawPayload) []CheckpointFingerprint {
values := make([]CheckpointFingerprint, 0, len(payloads))
for i, payload := range payloads {
values = append(values, CheckpointFingerprint{
Name: fmt.Sprintf("payload[%d]", i),
Value: checkpointContentDigest(payload.Content),
})
}
return normalizeCheckpointFingerprints(values)
}
func extractPayloads(outputs []contracts.ExtractOutput) []contracts.RawPayload {
if len(outputs) == 0 {
return nil
}
payloads := make([]contracts.RawPayload, 0, len(outputs))
for _, output := range outputs {
payloads = append(payloads, output.Payload)
}
return payloads
}
func digestFingerprints(name string, digest string) []CheckpointFingerprint {
digest = strings.TrimSpace(digest)
if digest == "" {
return nil
}
return []CheckpointFingerprint{{Name: name, Value: digest}}
}
func joinedChunkDigest(chunks []contracts.SourceChunk) string {
if len(chunks) == 0 {
return ""
}
values := make([]string, 0, len(chunks))
for _, chunk := range chunks {
values = append(values, chunk.ID+"="+checkpointContentDigest(chunk.Content))
}
sort.Strings(values)
sum := sha256.Sum256([]byte(strings.Join(values, "\n")))
return "sha256:" + hex.EncodeToString(sum[:])
}
func normalizeCheckpointFingerprints(values []CheckpointFingerprint) []CheckpointFingerprint {
if len(values) == 0 {
return nil
}
byName := make(map[string]string, len(values))
for _, value := range values {
name := strings.TrimSpace(value.Name)
fingerprint := strings.TrimSpace(value.Value)
if name == "" || fingerprint == "" {
continue
}
byName[name] = fingerprint
}
if len(byName) == 0 {
return nil
}
names := make([]string, 0, len(byName))
for name := range byName {
names = append(names, name)
}
sort.Strings(names)
out := make([]CheckpointFingerprint, 0, len(names))
for _, name := range names {
out = append(out, CheckpointFingerprint{Name: name, Value: byName[name]})
}
return out
}
func checkpointContentDigest(content []byte) string {
sum := sha256.Sum256(content)
return "sha256:" + hex.EncodeToString(sum[:])
}

View File

@@ -48,6 +48,7 @@ type RunInput struct {
LLMProfiles []artifacts.LLMProfileManifest
Metadata map[string]any
Warnings []contracts.Warning
Checkpoints CheckpointRecorder
}
type RunOutput struct {
@@ -70,6 +71,10 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (output RunOutput, err
}
output.Manifest = manifestFromPipeline(input)
checkpoints := input.Checkpoints
if checkpoints == nil {
checkpoints = NoopCheckpointRecorder()
}
defer func() {
output.Manifest.LLMProfiles = mergeLLMProfileManifests(input.LLMProfiles, llmProfileManifests(input.LLMClient))
}()
@@ -80,6 +85,9 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (output RunOutput, err
return failOutput(output), fmt.Errorf("build input adapter %q: %w", input.Pipeline.Input.Module, err)
}
attachModuleManifestMetadata(&output, "input", adapter)
if err := checkpoints.SourceRunning(adapter.Key()); err != nil {
return failOutput(output), fmt.Errorf("write source checkpoint: %w", err)
}
doc, err := adapter.Parse(ctx, contracts.ParseRequest{
SourceID: input.SourceID,
Path: input.Path,
@@ -89,11 +97,16 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (output RunOutput, err
Metadata: input.Metadata,
})
if err != nil {
_ = checkpoints.SourceFailed(adapter.Key(), err)
return failOutput(output), fmt.Errorf("parse input with adapter %q: %w", adapter.Key(), err)
}
if err := source.ValidateDocument(doc); err != nil {
_ = checkpoints.SourceFailed(adapter.Key(), err)
return failOutput(output), fmt.Errorf("validate source document: %w", err)
}
if err := checkpoints.SourceSucceeded(adapter.Key(), doc); err != nil {
return failOutput(output), fmt.Errorf("write source checkpoint: %w", err)
}
sourceInput := sourceInputMaterial(input.Path, input.RawInput)
sessionID := resolvedSessionID(input.SessionID, doc.ID)
output.Manifest.Metadata = manifestMetadataWithSessionID(output.Manifest.Metadata, sessionID)
@@ -104,6 +117,9 @@ 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)
if err := checkpoints.ChunkRunning(chunker.Key(), doc.Digest); err != nil {
return failOutput(output), fmt.Errorf("write chunk checkpoint: %w", err)
}
var canonicalChunks []contracts.SourceChunk
var chunkWarnings []contracts.Warning
chunksAccepted, chunkRejection, err := runWithRetry(ctx, input.Pipeline.Chunk.Retries, func(attempt int) (bool, *contracts.RejectedOutput, error) {
@@ -136,17 +152,24 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (output RunOutput, err
return true, nil, nil
})
if err != nil {
_ = checkpoints.ChunkFailed(chunker.Key(), doc.Digest, err)
return failOutput(output), err
}
if !chunksAccepted {
output.Rejected = append(output.Rejected, *chunkRejection)
if err := checkpoints.ChunkRejected(chunker.Key(), doc.Digest, *chunkRejection); err != nil {
return failOutput(output), fmt.Errorf("write chunk checkpoint: %w", err)
}
} else {
output.Warnings = append(output.Warnings, chunkWarnings...)
if err := checkpoints.ChunkSucceeded(chunker.Key(), doc.Digest, canonicalChunks, chunkWarnings); err != nil {
return failOutput(output), fmt.Errorf("write chunk checkpoint: %w", err)
}
}
if chunksAccepted {
for _, lane := range input.Pipeline.ArtifactLanes {
if err := r.runLane(ctx, input, doc, sourceInput, sessionID, canonicalChunks, lane, &output); err != nil {
if err := r.runLane(ctx, input, checkpoints, doc, sourceInput, sessionID, canonicalChunks, lane, &output); err != nil {
return failOutput(output), err
}
}
@@ -187,7 +210,7 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (output RunOutput, err
return output, nil
}
func (r *Runner) runLane(ctx context.Context, input RunInput, 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, doc *source.SourceDocument, sourceInput contracts.LLMInputMaterial, sessionID string, chunks []contracts.SourceChunk, 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)
@@ -203,6 +226,12 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
setLaneManifestMetadata(output, lane.ID, extractor, merger, normalizer)
extractOutputs := make([]contracts.ExtractOutput, 0, len(chunks))
extractWarnings := []contracts.Warning{}
extractRejectedStart := len(output.Rejected)
extractDependencies := digestFingerprints("chunks", joinedChunkDigest(chunks))
if err := checkpoints.ExtractRunning(lane.ID, extractor.Key(), extractDependencies); err != nil {
return fmt.Errorf("write extract checkpoint for lane %q: %w", lane.ID, err)
}
for index := range chunks {
chunk := chunks[index]
var acceptedOutput contracts.ExtractOutput
@@ -256,6 +285,7 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
return true, nil, nil
})
if err != nil {
_ = checkpoints.ExtractFailed(lane.ID, extractor.Key(), extractDependencies, err)
return err
}
if !accepted {
@@ -263,8 +293,13 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
continue
}
output.Warnings = append(output.Warnings, acceptedWarnings...)
extractWarnings = append(extractWarnings, acceptedWarnings...)
extractOutputs = append(extractOutputs, acceptedOutput)
}
extractRejected := cloneRejectedOutputs(output.Rejected[extractRejectedStart:])
if err := checkpoints.ExtractSucceeded(lane.ID, extractor.Key(), extractDependencies, extractOutputs, extractRejected, extractWarnings); err != nil {
return fmt.Errorf("write extract checkpoint for lane %q: %w", lane.ID, err)
}
if len(extractOutputs) == 0 {
return nil
@@ -272,6 +307,10 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
var acceptedMerge contracts.MergeOutput
var mergeWarnings []contracts.Warning
mergeDependencies := rawOutputDigests(extractPayloads(extractOutputs))
if err := checkpoints.MergeRunning(lane.ID, merger.Key(), mergeDependencies); err != nil {
return fmt.Errorf("write merge checkpoint for lane %q: %w", lane.ID, err)
}
mergeAccepted, mergeRejection, err := runWithRetry(ctx, lane.Merge.Retries, func(attempt int) (bool, *contracts.RejectedOutput, error) {
mergeResult, err := merger.Merge(ctx, contracts.MergeRequest{
Source: doc,
@@ -318,16 +357,27 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
return true, nil, nil
})
if err != nil {
_ = checkpoints.MergeFailed(lane.ID, merger.Key(), mergeDependencies, err)
return err
}
if !mergeAccepted {
output.Rejected = append(output.Rejected, *mergeRejection)
if err := checkpoints.MergeRejected(lane.ID, merger.Key(), mergeDependencies, *mergeRejection); err != nil {
return fmt.Errorf("write merge checkpoint for lane %q: %w", lane.ID, err)
}
return nil
}
output.Warnings = append(output.Warnings, mergeWarnings...)
if err := checkpoints.MergeSucceeded(lane.ID, merger.Key(), mergeDependencies, acceptedMerge, mergeWarnings); err != nil {
return fmt.Errorf("write merge checkpoint for lane %q: %w", lane.ID, err)
}
var acceptedNormalize contracts.NormalizeOutput
var normalizeWarnings []contracts.Warning
normalizeDependencies := rawOutputDigests([]contracts.RawPayload{acceptedMerge.Payload})
if err := checkpoints.NormalizeRunning(lane.ID, normalizer.Key(), normalizeDependencies); err != nil {
return fmt.Errorf("write normalize checkpoint for lane %q: %w", lane.ID, err)
}
normalizeAccepted, normalizeRejection, err := runWithRetry(ctx, lane.Normalize.Retries, func(attempt int) (bool, *contracts.RejectedOutput, error) {
normalizeResult, err := normalizer.Normalize(ctx, contracts.NormalizeRequest{
Source: doc,
@@ -374,13 +424,20 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
return true, nil, nil
})
if err != nil {
_ = checkpoints.NormalizeFailed(lane.ID, normalizer.Key(), normalizeDependencies, err)
return err
}
if !normalizeAccepted {
output.Rejected = append(output.Rejected, *normalizeRejection)
if err := checkpoints.NormalizeRejected(lane.ID, normalizer.Key(), normalizeDependencies, *normalizeRejection); err != nil {
return fmt.Errorf("write normalize checkpoint for lane %q: %w", lane.ID, err)
}
return nil
}
output.Warnings = append(output.Warnings, normalizeWarnings...)
if err := checkpoints.NormalizeSucceeded(lane.ID, normalizer.Key(), normalizeDependencies, acceptedNormalize, normalizeWarnings); err != nil {
return fmt.Errorf("write normalize checkpoint for lane %q: %w", lane.ID, err)
}
output.NormalizeOutputs = append(output.NormalizeOutputs, acceptedNormalize)
return nil
}

View File

@@ -992,6 +992,37 @@ func TestRunPassesChunkContentAndMediaTypeToExtractors(t *testing.T) {
}
}
func TestRunDoesNotPassCheckpointPathsToModules(t *testing.T) {
modules := defaultRunnerModules()
_, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{
Pipeline: resolvedPipeline(),
Checkpoints: NoopCheckpointRecorder(),
})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
for _, req := range modules.input.requests {
assertNoCheckpointMetadata(t, req.Metadata)
}
for _, req := range modules.chunker.requests {
assertNoCheckpointMetadata(t, req.Metadata)
}
for _, req := range modules.extractors["extract-alpha"].requests {
assertNoCheckpointMetadata(t, req.Metadata)
}
for _, req := range modules.mergers["merge"].requests {
assertNoCheckpointMetadata(t, req.Metadata)
}
for _, req := range modules.normalizers["normalize"].requests {
assertNoCheckpointMetadata(t, req.Metadata)
}
for _, req := range modules.output.requests {
assertNoCheckpointMetadata(t, req.Metadata)
}
}
func TestRunOmitsRejectedExtractOutputsFromMerge(t *testing.T) {
modules := defaultRunnerModules()
validator := &runnerChainValidator{name: "chain-extract", approved: []bool{false, true}, reason: "bad_extract", message: "extract rejected"}
@@ -2181,6 +2212,25 @@ func warningReasons(warnings []contracts.Warning) []string {
return reasons
}
func assertNoCheckpointMetadata(t *testing.T, metadata map[string]any) {
t.Helper()
for key, value := range metadata {
lowerKey := strings.ToLower(key)
if strings.Contains(lowerKey, "checkpoint") || strings.Contains(lowerKey, "workspace") {
t.Fatalf("metadata key %q exposes checkpoint/workspace state", key)
}
text, ok := value.(string)
if !ok {
continue
}
lowerValue := strings.ToLower(text)
if strings.Contains(lowerValue, "checkpoint") || strings.Contains(lowerValue, "workspace") {
t.Fatalf("metadata value for %q exposes checkpoint/workspace state: %q", key, text)
}
}
}
func assertRunError(t *testing.T, err error, want string) {
t.Helper()