Propagate structured repair requests

This commit is contained in:
2026-08-25 19:39:04 +00:00
parent ab9b743df6
commit e00cc45c6b
12 changed files with 154 additions and 134 deletions

View File

@@ -21,12 +21,13 @@ const (
)
type ModuleBinding struct {
Module string `json:"module"`
LLMProfile string `json:"llm_profile,omitempty"`
Retries int `json:"retries,omitempty"`
Options map[string]any `json:"options,omitempty"`
References map[string]ReferenceSource `json:"references,omitempty"`
Validators ValidatorOverride `json:"validators,omitempty"`
Module string `json:"module"`
LLMProfile string `json:"llm_profile,omitempty"`
StructuredOutputRepairAttempts *int `json:"structured_output_repair_attempts,omitempty"`
Retries int `json:"retries,omitempty"`
Options map[string]any `json:"options,omitempty"`
References map[string]ReferenceSource `json:"references,omitempty"`
Validators ValidatorOverride `json:"validators,omitempty"`
}
// ArtifactReference identifies a normalized artifact produced by an earlier

View File

@@ -173,11 +173,12 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (output RunOutput, err
return failOutput(output), err
}
doc, err = adapter.Parse(ctx, contracts.ParseRequest{
SourceID: input.SourceID,
Path: input.Path,
Raw: input.RawInput,
LLMProfile: input.pipeline.Input.LLMProfile,
Metadata: requestMetadata,
SourceID: input.SourceID,
Path: input.Path,
Raw: input.RawInput,
LLMProfile: input.pipeline.Input.LLMProfile,
StructuredOutputRepairAttempts: input.pipeline.Input.StructuredOutputRepairAttempts,
Metadata: requestMetadata,
})
if ctxErr := ctx.Err(); ctxErr != nil {
_ = checkpoints.SourceFailed(adapter.Key(), ctxErr)
@@ -360,14 +361,15 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (output RunOutput, err
return failOutput(output), err
}
encoded, err := encoder.Encode(ctx, contracts.OutputRequest{
Manifest: output.Manifest,
NormalizeOutputs: cloneSerializedOutputs(output.NormalizeOutputs),
Rejected: cloneRejectedOutputs(output.Rejected),
Warnings: output.Warnings,
LLMProfile: input.pipeline.Output.LLMProfile,
Metadata: outputMetadata,
ChunkMap: contracts.CloneSerializedArtifactPointer(acceptedChunkMap),
EvidenceContext: contracts.CloneSerializedArtifactPointer(evidenceArtifact),
Manifest: output.Manifest,
NormalizeOutputs: cloneSerializedOutputs(output.NormalizeOutputs),
Rejected: cloneRejectedOutputs(output.Rejected),
Warnings: output.Warnings,
LLMProfile: input.pipeline.Output.LLMProfile,
StructuredOutputRepairAttempts: input.pipeline.Output.StructuredOutputRepairAttempts,
Metadata: outputMetadata,
ChunkMap: contracts.CloneSerializedArtifactPointer(acceptedChunkMap),
EvidenceContext: contracts.CloneSerializedArtifactPointer(evidenceArtifact),
})
if ctxErr := ctx.Err(); ctxErr != nil {
return failOutput(output), ctxErr

View File

@@ -96,7 +96,7 @@ func (r *Runner) runChunkPlan(ctx context.Context, input RunInput, doc *source.S
chunkResult, callErr := chunker.Plan(attemptCtx, contracts.ChunkRequest{
Source: doc, SourceInput: sourceInput.Clone(), SessionID: sessionID,
References: CloneReferenceSet(input.pipeline.ChunkReferences.ReferenceSet),
LLMProfile: input.pipeline.Chunk.LLMProfile, Metadata: requestMetadata,
LLMProfile: input.pipeline.Chunk.LLMProfile, StructuredOutputRepairAttempts: input.pipeline.Chunk.StructuredOutputRepairAttempts, Metadata: requestMetadata,
})
if callErr != nil {
return retryAttemptResult{}, terminal.record(nil, fmt.Errorf("chunk source with chunker %q: %w", chunker.Key(), callErr))

View File

@@ -420,7 +420,7 @@ func (r *Runner) runExtractJob(ctx context.Context, input RunInput, doc *source.
return retryAttemptResult{}, terminal.record(nil, fmt.Errorf("clone extract request metadata: %w", metadataErr))
}
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})
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, StructuredOutputRepairAttempts: lane.Extract.StructuredOutputRepairAttempts, 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 retryAttemptResult{}, terminal.record(nil, attemptErr)

View File

@@ -258,7 +258,7 @@ func (r *Runner) runMergeStage(ctx context.Context, input RunInput, checkpoints
if metadataErr != nil {
return retryAttemptResult{}, terminal.record(nil, fmt.Errorf("clone merge request metadata: %w", metadataErr))
}
result, callErr := typed.merge(attemptCtx, typed.merger, contracts.TypedMergeRequest[any]{Source: doc, LaneID: lane.ID, ExtractOutputs: mergeInputs, SourceInput: sourceInput.Clone(), SessionID: sessionID, References: CloneReferenceSet(mergeReferences), LLMProfile: lane.Merge.LLMProfile, Metadata: requestMetadata})
result, callErr := typed.merge(attemptCtx, typed.merger, contracts.TypedMergeRequest[any]{Source: doc, LaneID: lane.ID, ExtractOutputs: mergeInputs, SourceInput: sourceInput.Clone(), SessionID: sessionID, References: CloneReferenceSet(mergeReferences), LLMProfile: lane.Merge.LLMProfile, StructuredOutputRepairAttempts: lane.Merge.StructuredOutputRepairAttempts, Metadata: requestMetadata})
if callErr != nil {
attemptErr := fmt.Errorf("merge lane %q with merger %q: %w", lane.ID, lane.Merge.Module, callErr)
return retryAttemptResult{}, terminal.record(nil, attemptErr)
@@ -360,7 +360,7 @@ func (r *Runner) runNormalizeStage(ctx context.Context, input RunInput, checkpoi
if metadataErr != nil {
return retryAttemptResult{}, terminal.record(nil, fmt.Errorf("clone normalize request metadata: %w", metadataErr))
}
result, callErr := typed.normalize(attemptCtx, typed.normalizer, contracts.TypedNormalizeRequest[any]{Source: doc, LaneID: lane.ID, MergeOutput: contracts.MergeArtifact[any]{LaneID: lane.ID, MergerKey: lane.Merge.Module, SourceID: doc.ID, Value: merged.Value}, SourceInput: sourceInput.Clone(), SessionID: sessionID, References: CloneReferenceSet(normalizeReferences), LLMProfile: lane.Normalize.LLMProfile, Metadata: requestMetadata})
result, callErr := typed.normalize(attemptCtx, typed.normalizer, contracts.TypedNormalizeRequest[any]{Source: doc, LaneID: lane.ID, MergeOutput: contracts.MergeArtifact[any]{LaneID: lane.ID, MergerKey: lane.Merge.Module, SourceID: doc.ID, Value: merged.Value}, SourceInput: sourceInput.Clone(), SessionID: sessionID, References: CloneReferenceSet(normalizeReferences), LLMProfile: lane.Normalize.LLMProfile, StructuredOutputRepairAttempts: lane.Normalize.StructuredOutputRepairAttempts, Metadata: requestMetadata})
if callErr != nil {
attemptErr := fmt.Errorf("normalize lane %q with normalizer %q: %w", lane.ID, lane.Normalize.Module, callErr)
return retryAttemptResult{}, terminal.record(nil, attemptErr)
@@ -511,6 +511,7 @@ func (r *Runner) validateTypedArtifact(ctx context.Context, codec artifactCodecE
}
requestTarget.value = candidateValue
requestTarget.llmProfile = binding.LLMProfile
requestTarget.structuredOutputRepairAttempts = binding.StructuredOutputRepairAttempts
result, err = item.typedValidate(validatorCtx, item.typed, requestTarget)
case ValidatorTargetSerialized:
artifact, encodeErr := validationCandidateArtifact(codec, target)
@@ -518,7 +519,7 @@ func (r *Runner) validateTypedArtifact(ctx context.Context, codec artifactCodecE
err = encodeErr
break
}
result, err = item.serialized.Validate(validatorCtx, contracts.SerializedValidationRequest{Stage: string(target.stage), LaneID: target.laneID, ModuleKey: target.moduleKey, Source: target.source, SourceID: target.sourceID, SourceInput: requestTarget.sourceInput, SessionID: target.sessionID, References: requestTarget.references, LLMProfile: binding.LLMProfile, Metadata: requestTarget.metadata, Chunk: requestTarget.chunk, Chunks: requestTarget.chunks, Schema: contracts.CloneArtifactSchema(artifact.Artifact.Schema), MediaType: artifact.Artifact.MediaType, Content: append([]byte(nil), artifact.Artifact.Content...)})
result, err = item.serialized.Validate(validatorCtx, contracts.SerializedValidationRequest{Stage: string(target.stage), LaneID: target.laneID, ModuleKey: target.moduleKey, Source: target.source, SourceID: target.sourceID, SourceInput: requestTarget.sourceInput, SessionID: target.sessionID, References: requestTarget.references, LLMProfile: binding.LLMProfile, StructuredOutputRepairAttempts: binding.StructuredOutputRepairAttempts, Metadata: requestTarget.metadata, Chunk: requestTarget.chunk, Chunks: requestTarget.chunks, Schema: contracts.CloneArtifactSchema(artifact.Artifact.Schema), MediaType: artifact.Artifact.MediaType, Content: append([]byte(nil), artifact.Artifact.Content...)})
default:
return nil, nil, fmt.Errorf("validator %q is incompatible with typed artifact validation", binding.Module)
}

View File

@@ -28,22 +28,23 @@ type erasedTypedResult struct {
}
type typedValidationTarget struct {
stage ModuleStage
stepID string
laneID string
moduleKey string
source *source.SourceDocument
sourceID string
sourceInput contracts.LLMInputMaterial
sessionID string
references contracts.ReferenceSet
llmProfile string
metadata map[string]any
chunk *source.Chunk
chunks []source.Chunk
ref source.SourceRef
value any
candidate *CheckpointArtifact
stage ModuleStage
stepID string
laneID string
moduleKey string
source *source.SourceDocument
sourceID string
sourceInput contracts.LLMInputMaterial
sessionID string
references contracts.ReferenceSet
llmProfile string
structuredOutputRepairAttempts *int
metadata map[string]any
chunk *source.Chunk
chunks []source.Chunk
ref source.SourceRef
value any
candidate *CheckpointArtifact
}
func exactTypedValue[T any](operation string, value any) (T, error) {

View File

@@ -94,6 +94,10 @@ func cloneModuleBindings(bindings []ModuleBinding) []ModuleBinding {
func cloneModuleBinding(binding ModuleBinding) ModuleBinding {
binding.Module = strings.TrimSpace(binding.Module)
binding.LLMProfile = strings.TrimSpace(binding.LLMProfile)
if binding.StructuredOutputRepairAttempts != nil {
value := *binding.StructuredOutputRepairAttempts
binding.StructuredOutputRepairAttempts = &value
}
binding.Options = cloneOptions(binding.Options)
if len(binding.References) > 0 {
references := make(map[string]ReferenceSource, len(binding.References))

View File

@@ -115,7 +115,7 @@ func RegisterTypedValidatorBuilder[T any](registry *ValidatorRegistry, kind cont
if err != nil {
return contracts.ValidationResult{}, err
}
return validator.Validate(ctx, contracts.TypedValidationRequest[T]{Stage: string(target.stage), LaneID: target.laneID, ModuleKey: target.moduleKey, Source: target.source, SourceID: target.sourceID, SourceInput: target.sourceInput, SessionID: target.sessionID, References: target.references, LLMProfile: target.llmProfile, Metadata: target.metadata, Chunk: target.chunk, Chunks: target.chunks, Ref: target.ref, Value: value})
return validator.Validate(ctx, contracts.TypedValidationRequest[T]{Stage: string(target.stage), LaneID: target.laneID, ModuleKey: target.moduleKey, Source: target.source, SourceID: target.sourceID, SourceInput: target.sourceInput, SessionID: target.sessionID, References: target.references, LLMProfile: target.llmProfile, StructuredOutputRepairAttempts: target.structuredOutputRepairAttempts, Metadata: target.metadata, Chunk: target.chunk, Chunks: target.chunks, Ref: target.ref, Value: value})
},
}
return nil