Preserve terminal rejection warnings
This commit is contained in:
@@ -134,7 +134,7 @@ func TestAssembledSpellPipelineHonorsNormalizeValidatorOverride(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestAssembledSpellPipelineRejectsUnknownSpellWithoutPromotingAttemptWarning(t *testing.T) {
|
||||
func TestAssembledSpellPipelinePromotesTerminalUnknownSpellWarning(t *testing.T) {
|
||||
registries, resolved, _ := assembledSpellPipeline(t, assembledSpellPipelineOptions{unknownSpell: true})
|
||||
prepared, err := pipeline.Prepare(resolved, registries, pipeline.ModuleDependencies{})
|
||||
if err != nil {
|
||||
@@ -161,10 +161,8 @@ func TestAssembledSpellPipelineRejectsUnknownSpellWithoutPromotingAttemptWarning
|
||||
if !reflect.DeepEqual(rejectedFile.Rejected, output.Rejected) {
|
||||
t.Fatalf("rejected file = %#v, run rejections = %#v, want durable rejection diagnostic", rejectedFile.Rejected, output.Rejected)
|
||||
}
|
||||
for _, warning := range output.Warnings {
|
||||
if warning.ReasonCode == spellnormalize.ReasonCodeSpellNameUnresolved {
|
||||
t.Fatalf("warnings = %#v, want rejected-attempt warning to remain non-durable", output.Warnings)
|
||||
}
|
||||
if len(output.Warnings) != 1 || output.Warnings[0].ReasonCode != spellnormalize.ReasonCodeSpellNameUnresolved || output.Warnings[0].Scope != "spell_casts[0]" {
|
||||
t.Fatalf("warnings = %#v, want terminal normalize catalog warning", output.Warnings)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -92,7 +92,7 @@ func TestProductionSpellCatalogValidationRetries(t *testing.T) {
|
||||
t.Fatalf("rejection = %#v, want exhausted unknown-spell rejection", rejection)
|
||||
}
|
||||
if len(output.Warnings) != 0 {
|
||||
t.Fatalf("warnings = %#v, want no warnings from rejected attempts", output.Warnings)
|
||||
t.Fatalf("warnings = %#v, want no emitted warnings from rejected attempts", output.Warnings)
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
@@ -240,9 +240,7 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (output RunOutput, err
|
||||
if chunkResult.rejection != nil {
|
||||
output.Rejected = append(output.Rejected, *chunkResult.rejection)
|
||||
}
|
||||
if chunkResult.accepted || chunkResult.lookup.Status == ChunkPlanHit {
|
||||
output.Warnings = append(output.Warnings, chunkResult.warnings...)
|
||||
}
|
||||
output.Warnings = append(output.Warnings, chunkResult.warnings...)
|
||||
chunkDebugPayload := map[string]any{
|
||||
"cache_mode": chunkMode,
|
||||
"lookup": chunkResult.lookup,
|
||||
@@ -422,45 +420,52 @@ func (r *Runner) runPreparedSteps(ctx context.Context, input RunInput, checkpoin
|
||||
return nil
|
||||
}
|
||||
|
||||
func runWithRetry(ctx context.Context, retries int, run func(attempt int) (bool, *contracts.RejectedOutput, error)) (bool, *contracts.RejectedOutput, error) {
|
||||
type retryAttemptResult struct {
|
||||
accepted bool
|
||||
rejection *contracts.RejectedOutput
|
||||
warnings []contracts.Warning
|
||||
}
|
||||
|
||||
func runWithRetry(ctx context.Context, retries int, run func(attempt int) (retryAttemptResult, error)) (retryAttemptResult, error) {
|
||||
attempts := retries + 1
|
||||
var last *contracts.RejectedOutput
|
||||
var last retryAttemptResult
|
||||
for attempt := 1; attempt <= attempts; attempt++ {
|
||||
if err := ctx.Err(); err != nil {
|
||||
return false, nil, err
|
||||
return retryAttemptResult{}, err
|
||||
}
|
||||
accepted, rejection, err := run(attempt)
|
||||
result, err := run(attempt)
|
||||
if err != nil {
|
||||
var debugErr *attemptDebugPersistenceError
|
||||
if errors.As(err, &debugErr) {
|
||||
return false, nil, fmt.Errorf("failed after %d attempt(s): %w", attempt, err)
|
||||
return retryAttemptResult{}, fmt.Errorf("failed after %d attempt(s): %w", attempt, err)
|
||||
}
|
||||
if attempt == attempts {
|
||||
return false, nil, fmt.Errorf("failed after %d attempt(s): %w", attempt, err)
|
||||
return retryAttemptResult{}, fmt.Errorf("failed after %d attempt(s): %w", attempt, err)
|
||||
}
|
||||
if ctxErr := ctx.Err(); ctxErr != nil {
|
||||
return false, nil, ctxErr
|
||||
return retryAttemptResult{}, ctxErr
|
||||
}
|
||||
continue
|
||||
}
|
||||
if accepted {
|
||||
return true, nil, nil
|
||||
if result.accepted {
|
||||
return result, nil
|
||||
}
|
||||
if rejection != nil {
|
||||
if result.rejection != nil {
|
||||
rejection := *result.rejection
|
||||
rejection.AttemptCount = attempt
|
||||
last = rejection
|
||||
last = retryAttemptResult{rejection: &rejection, warnings: cloneWarnings(result.warnings)}
|
||||
}
|
||||
if ctxErr := ctx.Err(); ctxErr != nil {
|
||||
return false, nil, ctxErr
|
||||
return retryAttemptResult{}, ctxErr
|
||||
}
|
||||
if attempt == attempts {
|
||||
if last == nil {
|
||||
last = &contracts.RejectedOutput{ReasonCode: "output_rejected", Message: "output rejected", AttemptCount: attempt}
|
||||
if last.rejection == nil {
|
||||
last.rejection = &contracts.RejectedOutput{ReasonCode: "output_rejected", Message: "output rejected", AttemptCount: attempt}
|
||||
}
|
||||
return false, last, nil
|
||||
return last, nil
|
||||
}
|
||||
}
|
||||
return false, last, nil
|
||||
return last, nil
|
||||
}
|
||||
|
||||
func (r *Runner) validateChunks(ctx context.Context, doc *source.SourceDocument, moduleKey string, chunks []source.Chunk, sourceInput contracts.LLMInputMaterial, sessionID string, references contracts.ReferenceSet, metadata map[string]any, prepared preparedValidatorChain, attempt int, debug DebugRecorder) ([]contracts.Warning, *contracts.RejectedOutput, error) {
|
||||
|
||||
@@ -84,14 +84,14 @@ func (r *Runner) runChunkPlan(ctx context.Context, input RunInput, doc *source.S
|
||||
}
|
||||
|
||||
var producerWarnings []contracts.Warning
|
||||
accepted, rejection, err := runWithRetry(ctx, input.pipeline.Chunk.Retries, func(attempt int) (bool, *contracts.RejectedOutput, error) {
|
||||
retryResult, err := runWithRetry(ctx, input.pipeline.Chunk.Retries, func(attempt int) (retryAttemptResult, error) {
|
||||
attemptStarted := time.Now().UTC()
|
||||
attemptPath := path.Join("chunk", fmt.Sprintf("attempt-%02d", attempt))
|
||||
attemptCtx, llmScope := withDebugLLMScope(ctx, attemptPath)
|
||||
terminal := newAttemptTerminalRecorder(input.Debug, attemptPath, "chunk", llmScope, debugTimedEnvelope{Stage: string(StageChunk), ModuleKey: chunker.Key(), Attempt: attempt, StartedAt: attemptStarted})
|
||||
requestMetadata, metadataErr := cloneMetadata(input.Metadata)
|
||||
if metadataErr != nil {
|
||||
return false, nil, terminal.record(nil, fmt.Errorf("clone chunk request metadata: %w", metadataErr))
|
||||
return retryAttemptResult{}, terminal.record(nil, fmt.Errorf("clone chunk request metadata: %w", metadataErr))
|
||||
}
|
||||
chunkResult, callErr := chunker.Plan(attemptCtx, contracts.ChunkRequest{
|
||||
Source: doc, SourceInput: sourceInput.Clone(), SessionID: sessionID,
|
||||
@@ -99,21 +99,21 @@ func (r *Runner) runChunkPlan(ctx context.Context, input RunInput, doc *source.S
|
||||
LLMProfile: input.pipeline.Chunk.LLMProfile, Metadata: requestMetadata,
|
||||
})
|
||||
if callErr != nil {
|
||||
return false, nil, terminal.record(nil, fmt.Errorf("chunk source with chunker %q: %w", chunker.Key(), callErr))
|
||||
return retryAttemptResult{}, terminal.record(nil, fmt.Errorf("chunk source with chunker %q: %w", chunker.Key(), callErr))
|
||||
}
|
||||
plan, chunks, validationErr := validateAndMaterializeChunkPlan(doc, chunkResult.Plan)
|
||||
if validationErr != nil {
|
||||
attemptErr := fmt.Errorf("validate chunk plan from chunker %q: %w", chunker.Key(), validationErr)
|
||||
payload := map[string]any{"plan": debugChunkPlanEnvelope(chunkResult.Plan), "warnings": debugWarningEnvelopes(chunkResult.Warnings)}
|
||||
return false, nil, terminal.record(payload, attemptErr)
|
||||
return retryAttemptResult{}, terminal.record(payload, attemptErr)
|
||||
}
|
||||
planDigest, digestErr := source.DigestChunkPlan(plan)
|
||||
if digestErr != nil {
|
||||
return false, nil, terminal.record(nil, fmt.Errorf("digest generated chunk plan: %w", digestErr))
|
||||
return retryAttemptResult{}, terminal.record(nil, fmt.Errorf("digest generated chunk plan: %w", digestErr))
|
||||
}
|
||||
producerMetadata, _, metadataErr := moduleManifestMetadata(chunker)
|
||||
if metadataErr != nil {
|
||||
return false, nil, terminal.record(nil, fmt.Errorf("clone chunker manifest metadata: %w", metadataErr))
|
||||
return retryAttemptResult{}, terminal.record(nil, fmt.Errorf("clone chunker manifest metadata: %w", metadataErr))
|
||||
}
|
||||
profile := ""
|
||||
if input.pipeline.ChunkExecutionClass == contracts.ExecutionClassLLMBacked {
|
||||
@@ -137,7 +137,7 @@ func (r *Runner) runChunkPlan(ctx context.Context, input RunInput, doc *source.S
|
||||
action = "bypassed"
|
||||
}
|
||||
if candidateErr := result.setCandidate(candidate, action); candidateErr != nil {
|
||||
return false, nil, terminal.record(nil, fmt.Errorf("clone generated chunk plan record: %w", candidateErr))
|
||||
return retryAttemptResult{}, terminal.record(nil, fmt.Errorf("clone generated chunk plan record: %w", candidateErr))
|
||||
}
|
||||
validationWarnings, rejected, validationErr := r.validateChunks(attemptCtx, doc, chunker.Key(), chunks, sourceInput, sessionID, input.pipeline.ChunkReferences.ReferenceSet, input.Metadata, input.Prepared.chunkValidators, attempt, input.Debug)
|
||||
attemptWarnings := append(cloneWarnings(chunkResult.Warnings), validationWarnings...)
|
||||
@@ -145,9 +145,16 @@ func (r *Runner) runChunkPlan(ctx context.Context, input RunInput, doc *source.S
|
||||
"plan": debugChunkPlanEnvelope(plan), "materialized_chunks": debugSourceChunkEnvelopes(chunks),
|
||||
"warnings": debugWarningEnvelopes(attemptWarnings), "rejection": debugRejectedOutputPtr(rejected),
|
||||
}
|
||||
if validationErr != nil || rejected != nil {
|
||||
if validationErr != nil {
|
||||
result.setValidation(validationWarnings, rejected, validationErr)
|
||||
return false, rejected, terminal.record(payload, validationErr)
|
||||
return retryAttemptResult{}, terminal.record(payload, validationErr)
|
||||
}
|
||||
if rejected != nil {
|
||||
result.setValidation(validationWarnings, rejected, nil)
|
||||
if debugErr := terminal.record(payload, nil); debugErr != nil {
|
||||
return retryAttemptResult{}, debugErr
|
||||
}
|
||||
return retryAttemptResult{rejection: rejected, warnings: attemptWarnings}, nil
|
||||
}
|
||||
result.chunks = chunks
|
||||
result.plan = &plan
|
||||
@@ -155,9 +162,9 @@ func (r *Runner) runChunkPlan(ctx context.Context, input RunInput, doc *source.S
|
||||
producerWarnings = cloneWarnings(chunkResult.Warnings)
|
||||
result.setValidation(validationWarnings, nil, nil)
|
||||
if debugErr := terminal.record(payload, nil); debugErr != nil {
|
||||
return false, nil, debugErr
|
||||
return retryAttemptResult{}, debugErr
|
||||
}
|
||||
return true, nil, nil
|
||||
return retryAttemptResult{accepted: true}, nil
|
||||
})
|
||||
if err != nil {
|
||||
if result.summary.ValidationStatus == "not_run" {
|
||||
@@ -165,9 +172,10 @@ func (r *Runner) runChunkPlan(ctx context.Context, input RunInput, doc *source.S
|
||||
}
|
||||
return result, err
|
||||
}
|
||||
result.accepted = accepted
|
||||
result.rejection = rejection
|
||||
if !accepted {
|
||||
result.accepted = retryResult.accepted
|
||||
result.rejection = retryResult.rejection
|
||||
if !retryResult.accepted {
|
||||
result.warnings = cloneWarnings(retryResult.warnings)
|
||||
return result, nil
|
||||
}
|
||||
|
||||
|
||||
@@ -254,6 +254,9 @@ func (e *laneEngine) startContinuationWorkers() {
|
||||
}
|
||||
}
|
||||
|
||||
// collect is the sole owner of pending, launch, and completion accounting. It
|
||||
// must drain closed extract results and one completion for every launched
|
||||
// continuation, even after cancellation.
|
||||
func (e *laneEngine) collect() {
|
||||
resultChannel := (<-chan extractJobResult)(e.results)
|
||||
for resultChannel != nil || len(e.pending) > 0 || e.completed < e.launched {
|
||||
@@ -407,20 +410,20 @@ func (r *Runner) runExtractJob(ctx context.Context, input RunInput, doc *source.
|
||||
var accepted erasedExtractArtifact
|
||||
var serialized CheckpointArtifact
|
||||
var acceptedWarnings []contracts.Warning
|
||||
ok, rejection, err := runWithRetry(ctx, lane.Extract.Retries, func(attempt int) (bool, *contracts.RejectedOutput, error) {
|
||||
retryResult, err := runWithRetry(ctx, lane.Extract.Retries, func(attempt int) (retryAttemptResult, error) {
|
||||
started := time.Now().UTC()
|
||||
attemptPath := path.Join("extract", fileio.EncodePathComponent(lane.ID), fmt.Sprintf("chunk-%06d", chunk.Index+1), fmt.Sprintf("attempt-%02d", attempt))
|
||||
attemptCtx, llmScope := withDebugLLMScope(ctx, attemptPath)
|
||||
terminal := newAttemptTerminalRecorder(input.Debug, attemptPath, "extract", llmScope, debugTimedEnvelope{Stage: string(StageExtract), StepID: input.stepID, LaneID: lane.ID, ModuleKey: lane.Extract.Module, Attempt: attempt, StartedAt: started})
|
||||
requestMetadata, metadataErr := cloneMetadata(input.Metadata)
|
||||
if metadataErr != nil {
|
||||
return false, nil, terminal.record(nil, fmt.Errorf("clone extract request metadata: %w", metadataErr))
|
||||
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})
|
||||
if callErr != nil {
|
||||
attemptErr := fmt.Errorf("extract lane %q chunk %q with extractor %q: %w", lane.ID, chunk.ID, lane.Extract.Module, callErr)
|
||||
return false, nil, terminal.record(nil, attemptErr)
|
||||
return retryAttemptResult{}, terminal.record(nil, attemptErr)
|
||||
}
|
||||
artifact := erasedExtractArtifact{LaneID: lane.ID, ExtractorKey: lane.Extract.Module, SourceID: doc.ID, ChunkID: chunk.ID, ChunkIndex: chunk.Index, ChunkRef: chunk.Ref, Value: extracted.Value}
|
||||
attemptWarnings := cloneWarnings(extracted.Warnings)
|
||||
@@ -428,31 +431,38 @@ func (r *Runner) runExtractJob(ctx context.Context, input RunInput, doc *source.
|
||||
if encodeErr != nil {
|
||||
attemptErr := fmt.Errorf("serialize extract candidate for lane %q chunk %q: %w", lane.ID, chunk.ID, encodeErr)
|
||||
payload := map[string]any{"warnings": debugWarningEnvelopes(attemptWarnings)}
|
||||
return false, nil, terminal.record(payload, attemptErr)
|
||||
return retryAttemptResult{}, terminal.record(payload, attemptErr)
|
||||
}
|
||||
serializedCandidate.ChunkID, serializedCandidate.ChunkIndex, serializedCandidate.ChunkRef = artifact.ChunkID, artifact.ChunkIndex, artifact.ChunkRef
|
||||
warnings, rejected, validateErr := r.validateTypedArtifact(attemptCtx, typed.codec, typedValidationTarget{stage: StageExtract, stepID: input.stepID, laneID: lane.ID, moduleKey: lane.Extract.Module, source: doc, sourceID: doc.ID, sourceInput: chunkInputMaterial(sourceInput, chunk), sessionID: sessionID, references: extractReferences, metadata: input.Metadata, chunk: &chunk, ref: chunk.Ref, value: extracted.Value, candidate: &serializedCandidate}, state.prepared.extractValidators, attempt, input.Debug)
|
||||
attemptWarnings = append(attemptWarnings, warnings...)
|
||||
payload := map[string]any{"output": debugCheckpointArtifact(serializedCandidate), "warnings": debugWarningEnvelopes(attemptWarnings), "rejection": debugRejectedOutputPtr(rejected)}
|
||||
if validateErr != nil || rejected != nil {
|
||||
return false, rejected, terminal.record(payload, validateErr)
|
||||
if validateErr != nil {
|
||||
return retryAttemptResult{}, terminal.record(payload, validateErr)
|
||||
}
|
||||
if rejected != nil {
|
||||
if debugErr := terminal.record(payload, nil); debugErr != nil {
|
||||
return retryAttemptResult{}, debugErr
|
||||
}
|
||||
return retryAttemptResult{rejection: rejected, warnings: attemptWarnings}, nil
|
||||
}
|
||||
stored, encodeErr := checkpointArtifact(typed.codec, artifact.LaneID, artifact.ExtractorKey, artifact.SourceID, artifact.Value)
|
||||
if encodeErr != nil {
|
||||
attemptErr := fmt.Errorf("serialize accepted extract output for lane %q chunk %q: %w", lane.ID, chunk.ID, encodeErr)
|
||||
return false, nil, terminal.record(payload, attemptErr)
|
||||
return retryAttemptResult{}, terminal.record(payload, attemptErr)
|
||||
}
|
||||
stored.ChunkID, stored.ChunkIndex, stored.ChunkRef = artifact.ChunkID, artifact.ChunkIndex, artifact.ChunkRef
|
||||
accepted, serialized = artifact, stored
|
||||
acceptedWarnings = attemptWarnings
|
||||
if debugErr := terminal.record(payload, nil); debugErr != nil {
|
||||
return false, nil, debugErr
|
||||
return retryAttemptResult{}, debugErr
|
||||
}
|
||||
return true, nil, nil
|
||||
return retryAttemptResult{accepted: true}, nil
|
||||
})
|
||||
result.err = err
|
||||
if err == nil && !ok {
|
||||
result.rejected = rejection
|
||||
if err == nil && !retryResult.accepted {
|
||||
result.rejected = retryResult.rejection
|
||||
result.warnings = cloneWarnings(retryResult.warnings)
|
||||
return result
|
||||
}
|
||||
result.value, result.serialized, result.warnings = accepted, serialized, acceptedWarnings
|
||||
@@ -470,6 +480,7 @@ func finalizeLaneExtract(checkpoints CheckpointRecorder, stepID string, state *l
|
||||
result := state.results[index]
|
||||
if result.rejected != nil {
|
||||
state.rejected = append(state.rejected, *result.rejected)
|
||||
state.warnings = append(state.warnings, result.warnings...)
|
||||
continue
|
||||
}
|
||||
state.values = append(state.values, result.value)
|
||||
|
||||
142
internal/framework/pipeline/runner_rejection_warnings_test.go
Normal file
142
internal/framework/pipeline/runner_rejection_warnings_test.go
Normal file
@@ -0,0 +1,142 @@
|
||||
package pipeline
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"reflect"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
|
||||
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
|
||||
)
|
||||
|
||||
type warningChunker struct {
|
||||
key string
|
||||
plan source.ChunkPlan
|
||||
calls int
|
||||
}
|
||||
|
||||
func (c *warningChunker) Key() string { return c.key }
|
||||
func (*warningChunker) ReferenceSlots() []contracts.ReferenceSlot { return nil }
|
||||
func (c *warningChunker) Plan(context.Context, contracts.ChunkRequest) (contracts.ChunkPlanResult, error) {
|
||||
c.calls++
|
||||
return contracts.ChunkPlanResult{
|
||||
Plan: source.CloneChunkPlan(c.plan),
|
||||
Warnings: []contracts.Warning{{Scope: fmt.Sprintf("operation-%d", c.calls), ReasonCode: "operation", Message: "operation warning"}},
|
||||
}, nil
|
||||
}
|
||||
|
||||
type chunkValidationFunc struct {
|
||||
name string
|
||||
validate func(context.Context, contracts.ChunkValidationRequest) (contracts.ValidationResult, error)
|
||||
}
|
||||
|
||||
func (v chunkValidationFunc) Name() string { return v.name }
|
||||
func (chunkValidationFunc) ExecutionClass() contracts.ExecutionClass {
|
||||
return contracts.ExecutionClassDeterministic
|
||||
}
|
||||
func (v chunkValidationFunc) Validate(ctx context.Context, request contracts.ChunkValidationRequest) (contracts.ValidationResult, error) {
|
||||
return v.validate(ctx, request)
|
||||
}
|
||||
|
||||
func TestRunnerPromotesOnlyTerminalRejectionWarnings(t *testing.T) {
|
||||
for _, target := range []ModuleStage{StageChunk, StageExtract, StageMerge, StageNormalize} {
|
||||
t.Run(string(target), func(t *testing.T) {
|
||||
prepared := preparedAttemptDebugPipeline(t)
|
||||
lane := &prepared.Steps[0].lanes[0]
|
||||
attempts := 0
|
||||
first := func() contracts.ValidationResult {
|
||||
return contracts.ValidationResult{Approved: true, Warnings: []contracts.Warning{{Scope: fmt.Sprintf("validator-%d", attempts), ReasonCode: "validator", Message: "validator warning"}}}
|
||||
}
|
||||
reject := func() contracts.ValidationResult {
|
||||
return contracts.ValidationResult{Approved: false, ReasonCode: "rejected", Message: "rejected"}
|
||||
}
|
||||
debug := newCapturedDebugRecorder()
|
||||
recorder := &extractCaptureRecorder{CheckpointRecorder: NoopCheckpointRecorder()}
|
||||
|
||||
switch target {
|
||||
case StageChunk:
|
||||
chunker := prepared.chunker.(*typedTestChunker)
|
||||
prepared.chunker = &warningChunker{key: prepared.resolved.Chunk.Module, plan: source.CloneChunkPlan(chunker.plan)}
|
||||
prepared.resolved.Chunk.Retries = 1
|
||||
prepared.chunkValidators.validators = []preparedValidator{
|
||||
{resolved: ResolvedValidator{Binding: Binding("warning-approval"), Target: ValidatorTargetChunk}, chunk: chunkValidationFunc{name: "warning-approval", validate: func(context.Context, contracts.ChunkValidationRequest) (contracts.ValidationResult, error) {
|
||||
return first(), nil
|
||||
}}},
|
||||
{resolved: ResolvedValidator{Binding: Binding("warning-rejection"), Target: ValidatorTargetChunk}, chunk: chunkValidationFunc{name: "warning-rejection", validate: func(context.Context, contracts.ChunkValidationRequest) (contracts.ValidationResult, error) {
|
||||
return reject(), nil
|
||||
}}},
|
||||
}
|
||||
chunkerWithWarnings := prepared.chunker.(*warningChunker)
|
||||
first = func() contracts.ValidationResult {
|
||||
return contracts.ValidationResult{Approved: true, Warnings: []contracts.Warning{{Scope: fmt.Sprintf("validator-%d", chunkerWithWarnings.calls), ReasonCode: "validator", Message: "validator warning"}}}
|
||||
}
|
||||
case StageExtract:
|
||||
lane.resolved.Extract.Retries = 1
|
||||
installExtractOperation(prepared, 0, func(context.Context, contracts.TypedExtractionRequest) (erasedTypedResult, error) {
|
||||
attempts++
|
||||
return erasedTypedResult{Value: codecNotes{Items: []string{"extract"}}, Warnings: []contracts.Warning{{Scope: fmt.Sprintf("operation-%d", attempts), ReasonCode: "operation", Message: "operation warning"}}}, nil
|
||||
})
|
||||
lane.extractValidators.validators = rejectionWarningTypedValidators(first, reject)
|
||||
case StageMerge:
|
||||
lane.resolved.Merge.Retries = 1
|
||||
lane.typed.merge = func(context.Context, any, contracts.TypedMergeRequest[any]) (erasedTypedResult, error) {
|
||||
attempts++
|
||||
return erasedTypedResult{Value: codecNotes{Items: []string{"merge"}}, Warnings: []contracts.Warning{{Scope: fmt.Sprintf("operation-%d", attempts), ReasonCode: "operation", Message: "operation warning"}}}, nil
|
||||
}
|
||||
lane.mergeValidators.validators = rejectionWarningTypedValidators(first, reject)
|
||||
case StageNormalize:
|
||||
lane.resolved.Normalize.Retries = 1
|
||||
lane.typed.normalize = func(context.Context, any, contracts.TypedNormalizeRequest[any]) (erasedTypedResult, error) {
|
||||
attempts++
|
||||
return erasedTypedResult{Value: codecNotes{Items: []string{"normalize"}}, Warnings: []contracts.Warning{{Scope: fmt.Sprintf("operation-%d", attempts), ReasonCode: "operation", Message: "operation warning"}}}, nil
|
||||
}
|
||||
lane.normalizeValidators.validators = rejectionWarningTypedValidators(first, reject)
|
||||
}
|
||||
|
||||
output, err := New().Run(context.Background(), RunInput{Prepared: prepared, RawInput: []byte("input"), Checkpoints: recorder, Debug: debug})
|
||||
if err != nil {
|
||||
t.Fatalf("Run() error = %v, want nil", err)
|
||||
}
|
||||
wantScopes := []string{"operation-2", "validator-2"}
|
||||
if got := rejectionWarningScopes(output.Warnings); !reflect.DeepEqual(got, wantScopes) {
|
||||
t.Fatalf("published warning scopes = %#v, want %#v", got, wantScopes)
|
||||
}
|
||||
if len(output.Rejected) != 1 || output.Rejected[0].AttemptCount != 2 {
|
||||
t.Fatalf("rejections = %#v, want final rejection after two attempts", output.Rejected)
|
||||
}
|
||||
if target == StageExtract && !reflect.DeepEqual(rejectionWarningScopes(recorder.checkpoint.Warnings), wantScopes) {
|
||||
t.Fatalf("extract checkpoint warnings = %#v, want %#v", recorder.checkpoint.Warnings, wantScopes)
|
||||
}
|
||||
attemptPath := fmt.Sprintf("%s/notes/attempt-01.json", target)
|
||||
if target == StageChunk {
|
||||
attemptPath = "chunk/attempt-01.json"
|
||||
} else if target == StageExtract {
|
||||
attemptPath = "extract/notes/chunk-000001/attempt-01.json"
|
||||
}
|
||||
if !strings.Contains(string(debug.json[attemptPath]), "operation-1") || !strings.Contains(string(debug.json[attemptPath]), "validator-1") {
|
||||
t.Fatalf("first attempt debug = %s, want discarded warnings", debug.json[attemptPath])
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func rejectionWarningTypedValidators(first func() contracts.ValidationResult, reject func() contracts.ValidationResult) []preparedValidator {
|
||||
return []preparedValidator{
|
||||
{resolved: ResolvedValidator{Binding: Binding("warning-approval"), Target: ValidatorTargetTyped, ArtifactKind: "test/notes"}, typedValidate: func(context.Context, any, typedValidationTarget) (contracts.ValidationResult, error) {
|
||||
return first(), nil
|
||||
}},
|
||||
{resolved: ResolvedValidator{Binding: Binding("warning-rejection"), Target: ValidatorTargetTyped, ArtifactKind: "test/notes"}, typedValidate: func(context.Context, any, typedValidationTarget) (contracts.ValidationResult, error) {
|
||||
return reject(), nil
|
||||
}},
|
||||
}
|
||||
}
|
||||
|
||||
func rejectionWarningScopes(warnings []contracts.Warning) []string {
|
||||
scopes := make([]string, len(warnings))
|
||||
for index := range warnings {
|
||||
scopes[index] = warnings[index].Scope
|
||||
}
|
||||
return scopes
|
||||
}
|
||||
@@ -249,52 +249,59 @@ func (r *Runner) runMergeStage(ctx context.Context, input RunInput, checkpoints
|
||||
if err := checkpointMergeRunning(checkpoints, input.stepID, lane.ID, lane.Merge.Module, mergeDeps); err != nil {
|
||||
return stageResult, err
|
||||
}
|
||||
ok, rejection, runErr := runWithRetry(ctx, lane.Merge.Retries, func(attempt int) (bool, *contracts.RejectedOutput, error) {
|
||||
retryResult, runErr := runWithRetry(ctx, lane.Merge.Retries, func(attempt int) (retryAttemptResult, error) {
|
||||
started := time.Now().UTC()
|
||||
attemptPath := path.Join("merge", fileio.EncodePathComponent(lane.ID), fmt.Sprintf("attempt-%02d", attempt))
|
||||
attemptCtx, llmScope := withDebugLLMScope(ctx, attemptPath)
|
||||
terminal := newAttemptTerminalRecorder(input.Debug, attemptPath, "merge", llmScope, debugTimedEnvelope{Stage: string(StageMerge), StepID: input.stepID, LaneID: lane.ID, ModuleKey: lane.Merge.Module, Attempt: attempt, StartedAt: started})
|
||||
requestMetadata, metadataErr := cloneMetadata(input.Metadata)
|
||||
if metadataErr != nil {
|
||||
return false, nil, terminal.record(nil, fmt.Errorf("clone merge request metadata: %w", metadataErr))
|
||||
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})
|
||||
if callErr != nil {
|
||||
attemptErr := fmt.Errorf("merge lane %q with merger %q: %w", lane.ID, lane.Merge.Module, callErr)
|
||||
return false, nil, terminal.record(nil, attemptErr)
|
||||
return retryAttemptResult{}, terminal.record(nil, attemptErr)
|
||||
}
|
||||
candidate := erasedMergeArtifact{LaneID: lane.ID, MergerKey: lane.Merge.Module, SourceID: doc.ID, Value: result.Value}
|
||||
attemptWarnings := cloneWarnings(result.Warnings)
|
||||
serializedCandidate, encodeErr := serializeCandidateArtifact(typed.codec, candidate.LaneID, candidate.MergerKey, candidate.SourceID, candidate.Value)
|
||||
if encodeErr != nil {
|
||||
attemptErr := fmt.Errorf("serialize merge candidate for lane %q: %w", lane.ID, encodeErr)
|
||||
return false, nil, terminal.record(map[string]any{"warnings": debugWarningEnvelopes(attemptWarnings)}, attemptErr)
|
||||
return retryAttemptResult{}, terminal.record(map[string]any{"warnings": debugWarningEnvelopes(attemptWarnings)}, attemptErr)
|
||||
}
|
||||
warnings, rejected, validateErr := r.validateTypedArtifact(attemptCtx, typed.codec, typedValidationTarget{stage: StageMerge, stepID: input.stepID, laneID: lane.ID, moduleKey: lane.Merge.Module, source: doc, sourceID: doc.ID, sourceInput: sourceInput.Clone(), sessionID: sessionID, references: mergeReferences, metadata: input.Metadata, value: result.Value, candidate: &serializedCandidate}, prepared.mergeValidators, attempt, input.Debug)
|
||||
attemptWarnings = append(attemptWarnings, warnings...)
|
||||
payload := map[string]any{"output": debugCheckpointArtifact(serializedCandidate), "warnings": debugWarningEnvelopes(attemptWarnings), "rejection": debugRejectedOutputPtr(rejected)}
|
||||
if validateErr != nil || rejected != nil {
|
||||
return false, rejected, terminal.record(payload, validateErr)
|
||||
if validateErr != nil {
|
||||
return retryAttemptResult{}, terminal.record(payload, validateErr)
|
||||
}
|
||||
if rejected != nil {
|
||||
if debugErr := terminal.record(payload, nil); debugErr != nil {
|
||||
return retryAttemptResult{}, debugErr
|
||||
}
|
||||
return retryAttemptResult{rejection: rejected, warnings: attemptWarnings}, nil
|
||||
}
|
||||
stored, encodeErr := checkpointArtifact(typed.codec, candidate.LaneID, candidate.MergerKey, candidate.SourceID, candidate.Value)
|
||||
if encodeErr != nil {
|
||||
attemptErr := fmt.Errorf("serialize accepted merge output for lane %q: %w", lane.ID, encodeErr)
|
||||
return false, nil, terminal.record(payload, attemptErr)
|
||||
return retryAttemptResult{}, terminal.record(payload, attemptErr)
|
||||
}
|
||||
if debugErr := terminal.record(payload, nil); debugErr != nil {
|
||||
return false, nil, debugErr
|
||||
return retryAttemptResult{}, debugErr
|
||||
}
|
||||
merged, serializedMerge = candidate, stored
|
||||
mergeWarnings = attemptWarnings
|
||||
return true, nil, nil
|
||||
return retryAttemptResult{accepted: true}, nil
|
||||
})
|
||||
if runErr != nil {
|
||||
_ = checkpointMergeFailed(checkpoints, input.stepID, lane.ID, lane.Merge.Module, mergeDeps, runErr)
|
||||
return stageResult, runErr
|
||||
}
|
||||
if !ok {
|
||||
output.Rejected = append(output.Rejected, *rejection)
|
||||
if err := checkpointMergeRejected(checkpoints, input.stepID, lane.ID, lane.Merge.Module, mergeDeps, *rejection); err != nil {
|
||||
if !retryResult.accepted {
|
||||
output.Warnings = append(output.Warnings, retryResult.warnings...)
|
||||
output.Rejected = append(output.Rejected, *retryResult.rejection)
|
||||
if err := checkpointMergeRejected(checkpoints, input.stepID, lane.ID, lane.Merge.Module, mergeDeps, *retryResult.rejection); err != nil {
|
||||
return stageResult, err
|
||||
}
|
||||
stageResult.terminal = true
|
||||
@@ -344,30 +351,30 @@ func (r *Runner) runNormalizeStage(ctx context.Context, input RunInput, checkpoi
|
||||
if err := checkpointNormalizeRunning(checkpoints, input.stepID, lane.ID, lane.Normalize.Module, normalizeDeps); err != nil {
|
||||
return stageResult, err
|
||||
}
|
||||
ok, rejection, runErr := runWithRetry(ctx, lane.Normalize.Retries, func(attempt int) (bool, *contracts.RejectedOutput, error) {
|
||||
retryResult, runErr := runWithRetry(ctx, lane.Normalize.Retries, func(attempt int) (retryAttemptResult, error) {
|
||||
started := time.Now().UTC()
|
||||
attemptPath := path.Join("normalize", fileio.EncodePathComponent(lane.ID), fmt.Sprintf("attempt-%02d", attempt))
|
||||
attemptCtx, llmScope := withDebugLLMScope(ctx, attemptPath)
|
||||
terminal := newAttemptTerminalRecorder(input.Debug, attemptPath, "normalize", llmScope, debugTimedEnvelope{Stage: string(StageNormalize), StepID: input.stepID, LaneID: lane.ID, ModuleKey: lane.Normalize.Module, Attempt: attempt, StartedAt: started})
|
||||
requestMetadata, metadataErr := cloneMetadata(input.Metadata)
|
||||
if metadataErr != nil {
|
||||
return false, nil, terminal.record(nil, fmt.Errorf("clone normalize request metadata: %w", metadataErr))
|
||||
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})
|
||||
if callErr != nil {
|
||||
attemptErr := fmt.Errorf("normalize lane %q with normalizer %q: %w", lane.ID, lane.Normalize.Module, callErr)
|
||||
return false, nil, terminal.record(nil, attemptErr)
|
||||
return retryAttemptResult{}, terminal.record(nil, attemptErr)
|
||||
}
|
||||
attemptWarnings := cloneWarnings(result.Warnings)
|
||||
serializedCandidate, encodeErr := serializeCandidateArtifact(typed.codec, lane.ID, lane.Normalize.Module, doc.ID, result.Value)
|
||||
if encodeErr != nil {
|
||||
attemptErr := fmt.Errorf("serialize normalize candidate for lane %q: %w", lane.ID, encodeErr)
|
||||
return false, nil, terminal.record(map[string]any{"warnings": debugWarningEnvelopes(attemptWarnings)}, attemptErr)
|
||||
return retryAttemptResult{}, terminal.record(map[string]any{"warnings": debugWarningEnvelopes(attemptWarnings)}, attemptErr)
|
||||
}
|
||||
var retryPayload map[string]any
|
||||
if result.Retry != nil {
|
||||
if err := validateNormalizeRetry(result.Retry); err != nil {
|
||||
return false, nil, terminal.record(map[string]any{"output": debugCheckpointArtifact(serializedCandidate), "warnings": debugWarningEnvelopes(attemptWarnings)}, fmt.Errorf("normalize lane %q returned invalid retry directive: %w", lane.ID, err))
|
||||
return retryAttemptResult{}, terminal.record(map[string]any{"output": debugCheckpointArtifact(serializedCandidate), "warnings": debugWarningEnvelopes(attemptWarnings)}, fmt.Errorf("normalize lane %q returned invalid retry directive: %w", lane.ID, err))
|
||||
}
|
||||
retryRemaining := attempt <= lane.Normalize.Retries
|
||||
retryPayload = map[string]any{
|
||||
@@ -378,7 +385,7 @@ func (r *Runner) runNormalizeStage(ctx context.Context, input RunInput, checkpoi
|
||||
}
|
||||
if retryRemaining {
|
||||
payload := map[string]any{"output": debugCheckpointArtifact(serializedCandidate), "warnings": debugWarningEnvelopes(attemptWarnings), "retry": retryPayload}
|
||||
return false, nil, terminal.record(payload, nil)
|
||||
return retryAttemptResult{}, terminal.record(payload, nil)
|
||||
}
|
||||
attemptWarnings = append(attemptWarnings, cloneWarnings(result.Retry.FallbackWarnings)...)
|
||||
}
|
||||
@@ -388,28 +395,35 @@ func (r *Runner) runNormalizeStage(ctx context.Context, input RunInput, checkpoi
|
||||
if retryPayload != nil {
|
||||
payload["retry"] = retryPayload
|
||||
}
|
||||
if validateErr != nil || rejected != nil {
|
||||
return false, rejected, terminal.record(payload, validateErr)
|
||||
if validateErr != nil {
|
||||
return retryAttemptResult{}, terminal.record(payload, validateErr)
|
||||
}
|
||||
if rejected != nil {
|
||||
if debugErr := terminal.record(payload, nil); debugErr != nil {
|
||||
return retryAttemptResult{}, debugErr
|
||||
}
|
||||
return retryAttemptResult{rejection: rejected, warnings: attemptWarnings}, nil
|
||||
}
|
||||
stored, encodeErr := checkpointArtifact(typed.codec, lane.ID, lane.Normalize.Module, doc.ID, result.Value)
|
||||
if encodeErr != nil {
|
||||
attemptErr := fmt.Errorf("serialize accepted normalize output for lane %q: %w", lane.ID, encodeErr)
|
||||
return false, nil, terminal.record(payload, attemptErr)
|
||||
return retryAttemptResult{}, terminal.record(payload, attemptErr)
|
||||
}
|
||||
if debugErr := terminal.record(payload, nil); debugErr != nil {
|
||||
return false, nil, debugErr
|
||||
return retryAttemptResult{}, debugErr
|
||||
}
|
||||
serializedNormalize = stored
|
||||
normalizeWarnings = attemptWarnings
|
||||
return true, nil, nil
|
||||
return retryAttemptResult{accepted: true}, nil
|
||||
})
|
||||
if runErr != nil {
|
||||
_ = checkpointNormalizeFailed(checkpoints, input.stepID, lane.ID, lane.Normalize.Module, normalizeDeps, runErr)
|
||||
return stageResult, runErr
|
||||
}
|
||||
if !ok {
|
||||
output.Rejected = append(output.Rejected, *rejection)
|
||||
if err := checkpointNormalizeRejected(checkpoints, input.stepID, lane.ID, lane.Normalize.Module, normalizeDeps, *rejection); err != nil {
|
||||
if !retryResult.accepted {
|
||||
output.Warnings = append(output.Warnings, retryResult.warnings...)
|
||||
output.Rejected = append(output.Rejected, *retryResult.rejection)
|
||||
if err := checkpointNormalizeRejected(checkpoints, input.stepID, lane.ID, lane.Normalize.Module, normalizeDeps, *retryResult.rejection); err != nil {
|
||||
return stageResult, err
|
||||
}
|
||||
return stageResult, nil
|
||||
|
||||
Reference in New Issue
Block a user