package pipeline import ( "context" "encoding/base64" "encoding/json" "errors" "fmt" "reflect" "strings" "testing" "gitea.maximumdirect.net/eric/notarius/internal/framework/contracts" ) type observedNotesCodec struct { candidateValues []codecNotes candidateDecodedValues []codecNotes finalValues []codecNotes candidateError string candidateDecodeError string finalError string } func (*observedNotesCodec) Kind() contracts.ArtifactKind { return "test/notes" } func (*observedNotesCodec) Schema() contracts.ArtifactSchema { return notesCodec().schema } func (*observedNotesCodec) MediaType() string { return "application/json" } func (c *observedNotesCodec) EncodeCandidate(value codecNotes) ([]byte, error) { c.candidateValues = append(c.candidateValues, value) if c.candidateError != "" && firstNote(value) == c.candidateError { return nil, errors.New("candidate encoding failed") } return json.Marshal(value) } func (c *observedNotesCodec) Encode(value codecNotes) ([]byte, error) { c.finalValues = append(c.finalValues, value) if c.finalError != "" && firstNote(value) == c.finalError { return nil, errors.New("final encoding failed") } if firstNote(value) == "invalid" { return nil, errors.New("invalid note is not a final artifact") } return json.Marshal(value) } func (*observedNotesCodec) Decode(content []byte) (codecNotes, error) { var value codecNotes return value, json.Unmarshal(content, &value) } func (c *observedNotesCodec) DecodeCandidate(content []byte) (codecNotes, error) { value, err := c.Decode(content) if err != nil { return codecNotes{}, err } if c.candidateDecodeError != "" && firstNote(value) == c.candidateDecodeError { return codecNotes{}, errors.New("candidate decoding failed") } c.candidateDecodedValues = append(c.candidateDecodedValues, value) return value, nil } func firstNote(value codecNotes) string { if len(value.Items) == 0 { return "" } return value.Items[0] } func (c *observedNotesCodec) candidateCalls(value string) int { return matchingNotes(c.candidateValues, value) } func (c *observedNotesCodec) finalCalls(value string) int { return matchingNotes(c.finalValues, value) } func (c *observedNotesCodec) candidateDecodeCount() int { return len(c.candidateDecodedValues) } func matchingNotes(values []codecNotes, value string) int { count := 0 for _, candidate := range values { if firstNote(candidate) == value { count++ } } return count } type candidateCheckpointRecorder struct { CheckpointRecorder mergeSucceeded int normalizeSucceeded int mergeOutput CheckpointArtifact normalizeOutput CheckpointArtifact } func (r *candidateCheckpointRecorder) MergeSucceeded(_ string, _ string, _ []CheckpointFingerprint, output CheckpointArtifact, _ []contracts.Warning) error { r.mergeSucceeded++ r.mergeOutput = cloneCheckpointArtifact(output) return nil } func (r *candidateCheckpointRecorder) NormalizeSucceeded(_ string, _ string, _ []CheckpointFingerprint, output CheckpointArtifact, _ []contracts.Warning) error { r.normalizeSucceeded++ r.normalizeOutput = cloneCheckpointArtifact(output) return nil } func installObservedNotesCodec(t *testing.T, prepared *PreparedPipeline, codec *observedNotesCodec) { t.Helper() registry := NewArtifactCodecRegistry() if err := RegisterArtifactCodec(registry, codec); err != nil { t.Fatalf("RegisterArtifactCodec() error = %v", err) } entry, _, err := registry.entry("test/notes") if err != nil { t.Fatalf("codec entry error = %v", err) } prepared.Steps[0].lanes[0].typed.codec = entry } func configureCandidateOperation(prepared *PreparedPipeline, target ModuleStage, value codecNotes) { lane := &prepared.Steps[0].lanes[0] switch target { case StageExtract: lane.typed.extract = func(context.Context, any, contracts.TypedExtractionRequest) (erasedTypedResult, error) { return erasedTypedResult{Value: value}, nil } lane.typed.merge = func(context.Context, any, contracts.TypedMergeRequest[any]) (erasedTypedResult, error) { return erasedTypedResult{Value: codecNotes{Items: []string{"merged-other"}}}, nil } lane.typed.normalize = func(context.Context, any, contracts.TypedNormalizeRequest[any]) (erasedTypedResult, error) { return erasedTypedResult{Value: codecNotes{Items: []string{"normalized-other"}}}, nil } case StageMerge: lane.typed.merge = func(context.Context, any, contracts.TypedMergeRequest[any]) (erasedTypedResult, error) { return erasedTypedResult{Value: value}, nil } lane.typed.normalize = func(context.Context, any, contracts.TypedNormalizeRequest[any]) (erasedTypedResult, error) { return erasedTypedResult{Value: codecNotes{Items: []string{"normalized-other"}}}, nil } case StageNormalize: lane.typed.merge = func(context.Context, any, contracts.TypedMergeRequest[any]) (erasedTypedResult, error) { return erasedTypedResult{Value: codecNotes{Items: []string{"merged-other"}}}, nil } lane.typed.normalize = func(context.Context, any, contracts.TypedNormalizeRequest[any]) (erasedTypedResult, error) { return erasedTypedResult{Value: value}, nil } } } func setCandidateValidator(prepared *PreparedPipeline, target ModuleStage, approved bool) { validator := preparedValidator{ resolved: ResolvedValidator{Binding: Binding("candidate-check"), Target: ValidatorTargetTyped, ArtifactKind: "test/notes"}, typedValidate: func(context.Context, any, typedValidationTarget) (contracts.ValidationResult, error) { return contracts.ValidationResult{Approved: approved, ReasonCode: "candidate_rejected", Message: "candidate rejected by validator"}, nil }, } switch target { case StageExtract: prepared.Steps[0].lanes[0].extractValidators.validators = []preparedValidator{validator} case StageMerge: prepared.Steps[0].lanes[0].mergeValidators.validators = []preparedValidator{validator} case StageNormalize: prepared.Steps[0].lanes[0].normalizeValidators.validators = []preparedValidator{validator} } } type serializedValidationFunc func(context.Context, contracts.SerializedValidationRequest) (contracts.ValidationResult, error) func (serializedValidationFunc) Name() string { return "candidate-serialized" } func (serializedValidationFunc) ExecutionClass() contracts.ExecutionClass { return contracts.ExecutionClassDeterministic } func (validate serializedValidationFunc) Validate(ctx context.Context, request contracts.SerializedValidationRequest) (contracts.ValidationResult, error) { return validate(ctx, request) } func TestRunnerIsolatesTypedValidatorCandidates(t *testing.T) { for _, target := range []ModuleStage{StageExtract, StageMerge, StageNormalize} { t.Run(string(target), func(t *testing.T) { prepared := preparedAttemptDebugPipeline(t) prepared.Steps[0].lanes[0].extractValidators = preparedValidatorChain{} prepared.Steps[0].lanes[0].mergeValidators = preparedValidatorChain{} prepared.Steps[0].lanes[0].normalizeValidators = preparedValidatorChain{} codec := &observedNotesCodec{} installObservedNotesCodec(t, prepared, codec) candidate := codecNotes{Items: []string{"candidate-" + string(target)}, Labels: map[string]string{"label": "original"}, Details: &codecNoteDetails{Name: "original"}} configureCandidateOperation(prepared, target, candidate) var laterValue, serializedValue, downstreamValue codecNotes firstValidator := preparedValidator{ resolved: ResolvedValidator{Binding: Binding("candidate-mutator"), Target: ValidatorTargetTyped, ArtifactKind: "test/notes"}, typedValidate: func(_ context.Context, _ any, request typedValidationTarget) (contracts.ValidationResult, error) { value := request.value.(codecNotes) value.Items[0] = "mutated" value.Labels["label"] = "mutated" value.Details.Name = "mutated" return contracts.ValidationResult{Approved: true}, nil }, } secondValidator := preparedValidator{ resolved: ResolvedValidator{Binding: Binding("candidate-observer"), Target: ValidatorTargetTyped, ArtifactKind: "test/notes"}, typedValidate: func(_ context.Context, _ any, request typedValidationTarget) (contracts.ValidationResult, error) { laterValue = request.value.(codecNotes) return contracts.ValidationResult{Approved: true}, nil }, } serializedValidator := preparedValidator{ resolved: ResolvedValidator{Binding: Binding("candidate-serialized"), Target: ValidatorTargetSerialized, ArtifactKind: "test/notes"}, serialized: serializedValidationFunc(func(_ context.Context, request contracts.SerializedValidationRequest) (contracts.ValidationResult, error) { if err := json.Unmarshal(request.Content, &serializedValue); err != nil { return contracts.ValidationResult{}, err } return contracts.ValidationResult{Approved: true}, nil }), } setCandidateValidators(prepared, target, []preparedValidator{firstValidator, secondValidator, serializedValidator}) lane := &prepared.Steps[0].lanes[0] switch target { case StageExtract: lane.typed.merge = func(_ context.Context, _ any, request contracts.TypedMergeRequest[any]) (erasedTypedResult, error) { downstreamValue = request.ExtractOutputs[0].Value.(codecNotes) return erasedTypedResult{Value: codecNotes{Items: []string{"merged-other"}}}, nil } case StageMerge: lane.typed.normalize = func(_ context.Context, _ any, request contracts.TypedNormalizeRequest[any]) (erasedTypedResult, error) { downstreamValue = request.MergeOutput.Value.(codecNotes) return erasedTypedResult{Value: codecNotes{Items: []string{"normalized-other"}}}, nil } } debug := newCapturedDebugRecorder() output, err := New().Run(context.Background(), RunInput{Prepared: prepared, RawInput: []byte("input"), Debug: debug}) if err != nil { t.Fatalf("Run() error = %v, want nil", err) } if !reflect.DeepEqual(laterValue, candidate) || !reflect.DeepEqual(serializedValue, candidate) { t.Fatalf("validator values = typed %#v serialized %#v, want %#v", laterValue, serializedValue, candidate) } if codec.candidateCalls(candidate.Items[0]) != 1 || codec.candidateDecodeCount() != 2 || codec.finalCalls(candidate.Items[0]) != 1 { t.Fatalf("candidate calls = encode %d decode %d final %d, want 1, 2, 1", codec.candidateCalls(candidate.Items[0]), codec.candidateDecodeCount(), codec.finalCalls(candidate.Items[0])) } switch target { case StageExtract, StageMerge: if !reflect.DeepEqual(downstreamValue, candidate) { t.Fatalf("downstream value = %#v, want %#v", downstreamValue, candidate) } case StageNormalize: var normalized codecNotes if err := json.Unmarshal(output.NormalizeOutputs[0].Artifact.Content, &normalized); err != nil || !reflect.DeepEqual(normalized, candidate) { t.Fatalf("normalized output = %#v, %v; want %#v", normalized, err, candidate) } } attemptPath := fmt.Sprintf("%s/notes/attempt-01.json", target) if target == StageExtract { attemptPath = "extract/notes/chunk-000001/attempt-01.json" } payload := debug.envelope(t, attemptPath).Payload.(map[string]any) content, err := base64.StdEncoding.DecodeString(payload["output"].(map[string]any)["content"].(map[string]any)["content_base64"].(string)) var debugValue codecNotes if err == nil { err = json.Unmarshal(content, &debugValue) } if err != nil || !reflect.DeepEqual(debugValue, candidate) { t.Fatalf("debug candidate = %#v, %v; want %#v", debugValue, err, candidate) } }) } } func setCandidateValidators(prepared *PreparedPipeline, target ModuleStage, validators []preparedValidator) { switch target { case StageExtract: prepared.Steps[0].lanes[0].extractValidators.validators = validators case StageMerge: prepared.Steps[0].lanes[0].mergeValidators.validators = validators case StageNormalize: prepared.Steps[0].lanes[0].normalizeValidators.validators = validators } } func TestRunnerReportsCandidateDecodeFailure(t *testing.T) { prepared := preparedAttemptDebugPipeline(t) codec := &observedNotesCodec{candidateDecodeError: "decode-failure"} installObservedNotesCodec(t, prepared, codec) configureCandidateOperation(prepared, StageMerge, codecNotes{Items: []string{"decode-failure"}}) setCandidateValidator(prepared, StageMerge, true) _, err := New().Run(context.Background(), RunInput{Prepared: prepared, RawInput: []byte("input")}) var codecErr *ArtifactCodecOperationError if err == nil || !errors.As(err, &codecErr) || codecErr.Operation != "decode candidate" || codec.finalCalls("decode-failure") != 0 { t.Fatalf("Run() error = %v, codec error = %#v, final calls = %d; want contextual candidate decode failure", err, codecErr, codec.finalCalls("decode-failure")) } } func TestRunnerRejectsCandidatesBeforeFinalEncoding(t *testing.T) { for _, target := range []ModuleStage{StageMerge, StageNormalize} { t.Run(string(target), func(t *testing.T) { prepared := preparedAttemptDebugPipeline(t) codec := &observedNotesCodec{} installObservedNotesCodec(t, prepared, codec) configureCandidateOperation(prepared, target, codecNotes{Items: []string{"invalid"}}) setCandidateValidator(prepared, target, false) recorder := &candidateCheckpointRecorder{CheckpointRecorder: NoopCheckpointRecorder()} output, err := New().Run(context.Background(), RunInput{Prepared: prepared, RawInput: []byte("input"), Checkpoints: recorder}) if err != nil { t.Fatalf("Run() error = %v, want validator rejection", err) } if len(output.Rejected) != 1 || output.Rejected[0].Stage != string(target) || output.Rejected[0].ReasonCode != "candidate_rejected" { t.Fatalf("rejected outputs = %#v, want %s validator rejection", output.Rejected, target) } if codec.candidateCalls("invalid") != 1 || codec.finalCalls("invalid") != 0 { t.Fatalf("invalid candidate calls = candidate %d, final %d; want 1, 0", codec.candidateCalls("invalid"), codec.finalCalls("invalid")) } if target == StageMerge && recorder.mergeSucceeded != 0 { t.Fatalf("merge checkpoints = %d, want none", recorder.mergeSucceeded) } if target == StageNormalize && recorder.normalizeSucceeded != 0 { t.Fatalf("normalize checkpoints = %d, want none", recorder.normalizeSucceeded) } }) } } func TestRunnerFinalEncodesAcceptedCandidatesOnce(t *testing.T) { for _, target := range []ModuleStage{StageMerge, StageNormalize} { t.Run(string(target), func(t *testing.T) { prepared := preparedAttemptDebugPipeline(t) codec := &observedNotesCodec{} installObservedNotesCodec(t, prepared, codec) value := "accepted-" + string(target) configureCandidateOperation(prepared, target, codecNotes{Items: []string{value}}) setCandidateValidator(prepared, target, true) recorder := &candidateCheckpointRecorder{CheckpointRecorder: NoopCheckpointRecorder()} loader := &extractResultLoader{CheckpointLoader: NoopCheckpointLoader(), decision: CheckpointDecision{Reason: "not found"}} output, err := New().Run(context.Background(), RunInput{Prepared: prepared, RawInput: []byte("input"), Checkpoints: recorder, Checkpoint: loader}) if err != nil { t.Fatalf("Run() error = %v, want nil", err) } if codec.candidateCalls(value) != 1 || codec.finalCalls(value) != 1 { t.Fatalf("accepted candidate calls = candidate %d, final %d; want 1, 1", codec.candidateCalls(value), codec.finalCalls(value)) } if target == StageMerge && recorder.mergeSucceeded != 1 { t.Fatalf("merge checkpoints = %d, want one", recorder.mergeSucceeded) } if target == StageNormalize && recorder.normalizeSucceeded != 1 { t.Fatalf("normalize checkpoints = %d, want one", recorder.normalizeSucceeded) } checkpoint := recorder.mergeOutput if target == StageNormalize { checkpoint = recorder.normalizeOutput } var stored codecNotes if err := json.Unmarshal(checkpoint.Artifact.Content, &stored); err != nil || !reflect.DeepEqual(stored, codecNotes{Items: []string{value}}) { t.Fatalf("checkpoint content = %s, %v; want accepted value %q", checkpoint.Artifact.Content, err, value) } gotStages := make([]string, len(output.CheckpointEvents)) for i, event := range output.CheckpointEvents { gotStages[i] = event.Stage } wantStages := []string{"source", string(StageExtract), string(StageMerge), string(StageNormalize)} if !reflect.DeepEqual(gotStages, wantStages) { t.Fatalf("checkpoint event stages = %#v, want %#v", gotStages, wantStages) } }) } } func TestRunnerRecordsCandidateAndFinalEncodingFailures(t *testing.T) { tests := []struct { name string target ModuleStage value string candidate bool wantError string }{ {name: "merge candidate", target: StageMerge, value: "merge-candidate-failure", candidate: true, wantError: "serialize merge candidate"}, {name: "normalize candidate", target: StageNormalize, value: "normalize-candidate-failure", candidate: true, wantError: "serialize normalize candidate"}, {name: "merge final", target: StageMerge, value: "merge-final-failure", wantError: "serialize accepted merge output"}, {name: "normalize final", target: StageNormalize, value: "normalize-final-failure", wantError: "serialize accepted normalize output"}, } for _, tc := range tests { t.Run(tc.name, func(t *testing.T) { prepared := preparedAttemptDebugPipeline(t) codec := &observedNotesCodec{} if tc.candidate { codec.candidateError = tc.value } else { codec.finalError = tc.value } installObservedNotesCodec(t, prepared, codec) configureCandidateOperation(prepared, tc.target, codecNotes{Items: []string{tc.value}}) setCandidateValidator(prepared, tc.target, true) recorder := &candidateCheckpointRecorder{CheckpointRecorder: NoopCheckpointRecorder()} debug := newCapturedDebugRecorder() _, err := New().Run(context.Background(), RunInput{Prepared: prepared, RawInput: []byte("input"), Checkpoints: recorder, Debug: debug}) if err == nil || !strings.Contains(err.Error(), tc.wantError) { t.Fatalf("Run() error = %v, want %q", err, tc.wantError) } attemptPath := fmt.Sprintf("%s/notes/attempt-01.json", tc.target) envelope := debug.envelope(t, attemptPath) if !strings.Contains(envelope.Error, tc.wantError) { t.Fatalf("attempt error = %q, want %q", envelope.Error, tc.wantError) } if tc.candidate && codec.finalCalls(tc.value) != 0 { t.Fatalf("final encode calls = %d, want none after candidate failure", codec.finalCalls(tc.value)) } if tc.target == StageMerge && recorder.mergeSucceeded != 0 { t.Fatalf("merge checkpoints = %d, want none", recorder.mergeSucceeded) } if tc.target == StageNormalize && recorder.normalizeSucceeded != 0 { t.Fatalf("normalize checkpoints = %d, want none", recorder.normalizeSucceeded) } }) } }