Clean up pipeline test naming

internal/core/artifacts/artifacts.go

@@ -33,8 +33,18 @@ type RejectedArtifact struct {
 	Message       string            `json:"message"`
 }
 
+type ArtifactLaneManifest struct {
+	ID         string   `json:"id"`
+	Extractor  string   `json:"extractor"`
+	Merger     string   `json:"merger"`
+	Normalizer string   `json:"normalizer"`
+	Validators []string `json:"validators,omitempty"`
+}
+
 type RunManifest struct {
 	RunID            string                 `json:"run_id,omitempty"`
+	PipelineID       string                 `json:"pipeline_id,omitempty"`
+	PipelineDigest   string                 `json:"pipeline_digest,omitempty"`
 	InputModule      string                 `json:"input_module,omitempty"`
 	Chunker          string                 `json:"chunker,omitempty"`
 	SourceDigests    []string               `json:"source_digests,omitempty"`
@@ -42,6 +52,7 @@ type RunManifest struct {
 	Merger           string                 `json:"merger,omitempty"`
 	Normalizer       string                 `json:"normalizer,omitempty"`
 	OutputEncoder    string                 `json:"output_encoder,omitempty"`
+	ArtifactLanes    []ArtifactLaneManifest `json:"artifact_lanes,omitempty"`
 	SchemaVersion    string                 `json:"schema_version,omitempty"`
 	ValidationStatus string                 `json:"validation_status,omitempty"`
 	StartedAt        *time.Time             `json:"started_at,omitempty"`

internal/core/artifacts/artifacts_test.go

@@ -123,6 +123,47 @@ func TestRunManifestOmitsEmptyOptionalFields(t *testing.T) {
 	}
 }
 
+func TestRunManifestIncludesPipelineAndArtifactLaneFields(t *testing.T) {
+	manifest := RunManifest{
+		PipelineID:     "pipeline-1",
+		PipelineDigest: "sha256:abc123",
+		ArtifactLanes: []ArtifactLaneManifest{
+			{
+				ID:         "events",
+				Extractor:  "event-extractor",
+				Merger:     "appendorder",
+				Normalizer: "noop",
+				Validators: []string{"grounded"},
+			},
+		},
+	}
+
+	gotJSON, err := json.Marshal(manifest)
+	if err != nil {
+		t.Fatalf("json.Marshal() error = %v", err)
+	}
+
+	var got map[string]any
+	if err := json.Unmarshal(gotJSON, &got); err != nil {
+		t.Fatalf("json.Unmarshal() error = %v", err)
+	}
+
+	assertHasKeys(t, got, "pipeline_id", "pipeline_digest", "artifact_lanes")
+
+	lanes, ok := got["artifact_lanes"].([]any)
+	if !ok {
+		t.Fatalf("artifact_lanes = %#v, want array", got["artifact_lanes"])
+	}
+	if len(lanes) != 1 {
+		t.Fatalf("len(artifact_lanes) = %d, want 1", len(lanes))
+	}
+	lane, ok := lanes[0].(map[string]any)
+	if !ok {
+		t.Fatalf("artifact_lanes[0] = %#v, want object", lanes[0])
+	}
+	assertHasKeys(t, lane, "id", "extractor", "merger", "normalizer", "validators")
+}
+
 func assertHasKeys(t *testing.T, values map[string]any, keys ...string) {
 	t.Helper()
 

internal/framework/contracts/composition_test.go

@@ -12,14 +12,22 @@ import (
 )
 
 var _ contracts.InputAdapter = compositionAdapter{}
+var _ contracts.Chunker = compositionChunker{}
 var _ contracts.Extractor = compositionExtractor{}
+var _ contracts.Merger = compositionMerger{}
+var _ contracts.Normalizer = compositionNormalizer{}
 var _ contracts.Validator = compositionValidator{}
+var _ contracts.OutputEncoder = compositionOutputEncoder{}
 
 func TestContractsComposeAcrossPackages(t *testing.T) {
 	ctx := context.Background()
 	adapter := compositionAdapter{}
+	chunker := compositionChunker{}
 	extractor := compositionExtractor{}
+	merger := compositionMerger{}
+	normalizer := compositionNormalizer{}
 	validator := compositionValidator{}
+	encoder := compositionOutputEncoder{}
 
 	doc, err := adapter.Parse(ctx, contracts.ParseRequest{SourceID: "source-1"})
 	if err != nil {
@@ -29,7 +37,22 @@ func TestContractsComposeAcrossPackages(t *testing.T) {
 		t.Fatalf("ValidateDocument() error = %v, want nil", err)
 	}
 
-	extraction, err := extractor.Extract(ctx, contracts.ExtractionRequest{Source: doc})
+	chunking, err := chunker.Chunk(ctx, contracts.ChunkRequest{
+		Source:   doc,
+		Metadata: map[string]any{"max_units": 2},
+	})
+	if err != nil {
+		t.Fatalf("Chunk() error = %v, want nil", err)
+	}
+	if len(chunking.Chunks) != 1 {
+		t.Fatalf("len(Chunks) = %d, want 1", len(chunking.Chunks))
+	}
+
+	extraction, err := extractor.Extract(ctx, contracts.ExtractionRequest{
+		Source:         doc,
+		Chunk:          &chunking.Chunks[0],
+		AmbientContext: map[string]any{"synopsis": "example synopsis"},
+	})
 	if err != nil {
 		t.Fatalf("Extract() error = %v, want nil", err)
 	}
@@ -44,9 +67,38 @@ func TestContractsComposeAcrossPackages(t *testing.T) {
 		}
 	}
 
+	merge, err := merger.Merge(ctx, contracts.MergeRequest{
+		Source: doc,
+		LaneID: candidate.ArtifactType,
+		ChunkArtifacts: []contracts.ChunkArtifacts{
+			{
+				Chunk:      chunking.Chunks[0],
+				Candidates: extraction.Candidates,
+			},
+		},
+	})
+	if err != nil {
+		t.Fatalf("Merge() error = %v, want nil", err)
+	}
+	if len(merge.Candidates) != 1 {
+		t.Fatalf("len(merge.Candidates) = %d, want 1", len(merge.Candidates))
+	}
+
+	normalize, err := normalizer.Normalize(ctx, contracts.NormalizeRequest{
+		Source:     doc,
+		LaneID:     candidate.ArtifactType,
+		Candidates: merge.Candidates,
+	})
+	if err != nil {
+		t.Fatalf("Normalize() error = %v, want nil", err)
+	}
+	if len(normalize.Candidates) != 1 {
+		t.Fatalf("len(normalize.Candidates) = %d, want 1", len(normalize.Candidates))
+	}
+
 	validation, err := validator.Validate(ctx, contracts.ValidationRequest{
 		Source:     doc,
-		Candidates: extraction.Candidates,
+		Candidates: normalize.Candidates,
 	})
 	if err != nil {
 		t.Fatalf("Validate() error = %v, want nil", err)
@@ -62,6 +114,22 @@ func TestContractsComposeAcrossPackages(t *testing.T) {
 	if decision.CandidateIndex != candidate.Index {
 		t.Fatalf("CandidateIndex = %d, want %d", decision.CandidateIndex, candidate.Index)
 	}
+
+	output, err := encoder.Encode(ctx, contracts.OutputRequest{
+		Manifest: artifacts.RunManifest{RunID: "run-1"},
+		Approved: []artifacts.Artifact{
+			artifacts.ArtifactFromCandidate(normalize.Candidates[0]),
+		},
+	})
+	if err != nil {
+		t.Fatalf("Encode() error = %v, want nil", err)
+	}
+	if output.ContentType != "application/json" {
+		t.Fatalf("ContentType = %q, want application/json", output.ContentType)
+	}
+	if len(output.Bytes) == 0 {
+		t.Fatal("len(Bytes) = 0, want encoded bytes")
+	}
 }
 
 type compositionAdapter struct{}
@@ -83,6 +151,30 @@ func (adapter compositionAdapter) Parse(ctx context.Context, req contracts.Parse
 	}, nil
 }
 
+type compositionChunker struct{}
+
+func (chunker compositionChunker) Key() string {
+	return "generic-chunker"
+}
+
+func (chunker compositionChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
+	if req.Source == nil {
+		return contracts.ChunkResult{}, errors.New("source document is required")
+	}
+
+	return contracts.ChunkResult{
+		Chunks: []contracts.SourceChunk{
+			{
+				ID:       req.Source.ID + ":chunk:0",
+				SourceID: req.Source.ID,
+				Index:    0,
+				Units:    append([]source.SourceUnit(nil), req.Source.Units...),
+				Metadata: map[string]any{"strategy": "whole-document"},
+			},
+		},
+	}, nil
+}
+
 type compositionExtractor struct{}
 
 func (extractor compositionExtractor) Key() string {
@@ -105,6 +197,13 @@ func (extractor compositionExtractor) Extract(ctx context.Context, req contracts
 	if req.Source == nil {
 		return contracts.ExtractionResult{}, errors.New("source document is required")
 	}
+	units := req.Source.Units
+	if req.Chunk != nil {
+		units = req.Chunk.Units
+	}
+	if req.AmbientContext["synopsis"] == "" {
+		return contracts.ExtractionResult{}, errors.New("ambient synopsis is required")
+	}
 
 	return contracts.ExtractionResult{
 		Candidates: []artifacts.ArtifactCandidate{
@@ -117,8 +216,8 @@ func (extractor compositionExtractor) Extract(ctx context.Context, req contracts
 				SourceRefs: []source.SourceRef{
 					{
 						SourceID:    req.Source.ID,
-						StartUnitID: req.Source.Units[0].ID,
+						StartUnitID: units[0].ID,
-						EndUnitID:   req.Source.Units[1].ID,
+						EndUnitID:   units[len(units)-1].ID,
 					},
 				},
 			},
@@ -126,6 +225,31 @@ func (extractor compositionExtractor) Extract(ctx context.Context, req contracts
 	}, nil
 }
 
+type compositionMerger struct{}
+
+func (merger compositionMerger) Key() string {
+	return "generic-merger"
+}
+
+func (merger compositionMerger) Merge(ctx context.Context, req contracts.MergeRequest) (contracts.MergeResult, error) {
+	var candidates []artifacts.ArtifactCandidate
+	for _, chunkArtifacts := range req.ChunkArtifacts {
+		candidates = append(candidates, chunkArtifacts.Candidates...)
+	}
+
+	return contracts.MergeResult{Candidates: candidates}, nil
+}
+
+type compositionNormalizer struct{}
+
+func (normalizer compositionNormalizer) Key() string {
+	return "generic-normalizer"
+}
+
+func (normalizer compositionNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
+	return contracts.NormalizeResult{Candidates: req.Candidates}, nil
+}
+
 type compositionValidator struct{}
 
 func (validator compositionValidator) Name() string {
@@ -148,3 +272,28 @@ func (validator compositionValidator) Validate(ctx context.Context, req contract
 		Decisions:     decisions,
 	}, nil
 }
+
+type compositionOutputEncoder struct{}
+
+func (encoder compositionOutputEncoder) Key() string {
+	return "generic-output"
+}
+
+func (encoder compositionOutputEncoder) Encode(ctx context.Context, req contracts.OutputRequest) (contracts.OutputResult, error) {
+	payload := struct {
+		RunID         string `json:"run_id"`
+		ApprovedCount int    `json:"approved_count"`
+	}{
+		RunID:         req.Manifest.RunID,
+		ApprovedCount: len(req.Approved),
+	}
+	encoded, err := json.Marshal(payload)
+	if err != nil {
+		return contracts.OutputResult{}, err
+	}
+
+	return contracts.OutputResult{
+		Bytes:       encoded,
+		ContentType: "application/json",
+	}, nil
+}

internal/framework/contracts/contracts.go

@@ -46,8 +46,33 @@ type InputAdapter interface {
 	Parse(ctx context.Context, req ParseRequest) (*source.SourceDocument, error)
 }
 
+type SourceChunk struct {
+	ID       string              `json:"id"`
+	SourceID string              `json:"source_id"`
+	Index    int                 `json:"index"`
+	Units    []source.SourceUnit `json:"units"`
+	Metadata map[string]any      `json:"metadata,omitempty"`
+}
+
+type ChunkRequest struct {
+	Source   *source.SourceDocument `json:"-"`
+	Metadata map[string]any         `json:"metadata,omitempty"`
+}
+
+type ChunkResult struct {
+	Chunks   []SourceChunk `json:"chunks"`
+	Warnings []Warning     `json:"warnings,omitempty"`
+}
+
+type Chunker interface {
+	Key() string
+	Chunk(ctx context.Context, req ChunkRequest) (ChunkResult, error)
+}
+
 type ExtractionRequest struct {
 	Source         *source.SourceDocument `json:"-"`
+	Chunk          *SourceChunk           `json:"chunk,omitempty"`
+	AmbientContext map[string]any         `json:"ambient_context,omitempty"`
 	LLMClient      StructuredLLMClient    `json:"-"`
 	Metadata       map[string]any         `json:"metadata,omitempty"`
 }
@@ -65,6 +90,45 @@ type Extractor interface {
 	Extract(ctx context.Context, req ExtractionRequest) (ExtractionResult, error)
 }
 
+type ChunkArtifacts struct {
+	Chunk      SourceChunk                   `json:"chunk"`
+	Candidates []artifacts.ArtifactCandidate `json:"candidates"`
+}
+
+type MergeRequest struct {
+	Source         *source.SourceDocument `json:"-"`
+	LaneID         string                 `json:"lane_id"`
+	ChunkArtifacts []ChunkArtifacts       `json:"chunk_artifacts"`
+	Metadata       map[string]any         `json:"metadata,omitempty"`
+}
+
+type MergeResult struct {
+	Candidates []artifacts.ArtifactCandidate `json:"candidates"`
+	Warnings   []Warning                     `json:"warnings,omitempty"`
+}
+
+type Merger interface {
+	Key() string
+	Merge(ctx context.Context, req MergeRequest) (MergeResult, error)
+}
+
+type NormalizeRequest struct {
+	Source     *source.SourceDocument        `json:"-"`
+	LaneID     string                        `json:"lane_id"`
+	Candidates []artifacts.ArtifactCandidate `json:"candidates"`
+	Metadata   map[string]any                `json:"metadata,omitempty"`
+}
+
+type NormalizeResult struct {
+	Candidates []artifacts.ArtifactCandidate `json:"candidates"`
+	Warnings   []Warning                     `json:"warnings,omitempty"`
+}
+
+type Normalizer interface {
+	Key() string
+	Normalize(ctx context.Context, req NormalizeRequest) (NormalizeResult, error)
+}
+
 type ValidationRequest struct {
 	Source     *source.SourceDocument        `json:"-"`
 	Candidates []artifacts.ArtifactCandidate `json:"candidates"`
@@ -95,3 +159,22 @@ type Warning struct {
 	ReasonCode string `json:"reason_code"`
 	Message    string `json:"message"`
 }
+
+type OutputRequest struct {
+	Manifest artifacts.RunManifest        `json:"manifest"`
+	Approved []artifacts.Artifact         `json:"approved,omitempty"`
+	Rejected []artifacts.RejectedArtifact `json:"rejected,omitempty"`
+	Warnings []Warning                    `json:"warnings,omitempty"`
+	Metadata map[string]any               `json:"metadata,omitempty"`
+}
+
+type OutputResult struct {
+	Bytes       []byte    `json:"-"`
+	ContentType string    `json:"content_type,omitempty"`
+	Warnings    []Warning `json:"warnings,omitempty"`
+}
+
+type OutputEncoder interface {
+	Key() string
+	Encode(ctx context.Context, req OutputRequest) (OutputResult, error)
+}

internal/framework/contracts/contracts_test.go

@@ -10,9 +10,13 @@ import (
 )
 
 var _ InputAdapter = fakeAdapter{}
+var _ Chunker = fakeChunker{}
 var _ Extractor = fakeExtractor{}
+var _ Merger = fakeMerger{}
+var _ Normalizer = fakeNormalizer{}
 var _ Validator = fakeValidator{}
 var _ StructuredLLMClient = fakeLLMClient{}
+var _ OutputEncoder = fakeOutputEncoder{}
 
 func TestFakeExtractorReturnsCandidateAndValidator(t *testing.T) {
 	validator := fakeValidator{name: "generic-validator"}
@@ -74,6 +78,166 @@ func TestFakeExtractorReturnsCandidateAndValidator(t *testing.T) {
 	}
 }
 
+func TestFakeChunkerReturnsSourceChunks(t *testing.T) {
+	doc := &source.SourceDocument{
+		ID:     "source-1",
+		Kind:   "document",
+		Format: "text/plain",
+		Digest: "sha256:abc123",
+		Units: []source.SourceUnit{
+			{ID: "u1", Kind: "section", Text: "Source text."},
+		},
+	}
+	chunker := fakeChunker{key: "generic-chunker"}
+
+	result, err := chunker.Chunk(context.Background(), ChunkRequest{Source: doc})
+	if err != nil {
+		t.Fatalf("Chunk() error = %v, want nil", err)
+	}
+
+	if chunker.Key() != "generic-chunker" {
+		t.Fatalf("Key() = %q, want generic-chunker", chunker.Key())
+	}
+	if len(result.Chunks) != 1 {
+		t.Fatalf("len(Chunks) = %d, want 1", len(result.Chunks))
+	}
+
+	chunk := result.Chunks[0]
+	if chunk.ID != "source-1:chunk:0" {
+		t.Fatalf("SourceChunk.ID = %q, want source-1:chunk:0", chunk.ID)
+	}
+	if chunk.SourceID != doc.ID {
+		t.Fatalf("SourceChunk.SourceID = %q, want %q", chunk.SourceID, doc.ID)
+	}
+	if chunk.Index != 0 {
+		t.Fatalf("SourceChunk.Index = %d, want 0", chunk.Index)
+	}
+	if len(chunk.Units) != 1 {
+		t.Fatalf("len(SourceChunk.Units) = %d, want 1", len(chunk.Units))
+	}
+}
+
+func TestFakeExtractorReceivesChunkAndAmbientContext(t *testing.T) {
+	extractor := fakeExtractor{
+		key:           "generic-extractor",
+		artifactType:  "generic-artifact",
+		schemaVersion: "v1",
+	}
+	doc := &source.SourceDocument{
+		ID:     "source-1",
+		Kind:   "document",
+		Format: "text/plain",
+		Digest: "sha256:abc123",
+		Units: []source.SourceUnit{
+			{ID: "u1", Kind: "section", Text: "First source text."},
+			{ID: "u2", Kind: "section", Text: "Second source text."},
+		},
+	}
+	chunk := SourceChunk{
+		ID:       "source-1:chunk:1",
+		SourceID: doc.ID,
+		Index:    1,
+		Units:    []source.SourceUnit{doc.Units[1]},
+	}
+
+	result, err := extractor.Extract(context.Background(), ExtractionRequest{
+		Source:         doc,
+		Chunk:          &chunk,
+		AmbientContext: map[string]any{"mode": "chunked"},
+	})
+	if err != nil {
+		t.Fatalf("Extract() error = %v, want nil", err)
+	}
+	if len(result.Candidates) != 1 {
+		t.Fatalf("len(Candidates) = %d, want 1", len(result.Candidates))
+	}
+
+	candidate := result.Candidates[0]
+	if string(candidate.Payload) != `{"value":"chunked"}` {
+		t.Fatalf("ArtifactCandidate.Payload = %s, want chunked payload", candidate.Payload)
+	}
+	if len(candidate.SourceRefs) != 1 {
+		t.Fatalf("len(SourceRefs) = %d, want 1", len(candidate.SourceRefs))
+	}
+	ref := candidate.SourceRefs[0]
+	if ref.StartUnitID != "u2" || ref.EndUnitID != "u2" {
+		t.Fatalf("SourceRef = %+v, want u2 range", ref)
+	}
+}
+
+func TestFakeMergeNormalizeAndOutputContracts(t *testing.T) {
+	candidate := artifacts.ArtifactCandidate{
+		Index:         0,
+		ExtractorKey:  "generic-extractor",
+		ArtifactType:  "generic-artifact",
+		SchemaVersion: "v1",
+		Payload:       json.RawMessage(`{"value":"example"}`),
+	}
+	chunk := SourceChunk{
+		ID:       "source-1:chunk:0",
+		SourceID: "source-1",
+		Index:    0,
+		Units: []source.SourceUnit{
+			{ID: "u1", Kind: "section", Text: "Source text."},
+		},
+	}
+	merger := fakeMerger{key: "generic-merger"}
+	normalizer := fakeNormalizer{key: "generic-normalizer"}
+	encoder := fakeOutputEncoder{key: "generic-output"}
+
+	merged, err := merger.Merge(context.Background(), MergeRequest{
+		LaneID: "generic-artifact",
+		ChunkArtifacts: []ChunkArtifacts{
+			{
+				Chunk:      chunk,
+				Candidates: []artifacts.ArtifactCandidate{candidate},
+			},
+		},
+	})
+	if err != nil {
+		t.Fatalf("Merge() error = %v, want nil", err)
+	}
+	if merger.Key() != "generic-merger" {
+		t.Fatalf("Merger.Key() = %q, want generic-merger", merger.Key())
+	}
+	if len(merged.Candidates) != 1 {
+		t.Fatalf("len(merged.Candidates) = %d, want 1", len(merged.Candidates))
+	}
+
+	normalized, err := normalizer.Normalize(context.Background(), NormalizeRequest{
+		LaneID:     "generic-artifact",
+		Candidates: merged.Candidates,
+	})
+	if err != nil {
+		t.Fatalf("Normalize() error = %v, want nil", err)
+	}
+	if normalizer.Key() != "generic-normalizer" {
+		t.Fatalf("Normalizer.Key() = %q, want generic-normalizer", normalizer.Key())
+	}
+	if len(normalized.Candidates) != 1 {
+		t.Fatalf("len(normalized.Candidates) = %d, want 1", len(normalized.Candidates))
+	}
+
+	encoded, err := encoder.Encode(context.Background(), OutputRequest{
+		Manifest: artifacts.RunManifest{RunID: "run-1"},
+		Approved: []artifacts.Artifact{
+			artifacts.ArtifactFromCandidate(normalized.Candidates[0]),
+		},
+	})
+	if err != nil {
+		t.Fatalf("Encode() error = %v, want nil", err)
+	}
+	if encoder.Key() != "generic-output" {
+		t.Fatalf("OutputEncoder.Key() = %q, want generic-output", encoder.Key())
+	}
+	if encoded.ContentType != "application/json" {
+		t.Fatalf("ContentType = %q, want application/json", encoded.ContentType)
+	}
+	if string(encoded.Bytes) != `{"run_id":"run-1","approved_count":1}` {
+		t.Fatalf("Bytes = %s, want encoded output", encoded.Bytes)
+	}
+}
+
 type fakeAdapter struct {
 	key string
 	doc *source.SourceDocument
@@ -87,6 +251,27 @@ func (adapter fakeAdapter) Parse(ctx context.Context, req ParseRequest) (*source
 	return adapter.doc, nil
 }
 
+type fakeChunker struct {
+	key string
+}
+
+func (chunker fakeChunker) Key() string {
+	return chunker.key
+}
+
+func (chunker fakeChunker) Chunk(ctx context.Context, req ChunkRequest) (ChunkResult, error) {
+	return ChunkResult{
+		Chunks: []SourceChunk{
+			{
+				ID:       req.Source.ID + ":chunk:0",
+				SourceID: req.Source.ID,
+				Index:    0,
+				Units:    append([]source.SourceUnit(nil), req.Source.Units...),
+			},
+		},
+	}, nil
+}
+
 type fakeExtractor struct {
 	key           string
 	artifactType  string
@@ -111,6 +296,15 @@ func (extractor fakeExtractor) Validators() []Validator {
 }
 
 func (extractor fakeExtractor) Extract(ctx context.Context, req ExtractionRequest) (ExtractionResult, error) {
+	units := req.Source.Units
+	if req.Chunk != nil {
+		units = req.Chunk.Units
+	}
+	payload := json.RawMessage(`{"value":"example"}`)
+	if req.AmbientContext["mode"] == "chunked" {
+		payload = json.RawMessage(`{"value":"chunked"}`)
+	}
+
 	return ExtractionResult{
 		Candidates: []artifacts.ArtifactCandidate{
 			{
@@ -118,12 +312,12 @@ func (extractor fakeExtractor) Extract(ctx context.Context, req ExtractionReques
 				ExtractorKey:  extractor.key,
 				ArtifactType:  extractor.artifactType,
 				SchemaVersion: extractor.schemaVersion,
-				Payload:       json.RawMessage(`{"value":"example"}`),
+				Payload:       payload,
 				SourceRefs: []source.SourceRef{
 					{
 						SourceID:    req.Source.ID,
-						StartUnitID: req.Source.Units[0].ID,
+						StartUnitID: units[0].ID,
-						EndUnitID:   req.Source.Units[0].ID,
+						EndUnitID:   units[len(units)-1].ID,
 					},
 				},
 			},
@@ -131,6 +325,35 @@ func (extractor fakeExtractor) Extract(ctx context.Context, req ExtractionReques
 	}, nil
 }
 
+type fakeMerger struct {
+	key string
+}
+
+func (merger fakeMerger) Key() string {
+	return merger.key
+}
+
+func (merger fakeMerger) Merge(ctx context.Context, req MergeRequest) (MergeResult, error) {
+	var candidates []artifacts.ArtifactCandidate
+	for _, chunkArtifacts := range req.ChunkArtifacts {
+		candidates = append(candidates, chunkArtifacts.Candidates...)
+	}
+
+	return MergeResult{Candidates: candidates}, nil
+}
+
+type fakeNormalizer struct {
+	key string
+}
+
+func (normalizer fakeNormalizer) Key() string {
+	return normalizer.key
+}
+
+func (normalizer fakeNormalizer) Normalize(ctx context.Context, req NormalizeRequest) (NormalizeResult, error) {
+	return NormalizeResult{Candidates: req.Candidates}, nil
+}
+
 type fakeValidator struct {
 	name string
 }
@@ -163,3 +386,18 @@ func (client fakeLLMClient) CompleteStructured(ctx context.Context, req Structur
 		Content: json.RawMessage(`{"value":"example"}`),
 	}, nil
 }
+
+type fakeOutputEncoder struct {
+	key string
+}
+
+func (encoder fakeOutputEncoder) Key() string {
+	return encoder.key
+}
+
+func (encoder fakeOutputEncoder) Encode(ctx context.Context, req OutputRequest) (OutputResult, error) {
+	return OutputResult{
+		Bytes:       []byte(`{"run_id":"` + req.Manifest.RunID + `","approved_count":1}`),
+		ContentType: "application/json",
+	}, nil
+}

internal/framework/pipeline/chunker_registry.go

@@ -0,0 +1,102 @@
+package pipeline
+
+import (
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+type ChunkerConstructor func() (contracts.Chunker, error)
+
+type ChunkerRegistry struct {
+	constructors map[string]ChunkerConstructor
+	specs        map[string]ModuleSpec
+}
+
+func NewChunkerRegistry() *ChunkerRegistry {
+	return &ChunkerRegistry{
+		constructors: make(map[string]ChunkerConstructor),
+		specs:        make(map[string]ModuleSpec),
+	}
+}
+
+func (r *ChunkerRegistry) Register(key string, constructor ChunkerConstructor) error {
+	return r.RegisterWithSpec(defaultModuleSpec(key, StageChunk), constructor)
+}
+
+func (r *ChunkerRegistry) RegisterWithSpec(spec ModuleSpec, constructor ChunkerConstructor) error {
+	if r == nil {
+		return fmt.Errorf("chunker registry must not be nil")
+	}
+
+	normalizedSpec := normalizeModuleSpec(spec)
+	if err := validateModuleSpec("chunker", StageChunk, normalizedSpec); err != nil {
+		return err
+	}
+	if constructor == nil {
+		return fmt.Errorf("chunker constructor for %q must not be nil", normalizedSpec.Key)
+	}
+	if _, ok := r.constructors[normalizedSpec.Key]; ok {
+		return fmt.Errorf("chunker %q is already registered", normalizedSpec.Key)
+	}
+
+	if r.constructors == nil {
+		r.constructors = make(map[string]ChunkerConstructor)
+	}
+	if r.specs == nil {
+		r.specs = make(map[string]ModuleSpec)
+	}
+	r.constructors[normalizedSpec.Key] = constructor
+	r.specs[normalizedSpec.Key] = cloneModuleSpec(normalizedSpec)
+	return nil
+}
+
+func (r *ChunkerRegistry) Build(key string) (contracts.Chunker, error) {
+	if r == nil {
+		return nil, fmt.Errorf("chunker registry must not be nil")
+	}
+
+	normalizedKey := strings.TrimSpace(key)
+	if normalizedKey == "" {
+		return nil, fmt.Errorf("chunker key must not be empty")
+	}
+
+	constructor, ok := r.constructors[normalizedKey]
+	if !ok {
+		return nil, fmt.Errorf("chunker %q is not registered", normalizedKey)
+	}
+
+	chunker, err := constructor()
+	if err != nil {
+		return nil, fmt.Errorf("build chunker %q: %w", normalizedKey, err)
+	}
+	if chunker == nil {
+		return nil, fmt.Errorf("chunker %q constructor returned nil", normalizedKey)
+	}
+	if chunker.Key() != normalizedKey {
+		return nil, fmt.Errorf("chunker %q returned key %q", normalizedKey, chunker.Key())
+	}
+
+	return chunker, nil
+}
+
+func (r *ChunkerRegistry) Spec(key string) (ModuleSpec, bool) {
+	if r == nil {
+		return ModuleSpec{}, false
+	}
+
+	spec, ok := r.specs[strings.TrimSpace(key)]
+	if !ok {
+		return ModuleSpec{}, false
+	}
+	return cloneModuleSpec(spec), true
+}
+
+func (r *ChunkerRegistry) RegisteredKeys() []string {
+	if r == nil {
+		return nil
+	}
+
+	return sortedRegistryKeys(r.constructors)
+}

internal/framework/pipeline/chunker_registry_test.go

@@ -0,0 +1,383 @@
+package pipeline
+
+import (
+	"context"
+	"errors"
+	"reflect"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+type registryBehaviorCase[M any] struct {
+	name             string
+	key              string
+	stage            ModuleStage
+	wrongStage       ModuleStage
+	newRegistry      func() any
+	register         func(any, string, func() (M, error)) error
+	registerWithSpec func(any, ModuleSpec, func() (M, error)) error
+	build            func(any, string) (M, error)
+	spec             func(any, string) (ModuleSpec, bool)
+	registeredKeys   func(any) []string
+	nilRegister      func(string, func() (M, error)) error
+	nilBuild         func(string) (M, error)
+	nilSpec          func(string) (ModuleSpec, bool)
+	nilRegisteredKey func() []string
+	constructor      func(string) func() (M, error)
+	moduleKey        func(M) string
+}
+
+func TestChunkerRegistryBehavior(t *testing.T) {
+	runRegistryBehaviorTests(t, registryBehaviorCase[contracts.Chunker]{
+		name:       "ChunkerRegistry",
+		key:        "generic-chunker",
+		stage:      StageChunk,
+		wrongStage: StageExtract,
+		newRegistry: func() any {
+			return NewChunkerRegistry()
+		},
+		register: func(registry any, key string, constructor func() (contracts.Chunker, error)) error {
+			return registry.(*ChunkerRegistry).Register(key, constructor)
+		},
+		registerWithSpec: func(registry any, spec ModuleSpec, constructor func() (contracts.Chunker, error)) error {
+			return registry.(*ChunkerRegistry).RegisterWithSpec(spec, constructor)
+		},
+		build: func(registry any, key string) (contracts.Chunker, error) {
+			return registry.(*ChunkerRegistry).Build(key)
+		},
+		spec: func(registry any, key string) (ModuleSpec, bool) {
+			return registry.(*ChunkerRegistry).Spec(key)
+		},
+		registeredKeys: func(registry any) []string {
+			return registry.(*ChunkerRegistry).RegisteredKeys()
+		},
+		nilRegister: func(key string, constructor func() (contracts.Chunker, error)) error {
+			var registry *ChunkerRegistry
+			return registry.Register(key, constructor)
+		},
+		nilBuild: func(key string) (contracts.Chunker, error) {
+			var registry *ChunkerRegistry
+			return registry.Build(key)
+		},
+		nilSpec: func(key string) (ModuleSpec, bool) {
+			var registry *ChunkerRegistry
+			return registry.Spec(key)
+		},
+		nilRegisteredKey: func() []string {
+			var registry *ChunkerRegistry
+			return registry.RegisteredKeys()
+		},
+		constructor: func(key string) func() (contracts.Chunker, error) {
+			return func() (contracts.Chunker, error) {
+				return registryChunker{key: key}, nil
+			}
+		},
+		moduleKey: func(module contracts.Chunker) string {
+			return module.Key()
+		},
+	})
+}
+
+func runRegistryBehaviorTests[M any](t *testing.T, testCase registryBehaviorCase[M]) {
+	t.Helper()
+
+	t.Run(testCase.name+"/register and build", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		if err := testCase.register(registry, testCase.key, testCase.constructor(testCase.key)); err != nil {
+			t.Fatalf("Register() error = %v, want nil", err)
+		}
+
+		module, err := testCase.build(registry, testCase.key)
+		if err != nil {
+			t.Fatalf("Build() error = %v, want nil", err)
+		}
+		if got := testCase.moduleKey(module); got != testCase.key {
+			t.Fatalf("module key = %q, want %q", got, testCase.key)
+		}
+	})
+
+	t.Run(testCase.name+"/metadata registration and lookup", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		spec := ModuleSpec{
+			Key:      " " + testCase.key + " ",
+			Stage:    testCase.stage,
+			Provides: []string{" beta ", "alpha", "", "beta"},
+			Requires: []string{" source ", "source", ""},
+		}
+		if err := testCase.registerWithSpec(registry, spec, testCase.constructor(testCase.key)); err != nil {
+			t.Fatalf("RegisterWithSpec() error = %v, want nil", err)
+		}
+
+		got, ok := testCase.spec(registry, " "+testCase.key+"\n")
+		if !ok {
+			t.Fatal("Spec() ok = false, want true")
+		}
+		want := ModuleSpec{
+			Key:      testCase.key,
+			Stage:    testCase.stage,
+			Provides: []string{"alpha", "beta"},
+			Requires: []string{"source"},
+		}
+		if !reflect.DeepEqual(got, want) {
+			t.Fatalf("Spec() = %#v, want %#v", got, want)
+		}
+
+		got.Provides[0] = "changed"
+		again, ok := testCase.spec(registry, testCase.key)
+		if !ok {
+			t.Fatal("Spec() after caller mutation ok = false, want true")
+		}
+		if !reflect.DeepEqual(again, want) {
+			t.Fatalf("Spec() after caller mutation = %#v, want %#v", again, want)
+		}
+	})
+
+	t.Run(testCase.name+"/default spec from register", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		if err := testCase.register(registry, " "+testCase.key+" ", testCase.constructor(testCase.key)); err != nil {
+			t.Fatalf("Register() error = %v, want nil", err)
+		}
+
+		spec, ok := testCase.spec(registry, testCase.key)
+		if !ok {
+			t.Fatal("Spec() ok = false, want true")
+		}
+		want := ModuleSpec{Key: testCase.key, Stage: testCase.stage}
+		if !reflect.DeepEqual(spec, want) {
+			t.Fatalf("Spec() = %#v, want %#v", spec, want)
+		}
+	})
+
+	t.Run(testCase.name+"/wrong stage rejection", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		err := testCase.registerWithSpec(registry, ModuleSpec{Key: testCase.key, Stage: testCase.wrongStage}, testCase.constructor(testCase.key))
+		if err == nil {
+			t.Fatal("RegisterWithSpec() error = nil, want error")
+		}
+		if !strings.Contains(err.Error(), "stage") {
+			t.Fatalf("RegisterWithSpec() error = %q, want stage error", err.Error())
+		}
+	})
+
+	t.Run(testCase.name+"/key trimming", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		if err := testCase.register(registry, " "+testCase.key+" ", testCase.constructor(testCase.key)); err != nil {
+			t.Fatalf("Register() error = %v, want nil", err)
+		}
+
+		module, err := testCase.build(registry, "\t"+testCase.key+"\n")
+		if err != nil {
+			t.Fatalf("Build() error = %v, want nil", err)
+		}
+		if got := testCase.moduleKey(module); got != testCase.key {
+			t.Fatalf("module key = %q, want %q", got, testCase.key)
+		}
+	})
+
+	t.Run(testCase.name+"/empty key rejection", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		err := testCase.register(registry, " \t", testCase.constructor(testCase.key))
+		if err == nil {
+			t.Fatal("Register() error = nil, want error")
+		}
+		if !strings.Contains(err.Error(), "key must not be empty") {
+			t.Fatalf("Register() error = %q, want empty key error", err.Error())
+		}
+	})
+
+	t.Run(testCase.name+"/duplicate key rejection", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		if err := testCase.register(registry, testCase.key, testCase.constructor(testCase.key)); err != nil {
+			t.Fatalf("Register() error = %v, want nil", err)
+		}
+
+		err := testCase.register(registry, " "+testCase.key+" ", testCase.constructor(testCase.key))
+		if err == nil {
+			t.Fatal("Register() error = nil, want error")
+		}
+		if !strings.Contains(err.Error(), "already registered") {
+			t.Fatalf("Register() error = %q, want duplicate key error", err.Error())
+		}
+	})
+
+	t.Run(testCase.name+"/nil constructor rejection", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		err := testCase.register(registry, testCase.key, nil)
+		if err == nil {
+			t.Fatal("Register() error = nil, want error")
+		}
+		if !strings.Contains(err.Error(), "constructor") {
+			t.Fatalf("Register() error = %q, want constructor error", err.Error())
+		}
+	})
+
+	t.Run(testCase.name+"/unknown key build error", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		_, err := testCase.build(registry, "missing")
+		if err == nil {
+			t.Fatal("Build() error = nil, want error")
+		}
+		if !strings.Contains(err.Error(), "not registered") {
+			t.Fatalf("Build() error = %q, want unknown key error", err.Error())
+		}
+	})
+
+	t.Run(testCase.name+"/constructor error wrapping", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		constructorErr := errors.New("constructor failed")
+		if err := testCase.register(registry, testCase.key, func() (M, error) {
+			var zero M
+			return zero, constructorErr
+		}); err != nil {
+			t.Fatalf("Register() error = %v, want nil", err)
+		}
+
+		_, err := testCase.build(registry, testCase.key)
+		if err == nil {
+			t.Fatal("Build() error = nil, want error")
+		}
+		if !errors.Is(err, constructorErr) {
+			t.Fatalf("Build() error = %v, want wrapped constructor error", err)
+		}
+		if !strings.Contains(err.Error(), testCase.key) {
+			t.Fatalf("Build() error = %q, want key context", err.Error())
+		}
+	})
+
+	t.Run(testCase.name+"/nil module rejection", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		if err := testCase.register(registry, testCase.key, func() (M, error) {
+			var zero M
+			return zero, nil
+		}); err != nil {
+			t.Fatalf("Register() error = %v, want nil", err)
+		}
+
+		_, err := testCase.build(registry, testCase.key)
+		if err == nil {
+			t.Fatal("Build() error = nil, want error")
+		}
+		if !strings.Contains(err.Error(), "returned nil") {
+			t.Fatalf("Build() error = %q, want nil module error", err.Error())
+		}
+	})
+
+	t.Run(testCase.name+"/key mismatch rejection", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		if err := testCase.register(registry, testCase.key, testCase.constructor("other")); err != nil {
+			t.Fatalf("Register() error = %v, want nil", err)
+		}
+
+		_, err := testCase.build(registry, testCase.key)
+		if err == nil {
+			t.Fatal("Build() error = nil, want error")
+		}
+		if !strings.Contains(err.Error(), "returned") {
+			t.Fatalf("Build() error = %q, want mismatch error", err.Error())
+		}
+	})
+
+	t.Run(testCase.name+"/sorted registered keys", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		for _, key := range []string{"zeta", "alpha", "middle"} {
+			if err := testCase.register(registry, key, testCase.constructor(key)); err != nil {
+				t.Fatalf("Register(%q) error = %v, want nil", key, err)
+			}
+		}
+
+		keys := testCase.registeredKeys(registry)
+		want := []string{"alpha", "middle", "zeta"}
+		if !reflect.DeepEqual(keys, want) {
+			t.Fatalf("RegisteredKeys() = %#v, want %#v", keys, want)
+		}
+
+		keys[0] = "changed"
+		if got := testCase.registeredKeys(registry); !reflect.DeepEqual(got, want) {
+			t.Fatalf("RegisteredKeys() after caller mutation = %#v, want %#v", got, want)
+		}
+	})
+
+	t.Run(testCase.name+"/nil registry behavior", func(t *testing.T) {
+		if err := testCase.nilRegister(testCase.key, testCase.constructor(testCase.key)); err == nil {
+			t.Fatal("Register() error = nil, want error")
+		}
+		if _, err := testCase.nilBuild(testCase.key); err == nil {
+			t.Fatal("Build() error = nil, want error")
+		}
+		if _, ok := testCase.nilSpec(testCase.key); ok {
+			t.Fatal("Spec() ok = true, want false")
+		}
+		if keys := testCase.nilRegisteredKey(); keys != nil {
+			t.Fatalf("RegisteredKeys() = %#v, want nil", keys)
+		}
+	})
+
+	t.Run(testCase.name+"/unknown spec lookup", func(t *testing.T) {
+		registry := testCase.newRegistry()
+		if _, ok := testCase.spec(registry, "missing"); ok {
+			t.Fatal("Spec() ok = true, want false")
+		}
+	})
+}
+
+type registryChunker struct {
+	key string
+}
+
+func (chunker registryChunker) Key() string {
+	return chunker.key
+}
+
+func (chunker registryChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
+	return contracts.ChunkResult{}, nil
+}
+
+type registryMerger struct {
+	key string
+}
+
+func (merger registryMerger) Key() string {
+	return merger.key
+}
+
+func (merger registryMerger) Merge(ctx context.Context, req contracts.MergeRequest) (contracts.MergeResult, error) {
+	return contracts.MergeResult{}, nil
+}
+
+type registryNormalizer struct {
+	key string
+}
+
+func (normalizer registryNormalizer) Key() string {
+	return normalizer.key
+}
+
+func (normalizer registryNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
+	return contracts.NormalizeResult{}, nil
+}
+
+type registryOutputEncoder struct {
+	key string
+}
+
+func (encoder registryOutputEncoder) Key() string {
+	return encoder.key
+}
+
+func (encoder registryOutputEncoder) Encode(ctx context.Context, req contracts.OutputRequest) (contracts.OutputResult, error) {
+	return contracts.OutputResult{}, nil
+}
+
+type registryValidator struct {
+	name string
+}
+
+func (validator registryValidator) Name() string {
+	return validator.name
+}
+
+func (validator registryValidator) Validate(ctx context.Context, req contracts.ValidationRequest) (contracts.ValidationResult, error) {
+	return contracts.ValidationResult{}, nil
+}

internal/framework/pipeline/extractor_registry.go

@@ -2,7 +2,6 @@ package pipeline
 
 import (
 	"fmt"
-	"sort"
 	"strings"
 
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
@@ -12,31 +11,44 @@ type ExtractorConstructor func() (contracts.Extractor, error)
 
 type ExtractorRegistry struct {
 	constructors map[string]ExtractorConstructor
+	specs        map[string]ModuleSpec
 }
 
 func NewExtractorRegistry() *ExtractorRegistry {
 	return &ExtractorRegistry{
 		constructors: make(map[string]ExtractorConstructor),
+		specs:        make(map[string]ModuleSpec),
 	}
 }
 
 func (r *ExtractorRegistry) Register(key string, constructor ExtractorConstructor) error {
+	return r.RegisterWithSpec(defaultModuleSpec(key, StageExtract), constructor)
+}
+
+func (r *ExtractorRegistry) RegisterWithSpec(spec ModuleSpec, constructor ExtractorConstructor) error {
 	if r == nil {
 		return fmt.Errorf("extractor registry must not be nil")
 	}
 
-	normalizedKey := strings.TrimSpace(key)
+	normalizedSpec := normalizeModuleSpec(spec)
-	if normalizedKey == "" {
+	if err := validateModuleSpec("extractor", StageExtract, normalizedSpec); err != nil {
-		return fmt.Errorf("extractor key must not be empty")
+		return err
 	}
 	if constructor == nil {
-		return fmt.Errorf("extractor constructor for %q must not be nil", normalizedKey)
+		return fmt.Errorf("extractor constructor for %q must not be nil", normalizedSpec.Key)
 	}
-	if _, ok := r.constructors[normalizedKey]; ok {
+	if _, ok := r.constructors[normalizedSpec.Key]; ok {
-		return fmt.Errorf("extractor %q is already registered", normalizedKey)
+		return fmt.Errorf("extractor %q is already registered", normalizedSpec.Key)
 	}
 
-	r.constructors[normalizedKey] = constructor
+	if r.constructors == nil {
+		r.constructors = make(map[string]ExtractorConstructor)
+	}
+	if r.specs == nil {
+		r.specs = make(map[string]ModuleSpec)
+	}
+	r.constructors[normalizedSpec.Key] = constructor
+	r.specs[normalizedSpec.Key] = cloneModuleSpec(normalizedSpec)
 	return nil
 }
 
@@ -69,15 +81,22 @@ func (r *ExtractorRegistry) Build(key string) (contracts.Extractor, error) {
 	return extractor, nil
 }
 
+func (r *ExtractorRegistry) Spec(key string) (ModuleSpec, bool) {
+	if r == nil {
+		return ModuleSpec{}, false
+	}
+
+	spec, ok := r.specs[strings.TrimSpace(key)]
+	if !ok {
+		return ModuleSpec{}, false
+	}
+	return cloneModuleSpec(spec), true
+}
+
 func (r *ExtractorRegistry) RegisteredKeys() []string {
 	if r == nil {
 		return nil
 	}
 
-	keys := make([]string, 0, len(r.constructors))
+	return sortedRegistryKeys(r.constructors)
-	for key := range r.constructors {
-		keys = append(keys, key)
-	}
-	sort.Strings(keys)
-	return keys
 }

internal/framework/pipeline/extractor_registry_test.go

@@ -42,6 +42,81 @@ func TestExtractorRegistryRegisterAndBuildTrimKeys(t *testing.T) {
 	}
 }
 
+func TestExtractorRegistryRegisterWithSpecStoresMetadata(t *testing.T) {
+	registry := NewExtractorRegistry()
+	spec := ModuleSpec{
+		Key:      " generic-extractor ",
+		Stage:    StageExtract,
+		Provides: []string{" generic-artifact ", "source-citations", "generic-artifact", ""},
+		Requires: []string{" source-document ", "source-document", ""},
+	}
+
+	if err := registry.RegisterWithSpec(spec, fakeExtractorConstructor("generic-extractor")); err != nil {
+		t.Fatalf("RegisterWithSpec() error = %v, want nil", err)
+	}
+
+	got, ok := registry.Spec("\tgeneric-extractor\n")
+	if !ok {
+		t.Fatal("Spec() ok = false, want true")
+	}
+	want := ModuleSpec{
+		Key:      "generic-extractor",
+		Stage:    StageExtract,
+		Provides: []string{"generic-artifact", "source-citations"},
+		Requires: []string{"source-document"},
+	}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("Spec() = %#v, want %#v", got, want)
+	}
+
+	got.Provides[0] = "changed"
+	again, ok := registry.Spec("generic-extractor")
+	if !ok {
+		t.Fatal("Spec() after caller mutation ok = false, want true")
+	}
+	if !reflect.DeepEqual(again, want) {
+		t.Fatalf("Spec() after caller mutation = %#v, want %#v", again, want)
+	}
+}
+
+func TestExtractorRegistryRegisterStoresDefaultSpec(t *testing.T) {
+	registry := NewExtractorRegistry()
+
+	if err := registry.Register(" generic-extractor ", fakeExtractorConstructor("generic-extractor")); err != nil {
+		t.Fatalf("Register() error = %v, want nil", err)
+	}
+
+	got, ok := registry.Spec("generic-extractor")
+	if !ok {
+		t.Fatal("Spec() ok = false, want true")
+	}
+	want := ModuleSpec{Key: "generic-extractor", Stage: StageExtract}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("Spec() = %#v, want %#v", got, want)
+	}
+}
+
+func TestExtractorRegistryRegisterWithSpecRejectsWrongStage(t *testing.T) {
+	registry := NewExtractorRegistry()
+
+	err := registry.RegisterWithSpec(ModuleSpec{Key: "generic-extractor", Stage: StageInput}, fakeExtractorConstructor("generic-extractor"))
+
+	if err == nil {
+		t.Fatal("RegisterWithSpec() error = nil, want error")
+	}
+	if !strings.Contains(err.Error(), "stage") {
+		t.Fatalf("RegisterWithSpec() error = %q, want stage error", err.Error())
+	}
+}
+
+func TestExtractorRegistrySpecRejectsUnknownKey(t *testing.T) {
+	registry := NewExtractorRegistry()
+
+	if _, ok := registry.Spec("missing-extractor"); ok {
+		t.Fatal("Spec() ok = true, want false")
+	}
+}
+
 func TestExtractorRegistryRegisterRejectsEmptyKey(t *testing.T) {
 	registry := NewExtractorRegistry()
 
@@ -183,6 +258,9 @@ func TestExtractorRegistryNilRegistryBehavior(t *testing.T) {
 	if _, err := registry.Build("generic-extractor"); err == nil {
 		t.Fatal("Build() error = nil, want error")
 	}
+	if _, ok := registry.Spec("generic-extractor"); ok {
+		t.Fatal("Spec() ok = true, want false")
+	}
 	if keys := registry.RegisteredKeys(); keys != nil {
 		t.Fatalf("RegisteredKeys() = %#v, want nil", keys)
 	}

internal/framework/pipeline/generic_stages.go

@@ -0,0 +1,70 @@
+package pipeline
+
+import (
+	"context"
+	"encoding/json"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+type AppendOrderMerger struct{}
+
+func (m AppendOrderMerger) Key() string {
+	return DefaultMergeModule
+}
+
+func (m AppendOrderMerger) Merge(ctx context.Context, req contracts.MergeRequest) (contracts.MergeResult, error) {
+	var candidates []artifacts.ArtifactCandidate
+	for _, chunkArtifacts := range req.ChunkArtifacts {
+		candidates = append(candidates, copyArtifactCandidates(chunkArtifacts.Candidates)...)
+	}
+	return contracts.MergeResult{Candidates: candidates}, nil
+}
+
+type NoopNormalizer struct{}
+
+func (n NoopNormalizer) Key() string {
+	return DefaultNormalizeModule
+}
+
+func (n NoopNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
+	return contracts.NormalizeResult{Candidates: copyArtifactCandidates(req.Candidates)}, nil
+}
+
+func copyArtifactCandidates(candidates []artifacts.ArtifactCandidate) []artifacts.ArtifactCandidate {
+	if len(candidates) == 0 {
+		return nil
+	}
+
+	copied := make([]artifacts.ArtifactCandidate, 0, len(candidates))
+	for _, candidate := range candidates {
+		copied = append(copied, copyArtifactCandidate(candidate))
+	}
+	return copied
+}
+
+func copyArtifactCandidate(candidate artifacts.ArtifactCandidate) artifacts.ArtifactCandidate {
+	return artifacts.ArtifactCandidate{
+		Index:         candidate.Index,
+		ExtractorKey:  candidate.ExtractorKey,
+		ArtifactType:  candidate.ArtifactType,
+		SchemaVersion: candidate.SchemaVersion,
+		Payload:       append(json.RawMessage(nil), candidate.Payload...),
+		SourceRefs:    append([]source.SourceRef(nil), candidate.SourceRefs...),
+		Metadata:      copyArtifactMetadata(candidate.Metadata),
+	}
+}
+
+func copyArtifactMetadata(metadata map[string]any) map[string]any {
+	if len(metadata) == 0 {
+		return nil
+	}
+
+	copied := make(map[string]any, len(metadata))
+	for key, value := range metadata {
+		copied[key] = value
+	}
+	return copied
+}

internal/framework/pipeline/generic_stages_test.go

@@ -0,0 +1,221 @@
+package pipeline
+
+import (
+	"context"
+	"encoding/json"
+	"reflect"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func TestGenericMergeAndNormalizeKeys(t *testing.T) {
+	merger := AppendOrderMerger{}
+	normalizer := NoopNormalizer{}
+
+	if merger.Key() != DefaultMergeModule {
+		t.Fatalf("AppendOrderMerger.Key() = %q, want %q", merger.Key(), DefaultMergeModule)
+	}
+	if normalizer.Key() != DefaultNormalizeModule {
+		t.Fatalf("NoopNormalizer.Key() = %q, want %q", normalizer.Key(), DefaultNormalizeModule)
+	}
+}
+
+func TestAppendOrderMergerConcatenatesByChunkAndCandidateOrder(t *testing.T) {
+	merger := AppendOrderMerger{}
+	chunks := []contracts.ChunkArtifacts{
+		{
+			Chunk: sourceChunk(0),
+			Candidates: []artifacts.ArtifactCandidate{
+				candidate(2, "first-b"),
+				candidate(1, "first-a"),
+			},
+		},
+		{
+			Chunk: sourceChunk(1),
+			Candidates: []artifacts.ArtifactCandidate{
+				candidate(4, "second-b"),
+				candidate(3, "second-a"),
+			},
+		},
+	}
+
+	result, err := merger.Merge(context.Background(), contracts.MergeRequest{ChunkArtifacts: chunks})
+	if err != nil {
+		t.Fatalf("Merge() error = %v, want nil", err)
+	}
+	if len(result.Warnings) != 0 {
+		t.Fatalf("Warnings = %#v, want none", result.Warnings)
+	}
+
+	got := candidateNames(result.Candidates)
+	want := []string{"first-b", "first-a", "second-b", "second-a"}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("candidate order = %#v, want %#v", got, want)
+	}
+}
+
+func TestAppendOrderMergerReturnsMutationSafeCandidates(t *testing.T) {
+	merger := AppendOrderMerger{}
+	input := []contracts.ChunkArtifacts{
+		{
+			Chunk: sourceChunk(0),
+			Candidates: []artifacts.ArtifactCandidate{
+				candidate(1, "original"),
+			},
+		},
+	}
+
+	result, err := merger.Merge(context.Background(), contracts.MergeRequest{ChunkArtifacts: input})
+	if err != nil {
+		t.Fatalf("Merge() error = %v, want nil", err)
+	}
+	if len(result.Candidates) != 1 {
+		t.Fatalf("len(Candidates) = %d, want 1", len(result.Candidates))
+	}
+
+	input[0].Candidates[0].Index = 99
+	input[0].Candidates[0].Payload[0] = '['
+	input[0].Candidates[0].SourceRefs[0].StartUnitID = "changed"
+	input[0].Candidates[0].Metadata["name"] = "changed"
+
+	got := result.Candidates[0]
+	if got.Index != 1 {
+		t.Fatalf("Index = %d, want 1", got.Index)
+	}
+	if string(got.Payload) != `{"name":"original"}` {
+		t.Fatalf("Payload = %s, want original payload", got.Payload)
+	}
+	if got.SourceRefs[0].StartUnitID != "u1" {
+		t.Fatalf("SourceRefs = %#v, want original source ref", got.SourceRefs)
+	}
+	if got.Metadata["name"] != "original" {
+		t.Fatalf("Metadata = %#v, want original metadata", got.Metadata)
+	}
+}
+
+func TestNoopNormalizerPreservesOrderAndValues(t *testing.T) {
+	normalizer := NoopNormalizer{}
+	input := []artifacts.ArtifactCandidate{
+		candidate(3, "third"),
+		candidate(1, "first"),
+		candidate(2, "second"),
+	}
+
+	result, err := normalizer.Normalize(context.Background(), contracts.NormalizeRequest{Candidates: input})
+	if err != nil {
+		t.Fatalf("Normalize() error = %v, want nil", err)
+	}
+	if len(result.Warnings) != 0 {
+		t.Fatalf("Warnings = %#v, want none", result.Warnings)
+	}
+
+	got := candidateNames(result.Candidates)
+	want := []string{"third", "first", "second"}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("candidate order = %#v, want %#v", got, want)
+	}
+
+	if !reflect.DeepEqual(result.Candidates[0].SourceRefs, input[0].SourceRefs) {
+		t.Fatalf("SourceRefs = %#v, want %#v", result.Candidates[0].SourceRefs, input[0].SourceRefs)
+	}
+	if !reflect.DeepEqual(result.Candidates[0].Metadata, input[0].Metadata) {
+		t.Fatalf("Metadata = %#v, want %#v", result.Candidates[0].Metadata, input[0].Metadata)
+	}
+}
+
+func TestNoopNormalizerReturnsMutationSafeCandidates(t *testing.T) {
+	normalizer := NoopNormalizer{}
+	input := []artifacts.ArtifactCandidate{candidate(1, "original")}
+
+	result, err := normalizer.Normalize(context.Background(), contracts.NormalizeRequest{Candidates: input})
+	if err != nil {
+		t.Fatalf("Normalize() error = %v, want nil", err)
+	}
+	if len(result.Candidates) != 1 {
+		t.Fatalf("len(Candidates) = %d, want 1", len(result.Candidates))
+	}
+
+	input[0].Index = 99
+	input[0].Payload[0] = '['
+	input[0].SourceRefs[0].EndUnitID = "changed"
+	input[0].Metadata["name"] = "changed"
+
+	got := result.Candidates[0]
+	if got.Index != 1 {
+		t.Fatalf("Index = %d, want 1", got.Index)
+	}
+	if string(got.Payload) != `{"name":"original"}` {
+		t.Fatalf("Payload = %s, want original payload", got.Payload)
+	}
+	if got.SourceRefs[0].EndUnitID != "u1" {
+		t.Fatalf("SourceRefs = %#v, want original source ref", got.SourceRefs)
+	}
+	if got.Metadata["name"] != "original" {
+		t.Fatalf("Metadata = %#v, want original metadata", got.Metadata)
+	}
+}
+
+func TestGenericMergeAndNormalizeHandleEmptyInput(t *testing.T) {
+	merger := AppendOrderMerger{}
+	normalizer := NoopNormalizer{}
+
+	mergeResult, err := merger.Merge(context.Background(), contracts.MergeRequest{})
+	if err != nil {
+		t.Fatalf("Merge() error = %v, want nil", err)
+	}
+	if len(mergeResult.Candidates) != 0 {
+		t.Fatalf("len(mergeResult.Candidates) = %d, want 0", len(mergeResult.Candidates))
+	}
+	if len(mergeResult.Warnings) != 0 {
+		t.Fatalf("merge warnings = %#v, want none", mergeResult.Warnings)
+	}
+
+	normalizeResult, err := normalizer.Normalize(context.Background(), contracts.NormalizeRequest{})
+	if err != nil {
+		t.Fatalf("Normalize() error = %v, want nil", err)
+	}
+	if len(normalizeResult.Candidates) != 0 {
+		t.Fatalf("len(normalizeResult.Candidates) = %d, want 0", len(normalizeResult.Candidates))
+	}
+	if len(normalizeResult.Warnings) != 0 {
+		t.Fatalf("normalize warnings = %#v, want none", normalizeResult.Warnings)
+	}
+}
+
+func candidate(index int, name string) artifacts.ArtifactCandidate {
+	return artifacts.ArtifactCandidate{
+		Index:         index,
+		ExtractorKey:  "generic-extractor",
+		ArtifactType:  "generic-artifact",
+		SchemaVersion: "v1",
+		Payload:       json.RawMessage(`{"name":"` + name + `"}`),
+		SourceRefs: []source.SourceRef{
+			{SourceID: "source-1", StartUnitID: "u1", EndUnitID: "u1"},
+		},
+		Metadata: map[string]any{
+			"name": name,
+		},
+	}
+}
+
+func candidateNames(candidates []artifacts.ArtifactCandidate) []string {
+	names := make([]string, 0, len(candidates))
+	for _, candidate := range candidates {
+		names = append(names, candidate.Metadata["name"].(string))
+	}
+	return names
+}
+
+func sourceChunk(index int) contracts.SourceChunk {
+	return contracts.SourceChunk{
+		ID:       "chunk",
+		SourceID: "source-1",
+		Index:    index,
+		Units: []source.SourceUnit{
+			{ID: "u1", Kind: "unit", Text: "Source unit."},
+		},
+	}
+}

internal/framework/pipeline/input_registry.go

@@ -2,7 +2,6 @@ package pipeline
 
 import (
 	"fmt"
-	"sort"
 	"strings"
 
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
@@ -12,31 +11,44 @@ type InputAdapterConstructor func() (contracts.InputAdapter, error)
 
 type InputAdapterRegistry struct {
 	constructors map[string]InputAdapterConstructor
+	specs        map[string]ModuleSpec
 }
 
 func NewInputAdapterRegistry() *InputAdapterRegistry {
 	return &InputAdapterRegistry{
 		constructors: make(map[string]InputAdapterConstructor),
+		specs:        make(map[string]ModuleSpec),
 	}
 }
 
 func (r *InputAdapterRegistry) Register(key string, constructor InputAdapterConstructor) error {
+	return r.RegisterWithSpec(defaultModuleSpec(key, StageInput), constructor)
+}
+
+func (r *InputAdapterRegistry) RegisterWithSpec(spec ModuleSpec, constructor InputAdapterConstructor) error {
 	if r == nil {
 		return fmt.Errorf("input adapter registry must not be nil")
 	}
 
-	normalizedKey := strings.TrimSpace(key)
+	normalizedSpec := normalizeModuleSpec(spec)
-	if normalizedKey == "" {
+	if err := validateModuleSpec("input adapter", StageInput, normalizedSpec); err != nil {
-		return fmt.Errorf("input adapter key must not be empty")
+		return err
 	}
 	if constructor == nil {
-		return fmt.Errorf("input adapter constructor for %q must not be nil", normalizedKey)
+		return fmt.Errorf("input adapter constructor for %q must not be nil", normalizedSpec.Key)
 	}
-	if _, ok := r.constructors[normalizedKey]; ok {
+	if _, ok := r.constructors[normalizedSpec.Key]; ok {
-		return fmt.Errorf("input adapter %q is already registered", normalizedKey)
+		return fmt.Errorf("input adapter %q is already registered", normalizedSpec.Key)
 	}
 
-	r.constructors[normalizedKey] = constructor
+	if r.constructors == nil {
+		r.constructors = make(map[string]InputAdapterConstructor)
+	}
+	if r.specs == nil {
+		r.specs = make(map[string]ModuleSpec)
+	}
+	r.constructors[normalizedSpec.Key] = constructor
+	r.specs[normalizedSpec.Key] = cloneModuleSpec(normalizedSpec)
 	return nil
 }
 
@@ -69,15 +81,22 @@ func (r *InputAdapterRegistry) Build(key string) (contracts.InputAdapter, error)
 	return adapter, nil
 }
 
+func (r *InputAdapterRegistry) Spec(key string) (ModuleSpec, bool) {
+	if r == nil {
+		return ModuleSpec{}, false
+	}
+
+	spec, ok := r.specs[strings.TrimSpace(key)]
+	if !ok {
+		return ModuleSpec{}, false
+	}
+	return cloneModuleSpec(spec), true
+}
+
 func (r *InputAdapterRegistry) RegisteredKeys() []string {
 	if r == nil {
 		return nil
 	}
 
-	keys := make([]string, 0, len(r.constructors))
+	return sortedRegistryKeys(r.constructors)
-	for key := range r.constructors {
-		keys = append(keys, key)
-	}
-	sort.Strings(keys)
-	return keys
 }

internal/framework/pipeline/input_registry_test.go

@@ -43,6 +43,81 @@ func TestInputAdapterRegistryRegisterAndBuildTrimKeys(t *testing.T) {
 	}
 }
 
+func TestInputAdapterRegistryRegisterWithSpecStoresMetadata(t *testing.T) {
+	registry := NewInputAdapterRegistry()
+	spec := ModuleSpec{
+		Key:      " generic-input ",
+		Stage:    StageInput,
+		Provides: []string{" parsed-source ", "source-document", "parsed-source", ""},
+		Requires: []string{" raw-bytes ", "raw-bytes", ""},
+	}
+
+	if err := registry.RegisterWithSpec(spec, fakeInputAdapterConstructor("generic-input")); err != nil {
+		t.Fatalf("RegisterWithSpec() error = %v, want nil", err)
+	}
+
+	got, ok := registry.Spec("\tgeneric-input\n")
+	if !ok {
+		t.Fatal("Spec() ok = false, want true")
+	}
+	want := ModuleSpec{
+		Key:      "generic-input",
+		Stage:    StageInput,
+		Provides: []string{"parsed-source", "source-document"},
+		Requires: []string{"raw-bytes"},
+	}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("Spec() = %#v, want %#v", got, want)
+	}
+
+	got.Provides[0] = "changed"
+	again, ok := registry.Spec("generic-input")
+	if !ok {
+		t.Fatal("Spec() after caller mutation ok = false, want true")
+	}
+	if !reflect.DeepEqual(again, want) {
+		t.Fatalf("Spec() after caller mutation = %#v, want %#v", again, want)
+	}
+}
+
+func TestInputAdapterRegistryRegisterStoresDefaultSpec(t *testing.T) {
+	registry := NewInputAdapterRegistry()
+
+	if err := registry.Register(" generic-input ", fakeInputAdapterConstructor("generic-input")); err != nil {
+		t.Fatalf("Register() error = %v, want nil", err)
+	}
+
+	got, ok := registry.Spec("generic-input")
+	if !ok {
+		t.Fatal("Spec() ok = false, want true")
+	}
+	want := ModuleSpec{Key: "generic-input", Stage: StageInput}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("Spec() = %#v, want %#v", got, want)
+	}
+}
+
+func TestInputAdapterRegistryRegisterWithSpecRejectsWrongStage(t *testing.T) {
+	registry := NewInputAdapterRegistry()
+
+	err := registry.RegisterWithSpec(ModuleSpec{Key: "generic-input", Stage: StageExtract}, fakeInputAdapterConstructor("generic-input"))
+
+	if err == nil {
+		t.Fatal("RegisterWithSpec() error = nil, want error")
+	}
+	if !strings.Contains(err.Error(), "stage") {
+		t.Fatalf("RegisterWithSpec() error = %q, want stage error", err.Error())
+	}
+}
+
+func TestInputAdapterRegistrySpecRejectsUnknownKey(t *testing.T) {
+	registry := NewInputAdapterRegistry()
+
+	if _, ok := registry.Spec("missing-input"); ok {
+		t.Fatal("Spec() ok = true, want false")
+	}
+}
+
 func TestInputAdapterRegistryRegisterRejectsEmptyKey(t *testing.T) {
 	registry := NewInputAdapterRegistry()
 
@@ -184,6 +259,9 @@ func TestInputAdapterRegistryNilRegistryBehavior(t *testing.T) {
 	if _, err := registry.Build("generic-input"); err == nil {
 		t.Fatal("Build() error = nil, want error")
 	}
+	if _, ok := registry.Spec("generic-input"); ok {
+		t.Fatal("Spec() ok = true, want false")
+	}
 	if keys := registry.RegisteredKeys(); keys != nil {
 		t.Fatalf("RegisteredKeys() = %#v, want nil", keys)
 	}

internal/framework/pipeline/merger_registry.go

@@ -0,0 +1,102 @@
+package pipeline
+
+import (
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+type MergerConstructor func() (contracts.Merger, error)
+
+type MergerRegistry struct {
+	constructors map[string]MergerConstructor
+	specs        map[string]ModuleSpec
+}
+
+func NewMergerRegistry() *MergerRegistry {
+	return &MergerRegistry{
+		constructors: make(map[string]MergerConstructor),
+		specs:        make(map[string]ModuleSpec),
+	}
+}
+
+func (r *MergerRegistry) Register(key string, constructor MergerConstructor) error {
+	return r.RegisterWithSpec(defaultModuleSpec(key, StageMerge), constructor)
+}
+
+func (r *MergerRegistry) RegisterWithSpec(spec ModuleSpec, constructor MergerConstructor) error {
+	if r == nil {
+		return fmt.Errorf("merger registry must not be nil")
+	}
+
+	normalizedSpec := normalizeModuleSpec(spec)
+	if err := validateModuleSpec("merger", StageMerge, normalizedSpec); err != nil {
+		return err
+	}
+	if constructor == nil {
+		return fmt.Errorf("merger constructor for %q must not be nil", normalizedSpec.Key)
+	}
+	if _, ok := r.constructors[normalizedSpec.Key]; ok {
+		return fmt.Errorf("merger %q is already registered", normalizedSpec.Key)
+	}
+
+	if r.constructors == nil {
+		r.constructors = make(map[string]MergerConstructor)
+	}
+	if r.specs == nil {
+		r.specs = make(map[string]ModuleSpec)
+	}
+	r.constructors[normalizedSpec.Key] = constructor
+	r.specs[normalizedSpec.Key] = cloneModuleSpec(normalizedSpec)
+	return nil
+}
+
+func (r *MergerRegistry) Build(key string) (contracts.Merger, error) {
+	if r == nil {
+		return nil, fmt.Errorf("merger registry must not be nil")
+	}
+
+	normalizedKey := strings.TrimSpace(key)
+	if normalizedKey == "" {
+		return nil, fmt.Errorf("merger key must not be empty")
+	}
+
+	constructor, ok := r.constructors[normalizedKey]
+	if !ok {
+		return nil, fmt.Errorf("merger %q is not registered", normalizedKey)
+	}
+
+	merger, err := constructor()
+	if err != nil {
+		return nil, fmt.Errorf("build merger %q: %w", normalizedKey, err)
+	}
+	if merger == nil {
+		return nil, fmt.Errorf("merger %q constructor returned nil", normalizedKey)
+	}
+	if merger.Key() != normalizedKey {
+		return nil, fmt.Errorf("merger %q returned key %q", normalizedKey, merger.Key())
+	}
+
+	return merger, nil
+}
+
+func (r *MergerRegistry) Spec(key string) (ModuleSpec, bool) {
+	if r == nil {
+		return ModuleSpec{}, false
+	}
+
+	spec, ok := r.specs[strings.TrimSpace(key)]
+	if !ok {
+		return ModuleSpec{}, false
+	}
+	return cloneModuleSpec(spec), true
+}
+
+func (r *MergerRegistry) RegisteredKeys() []string {
+	if r == nil {
+		return nil
+	}
+
+	return sortedRegistryKeys(r.constructors)
+}

internal/framework/pipeline/merger_registry_test.go

@@ -0,0 +1,58 @@
+package pipeline
+
+import (
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func TestMergerRegistryBehavior(t *testing.T) {
+	runRegistryBehaviorTests(t, registryBehaviorCase[contracts.Merger]{
+		name:       "MergerRegistry",
+		key:        "generic-merger",
+		stage:      StageMerge,
+		wrongStage: StageExtract,
+		newRegistry: func() any {
+			return NewMergerRegistry()
+		},
+		register: func(registry any, key string, constructor func() (contracts.Merger, error)) error {
+			return registry.(*MergerRegistry).Register(key, constructor)
+		},
+		registerWithSpec: func(registry any, spec ModuleSpec, constructor func() (contracts.Merger, error)) error {
+			return registry.(*MergerRegistry).RegisterWithSpec(spec, constructor)
+		},
+		build: func(registry any, key string) (contracts.Merger, error) {
+			return registry.(*MergerRegistry).Build(key)
+		},
+		spec: func(registry any, key string) (ModuleSpec, bool) {
+			return registry.(*MergerRegistry).Spec(key)
+		},
+		registeredKeys: func(registry any) []string {
+			return registry.(*MergerRegistry).RegisteredKeys()
+		},
+		nilRegister: func(key string, constructor func() (contracts.Merger, error)) error {
+			var registry *MergerRegistry
+			return registry.Register(key, constructor)
+		},
+		nilBuild: func(key string) (contracts.Merger, error) {
+			var registry *MergerRegistry
+			return registry.Build(key)
+		},
+		nilSpec: func(key string) (ModuleSpec, bool) {
+			var registry *MergerRegistry
+			return registry.Spec(key)
+		},
+		nilRegisteredKey: func() []string {
+			var registry *MergerRegistry
+			return registry.RegisteredKeys()
+		},
+		constructor: func(key string) func() (contracts.Merger, error) {
+			return func() (contracts.Merger, error) {
+				return registryMerger{key: key}, nil
+			}
+		},
+		moduleKey: func(module contracts.Merger) string {
+			return module.Key()
+		},
+	})
+}

internal/framework/pipeline/module.go

@@ -0,0 +1,99 @@
+package pipeline
+
+import (
+	"fmt"
+	"sort"
+	"strings"
+)
+
+type ModuleStage string
+
+const (
+	StageInput     ModuleStage = "input"
+	StageChunk     ModuleStage = "chunk"
+	StageExtract   ModuleStage = "extract"
+	StageMerge     ModuleStage = "merge"
+	StageNormalize ModuleStage = "normalize"
+	StageValidate  ModuleStage = "validate"
+	StageOutput    ModuleStage = "output"
+)
+
+type ModuleSpec struct {
+	Key      string
+	Stage    ModuleStage
+	Provides []string
+	Requires []string
+}
+
+func defaultModuleSpec(key string, stage ModuleStage) ModuleSpec {
+	return ModuleSpec{
+		Key:   key,
+		Stage: stage,
+	}
+}
+
+func normalizeModuleSpec(spec ModuleSpec) ModuleSpec {
+	return ModuleSpec{
+		Key:      strings.TrimSpace(spec.Key),
+		Stage:    spec.Stage,
+		Provides: normalizeCapabilities(spec.Provides),
+		Requires: normalizeCapabilities(spec.Requires),
+	}
+}
+
+func normalizeCapabilities(values []string) []string {
+	if len(values) == 0 {
+		return nil
+	}
+
+	seen := make(map[string]struct{}, len(values))
+	for _, value := range values {
+		normalized := strings.TrimSpace(value)
+		if normalized == "" {
+			continue
+		}
+		seen[normalized] = struct{}{}
+	}
+	if len(seen) == 0 {
+		return nil
+	}
+
+	capabilities := make([]string, 0, len(seen))
+	for value := range seen {
+		capabilities = append(capabilities, value)
+	}
+	sort.Strings(capabilities)
+	return capabilities
+}
+
+func cloneModuleSpec(spec ModuleSpec) ModuleSpec {
+	return ModuleSpec{
+		Key:      spec.Key,
+		Stage:    spec.Stage,
+		Provides: append([]string(nil), spec.Provides...),
+		Requires: append([]string(nil), spec.Requires...),
+	}
+}
+
+func validateModuleSpec(kind string, expectedStage ModuleStage, spec ModuleSpec) error {
+	if spec.Key == "" {
+		return fmt.Errorf("%s key must not be empty", kind)
+	}
+	if spec.Stage != expectedStage {
+		return fmt.Errorf("%s %q must use %q stage, got %q", kind, spec.Key, expectedStage, spec.Stage)
+	}
+	return nil
+}
+
+func sortedRegistryKeys[C any](constructors map[string]C) []string {
+	if len(constructors) == 0 {
+		return nil
+	}
+
+	keys := make([]string, 0, len(constructors))
+	for key := range constructors {
+		keys = append(keys, key)
+	}
+	sort.Strings(keys)
+	return keys
+}

internal/framework/pipeline/normalizer_registry.go

@@ -0,0 +1,102 @@
+package pipeline
+
+import (
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+type NormalizerConstructor func() (contracts.Normalizer, error)
+
+type NormalizerRegistry struct {
+	constructors map[string]NormalizerConstructor
+	specs        map[string]ModuleSpec
+}
+
+func NewNormalizerRegistry() *NormalizerRegistry {
+	return &NormalizerRegistry{
+		constructors: make(map[string]NormalizerConstructor),
+		specs:        make(map[string]ModuleSpec),
+	}
+}
+
+func (r *NormalizerRegistry) Register(key string, constructor NormalizerConstructor) error {
+	return r.RegisterWithSpec(defaultModuleSpec(key, StageNormalize), constructor)
+}
+
+func (r *NormalizerRegistry) RegisterWithSpec(spec ModuleSpec, constructor NormalizerConstructor) error {
+	if r == nil {
+		return fmt.Errorf("normalizer registry must not be nil")
+	}
+
+	normalizedSpec := normalizeModuleSpec(spec)
+	if err := validateModuleSpec("normalizer", StageNormalize, normalizedSpec); err != nil {
+		return err
+	}
+	if constructor == nil {
+		return fmt.Errorf("normalizer constructor for %q must not be nil", normalizedSpec.Key)
+	}
+	if _, ok := r.constructors[normalizedSpec.Key]; ok {
+		return fmt.Errorf("normalizer %q is already registered", normalizedSpec.Key)
+	}
+
+	if r.constructors == nil {
+		r.constructors = make(map[string]NormalizerConstructor)
+	}
+	if r.specs == nil {
+		r.specs = make(map[string]ModuleSpec)
+	}
+	r.constructors[normalizedSpec.Key] = constructor
+	r.specs[normalizedSpec.Key] = cloneModuleSpec(normalizedSpec)
+	return nil
+}
+
+func (r *NormalizerRegistry) Build(key string) (contracts.Normalizer, error) {
+	if r == nil {
+		return nil, fmt.Errorf("normalizer registry must not be nil")
+	}
+
+	normalizedKey := strings.TrimSpace(key)
+	if normalizedKey == "" {
+		return nil, fmt.Errorf("normalizer key must not be empty")
+	}
+
+	constructor, ok := r.constructors[normalizedKey]
+	if !ok {
+		return nil, fmt.Errorf("normalizer %q is not registered", normalizedKey)
+	}
+
+	normalizer, err := constructor()
+	if err != nil {
+		return nil, fmt.Errorf("build normalizer %q: %w", normalizedKey, err)
+	}
+	if normalizer == nil {
+		return nil, fmt.Errorf("normalizer %q constructor returned nil", normalizedKey)
+	}
+	if normalizer.Key() != normalizedKey {
+		return nil, fmt.Errorf("normalizer %q returned key %q", normalizedKey, normalizer.Key())
+	}
+
+	return normalizer, nil
+}
+
+func (r *NormalizerRegistry) Spec(key string) (ModuleSpec, bool) {
+	if r == nil {
+		return ModuleSpec{}, false
+	}
+
+	spec, ok := r.specs[strings.TrimSpace(key)]
+	if !ok {
+		return ModuleSpec{}, false
+	}
+	return cloneModuleSpec(spec), true
+}
+
+func (r *NormalizerRegistry) RegisteredKeys() []string {
+	if r == nil {
+		return nil
+	}
+
+	return sortedRegistryKeys(r.constructors)
+}

internal/framework/pipeline/normalizer_registry_test.go

@@ -0,0 +1,58 @@
+package pipeline
+
+import (
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func TestNormalizerRegistryBehavior(t *testing.T) {
+	runRegistryBehaviorTests(t, registryBehaviorCase[contracts.Normalizer]{
+		name:       "NormalizerRegistry",
+		key:        "generic-normalizer",
+		stage:      StageNormalize,
+		wrongStage: StageExtract,
+		newRegistry: func() any {
+			return NewNormalizerRegistry()
+		},
+		register: func(registry any, key string, constructor func() (contracts.Normalizer, error)) error {
+			return registry.(*NormalizerRegistry).Register(key, constructor)
+		},
+		registerWithSpec: func(registry any, spec ModuleSpec, constructor func() (contracts.Normalizer, error)) error {
+			return registry.(*NormalizerRegistry).RegisterWithSpec(spec, constructor)
+		},
+		build: func(registry any, key string) (contracts.Normalizer, error) {
+			return registry.(*NormalizerRegistry).Build(key)
+		},
+		spec: func(registry any, key string) (ModuleSpec, bool) {
+			return registry.(*NormalizerRegistry).Spec(key)
+		},
+		registeredKeys: func(registry any) []string {
+			return registry.(*NormalizerRegistry).RegisteredKeys()
+		},
+		nilRegister: func(key string, constructor func() (contracts.Normalizer, error)) error {
+			var registry *NormalizerRegistry
+			return registry.Register(key, constructor)
+		},
+		nilBuild: func(key string) (contracts.Normalizer, error) {
+			var registry *NormalizerRegistry
+			return registry.Build(key)
+		},
+		nilSpec: func(key string) (ModuleSpec, bool) {
+			var registry *NormalizerRegistry
+			return registry.Spec(key)
+		},
+		nilRegisteredKey: func() []string {
+			var registry *NormalizerRegistry
+			return registry.RegisteredKeys()
+		},
+		constructor: func(key string) func() (contracts.Normalizer, error) {
+			return func() (contracts.Normalizer, error) {
+				return registryNormalizer{key: key}, nil
+			}
+		},
+		moduleKey: func(module contracts.Normalizer) string {
+			return module.Key()
+		},
+	})
+}

internal/framework/pipeline/output_registry.go

@@ -0,0 +1,102 @@
+package pipeline
+
+import (
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+type OutputEncoderConstructor func() (contracts.OutputEncoder, error)
+
+type OutputEncoderRegistry struct {
+	constructors map[string]OutputEncoderConstructor
+	specs        map[string]ModuleSpec
+}
+
+func NewOutputEncoderRegistry() *OutputEncoderRegistry {
+	return &OutputEncoderRegistry{
+		constructors: make(map[string]OutputEncoderConstructor),
+		specs:        make(map[string]ModuleSpec),
+	}
+}
+
+func (r *OutputEncoderRegistry) Register(key string, constructor OutputEncoderConstructor) error {
+	return r.RegisterWithSpec(defaultModuleSpec(key, StageOutput), constructor)
+}
+
+func (r *OutputEncoderRegistry) RegisterWithSpec(spec ModuleSpec, constructor OutputEncoderConstructor) error {
+	if r == nil {
+		return fmt.Errorf("output encoder registry must not be nil")
+	}
+
+	normalizedSpec := normalizeModuleSpec(spec)
+	if err := validateModuleSpec("output encoder", StageOutput, normalizedSpec); err != nil {
+		return err
+	}
+	if constructor == nil {
+		return fmt.Errorf("output encoder constructor for %q must not be nil", normalizedSpec.Key)
+	}
+	if _, ok := r.constructors[normalizedSpec.Key]; ok {
+		return fmt.Errorf("output encoder %q is already registered", normalizedSpec.Key)
+	}
+
+	if r.constructors == nil {
+		r.constructors = make(map[string]OutputEncoderConstructor)
+	}
+	if r.specs == nil {
+		r.specs = make(map[string]ModuleSpec)
+	}
+	r.constructors[normalizedSpec.Key] = constructor
+	r.specs[normalizedSpec.Key] = cloneModuleSpec(normalizedSpec)
+	return nil
+}
+
+func (r *OutputEncoderRegistry) Build(key string) (contracts.OutputEncoder, error) {
+	if r == nil {
+		return nil, fmt.Errorf("output encoder registry must not be nil")
+	}
+
+	normalizedKey := strings.TrimSpace(key)
+	if normalizedKey == "" {
+		return nil, fmt.Errorf("output encoder key must not be empty")
+	}
+
+	constructor, ok := r.constructors[normalizedKey]
+	if !ok {
+		return nil, fmt.Errorf("output encoder %q is not registered", normalizedKey)
+	}
+
+	encoder, err := constructor()
+	if err != nil {
+		return nil, fmt.Errorf("build output encoder %q: %w", normalizedKey, err)
+	}
+	if encoder == nil {
+		return nil, fmt.Errorf("output encoder %q constructor returned nil", normalizedKey)
+	}
+	if encoder.Key() != normalizedKey {
+		return nil, fmt.Errorf("output encoder %q returned key %q", normalizedKey, encoder.Key())
+	}
+
+	return encoder, nil
+}
+
+func (r *OutputEncoderRegistry) Spec(key string) (ModuleSpec, bool) {
+	if r == nil {
+		return ModuleSpec{}, false
+	}
+
+	spec, ok := r.specs[strings.TrimSpace(key)]
+	if !ok {
+		return ModuleSpec{}, false
+	}
+	return cloneModuleSpec(spec), true
+}
+
+func (r *OutputEncoderRegistry) RegisteredKeys() []string {
+	if r == nil {
+		return nil
+	}
+
+	return sortedRegistryKeys(r.constructors)
+}

internal/framework/pipeline/output_registry_test.go

@@ -0,0 +1,58 @@
+package pipeline
+
+import (
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func TestOutputEncoderRegistryBehavior(t *testing.T) {
+	runRegistryBehaviorTests(t, registryBehaviorCase[contracts.OutputEncoder]{
+		name:       "OutputEncoderRegistry",
+		key:        "generic-output",
+		stage:      StageOutput,
+		wrongStage: StageExtract,
+		newRegistry: func() any {
+			return NewOutputEncoderRegistry()
+		},
+		register: func(registry any, key string, constructor func() (contracts.OutputEncoder, error)) error {
+			return registry.(*OutputEncoderRegistry).Register(key, constructor)
+		},
+		registerWithSpec: func(registry any, spec ModuleSpec, constructor func() (contracts.OutputEncoder, error)) error {
+			return registry.(*OutputEncoderRegistry).RegisterWithSpec(spec, constructor)
+		},
+		build: func(registry any, key string) (contracts.OutputEncoder, error) {
+			return registry.(*OutputEncoderRegistry).Build(key)
+		},
+		spec: func(registry any, key string) (ModuleSpec, bool) {
+			return registry.(*OutputEncoderRegistry).Spec(key)
+		},
+		registeredKeys: func(registry any) []string {
+			return registry.(*OutputEncoderRegistry).RegisteredKeys()
+		},
+		nilRegister: func(key string, constructor func() (contracts.OutputEncoder, error)) error {
+			var registry *OutputEncoderRegistry
+			return registry.Register(key, constructor)
+		},
+		nilBuild: func(key string) (contracts.OutputEncoder, error) {
+			var registry *OutputEncoderRegistry
+			return registry.Build(key)
+		},
+		nilSpec: func(key string) (ModuleSpec, bool) {
+			var registry *OutputEncoderRegistry
+			return registry.Spec(key)
+		},
+		nilRegisteredKey: func() []string {
+			var registry *OutputEncoderRegistry
+			return registry.RegisteredKeys()
+		},
+		constructor: func(key string) func() (contracts.OutputEncoder, error) {
+			return func() (contracts.OutputEncoder, error) {
+				return registryOutputEncoder{key: key}, nil
+			}
+		},
+		moduleKey: func(module contracts.OutputEncoder) string {
+			return module.Key()
+		},
+	})
+}

internal/framework/pipeline/profile.go

@@ -0,0 +1,404 @@
+package pipeline
+
+import (
+	"crypto/sha256"
+	"encoding/hex"
+	"encoding/json"
+	"fmt"
+	"sort"
+	"strings"
+)
+
+const (
+	DefaultChunkModule     = "generic"
+	DefaultMergeModule     = "appendorder"
+	DefaultNormalizeModule = "noop"
+	DefaultOutputModule    = "json"
+	DefaultLLMProfile      = "default"
+)
+
+type ModuleBinding struct {
+	Module     string         `json:"module"`
+	LLMProfile string         `json:"llm_profile,omitempty"`
+	Options    map[string]any `json:"options,omitempty"`
+}
+
+type ArtifactLaneProfile struct {
+	Extract    ModuleBinding   `json:"extract"`
+	Merge      ModuleBinding   `json:"merge,omitempty"`
+	Normalize  ModuleBinding   `json:"normalize,omitempty"`
+	Validators []ModuleBinding `json:"validators,omitempty"`
+}
+
+type PipelineProfile struct {
+	ID        string                         `json:"id"`
+	Input     ModuleBinding                  `json:"input"`
+	Chunk     ModuleBinding                  `json:"chunk,omitempty"`
+	Artifacts map[string]ArtifactLaneProfile `json:"artifacts"`
+	Output    ModuleBinding                  `json:"output,omitempty"`
+}
+
+type ResolveOptions struct {
+	Only []string
+}
+
+type ResolvedArtifactLane struct {
+	ID         string
+	Extract    ModuleBinding
+	Merge      ModuleBinding
+	Normalize  ModuleBinding
+	Validators []ModuleBinding
+}
+
+type ResolvedPipeline struct {
+	ID            string
+	Digest        string
+	Input         ModuleBinding
+	Chunk         ModuleBinding
+	ArtifactLanes []ResolvedArtifactLane
+	Output        ModuleBinding
+}
+
+type ModuleCatalog struct {
+	Inputs      *InputAdapterRegistry
+	Chunkers    *ChunkerRegistry
+	Extractors  *ExtractorRegistry
+	Mergers     *MergerRegistry
+	Normalizers *NormalizerRegistry
+	Validators  *ValidatorRegistry
+	Outputs     *OutputEncoderRegistry
+}
+
+func Binding(module string) ModuleBinding {
+	return ModuleBinding{Module: strings.TrimSpace(module)}
+}
+
+func ResolvePipeline(profile PipelineProfile, options ResolveOptions, catalog ModuleCatalog) (ResolvedPipeline, error) {
+	pipelineID := strings.TrimSpace(profile.ID)
+	if pipelineID == "" {
+		return ResolvedPipeline{}, fmt.Errorf("pipeline id must not be empty")
+	}
+
+	if len(profile.Artifacts) == 0 {
+		return ResolvedPipeline{}, fmt.Errorf("pipeline %q must declare at least one artifact lane", pipelineID)
+	}
+
+	input := resolveBinding(profile.Input, "")
+	if input.Module == "" {
+		return ResolvedPipeline{}, fmt.Errorf("pipeline %q input module must not be empty", pipelineID)
+	}
+	inputModuleSpec, err := inputSpec(catalog, input.Module)
+	if err != nil {
+		return ResolvedPipeline{}, moduleLookupError(pipelineID, "", StageInput, input.Module, err)
+	}
+
+	capabilities := newCapabilitySet()
+	if missing, ok := capabilities.missing(inputModuleSpec.Requires); ok {
+		return ResolvedPipeline{}, capabilityError(pipelineID, "", StageInput, input.Module, missing)
+	}
+	capabilities.add(inputModuleSpec.Provides...)
+
+	chunk := resolveBinding(profile.Chunk, DefaultChunkModule)
+	chunkSpec, err := chunkerSpec(catalog, chunk.Module)
+	if err != nil {
+		return ResolvedPipeline{}, moduleLookupError(pipelineID, "", StageChunk, chunk.Module, err)
+	}
+	if missing, ok := capabilities.missing(chunkSpec.Requires); ok {
+		return ResolvedPipeline{}, capabilityError(pipelineID, "", StageChunk, chunk.Module, missing)
+	}
+	capabilities.add(chunkSpec.Provides...)
+
+	lanesByID, selectedLaneIDs, err := selectedArtifactLanes(pipelineID, profile.Artifacts, options)
+	if err != nil {
+		return ResolvedPipeline{}, err
+	}
+	if len(selectedLaneIDs) == 0 {
+		return ResolvedPipeline{}, fmt.Errorf("pipeline %q must select at least one artifact lane", pipelineID)
+	}
+
+	resolved := ResolvedPipeline{
+		ID:     pipelineID,
+		Input:  input,
+		Chunk:  chunk,
+		Output: resolveBinding(profile.Output, DefaultOutputModule),
+	}
+	outputCapabilities := capabilities.clone()
+
+	for _, laneID := range selectedLaneIDs {
+		laneProfile := lanesByID[laneID]
+		lane, laneCapabilities, err := resolveArtifactLane(pipelineID, laneID, laneProfile, capabilities, catalog)
+		if err != nil {
+			return ResolvedPipeline{}, err
+		}
+		resolved.ArtifactLanes = append(resolved.ArtifactLanes, lane)
+		outputCapabilities.addSet(laneCapabilities)
+	}
+
+	outputSpec, err := outputSpec(catalog, resolved.Output.Module)
+	if err != nil {
+		return ResolvedPipeline{}, moduleLookupError(pipelineID, "", StageOutput, resolved.Output.Module, err)
+	}
+	if missing, ok := outputCapabilities.missing(outputSpec.Requires); ok {
+		return ResolvedPipeline{}, capabilityError(pipelineID, "", StageOutput, resolved.Output.Module, missing)
+	}
+
+	digest, err := resolvedPipelineDigest(resolved)
+	if err != nil {
+		return ResolvedPipeline{}, fmt.Errorf("pipeline %q digest: %w", pipelineID, err)
+	}
+	resolved.Digest = digest
+	return resolved, nil
+}
+
+func resolveArtifactLane(pipelineID, laneID string, profile ArtifactLaneProfile, inherited capabilitySet, catalog ModuleCatalog) (ResolvedArtifactLane, capabilitySet, error) {
+	lane := ResolvedArtifactLane{
+		ID:         laneID,
+		Extract:    resolveBinding(profile.Extract, ""),
+		Merge:      resolveBinding(profile.Merge, DefaultMergeModule),
+		Normalize:  resolveBinding(profile.Normalize, DefaultNormalizeModule),
+		Validators: resolveBindings(profile.Validators, ""),
+	}
+	if lane.Extract.Module == "" {
+		return ResolvedArtifactLane{}, nil, fmt.Errorf("pipeline %q lane %q extract module must not be empty", pipelineID, laneID)
+	}
+
+	capabilities := inherited.clone()
+
+	extractSpec, err := extractorSpec(catalog, lane.Extract.Module)
+	if err != nil {
+		return ResolvedArtifactLane{}, nil, moduleLookupError(pipelineID, laneID, StageExtract, lane.Extract.Module, err)
+	}
+	if missing, ok := capabilities.missing(extractSpec.Requires); ok {
+		return ResolvedArtifactLane{}, nil, capabilityError(pipelineID, laneID, StageExtract, lane.Extract.Module, missing)
+	}
+	capabilities.add(extractSpec.Provides...)
+
+	mergeSpec, err := mergerSpec(catalog, lane.Merge.Module)
+	if err != nil {
+		return ResolvedArtifactLane{}, nil, moduleLookupError(pipelineID, laneID, StageMerge, lane.Merge.Module, err)
+	}
+	if missing, ok := capabilities.missing(mergeSpec.Requires); ok {
+		return ResolvedArtifactLane{}, nil, capabilityError(pipelineID, laneID, StageMerge, lane.Merge.Module, missing)
+	}
+	capabilities.add(mergeSpec.Provides...)
+
+	normalizeSpec, err := normalizerSpec(catalog, lane.Normalize.Module)
+	if err != nil {
+		return ResolvedArtifactLane{}, nil, moduleLookupError(pipelineID, laneID, StageNormalize, lane.Normalize.Module, err)
+	}
+	if missing, ok := capabilities.missing(normalizeSpec.Requires); ok {
+		return ResolvedArtifactLane{}, nil, capabilityError(pipelineID, laneID, StageNormalize, lane.Normalize.Module, missing)
+	}
+	capabilities.add(normalizeSpec.Provides...)
+
+	for _, validator := range lane.Validators {
+		validatorSpec, err := validatorSpec(catalog, validator.Module)
+		if err != nil {
+			return ResolvedArtifactLane{}, nil, moduleLookupError(pipelineID, laneID, StageValidate, validator.Module, err)
+		}
+		if missing, ok := capabilities.missing(validatorSpec.Requires); ok {
+			return ResolvedArtifactLane{}, nil, capabilityError(pipelineID, laneID, StageValidate, validator.Module, missing)
+		}
+		capabilities.add(validatorSpec.Provides...)
+	}
+
+	return lane, capabilities, nil
+}
+
+func resolveBinding(binding ModuleBinding, defaultModule string) ModuleBinding {
+	module := strings.TrimSpace(binding.Module)
+	if module == "" {
+		module = defaultModule
+	}
+	llmProfile := strings.TrimSpace(binding.LLMProfile)
+	if llmProfile == "" {
+		llmProfile = DefaultLLMProfile
+	}
+	return ModuleBinding{
+		Module:     module,
+		LLMProfile: llmProfile,
+		Options:    cloneOptions(binding.Options),
+	}
+}
+
+func resolveBindings(bindings []ModuleBinding, defaultModule string) []ModuleBinding {
+	if len(bindings) == 0 {
+		return nil
+	}
+
+	resolved := make([]ModuleBinding, 0, len(bindings))
+	for _, binding := range bindings {
+		resolvedBinding := resolveBinding(binding, defaultModule)
+		resolved = append(resolved, resolvedBinding)
+	}
+	return resolved
+}
+
+func cloneOptions(options map[string]any) map[string]any {
+	if len(options) == 0 {
+		return nil
+	}
+
+	copied := make(map[string]any, len(options))
+	for key, value := range options {
+		copied[key] = value
+	}
+	return copied
+}
+
+func selectedArtifactLanes(pipelineID string, artifacts map[string]ArtifactLaneProfile, options ResolveOptions) (map[string]ArtifactLaneProfile, []string, error) {
+	lanesByID := make(map[string]ArtifactLaneProfile, len(artifacts))
+	for rawLaneID, lane := range artifacts {
+		laneID := strings.TrimSpace(rawLaneID)
+		if laneID == "" {
+			return nil, nil, fmt.Errorf("pipeline %q artifact lane id must not be empty", pipelineID)
+		}
+		if _, ok := lanesByID[laneID]; ok {
+			return nil, nil, fmt.Errorf("pipeline %q artifact lane %q is duplicated after trimming", pipelineID, laneID)
+		}
+		lanesByID[laneID] = lane
+	}
+
+	if len(options.Only) == 0 {
+		keys := make([]string, 0, len(lanesByID))
+		for laneID := range lanesByID {
+			keys = append(keys, laneID)
+		}
+		sort.Strings(keys)
+		return lanesByID, keys, nil
+	}
+
+	selected := make(map[string]struct{}, len(options.Only))
+	for _, rawLaneID := range options.Only {
+		laneID := strings.TrimSpace(rawLaneID)
+		if laneID == "" {
+			return nil, nil, fmt.Errorf("pipeline %q selected artifact lane id must not be empty", pipelineID)
+		}
+		if _, ok := lanesByID[laneID]; !ok {
+			return nil, nil, fmt.Errorf("pipeline %q selected artifact lane %q is not declared", pipelineID, laneID)
+		}
+		selected[laneID] = struct{}{}
+	}
+
+	keys := make([]string, 0, len(selected))
+	for laneID := range selected {
+		keys = append(keys, laneID)
+	}
+	sort.Strings(keys)
+	return lanesByID, keys, nil
+}
+
+func resolvedPipelineDigest(resolved ResolvedPipeline) (string, error) {
+	withoutDigest := struct {
+		ID            string
+		Input         ModuleBinding
+		Chunk         ModuleBinding
+		ArtifactLanes []ResolvedArtifactLane
+		Output        ModuleBinding
+	}{
+		ID:            resolved.ID,
+		Input:         resolved.Input,
+		Chunk:         resolved.Chunk,
+		ArtifactLanes: resolved.ArtifactLanes,
+		Output:        resolved.Output,
+	}
+	encoded, err := json.Marshal(withoutDigest)
+	if err != nil {
+		return "", err
+	}
+
+	sum := sha256.Sum256(encoded)
+	return "sha256:" + hex.EncodeToString(sum[:]), nil
+}
+
+func inputSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
+	return registrySpec(catalog.Inputs, key)
+}
+
+func chunkerSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
+	return registrySpec(catalog.Chunkers, key)
+}
+
+func extractorSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
+	return registrySpec(catalog.Extractors, key)
+}
+
+func mergerSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
+	return registrySpec(catalog.Mergers, key)
+}
+
+func normalizerSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
+	return registrySpec(catalog.Normalizers, key)
+}
+
+func validatorSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
+	return registrySpec(catalog.Validators, key)
+}
+
+func outputSpec(catalog ModuleCatalog, key string) (ModuleSpec, error) {
+	return registrySpec(catalog.Outputs, key)
+}
+
+type specRegistry interface {
+	Spec(key string) (ModuleSpec, bool)
+}
+
+func registrySpec(registry specRegistry, key string) (ModuleSpec, error) {
+	if registry == nil {
+		return ModuleSpec{}, fmt.Errorf("module %q is not registered", key)
+	}
+	spec, ok := registry.Spec(key)
+	if !ok {
+		return ModuleSpec{}, fmt.Errorf("module %q is not registered", key)
+	}
+	return spec, nil
+}
+
+func moduleLookupError(pipelineID, laneID string, stage ModuleStage, module string, err error) error {
+	if laneID != "" {
+		return fmt.Errorf("pipeline %q lane %q %s module %q: %w", pipelineID, laneID, stage, module, err)
+	}
+	return fmt.Errorf("pipeline %q %s module %q: %w", pipelineID, stage, module, err)
+}
+
+func capabilityError(pipelineID, laneID string, stage ModuleStage, module, capability string) error {
+	if laneID != "" {
+		return fmt.Errorf("pipeline %q lane %q %s module %q requires missing capability %q", pipelineID, laneID, stage, module, capability)
+	}
+	return fmt.Errorf("pipeline %q %s module %q requires missing capability %q", pipelineID, stage, module, capability)
+}
+
+type capabilitySet map[string]struct{}
+
+func newCapabilitySet() capabilitySet {
+	return make(capabilitySet)
+}
+
+func (set capabilitySet) clone() capabilitySet {
+	copied := make(capabilitySet, len(set))
+	for capability := range set {
+		copied[capability] = struct{}{}
+	}
+	return copied
+}
+
+func (set capabilitySet) add(values ...string) {
+	for _, value := range values {
+		set[value] = struct{}{}
+	}
+}
+
+func (set capabilitySet) addSet(other capabilitySet) {
+	for value := range other {
+		set[value] = struct{}{}
+	}
+}
+
+func (set capabilitySet) missing(required []string) (string, bool) {
+	for _, capability := range required {
+		if _, ok := set[capability]; !ok {
+			return capability, true
+		}
+	}
+	return "", false
+}

internal/framework/pipeline/profile_test.go

@@ -0,0 +1,630 @@
+package pipeline
+
+import (
+	"context"
+	"encoding/json"
+	"reflect"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func TestResolvePipelineWithExplicitModules(t *testing.T) {
+	catalog := newProfileCatalog(t)
+	registerProfileSpecs(t, catalog,
+		ModuleSpec{Key: "window", Stage: StageChunk, Requires: []string{"source"}, Provides: []string{"chunk"}},
+		ModuleSpec{Key: "record-extractor", Stage: StageExtract, Requires: []string{"chunk"}, Provides: []string{"candidate"}},
+		ModuleSpec{Key: "dedupe", Stage: StageMerge, Requires: []string{"candidate"}, Provides: []string{"merged"}},
+		ModuleSpec{Key: "canonical", Stage: StageNormalize, Requires: []string{"merged"}, Provides: []string{"normalized"}},
+		ModuleSpec{Key: "schema-check", Stage: StageValidate, Requires: []string{"normalized"}, Provides: []string{"validated"}},
+		ModuleSpec{Key: "ndjson", Stage: StageOutput, Requires: []string{"validated"}, Provides: []string{"encoded"}},
+	)
+
+	resolved, err := ResolvePipeline(PipelineProfile{
+		ID:    " campaign ",
+		Input: ModuleBinding{Module: " text ", LLMProfile: " fast "},
+		Chunk: ModuleBinding{Module: " window ", Options: map[string]any{
+			"size": 10,
+		}},
+		Artifacts: map[string]ArtifactLaneProfile{
+			" records ": {
+				Extract:    ModuleBinding{Module: " record-extractor ", LLMProfile: " careful "},
+				Merge:      Binding(" dedupe "),
+				Normalize:  Binding(" canonical "),
+				Validators: []ModuleBinding{Binding(" schema-check ")},
+			},
+		},
+		Output: Binding(" ndjson "),
+	}, ResolveOptions{}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	if resolved.ID != "campaign" {
+		t.Fatalf("ID = %q, want campaign", resolved.ID)
+	}
+	if !reflect.DeepEqual(resolved.Input, ModuleBinding{Module: "text", LLMProfile: "fast"}) {
+		t.Fatalf("Input = %#v, want trimmed explicit input", resolved.Input)
+	}
+	if resolved.Chunk.Module != "window" || resolved.Chunk.LLMProfile != DefaultLLMProfile {
+		t.Fatalf("Chunk = %#v, want explicit module and default LLM profile", resolved.Chunk)
+	}
+	if resolved.Chunk.Options["size"] != 10 {
+		t.Fatalf("Chunk.Options = %#v, want size option", resolved.Chunk.Options)
+	}
+	if len(resolved.ArtifactLanes) != 1 {
+		t.Fatalf("len(ArtifactLanes) = %d, want 1", len(resolved.ArtifactLanes))
+	}
+	lane := resolved.ArtifactLanes[0]
+	if lane.ID != "records" {
+		t.Fatalf("lane.ID = %q, want records", lane.ID)
+	}
+	if !reflect.DeepEqual(lane.Extract, ModuleBinding{Module: "record-extractor", LLMProfile: "careful"}) {
+		t.Fatalf("lane.Extract = %#v, want explicit extractor", lane.Extract)
+	}
+	if lane.Merge.Module != "dedupe" || lane.Normalize.Module != "canonical" {
+		t.Fatalf("lane merge/normalize = %#v/%#v, want explicit modules", lane.Merge, lane.Normalize)
+	}
+	if len(lane.Validators) != 1 || lane.Validators[0].Module != "schema-check" {
+		t.Fatalf("lane.Validators = %#v, want schema-check", lane.Validators)
+	}
+	if resolved.Output.Module != "ndjson" {
+		t.Fatalf("Output.Module = %q, want ndjson", resolved.Output.Module)
+	}
+	if !strings.HasPrefix(resolved.Digest, "sha256:") {
+		t.Fatalf("Digest = %q, want sha256 digest", resolved.Digest)
+	}
+}
+
+func TestResolvePipelineAppliesDefaults(t *testing.T) {
+	resolved, err := ResolvePipeline(PipelineProfile{
+		ID:    "defaulted",
+		Input: Binding("text"),
+		Artifacts: map[string]ArtifactLaneProfile{
+			"events": {Extract: Binding("event-extractor")},
+		},
+	}, ResolveOptions{}, newProfileCatalog(t))
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	if resolved.Input.LLMProfile != DefaultLLMProfile {
+		t.Fatalf("Input.LLMProfile = %q, want %q", resolved.Input.LLMProfile, DefaultLLMProfile)
+	}
+	if !reflect.DeepEqual(resolved.Chunk, ModuleBinding{Module: DefaultChunkModule, LLMProfile: DefaultLLMProfile}) {
+		t.Fatalf("Chunk = %#v, want default chunk binding", resolved.Chunk)
+	}
+	if !reflect.DeepEqual(resolved.Output, ModuleBinding{Module: DefaultOutputModule, LLMProfile: DefaultLLMProfile}) {
+		t.Fatalf("Output = %#v, want default output binding", resolved.Output)
+	}
+	lane := resolved.ArtifactLanes[0]
+	if !reflect.DeepEqual(lane.Merge, ModuleBinding{Module: DefaultMergeModule, LLMProfile: DefaultLLMProfile}) {
+		t.Fatalf("Merge = %#v, want default merge binding", lane.Merge)
+	}
+	if !reflect.DeepEqual(lane.Normalize, ModuleBinding{Module: DefaultNormalizeModule, LLMProfile: DefaultLLMProfile}) {
+		t.Fatalf("Normalize = %#v, want default normalize binding", lane.Normalize)
+	}
+	if lane.Extract.LLMProfile != DefaultLLMProfile {
+		t.Fatalf("Extract.LLMProfile = %q, want %q", lane.Extract.LLMProfile, DefaultLLMProfile)
+	}
+}
+
+func TestResolvePipelineSelectsOnlyRequestedLanes(t *testing.T) {
+	profile := multiLaneProfile()
+	resolved, err := ResolvePipeline(profile, ResolveOptions{Only: []string{" summaries ", "events", "summaries"}}, newProfileCatalog(t))
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	got := laneIDs(resolved.ArtifactLanes)
+	want := []string{"events", "summaries"}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("lane IDs = %#v, want %#v", got, want)
+	}
+}
+
+func TestResolvePipelineRejectsUnknownOnlyLane(t *testing.T) {
+	_, err := ResolvePipeline(multiLaneProfile(), ResolveOptions{Only: []string{"missing"}}, newProfileCatalog(t))
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	assertErrorContains(t, err, "pipeline", "missing", "not declared")
+}
+
+func TestResolvePipelineRejectsEmptyOnlyLane(t *testing.T) {
+	_, err := ResolvePipeline(multiLaneProfile(), ResolveOptions{Only: []string{" \t"}}, newProfileCatalog(t))
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	assertErrorContains(t, err, "pipeline", "artifact lane", "empty")
+}
+
+func TestResolvePipelineRejectsEmptyArtifactSet(t *testing.T) {
+	_, err := ResolvePipeline(PipelineProfile{
+		ID:        "empty",
+		Input:     Binding("text"),
+		Artifacts: map[string]ArtifactLaneProfile{},
+	}, ResolveOptions{}, newProfileCatalog(t))
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	assertErrorContains(t, err, "empty", "artifact lane")
+}
+
+func TestResolvePipelineRejectsEmptyPipelineID(t *testing.T) {
+	_, err := ResolvePipeline(PipelineProfile{
+		ID:    " ",
+		Input: Binding("text"),
+		Artifacts: map[string]ArtifactLaneProfile{
+			"events": {Extract: Binding("event-extractor")},
+		},
+	}, ResolveOptions{}, newProfileCatalog(t))
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	assertErrorContains(t, err, "pipeline id", "empty")
+}
+
+func TestResolvePipelineRejectsMissingInput(t *testing.T) {
+	_, err := ResolvePipeline(PipelineProfile{
+		ID: "missing-input",
+		Artifacts: map[string]ArtifactLaneProfile{
+			"events": {Extract: Binding("event-extractor")},
+		},
+	}, ResolveOptions{}, newProfileCatalog(t))
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	assertErrorContains(t, err, "missing-input", "input", "empty")
+}
+
+func TestResolvePipelineRejectsUnknownModuleKeys(t *testing.T) {
+	tests := []struct {
+		name    string
+		profile PipelineProfile
+		want    []string
+	}{
+		{
+			name: "input",
+			profile: PipelineProfile{
+				ID:    "unknown-input",
+				Input: Binding("missing-input"),
+				Artifacts: map[string]ArtifactLaneProfile{
+					"events": {Extract: Binding("event-extractor")},
+				},
+			},
+			want: []string{"unknown-input", "input", "missing-input"},
+		},
+		{
+			name: "chunk",
+			profile: withProfileChange(func(profile PipelineProfile) PipelineProfile {
+				profile.Chunk = Binding("missing-chunk")
+				return profile
+			}),
+			want: []string{"baseline", "chunk", "missing-chunk"},
+		},
+		{
+			name: "extract",
+			profile: withProfileChange(func(profile PipelineProfile) PipelineProfile {
+				lane := profile.Artifacts["events"]
+				lane.Extract = Binding("missing-extractor")
+				profile.Artifacts["events"] = lane
+				return profile
+			}),
+			want: []string{"baseline", "events", "extract", "missing-extractor"},
+		},
+		{
+			name: "merge",
+			profile: withProfileChange(func(profile PipelineProfile) PipelineProfile {
+				lane := profile.Artifacts["events"]
+				lane.Merge = Binding("missing-merge")
+				profile.Artifacts["events"] = lane
+				return profile
+			}),
+			want: []string{"baseline", "events", "merge", "missing-merge"},
+		},
+		{
+			name: "normalize",
+			profile: withProfileChange(func(profile PipelineProfile) PipelineProfile {
+				lane := profile.Artifacts["events"]
+				lane.Normalize = Binding("missing-normalize")
+				profile.Artifacts["events"] = lane
+				return profile
+			}),
+			want: []string{"baseline", "events", "normalize", "missing-normalize"},
+		},
+		{
+			name: "validate",
+			profile: withProfileChange(func(profile PipelineProfile) PipelineProfile {
+				lane := profile.Artifacts["events"]
+				lane.Validators = []ModuleBinding{Binding("missing-validator")}
+				profile.Artifacts["events"] = lane
+				return profile
+			}),
+			want: []string{"baseline", "events", "validate", "missing-validator"},
+		},
+		{
+			name: "output",
+			profile: withProfileChange(func(profile PipelineProfile) PipelineProfile {
+				profile.Output = Binding("missing-output")
+				return profile
+			}),
+			want: []string{"baseline", "output", "missing-output"},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			_, err := ResolvePipeline(test.profile, ResolveOptions{}, newProfileCatalog(t))
+			if err == nil {
+				t.Fatal("ResolvePipeline() error = nil, want error")
+			}
+			assertErrorContains(t, err, test.want...)
+		})
+	}
+}
+
+func TestResolvePipelineRejectsMissingCapabilities(t *testing.T) {
+	tests := []struct {
+		name string
+		spec ModuleSpec
+		want []string
+	}{
+		{
+			name: "input",
+			spec: ModuleSpec{Key: "text", Stage: StageInput, Requires: []string{"raw"}},
+			want: []string{"baseline", "input", "text", "raw"},
+		},
+		{
+			name: "chunk",
+			spec: ModuleSpec{Key: "generic", Stage: StageChunk, Requires: []string{"missing"}},
+			want: []string{"baseline", "chunk", "generic", "missing"},
+		},
+		{
+			name: "extract",
+			spec: ModuleSpec{Key: "event-extractor", Stage: StageExtract, Requires: []string{"missing"}},
+			want: []string{"baseline", "events", "extract", "event-extractor", "missing"},
+		},
+		{
+			name: "merge",
+			spec: ModuleSpec{Key: "appendorder", Stage: StageMerge, Requires: []string{"missing"}},
+			want: []string{"baseline", "events", "merge", "appendorder", "missing"},
+		},
+		{
+			name: "normalize",
+			spec: ModuleSpec{Key: "noop", Stage: StageNormalize, Requires: []string{"missing"}},
+			want: []string{"baseline", "events", "normalize", "noop", "missing"},
+		},
+		{
+			name: "validate",
+			spec: ModuleSpec{Key: "grounded", Stage: StageValidate, Requires: []string{"missing"}},
+			want: []string{"baseline", "events", "validate", "grounded", "missing"},
+		},
+		{
+			name: "output",
+			spec: ModuleSpec{Key: "json", Stage: StageOutput, Requires: []string{"missing"}},
+			want: []string{"baseline", "output", "json", "missing"},
+		},
+	}
+
+	for _, test := range tests {
+		t.Run(test.name, func(t *testing.T) {
+			catalog := newProfileCatalogWithOverride(t, test.spec)
+			profile := baselineProfile()
+			lane := profile.Artifacts["events"]
+			lane.Validators = []ModuleBinding{Binding("grounded")}
+			profile.Artifacts["events"] = lane
+
+			_, err := ResolvePipeline(profile, ResolveOptions{}, catalog)
+			if err == nil {
+				t.Fatal("ResolvePipeline() error = nil, want error")
+			}
+			assertErrorContains(t, err, test.want...)
+		})
+	}
+}
+
+func TestResolvePipelineOrdersLanesDeterministically(t *testing.T) {
+	resolved, err := ResolvePipeline(multiLaneProfile(), ResolveOptions{}, newProfileCatalog(t))
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	got := laneIDs(resolved.ArtifactLanes)
+	want := []string{"events", "notes", "summaries"}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("lane IDs = %#v, want %#v", got, want)
+	}
+}
+
+func TestResolvePipelineDigestIsDeterministicForEquivalentMaps(t *testing.T) {
+	left := PipelineProfile{
+		ID:     "digest",
+		Input:  Binding("text"),
+		Output: Binding("json"),
+		Chunk:  ModuleBinding{Module: "generic", Options: map[string]any{"b": 2, "a": 1}},
+		Artifacts: map[string]ArtifactLaneProfile{
+			"events": {Extract: Binding("event-extractor")},
+			"notes":  {Extract: Binding("note-extractor")},
+		},
+	}
+	right := PipelineProfile{
+		ID:     "digest",
+		Input:  Binding("text"),
+		Output: Binding("json"),
+		Chunk:  ModuleBinding{Module: "generic", Options: map[string]any{"a": 1, "b": 2}},
+		Artifacts: map[string]ArtifactLaneProfile{
+			"notes":  {Extract: Binding("note-extractor")},
+			"events": {Extract: Binding("event-extractor")},
+		},
+	}
+
+	leftResolved, err := ResolvePipeline(left, ResolveOptions{}, newProfileCatalog(t))
+	if err != nil {
+		t.Fatalf("ResolvePipeline(left) error = %v, want nil", err)
+	}
+	rightResolved, err := ResolvePipeline(right, ResolveOptions{}, newProfileCatalog(t))
+	if err != nil {
+		t.Fatalf("ResolvePipeline(right) error = %v, want nil", err)
+	}
+
+	if leftResolved.Digest != rightResolved.Digest {
+		t.Fatalf("digests differ for equivalent profiles: %q != %q", leftResolved.Digest, rightResolved.Digest)
+	}
+}
+
+func TestResolvePipelineDigestChangesWhenBindingChanges(t *testing.T) {
+	left := baselineProfile()
+	right := baselineProfile()
+	right.Chunk = Binding("window")
+	catalog := newProfileCatalog(t)
+	registerProfileSpecs(t, catalog, ModuleSpec{Key: "window", Stage: StageChunk, Requires: []string{"source"}, Provides: []string{"chunk"}})
+
+	leftResolved, err := ResolvePipeline(left, ResolveOptions{}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline(left) error = %v, want nil", err)
+	}
+	rightResolved, err := ResolvePipeline(right, ResolveOptions{}, catalog)
+	if err != nil {
+		t.Fatalf("ResolvePipeline(right) error = %v, want nil", err)
+	}
+
+	if leftResolved.Digest == rightResolved.Digest {
+		t.Fatalf("digest = %q for both profiles, want changed digest", leftResolved.Digest)
+	}
+}
+
+func TestBindingTrimsModuleAndLeavesResolutionFieldsEmpty(t *testing.T) {
+	binding := Binding(" module ")
+	if binding.Module != "module" {
+		t.Fatalf("Module = %q, want module", binding.Module)
+	}
+	if binding.LLMProfile != "" {
+		t.Fatalf("LLMProfile = %q, want empty", binding.LLMProfile)
+	}
+	if binding.Options != nil {
+		t.Fatalf("Options = %#v, want nil", binding.Options)
+	}
+}
+
+func TestResolvedPipelineDigestExcludesDigestField(t *testing.T) {
+	resolved, err := ResolvePipeline(baselineProfile(), ResolveOptions{}, newProfileCatalog(t))
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+	changed := resolved
+	changed.Digest = "sha256:changed"
+
+	leftDigest, err := resolvedPipelineDigest(resolved)
+	if err != nil {
+		t.Fatalf("resolvedPipelineDigest(resolved) error = %v, want nil", err)
+	}
+	rightDigest, err := resolvedPipelineDigest(changed)
+	if err != nil {
+		t.Fatalf("resolvedPipelineDigest(changed) error = %v, want nil", err)
+	}
+	if leftDigest != rightDigest {
+		t.Fatalf("digest with changed digest field = %q, want %q", rightDigest, leftDigest)
+	}
+}
+
+func baselineProfile() PipelineProfile {
+	return PipelineProfile{
+		ID:    "baseline",
+		Input: Binding("text"),
+		Artifacts: map[string]ArtifactLaneProfile{
+			"events": {Extract: Binding("event-extractor")},
+		},
+	}
+}
+
+func multiLaneProfile() PipelineProfile {
+	profile := baselineProfile()
+	profile.ID = "multi"
+	profile.Artifacts = map[string]ArtifactLaneProfile{
+		"summaries": {Extract: Binding("note-extractor")},
+		"events":    {Extract: Binding("event-extractor")},
+		"notes":     {Extract: Binding("note-extractor")},
+	}
+	return profile
+}
+
+func withProfileChange(change func(PipelineProfile) PipelineProfile) PipelineProfile {
+	return change(baselineProfile())
+}
+
+func laneIDs(lanes []ResolvedArtifactLane) []string {
+	ids := make([]string, 0, len(lanes))
+	for _, lane := range lanes {
+		ids = append(ids, lane.ID)
+	}
+	return ids
+}
+
+func assertErrorContains(t *testing.T, err error, values ...string) {
+	t.Helper()
+
+	message := err.Error()
+	for _, value := range values {
+		if !strings.Contains(message, value) {
+			t.Fatalf("error = %q, want substring %q", message, value)
+		}
+	}
+}
+
+func newProfileCatalog(t *testing.T) ModuleCatalog {
+	t.Helper()
+
+	catalog := emptyProfileCatalog()
+	registerProfileSpecs(t, catalog, defaultProfileSpecs()...)
+	return catalog
+}
+
+func newProfileCatalogWithOverride(t *testing.T, override ModuleSpec) ModuleCatalog {
+	t.Helper()
+
+	specs := defaultProfileSpecs()
+	for index, spec := range specs {
+		if spec.Stage == override.Stage && spec.Key == override.Key {
+			specs[index] = override
+			catalog := emptyProfileCatalog()
+			registerProfileSpecs(t, catalog, specs...)
+			return catalog
+		}
+	}
+
+	catalog := emptyProfileCatalog()
+	registerProfileSpecs(t, catalog, specs...)
+	registerProfileSpecs(t, catalog, override)
+	return catalog
+}
+
+func emptyProfileCatalog() ModuleCatalog {
+	return ModuleCatalog{
+		Inputs:      NewInputAdapterRegistry(),
+		Chunkers:    NewChunkerRegistry(),
+		Extractors:  NewExtractorRegistry(),
+		Mergers:     NewMergerRegistry(),
+		Normalizers: NewNormalizerRegistry(),
+		Validators:  NewValidatorRegistry(),
+		Outputs:     NewOutputEncoderRegistry(),
+	}
+}
+
+func defaultProfileSpecs() []ModuleSpec {
+	return []ModuleSpec{
+		ModuleSpec{Key: "text", Stage: StageInput, Provides: []string{"source"}},
+		ModuleSpec{Key: "generic", Stage: StageChunk, Requires: []string{"source"}, Provides: []string{"chunk"}},
+		ModuleSpec{Key: "event-extractor", Stage: StageExtract, Requires: []string{"chunk"}, Provides: []string{"candidate"}},
+		ModuleSpec{Key: "note-extractor", Stage: StageExtract, Requires: []string{"chunk"}, Provides: []string{"candidate"}},
+		ModuleSpec{Key: "appendorder", Stage: StageMerge, Requires: []string{"candidate"}, Provides: []string{"merged"}},
+		ModuleSpec{Key: "noop", Stage: StageNormalize, Requires: []string{"merged"}, Provides: []string{"normalized"}},
+		ModuleSpec{Key: "grounded", Stage: StageValidate, Requires: []string{"normalized"}, Provides: []string{"validated"}},
+		ModuleSpec{Key: "json", Stage: StageOutput, Requires: []string{"normalized"}, Provides: []string{"encoded"}},
+	}
+}
+
+func registerProfileSpecs(t *testing.T, catalog ModuleCatalog, specs ...ModuleSpec) {
+	t.Helper()
+
+	for _, spec := range specs {
+		switch spec.Stage {
+		case StageInput:
+			if err := catalog.Inputs.RegisterWithSpec(spec, profileInputConstructor(spec.Key)); err != nil {
+				t.Fatalf("register input spec %#v: %v", spec, err)
+			}
+		case StageChunk:
+			if err := catalog.Chunkers.RegisterWithSpec(spec, profileChunkerConstructor(spec.Key)); err != nil {
+				t.Fatalf("register chunk spec %#v: %v", spec, err)
+			}
+		case StageExtract:
+			if err := catalog.Extractors.RegisterWithSpec(spec, profileExtractorConstructor(spec.Key)); err != nil {
+				t.Fatalf("register extractor spec %#v: %v", spec, err)
+			}
+		case StageMerge:
+			if err := catalog.Mergers.RegisterWithSpec(spec, profileMergerConstructor(spec.Key)); err != nil {
+				t.Fatalf("register merger spec %#v: %v", spec, err)
+			}
+		case StageNormalize:
+			if err := catalog.Normalizers.RegisterWithSpec(spec, profileNormalizerConstructor(spec.Key)); err != nil {
+				t.Fatalf("register normalizer spec %#v: %v", spec, err)
+			}
+		case StageValidate:
+			if err := catalog.Validators.RegisterWithSpec(spec, profileValidatorConstructor(spec.Key)); err != nil {
+				t.Fatalf("register validator spec %#v: %v", spec, err)
+			}
+		case StageOutput:
+			if err := catalog.Outputs.RegisterWithSpec(spec, profileOutputConstructor(spec.Key)); err != nil {
+				t.Fatalf("register output spec %#v: %v", spec, err)
+			}
+		default:
+			t.Fatalf("unsupported spec stage %q", spec.Stage)
+		}
+	}
+}
+
+func profileInputConstructor(key string) InputAdapterConstructor {
+	return func() (contracts.InputAdapter, error) {
+		return profileInputAdapter{key: key}, nil
+	}
+}
+
+type profileInputAdapter struct {
+	key string
+}
+
+func (adapter profileInputAdapter) Key() string {
+	return adapter.key
+}
+
+func (adapter profileInputAdapter) Parse(ctx context.Context, req contracts.ParseRequest) (*source.SourceDocument, error) {
+	return &source.SourceDocument{}, nil
+}
+
+func profileChunkerConstructor(key string) ChunkerConstructor {
+	return func() (contracts.Chunker, error) {
+		return registryChunker{key: key}, nil
+	}
+}
+
+func profileExtractorConstructor(key string) ExtractorConstructor {
+	return func() (contracts.Extractor, error) {
+		return registryFakeExtractor{key: key}, nil
+	}
+}
+
+func profileMergerConstructor(key string) MergerConstructor {
+	return func() (contracts.Merger, error) {
+		return registryMerger{key: key}, nil
+	}
+}
+
+func profileNormalizerConstructor(key string) NormalizerConstructor {
+	return func() (contracts.Normalizer, error) {
+		return registryNormalizer{key: key}, nil
+	}
+}
+
+func profileValidatorConstructor(key string) ValidatorConstructor {
+	return func() (contracts.Validator, error) {
+		return registryValidator{name: key}, nil
+	}
+}
+
+func profileOutputConstructor(key string) OutputEncoderConstructor {
+	return func() (contracts.OutputEncoder, error) {
+		return registryOutputEncoder{key: key}, nil
+	}
+}
+
+func TestResolvedPipelineCanMarshalToCanonicalJSON(t *testing.T) {
+	resolved, err := ResolvePipeline(baselineProfile(), ResolveOptions{}, newProfileCatalog(t))
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+	if _, err := json.Marshal(resolved); err != nil {
+		t.Fatalf("json.Marshal(resolved) error = %v, want nil", err)
+	}
+}

internal/framework/pipeline/registry_integration_test.go

@@ -12,54 +12,128 @@ import (
 	validate "gitea.maximumdirect.net/eric/notarius/internal/framework/validate"
 )
 
-func TestRunnerUsesExtractorRegistry(t *testing.T) {
+func TestRunnerUsesRegistries(t *testing.T) {
-	var builtKeys []string
+	var built []string
-	var executedKeys []string
+	var executed []string
-	registry := NewExtractorRegistry()
+	registries := integrationRegistries(t, &built, &executed)
 
-	registerIntegrationExtractor(t, registry, "second", &builtKeys, &executedKeys, []contracts.Validator{
+	output, err := New(registries).Run(context.Background(), RunInput{
-		integrationValidator{name: "reject-second", approve: false},
+		Pipeline: integrationPipeline(),
-	})
+		SourceID: "source-1",
-	registerIntegrationExtractor(t, registry, "first", &builtKeys, &executedKeys, []contracts.Validator{
+		RawInput: []byte("source text"),
-		integrationValidator{name: "approve-first", approve: true},
-	})
-
-	output, err := New(registry).Run(context.Background(), RunInput{
-		Source:        integrationSourceDocument(),
-		ExtractorKeys: []string{"second", "first"},
 	})
 	if err != nil {
 		t.Fatalf("Run() error = %v, want nil", err)
 	}
 
-	if !reflect.DeepEqual(builtKeys, []string{"second", "first"}) {
+	wantBuilt := []string{"input", "chunk", "extract-first", "merge", "normalize", "extract-second", "merge", "normalize", "output"}
-		t.Fatalf("built keys = %#v, want configured order", builtKeys)
+	if !reflect.DeepEqual(built, wantBuilt) {
+		t.Fatalf("built = %#v, want %#v", built, wantBuilt)
 	}
-	if !reflect.DeepEqual(executedKeys, []string{"second", "first"}) {
+	if !reflect.DeepEqual(executed, []string{"extract-first:chunk-0", "extract-second:chunk-0"}) {
-		t.Fatalf("executed keys = %#v, want configured order", executedKeys)
+		t.Fatalf("executed = %#v, want extractor chunk execution", executed)
 	}
-	if got := artifactKeys(output.Approved); !reflect.DeepEqual(got, []string{"first"}) {
+	if got := artifactKeys(output.Approved); !reflect.DeepEqual(got, []string{"extract-first"}) {
-		t.Fatalf("approved keys = %#v, want [first]", got)
+		t.Fatalf("approved keys = %#v, want [extract-first]", got)
 	}
-	if got := rejectedKeys(output.Rejected); !reflect.DeepEqual(got, []string{"second"}) {
+	if got := rejectedKeys(output.Rejected); !reflect.DeepEqual(got, []string{"extract-second"}) {
-		t.Fatalf("rejected keys = %#v, want [second]", got)
+		t.Fatalf("rejected keys = %#v, want [extract-second]", got)
 	}
 }
 
-func registerIntegrationExtractor(t *testing.T, registry *ExtractorRegistry, key string, builtKeys *[]string, executedKeys *[]string, validators []contracts.Validator) {
+func integrationRegistries(t *testing.T, built, executed *[]string) Registries {
+	t.Helper()
+
+	registries := Registries{
+		Inputs:      NewInputAdapterRegistry(),
+		Chunkers:    NewChunkerRegistry(),
+		Extractors:  NewExtractorRegistry(),
+		Mergers:     NewMergerRegistry(),
+		Normalizers: NewNormalizerRegistry(),
+		Outputs:     NewOutputEncoderRegistry(),
+	}
+	if err := registries.Inputs.Register("input", func() (contracts.InputAdapter, error) {
+		*built = append(*built, "input")
+		return integrationInput{}, nil
+	}); err != nil {
+		t.Fatalf("register input: %v", err)
+	}
+	if err := registries.Chunkers.Register("chunk", func() (contracts.Chunker, error) {
+		*built = append(*built, "chunk")
+		return integrationChunker{}, nil
+	}); err != nil {
+		t.Fatalf("register chunker: %v", err)
+	}
+	registerIntegrationExtractor(t, registries.Extractors, "extract-first", built, executed, []contracts.Validator{
+		integrationValidator{name: "approve-first", approve: true},
+	})
+	registerIntegrationExtractor(t, registries.Extractors, "extract-second", built, executed, []contracts.Validator{
+		integrationValidator{name: "reject-second", approve: false},
+	})
+	if err := registries.Mergers.Register("merge", func() (contracts.Merger, error) {
+		*built = append(*built, "merge")
+		return integrationMerger{}, nil
+	}); err != nil {
+		t.Fatalf("register merger: %v", err)
+	}
+	if err := registries.Normalizers.Register("normalize", func() (contracts.Normalizer, error) {
+		*built = append(*built, "normalize")
+		return integrationNormalizer{}, nil
+	}); err != nil {
+		t.Fatalf("register normalizer: %v", err)
+	}
+	if err := registries.Outputs.Register("output", func() (contracts.OutputEncoder, error) {
+		*built = append(*built, "output")
+		return integrationOutput{}, nil
+	}); err != nil {
+		t.Fatalf("register output: %v", err)
+	}
+	return registries
+}
+
+func registerIntegrationExtractor(t *testing.T, registry *ExtractorRegistry, key string, built, executed *[]string, validators []contracts.Validator) {
 	t.Helper()
 
 	if err := registry.Register(key, func() (contracts.Extractor, error) {
-		*builtKeys = append(*builtKeys, key)
+		*built = append(*built, key)
-		return integrationExtractor{key: key, executedKeys: executedKeys, validators: validators}, nil
+		return integrationExtractor{key: key, executed: executed, validators: validators}, nil
 	}); err != nil {
 		t.Fatalf("Register(%q) error = %v, want nil", key, err)
 	}
 }
 
+type integrationInput struct{}
+
+func (input integrationInput) Key() string {
+	return "input"
+}
+
+func (input integrationInput) Parse(ctx context.Context, req contracts.ParseRequest) (*source.SourceDocument, error) {
+	return integrationSourceDocument(), nil
+}
+
+type integrationChunker struct{}
+
+func (chunker integrationChunker) Key() string {
+	return "chunk"
+}
+
+func (chunker integrationChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
+	return contracts.ChunkResult{
+		Chunks: []contracts.SourceChunk{
+			{
+				ID:       "chunk-0",
+				SourceID: req.Source.ID,
+				Index:    0,
+				Units:    req.Source.Units,
+			},
+		},
+	}, nil
+}
+
 type integrationExtractor struct {
 	key        string
-	executedKeys *[]string
+	executed   *[]string
 	validators []contracts.Validator
 }
 
@@ -80,7 +154,7 @@ func (extractor integrationExtractor) Validators() []contracts.Validator {
 }
 
 func (extractor integrationExtractor) Extract(ctx context.Context, req contracts.ExtractionRequest) (contracts.ExtractionResult, error) {
-	*extractor.executedKeys = append(*extractor.executedKeys, extractor.key)
+	*extractor.executed = append(*extractor.executed, extractor.key+":"+req.Chunk.ID)
 	return contracts.ExtractionResult{
 		Candidates: []artifacts.ArtifactCandidate{
 			{Payload: []byte(`{"value":true}`)},
@@ -88,6 +162,40 @@ func (extractor integrationExtractor) Extract(ctx context.Context, req contracts
 	}, nil
 }
 
+type integrationNormalizer struct{}
+
+type integrationMerger struct{}
+
+func (merger integrationMerger) Key() string {
+	return "merge"
+}
+
+func (merger integrationMerger) Merge(ctx context.Context, req contracts.MergeRequest) (contracts.MergeResult, error) {
+	var candidates []artifacts.ArtifactCandidate
+	for _, chunkArtifacts := range req.ChunkArtifacts {
+		candidates = append(candidates, chunkArtifacts.Candidates...)
+	}
+	return contracts.MergeResult{Candidates: candidates}, nil
+}
+
+func (normalizer integrationNormalizer) Key() string {
+	return "normalize"
+}
+
+func (normalizer integrationNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
+	return contracts.NormalizeResult{Candidates: req.Candidates}, nil
+}
+
+type integrationOutput struct{}
+
+func (output integrationOutput) Key() string {
+	return "output"
+}
+
+func (output integrationOutput) Encode(ctx context.Context, req contracts.OutputRequest) (contracts.OutputResult, error) {
+	return contracts.OutputResult{Bytes: []byte(`{}`), ContentType: "application/json"}, nil
+}
+
 type integrationValidator struct {
 	name    string
 	approve bool
@@ -112,6 +220,30 @@ func (validator integrationValidator) Validate(ctx context.Context, req contract
 	}, nil
 }
 
+func integrationPipeline() ResolvedPipeline {
+	return ResolvedPipeline{
+		ID:     "pipeline-1",
+		Digest: "sha256:pipeline",
+		Input:  Binding("input"),
+		Chunk:  Binding("chunk"),
+		ArtifactLanes: []ResolvedArtifactLane{
+			{
+				ID:        "first",
+				Extract:   Binding("extract-first"),
+				Merge:     Binding("merge"),
+				Normalize: Binding("normalize"),
+			},
+			{
+				ID:        "second",
+				Extract:   Binding("extract-second"),
+				Merge:     Binding("merge"),
+				Normalize: Binding("normalize"),
+			},
+		},
+		Output: Binding("output"),
+	}
+}
+
 func integrationSourceDocument() *source.SourceDocument {
 	return &source.SourceDocument{
 		ID:     "source-1",

internal/framework/pipeline/runner.go

@@ -10,29 +10,40 @@ import (
 	"gitea.maximumdirect.net/eric/notarius/internal/framework/validate"
 )
 
-type ExtractorFactory interface {
+type Registries struct {
-	Build(key string) (contracts.Extractor, error)
+	Inputs      *InputAdapterRegistry
+	Chunkers    *ChunkerRegistry
+	Extractors  *ExtractorRegistry
+	Mergers     *MergerRegistry
+	Normalizers *NormalizerRegistry
+	Validators  *ValidatorRegistry
+	Outputs     *OutputEncoderRegistry
 }
 
 type Runner struct {
-	extractors ExtractorFactory
+	registries Registries
 }
 
-func New(extractors ExtractorFactory) *Runner {
+func New(registries Registries) *Runner {
-	return &Runner{extractors: extractors}
+	return &Runner{registries: registries}
 }
 
 type RunInput struct {
-	Source        *source.SourceDocument
+	Pipeline  ResolvedPipeline
-	ExtractorKeys []string
+	SourceID  string
+	Path      string
+	RawInput  []byte
 	LLMClient contracts.StructuredLLMClient
 	Metadata  map[string]any
 }
 
 type RunOutput struct {
+	Manifest      artifacts.RunManifest        `json:"manifest"`
 	Approved      []artifacts.Artifact         `json:"approved,omitempty"`
 	Rejected      []artifacts.RejectedArtifact `json:"rejected,omitempty"`
 	Warnings      []contracts.Warning          `json:"warnings,omitempty"`
+	EncodedOutput []byte                       `json:"-"`
+	ContentType   string                       `json:"content_type,omitempty"`
 }
 
 func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
@@ -40,54 +51,283 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
 	if r == nil {
 		return output, fmt.Errorf("runner must not be nil")
 	}
-	if r.extractors == nil {
+	if err := validateRunInput(input); err != nil {
-		return output, fmt.Errorf("runner extractor factory must not be nil")
+		return output, err
 	}
-	if err := source.ValidateDocument(input.Source); err != nil {
+	if err := r.validateRegistries(input.Pipeline); err != nil {
-		return output, fmt.Errorf("validate source document: %w", err)
+		return output, err
 	}
-	if len(input.ExtractorKeys) == 0 {
+
-		return output, fmt.Errorf("extractor keys must not be empty")
+	output.Manifest = manifestFromPipeline(input.Pipeline)
+
+	adapter, err := r.registries.Inputs.Build(input.Pipeline.Input.Module)
+	if err != nil {
+		return failOutput(output), fmt.Errorf("build input adapter %q: %w", input.Pipeline.Input.Module, err)
+	}
+	doc, err := adapter.Parse(ctx, contracts.ParseRequest{
+		SourceID: input.SourceID,
+		Path:     input.Path,
+		Raw:      input.RawInput,
+		Metadata: input.Metadata,
+	})
+	if err != nil {
+		return failOutput(output), fmt.Errorf("parse input with adapter %q: %w", adapter.Key(), err)
+	}
+	if err := source.ValidateDocument(doc); err != nil {
+		return failOutput(output), fmt.Errorf("validate source document: %w", err)
+	}
+	output.Manifest.SourceDigests = []string{doc.Digest}
+
+	chunker, err := r.registries.Chunkers.Build(input.Pipeline.Chunk.Module)
+	if err != nil {
+		return failOutput(output), fmt.Errorf("build chunker %q: %w", input.Pipeline.Chunk.Module, err)
+	}
+	chunkResult, err := chunker.Chunk(ctx, contracts.ChunkRequest{
+		Source:   doc,
+		Metadata: input.Metadata,
+	})
+	output.Warnings = append(output.Warnings, chunkResult.Warnings...)
+	if err != nil {
+		return failOutput(output), fmt.Errorf("chunk source with chunker %q: %w", chunker.Key(), err)
+	}
+	if len(chunkResult.Chunks) == 0 {
+		return failOutput(output), fmt.Errorf("chunker %q returned no chunks", chunker.Key())
 	}
 
 	nextCandidateIndex := 0
-	for _, extractorKey := range input.ExtractorKeys {
+	for _, lane := range input.Pipeline.ArtifactLanes {
-		extractor, err := r.extractors.Build(extractorKey)
+		if err := r.runLane(ctx, input, doc, chunkResult.Chunks, lane, &output, &nextCandidateIndex); err != nil {
-		if err != nil {
+			return failOutput(output), err
-			return output, fmt.Errorf("build extractor %q: %w", extractorKey, err)
 		}
-		if extractor == nil {
-			return output, fmt.Errorf("build extractor %q: returned nil extractor", extractorKey)
 	}
 
+	if len(output.Rejected) > 0 {
+		output.Manifest.ValidationStatus = "rejected"
+	} else {
+		output.Manifest.ValidationStatus = "approved"
+	}
+
+	encoder, err := r.registries.Outputs.Build(input.Pipeline.Output.Module)
+	if err != nil {
+		return failOutput(output), fmt.Errorf("build output encoder %q: %w", input.Pipeline.Output.Module, err)
+	}
+	encoded, err := encoder.Encode(ctx, contracts.OutputRequest{
+		Manifest: output.Manifest,
+		Approved: output.Approved,
+		Rejected: output.Rejected,
+		Warnings: output.Warnings,
+		Metadata: input.Metadata,
+	})
+	output.Warnings = append(output.Warnings, encoded.Warnings...)
+	if err != nil {
+		return failOutput(output), fmt.Errorf("encode output with encoder %q: %w", encoder.Key(), err)
+	}
+	output.EncodedOutput = encoded.Bytes
+	output.ContentType = encoded.ContentType
+
+	return output, nil
+}
+
+func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.SourceDocument, chunks []contracts.SourceChunk, lane ResolvedArtifactLane, output *RunOutput, nextCandidateIndex *int) 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)
+	}
+	merger, err := r.registries.Mergers.Build(lane.Merge.Module)
+	if err != nil {
+		return fmt.Errorf("build merger %q for lane %q: %w", lane.Merge.Module, lane.ID, err)
+	}
+	normalizer, err := r.registries.Normalizers.Build(lane.Normalize.Module)
+	if err != nil {
+		return fmt.Errorf("build normalizer %q for lane %q: %w", lane.Normalize.Module, lane.ID, err)
+	}
+
+	var validators []contracts.Validator
+	if len(lane.Validators) > 0 {
+		validators, err = r.buildConfiguredValidators(lane)
+		if err != nil {
+			return err
+		}
+	} else {
+		validators = extractor.Validators()
+	}
+
+	chunkArtifacts := make([]contracts.ChunkArtifacts, 0, len(chunks))
+	for index := range chunks {
+		chunk := chunks[index]
 		result, err := extractor.Extract(ctx, contracts.ExtractionRequest{
-			Source:    input.Source,
+			Source:    doc,
+			Chunk:     &chunk,
 			LLMClient: input.LLMClient,
 			Metadata:  input.Metadata,
 		})
 		output.Warnings = append(output.Warnings, result.Warnings...)
 		if err != nil {
-			return output, fmt.Errorf("extract with extractor %q: %w", extractor.Key(), err)
+			return fmt.Errorf("extract lane %q chunk %q with extractor %q: %w", lane.ID, chunk.ID, extractor.Key(), err)
 		}
 
-		candidates, err := normalizeCandidates(extractor, result.Candidates, &nextCandidateIndex)
+		candidates, err := normalizeCandidates(extractor, result.Candidates, nextCandidateIndex)
 		if err != nil {
-			return output, err
+			return err
+		}
+		chunkArtifacts = append(chunkArtifacts, contracts.ChunkArtifacts{
+			Chunk:      chunk,
+			Candidates: candidates,
+		})
 	}
 
-		approved, rejected, warnings, err := runValidators(ctx, extractor, input.Source, candidates, input.Metadata)
+	mergeResult, err := merger.Merge(ctx, contracts.MergeRequest{
+		Source:         doc,
+		LaneID:         lane.ID,
+		ChunkArtifacts: chunkArtifacts,
+		Metadata:       input.Metadata,
+	})
+	output.Warnings = append(output.Warnings, mergeResult.Warnings...)
+	if err != nil {
+		return fmt.Errorf("merge lane %q with merger %q: %w", lane.ID, merger.Key(), err)
+	}
+
+	normalizeResult, err := normalizer.Normalize(ctx, contracts.NormalizeRequest{
+		Source:     doc,
+		LaneID:     lane.ID,
+		Candidates: mergeResult.Candidates,
+		Metadata:   input.Metadata,
+	})
+	output.Warnings = append(output.Warnings, normalizeResult.Warnings...)
+	if err != nil {
+		return fmt.Errorf("normalize lane %q with normalizer %q: %w", lane.ID, normalizer.Key(), err)
+	}
+
+	approved, rejected, warnings, err := runValidators(ctx, extractor.Key(), validators, doc, normalizeResult.Candidates, input.Metadata)
 	output.Warnings = append(output.Warnings, warnings...)
 	output.Rejected = append(output.Rejected, rejected...)
 	if err != nil {
-			return output, err
+		return err
 	}
 
 	for _, candidate := range approved {
 		output.Approved = append(output.Approved, artifacts.ArtifactFromCandidate(candidate))
 	}
+	return nil
+}
+
+func (r *Runner) buildConfiguredValidators(lane ResolvedArtifactLane) ([]contracts.Validator, error) {
+	validators := make([]contracts.Validator, 0, len(lane.Validators))
+	for _, binding := range lane.Validators {
+		validator, err := r.registries.Validators.Build(binding.Module)
+		if err != nil {
+			return nil, fmt.Errorf("build validator %q for lane %q: %w", binding.Module, lane.ID, err)
+		}
+		validators = append(validators, validator)
+	}
+	return validators, nil
+}
+
+func (r *Runner) validateRegistries(pipeline ResolvedPipeline) error {
+	if r.registries.Inputs == nil {
+		return fmt.Errorf("input registry must not be nil")
+	}
+	if r.registries.Chunkers == nil {
+		return fmt.Errorf("chunker registry must not be nil")
+	}
+	if r.registries.Extractors == nil {
+		return fmt.Errorf("extractor registry must not be nil")
+	}
+	if r.registries.Mergers == nil {
+		return fmt.Errorf("merger registry must not be nil")
+	}
+	if r.registries.Normalizers == nil {
+		return fmt.Errorf("normalizer registry must not be nil")
+	}
+	if r.registries.Outputs == nil {
+		return fmt.Errorf("output encoder registry must not be nil")
+	}
+	if pipelineUsesConfiguredValidators(pipeline) && r.registries.Validators == nil {
+		return fmt.Errorf("validator registry must not be nil")
+	}
+	return nil
+}
+
+func validateRunInput(input RunInput) error {
+	if input.Pipeline.ID == "" {
+		return fmt.Errorf("resolved pipeline id must not be empty")
+	}
+	if input.Pipeline.Digest == "" {
+		return fmt.Errorf("resolved pipeline digest must not be empty")
+	}
+	if input.Pipeline.Input.Module == "" {
+		return fmt.Errorf("resolved pipeline input module must not be empty")
+	}
+	if input.Pipeline.Chunk.Module == "" {
+		return fmt.Errorf("resolved pipeline chunk module must not be empty")
+	}
+	if input.Pipeline.Output.Module == "" {
+		return fmt.Errorf("resolved pipeline output module must not be empty")
+	}
+	if len(input.Pipeline.ArtifactLanes) == 0 {
+		return fmt.Errorf("resolved pipeline artifact lanes must not be empty")
+	}
+	for _, lane := range input.Pipeline.ArtifactLanes {
+		if lane.ID == "" {
+			return fmt.Errorf("resolved pipeline artifact lane id must not be empty")
+		}
+		if lane.Extract.Module == "" {
+			return fmt.Errorf("resolved pipeline lane %q extract module must not be empty", lane.ID)
+		}
+		if lane.Merge.Module == "" {
+			return fmt.Errorf("resolved pipeline lane %q merge module must not be empty", lane.ID)
+		}
+		if lane.Normalize.Module == "" {
+			return fmt.Errorf("resolved pipeline lane %q normalize module must not be empty", lane.ID)
+		}
+		for _, validator := range lane.Validators {
+			if validator.Module == "" {
+				return fmt.Errorf("resolved pipeline lane %q validator module must not be empty", lane.ID)
+			}
+		}
+	}
+	return nil
+}
+
+func manifestFromPipeline(pipeline ResolvedPipeline) artifacts.RunManifest {
+	manifest := artifacts.RunManifest{
+		PipelineID:     pipeline.ID,
+		PipelineDigest: pipeline.Digest,
+		InputModule:    pipeline.Input.Module,
+		Chunker:        pipeline.Chunk.Module,
+		OutputEncoder:  pipeline.Output.Module,
+		ArtifactLanes:  make([]artifacts.ArtifactLaneManifest, 0, len(pipeline.ArtifactLanes)),
 	}
 
-	return output, nil
+	for _, lane := range pipeline.ArtifactLanes {
+		laneManifest := artifacts.ArtifactLaneManifest{
+			ID:         lane.ID,
+			Extractor:  lane.Extract.Module,
+			Merger:     lane.Merge.Module,
+			Normalizer: lane.Normalize.Module,
+		}
+		for _, validator := range lane.Validators {
+			laneManifest.Validators = append(laneManifest.Validators, validator.Module)
+		}
+		manifest.ArtifactLanes = append(manifest.ArtifactLanes, laneManifest)
+	}
+	return manifest
+}
+
+func failOutput(output RunOutput) RunOutput {
+	if output.Manifest.PipelineID != "" {
+		output.Manifest.ValidationStatus = "failed"
+	}
+	return output
+}
+
+func pipelineUsesConfiguredValidators(pipeline ResolvedPipeline) bool {
+	for _, lane := range pipeline.ArtifactLanes {
+		if len(lane.Validators) > 0 {
+			return true
+		}
+	}
+	return false
 }
 
 func normalizeCandidates(extractor contracts.Extractor, candidates []artifacts.ArtifactCandidate, nextIndex *int) ([]artifacts.ArtifactCandidate, error) {
@@ -119,14 +359,14 @@ func normalizeCandidates(extractor contracts.Extractor, candidates []artifacts.A
 	return normalized, nil
 }
 
-func runValidators(ctx context.Context, extractor contracts.Extractor, doc *source.SourceDocument, candidates []artifacts.ArtifactCandidate, metadata map[string]any) ([]artifacts.ArtifactCandidate, []artifacts.RejectedArtifact, []contracts.Warning, error) {
+func runValidators(ctx context.Context, extractorKey string, validators []contracts.Validator, doc *source.SourceDocument, candidates []artifacts.ArtifactCandidate, metadata map[string]any) ([]artifacts.ArtifactCandidate, []artifacts.RejectedArtifact, []contracts.Warning, error) {
 	eligible := candidates
 	var rejected []artifacts.RejectedArtifact
 	var warnings []contracts.Warning
 
-	for validatorIndex, validator := range extractor.Validators() {
+	for validatorIndex, validator := range validators {
 		if validator == nil {
-			return nil, rejected, warnings, fmt.Errorf("extractor %q validator[%d] must not be nil", extractor.Key(), validatorIndex)
+			return nil, rejected, warnings, fmt.Errorf("extractor %q validator[%d] must not be nil", extractorKey, validatorIndex)
 		}
 		result, err := validator.Validate(ctx, contracts.ValidationRequest{
 			Source:     doc,
@@ -135,13 +375,13 @@ func runValidators(ctx context.Context, extractor contracts.Extractor, doc *sour
 		})
 		warnings = append(warnings, result.Warnings...)
 		if err != nil {
-			return nil, rejected, warnings, fmt.Errorf("validate extractor %q with validator %q: %w", extractor.Key(), validator.Name(), err)
+			return nil, rejected, warnings, fmt.Errorf("validate extractor %q with validator %q: %w", extractorKey, validator.Name(), err)
 		}
 		if result.ValidatorName != validator.Name() {
 			return nil, rejected, warnings, fmt.Errorf("validator %q returned result for %q", validator.Name(), result.ValidatorName)
 		}
 		if err := validate.EnforceDecisionCardinality(eligible, result.Decisions); err != nil {
-			return nil, rejected, warnings, fmt.Errorf("validate extractor %q with validator %q: %w", extractor.Key(), validator.Name(), err)
+			return nil, rejected, warnings, fmt.Errorf("validate extractor %q with validator %q: %w", extractorKey, validator.Name(), err)
 		}
 
 		decisions := make(map[int]contracts.ValidationDecision, len(result.Decisions))

internal/framework/pipeline/testdata/walking_skeleton_input.json

@@ -0,0 +1,17 @@
+{
+  "id": "fixture-source",
+  "units": [
+    {
+      "id": "u1",
+      "text": "First event."
+    },
+    {
+      "id": "u2",
+      "text": "Second event."
+    },
+    {
+      "id": "u3",
+      "text": "Third event."
+    }
+  ]
+}

internal/framework/pipeline/testdata/walking_skeleton_output.json

@@ -0,0 +1,51 @@
+{
+  "manifest": {
+    "pipeline_id": "walking-skeleton",
+    "pipeline_digest": "sha256:5df1e501a2307ef75bbfeb59d315b3710571d52e5466a9c7f8320248740e6fca",
+    "validation_status": "approved",
+    "artifact_lanes": [
+      {
+        "id": "events",
+        "extractor": "fake/extract",
+        "merger": "appendorder",
+        "normalizer": "noop"
+      }
+    ]
+  },
+  "approved": [
+    {
+      "extractor_key": "fake/extract",
+      "artifact_type": "fake_event",
+      "schema_version": "v1",
+      "payload": {
+        "chunk_id": "fixture-source:chunk:0",
+        "llm_call": 1,
+        "text": "First event. Second event."
+      },
+      "source_refs": [
+        {
+          "source_id": "fixture-source",
+          "start_unit_id": "u1",
+          "end_unit_id": "u2"
+        }
+      ]
+    },
+    {
+      "extractor_key": "fake/extract",
+      "artifact_type": "fake_event",
+      "schema_version": "v1",
+      "payload": {
+        "chunk_id": "fixture-source:chunk:1",
+        "llm_call": 2,
+        "text": "Third event."
+      },
+      "source_refs": [
+        {
+          "source_id": "fixture-source",
+          "start_unit_id": "u3",
+          "end_unit_id": "u3"
+        }
+      ]
+    }
+  ]
+}

internal/framework/pipeline/validator_registry.go

@@ -0,0 +1,102 @@
+package pipeline
+
+import (
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+type ValidatorConstructor func() (contracts.Validator, error)
+
+type ValidatorRegistry struct {
+	constructors map[string]ValidatorConstructor
+	specs        map[string]ModuleSpec
+}
+
+func NewValidatorRegistry() *ValidatorRegistry {
+	return &ValidatorRegistry{
+		constructors: make(map[string]ValidatorConstructor),
+		specs:        make(map[string]ModuleSpec),
+	}
+}
+
+func (r *ValidatorRegistry) Register(key string, constructor ValidatorConstructor) error {
+	return r.RegisterWithSpec(defaultModuleSpec(key, StageValidate), constructor)
+}
+
+func (r *ValidatorRegistry) RegisterWithSpec(spec ModuleSpec, constructor ValidatorConstructor) error {
+	if r == nil {
+		return fmt.Errorf("validator registry must not be nil")
+	}
+
+	normalizedSpec := normalizeModuleSpec(spec)
+	if err := validateModuleSpec("validator", StageValidate, normalizedSpec); err != nil {
+		return err
+	}
+	if constructor == nil {
+		return fmt.Errorf("validator constructor for %q must not be nil", normalizedSpec.Key)
+	}
+	if _, ok := r.constructors[normalizedSpec.Key]; ok {
+		return fmt.Errorf("validator %q is already registered", normalizedSpec.Key)
+	}
+
+	if r.constructors == nil {
+		r.constructors = make(map[string]ValidatorConstructor)
+	}
+	if r.specs == nil {
+		r.specs = make(map[string]ModuleSpec)
+	}
+	r.constructors[normalizedSpec.Key] = constructor
+	r.specs[normalizedSpec.Key] = cloneModuleSpec(normalizedSpec)
+	return nil
+}
+
+func (r *ValidatorRegistry) Build(key string) (contracts.Validator, error) {
+	if r == nil {
+		return nil, fmt.Errorf("validator registry must not be nil")
+	}
+
+	normalizedKey := strings.TrimSpace(key)
+	if normalizedKey == "" {
+		return nil, fmt.Errorf("validator key must not be empty")
+	}
+
+	constructor, ok := r.constructors[normalizedKey]
+	if !ok {
+		return nil, fmt.Errorf("validator %q is not registered", normalizedKey)
+	}
+
+	validator, err := constructor()
+	if err != nil {
+		return nil, fmt.Errorf("build validator %q: %w", normalizedKey, err)
+	}
+	if validator == nil {
+		return nil, fmt.Errorf("validator %q constructor returned nil", normalizedKey)
+	}
+	if validator.Name() != normalizedKey {
+		return nil, fmt.Errorf("validator %q returned name %q", normalizedKey, validator.Name())
+	}
+
+	return validator, nil
+}
+
+func (r *ValidatorRegistry) Spec(key string) (ModuleSpec, bool) {
+	if r == nil {
+		return ModuleSpec{}, false
+	}
+
+	spec, ok := r.specs[strings.TrimSpace(key)]
+	if !ok {
+		return ModuleSpec{}, false
+	}
+	return cloneModuleSpec(spec), true
+}
+
+func (r *ValidatorRegistry) RegisteredKeys() []string {
+	if r == nil {
+		return nil
+	}
+
+	return sortedRegistryKeys(r.constructors)
+}

internal/framework/pipeline/validator_registry_test.go

@@ -0,0 +1,58 @@
+package pipeline
+
+import (
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func TestValidatorRegistryBehavior(t *testing.T) {
+	runRegistryBehaviorTests(t, registryBehaviorCase[contracts.Validator]{
+		name:       "ValidatorRegistry",
+		key:        "generic-validator",
+		stage:      StageValidate,
+		wrongStage: StageExtract,
+		newRegistry: func() any {
+			return NewValidatorRegistry()
+		},
+		register: func(registry any, key string, constructor func() (contracts.Validator, error)) error {
+			return registry.(*ValidatorRegistry).Register(key, constructor)
+		},
+		registerWithSpec: func(registry any, spec ModuleSpec, constructor func() (contracts.Validator, error)) error {
+			return registry.(*ValidatorRegistry).RegisterWithSpec(spec, constructor)
+		},
+		build: func(registry any, key string) (contracts.Validator, error) {
+			return registry.(*ValidatorRegistry).Build(key)
+		},
+		spec: func(registry any, key string) (ModuleSpec, bool) {
+			return registry.(*ValidatorRegistry).Spec(key)
+		},
+		registeredKeys: func(registry any) []string {
+			return registry.(*ValidatorRegistry).RegisteredKeys()
+		},
+		nilRegister: func(key string, constructor func() (contracts.Validator, error)) error {
+			var registry *ValidatorRegistry
+			return registry.Register(key, constructor)
+		},
+		nilBuild: func(key string) (contracts.Validator, error) {
+			var registry *ValidatorRegistry
+			return registry.Build(key)
+		},
+		nilSpec: func(key string) (ModuleSpec, bool) {
+			var registry *ValidatorRegistry
+			return registry.Spec(key)
+		},
+		nilRegisteredKey: func() []string {
+			var registry *ValidatorRegistry
+			return registry.RegisteredKeys()
+		},
+		constructor: func(key string) func() (contracts.Validator, error) {
+			return func() (contracts.Validator, error) {
+				return registryValidator{name: key}, nil
+			}
+		},
+		moduleKey: func(module contracts.Validator) string {
+			return module.Name()
+		},
+	})
+}

internal/framework/pipeline/walking_skeleton_test.go

@@ -0,0 +1,379 @@
+package pipeline
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"encoding/json"
+	"fmt"
+	"os"
+	"reflect"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func TestWalkingSkeletonFixture(t *testing.T) {
+	inputBytes := readTestFixture(t, "testdata/walking_skeleton_input.json")
+	expectedBytes := readTestFixture(t, "testdata/walking_skeleton_output.json")
+	llmClient := &walkingSkeletonLLMClient{}
+
+	resolved, err := ResolvePipeline(walkingSkeletonProfile(), ResolveOptions{}, walkingSkeletonCatalog(t))
+	if err != nil {
+		t.Fatalf("ResolvePipeline() error = %v, want nil", err)
+	}
+
+	output, err := New(walkingSkeletonRegistries(t)).Run(context.Background(), RunInput{
+		Pipeline:  resolved,
+		SourceID:  "fixture-source",
+		Path:      "walking_skeleton_input.json",
+		RawInput:  inputBytes,
+		LLMClient: llmClient,
+	})
+	if err != nil {
+		t.Fatalf("Run() error = %v, want nil", err)
+	}
+	if output.ContentType != "application/json" {
+		t.Fatalf("ContentType = %q, want application/json", output.ContentType)
+	}
+	assertStructuralJSONEqual(t, output.EncodedOutput, expectedBytes)
+	if llmClient.calls != 2 {
+		t.Fatalf("LLM calls = %d, want chunk count 2", llmClient.calls)
+	}
+}
+
+func TestWalkingSkeletonResolutionRejectsMissingCapability(t *testing.T) {
+	catalog := walkingSkeletonCatalog(t)
+	catalog.Extractors = NewExtractorRegistry()
+	if err := catalog.Extractors.RegisterWithSpec(ModuleSpec{
+		Key:      "fake/extract",
+		Stage:    StageExtract,
+		Requires: []string{"missing"},
+		Provides: []string{"fake_artifacts"},
+	}, func() (contracts.Extractor, error) {
+		return walkingSkeletonExtractor{}, nil
+	}); err != nil {
+		t.Fatalf("RegisterWithSpec() error = %v, want nil", err)
+	}
+
+	_, err := ResolvePipeline(walkingSkeletonProfile(), ResolveOptions{}, catalog)
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	if !strings.Contains(err.Error(), "missing") {
+		t.Fatalf("ResolvePipeline() error = %q, want missing capability", err.Error())
+	}
+}
+
+func TestWalkingSkeletonResolutionRejectsUnknownOnlyLane(t *testing.T) {
+	_, err := ResolvePipeline(walkingSkeletonProfile(), ResolveOptions{Only: []string{"missing"}}, walkingSkeletonCatalog(t))
+	if err == nil {
+		t.Fatal("ResolvePipeline() error = nil, want error")
+	}
+	if !strings.Contains(err.Error(), "missing") || !strings.Contains(err.Error(), "not declared") {
+		t.Fatalf("ResolvePipeline() error = %q, want unknown lane error", err.Error())
+	}
+}
+
+func walkingSkeletonProfile() PipelineProfile {
+	return PipelineProfile{
+		ID:     "walking-skeleton",
+		Input:  Binding("fake/input"),
+		Chunk:  Binding("fake/chunk"),
+		Output: Binding("json"),
+		Artifacts: map[string]ArtifactLaneProfile{
+			"events": {Extract: Binding("fake/extract")},
+		},
+	}
+}
+
+func walkingSkeletonCatalog(t *testing.T) ModuleCatalog {
+	t.Helper()
+
+	catalog := ModuleCatalog{
+		Inputs:      NewInputAdapterRegistry(),
+		Chunkers:    NewChunkerRegistry(),
+		Extractors:  NewExtractorRegistry(),
+		Mergers:     NewMergerRegistry(),
+		Normalizers: NewNormalizerRegistry(),
+		Outputs:     NewOutputEncoderRegistry(),
+	}
+	if err := catalog.Inputs.RegisterWithSpec(ModuleSpec{
+		Key:      "fake/input",
+		Stage:    StageInput,
+		Provides: []string{"plain_text"},
+	}, func() (contracts.InputAdapter, error) {
+		return walkingSkeletonInput{}, nil
+	}); err != nil {
+		t.Fatalf("register fake input: %v", err)
+	}
+	if err := catalog.Chunkers.RegisterWithSpec(ModuleSpec{
+		Key:      "fake/chunk",
+		Stage:    StageChunk,
+		Requires: []string{"plain_text"},
+		Provides: []string{"chunks"},
+	}, func() (contracts.Chunker, error) {
+		return walkingSkeletonChunker{}, nil
+	}); err != nil {
+		t.Fatalf("register fake chunker: %v", err)
+	}
+	if err := catalog.Extractors.RegisterWithSpec(ModuleSpec{
+		Key:      "fake/extract",
+		Stage:    StageExtract,
+		Requires: []string{"chunks"},
+		Provides: []string{"fake_artifacts"},
+	}, func() (contracts.Extractor, error) {
+		return walkingSkeletonExtractor{}, nil
+	}); err != nil {
+		t.Fatalf("register fake extractor: %v", err)
+	}
+	if err := catalog.Mergers.RegisterWithSpec(ModuleSpec{
+		Key:      DefaultMergeModule,
+		Stage:    StageMerge,
+		Requires: []string{"fake_artifacts"},
+	}, func() (contracts.Merger, error) {
+		return AppendOrderMerger{}, nil
+	}); err != nil {
+		t.Fatalf("register append-order merger: %v", err)
+	}
+	if err := catalog.Normalizers.RegisterWithSpec(ModuleSpec{
+		Key:   DefaultNormalizeModule,
+		Stage: StageNormalize,
+	}, func() (contracts.Normalizer, error) {
+		return NoopNormalizer{}, nil
+	}); err != nil {
+		t.Fatalf("register no-op normalizer: %v", err)
+	}
+	if err := catalog.Outputs.RegisterWithSpec(ModuleSpec{
+		Key:   "json",
+		Stage: StageOutput,
+	}, func() (contracts.OutputEncoder, error) {
+		return walkingSkeletonOutput{}, nil
+	}); err != nil {
+		t.Fatalf("register fake output: %v", err)
+	}
+	return catalog
+}
+
+func walkingSkeletonRegistries(t *testing.T) Registries {
+	t.Helper()
+
+	catalog := walkingSkeletonCatalog(t)
+	return Registries{
+		Inputs:      catalog.Inputs,
+		Chunkers:    catalog.Chunkers,
+		Extractors:  catalog.Extractors,
+		Mergers:     catalog.Mergers,
+		Normalizers: catalog.Normalizers,
+		Outputs:     catalog.Outputs,
+	}
+}
+
+type walkingSkeletonInput struct{}
+
+func (input walkingSkeletonInput) Key() string {
+	return "fake/input"
+}
+
+func (input walkingSkeletonInput) Parse(ctx context.Context, req contracts.ParseRequest) (*source.SourceDocument, error) {
+	var fixture struct {
+		ID    string `json:"id"`
+		Units []struct {
+			ID   string `json:"id"`
+			Text string `json:"text"`
+		} `json:"units"`
+	}
+	if err := json.Unmarshal(req.Raw, &fixture); err != nil {
+		return nil, err
+	}
+
+	units := make([]source.SourceUnit, 0, len(fixture.Units))
+	for _, unit := range fixture.Units {
+		units = append(units, source.SourceUnit{
+			ID:   unit.ID,
+			Kind: "unit",
+			Text: unit.Text,
+		})
+	}
+	return &source.SourceDocument{
+		ID:     fixture.ID,
+		Kind:   "fixture",
+		Format: "application/json",
+		Digest: rawDigest(req.Raw),
+		Units:  units,
+	}, nil
+}
+
+type walkingSkeletonChunker struct{}
+
+func (chunker walkingSkeletonChunker) Key() string {
+	return "fake/chunk"
+}
+
+func (chunker walkingSkeletonChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
+	if len(req.Source.Units) < 3 {
+		return contracts.ChunkResult{}, fmt.Errorf("fixture source must contain at least three units")
+	}
+	return contracts.ChunkResult{
+		Chunks: []contracts.SourceChunk{
+			{
+				ID:       req.Source.ID + ":chunk:0",
+				SourceID: req.Source.ID,
+				Index:    0,
+				Units:    append([]source.SourceUnit(nil), req.Source.Units[:2]...),
+			},
+			{
+				ID:       req.Source.ID + ":chunk:1",
+				SourceID: req.Source.ID,
+				Index:    1,
+				Units:    append([]source.SourceUnit(nil), req.Source.Units[2:]...),
+			},
+		},
+	}, nil
+}
+
+type walkingSkeletonExtractor struct{}
+
+func (extractor walkingSkeletonExtractor) Key() string {
+	return "fake/extract"
+}
+
+func (extractor walkingSkeletonExtractor) ArtifactType() string {
+	return "fake_event"
+}
+
+func (extractor walkingSkeletonExtractor) SchemaVersion() string {
+	return "v1"
+}
+
+func (extractor walkingSkeletonExtractor) Validators() []contracts.Validator {
+	return nil
+}
+
+func (extractor walkingSkeletonExtractor) Extract(ctx context.Context, req contracts.ExtractionRequest) (contracts.ExtractionResult, error) {
+	var response struct {
+		Call int `json:"call"`
+	}
+	if _, err := req.LLMClient.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
+		StageName:          "fake/extract",
+		ResponseSchemaName: "fake_event",
+	}, &response); err != nil {
+		return contracts.ExtractionResult{}, err
+	}
+
+	payload, err := json.Marshal(map[string]any{
+		"chunk_id": req.Chunk.ID,
+		"llm_call": response.Call,
+		"text":     chunkText(req.Chunk.Units),
+	})
+	if err != nil {
+		return contracts.ExtractionResult{}, err
+	}
+
+	return contracts.ExtractionResult{
+		Candidates: []artifacts.ArtifactCandidate{
+			{
+				Payload: payload,
+				SourceRefs: []source.SourceRef{
+					{
+						SourceID:    req.Source.ID,
+						StartUnitID: req.Chunk.Units[0].ID,
+						EndUnitID:   req.Chunk.Units[len(req.Chunk.Units)-1].ID,
+					},
+				},
+			},
+		},
+	}, nil
+}
+
+type walkingSkeletonLLMClient struct {
+	calls int
+}
+
+func (client *walkingSkeletonLLMClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
+	client.calls++
+	if response, ok := out.(*struct {
+		Call int `json:"call"`
+	}); ok {
+		response.Call = client.calls
+	}
+	content, err := json.Marshal(map[string]any{"call": client.calls})
+	if err != nil {
+		return contracts.StructuredCompletionResponse{}, err
+	}
+	return contracts.StructuredCompletionResponse{
+		Content: content,
+	}, nil
+}
+
+type walkingSkeletonOutput struct{}
+
+func (output walkingSkeletonOutput) Key() string {
+	return "json"
+}
+
+func (output walkingSkeletonOutput) Encode(ctx context.Context, req contracts.OutputRequest) (contracts.OutputResult, error) {
+	encoded, err := json.Marshal(struct {
+		Manifest artifacts.RunManifest `json:"manifest"`
+		Approved []artifacts.Artifact  `json:"approved"`
+	}{
+		Manifest: artifacts.RunManifest{
+			PipelineID:       req.Manifest.PipelineID,
+			PipelineDigest:   req.Manifest.PipelineDigest,
+			ArtifactLanes:    req.Manifest.ArtifactLanes,
+			ValidationStatus: req.Manifest.ValidationStatus,
+		},
+		Approved: req.Approved,
+	})
+	if err != nil {
+		return contracts.OutputResult{}, err
+	}
+	return contracts.OutputResult{
+		Bytes:       encoded,
+		ContentType: "application/json",
+	}, nil
+}
+
+func readTestFixture(t *testing.T, path string) []byte {
+	t.Helper()
+
+	bytes, err := os.ReadFile(path)
+	if err != nil {
+		t.Fatalf("read fixture %q: %v", path, err)
+	}
+	return bytes
+}
+
+func assertStructuralJSONEqual(t *testing.T, gotBytes, wantBytes []byte) {
+	t.Helper()
+
+	var got any
+	if err := json.Unmarshal(gotBytes, &got); err != nil {
+		t.Fatalf("unmarshal actual JSON: %v\n%s", err, gotBytes)
+	}
+	var want any
+	if err := json.Unmarshal(wantBytes, &want); err != nil {
+		t.Fatalf("unmarshal expected JSON: %v\n%s", err, wantBytes)
+	}
+	if !reflect.DeepEqual(got, want) {
+		gotFormatted, _ := json.MarshalIndent(got, "", "  ")
+		wantFormatted, _ := json.MarshalIndent(want, "", "  ")
+		t.Fatalf("actual JSON:\n%s\nwant:\n%s", gotFormatted, wantFormatted)
+	}
+}
+
+func chunkText(units []source.SourceUnit) string {
+	parts := make([]string, 0, len(units))
+	for _, unit := range units {
+		parts = append(parts, unit.Text)
+	}
+	return strings.Join(parts, " ")
+}
+
+func rawDigest(raw []byte) string {
+	sum := sha256.Sum256(raw)
+	return "sha256:" + hex.EncodeToString(sum[:])
+}