Add reference contracts to extractor metadata

internal/framework/contracts/composition_test.go

@@ -203,6 +203,10 @@ func (extractor compositionExtractor) SchemaVersion() string {
 	return "v1"
 }
 
+func (extractor compositionExtractor) ReferenceSlots() []contracts.ReferenceSlot {
+	return nil
+}
+
 func (extractor compositionExtractor) Validators() []contracts.Validator {
 	return []contracts.Validator{compositionValidator{}}
 }

internal/framework/contracts/contracts.go

@@ -74,10 +74,49 @@ type Chunker interface {
 	Chunk(ctx context.Context, req ChunkRequest) (ChunkResult, error)
 }
 
+const (
+	ReferenceBindingSourceConfig = "config"
+	ReferenceBindingSourceCLI    = "cli"
+)
+
+type ReferenceSlot struct {
+	Name               string   `json:"name"`
+	Description        string   `json:"description,omitempty"`
+	Required           bool     `json:"required,omitempty"`
+	AcceptedMediaTypes []string `json:"accepted_media_types,omitempty"`
+	Multiple           bool     `json:"multiple,omitempty"`
+	MaxBytes           int64    `json:"max_bytes,omitempty"`
+}
+
+type ReferenceOrigin struct {
+	Type string `json:"type"`
+	URI  string `json:"uri,omitempty"`
+}
+
+type ReferenceItem struct {
+	SlotName      string          `json:"slot_name"`
+	MediaType     string          `json:"media_type,omitempty"`
+	Content       []byte          `json:"-"`
+	Digest        string          `json:"digest,omitempty"`
+	Origin        ReferenceOrigin `json:"origin"`
+	SizeBytes     int64           `json:"size_bytes,omitempty"`
+	BindingSource string          `json:"binding_source,omitempty"`
+}
+
+type ResolvedReferenceSlot struct {
+	Slot  ReferenceSlot   `json:"slot"`
+	Items []ReferenceItem `json:"items,omitempty"`
+}
+
+type ReferenceSet struct {
+	Slots map[string]ResolvedReferenceSlot `json:"slots,omitempty"`
+}
+
 type ExtractionRequest struct {
 	Source         *source.SourceDocument `json:"-"`
 	Chunk          *SourceChunk           `json:"chunk,omitempty"`
 	AmbientContext map[string]any         `json:"ambient_context,omitempty"`
+	References     ReferenceSet           `json:"references,omitempty"`
 	LLMClient      StructuredLLMClient    `json:"-"`
 	LLMProfile     string                 `json:"llm_profile,omitempty"`
 	Options        map[string]any         `json:"options,omitempty"`
@@ -93,6 +132,7 @@ type Extractor interface {
 	Key() string
 	ArtifactType() string
 	SchemaVersion() string
+	ReferenceSlots() []ReferenceSlot
 	Validators() []Validator
 	Extract(ctx context.Context, req ExtractionRequest) (ExtractionResult, error)
 }

internal/framework/contracts/contracts_test.go

@@ -186,6 +186,71 @@ func TestFakeExtractorReceivesChunkAndAmbientContext(t *testing.T) {
 	}
 }
 
+func TestReferenceSetDataTypes(t *testing.T) {
+	references := ReferenceSet{
+		Slots: map[string]ResolvedReferenceSlot{
+			"roster": {
+				Slot: ReferenceSlot{
+					Name:               "roster",
+					Description:        "Known characters",
+					Required:           true,
+					AcceptedMediaTypes: []string{"text/plain"},
+					Multiple:           true,
+					MaxBytes:           4096,
+				},
+				Items: []ReferenceItem{
+					{
+						SlotName:  "roster",
+						MediaType: "text/plain",
+						Content:   []byte("Aria\nBryn\n"),
+						Digest:    "sha256:reference",
+						Origin: ReferenceOrigin{
+							Type: "file",
+							URI:  "file:///tmp/roster.txt",
+						},
+						SizeBytes:     10,
+						BindingSource: ReferenceBindingSourceConfig,
+					},
+				},
+			},
+		},
+	}
+
+	item := references.Slots["roster"].Items[0]
+	if item.SlotName != "roster" || item.MediaType != "text/plain" || string(item.Content) != "Aria\nBryn\n" {
+		t.Fatalf("reference item = %#v, want constructed item fields", item)
+	}
+	if item.BindingSource != ReferenceBindingSourceConfig {
+		t.Fatalf("BindingSource = %q, want %q", item.BindingSource, ReferenceBindingSourceConfig)
+	}
+}
+
+func TestReferenceItemJSONOmitsContent(t *testing.T) {
+	item := ReferenceItem{
+		SlotName:  "roster",
+		MediaType: "text/plain",
+		Content:   []byte("reference content"),
+		Digest:    "sha256:reference",
+		Origin:    ReferenceOrigin{Type: "file", URI: "file:///tmp/roster.txt"},
+	}
+
+	encoded, err := json.Marshal(item)
+	if err != nil {
+		t.Fatalf("json.Marshal() error = %v, want nil", err)
+	}
+
+	var got map[string]any
+	if err := json.Unmarshal(encoded, &got); err != nil {
+		t.Fatalf("json.Unmarshal() error = %v, want nil", err)
+	}
+	if _, ok := got["content"]; ok {
+		t.Fatalf("encoded reference item leaked content: %s", encoded)
+	}
+	if _, ok := got["Content"]; ok {
+		t.Fatalf("encoded reference item leaked Content: %s", encoded)
+	}
+}
+
 func TestFakeMergeNormalizeAndOutputContracts(t *testing.T) {
 	candidate := artifacts.ArtifactCandidate{
 		Index:         0,
@@ -359,6 +424,10 @@ func (extractor fakeExtractor) SchemaVersion() string {
 	return extractor.schemaVersion
 }
 
+func (extractor fakeExtractor) ReferenceSlots() []ReferenceSlot {
+	return nil
+}
+
 func (extractor fakeExtractor) Validators() []Validator {
 	return extractor.validators
 }