Add D&D location extractor

internal/modules/dnd/extract/locations/assets.go

@@ -0,0 +1,6 @@
+package locations
+
+import "embed"
+
+//go:embed assets/prompts/*.yaml assets/prompts/*.md assets/schemas/*.json
+var embeddedAssets embed.FS

internal/modules/dnd/extract/locations/assets/prompts/dnd.locations.yaml

@@ -0,0 +1,42 @@
+id: dnd.locations
+version: "v1"
+default_profile: dnd-extraction
+inputs:
+  - name: transcript
+    required: true
+    content_type: application/json
+  - name: players
+    required: false
+    content_type: text/plain
+  - name: party
+    required: false
+    content_type: text/plain
+  - name: glossary
+    required: false
+    content_type: text/plain
+messages:
+  - role: system
+    content_file: ./sharedassets/common-dnd-system.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-identity.md
+  - role: user
+    content_file: ./sharedassets/common-dnd-references.md
+    cache_control:
+      type: ephemeral
+  - role: user
+    content_file: ./sharedassets/common-dnd-transcript.md
+    cache_control:
+      type: ephemeral
+  - role: user
+    content_file: ./sharedassets/common-dnd-extraction-evidence.md
+  - role: user
+    content_file: ./task.md
+  - role: user
+    content_file: ./instructions.md
+    cache_control:
+      type: ephemeral
+output:
+  format: json
+  validation_mode: json_schema
+  schema_path: dnd_locations_llm.v1.json
+  repair_attempts: 0

internal/modules/dnd/extract/locations/assets/prompts/instructions.md

@@ -0,0 +1,6 @@
+Return only observed location display names and narrow transcript source ranges.
+
+Exclude people, creatures, objects, organizations, abstract concepts, and
+places merely inferred from an event. Omit uncertain or unsupported places.
+Campaign references may clarify terms already present in the transcript, but
+they are not evidence and must never supply a source range.

internal/modules/dnd/extract/locations/assets/prompts/task.md

@@ -0,0 +1,8 @@
+Extract physical places established by the provided Dungeons & Dragons
+transcript and cite where each place is identified.
+
+Include planes, regions, settlements, districts, buildings, rooms, landmarks,
+routes, and geographic features. A generic label such as "the tavern" is
+allowed only when the transcript uses it for a specific place. Keep aliases and
+nested places when the transcript identifies them; do not merge or invent
+qualifiers for similarly named places.

internal/modules/dnd/extract/locations/assets/schemas/dnd_locations_llm.v1.json

@@ -0,0 +1,32 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "$id": "notarius.dnd.locations.llm",
+  "type": "object",
+  "additionalProperties": false,
+  "required": ["locations"],
+  "properties": {
+    "locations": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "additionalProperties": false,
+        "required": ["name", "source_refs"],
+        "properties": {
+          "name": {"type": "string"},
+          "source_refs": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "additionalProperties": false,
+              "required": ["start_unit_id", "end_unit_id"],
+              "properties": {
+                "start_unit_id": {"type": "integer"},
+                "end_unit_id": {"type": "integer"}
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}

internal/modules/dnd/extract/locations/canonicalize.go

@@ -0,0 +1,86 @@
+package locations
+
+import (
+	"sort"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/locations/identity"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
+)
+
+type orderedLocationResponse struct {
+	value       locationResponse
+	earliest    int
+	hasEvidence bool
+}
+
+func canonicalizeResponse(response *extractionResponse, order shared.SourceRefOrder, sourceID string) {
+	if response == nil {
+		return
+	}
+	ordered := make([]orderedLocationResponse, len(response.Locations))
+	for index := range response.Locations {
+		earliest, hasEvidence := canonicalizeLocation(&response.Locations[index], order, sourceID)
+		ordered[index] = orderedLocationResponse{value: response.Locations[index], earliest: earliest, hasEvidence: hasEvidence}
+	}
+	sort.SliceStable(ordered, func(left, right int) bool {
+		if ordered[left].hasEvidence != ordered[right].hasEvidence {
+			return ordered[left].hasEvidence
+		}
+		if !ordered[left].hasEvidence {
+			return false
+		}
+		return ordered[left].earliest < ordered[right].earliest
+	})
+	for index := range ordered {
+		response.Locations[index] = ordered[index].value
+	}
+}
+
+func canonicalizeLocation(location *locationResponse, order shared.SourceRefOrder, sourceID string) (int, bool) {
+	if location == nil {
+		return 0, false
+	}
+	refs := order.Canonicalize(canonicalSourceRefs(location.SourceRefs, sourceID))
+	location.SourceRefs = locationResponseRefs(refs)
+	return order.EarliestValid(refs)
+}
+
+func canonicalLocationList(response extractionResponse, sourceID string) dnd.LocationList {
+	if response.Locations == nil {
+		return dnd.LocationList{Locations: nil}
+	}
+	locations := make([]dnd.Location, len(response.Locations))
+	for index, location := range response.Locations {
+		refs := canonicalSourceRefs(location.SourceRefs, sourceID)
+		locations[index] = dnd.Location{
+			ID:         identity.DeriveID(location.Name, refs),
+			Name:       location.Name,
+			SourceRefs: refs,
+		}
+	}
+	return dnd.LocationList{Locations: locations}
+}
+
+func canonicalSourceRefs(values []locationSourceRefResponse, sourceID string) []source.SourceRef {
+	if values == nil {
+		return nil
+	}
+	refs := make([]source.SourceRef, len(values))
+	for index, value := range values {
+		refs[index] = source.SourceRef{SourceID: sourceID, StartUnitID: value.StartUnitID, EndUnitID: value.EndUnitID}
+	}
+	return refs
+}
+
+func locationResponseRefs(values []source.SourceRef) []locationSourceRefResponse {
+	if values == nil {
+		return nil
+	}
+	refs := make([]locationSourceRefResponse, len(values))
+	for index, value := range values {
+		refs[index] = locationSourceRefResponse{StartUnitID: value.StartUnitID, EndUnitID: value.EndUnitID}
+	}
+	return refs
+}

internal/modules/dnd/extract/locations/extractor.go

@@ -0,0 +1,152 @@
+// Package locations extracts source-grounded D&D physical location candidates.
+package locations
+
+import (
+	"context"
+	"fmt"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/locations/identity"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
+)
+
+const (
+	Key           = "dnd/locations"
+	mappingPolicy = "dnd.locations.extract_mapping.v1"
+)
+
+var requiredCapabilities = []string{"chunks", "source.transcript"}
+var providedCapabilities = []string{"dnd.locations"}
+
+var referenceSlotDescriptions = shared.ReferenceSlotDescriptions{
+	Glossary: "Optional campaign glossary reference material used only for location disambiguation.",
+	Party:    "Optional party roster reference material used only for location disambiguation.",
+	Players:  "Optional player list reference material used only for location disambiguation.",
+	Roster:   "Deprecated alias for party roster reference material used only for location disambiguation.",
+}
+
+func referenceSlots() []contracts.ReferenceSlot {
+	return shared.ReferenceSlots(referenceSlotDescriptions)
+}
+
+var _ contracts.Extractor[dnd.LocationList] = (*Extractor)(nil)
+var _ contracts.ManifestMetadataProvider = (*Extractor)(nil)
+var _ pipeline.CheckpointFingerprintProvider = (*Extractor)(nil)
+
+type Options struct{}
+
+type Extractor struct {
+	llm               contracts.StructuredLLMClient
+	promptSHA         string
+	responseSchemaSHA string
+}
+
+func New(llmClient contracts.StructuredLLMClient, _ Options, references ...contracts.ReferenceSet) (*Extractor, error) {
+	if llmClient == nil {
+		return nil, extractorErrorf("LLM client must not be nil")
+	}
+	if len(references) > 1 {
+		return nil, extractorErrorf("at most one reference set may be supplied")
+	}
+	promptSHA, err := promptAssetMetadata()
+	if err != nil {
+		return nil, extractorErrorf("load prompt metadata: %w", err)
+	}
+	responseSchema, err := loadResponseSchema()
+	if err != nil {
+		return nil, extractorErrorf("load response schema: %w", err)
+	}
+	return &Extractor{llm: llmClient, promptSHA: promptSHA, responseSchemaSHA: responseSchema.SHA256}, nil
+}
+
+func (e *Extractor) Key() string { return Key }
+
+func (e *Extractor) ReferenceSlots() []contracts.ReferenceSlot { return referenceSlots() }
+
+func (e *Extractor) ManifestMetadata() map[string]any {
+	if e == nil {
+		return nil
+	}
+	return map[string]any{
+		"prompt_id":               PromptID,
+		"prompt_version":          SchemaVersion,
+		"prompt_sha256":           e.promptSHA,
+		"response_schema_key":     string(ResponseSchemaKey),
+		"response_schema_id":      ResponseSchemaID,
+		"response_schema_name":    ResponseSchemaName,
+		"response_schema_version": SchemaVersion,
+		"response_schema_sha256":  e.responseSchemaSHA,
+		"identity_policy":         identity.Policy,
+		"mapping_policy":          mappingPolicy,
+	}
+}
+
+func (e *Extractor) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
+	if e == nil {
+		return nil
+	}
+	return []pipeline.CheckpointFingerprint{
+		{Name: "prompt", Value: e.promptSHA},
+		{Name: "response_schema", Value: e.responseSchemaSHA},
+		{Name: "identity_policy", Value: identity.Policy},
+		{Name: "mapping_policy", Value: mappingPolicy},
+	}
+}
+
+func (e *Extractor) Extract(ctx context.Context, req contracts.TypedExtractionRequest) (contracts.TypedExtractionResult[dnd.LocationList], error) {
+	if e == nil {
+		return contracts.TypedExtractionResult[dnd.LocationList]{}, extractorErrorf("extractor must not be nil")
+	}
+	if e.llm == nil {
+		return contracts.TypedExtractionResult[dnd.LocationList]{}, extractorErrorf("LLM client must not be nil")
+	}
+	sourceInput, err := shared.PrepareChunkExtraction(ctx, req)
+	if err != nil {
+		return contracts.TypedExtractionResult[dnd.LocationList]{}, extractorErrorf("%w", err)
+	}
+	order := shared.NewSourceRefOrder(req.Source)
+
+	var response extractionResponse
+	if _, err := e.llm.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
+		StageName: Key, PromptID: PromptID, PromptVersion: SchemaVersion,
+		ProfileID: req.LLMProfile, SessionID: req.SessionID,
+		Inputs: shared.PromptInputs(sourceInput, req.References),
+	}, &response); err != nil {
+		return contracts.TypedExtractionResult[dnd.LocationList]{}, extractorErrorf("complete structured output: %w", err)
+	}
+	canonicalizeResponse(&response, order, req.Source.ID)
+	return contracts.TypedExtractionResult[dnd.LocationList]{Value: canonicalLocationList(response, req.Source.ID)}, nil
+}
+
+func ModuleSpec() pipeline.ModuleSpec {
+	return pipeline.ModuleSpec{
+		Key: Key, Stage: pipeline.StageExtract, ExecutionClass: contracts.ExecutionClassLLMBacked,
+		Requires: append([]string(nil), requiredCapabilities...), Provides: append([]string(nil), providedCapabilities...),
+		ArtifactKind: dnd.LocationListKind, ReferenceSlots: referenceSlots(),
+	}
+}
+
+func Register(registry *pipeline.ExtractorRegistry) error {
+	return pipeline.RegisterExtractorBuilder(registry, ModuleSpec(), validateOptions, func(request pipeline.BuildRequest) (contracts.Extractor[dnd.LocationList], error) {
+		options, err := DecodeOptions(request.Options)
+		if err != nil {
+			return nil, err
+		}
+		return New(request.Dependencies.LLM, options, request.References)
+	})
+}
+
+func validateOptions(options map[string]any) error { _, err := DecodeOptions(options); return err }
+
+func DecodeOptions(options map[string]any) (Options, error) {
+	if err := pipeline.RejectUnknownOptions(options); err != nil {
+		return Options{}, extractorErrorf("%w", err)
+	}
+	return Options{}, nil
+}
+
+func extractorErrorf(format string, args ...any) error {
+	return fmt.Errorf("dnd locations extractor: "+format, args...)
+}

internal/modules/dnd/extract/locations/extractor_test.go

@@ -0,0 +1,125 @@
+package locations
+
+import (
+	"context"
+	"errors"
+	"reflect"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/locations/identity"
+)
+
+func TestExtractMapsLocationsWithOwnedEvidenceAndDeterministicOrder(t *testing.T) {
+	client := &fakeLocationsLLMClient{response: extractionResponse{Locations: []locationResponse{
+		{Name: "The Tavern", SourceRefs: responseSourceRefs(3, 3)},
+		{Name: "Old Mill", SourceRefs: []locationSourceRefResponse{{StartUnitID: 2, EndUnitID: 2}, {StartUnitID: 1, EndUnitID: 1}, {StartUnitID: 1, EndUnitID: 1}}},
+	}}}
+	result, err := newExtractor(t, client).Extract(context.Background(), extractionRequest())
+	if err != nil {
+		t.Fatalf("Extract() error = %v, want nil", err)
+	}
+	refs := []source.SourceRef{{SourceID: "session-locations", StartUnitID: 1, EndUnitID: 1}, {SourceID: "session-locations", StartUnitID: 2, EndUnitID: 2}}
+	want := dnd.LocationList{Locations: []dnd.Location{
+		{ID: identity.DeriveID("Old Mill", refs), Name: "Old Mill", SourceRefs: refs},
+		{ID: identity.DeriveID("The Tavern", []source.SourceRef{{SourceID: "session-locations", StartUnitID: 3, EndUnitID: 3}}), Name: "The Tavern", SourceRefs: []source.SourceRef{{SourceID: "session-locations", StartUnitID: 3, EndUnitID: 3}}},
+	}}
+	if !reflect.DeepEqual(result.Value, want) {
+		t.Fatalf("Value = %#v, want %#v", result.Value, want)
+	}
+	result.Value.Locations[0].SourceRefs[0].StartUnitID = 99
+	for _, location := range client.response.Locations {
+		for _, ref := range location.SourceRefs {
+			if ref.StartUnitID == 99 {
+				t.Fatal("result source references alias the model response")
+			}
+		}
+	}
+}
+
+func TestExtractRetainsSameNameLocationsAtDifferentAnchors(t *testing.T) {
+	client := &fakeLocationsLLMClient{response: extractionResponse{Locations: []locationResponse{
+		{Name: "the tavern", SourceRefs: responseSourceRefs(1, 1)},
+		{Name: "the tavern", SourceRefs: responseSourceRefs(3, 3)},
+	}}}
+	result, err := newExtractor(t, client).Extract(context.Background(), extractionRequest())
+	if err != nil || len(result.Value.Locations) != 2 {
+		t.Fatalf("Extract() = %#v, %v; want both same-name candidates", result, err)
+	}
+	if result.Value.Locations[0].ID == result.Value.Locations[1].ID || result.Value.Locations[0].Name != result.Value.Locations[1].Name {
+		t.Fatalf("locations = %#v, want distinct evidence-anchored IDs", result.Value.Locations)
+	}
+}
+
+func TestExtractPreservesInvalidCandidatesForValidators(t *testing.T) {
+	client := &fakeLocationsLLMClient{content: []byte(`{"locations":[{"name":"","source_refs":[{"start_unit_id":0,"end_unit_id":-1}]}]}`)}
+	result, err := newExtractor(t, client).Extract(context.Background(), extractionRequest())
+	if err != nil {
+		t.Fatalf("Extract() error = %v, want nil", err)
+	}
+	location := result.Value.Locations[0]
+	if location.ID != "" || location.Name != "" || !reflect.DeepEqual(location.SourceRefs, []source.SourceRef{{SourceID: "session-locations", StartUnitID: 0, EndUnitID: -1}}) {
+		t.Fatalf("location = %#v, want invalid candidate preserved", location)
+	}
+}
+
+func TestExtractPassesReferencesWithoutTreatingThemAsEvidence(t *testing.T) {
+	client := &fakeLocationsLLMClient{response: extractionResponse{Locations: []locationResponse{}}}
+	req := extractionRequest()
+	req.References = contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{
+		"glossary": {Slot: contracts.ReferenceSlot{Name: "glossary"}, Items: []contracts.ReferenceItem{{SlotName: "glossary", Content: []byte("Old Mill: abandoned granary")}}},
+	}}
+	if _, err := newExtractor(t, client).Extract(context.Background(), req); err != nil {
+		t.Fatalf("Extract() error = %v", err)
+	}
+	inputs := client.requests[0].Inputs
+	if string(inputs["glossary"].Content) != "Old Mill: abandoned granary" || strings.Contains(string(inputs["transcript"].Content), "abandoned granary") {
+		t.Fatalf("prompt inputs = %#v, want separated reference material", inputs)
+	}
+}
+
+func TestExtractDoesNotMutateRequestMaterials(t *testing.T) {
+	client := &fakeLocationsLLMClient{response: extractionResponse{Locations: []locationResponse{{Name: "Old Mill", SourceRefs: responseSourceRefs(1, 1)}}}}
+	req := extractionRequest()
+	beforeUnits := append([]source.SourceUnit(nil), req.Source.Units...)
+	beforeChunkUnits := append([]source.SourceUnit(nil), req.Chunk.Units...)
+	beforeContent := append([]byte(nil), req.Chunk.Content...)
+	if _, err := newExtractor(t, client).Extract(context.Background(), req); err != nil {
+		t.Fatalf("Extract() error = %v", err)
+	}
+	if !reflect.DeepEqual(req.Source.Units, beforeUnits) || !reflect.DeepEqual(req.Chunk.Units, beforeChunkUnits) || !reflect.DeepEqual(req.Chunk.Content, beforeContent) {
+		t.Fatalf("Extract() mutated request: %#v", req)
+	}
+}
+
+func TestExtractHandlesEmptyOutputAndLocalFailures(t *testing.T) {
+	empty, err := newExtractor(t, &fakeLocationsLLMClient{response: extractionResponse{Locations: []locationResponse{}}}).Extract(context.Background(), extractionRequest())
+	if err != nil || empty.Value.Locations == nil || len(empty.Value.Locations) != 0 {
+		t.Fatalf("empty Extract() = %#v, %v; want empty list", empty, err)
+	}
+	request := extractionRequest()
+	var nilExtractor *Extractor
+	for _, test := range []struct {
+		name      string
+		extractor *Extractor
+		req       contracts.TypedExtractionRequest
+		want      string
+	}{
+		{name: "nil extractor", extractor: nilExtractor, req: request, want: "extractor"},
+		{name: "nil client", extractor: &Extractor{}, req: request, want: "LLM client"},
+		{name: "preflight", extractor: newExtractor(t, &fakeLocationsLLMClient{}), req: mismatchedSourceInputRequest(request), want: "must match chunk"},
+	} {
+		t.Run(test.name, func(t *testing.T) {
+			if _, err := test.extractor.Extract(context.Background(), test.req); err == nil || !strings.Contains(err.Error(), "dnd locations") || !strings.Contains(err.Error(), test.want) {
+				t.Fatalf("Extract() error = %v, want local context", err)
+			}
+		})
+	}
+	_, err = newExtractor(t, &fakeLocationsLLMClient{err: errors.New("provider unavailable")}).Extract(context.Background(), request)
+	if err == nil || !strings.Contains(err.Error(), "dnd locations") || !strings.Contains(err.Error(), "provider unavailable") {
+		t.Fatalf("provider error = %v, want contextual provider error", err)
+	}
+}

internal/modules/dnd/extract/locations/model.go

@@ -0,0 +1,15 @@
+package locations
+
+type extractionResponse struct {
+	Locations []locationResponse `json:"locations"`
+}
+
+type locationResponse struct {
+	Name       string                      `json:"name"`
+	SourceRefs []locationSourceRefResponse `json:"source_refs"`
+}
+
+type locationSourceRefResponse struct {
+	StartUnitID int `json:"start_unit_id"`
+	EndUnitID   int `json:"end_unit_id"`
+}

internal/modules/dnd/extract/locations/prompt_assets.go

@@ -0,0 +1,52 @@
+package locations
+
+import (
+	"fmt"
+	"sync"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/promptfs"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
+)
+
+const promptAssetRoot = "assets/prompts"
+
+var promptAssetManifest = shared.PromptAssetManifest{
+	ModuleDir: PromptID,
+	ModuleFiles: []promptfs.ModulePromptFile{
+		{Name: "dnd.locations.yaml", Path: "assets/prompts/dnd.locations.yaml"},
+		{Name: "task.md", Path: "assets/prompts/task.md"},
+		{Name: "instructions.md", Path: "assets/prompts/instructions.md"},
+	},
+	SharedFiles: []string{
+		"common-dnd-system.md",
+		"common-dnd-extraction-evidence.md",
+		"common-dnd-identity.md",
+		"common-dnd-transcript.md",
+		"common-dnd-references.md",
+	},
+}
+
+func RegisterPromptAssets(registry *llm.AssetRegistry) error {
+	promptFS, err := promptAssetManifest.PromptFS(embeddedAssets)
+	if err != nil {
+		return fmt.Errorf("prepare location prompt assets: %w", err)
+	}
+	if err := registry.RegisterPromptFS(promptFS, promptAssetRoot); err != nil {
+		return err
+	}
+	return registry.RegisterSchemaFS(embeddedAssets, "assets/schemas")
+}
+
+func promptAssetMetadata() (string, error) {
+	promptAssetHashOnce.Do(func() {
+		promptAssetHash, promptAssetHashErr = promptAssetManifest.Hash(embeddedAssets)
+	})
+	return promptAssetHash, promptAssetHashErr
+}
+
+var (
+	promptAssetHashOnce sync.Once
+	promptAssetHash     string
+	promptAssetHashErr  error
+)

internal/modules/dnd/extract/locations/prompt_assets_test.go

@@ -0,0 +1,50 @@
+package locations
+
+import (
+	"context"
+	"slices"
+	"strings"
+	"testing"
+	"time"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
+	"gitea.maximumdirect.net/eric/promptkit"
+)
+
+func TestRegisterPromptAssetsPreparesLocationPrompt(t *testing.T) {
+	for _, name := range []string{"common-dnd-system.md", "common-dnd-identity.md", "common-dnd-references.md", "common-dnd-transcript.md", "common-dnd-extraction-evidence.md"} {
+		if !slices.Contains(promptAssetManifest.SharedFiles, name) {
+			t.Fatalf("shared prompt assets = %#v, missing %q", promptAssetManifest.SharedFiles, name)
+		}
+	}
+	registry := llm.NewAssetRegistry()
+	if err := RegisterPromptAssets(registry); err != nil {
+		t.Fatalf("RegisterPromptAssets() error = %v", err)
+	}
+	options, err := registry.PromptKitOptions()
+	if err != nil {
+		t.Fatalf("PromptKitOptions() error = %v", err)
+	}
+	options = append(options, promptkit.WithProfiles(promptkit.OpenAICompatibleProfile(promptkit.OpenAICompatibleProfileConfig{ID: "location-test-profile", Endpoint: "http://127.0.0.1:1/v1", Model: "location-test-model"})))
+	engine, err := promptkit.NewEngine(promptkit.Config{Timeout: time.Second}, options...)
+	if err != nil {
+		t.Fatalf("NewEngine() error = %v", err)
+	}
+	prepared, err := engine.Prepare(context.Background(), promptkit.RunRequest{PromptID: PromptID, PromptVersion: SchemaVersion, ProfileID: "location-test-profile", Inputs: map[string]promptkit.ArtifactRef{
+		"transcript": promptkit.Inline(`{"units":[1]}`), "players": promptkit.Inline(" "), "party": promptkit.Inline(" "), "glossary": promptkit.Inline(" "),
+	}})
+	if err != nil {
+		t.Fatalf("Prepare() error = %v", err)
+	}
+	if prepared.OutputContract.SchemaPath != "dnd_locations_llm.v1.json" {
+		t.Fatalf("output contract = %#v", prepared.OutputContract)
+	}
+	if len(prepared.Messages) != 7 || !strings.Contains(prepared.Messages[3].Content, `"units"`) || strings.Contains(prepared.Messages[3].Content, "location-test") {
+		t.Fatalf("prepared messages = %#v, want rendered transcript only in transcript message", prepared.Messages)
+	}
+	for _, index := range []int{2, 3, 6} {
+		if prepared.Messages[index].CacheControl == nil || prepared.Messages[index].CacheControl.Type != promptkit.CacheControlEphemeral {
+			t.Fatalf("message %d cache control = %#v, want ephemeral", index, prepared.Messages[index].CacheControl)
+		}
+	}
+}

internal/modules/dnd/extract/locations/registry_test.go

@@ -0,0 +1,53 @@
+package locations
+
+import (
+	"reflect"
+	"strings"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/locations/identity"
+)
+
+func TestModuleRegistrationAndMetadata(t *testing.T) {
+	if _, err := New(nil, Options{}); err == nil || !strings.Contains(err.Error(), "LLM client") {
+		t.Fatalf("New(nil) error = %v, want client rejection", err)
+	}
+	if _, err := New(&fakeLocationsLLMClient{}, Options{}, contracts.ReferenceSet{}, contracts.ReferenceSet{}); err == nil || !strings.Contains(err.Error(), "at most one") {
+		t.Fatalf("New() error = %v, want reference-set rejection", err)
+	}
+	want := pipeline.ModuleSpec{Key: Key, Stage: pipeline.StageExtract, ExecutionClass: contracts.ExecutionClassLLMBacked, Requires: []string{"chunks", "source.transcript"}, Provides: []string{"dnd.locations"}, ArtifactKind: dnd.LocationListKind, ReferenceSlots: referenceSlots()}
+	if got := ModuleSpec(); !reflect.DeepEqual(got, want) {
+		t.Fatalf("ModuleSpec() = %#v, want %#v", got, want)
+	}
+	registry := pipeline.NewExtractorRegistry()
+	if err := Register(registry); err != nil {
+		t.Fatalf("Register() error = %v", err)
+	}
+	if got, ok := registry.Spec(Key); !ok || !reflect.DeepEqual(got, want) {
+		t.Fatalf("registry spec = %#v, present = %t", got, ok)
+	}
+	if err := Register(nil); err == nil || !strings.Contains(err.Error(), "extractor registry") {
+		t.Fatalf("Register(nil) error = %v, want registry rejection", err)
+	}
+	if _, err := DecodeOptions(map[string]any{"unknown": true}); err == nil {
+		t.Fatal("DecodeOptions() accepted unknown option")
+	}
+	extractor := newExtractor(t, &fakeLocationsLLMClient{})
+	metadata := extractor.ManifestMetadata()
+	for key, value := range map[string]string{
+		"prompt_id": PromptID, "prompt_version": SchemaVersion,
+		"response_schema_key": string(ResponseSchemaKey), "response_schema_id": ResponseSchemaID,
+		"response_schema_name": ResponseSchemaName, "response_schema_version": SchemaVersion,
+		"identity_policy": identity.Policy, "mapping_policy": mappingPolicy,
+	} {
+		if metadata[key] != value {
+			t.Fatalf("metadata[%q] = %#v, want %q", key, metadata[key], value)
+		}
+	}
+	if got := extractor.CheckpointFingerprints(); len(got) != 4 || got[0].Name != "prompt" || got[1].Name != "response_schema" || got[2].Value != identity.Policy || got[3].Value != mappingPolicy {
+		t.Fatalf("CheckpointFingerprints() = %#v", got)
+	}
+}

internal/modules/dnd/extract/locations/schema.go

@@ -0,0 +1,21 @@
+package locations
+
+import "gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
+
+const (
+	PromptID           = "dnd.locations"
+	ResponseSchemaKey  = llm.ResponseSchemaKey("dnd_locations_llm")
+	ResponseSchemaID   = "notarius.dnd.locations.llm"
+	ResponseSchemaName = "notarius_dnd_locations_llm_v1"
+	SchemaVersion      = "v1"
+)
+
+func loadResponseSchema() (llm.ResponseSchema, error) {
+	return llm.LoadResponseSchema(embeddedAssets, llm.ResponseSchemaDefinition{
+		Key:       ResponseSchemaKey,
+		ID:        ResponseSchemaID,
+		Version:   SchemaVersion,
+		Name:      ResponseSchemaName,
+		AssetPath: "assets/schemas/dnd_locations_llm.v1.json",
+	})
+}

internal/modules/dnd/extract/locations/schema_test.go

@@ -0,0 +1,25 @@
+package locations
+
+import (
+	"encoding/json"
+	"strings"
+	"testing"
+)
+
+func TestLocationResponseSchemaIsPrivateAndStructural(t *testing.T) {
+	schema, err := loadResponseSchema()
+	if err != nil {
+		t.Fatalf("loadResponseSchema() error = %v", err)
+	}
+	if schema.Key != ResponseSchemaKey || schema.ID != ResponseSchemaID || schema.Name != ResponseSchemaName || schema.Version != SchemaVersion || !strings.HasPrefix(schema.SHA256, "sha256:") || !json.Valid(schema.JSONSchema) {
+		t.Fatalf("schema = %#v, want location response schema", schema)
+	}
+	var document map[string]any
+	if err := json.Unmarshal(schema.JSONSchema, &document); err != nil {
+		t.Fatal(err)
+	}
+	encoded, err := json.Marshal(document)
+	if err != nil || strings.Contains(string(encoded), `"id"`) {
+		t.Fatalf("schema = %s, want no durable ID field", encoded)
+	}
+}

internal/modules/dnd/extract/locations/test_helpers_test.go

@@ -0,0 +1,89 @@
+package locations
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+)
+
+func extractionRequest() contracts.TypedExtractionRequest {
+	doc := sourceDocument()
+	chunk := &source.Chunk{
+		ID: "session-locations:chunk:0", SourceID: doc.ID, Index: 0,
+		Ref:     source.SourceRef{SourceID: doc.ID, StartUnitID: 1, EndUnitID: 3},
+		Content: []byte(`{"units":[1,2,3]}`), MediaType: "application/json",
+		Units: append([]source.SourceUnit(nil), doc.Units...),
+	}
+	return contracts.TypedExtractionRequest{
+		Source: doc, Chunk: chunk,
+		SourceInput: contracts.NewLLMInputMaterial("source", chunk.MediaType, chunk.Content, "sha256:chunk", "file:///session-locations.json"),
+		SessionID:   "location-session", LLMProfile: "location-profile",
+	}
+}
+
+func sourceDocument() *source.SourceDocument {
+	return &source.SourceDocument{ID: "session-locations", Kind: "transcript", Format: "application/json", Digest: "sha256:test", Units: []source.SourceUnit{
+		{ID: 1, Kind: "transcript_segment", Text: "The party enters the Old Mill."},
+		{ID: 2, Kind: "transcript_segment", Text: "They leave the old road behind."},
+		{ID: 3, Kind: "transcript_segment", Text: "The tavern is quiet."},
+	}}
+}
+
+func responseSourceRefs(startUnitID, endUnitID int) []locationSourceRefResponse {
+	return []locationSourceRefResponse{{StartUnitID: startUnitID, EndUnitID: endUnitID}}
+}
+
+func newExtractor(t *testing.T, client contracts.StructuredLLMClient, references ...contracts.ReferenceSet) *Extractor {
+	t.Helper()
+	extractor, err := New(client, Options{}, references...)
+	if err != nil {
+		t.Fatalf("New() error = %v, want nil", err)
+	}
+	return extractor
+}
+
+func mismatchedSourceInputRequest(req contracts.TypedExtractionRequest) contracts.TypedExtractionRequest {
+	req.SourceInput = contracts.NewLLMInputMaterial("source", "application/json", []byte(`{"different":true}`), "sha256:other", "file:///other.json")
+	return req
+}
+
+type fakeLocationsLLMClient struct {
+	response extractionResponse
+	content  []byte
+	err      error
+	requests []contracts.StructuredCompletionRequest
+}
+
+func (client *fakeLocationsLLMClient) CompleteStructured(_ context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
+	client.requests = append(client.requests, cloneStructuredCompletionRequest(req))
+	if client.err != nil {
+		return contracts.StructuredCompletionResponse{}, client.err
+	}
+	target, ok := out.(*extractionResponse)
+	if !ok {
+		return contracts.StructuredCompletionResponse{}, errors.New("unexpected output target")
+	}
+	content := append([]byte(nil), client.content...)
+	if len(content) != 0 {
+		if err := json.Unmarshal(content, target); err != nil {
+			return contracts.StructuredCompletionResponse{}, err
+		}
+	} else {
+		*target = client.response
+		var err error
+		content, err = json.Marshal(client.response)
+		if err != nil {
+			return contracts.StructuredCompletionResponse{}, err
+		}
+	}
+	return contracts.StructuredCompletionResponse{Content: content}, nil
+}
+
+func cloneStructuredCompletionRequest(req contracts.StructuredCompletionRequest) contracts.StructuredCompletionRequest {
+	req.Inputs = req.Inputs.Clone()
+	return req
+}