Move NPC registry to canonical namespace

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

@@ -0,0 +1,93 @@
+package npcregistry
+
+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/npcs/identity"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
+)
+
+type orderedNPCResponse struct {
+	value       npcResponse
+	earliest    int
+	hasEvidence bool
+}
+
+func canonicalizeResponse(response *extractionResponse, order shared.SourceRefOrder, sourceID string) {
+	if response == nil {
+		return
+	}
+	ordered := make([]orderedNPCResponse, len(response.NPCs))
+	for index := range response.NPCs {
+		earliest, hasEvidence := canonicalizeNPC(&response.NPCs[index], order, sourceID)
+		ordered[index] = orderedNPCResponse{
+			value:       response.NPCs[index],
+			earliest:    earliest,
+			hasEvidence: hasEvidence,
+		}
+	}
+	sort.SliceStable(ordered, func(i, j int) bool {
+		if ordered[i].hasEvidence != ordered[j].hasEvidence {
+			return ordered[i].hasEvidence
+		}
+		if !ordered[i].hasEvidence {
+			return false
+		}
+		return ordered[i].earliest < ordered[j].earliest
+	})
+	for index := range ordered {
+		response.NPCs[index] = ordered[index].value
+	}
+}
+
+func canonicalizeNPC(npc *npcResponse, order shared.SourceRefOrder, sourceID string) (int, bool) {
+	if npc == nil {
+		return 0, false
+	}
+	refs := order.Canonicalize(canonicalSourceRefs(npc.SourceRefs, sourceID))
+	npc.SourceRefs = npcResponseRefs(refs)
+	return order.EarliestValid(refs)
+}
+
+func canonicalNPCRegistry(response extractionResponse, sourceID string) dnd.NPCRegistry {
+	if response.NPCs == nil {
+		return dnd.NPCRegistry{NPCs: nil}
+	}
+	npcs := make([]dnd.NPC, len(response.NPCs))
+	for index, npc := range response.NPCs {
+		npcs[index] = dnd.NPC{
+			ID:         identity.DeriveID(npc.Name),
+			Name:       npc.Name,
+			SourceRefs: canonicalSourceRefs(npc.SourceRefs, sourceID),
+		}
+	}
+	return dnd.NPCRegistry{NPCs: npcs}
+}
+
+func canonicalSourceRefs(values []npcSourceRefResponse, sourceID string) []source.SourceRef {
+	if values == nil {
+		return nil
+	}
+	out := make([]source.SourceRef, len(values))
+	for index, value := range values {
+		out[index] = source.SourceRef{
+			SourceID:    sourceID,
+			StartUnitID: value.StartUnitID,
+			EndUnitID:   value.EndUnitID,
+		}
+	}
+	return out
+}
+
+func npcResponseRefs(values []source.SourceRef) []npcSourceRefResponse {
+	if values == nil {
+		return nil
+	}
+	out := make([]npcSourceRefResponse, len(values))
+	for index, value := range values {
+		out[index] = npcSourceRefResponse{StartUnitID: value.StartUnitID, EndUnitID: value.EndUnitID}
+	}
+	return out
+}

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

@@ -0,0 +1,170 @@
+package npcregistry
+
+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/npcs/identity"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
+)
+
+const Key = "dnd/npc-registry"
+
+const mappingPolicy = "dnd.npc_registry.extract_mapping.v2"
+
+var requiredCapabilities = []string{
+	"chunks",
+	"source.transcript",
+}
+
+var providedCapabilities = []string{
+	"dnd.npc_registry",
+}
+
+var referenceSlotDescriptions = shared.ReferenceSlotDescriptions{
+	Glossary: "Optional campaign glossary reference material used only for NPC disambiguation.",
+	Party:    "Optional party roster reference material used only for NPC disambiguation.",
+	Players:  "Optional player list reference material used only for NPC disambiguation.",
+	Roster:   "Deprecated alias for party roster reference material used only for NPC disambiguation.",
+}
+
+func referenceSlots() []contracts.ReferenceSlot {
+	return shared.ReferenceSlots(referenceSlotDescriptions)
+}
+
+var _ contracts.Extractor[dnd.NPCRegistry] = (*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.NPCRegistry], error) {
+	if e == nil {
+		return contracts.TypedExtractionResult[dnd.NPCRegistry]{}, extractorErrorf("extractor must not be nil")
+	}
+	if e.llm == nil {
+		return contracts.TypedExtractionResult[dnd.NPCRegistry]{}, extractorErrorf("LLM client must not be nil")
+	}
+	sourceInput, err := shared.PrepareChunkExtraction(ctx, req)
+	if err != nil {
+		return contracts.TypedExtractionResult[dnd.NPCRegistry]{}, 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.NPCRegistry]{}, extractorErrorf("complete structured output: %w", err)
+	}
+	canonicalizeResponse(&response, order, req.Source.ID)
+	return contracts.TypedExtractionResult[dnd.NPCRegistry]{Value: canonicalNPCRegistry(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.NPCRegistryKind,
+		ReferenceSlots: referenceSlots(),
+	}
+}
+
+func Register(registry *pipeline.ExtractorRegistry) error {
+	return pipeline.RegisterExtractorBuilder(registry, ModuleSpec(), validateOptions, func(request pipeline.BuildRequest) (contracts.Extractor[dnd.NPCRegistry], 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 npc registry extractor: "+format, args...)
+}

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

@@ -0,0 +1,200 @@
+package npcregistry
+
+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/npcs/identity"
+)
+
+func TestExtractReturnsCanonicalNPCRegistryFromPrivateResponse(t *testing.T) {
+	client := &fakeNPCsLLMClient{response: extractionResponse{NPCs: []npcResponse{
+		{
+			Name: "Captain Vale", SourceRefs: responseSourceRefs(3, 3),
+		},
+		{
+			Name: "Mira Thorn",
+			SourceRefs: []npcSourceRefResponse{
+				{StartUnitID: 2, EndUnitID: 2},
+				{StartUnitID: 1, EndUnitID: 2},
+				{StartUnitID: 1, EndUnitID: 2},
+			},
+		},
+	}}}
+
+	result, err := newExtractor(t, client).Extract(context.Background(), extractionRequest())
+	if err != nil {
+		t.Fatalf("Extract() error = %v, want nil", err)
+	}
+	want := dnd.NPCRegistry{NPCs: []dnd.NPC{
+		{ID: identity.DeriveID("Mira Thorn"), Name: "Mira Thorn", SourceRefs: []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 1, EndUnitID: 2}, {SourceID: "session-alpha", StartUnitID: 2, EndUnitID: 2}}},
+		{ID: identity.DeriveID("Captain Vale"), Name: "Captain Vale", SourceRefs: []source.SourceRef{{SourceID: "session-alpha", StartUnitID: 3, EndUnitID: 3}}},
+	}}
+	if !reflect.DeepEqual(result.Value, want) {
+		t.Fatalf("Value = %#v, want %#v", result.Value, want)
+	}
+	if len(client.requests) != 1 {
+		t.Fatalf("LLM calls = %d, want 1", len(client.requests))
+	}
+	request := client.requests[0]
+	if request.StageName != Key || request.PromptID != PromptID || request.PromptVersion != SchemaVersion || request.ProfileID != "profile-npcs" || request.SessionID != "session-123" {
+		t.Fatalf("LLM request identity = %#v", request)
+	}
+	transcript := request.Inputs["transcript"]
+	if transcript.Name != "transcript" || transcript.MediaType != "application/json" || transcript.Digest != "sha256:chunk" || transcript.OriginURI != "file:///session-alpha.json" || string(transcript.Content) != string(extractionRequest().Chunk.Content) {
+		t.Fatalf("transcript input = %#v, want chunk-scoped material", transcript)
+	}
+}
+
+func TestExtractOrdersNPCsBySourcePositionRatherThanUnitID(t *testing.T) {
+	client := &fakeNPCsLLMClient{response: extractionResponse{NPCs: []npcResponse{
+		{
+			Name:       "Later NPC",
+			SourceRefs: responseSourceRefs(10, 10),
+		},
+		{
+			Name: "Earlier NPC",
+			SourceRefs: []npcSourceRefResponse{
+				{StartUnitID: 50, EndUnitID: 50},
+				{StartUnitID: 100, EndUnitID: 100},
+			},
+		},
+	}}}
+	req := extractionRequest()
+	req.Source.Units = []source.SourceUnit{
+		{ID: 100, Kind: "transcript_segment", Text: "Earlier NPC appears."},
+		{ID: 10, Kind: "transcript_segment", Text: "Later NPC appears."},
+		{ID: 50, Kind: "transcript_segment", Text: "Earlier NPC appears again."},
+	}
+	req.Chunk.Units = append([]source.SourceUnit(nil), req.Source.Units...)
+	req.Chunk.Ref = source.SourceRef{SourceID: req.Source.ID, StartUnitID: 100, EndUnitID: 50}
+
+	result, err := newExtractor(t, client).Extract(context.Background(), req)
+	if err != nil {
+		t.Fatalf("Extract() error = %v, want nil", err)
+	}
+	if len(result.Value.NPCs) != 2 || result.Value.NPCs[0].Name != "Earlier NPC" || result.Value.NPCs[1].Name != "Later NPC" {
+		t.Fatalf("NPC order = %#v, want source-document order", result.Value.NPCs)
+	}
+}
+
+func TestExtractUsesDocumentOrderForNPCReferencesAndStableTies(t *testing.T) {
+	client := &fakeNPCsLLMClient{response: extractionResponse{NPCs: []npcResponse{
+		{Name: "Later", SourceRefs: responseSourceRefs(10, 10)},
+		{Name: "First", SourceRefs: []npcSourceRefResponse{
+			{StartUnitID: 10, EndUnitID: 10},
+			{StartUnitID: 30, EndUnitID: 30},
+			{StartUnitID: 30, EndUnitID: 30},
+			{StartUnitID: 999, EndUnitID: 0},
+		}},
+		{Name: "Second", SourceRefs: responseSourceRefs(30, 30)},
+	}}}
+	req := extractionRequest()
+	req.Source.Units = []source.SourceUnit{{ID: 30}, {ID: 10}}
+	req.Chunk.Units = append([]source.SourceUnit(nil), req.Source.Units...)
+	req.Chunk.Ref = source.SourceRef{SourceID: req.Source.ID, StartUnitID: 30, EndUnitID: 10}
+
+	result, err := newExtractor(t, client).Extract(context.Background(), req)
+	if err != nil {
+		t.Fatalf("Extract() error = %v", err)
+	}
+	if got := []string{result.Value.NPCs[0].Name, result.Value.NPCs[1].Name, result.Value.NPCs[2].Name}; !reflect.DeepEqual(got, []string{"First", "Second", "Later"}) {
+		t.Fatalf("NPC order = %#v, want document chronology with stable equal-evidence ties", got)
+	}
+	refs := result.Value.NPCs[0].SourceRefs
+	if got := []int{refs[0].StartUnitID, refs[1].StartUnitID, refs[2].StartUnitID}; !reflect.DeepEqual(got, []int{30, 10, 999}) {
+		t.Fatalf("source refs = %#v, want document order with exact duplicate removed", refs)
+	}
+	refs[0].StartUnitID = 777
+	for _, npc := range client.response.NPCs {
+		for _, ref := range npc.SourceRefs {
+			if ref.StartUnitID == 777 {
+				t.Fatal("result source references alias the model response")
+			}
+		}
+	}
+}
+
+func TestExtractPassesCampaignReferencesAsPromptInputs(t *testing.T) {
+	client := &fakeNPCsLLMClient{response: extractionResponse{NPCs: []npcResponse{}}}
+	req := extractionRequest()
+	req.References = contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{
+		"players":  {Slot: contracts.ReferenceSlot{Name: "players"}, Items: []contracts.ReferenceItem{{SlotName: "players", Content: []byte("Dana: Mira")}}},
+		"party":    {Slot: contracts.ReferenceSlot{Name: "party"}, Items: []contracts.ReferenceItem{{SlotName: "party", Content: []byte("Mira: ranger")}}},
+		"glossary": {Slot: contracts.ReferenceSlot{Name: "glossary"}, Items: []contracts.ReferenceItem{{SlotName: "glossary", Content: []byte("Greencloak: local title")}}},
+	}}
+	if _, err := newExtractor(t, client).Extract(context.Background(), req); err != nil {
+		t.Fatalf("Extract() error = %v, want nil", err)
+	}
+	inputs := client.requests[0].Inputs
+	if string(inputs["players"].Content) != "Dana: Mira" || string(inputs["party"].Content) != "Mira: ranger" || string(inputs["glossary"].Content) != "Greencloak: local title" {
+		t.Fatalf("reference inputs = %#v", inputs)
+	}
+	if strings.Contains(string(inputs["transcript"].Content), "local title") {
+		t.Fatal("transcript input contains reference content")
+	}
+}
+
+func TestExtractPreservesMalformedCandidatesForValidators(t *testing.T) {
+	client := &fakeNPCsLLMClient{response: extractionResponse{NPCs: []npcResponse{{
+		Name:       "",
+		SourceRefs: []npcSourceRefResponse{{StartUnitID: 99, EndUnitID: 0}},
+	}}}}
+	result, err := newExtractor(t, client).Extract(context.Background(), extractionRequest())
+	if err != nil {
+		t.Fatalf("Extract() error = %v, want nil", err)
+	}
+	if len(result.Value.NPCs) != 1 || result.Value.NPCs[0].ID != "" || result.Value.NPCs[0].Name != "" {
+		t.Fatalf("malformed candidate = %#v, want invalid values preserved", result.Value)
+	}
+	if refs := result.Value.NPCs[0].SourceRefs; len(refs) != 1 || refs[0].SourceID != "session-alpha" || refs[0].StartUnitID != 99 || refs[0].EndUnitID != 0 {
+		t.Fatalf("malformed source refs = %#v, want invalid range preserved after exact deduplication", refs)
+	}
+}
+
+func TestExtractMapsRawSemanticCandidatesWithoutRepair(t *testing.T) {
+	client := &fakeNPCsLLMClient{content: []byte(`{"npcs":[{"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)
+	}
+	npc := result.Value.NPCs[0]
+	if npc.ID != "" || npc.Name != "" {
+		t.Fatalf("NPC = %#v, want blank semantic values preserved", npc)
+	}
+	if refs := npc.SourceRefs; len(refs) != 1 || refs[0] != (source.SourceRef{SourceID: "session-alpha", StartUnitID: 0, EndUnitID: -1}) {
+		t.Fatalf("source refs = %#v, want raw nonpositive candidates preserved", refs)
+	}
+}
+
+func TestExtractRetainsLocalErrorContextAndProviderFailures(t *testing.T) {
+	request := extractionRequest()
+	extractor := newExtractor(t, &fakeNPCsLLMClient{response: extractionResponse{NPCs: []npcResponse{}}})
+	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 LLM client", extractor: &Extractor{}, req: request, want: "LLM client"},
+		{name: "wrapped preflight failure", extractor: extractor, 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 npc registry") || !strings.Contains(err.Error(), test.want) {
+				t.Fatalf("Extract() error = %v, want contextual local error", err)
+			}
+		})
+	}
+	_, err := newExtractor(t, &fakeNPCsLLMClient{err: errors.New("provider unavailable")}).Extract(context.Background(), request)
+	if err == nil || !strings.Contains(err.Error(), "dnd npc registry") || !strings.Contains(err.Error(), "provider unavailable") {
+		t.Fatalf("provider Extract() error = %v, want contextual provider error", err)
+	}
+}

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

@@ -0,0 +1,15 @@
+package npcregistry
+
+type extractionResponse struct {
+	NPCs []npcResponse `json:"npcs"`
+}
+
+type npcResponse struct {
+	Name       string                 `json:"name"`
+	SourceRefs []npcSourceRefResponse `json:"source_refs"`
+}
+
+type npcSourceRefResponse struct {
+	StartUnitID int `json:"start_unit_id"`
+	EndUnitID   int `json:"end_unit_id"`
+}

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

@@ -0,0 +1,74 @@
+package npcregistry
+
+import (
+	"fmt"
+	"io/fs"
+	"sync"
+
+	rootassets "gitea.maximumdirect.net/eric/notarius/assets"
+	"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: "dnd.npc_registry",
+	ModuleFiles: []promptfs.ModulePromptFile{
+		{Name: "prompt.yaml", Path: "prompts/prompt.yaml"},
+		{Name: "instructions.md", Path: "prompts/instructions.md"},
+	},
+	SharedFiles: []string{
+		"common-dnd-system.md",
+		"common-dnd-extraction-evidence.md",
+		"common-dnd-identity.md",
+		"common-dnd-transcript-chunk.md",
+		"common-dnd-references.md",
+	},
+}
+
+func moduleAssetFS() (fs.FS, error) {
+	assets, err := fs.Sub(rootassets.FS(), "dnd/npc-registry/extract")
+	if err != nil {
+		return nil, fmt.Errorf("scope NPC extraction assets: %w", err)
+	}
+	return assets, nil
+}
+
+func RegisterPromptAssets(registry *llm.AssetRegistry) error {
+	assets, err := moduleAssetFS()
+	if err != nil {
+		return err
+	}
+	promptFS, err := promptAssetManifest.PromptFS(assets)
+	if err != nil {
+		return fmt.Errorf("prepare NPC prompt assets: %w", err)
+	}
+	if err := registry.RegisterPromptFS(promptFS, promptAssetRoot); err != nil {
+		return err
+	}
+	schemas, err := fs.Sub(assets, "schemas")
+	if err != nil {
+		return fmt.Errorf("scope NPC extraction schemas: %w", err)
+	}
+	return registry.RegisterSchemaFS(schemas, ".")
+}
+
+func promptAssetMetadata() (string, error) {
+	promptAssetHashOnce.Do(func() {
+		assets, err := moduleAssetFS()
+		if err != nil {
+			promptAssetHashErr = err
+			return
+		}
+		promptAssetHash, promptAssetHashErr = promptAssetManifest.Hash(assets)
+	})
+	return promptAssetHash, promptAssetHashErr
+}
+
+var (
+	promptAssetHashOnce sync.Once
+	promptAssetHash     string
+	promptAssetHashErr  error
+)

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

@@ -0,0 +1,62 @@
+package npcregistry
+
+import (
+	"context"
+	"encoding/json"
+	"strings"
+	"testing"
+	"time"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
+	"gitea.maximumdirect.net/eric/promptkit"
+)
+
+func TestRegisterPromptAssetsAndPrepareNPCPrompt(t *testing.T) {
+	registry := llm.NewAssetRegistry()
+	if err := RegisterPromptAssets(registry); err != nil {
+		t.Fatalf("RegisterPromptAssets() error = %v, want nil", err)
+	}
+	options, err := registry.PromptKitOptions()
+	if err != nil {
+		t.Fatalf("PromptKitOptions() error = %v, want nil", err)
+	}
+	options = append(options, promptkit.WithProfiles(promptkit.OpenAICompatibleProfile(promptkit.OpenAICompatibleProfileConfig{
+		ID: "npc-test-profile", Endpoint: "http://127.0.0.1:1/v1", Model: "npc-test-model",
+	})))
+	engine, err := promptkit.NewEngine(promptkit.Config{Timeout: time.Second}, options...)
+	if err != nil {
+		t.Fatalf("NewEngine() error = %v, want nil", err)
+	}
+	prepared, err := engine.Prepare(context.Background(), promptkit.RunRequest{
+		PromptID: PromptID, PromptVersion: SchemaVersion, ProfileID: "npc-test-profile",
+		Inputs: map[string]promptkit.ArtifactRef{
+			"transcript": promptkit.InlineWithURI("file:///session.json", `{"units":[{"sentinel":"npc-transcript"}]}`),
+			"players":    promptkit.Inline("npc-player"),
+			"party":      promptkit.Inline(" "),
+			"glossary":   promptkit.Inline(" "),
+		},
+	})
+	if err != nil {
+		t.Fatalf("Prepare() error = %v, want nil", err)
+	}
+	if prepared.PromptID != PromptID || prepared.OutputContract.SchemaPath != "dnd_npc_registry_llm.v1.json" {
+		t.Fatalf("prepared prompt = %#v, want NPC prompt identity and wiring", prepared)
+	}
+}
+
+func TestPromptMetadataAndDiagnosticsDoNotContainRawAssets(t *testing.T) {
+	hash, err := promptAssetMetadata()
+	if err != nil || !strings.HasPrefix(hash, "sha256:") {
+		t.Fatalf("promptAssetMetadata() = %q, %v; want hash", hash, err)
+	}
+	metadata := newExtractor(t, &fakeNPCsLLMClient{}).ManifestMetadata()
+	payload, err := json.Marshal(metadata)
+	if err != nil {
+		t.Fatal(err)
+	}
+	for _, forbidden := range []string{"common-dnd-system", "dnd_npc_registry_llm.v1.json"} {
+		if strings.Contains(string(payload), forbidden) {
+			t.Fatalf("metadata leaked raw prompt/schema content %q: %s", forbidden, payload)
+		}
+	}
+}

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

@@ -0,0 +1,102 @@
+package npcregistry
+
+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"
+)
+
+func TestNewRequiresLLMClientAndRejectsAmbiguousReferences(t *testing.T) {
+	if _, err := New(nil, Options{}); err == nil || !strings.Contains(err.Error(), "LLM client") {
+		t.Fatalf("New(nil) error = %v, want dependency error", err)
+	}
+	if _, err := New(&fakeNPCsLLMClient{}, Options{}, contracts.ReferenceSet{}, contracts.ReferenceSet{}); err == nil || !strings.Contains(err.Error(), "at most one reference set") {
+		t.Fatalf("New() error = %v, want reference-set error", err)
+	}
+	if got := newExtractor(t, &fakeNPCsLLMClient{}).Key(); got != Key {
+		t.Fatalf("Key() = %q, want %q", got, Key)
+	}
+}
+
+func TestModuleSpecAndReferenceSlots(t *testing.T) {
+	got := ModuleSpec()
+	want := pipeline.ModuleSpec{
+		Key:            Key,
+		Stage:          pipeline.StageExtract,
+		ExecutionClass: contracts.ExecutionClassLLMBacked,
+		Requires:       []string{"chunks", "source.transcript"},
+		Provides:       []string{"dnd.npc_registry"},
+		ArtifactKind:   dnd.NPCRegistryKind,
+		ReferenceSlots: []contracts.ReferenceSlot{
+			{Name: "glossary", Description: "Optional campaign glossary reference material used only for NPC disambiguation.", AcceptedMediaTypes: []string{"application/json", "application/x-yaml", "application/yaml", "text/markdown", "text/plain"}},
+			{Name: "party", Description: "Optional party roster reference material used only for NPC disambiguation.", AcceptedMediaTypes: []string{"application/json", "application/x-yaml", "application/yaml", "text/markdown", "text/plain"}},
+			{Name: "players", Description: "Optional player list reference material used only for NPC disambiguation.", AcceptedMediaTypes: []string{"application/json", "application/x-yaml", "application/yaml", "text/markdown", "text/plain"}},
+			{Name: "roster", Description: "Deprecated alias for party roster reference material used only for NPC disambiguation.", AcceptedMediaTypes: []string{"application/json", "application/x-yaml", "application/yaml", "text/markdown", "text/plain"}},
+		},
+	}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("ModuleSpec() = %#v, want %#v", got, want)
+	}
+	got.Requires[0] = "changed"
+	got.Provides[0] = "changed"
+	got.ReferenceSlots[0].AcceptedMediaTypes[0] = "changed"
+	if !reflect.DeepEqual(ModuleSpec(), want) {
+		t.Fatal("ModuleSpec() returned mutable shared slices")
+	}
+	extractor := newExtractor(t, &fakeNPCsLLMClient{})
+	if !reflect.DeepEqual(extractor.ReferenceSlots(), want.ReferenceSlots) {
+		t.Fatalf("ReferenceSlots() = %#v, want %#v", extractor.ReferenceSlots(), want.ReferenceSlots)
+	}
+}
+
+func TestRegisterStoresTypedModuleSpec(t *testing.T) {
+	registry := pipeline.NewExtractorRegistry()
+	if err := Register(registry); err != nil {
+		t.Fatalf("Register() error = %v, want nil", err)
+	}
+	got, ok := registry.Spec(Key)
+	if !ok || !reflect.DeepEqual(got, ModuleSpec()) {
+		t.Fatalf("registry.Spec(%q) = %#v, present = %t", Key, got, ok)
+	}
+	if err := Register(nil); err == nil || !strings.Contains(err.Error(), "extractor registry") {
+		t.Fatalf("Register(nil) error = %v, want registry error", err)
+	}
+	if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil || !strings.Contains(err.Error(), "unknown option") {
+		t.Fatalf("DecodeOptions() error = %v, want strict options error", err)
+	}
+}
+
+func TestExtractorMetadataAndCheckpointIdentity(t *testing.T) {
+	extractor := newExtractor(t, &fakeNPCsLLMClient{})
+	metadata := extractor.ManifestMetadata()
+	for key, want := 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": "dnd.npc_registry.identity.v1",
+		"mapping_policy":  mappingPolicy,
+	} {
+		if metadata[key] != want {
+			t.Fatalf("metadata[%q] = %#v, want %q", key, metadata[key], want)
+		}
+	}
+	for _, key := range []string{"prompt_sha256", "response_schema_sha256"} {
+		if value, ok := metadata[key].(string); !ok || !strings.HasPrefix(value, "sha256:") {
+			t.Fatalf("metadata[%q] = %#v, want hash", key, metadata[key])
+		}
+	}
+	fingerprints := extractor.CheckpointFingerprints()
+	want := map[string]string{"prompt": metadata["prompt_sha256"].(string), "response_schema": metadata["response_schema_sha256"].(string), "identity_policy": "dnd.npc_registry.identity.v1", "mapping_policy": mappingPolicy}
+	if len(fingerprints) != len(want) {
+		t.Fatalf("CheckpointFingerprints() = %#v, want %d entries", fingerprints, len(want))
+	}
+	for _, fingerprint := range fingerprints {
+		if fingerprint.Value != want[fingerprint.Name] {
+			t.Fatalf("fingerprint %q = %q, want %#v", fingerprint.Name, fingerprint.Value, want)
+		}
+	}
+}

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

@@ -0,0 +1,25 @@
+package npcregistry
+
+import "gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
+
+const (
+	PromptID           = "dnd.npc_registry"
+	ResponseSchemaKey  = llm.ResponseSchemaKey("dnd_npc_registry_llm")
+	ResponseSchemaID   = "notarius.dnd.npc_registry.llm"
+	ResponseSchemaName = "notarius_dnd_npc_registry_llm_v1"
+	SchemaVersion      = "v1"
+)
+
+func loadResponseSchema() (llm.ResponseSchema, error) {
+	assets, err := moduleAssetFS()
+	if err != nil {
+		return llm.ResponseSchema{}, err
+	}
+	return llm.LoadResponseSchema(assets, llm.ResponseSchemaDefinition{
+		Key:       ResponseSchemaKey,
+		ID:        ResponseSchemaID,
+		Version:   SchemaVersion,
+		Name:      ResponseSchemaName,
+		AssetPath: "schemas/dnd_npc_registry_llm.v1.json",
+	})
+}

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

@@ -0,0 +1,138 @@
+package npcregistry
+
+import (
+	"bytes"
+	"encoding/json"
+	"strings"
+	"testing"
+
+	"github.com/santhosh-tekuri/jsonschema/v6"
+)
+
+func TestLoadResponseSchemaUsesPrivateNPCSchema(t *testing.T) {
+	schema, err := loadResponseSchema()
+	if err != nil {
+		t.Fatalf("loadResponseSchema() error = %v, want nil", err)
+	}
+	if schema.Key != ResponseSchemaKey || schema.ID != ResponseSchemaID || schema.Version != SchemaVersion || schema.Name != ResponseSchemaName || !strings.HasPrefix(schema.SHA256, "sha256:") || !json.Valid(schema.JSONSchema) {
+		t.Fatalf("schema = %#v, want private NPC schema identity", schema)
+	}
+	valid := map[string]any{"npcs": []any{map[string]any{
+		"name":        "Mira Thorn",
+		"source_refs": []any{map[string]any{"start_unit_id": 1, "end_unit_id": 2}},
+	}}}
+	validJSON, err := json.Marshal(valid)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := validateJSONSchema(validJSON, schema.JSONSchema); err != nil {
+		t.Fatalf("valid private NPC response rejected: %v", err)
+	}
+	for _, test := range []struct {
+		name     string
+		response map[string]any
+		valid    bool
+	}{
+		{
+			name: "semantic blanks and empty collections",
+			response: map[string]any{"npcs": []any{map[string]any{
+				"name": "", "source_refs": []any{},
+			}}},
+			valid: true,
+		},
+		{
+			name: "nonpositive unit candidates",
+			response: map[string]any{"npcs": []any{map[string]any{
+				"name":        "Mira Thorn",
+				"source_refs": []any{map[string]any{"start_unit_id": 0, "end_unit_id": -1}},
+			}}},
+			valid: true,
+		},
+		{
+			name: "missing required field",
+			response: map[string]any{"npcs": []any{map[string]any{
+				"source_refs": []any{},
+			}}},
+		},
+		{
+			name: "unknown field",
+			response: map[string]any{"npcs": []any{map[string]any{
+				"name": "Mira Thorn", "source_refs": []any{}, "id": "assigned later",
+			}}},
+		},
+		{
+			name: "wrong field type",
+			response: map[string]any{"npcs": []any{map[string]any{
+				"name": 7, "source_refs": []any{},
+			}}},
+		},
+		{
+			name: "noninteger source identifier",
+			response: map[string]any{"npcs": []any{map[string]any{
+				"name":        "Mira Thorn",
+				"source_refs": []any{map[string]any{"start_unit_id": 1.5, "end_unit_id": 2}},
+			}}},
+		},
+	} {
+		t.Run(test.name, func(t *testing.T) {
+			content, err := json.Marshal(test.response)
+			if err != nil {
+				t.Fatal(err)
+			}
+			err = validateJSONSchema(content, schema.JSONSchema)
+			if (err == nil) != test.valid {
+				t.Fatalf("validateJSONSchema() error = %v, want valid=%t", err, test.valid)
+			}
+		})
+	}
+	if err := validateJSONSchema([]byte(`{"npcs":`), schema.JSONSchema); err == nil {
+		t.Fatal("validateJSONSchema() error = nil, want malformed JSON rejected")
+	}
+	withID := map[string]any{"npcs": []any{map[string]any{
+		"name": "Mira Thorn", "id": "assigned-later",
+		"source_refs": []any{map[string]any{"start_unit_id": 1, "end_unit_id": 2}},
+	}}}
+	withIDJSON, err := json.Marshal(withID)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if err := validateJSONSchema(withIDJSON, schema.JSONSchema); err == nil {
+		t.Fatal("private schema accepted framework-assigned id")
+	}
+}
+
+func TestResponseSchemaIsMutationSafeAndDiagnosticsRedactContent(t *testing.T) {
+	first, err := loadResponseSchema()
+	if err != nil {
+		t.Fatal(err)
+	}
+	first.JSONSchema[0] = '['
+	second, err := loadResponseSchema()
+	if err != nil || !json.Valid(second.JSONSchema) || bytes.Equal(first.JSONSchema, second.JSONSchema) {
+		t.Fatalf("second schema = %s, %v; want defensive copy", second.JSONSchema, err)
+	}
+	diagnostics := second.DiagnosticsMap()
+	if _, ok := diagnostics["json_schema"]; ok {
+		t.Fatalf("schema diagnostics included raw content: %#v", diagnostics)
+	}
+}
+
+func validateJSONSchema(instanceContent, schemaContent []byte) error {
+	instance, err := jsonschema.UnmarshalJSON(bytes.NewReader(instanceContent))
+	if err != nil {
+		return err
+	}
+	schemaDocument, err := jsonschema.UnmarshalJSON(bytes.NewReader(schemaContent))
+	if err != nil {
+		return err
+	}
+	compiler := jsonschema.NewCompiler()
+	if err := compiler.AddResource("schema.json", schemaDocument); err != nil {
+		return err
+	}
+	compiled, err := compiler.Compile("schema.json")
+	if err != nil {
+		return err
+	}
+	return compiled.Validate(instance)
+}

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

@@ -0,0 +1,110 @@
+package npcregistry
+
+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-alpha: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...),
+		Metadata:  map[string]any{"ignored": "chunk metadata"},
+	}
+	return contracts.TypedExtractionRequest{
+		Source:      doc,
+		Chunk:       chunk,
+		SourceInput: contracts.NewLLMInputMaterial("source", chunk.MediaType, chunk.Content, "sha256:chunk", "file:///session-alpha.json"),
+		SessionID:   "session-123",
+		LLMProfile:  "profile-npcs",
+	}
+}
+
+func sourceDocument() *source.SourceDocument {
+	return &source.SourceDocument{
+		ID:     "session-alpha",
+		Kind:   "transcript",
+		Format: "application/vnd.seriatim.minimal+json",
+		Digest: "sha256:test",
+		Units: []source.SourceUnit{
+			{ID: 1, Kind: "transcript_segment", Text: "Mira Thorn greets the party."},
+			{ID: 2, Kind: "transcript_segment", Text: "The Greencloak watches the northern road."},
+			{ID: 3, Kind: "transcript_segment", Text: "Captain Vale reports to Mira Thorn."},
+		},
+	}
+}
+
+func responseSourceRefs(startUnitID, endUnitID int) []npcSourceRefResponse {
+	return []npcSourceRefResponse{{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
+}
+
+func cloneStructuredCompletionRequest(req contracts.StructuredCompletionRequest) contracts.StructuredCompletionRequest {
+	req.Inputs = req.Inputs.Clone()
+	if len(req.Vars) == 0 {
+		req.Vars = nil
+		return req
+	}
+	vars := make(map[string]any, len(req.Vars))
+	for key, value := range req.Vars {
+		vars[key] = value
+	}
+	req.Vars = vars
+	return req
+}
+
+type fakeNPCsLLMClient struct {
+	response extractionResponse
+	content  []byte
+	err      error
+	requests []contracts.StructuredCompletionRequest
+}
+
+func (client *fakeNPCsLLMClient) 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
+}