Add D&D NPC extraction and validation

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

@@ -0,0 +1,100 @@
+package npcs
+
+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,
+		Requires:     []string{"chunks", "source.transcript"},
+		Provides:     []string{"dnd.npcs"},
+		ArtifactKind: dnd.NPCListKind,
+		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.npcs.identity.v1",
+	} {
+		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.npcs.identity.v1"}
+	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)
+		}
+	}
+}