package locationregistry 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/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/entityreconcile" ) func TestModuleContractAndMetadata(t *testing.T) { want := pipeline.ModuleSpec{Key: Key, Stage: pipeline.StageNormalize, ExecutionClass: contracts.ExecutionClassLLMBacked, Requires: []string{"merged"}, Provides: []string{"normalized"}, ArtifactKind: dnd.LocationRegistryKind} if got := ModuleSpec(); !reflect.DeepEqual(got, want) { t.Fatalf("ModuleSpec() = %#v, want %#v", got, want) } registry := pipeline.NewNormalizerRegistry() if err := Register(registry); err != nil { t.Fatal(err) } if _, err := New(nil, Options{}); err == nil { t.Fatal("New() accepted nil client") } normalizer := newNormalizer(t, &recordingLocationNormalizerClient{}) metadata := normalizer.ManifestMetadata() if metadata["identity_policy"] != identity.Policy || metadata["response_schema_id"] != entityreconcile.ResponseSchemaID || metadata["normalization_policy"] != normalizationPolicy || metadata["semantic_context_radius"] != semanticContextRadius { t.Fatalf("metadata = %#v", metadata) } if got := normalizer.CheckpointFingerprints(); len(got) != 5 || got[2].Value != identity.Policy || got[3].Value != normalizationPolicy || got[4].Value != semanticContextPolicy+":2" { t.Fatalf("fingerprints = %#v", got) } } func TestNormalizePreparesOnlyExactDuplicatesAndRetainsSameNameAndNestedPlaces(t *testing.T) { input := dnd.LocationRegistry{Locations: []dnd.Location{ {Name: " The Tavern ", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}, {Name: "the tavern", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 1, EndUnitID: 1}}}, {Name: "The Tavern", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 2, EndUnitID: 2}}}, {Name: "The Tavern Cellar", SourceRefs: []source.SourceRef{{SourceID: "session", StartUnitID: 2, EndUnitID: 2}}}, }} before := dnd.LocationRegistry{Locations: append([]dnd.Location(nil), input.Locations...)} result, err := newNormalizer(t, &recordingLocationNormalizerClient{}).Normalize(context.Background(), normalizeRequest(input)) if err != nil || len(result.Value.Locations) != 3 { t.Fatalf("Normalize() = %#v, %v; want one exact duplicate removed", result, err) } if !reflect.DeepEqual(input, before) { t.Fatalf("Normalize() mutated input: %#v", input) } if got := []string{result.Value.Locations[0].Name, result.Value.Locations[1].Name, result.Value.Locations[2].Name}; !reflect.DeepEqual(got, []string{"The Tavern", "The Tavern", "The Tavern Cellar"}) { t.Fatalf("locations = %#v, want same names and nested place retained", got) } if result.Value.Locations[0].ID == result.Value.Locations[1].ID || !hasWarning(result.Warnings, ReasonCodeDuplicateLocationCollapsed) { t.Fatalf("result = %#v, want evidence-anchored IDs and exact duplicate warning", result) } } func TestNormalizeAppliesSafeAliasGroupAndUsesOpaqueInputs(t *testing.T) { client := &recordingLocationNormalizerClient{response: `{"duplicate_groups":[{"members":["candidate-000001","candidate-000002"],"canonical":"candidate-000002"}]}`} doc := semanticDocument() input := dnd.LocationRegistry{Locations: []dnd.Location{ {Name: "Old Mill", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}}, {Name: "the Greencloak's refuge", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}}, {Name: "The Tavern", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 30, EndUnitID: 30}}}, }} result, err := newNormalizer(t, client).Normalize(context.Background(), normalizeRequestWithSource(input, doc)) if err != nil || result.Retry != nil || len(result.Value.Locations) != 2 { t.Fatalf("Normalize() = %#v, %v", result, err) } merged := result.Value.Locations[0] if merged.Name != "the Greencloak's refuge" || merged.ID != identity.DeriveID(merged.Name, merged.SourceRefs) || len(merged.SourceRefs) != 2 || !hasWarning(result.Warnings, ReasonCodeDuplicateLocationCollapsed) { t.Fatalf("merged location = %#v, warnings = %#v", merged, result.Warnings) } encoded := string(client.requests[0].Inputs["candidates"].Content) + string(client.requests[0].Inputs["transcript"].Content) if strings.Contains(encoded, doc.ID) || !strings.Contains(encoded, "candidate-000001") || strings.Contains(encoded, merged.ID) { t.Fatalf("private inputs = %s", encoded) } } func TestNormalizeRejectsUnsafeAndOverlappingGroupsWithoutLosingCandidates(t *testing.T) { doc := semanticDocument() input := dnd.LocationRegistry{Locations: []dnd.Location{ {Name: "Old Mill", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}}, {Name: "Mill", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}}, {Name: "Tavern", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 30, EndUnitID: 30}}}, }} client := &recordingLocationNormalizerClient{response: `{"duplicate_groups":[{"members":["candidate-000001","candidate-000002"],"canonical":"candidate-000001"},{"members":["candidate-000002","candidate-000003"],"canonical":"candidate-000003"}]}`} result, err := newNormalizer(t, client).Normalize(context.Background(), normalizeRequestWithSource(input, doc)) if err != nil || result.Retry == nil || len(result.Value.Locations) != 3 || !strings.Contains(result.Retry.Message, "overlapping_member") { t.Fatalf("Normalize() = %#v, %v; want safe retry fallback", result, err) } if len(result.Retry.FallbackWarnings) != 1 || !strings.Contains(result.Retry.FallbackWarnings[0].Message, "2 proposal group") { t.Fatalf("fallback warnings = %#v", result.Retry.FallbackWarnings) } } func TestNormalizeHandlesRetryFallbackAndErrors(t *testing.T) { doc := semanticDocument() input := dnd.LocationRegistry{Locations: []dnd.Location{{Name: "Old Mill", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}}}, {Name: "Mill", SourceRefs: []source.SourceRef{{SourceID: doc.ID, StartUnitID: 20, EndUnitID: 20}}}}} invalid, err := newNormalizer(t, &recordingLocationNormalizerClient{err: contracts.ErrInvalidStructuredOutput}).Normalize(context.Background(), normalizeRequestWithSource(input, doc)) if err != nil || invalid.Retry == nil || invalid.Retry.ReasonCode != ReasonCodeLocationSemanticProposalInvalid { t.Fatalf("invalid result = %#v, %v", invalid, err) } _, err = newNormalizer(t, &recordingLocationNormalizerClient{err: errors.New("provider unavailable")}).Normalize(context.Background(), normalizeRequestWithSource(input, doc)) if err == nil || !strings.Contains(err.Error(), "provider unavailable") { t.Fatalf("provider error = %v", err) } warnings := make([]contracts.Warning, 25) bounded := limitWarningsForRetry(warnings) if len(bounded) != 19 || bounded[len(bounded)-1].ReasonCode != ReasonCodeLocationNormalizationWarningsOmitted { t.Fatalf("retry warning limit = %#v", bounded) } } func TestNormalizeOrdersEvidenceAndIsIdempotent(t *testing.T) { doc := &source.SourceDocument{ID: "ordered", Units: []source.SourceUnit{{ID: 30}, {ID: 10}}} input := dnd.LocationRegistry{Locations: []dnd.Location{{Name: "Old Mill", SourceRefs: []source.SourceRef{ {SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10}, {SourceID: doc.ID, StartUnitID: 30, EndUnitID: 30}, {SourceID: doc.ID, StartUnitID: 30, EndUnitID: 30}, }}}} normalizer := newNormalizer(t, &recordingLocationNormalizerClient{}) first, err := normalizer.Normalize(context.Background(), normalizeRequestWithSource(input, doc)) if err != nil || !reflect.DeepEqual([]int{first.Value.Locations[0].SourceRefs[0].StartUnitID, first.Value.Locations[0].SourceRefs[1].StartUnitID}, []int{30, 10}) { t.Fatalf("first Normalize() = %#v, %v; want document-ordered evidence", first, err) } second, err := normalizer.Normalize(context.Background(), normalizeRequestWithSource(first.Value, doc)) if err != nil || !reflect.DeepEqual(second.Value, first.Value) { t.Fatalf("second Normalize() = %#v, %v; want idempotent value %#v", second, err, first.Value) } }