Add item registry extraction and validation

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

@@ -0,0 +1,60 @@
+package itemregistry
+
+import (
+	"encoding/json"
+	"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/items/identity"
+)
+
+func TestModuleRegistrationMetadataAndRedaction(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(&fakeItemsLLMClient{}, 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.item_registry"}, ArtifactKind: dnd.ItemRegistryKind, 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")
+	}
+	references := contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{
+		"glossary": {Items: []contracts.ReferenceItem{{Content: []byte("secret-campaign-context")}}},
+	}}
+	metadata := newExtractor(t, &fakeItemsLLMClient{}, references).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)
+		}
+	}
+	encoded, err := json.Marshal(metadata)
+	if err != nil || strings.Contains(string(encoded), "secret-campaign-context") || strings.Contains(string(encoded), "session-items") {
+		t.Fatalf("manifest metadata = %s, want static redacted provenance only", encoded)
+	}
+	if got := newExtractor(t, &fakeItemsLLMClient{}).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)
+	}
+}