Reuse canonical item occurrence evidence

internal/modules/dnd/normalize/itemoccurrences/normalizer.go

@@ -113,6 +113,7 @@ func (n *Normalizer) Normalize(ctx context.Context, req contracts.TypedNormalize
 
 type normalizedRecord struct {
 	occurrence dnd.ItemOccurrence
+	identity   string
 	inputIndex int
 }
 
@@ -125,7 +126,7 @@ func normalizeList(input dnd.ItemOccurrenceList, index source.DocumentIndex, ord
 	warnings := make([]contracts.Warning, 0)
 	for index, inputOccurrence := range input.Occurrences {
 		occurrence, changedFields, found, refsChanged := normalizeOccurrence(inputOccurrence, order, registry)
-		records[index] = normalizedRecord{occurrence: occurrence, inputIndex: index}
+		records[index] = normalizedRecord{occurrence: occurrence, identity: itemoccurrencemodel.CanonicalExactIdentity(occurrence), inputIndex: index}
 		if len(changedFields) != 0 {
 			warnings = append(warnings, contracts.Warning{
 				Scope:      occurrenceScope(index),
@@ -153,7 +154,7 @@ func normalizeList(input dnd.ItemOccurrenceList, index source.DocumentIndex, ord
 	}
 
 	sort.SliceStable(records, func(left, right int) bool {
-		return itemoccurrencemodel.Less(order, records[left].occurrence, records[right].occurrence)
+		return itemoccurrencemodel.CanonicalLess(order, records[left].occurrence, records[right].occurrence)
 	})
 	for position, record := range records {
 		if position == record.inputIndex {
@@ -166,7 +167,7 @@ func normalizeList(input dnd.ItemOccurrenceList, index source.DocumentIndex, ord
 		})
 	}
 
-	output, duplicateWarnings := collapseDuplicates(records, index, order)
+	output, duplicateWarnings := collapseDuplicates(records, index)
 	warnings = append(warnings, duplicateWarnings...)
 	return dnd.ItemOccurrenceList{Occurrences: output}, diagnostics.LimitWarnings(warnings, "item_occurrences", ReasonCodeWarningsOmitted)
 }
@@ -208,28 +209,35 @@ func cloneOccurrence(input dnd.ItemOccurrence) dnd.ItemOccurrence {
 }
 
 type duplicateGroup struct {
-	retainedIndex int
-	removed       []int
+	retainedIndex  int
+	retainedRecord int
+	removed        []int
 }
 
-func collapseDuplicates(records []normalizedRecord, index source.DocumentIndex, order shared.SourceRefOrder) ([]dnd.ItemOccurrence, []contracts.Warning) {
+func collapseDuplicates(records []normalizedRecord, index source.DocumentIndex) ([]dnd.ItemOccurrence, []contracts.Warning) {
 	if len(records) == 0 {
 		return make([]dnd.ItemOccurrence, 0), nil
 	}
 
 	keep := make([]bool, len(records))
 	groups := make([]duplicateGroup, 0)
-	groupByKey := make(map[string]int)
+	groupByKey := make(map[string][]int)
 	for recordIndex, record := range records {
 		if !itemoccurrencemodel.ValidSourceRefs(index, record.occurrence.SourceRefs) {
 			keep[recordIndex] = true
 			continue
 		}
-		key := itemoccurrencemodel.ExactIdentity(order, record.occurrence)
-		groupIndex, exists := groupByKey[key]
-		if !exists {
-			groupByKey[key] = len(groups)
-			groups = append(groups, duplicateGroup{retainedIndex: record.inputIndex})
+		groupIndex := -1
+		for _, candidate := range groupByKey[record.identity] {
+			if itemoccurrencemodel.CanonicalExactEqual(records[groups[candidate].retainedRecord].occurrence, record.occurrence) {
+				groupIndex = candidate
+				break
+			}
+		}
+		if groupIndex < 0 {
+			groupIndex = len(groups)
+			groupByKey[record.identity] = append(groupByKey[record.identity], groupIndex)
+			groups = append(groups, duplicateGroup{retainedIndex: record.inputIndex, retainedRecord: recordIndex})
 			keep[recordIndex] = true
 			continue
 		}

internal/modules/dnd/normalize/npcoccurrences/normalizer.go

@@ -35,13 +35,6 @@ const (
 var requiredCapabilities = []string{"merged"}
 var providedCapabilities = []string{"normalized"}
 
-var referenceSlotDescriptions = shared.ReferenceSlotDescriptions{
-	Glossary: "Optional campaign glossary reference material used only for occurrence disambiguation.",
-	Party:    "Optional party roster reference material used only for occurrence disambiguation.",
-	Players:  "Optional player list reference material used only for occurrence disambiguation.",
-	Roster:   "Deprecated alias for party roster reference material used only for occurrence disambiguation.",
-}
-
 var _ contracts.Normalizer[dnd.NPCOccurrenceList] = (*Normalizer)(nil)
 var _ contracts.ManifestMetadataProvider = (*Normalizer)(nil)
 var _ pipeline.CheckpointFingerprintProvider = (*Normalizer)(nil)
@@ -250,17 +243,14 @@ func duplicateWarning(retainedIndex int, removed []int) contracts.Warning {
 func occurrenceScope(index int) string { return fmt.Sprintf("occurrences[%d]", index) }
 
 func referenceSlots() []contracts.ReferenceSlot {
-	slots := shared.ReferenceSlots(referenceSlotDescriptions)
-	slots = append(slots, contracts.ReferenceSlot{
+	return []contracts.ReferenceSlot{{
 		Name:                  NPCRegistryReferenceSlot,
 		Description:           "Required normalized NPC registry used only for occurrence identity grounding, never as occurrence evidence.",
 		Required:              true,
 		AcceptedMediaTypes:    []string{"application/json"},
 		AcceptedArtifactKinds: []contracts.ArtifactKind{dnd.NPCRegistryKind},
 		MaxBytes:              NPCRegistryMaxBytes,
-	})
-	sort.Slice(slots, func(left, right int) bool { return slots[left].Name < slots[right].Name })
-	return slots
+	}}
 }
 
 func ModuleSpec() pipeline.ModuleSpec {

internal/modules/dnd/normalize/npcoccurrences/normalizer_test.go

@@ -126,7 +126,7 @@ func TestNormalizerContractAndDeterministicWarnings(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	if spec := ModuleSpec(); spec.Key != Key || spec.Stage != pipeline.StageNormalize || spec.ArtifactKind != dnd.NPCOccurrenceListKind || len(spec.ReferenceSlots) == 0 {
+	if spec := ModuleSpec(); spec.Key != Key || spec.Stage != pipeline.StageNormalize || spec.ArtifactKind != dnd.NPCOccurrenceListKind || len(spec.ReferenceSlots) != 1 || spec.ReferenceSlots[0].Name != NPCRegistryReferenceSlot || !spec.ReferenceSlots[0].Required {
 		t.Fatalf("ModuleSpec() = %#v", spec)
 	}
 	if metadata := normalizer.ManifestMetadata(); metadata["normalization_policy"] != normalizationPolicy || metadata["npc_registry_digest"] == "" || metadata["npc_count"] != 2 {