Fix D&D extraction issues and retire the completed audit

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

@@ -9,31 +9,46 @@ import (
 	"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 {
-		canonicalizeNPC(&response.NPCs[index], order, sourceID)
-	}
-	sort.SliceStable(response.NPCs, func(i, j int) bool {
-		left, leftOK := order.EarliestValid(canonicalSourceRefs(response.NPCs[i].SourceRefs, sourceID))
-		right, rightOK := order.EarliestValid(canonicalSourceRefs(response.NPCs[j].SourceRefs, sourceID))
-		if leftOK != rightOK {
-			return leftOK
+		earliest, hasEvidence := canonicalizeNPC(&response.NPCs[index], order, sourceID)
+		ordered[index] = orderedNPCResponse{
+			value:       response.NPCs[index],
+			earliest:    earliest,
+			hasEvidence: hasEvidence,
 		}
-		if !leftOK {
+	}
+	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 left < right
+		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) {
+func canonicalizeNPC(npc *npcResponse, order shared.SourceRefOrder, sourceID string) (int, bool) {
 	if npc == nil {
-		return
+		return 0, false
 	}
-	npc.SourceRefs = npcResponseRefs(order.Canonicalize(canonicalSourceRefs(npc.SourceRefs, sourceID)))
+	refs := order.Canonicalize(canonicalSourceRefs(npc.SourceRefs, sourceID))
+	npc.SourceRefs = npcResponseRefs(refs)
+	return order.EarliestValid(refs)
 }
 
 func canonicalNPCList(response extractionResponse, sourceID string) dnd.NPCList {

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

@@ -45,13 +45,14 @@ func TestRegisterPromptAssetsAndPrepareNPCPrompt(t *testing.T) {
 	for index, want := range []struct {
 		role   string
 		cached bool
+		marker string
 	}{
-		{role: "system"},
-		{role: "user"},
-		{role: "user", cached: true},
-		{role: "user", cached: true},
-		{role: "user"},
+		{role: "system", marker: "Dungeons & Dragons gameplay transcripts"},
+		{role: "user", marker: "Transcript units are the only evidence"},
+		{role: "user", cached: true, marker: "most specific supported in-world"},
 		{role: "user", cached: true},
+		{role: "user", marker: "individually identifiable"},
+		{role: "user", cached: true, marker: "observed display name"},
 		{role: "user"},
 	} {
 		if index >= len(prepared.Messages) {
@@ -68,6 +69,9 @@ func TestRegisterPromptAssetsAndPrepareNPCPrompt(t *testing.T) {
 		} else if message.CacheControl != nil {
 			t.Errorf("message %d cache control = %#v, want nil", index, message.CacheControl)
 		}
+		if want.marker != "" && !strings.Contains(message.Content, want.marker) {
+			t.Errorf("message %d content does not contain purpose marker %q", index, want.marker)
+		}
 	}
 	if len(prepared.Messages) != 7 {
 		t.Fatalf("prepared prompt has %d messages, want 7", len(prepared.Messages))