feat(archive): rich metadata in semantic search — username/channel/guild context + guild filter

Archive payload now stores username, channel_id, guild_id, thread_id and the
real message created_at (not embed time). Backend searchArray accepts an
optional guildId and applies a Qdrant payload filter so results can be scoped
to the guild being viewed. API/frontend expose the new fields and the
semantic results card shows who said it, in which channel, and when —
turning bare text blobs into contextual results. Old points fall back to
analyzed_at and omit the new fields gracefully.

services/backend/src/modules/messages/messages.service.ts

@@ -105,6 +105,7 @@ export class MessagesService {
       vector,
       input.limit,
       config.AI_LLM_EMBEDDING_ARCHIVE_MIN_SIMILARITY,
+      input.guildId,
     );
     const results = hits.map((h) => mapSearchHit(h));
     return { results, nextCursor: null };
@@ -120,16 +121,31 @@ export class MessagesService {
   }
 }
 
-/** Shape returned to the frontend (text + metadata from the archive payload). */
+/** Shape returned to the frontend (text + rich metadata from the archive payload). */
 function mapSearchHit(hit: {
   score: number;
-  payload: { text: string; content_hash?: string; analyzed_at: number };
+  payload: {
+    text: string;
+    content_hash?: string;
+    analyzed_at: number;
+    username?: string;
+    channel_id?: string;
+    guild_id?: string;
+    thread_id?: string | null;
+    created_at?: number;
+  };
 }) {
   return {
     message_id: hit.payload.content_hash ?? null,
     content: hit.payload.text,
     score: hit.score,
-    created_at: hit.payload.analyzed_at,
+    // Prefer the real message timestamp; fall back to embed time for old
+    // points that predate rich metadata.
+    created_at: hit.payload.created_at ?? hit.payload.analyzed_at,
+    username: hit.payload.username ?? null,
+    channel_id: hit.payload.channel_id ?? null,
+    guild_id: hit.payload.guild_id ?? null,
+    thread_id: hit.payload.thread_id ?? null,
   };
 }
 

services/backend/src/modules/messages/qdrant.ts

@@ -10,6 +10,11 @@ export interface ArchiveHit {
     content_hash?: string;
     analyzed_at: number;
     expires_at: number;
+    username?: string;
+    channel_id?: string;
+    guild_id?: string;
+    thread_id?: string | null;
+    created_at?: number;
   };
 }
 
@@ -61,6 +66,7 @@ export async function searchArchive(
   vector: number[],
   limit: number,
   scoreThreshold: number,
+  guildId?: string,
 ): Promise<ArchiveHit[]> {
   if (!config.QDRANT_URL) return [];
   try {
@@ -72,6 +78,17 @@ export async function searchArchive(
         limit,
         score_threshold: scoreThreshold,
         with_payload: true,
+        // Optional scope: only return vectors from a specific guild's archive.
+        // Old points (embedded before rich metadata) have no guild_id payload —
+        // the `must` match simply excludes them, which is the correct behavior
+        // for a guild-scoped search.
+        ...(guildId
+          ? {
+              filter: {
+                must: [{ key: "guild_id", match: { value: guildId } }],
+              },
+            }
+          : {}),
       },
     )) as {
       result?: Array<{