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<{

services/discord-gateway/src/modules/ai-moderation/qdrantClient.ts

@@ -37,6 +37,14 @@ export interface QdrantVerdictPayload {
   /** Bare content hash (16 hex chars) — enables content-based invalidation
    *  regardless of the (context-scoped) point id. */
   content_hash?: string;
+  // Archive metadata (archiveEmbedder writes these; moderation cache doesn't).
+  // Optional so the same payload shape serves both the moderation cache
+  // collection and the public message archive collection.
+  username?: string;
+  channel_id?: string;
+  guild_id?: string;
+  thread_id?: string | null;
+  created_at?: number;
 }
 
 function baseUrl(): string {

services/discord-gateway/src/modules/message-capture/archiveEmbedder.ts

@@ -18,6 +18,7 @@ export interface ArchiveMessage {
   username: string;
   channel_id: string;
   guild_id: string;
+  thread_id: string | null;
   created_at: number;
   /** True when the message came from an age-restricted (NSFW) channel. NSFW
    *  content is deliberately NOT embedded into the public archive so it can't
@@ -58,6 +59,13 @@ export function archiveMessageEmbedded(message: ArchiveMessage): void {
         {
           text: normalized.slice(0, 4000),
           flags: "",
+          // Rich metadata so public semantic search results can be shown in
+          // context (who said it, where, when) instead of a bare text blob.
+          username: message.username ?? "",
+          channel_id: message.channel_id ?? "",
+          guild_id: message.guild_id ?? "",
+          thread_id: message.thread_id ?? null,
+          created_at: message.created_at ?? Date.now(),
           analyzed_at: Date.now(),
           // 5-year persistent window (archive is NOT a TTL cache).
           expires_at: Date.now() + 1000 * 60 * 60 * 24 * 365 * 5,

services/frontend/src/app/(dashboard)/messages/view.tsx

@@ -129,6 +129,7 @@ export function MessagesView({
   const semantic = useSemanticSearch(
     query,
     query.trim().length >= 2 && semanticMode,
+    guildId,
   );
   const activity = useMessageActivity(30);
   const edits = useRecentEdits(50, undefined, initialEdits);
@@ -360,6 +361,16 @@ export function MessagesView({
                         <span className="font-mono text-[10px] font-semibold text-signal">
                           {(r.score * 100).toFixed(0)}% RELEVANCE
                         </span>
+                        {r.username && (
+                          <span className="font-mono text-[10px] font-medium text-ink">
+                            {r.username}
+                          </span>
+                        )}
+                        {r.channel_id && (
+                          <span className="font-mono text-[10px] text-ink-muted">
+                            #{r.channel_id}
+                          </span>
+                        )}
                         <span
                           className="ml-auto font-mono text-[10px] text-ink-muted"
                           suppressHydrationWarning

services/frontend/src/hooks/use-messages.ts

@@ -212,13 +212,21 @@ export function useMessageSearch(query: string, enabled: boolean) {
 
 // ── Semantic Search (public archive, Qdrant) ──────
 
-export function useSemanticSearch(query: string, enabled: boolean) {
+export function useSemanticSearch(
+  query: string,
+  enabled: boolean,
+  guildId?: string | null,
+) {
   return useSWR<SemanticSearchResult[]>(
     enabled && query.trim().length >= 2
-      ? ["semantic-search", query.trim()]
+      ? ["semantic-search", query.trim(), guildId ?? ""]
       : null,
     async () => {
-      const res = await messagesApi.semanticSearch(query.trim(), 10);
+      const res = await messagesApi.semanticSearch(
+        query.trim(),
+        10,
+        guildId ?? undefined,
+      );
       return res.results;
     },
     { keepPreviousData: true },

services/frontend/src/lib/api/messages.ts

@@ -70,8 +70,12 @@ export const messagesApi = {
     }>,
 
   // Public semantic search over the persistent message archive (Qdrant).
-  semanticSearch: (query: string, limit?: number) =>
-    orpc.messages.semanticSearch({ query, limit }) as unknown as Promise<{
+  semanticSearch: (query: string, limit?: number, guildId?: string) =>
+    orpc.messages.semanticSearch({
+      query,
+      limit,
+      ...(guildId ? { guildId } : {}),
+    }) as unknown as Promise<{
       results: SemanticSearchResult[];
       nextCursor: null;
     }>,

services/frontend/src/lib/types/message.ts

@@ -173,6 +173,10 @@ export interface SemanticSearchResult {
   content: string;
   score: number;
   created_at: number;
+  username: string | null;
+  channel_id: string | null;
+  guild_id: string | null;
+  thread_id: string | null;
 }
 
 export interface MessageActivityBucket {