feat(gmw): moderation explainability + semantic message search

- Persist structured verdict (flags/severity/confidence/evidence) on moderation_actions so the public web can show WHY a message was moderated. - Add a persistent Qdrant archive collection (gmw_message_archive); embed every captured message at capture time (fire-and-forget, best-effort). - Public semantic search over the archive (backend oRPC + FE toggle on the messages view). Both features are read-only/public and fully automatic. Migration: 0015_add_moderation_explainability.sql
2026-08-18 15:11:01 +07:00
parent d68f6b653a
commit 1ae19074ee
25 changed files with 1189 additions and 7 deletions
@@ -0,0 +1,63 @@
+import { embedText } from "@/modules/ai-moderation/embeddingClient.js";
+import {
+  ARCHIVE_COLLECTION,
+  qdrantPointId,
+  upsertQdrantPointV2,
+} from "@/modules/ai-moderation/qdrantClient.js";
+import { config } from "@/shared/config/config.js";
+import { createChildLogger } from "@/shared/logger/index";
+
+const log = createChildLogger("archive-embedder");
+
+export interface ArchiveMessage {
+  id: string;
+  content: string;
+  username: string;
+  channel_id: string;
+  guild_id: string;
+  created_at: number;
+}
+
+/**
+ * Fire-and-forget: embed a captured message and upsert it into the persistent
+ * archive collection so the public web can semantic-search the corpus.
+ *
+ * Failures are swallowed — searching is a nice-to-have, never a precondition
+ * for capture or moderation. The message text is kept in the payload so the
+ * search endpoint can return results even for deleted messages.
+ */
+export function archiveMessageEmbedded(message: ArchiveMessage): void {
+  if (!config.AI_LLM_EMBEDDING_MODEL) return; // embeddings disabled → skip
+  const text = message.content?.trim();
+  if (!text || text.length < 3) return;
+
+  void (async () => {
+    try {
+      const vector = await embedText(text);
+      if (!vector) return;
+      const ok = await upsertQdrantPointV2(
+        ARCHIVE_COLLECTION,
+        qdrantPointId(`archive:${message.id}`),
+        vector,
+        {
+          text: text.slice(0, 4000),
+          flags: "",
+          analyzed_at: Date.now(),
+          // 5-year persistent window (archive is NOT a TTL cache).
+          expires_at: Date.now() + 1000 * 60 * 60 * 24 * 365 * 5,
+          content_hash: message.id,
+        },
+      );
+      if (!ok) return;
+      log.debug({ messageId: message.id }, "Archived message embedding");
+    } catch (err) {
+      log.debug(
+        {
+          messageId: message.id,
+          error: err instanceof Error ? err.message : String(err),
+        },
+        "archive embed skipped",
+      );
+    }
+  })();
+}