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

This commit is contained in:

asepharyana

2026-08-18 15:11:01 +07:00

parent d68f6b653a

commit 1ae19074ee

25 changed files with 1189 additions and 7 deletions

									
										services/frontend/src/hooks/index.ts
									
		+1
		
												View File
												
				@@ -28,6 +28,7 @@ export {

				  useMessagesStream,

				  useMessagesWsSync,

				  useReview,

				  useSemanticSearch,

				  useTextChannels,

				} from "./use-messages";

				export {