3 Commits

Include renames

Author	SHA1	Message	Date
asepharyana	7ef86c81ca	feat(ai): audit + harden embedding pipeline ... - Normalize text before embedding (strip mentions/URLs/emoji/markdown/control chars, lowercase, truncate) on both write and query sides so vectors aren't diluted and tokens aren't wasted - embeddingClient: retry embeddings (maxRetries 2), validate batch dimension consistency, preserve index alignment for empty-normalized texts - archiveEmbedder: store normalized text in archive payload, skip empty-normalized content - backend: normalize search queries, make archive search similarity threshold configurable (AI_LLM_EMBEDDING_ARCHIVE_MIN_SIMILARITY, default 0.6)	2026-09-01 18:01:47 +07:00
asepharyana	100b62800c	fix(backend): drop .js extension on @/ alias imports (embed/qdrant) ... Backend uses extensionless @/ alias imports; the double .js caused ERR_MODULE_NOT_FOUND at runtime (index.js.js).	2026-08-18 15:19:05 +07:00
asepharyana	1ae19074ee	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