3 Commits

Include renames

Author	SHA1	Message	Date
asepharyana	1397380fe9	fix(ai): pertahankan status warn di cache moderasi + bersihkan prompt stale ... - normalizeStoredStatus(): exact-hash & semantic (Qdrant/PG) cache reader sebelumnya menipiskan 'warn' jadi 'flagged'/'clean' (type narrowing legacy clean|flagged) — merusak gating auto-delete & label dashboard. Kini status tersimpan dipertahankan penuh (clean/warn/flagged). - prompts: hapus referensi <user_history> yang tak pernah di-inject, SearXNG -> Wikipedia (sudah migrasi), referensi section yang tak ada, typo 'secifik', dan baris list rusak '|-'. - moderationBuilders: buang dead code buildUserProfilesBlock/ buildUserProfileRef/UserProfileEntry/buildUserHistoryXml (tanpa caller produksi sejak context minimization) + test-nya. - test baru: tests/storedStatusNormalization.test.ts (regresi warn).	2026-08-22 16:17:55 +07:00
asepharyana	2a8f6d9062	refactor(gateway): remove user reputation feature entirely ... Drop trust-score/infraction system: delete userReputationStore, remove call sites in fallback/batch processors, drop formatReputationAttrs, drop user_reputations table (migration 0016), delete trust-model test, update docs.	2026-08-18 18:27:15 +07:00
asepharyana	65c9c2cd9e	feat(ai-moderation): enrich analysis context with recency, repetition, user history and channel topic ... - <message> targets now carry time (ISO), repetitions (N identical short texts = spam signal), bot and edited flags; escape id/user XML - rich <user_reputation>: total_infractions, clean_streak, last_offense_days_ago, repeat_offender (7-day window) - <user_history> with last flagged messages for repeat offenders (wires dead getUserRecentInfractions) - <user_profile as_of> staleness signal; <location_context topic> from captured channel topic - prompt framing + output instructions teach the LLM to use the new signals without treating history as proof - tests: contextEnrichment.test.ts (13) + topic cases in conversationContext.test.ts	2026-08-10 17:15:33 +07:00