user_history (riwayat flag sebelumnya) dan clean_streak/total_infractions
dikirim ke LLM setiap kali menganalisis pesan — ini bikin self-fulfilling
prophecy: user yg pernah kena false positive jadi makin gampang dituduh
lagi, dan link Instagram pun dianggap sexual_deviation cuma karena
riwayat user.
Changes:
- Hapus getUserRecentInfractions dari text batch path
- Hapus getUserRecentInfractions dari media analysis path
- Hapus import getUserRecentInfractions yg gak dipakai
- Ubah instruksi prompt dari 'jadilah lebih tegas jika riwayat jelek'
jadi 'setiap pesan dinilai berdasarkan isinya sendiri'
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The rule-based badword detector was injecting [normalized_text] and
[normalization_notes] tags into the LLM prompt that caused false
positive hallucinations - the LLM started associating innocent words
('sapik', 'furina') with furry/sexual_deviation due to misleading
context injected by the normalizer.
Removed:
- indonesianTextNormalizer.ts (full file deletion)
- formatModerationTextEvidenceForPrompt import/usage in llmModerationClient
- formatModerationTextEvidenceForPrompt import/usage in conversationContext
- stale re-exports in index.ts
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Nama karakter game/anime populer seperti 'Furina' dari Genshin Impact
sering kena false positive sebagai 'sexual_deviation' karena kemiripan
fonetik dengan kata 'furry'. Menambahkan aturan eksplisit bahwa nama
karakter fiksi normal bukan referensi furry fetish, dgn pengecualian
jika konteks pesan secara eksplisit membahas aspek fetish/seksual.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Implements a context-aware moderation system by tracking user behavior
and channel-specific norms to improve AI decision-making accuracy.
- Adds `user_reputations` table to track trust scores, clean streaks,
and infraction history.
- Adds `channel_cultures` table to store AI-generated summaries of
channel-specific norms and slang.
- Implements `userReputationStore` to autonomously update user scores
based on moderation outcomes (clean vs. flagged).
- Implements `cultureLearner` and `channelCultureStore` to manage
evolving channel contexts.
- Enhances LLM prompts to inject user reputation (trust scores,
history) and channel culture summaries, enabling "wisdom-based"
moderation (e.g., giving benefit of the doubt to high-trust users).
- Integrates reputation and culture updates into the existing
`aiAnalyzer` pipeline.
Refactors the AI moderation pipeline to improve concurrency control and
cache efficiency by moving from user-centric to content-centric caching.
- Implements a distributed locking mechanism for media analysis using
`acquireMediaAnalysisLock` to prevent redundant LLM vision calls across
multiple pods.
- Transitions text moderation caching from `user_mod:userId:hash` to a
purely content-based `text_mod:hash` approach to increase hit rates.
- Enhances `getPendingMessagesByConversation` with atomic transactions
and `FOR UPDATE SKIP LOCKED` to safely transition messages from
`pending` to `processing` state.
- Adds `processing` status to the `AIStatus` type and database schema to
track active analysis lifecycles.
- Implements polling logic in `llmModerationClient.ts` to wait for
in-progress media analyses.
- Replace all local logger imports (../../shared/logger/logger.js) with @bete/shared/logger across 26 files
- Remove winston dependency, add pino to discord-gateway package.json
- Delete shared/logger/logger.ts (winston-based, 132 lines) and serialization.ts (109 lines)
- Replace local retryWithBackoff imports with @bete/shared/utils across 6 files
- Delete shared/utils/retry.ts (42 lines)
- Add CustomLogger type alias to @bete/shared/logger for backwards compatibility
- Remove logger param from all retryWithBackoff calls and uploadToTele interfaces
- Frontend: convert entity type files to re-exports from shared/api/client.ts
- Full monorepo typecheck clean (4/4 packages)
35 files changed, 42 insertions(+), 488 deletions(-)
- Delete unused OpenAI WAF bypass client block (60+ lines) from both monolith
and microservice llmModerationClient.ts
- Replace OpenAI.Chat.Completions.ChatCompletion with type-only ChatCompletion
import from openai/resources/chat/completions
- All LLM chat calls already go through centralized llmClient.ts helper
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- aiAnalyzer.ts: removed unused logAnalysisSummary and logFalsePositiveDetected
- llmModerationClient.ts: removed unused logVisionAnalysis, logVisionError, logRetryAttempt
These functions are not called in the codebase.
MythEclipse