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.
Root cause: vision model diminta untuk 'flag' dan 'menilai' gambar,
sehingga screenshot terminal/chat biasa diklaim sebagai 'situs perjudian'.
Fix:
- vision prompt: HANYA deskripsi objektif (objek, teks, layout, jenis gambar)
- larang tegas kata 'gambling', 'judi', 'pelanggaran', 'harus dihapus'
- tambah buildGeneralImageVisionPrompt di discord-gateway stickerPrompt
- MEDIA_INSTRUCTIONS: tegaskan batch LLM adalah hakim, vision hanya saksi mata
- deskripsi netral (terminal, chat, editor kode) tidak boleh jadi dasar flag
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
MythEclipse