Commit Graph
24 Commits
Author SHA1 Message Date
asepharyana 185d81f0e0 feat(ai-moderation): reset offensive nickname instead of deleting message
When the ONLY violation is offensive_username (message content clean):
- Message is NOT deleted (nickname-only violation bypasses auto-delete)
- Member's server nickname is reset to default username via
  setNickname(null) (Discord shows the global username again)
- Action 'reset_nickname' logged to moderation_actions; cooldown
  10min per guild:user (LRU) so repeated messages by same member
  don't hammer the Discord PATCH
- Config: AUTO_NICKNAME_RESET_ENABLED / AUTO_NICKNAME_RESET_COOLDOWN_MS
2026-08-10 11:48:27 +07:00
asepharyana 4049ab4201 feat(ai-moderation): rich context + link media vision analysis
- Conversation context recency gates (GAP_MS/MAX_AGE_MS): drop stale
  messages before silence gaps; cold_start anchor + flow descriptor
  tells LLM whether conversation is ongoing or restarted
- [location] block: channel name, thread name, nsfw/age flags from
  captured metadata (thread names instead of bare IDs)
- Link media -> multimodal: text-batch URL fetches that resolve to
  images now run vision analysis (bounded 15s) and switch prompt to
  mixed mode; <web_content> gains og:title for page context
- pnpm-workspace.yaml: approve sharp build script (unblocks install)
2026-08-10 11:26:26 +07:00
Developer 6df4f306dd refactor: remove unused text analysis module and integrate Qdrant enhancements
Build & Deploy (Nix) / build-and-deploy (backend) (push) Successful in 2m30s
Build & Deploy (Nix) / build-and-deploy (discord-gateway) (push) Successful in 3m7s
Build & Deploy (Nix) / build-and-deploy (proxy) (push) Successful in 3m20s
- Deleted the text analysis prompt constants and helpers as they are no longer needed.
- Added batch search functionality for Qdrant to optimize vector searches.
- Implemented methods for deleting expired Qdrant points and invalidating cache based on content hash.
- Updated text batch processor to use new timeout configurations and modified content building for moderation prompts.
- Enhanced text cache store to support new Qdrant integration and improved cache invalidation logic.
- Introduced a new user reputation model with a more nuanced trust scoring system, including penalties and rewards for user behavior.
- Added unit tests for the new trust model to ensure correctness of penalty and trust gain calculations.
- Updated configuration schema to reflect new timeout settings and removed deprecated OpenAI moderation keys.
2026-07-31 23:09:00 +07:00
Developer fc475dfbb7 feat(automod): store semantic cache embeddings in Qdrant
Build & Deploy (Nix) / build-and-deploy (backend) (push) Successful in 3m7s
Build & Deploy (Nix) / build-and-deploy (discord-gateway) (push) Successful in 2m21s
Build & Deploy (Nix) / build-and-deploy (proxy) (push) Successful in 2m33s
New qdrantClient.ts (zero-dep fetch REST): ensure collection with cosine
distance (auto-recreate on vector-size change), upsert point w/ verdict
payload, search w/ expires_at filter + score threshold.

textCacheStore: when QDRANT_URL set, embeddings are upserted to Qdrant
(primary) and searched there first; Postgres embedding column remains as
legacy fallback for pre-Qdrant rows. Config: QDRANT_URL/COLLECTION/API_KEY.
QDRANT_URL already in repo .env; added to VPS env + GATEWAY_ENV secret.
2026-07-31 21:30:43 +07:00
Developer 1249ae81d8 perf(automod): compress prompts ~40% + semantic cache via AI_LLM_EMBEDDING_MODEL
Build & Deploy (Nix) / build-and-deploy (backend) (push) Successful in 3m4s
Build & Deploy (Nix) / build-and-deploy (discord-gateway) (push) Successful in 2m29s
Build & Deploy (Nix) / build-and-deploy (proxy) (push) Successful in 2m33s
Prompt overhaul (token-frugal, same quality):
- rules.ts 28KB -> 10.3KB: every normative rule kept (safe lists, SARA
  6 kategori, LGBT/Israel zero tolerance, anti-evasion, decision tree,
  evasi hierarchy, image rules) with duplicated phrasing removed
- examples.ts 24.7KB -> 20KB: all 31 teaching examples kept; analysis
  strings shortened, redundant categories/policy_version dropped from
  example outputs (both optional in the response schema)
- output.ts 13.8KB -> 6.8KB: compressed schema + personality + format
  rules; CRITICAL bans on generic analysis and reply-context requirement
  retained
- system.ts: MEDIA_INSTRUCTIONS compressed, key rules kept

Semantic moderation cache (AI_LLM_EMBEDDING_MODEL):
- New embeddingClient.ts: OpenAI-compatible embeddings + cosine
  similarity; degrades gracefully when model/key unset
- textCacheStore: stores embedding JSON per verdict, findSimilarTextModeration
  reuses near-duplicate verdicts (min 0.97 cosine, processing locks skipped)
- moderationOrchestrator: after exact-hash miss, embed text-only targets
  and reuse stored verdict for near-duplicates -> skips expensive chat
  completion for spam variants; fresh verdicts written back with embedding
- Config: AI_LLM_EMBEDDING_MODEL / MIN_SIMILARITY (0.97) / MAX_CANDIDATES (30)
- Migration 0012: ADD COLUMN embedding to text_analysis_cache (idempotent)
- .env.example documents the new vars
2026-07-31 19:37:53 +07:00
Developer dcd13482c2 refactor: break monorepo into 3 standalone services (gateway, backend, frontend)
Build & Deploy / build-and-push (backend) (push) Failing after 35s
Build & Deploy / build-and-push (discord-gateway) (push) Failing after 25s
Build & Deploy / build-and-push (proxy) (push) Failing after 25s
- Remove pnpm workspace, moon repo, and all monorepo tooling
- Delete packages/shared/, embed shared code directly into each service
- Copy packages/shared/src/* -> services/backend/src/shared/ and services/discord-gateway/src/shared/
- Replace all @bete/shared imports with @/shared/ path alias
- Remove @bete/shared workspace dependency from both services
- Update root package.json scripts from --filter to --prefix
- Rewrite Dockerfiles to build each service standalone
- Clean up biome.json, .gitignore, remove root drizzle.config.ts
2026-07-30 11:50:48 +07:00
DeveloperandClaude Opus 4.8 5802d02e29 refactor: large codebase cleanup - consolidate schemas, migrate to Drizzle ORM, extract frontend components, modernize Docker builds
Build & Deploy / build-and-push (discord-gateway) (push) Failing after 2m22s
Build & Deploy / build-and-push (backend) (push) Failing after 3m22s
Build & Deploy / build-and-push (proxy) (push) Successful in 1m36s
Build & Deploy / deploy (push) Skipped
- Consolidate all DB schema definitions into packages/shared as single source of truth
- Migrate backend from raw SQL to Drizzle ORM across all modules
- Extract frontend inline UI into separate component files
- Refactor discord-gateway circuitBreaker into conversationState + moderationState
- Convert messageStore to Proxy singleton pattern
- Add validateBody/validateQuery middleware + Zod schemas for API endpoints
- Modernize Docker builds with multi-stage + pnpm deploy
- Migrate CI/CD from deployment to image-based pipeline
- Remove 60+ unused/dead files (~15K lines)
- Update color scheme from sky-blue to teal-cyan
- Move DB connection management to @bete/shared/database

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-27 21:54:31 +07:00
MythEclipse 2e14b5e4ed chore(auto): task completed - unknown 2026-06-13 13:35:11 +07:00
MythEclipseandClaude Opus 4.8 b68789fffc refactor: atomic, DRY, and logging improvements
- Shared Redis channel constants as single source of truth (redis-channels.ts)
- commandHandler.ts split into VoiceHandler, MediaHandler, GuildHandler,
  ModerationHandler with handler-registry.ts dispatch
- messageStore.ts (1322 lines) split into domain-specific DB files:
  messages.db.ts, attachments.db.ts, reviews.db.ts,
  moderation-actions.db.ts, retention.db.ts
- recorder.ts startSpeaking callback extracted into speakingHandler.ts,
  streamSetup.ts, segmentFinalizer.ts
- autoDeleteManager.ts split into autoDeleteEligibility.ts,
  autoDeleteNotify.ts, autoDeleteLogger.ts
- Added createChildLogger() logging across 8 service files
- Backend messages.repository.ts migrated from raw SQL to Drizzle ORM
- Fixed biome.json to exclude packages/**/dist/* from lint
- Fixed config.ts GUILD_ID pre-existing type error

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-09 17:34:18 +07:00
MythEclipseandClaude Opus 4.8 3a7b005d95 fix: resolve architecture disconnects and codebase weaknesses
- Add TEXT_CHANNEL_ID and TEXT_GUILD_ID to config schema (fix silent channel monitoring)
- Remove dead files: message-capture/broadcaster.ts, voice-recording/index.ts
- Fix WebSocket voice_command payload to forward from frontend
- Implement moderation:action handler in commandHandler
- Fix useMascotChat to use canonical request() wrapper
- Fix useAudioPlayback userId hash collision (use string not parseInt)
- Add catch blocks to useMediaControl.skip/stop
- Add typed broadcast functions (messageAnalyzed, voicePcmData, voiceActiveUser)
- Apply Biome formatting and lint fixes

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-09 16:36:23 +07:00
MythEclipseandClaude Opus 4.8 3614d32701 fix: resolve architecture disconnects and codebase weaknesses
- Standardize MessageRecord types — single source of truth from @bete/shared
- Clean up config: remove unused GUILD_ID/TEXT_GUILD_ID/TEXT_CHANNEL_ID, fix WEBSERVER_PORT default (3001), remove default admin password
- Move mascot_chat_messages table to Drizzle schema with proper migration
- Remove runtime DDL (CREATE TABLE IF NOT EXISTS) from mascot-chat repository
- Remove phantom analytics/ module from documentation
- Add better-sqlite3 dependency to root devDependencies
- Replace 'as any' casts with proper type assertions across AI moderation
- Add error logging to silent catch blocks in LLM client
- Apply Biome formatting and import organization

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-09 13:07:01 +07:00
MythEclipse 67d66bb5dd refactor(shared): centralize configuration and types
Migrate configuration validation and core moderation types from individual services to the `@bete/shared` package to ensure consistency across the monorepo.

- Move `AppConfig` and moderation-related interfaces to `packages/shared`.
- Replace service-specific Zod schemas with the centralized shared configuration.
- Refactor `services/backend` and `services/discord-gateway` to consume shared config and types.
- Remove redundant type definitions and local configuration logic in services.
- Update `packages/shared` exports to include new `config` and `moderation-types` modules.
- Clean up unused files and deprecated utility functions in `packages/shared`.
2026-06-09 11:56:03 +07:00
MythEclipseandClaude Opus 4.8 4becf0d6f1 refactor: comprehensive codebase cleanup and architecture hardening
- Sprint 1 (Quick Wins): Remove dead analytics modules, fix 4 unresolved
  imports, replace 3 console.warn with logger, remove mock-crc import
- Sprint 2 (Architecture): Create MascotChatRepository, AnalysisRepository,
  3 Zod schemas (mascot-chat, analysis, voice), deduplicate error classes,
  move 3 SQL queries from routes to repository
- Sprint 3 (Complexity): Replace 7 any types with proper interfaces,
  extract 6 helpers from prepareMediaMessage (CC 85 -> ~15)
- Sprint 4 (Config): Remove 22 dead env vars from .env, add 30 missing
  vars to .env.example, standardize naming

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-09 10:16:04 +07:00
MythEclipseandClaude Opus 4.8 13a75a5101 fix(voice): restore voice features and apply critical optimizations
Voice Feature Restoration:
- Implemented full Redis pub/sub pipeline for real-time voice data
- Added VOICE_PCM and VOICE_ACTIVE_USER Redis channels
- Implemented EventBroadcaster.voicePcmData() and voiceActiveUser() methods
- Extended backend redis-bridge to subscribe to voice channels
- Updated backend WebSocket server for binary PCM broadcast
- Replaced globalThis PcmBroadcaster pattern with proper EventBroadcaster DI
- Fixed root cause: PcmBroadcaster functions were never initialized

Bug Fixes:
- Fixed prism-media version conflict (2.0.0-alpha.0 → 1.3.5)
- Fixed type inconsistency in commandHandler.ts (AudioPlayerStatus → string)

Critical Optimizations:
- P1.1: Fixed unbounded memory growth in aiAnalyzer (added LRU caching, max 10K entries)
- P1.2: Converted sync file I/O to async in audio hot paths (recorder, sessionRecording)
- P1.3: Replaced process.exit(1) with proper error handling (bootstrap, aiAnalysisWorker)

Code Quality:
- Removed unused logger field in EventBroadcaster
- Replaced console.* with structured logger.* calls (player, decoder)
- Fixed typos and removed commented debug code
- Added DatabaseError class for better error handling

Files Modified: 18 (discord-gateway: 14, backend: 3, root: 1)
Architecture: Discord → EventBroadcaster → Redis → Backend WebSocket → Frontend

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-08 19:14:34 +07:00
MythEclipse 2643a3c278 refactor(discord-gateway): optimize redis usage and audio stream handling
- refactor(command-handler): replace per-call Redis connection creation with a persistent publisher connection to reduce overhead
- refactor(recorder): switch from manual audio stream subscription to direct event listeners on the existing stream
- feat(recorder): implement exponential backoff for voice connection retries
- chore(config): update default DECODER_COOLDOWN_MS to 30000ms
2026-06-08 18:09:17 +07:00
MythEclipse 25c86dcc30 fix(ai-moderation): raise retry backoffs and cooldowns, make 429 retryable, reduce prompt false positives 2026-06-05 21:47:02 +07:00
MythEclipse ce8a42f5fd feat(ai-moderation): eliminate LLM-based badword detection in favor of pure rule-based matching 2026-06-04 17:33:08 +07:00
MythEclipse 5d9713b162 chore(config): update TELE_UPLOAD_URL domain across all services 2026-06-04 17:12:02 +07:00
MythEclipse f163ead3cf feat(discord-gateway): add local badword pre-filter, accurate token estimation, Piscina maxThreads config, and PromptMode support 2026-06-02 22:50:23 +07:00
MythEclipse 1e1fbb4583 fix(discord-gateway): require LLM API key only when AI analysis is enabled 2026-06-02 21:46:15 +07:00
MythEclipse 498ab73d62 chore: auto-commit task - 2026-06-02 17:08:42 +07:00
MythEclipse 406a6cbf79 refactor: migrate sticker cache to PostgreSQL, remove versioning
- Replace file-based sticker cache (.dat + index.json) with PostgreSQL sticker_cache table
- Remove model_version column and all versioning logic (git branch detection, GitHub API, CACHE_MODEL_VERSION)
- Strip VISION_MODEL_VERSION, logCacheEvent calls, and version filtering from SQL queries
- Remove STICKER_CACHE_DIR and STICKER_CACHE_MAX_SIZE_MB config variables
- Delete dead migration add_model_version_to_cache.sql

textCacheStore.ts reduced 482→204 lines (-57%)
stickerCache.ts reduced 210→144 lines (-31%)
Total: 11 files changed, 233 insertions, 591 deletions
2026-06-02 14:05:51 +07:00
MythEclipseandClaude Opus 4.8 64643bb066 perf: hapus semua cooldown/backoff delay — retry tanpa bottleneck
Semua retry sekarang instant (retries=0, minTimeout=0, maxTimeout=0):
- retry.ts (kedua) — default minTimeout/maxTimeout 0, factor 1
- config.ts (kedua) — DECODER_COOLDOWN_MS=0, AI_ANALYSIS_ERROR_COOLDOWN_MS=0
- llmModerationClient.ts (kedua) — retries 0 tanpa delay
- aiAnalyzer.ts (kedua) — retries 0, AI_ANALYSIS_ERROR_COOLDOWN jadi 0
- indonesianTextNormalizer.ts (kedua) — semua rate limit cooldown 0
- recorder.ts (kedua), teleUpload (3 files), uploader (2 files) — retry instant
- attachmentUploader (kedua) — retries 0
- syncRoutes.ts — BACKLOG_SYNC_COOLDOWN 0

20 files changed. Semua cooldown bottleneck dihapus.

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-02 11:29:52 +07:00
MythEclipseandClaude Opus 4.8 c48a0c5e3b refactor: split monolith into 3 microservices (frontend, backend, discord-gateway)
- Extract services into services/{frontend,backend,discord-gateway}
- Create packages/shared/ for shared logger, errors, utils, types
- Setup Modular MVC pattern in backend (controller→service→repository)
- Setup event-driven architecture in discord-gateway with Redis pub/sub
- Move Docker files to infra/docker/ with per-service Dockerfiles
- Update docker-compose.yml to use Traefik-only routing (no port exposes)
- Update GitHub Actions deploy workflow for multi-service matrix build
- Fix all import paths and resolve type errors across all services
- All 3 services pass tsc --noEmit clean

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-01 21:44:29 +07:00