Files
GMW/.env.example
mytheclipsebotreview 2b6ec59286 refactor(ai): remove semantic embedding cache + Qdrant vector store
Hapus seluruh fitur embedding/Qdrant (tidak dipakai lagi):

- gateway: drop embeddingClient.ts, qdrantClient.ts, archiveEmbedder.ts
  dan tes qdrantEnsure.test.ts; moderationOrchestrator kembali ke
  exact-hash cache -> LLM (tanpa phase-2 semantic lookup); textCacheStore
  kehilangan findSimilarTextModeration / parseQdrantVerdict /
  isSemanticBandAccepted / upsertBareKeyToQdrant; cache-prune hanya
  menyapu Postgres.
- backend: drop embed.ts + qdrant.ts, endpoint messages.semanticSearch
  dan schema/type terkait; kolom embedding dilepas dari schema
  text_analysis_cache.
- frontend: hapus toggle EXACT/SEMANTIC, hook useSemanticSearch,
  API client + tipe SemanticSearchResult.
- config: buang AI_LLM_EMBEDDING_* dan QDRANT_* (env + .env.example).
- docs: ARCHITECTURE.md / AGENTS.md / README.md / diagram arsitektur
  disesuaikan (LLM caller - vision, cache = exact-hash saja).

Verifikasi: tsc 0 (backend, gateway, frontend); bun test 135 pass +
37 pass, 0 fail; biome 0 error.
2026-09-25 01:38:51 +07:00

111 lines
6.8 KiB
Bash

# Discord Bot Configuration
# =============================================================================
#
# PRODUCTION ENV IS DECLARATIVE:
# The runtime env files on the VPS (/etc/gmw/backend.env,
# /etc/gmw/discord-gateway.env) are WRITTEN BY CI from Gitea Actions secrets
# (BACKEND_ENV, GATEWAY_ENV) — see .gitea/workflows/deploy.yml.
# To change production env: update the secret in Gitea repo settings
# (Settings → Actions → Secrets), then push any commit to main. Never
# SSH into the VPS to edit env files by hand — CI will overwrite them.
#
# This file documents every variable; values for production live in the
# secrets, not here.
# === Discord ===
DISCORD_TOKEN=your_bot_token_here # REQUIRED
MONITOR_GUILD_ID=your_guild_id_here # Target guild for text monitoring
TEXT_GUILD_ID=optional_text_guild_id # Override text capture guild (falls back to MONITOR_GUILD_ID)
TEXT_CHANNEL_ID=optional_text_channel_id # Restrict text capture to a single channel
AVATAR_SIZE=64 # User avatar size in pixels (default: 64)
# === Webserver ===
WEBSERVER_PORT=4001 # Backend HTTP/WS server port (default: 4001)
# === Connection ===
RECONNECT_TIMEOUT_MS=5000 # Reconnect timeout in ms (default: 5000)
# === Logging ===
LOG_LEVEL=info # Pino log level: error|warn|info|http|verbose|debug|silly (default: info)
NODE_ENV=development # Environment: development|production|test (default: development)
VERBOSE=false # Enable verbose/debug logging (default: false)
# === Admin ===
# ADMIN_PASSWORD removed — dashboard is public
# === Database (PostgreSQL) ===
# Option 1: Connection string (overrides individual params)
DATABASE_URL=postgresql://asephs:***@100.121.180.82:6432/dcbot
# Option 2: Individual connection parameters
POSTGRES_HOST=localhost # PostgreSQL host (default: localhost)
POSTGRES_PORT=5432 # PostgreSQL port (default: 5432)
POSTGRES_USER=postgres # PostgreSQL user (optional if DATABASE_URL provided)
POSTGRES_PASSWORD=your_password_here # PostgreSQL password (optional if DATABASE_URL provided)
POSTGRES_DB=discord_bot # PostgreSQL database name (optional if DATABASE_URL provided)
POSTGRES_POOL_MIN=2 # Minimum pool connections (default: 2)
POSTGRES_POOL_MAX=10 # Maximum pool connections (default: 10)
# === Redis ===
REDIS_URL=redis://100.121.180.82:6379 # Redis connection string (default: redis://localhost:6379)
# === Attachments ===
TELE_UPLOAD_URL=https://upload.asepharyana.my.id/api/upload # Attachment upload endpoint (default)
ATTACHMENT_UPLOAD_TIMEOUT_MS=30000 # Upload timeout in ms (default: 30000)
ATTACHMENT_MAX_SIZE_MB=100 # Max attachment size in MB (default: 100)
ATTACHMENT_RETRY_ATTEMPTS=3 # Upload retry count (default: 3)
BACKLOG_SYNC_HOURS=24 # Backlog sync lookback window in hours (default: 24)
BACKLOG_SYNC_BATCH_SIZE=100 # Messages per backlog batch, max 100 (default: 100)
# === AI Analysis ===
AI_ANALYSIS_ENABLED=false # Enable AI content moderation (default: false)
AI_LLM_API_KEY= # REQUIRED if AI_ANALYSIS_ENABLED=true. LLM API key
AI_LLM_BASE_URL=http://100.121.180.82:20128/api/v1 # LLM API base URL (omniroute — OpenAI-compatible router on imrnes, Tailscale 100.121.180.82)
AI_LLM_MODEL=text # LLM text model name (default: text)
# AI_LLM_VISION_MODEL= # Vision model for image analysis (falls back to AI_LLM_MODEL)
AI_LLM_MAX_CONCURRENT=5 # Max concurrent LLM API calls (default: 5)
AI_LLM_IMAGE_MAX_DIMENSION=1024 # Max image dimension in pixels before resize (default: 1024)
AI_LLM_TEXT_BATCH_SIZE=20 # Max messages per text-only moderation batch (default: 20)
AI_LLM_MEDIA_ANALYSIS_TIMEOUT_MS=60000 # Timeout in ms for media analysis calls (default: 60000)
AI_LLM_TEXT_ANALYSIS_TIMEOUT_MS=30000 # Timeout in ms for text-only analysis calls (default: 30000)
# === AI Analysis Tuning ===
AI_ANALYSIS_DEBOUNCE_MS=500 # Debounce window for batching messages in ms (default: 500)
AI_ANALYSIS_RECOVERY_INTERVAL_MS=15000 # Recovery interval after errors in ms (default: 15000)
AI_ANALYSIS_ERROR_COOLDOWN_MS=30000 # Cooldown period after consecutive errors in ms (default: 30000)
AI_ANALYSIS_MAX_BATCH_SIZE=200 # Max messages fetched per conversation batch (default: 200)
AI_ANALYSIS_MAX_CONTEXT_TOKENS=8000 # Token budget for context window (default: 8000)
AI_ANALYSIS_MAX_TARGET_TOKENS=4000 # Token budget for target messages (default: 4000)
AI_ANALYSIS_CONTEXT_MESSAGE_LIMIT=20 # Max messages in context window (default: 20)
AI_ANALYSIS_PROCESSING_TIMEOUT_MS=120000 # Conversation lock timeout in ms (default: 120000)
AI_ANALYSIS_INDIVIDUAL_MAX_CONCURRENT=50 # Max concurrent individual-fallback jobs (default: 50)
AI_ANALYSIS_INDIVIDUAL_CB_THRESHOLD=50 # Consecutive errors before circuit breaker trips (default: 50)
# === Auto-Delete ===
AUTO_DELETE_FLAGGED_ENABLED=true # Enable auto-deletion of flagged messages (default: true)
AUTO_DELETE_FLAGGED_DRY_RUN=true # Dry-run mode: log but do not delete (default: false)
AUTO_DELETE_FLAGGED_DELAY_MS=0 # Delay before auto-delete in ms (default: 0)
AUTO_DELETE_MIN_CONFIDENCE=0.5 # Minimum AI confidence threshold 0-1 (default: 0.5)
AUTO_DELETE_ALLOWED_SEVERITIES=critical,high,medium,low # Comma-separated severities (default)
AUTO_DELETE_ALLOWED_CATEGORIES= # Comma-separated category filter (empty = all)
AUTO_DELETE_EXCLUDED_CHANNEL_IDS= # Comma-separated channel IDs to exclude
AUTO_DELETE_EXCLUDED_USER_IDS= # Comma-separated user IDs to exclude
AUTO_DELETE_NOTIFY_USER=false # Notify user when their message is auto-deleted (default: false)
AUTO_DELETE_LOG_CHANNEL_ID= # Channel ID to log auto-delete actions
# === Retention (0 = disabled) ===
RETENTION_MESSAGES_DAYS=0 # Message retention in days (default: 0 = off)
RETENTION_ATTACHMENTS_DAYS=0 # Attachment retention in days (default: 0 = off)
RETENTION_CLEANUP_INTERVAL_MS=86400000 # Cleanup interval in ms (default: 24h)
RETENTION_DRY_RUN=true # Dry-run: log but do not delete (default: true)
# === Migration ===
AUTO_MIGRATE_ON_STARTUP=true # Run database migrations on startup (default: true)
# === Worker Pool ===
# Text and media AI-analysis batches run on separate Piscina pools so a slow
# image/vision batch can never queue-block fast text-only batches.
# PISCINA_MAX_THREADS=4 # Text-analysis worker pool size (optional, defaults to CPU cores)
# PISCINA_MEDIA_MAX_THREADS=2 # Media-analysis worker pool size (optional, default 2)