gendesign/docker-compose.prod.yml

# Production compose. Pulls pre-built images from GHCR
# (built and pushed by .github/workflows/deploy.yml).
#
# Place at /opt/gendesign/docker-compose.prod.yml on the VM.
# Required env in /opt/gendesign/.env:
#   POSTGRES_DB, POSTGRES_USER, POSTGRES_PASSWORD
#   IMAGE_TAG (defaults to "latest")
#
# In production the browser talks to Caddy on :80/:443.
# Caddy proxies /api/* and /health straight to backend, the rest to frontend.
# So the frontend uses same-origin relative URLs — no NEXT_PUBLIC_API_BASE_URL needed.
#
# Postgres + Redis run alongside the app on the same VM (Discovery mode).
# Volumes are shared with docker-compose.yml so switching between files preserves data.

services:
  postgres:
    image: postgis/postgis:16-3.4
    restart: unless-stopped
    environment:
      POSTGRES_DB: ${POSTGRES_DB}
      POSTGRES_USER: ${POSTGRES_USER}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
    # Bind to 127.0.0.1 only — accessible from host (for SSH tunnel) but not from public internet.
    # UFW additionally blocks 5432 from outside.
    ports:
      - "127.0.0.1:5432:5432"
    volumes:
      - postgres_data:/var/lib/postgresql/data
      - ./backend/db/init:/docker-entrypoint-initdb.d:ro
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U $${POSTGRES_USER}"]
      interval: 5s
      timeout: 5s
      retries: 10
    networks:
      default: {}
      shared:
        aliases:
          - gendesign-postgres

  redis:
    image: redis:7-alpine
    restart: unless-stopped
    volumes:
      - redis_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 3s
      retries: 5

  backend:
    image: ghcr.io/lekss361/gendesign-backend:${IMAGE_TAG:-latest}
    restart: unless-stopped
    # .env.runtime пишется deploy.yml через SSH (SENTRY_RELEASE=$IMAGE_TAG).
    # required: false — compose не падает если файла нет (первый деплой).
    env_file:
      - path: ./backend/.env
      - path: ./backend/.env.runtime
        required: false
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
    ports:
      - "127.0.0.1:8000:8000"
    volumes:
      # RBAC roles config — single source of truth (auth/roles.yaml в репо).
      # FastAPI middleware и /api/v1/me читают этот файл при старте (см.
      # app/core/auth.py). Read-only — мутация только через PR.
      - ./auth/roles.yaml:/app/auth/roles.yaml:ro
    healthcheck:
      test: ["CMD", "curl", "-fsS", "http://localhost:8000/health"]
      interval: 30s
      timeout: 5s
      retries: 5
      start_period: 20s

  frontend:
    image: ghcr.io/lekss361/gendesign-frontend:${IMAGE_TAG:-latest}
    restart: unless-stopped
    ports:
      - "127.0.0.1:3000:3000"
    depends_on:
      - backend
    # TCP-only probe через node (есть в alpine image, запускает сам server.js).
    # НЕ использует HTTP semantics — проверяет только что порт 3000 слушает.
    # Если Next.js процесс жив и порт открыт → healthy, независимо от HTTP status.
    # start_period 60s даёт время Next.js standalone bundle bootstrap.
    healthcheck:
      test: ["CMD", "node", "-e", "require('net').createConnection({port:3000,host:'127.0.0.1'}).once('connect',function(){process.exit(0)}).once('error',function(){process.exit(1)})"]
      interval: 15s
      timeout: 5s
      retries: 6
      start_period: 60s

  worker:
    # Отдельный chromium-образ (+200 МБ Playwright). См. backend/Dockerfile target=runner-with-chromium.
    image: ghcr.io/lekss361/gendesign-worker:${IMAGE_TAG:-latest}
    restart: unless-stopped
    env_file:
      - path: ./backend/.env
      - path: ./backend/.env.runtime
        required: false
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
    volumes:
      - ./data:/app/data    # playwright_state.json + photo binaries
      # Read-only bind-mount Антоновского /sf/ SQLite — для objective_etl task.
      # На VPS файл лежит в /opt/gendesign/site-finder/analysis.db; путь внутри
      # контейнера задан settings.objective_anton_sqlite_path (default
      # /data/anton-sqlite/analysis.db).
      - /opt/gendesign/site-finder:/data/anton-sqlite:ro
    command: ["celery", "-A", "app.workers.celery_app", "worker", "--loglevel=info", "--concurrency=8", "--queues=celery,scrape_kn,geo"]

  beat:
    # Lean backend-образ (без Chromium) — beat только триггерит таски в Redis.
    image: ghcr.io/lekss361/gendesign-backend:${IMAGE_TAG:-latest}
    restart: unless-stopped
    env_file:
      - path: ./backend/.env
      - path: ./backend/.env.runtime
        required: false
    depends_on:
      redis:
        condition: service_healthy
    # --schedule=/tmp/...: default location `/app/celerybeat-schedule` падает
    # с Permission denied — WORKDIR `/app` принадлежит root, `app` (uid 1000)
    # не может создавать там файлы. `/tmp` всегда writable; schedule-файл
    # хранит только last_run_at для periodic tasks — потеря на restart OK,
    # beat перестроит из `celery_app.conf.beat_schedule` на старте.
    command: ["celery", "-A", "app.workers.celery_app", "beat", "--loglevel=info", "--schedule=/tmp/celerybeat-schedule"]

  glitchtip-web:
    image: glitchtip/glitchtip:6.1.6
    container_name: glitchtip-web
    # profiles: ["glitchtip"] keeps this service from starting on plain `compose up -d`.
    # Bootstrap script activates the profile after DB + secrets are ready.
    # On subsequent deploys, set COMPOSE_PROFILES=glitchtip in /opt/gendesign/.env.
    profiles: ["glitchtip"]
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_started
    environment:
      DATABASE_URL: postgres://glitchtip:${GLITCHTIP_DB_PASS}@postgres:5432/glitchtip
      REDIS_URL: redis://redis:6379/2
      SECRET_KEY: ${GLITCHTIP_SECRET}
      PORT: "8080"
      EMAIL_URL: consolemail://
      GLITCHTIP_DOMAIN: https://errors.gendsgn.ru
      DEFAULT_FROM_EMAIL: errors@gendsgn.ru
      ENABLE_USER_REGISTRATION: "true"
      ENABLE_ORGANIZATION_CREATION: "false"
    restart: always
    mem_limit: 512m
    healthcheck:
      test: ["CMD", "wget", "-q", "--spider", "http://localhost:8080/api/0/"]
      interval: 30s
      timeout: 5s
      retries: 5
      start_period: 60s
    networks: [default]

  glitchtip-worker:
    image: glitchtip/glitchtip:6.1.6
    container_name: glitchtip-worker
    profiles: ["glitchtip"]
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_started
    command: ./bin/run-celery-with-beat.sh
    environment:
      DATABASE_URL: postgres://glitchtip:${GLITCHTIP_DB_PASS}@postgres:5432/glitchtip
      REDIS_URL: redis://redis:6379/2
      SECRET_KEY: ${GLITCHTIP_SECRET}
      CELERY_WORKER_AUTOSCALE: "1,3"
    restart: always
    mem_limit: 384m
    networks: [default]

  caddy:
    image: caddy:2
    restart: unless-stopped
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./Caddyfile:/etc/caddy/Caddyfile:ro
      - ./caddy/users.caddy.snippet:/etc/caddy/caddy/users.caddy.snippet:ro
      - ./preview:/srv/preview:ro
      - caddy_data:/data
      - caddy_config:/config
      - caddy_logs:/var/log/caddy
    # backend: service_healthy — backend имеет /health endpoint, готов до Caddy.
    # frontend: service_started — НЕ service_healthy: даже если frontend healthcheck
    # дребезжит, Caddy всё равно стартует (можно отдавать 502 для /, но
    # obsidian.gendsgn.ru, api.gendsgn.ru и т.д. остаются доступны).
    depends_on:
      backend:
        condition: service_healthy
      frontend:
        condition: service_started
    networks:
      - default
      # shared — для маршрута obsidian.gendsgn.ru → couchdb (отдельный stack).
      # Если obsidian-стек не задеплоен, Caddy просто получит 502 на этом маршруте,
      # main-приложение не страдает.
      - shared

  glitchtip-auth-forwarder:
    # Собирается локально на VPS при деплое (не тянется из GHCR).
    # deploy.yml запускает: docker compose build glitchtip-auth-forwarder
    build: ./ops/glitchtip-auth-forwarder
    container_name: gendesign-auth-forwarder
    restart: unless-stopped
    environment:
      GLITCHTIP_DSN: ${GLITCHTIP_DSN}
      APP_ENV: production
      APP_RELEASE: auth-forwarder-1
      CADDY_LOG_FILE: /var/log/caddy/auth_audit.log
      STATE_FILE: /state/offset.json
    volumes:
      # Read-only доступ к Caddy access log
      - caddy_logs:/var/log/caddy:ro
      # Persistent offset — выживает при перезапуске контейнера
      - auth_forwarder_state:/state
    depends_on:
      - caddy

volumes:
  postgres_data:
  redis_data:
  caddy_data:
  caddy_config:
  caddy_logs:
  auth_forwarder_state:

networks:
  # Внешняя сеть, создаётся вне compose (см. docs/obsidian-livesync.md).
  # Связывает main-stack (Caddy) и obsidian-stack (CouchDB).
  shared:
    external: true
    name: gendesign_shared