AfiS-Aktensystem/compose.yaml

# AfiS-Aktensystem - ein einziger Dockge-Stack.
# Ablage: /opt/stacks/afis/compose.yaml, .env im eigenen Dockge-Reiter.
# Begründung der Entscheidungen in docs/11-betrieb.md:
#  - keine Einmal- und keine Init-Container, Dockge zeigt beendete Container nicht
#  - Migrationen laufen im Startkommando von `web`
#  - jeder Dienst hat einen Healthcheck, das ist in Dockge die Statusanzeige
#  - kein Reverse Proxy: TLS und Kompression macht der Cloudflare Tunnel
#
# DEIN-USER durch den eigenen GitHub-Namen ersetzen.

x-logging: &logging
  logging:
    driver: json-file
    options: { max-size: '10m', max-file: '3' }

services:
  web:
    <<: *logging
    image: ghcr.io/DEIN-USER/afis-web:latest
    restart: unless-stopped
    # Die Migration läuft im Startkommando, nicht in einem Init-Container.
    # Die Prisma-CLI liegt im Image unter /app/migrator, es wird nichts nachgeladen.
    command: sh -c "cd /app/migrator && node node_modules/prisma/build/index.js migrate deploy && cd /app && node web/server.js"
    env_file: .env
    environment:
      NODE_ENV: production
      PORT: '3000'
      HOSTNAME: '0.0.0.0'
    volumes:
      - files:/data/files
      - clamav_socket:/var/run/clamav
    ports:
      - '3000:3000' # nur im LAN, von außen kommt der Tunnel
    depends_on:
      pgbouncer: { condition: service_healthy }
      clamav: { condition: service_healthy }
    healthcheck:
      test: ['CMD', 'wget', '-qO-', 'http://localhost:3000/api/health']
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 40s

  worker:
    <<: *logging
    image: ghcr.io/DEIN-USER/afis-worker:latest
    restart: unless-stopped
    env_file: .env
    depends_on:
      pgbouncer: { condition: service_healthy }
    healthcheck:
      test: ['CMD', 'node', 'healthcheck.js'] # prüft Gateway-Verbindung
      interval: 60s
      timeout: 10s
      retries: 3
      start_period: 30s

  db:
    <<: *logging
    image: postgres:16-alpine
    restart: unless-stopped
    environment:
      POSTGRES_DB: afis
      POSTGRES_USER: afis
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
      TZ: ${TZ}
    volumes:
      - pgdata:/var/lib/postgresql/data
    healthcheck:
      test: ['CMD-SHELL', 'pg_isready -U afis -d afis']
      interval: 10s
      timeout: 5s
      retries: 5

  pgbouncer:
    <<: *logging
    image: edoburu/pgbouncer:latest
    restart: unless-stopped
    environment:
      DB_HOST: db
      DB_USER: afis
      DB_PASSWORD: ${POSTGRES_PASSWORD}
      DB_NAME: afis
      POOL_MODE: transaction
      MAX_CLIENT_CONN: '100'
      DEFAULT_POOL_SIZE: '20'
      AUTH_TYPE: scram-sha-256
    depends_on:
      db: { condition: service_healthy }
    healthcheck:
      test: ['CMD-SHELL', 'pg_isready -h 127.0.0.1 -p 6432 -U afis']
      interval: 15s
      timeout: 5s
      retries: 5

  clamav:
    <<: *logging
    image: clamav/clamav:stable
    restart: unless-stopped
    environment:
      CLAMAV_NO_MILTERD: 'true'
      FRESHCLAM_CHECKS: '2'
    volumes:
      - clamav_db:/var/lib/clamav
      - clamav_socket:/var/run/clamav
      - files:/data/files
    healthcheck:
      test: ['CMD-SHELL', 'clamdscan --ping 1 || exit 1']
      interval: 60s
      timeout: 15s
      retries: 3
      start_period: 300s # erster Signaturdownload dauert

  pdf:
    <<: *logging
    image: ghcr.io/DEIN-USER/afis-pdf:latest # Playwright-Basis
    restart: unless-stopped
    environment:
      PORT: '3000'
      APP_URL: ${APP_URL}
    healthcheck:
      test: ['CMD', 'wget', '-qO-', 'http://localhost:3000/health']
      interval: 60s
      timeout: 10s
      retries: 3
      start_period: 30s

  cloudflared:
    <<: *logging
    image: cloudflare/cloudflared:latest
    restart: unless-stopped
    command: tunnel --no-autoupdate run
    environment:
      TUNNEL_TOKEN: ${CLOUDFLARE_TUNNEL_TOKEN}
    depends_on:
      web: { condition: service_healthy }
    healthcheck:
      test: ['CMD', 'cloudflared', '--version']
      interval: 60s
      timeout: 10s
      retries: 3
      start_period: 20s

  db-backup:
    <<: *logging
    image: prodrigestivill/postgres-backup-local:16
    restart: unless-stopped
    environment:
      POSTGRES_HOST: db
      POSTGRES_DB: afis
      POSTGRES_USER: afis
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
      POSTGRES_EXTRA_OPTS: '-Fc'
      SCHEDULE: '0 15 4 * * *' # täglich 04:15
      BACKUP_KEEP_DAYS: '7'
      BACKUP_KEEP_WEEKS: '4'
      BACKUP_KEEP_MONTHS: '6'
      HEALTHCHECK_PORT: '8080'
      TZ: ${TZ}
    volumes:
      - /mnt/backup/afis/db:/backups
    depends_on:
      db: { condition: service_healthy }
    healthcheck:
      test: ['CMD-SHELL', 'wget -qO- http://localhost:8080/ || exit 1']
      interval: 60s
      timeout: 10s
      retries: 3
      start_period: 30s

  offsite-backup:
    <<: *logging
    image: mazzolino/restic:latest
    restart: unless-stopped
    environment:
      RUN_ON_STARTUP: 'false'
      BACKUP_CRON: '0 30 4 * * *' # 15 Minuten nach dem Dump
      RESTIC_REPOSITORY: ${RESTIC_REPOSITORY}
      RESTIC_PASSWORD: ${RESTIC_PASSWORD}
      RESTIC_BACKUP_SOURCES: /data/db /data/files
      RESTIC_FORGET_ARGS: '--keep-daily 7 --keep-weekly 4 --keep-monthly 6 --prune'
      TZ: ${TZ}
    volumes:
      - /mnt/backup/afis/db:/data/db:ro
      - files:/data/files:ro
    # Kein HTTP-Endpunkt im Image. Geprüft wird, dass der Cron-Dauerläufer noch
    # steht und restic aufrufbar ist. Ohne Healthcheck wäre der Dienst in Dockge
    # nur "läuft", auch wenn er seit Wochen nichts mehr sichert.
    healthcheck:
      test: ['CMD-SHELL', 'pgrep -f go-crond >/dev/null && restic version >/dev/null || exit 1']
      interval: 300s
      timeout: 15s
      retries: 3
      start_period: 30s

volumes:
  pgdata:
  files:
  clamav_db:
  clamav_socket: