familienarchiv/docker-compose.prod.yml

# Production / staging Docker Compose for Familienarchiv.
#
# This is a self-contained file (not an overlay over docker-compose.yml).
# All services for the prod stack live here. Environment isolation is
# achieved via the docker compose project name:
#
#   production: docker compose -f docker-compose.prod.yml -p archiv-production ...
#   staging:    docker compose -f docker-compose.prod.yml -p archiv-staging --profile staging ...
#
# Volumes, networks and containers are namespaced by the project name,
# so the two environments cohabit cleanly on the same host.
#
# Required env vars (provided by .env.production / .env.staging in CI):
#   TAG                         image tag (release tag or "nightly")
#   PORT_BACKEND, PORT_FRONTEND host-side ports (bound to 127.0.0.1 only)
#   APP_DOMAIN                  e.g. archiv.raddatz.cloud / staging.raddatz.cloud
#   POSTGRES_PASSWORD           Postgres password
#   MINIO_PASSWORD              MinIO root password (admin operations only)
#   MINIO_APP_PASSWORD          MinIO application service-account password
#                               (least-privilege scope: archive bucket only)
#   OCR_TRAINING_TOKEN          token guarding ocr-service /train endpoint
#   APP_ADMIN_USERNAME          seeded admin email (e.g. admin@archiv.raddatz.cloud)
#   APP_ADMIN_PASSWORD          seeded admin password — CRITICAL: locked in on
#                               first deploy because UserDataInitializer only
#                               creates the account if the email does not exist
#   MAIL_HOST, MAIL_PORT,       SMTP relay (production only; staging uses mailpit)
#   MAIL_USERNAME, MAIL_PASSWORD
#   APP_MAIL_FROM               sender address (e.g. noreply@raddatz.cloud)

networks:
  archiv-net:
    driver: bridge

volumes:
  postgres-data:
  minio-data:
  ocr-models:
  ocr-cache:

services:
  db:
    image: postgres:16-alpine
    restart: unless-stopped
    environment:
      POSTGRES_USER: archiv
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
      POSTGRES_DB: archiv
    volumes:
      - postgres-data:/var/lib/postgresql/data
    networks:
      - archiv-net
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U archiv -d archiv"]
      interval: 10s
      timeout: 5s
      retries: 5

  minio:
    # Pinned MinIO release for reproducible deploys. Bumped manually until
    # Renovate is bootstrapped for these production images (see follow-up issue).
    image: minio/minio:RELEASE.2025-02-28T09-55-16Z
    restart: unless-stopped
    command: server /data --console-address ":9001"
    environment:
      MINIO_ROOT_USER: archiv
      MINIO_ROOT_PASSWORD: ${MINIO_PASSWORD}
    volumes:
      - minio-data:/data
    networks:
      - archiv-net
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
      interval: 30s
      timeout: 20s
      retries: 3

  # Idempotent bucket bootstrap + service-account creation.
  # Runs once per `docker compose up` and exits 0. The entrypoint is
  # extracted to infra/minio/bootstrap.sh so the (non-trivial) idempotent
  # logic is readable, reviewable, and unit-testable as a script rather
  # than YAML-escaped shell.
  create-buckets:
    # Custom image bakes bootstrap.sh in at build time. A bind-mount fails on
    # the Docker-out-of-Docker production runner because the host daemon
    # resolves the relative path against the host filesystem, not the
    # runner container's CWD. See #506 + infra/minio/Dockerfile.
    build:
      context: ./infra/minio
    # Declare one-shot intent so `docker compose up -d --wait` treats
    # exited(0) as success rather than "not running, fail". Pair with
    # backend's `service_completed_successfully` dependency below. See #510.
    restart: "no"
    depends_on:
      minio:
        condition: service_healthy
    networks:
      - archiv-net
    environment:
      MINIO_PASSWORD: ${MINIO_PASSWORD}
      MINIO_APP_PASSWORD: ${MINIO_APP_PASSWORD}

  # Dev-only mail catcher; gated behind the staging profile so production
  # never starts it. Staging workflow runs with `--profile staging`.
  mailpit:
    # Pinned for reproducibility; bumped manually until Renovate is bootstrapped.
    image: axllent/mailpit:v1.29.7
    restart: unless-stopped
    profiles: ["staging"]
    networks:
      - archiv-net
    healthcheck:
      # TCP-port open check via BusyBox `nc`. The previous wget-based probe
      # introduced a non-obvious binary dependency on the mailpit image; a
      # future tag that ships without wget would silently disable the
      # healthcheck. `nc` is part of BusyBox in the upstream image.
      test: ["CMD-SHELL", "nc -z localhost 8025 || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5

  ocr-service:
    build:
      context: ./ocr-service
    restart: unless-stopped
    expose:
      - "8000"
    # Surya OCR loads ~5GB of transformer models at startup; first request
    # triggers a further ~1GB Kraken model download into ocr-cache.
    # CX42+ (16 GB RAM) honours the default. On a CX32 (8 GB) override with
    # OCR_MEM_LIMIT=6g (slower first-request, fits the host).
    mem_limit: ${OCR_MEM_LIMIT:-12g}
    memswap_limit: ${OCR_MEM_LIMIT:-12g}
    volumes:
      - ocr-models:/app/models
      - ocr-cache:/root/.cache
    environment:
      KRAKEN_MODEL_PATH: /app/models/german_kurrent.mlmodel
      TRAINING_TOKEN: ${OCR_TRAINING_TOKEN}
      OCR_CONFIDENCE_THRESHOLD: "0.3"
      OCR_CONFIDENCE_THRESHOLD_KURRENT: "0.5"
      # SSRF allowlist pinned explicitly to the internal MinIO hostname.
      # In prod the OCR service only fetches PDFs from MinIO over the
      # docker network; localhost/127.0.0.1 are dev-only sources and
      # must NOT be reachable here. Do not widen to `*`.
      ALLOWED_PDF_HOSTS: "minio"
    networks:
      - archiv-net
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 10s
      timeout: 5s
      retries: 12
      start_period: 120s

  backend:
    image: familienarchiv/backend:${TAG:-nightly}
    build:
      context: ./backend
    restart: unless-stopped
    depends_on:
      db:
        condition: service_healthy
      minio:
        condition: service_healthy
      ocr-service:
        condition: service_healthy
      # Gate startup on the bucket bootstrap. Without this, backend
      # starts in parallel with create-buckets and may race the policy
      # bind. Also tells compose's `up -d --wait` that create-buckets
      # is a one-shot that must complete successfully. See #510.
      create-buckets:
        condition: service_completed_successfully
    # Bound to localhost only — Caddy fronts external traffic.
    ports:
      - "127.0.0.1:${PORT_BACKEND}:8080"
    environment:
      SPRING_DATASOURCE_URL: jdbc:postgresql://db:5432/archiv
      SPRING_DATASOURCE_USERNAME: archiv
      SPRING_DATASOURCE_PASSWORD: ${POSTGRES_PASSWORD}
      # Application uses the bucket-scoped service account, not MinIO root.
      S3_ENDPOINT: http://minio:9000
      S3_ACCESS_KEY: archiv-app
      S3_SECRET_KEY: ${MINIO_APP_PASSWORD}
      S3_BUCKET_NAME: familienarchiv
      S3_REGION: us-east-1
      # No SPRING_PROFILES_ACTIVE — base application.yaml is production-ready
      # (Swagger disabled, show-sql off, open-in-view false).
      APP_BASE_URL: https://${APP_DOMAIN}
      APP_ADMIN_USERNAME: ${APP_ADMIN_USERNAME}
      APP_ADMIN_PASSWORD: ${APP_ADMIN_PASSWORD}
      APP_OCR_BASE_URL: http://ocr-service:8000
      APP_OCR_TRAINING_TOKEN: ${OCR_TRAINING_TOKEN}
      MAIL_HOST: ${MAIL_HOST}
      MAIL_PORT: ${MAIL_PORT:-587}
      MAIL_USERNAME: ${MAIL_USERNAME:-}
      MAIL_PASSWORD: ${MAIL_PASSWORD:-}
      APP_MAIL_FROM: ${APP_MAIL_FROM:-noreply@raddatz.cloud}
      SPRING_MAIL_PROPERTIES_MAIL_SMTP_AUTH: ${MAIL_SMTP_AUTH:-true}
      SPRING_MAIL_PROPERTIES_MAIL_SMTP_STARTTLS_ENABLE: ${MAIL_STARTTLS_ENABLE:-true}
    networks:
      - archiv-net
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:8080/actuator/health | grep -q UP || exit 1"]
      interval: 15s
      timeout: 5s
      retries: 10
      start_period: 30s

  frontend:
    image: familienarchiv/frontend:${TAG:-nightly}
    build:
      context: ./frontend
      target: production
    restart: unless-stopped
    depends_on:
      backend:
        condition: service_healthy
    ports:
      - "127.0.0.1:${PORT_FRONTEND}:3000"
    environment:
      # SSR fetches go inside the docker network; clients hit https://${APP_DOMAIN}
      API_INTERNAL_URL: http://backend:8080
      ORIGIN: https://${APP_DOMAIN}
    networks:
      - archiv-net
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:3000/login >/dev/null 2>&1 || exit 1"]
      interval: 15s
      timeout: 5s
      retries: 10
      start_period: 20s