provenance/deploy/docker-compose.yml

name: provenance

# One stack stands up the whole system. Configuration is entirely env-driven
# (see .env.example). Run from this directory: `docker compose up -d`.
#
# backend/frontend are PULLED from the public registry (git.jpaul.io); CI pushes
# them to the LAN endpoint (192.168.0.2:1234). For local building instead of
# pulling, layer the dev override:
#   docker compose -f docker-compose.yml -f docker-compose.dev.yml up -d --build

services:
  postgres:
    # pgvector image = Postgres + pgvector; pg_trgm ships in contrib.
    image: pgvector/pgvector:pg17
    environment:
      POSTGRES_USER: ${POSTGRES_USER:-provenance}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-provenance}
      POSTGRES_DB: ${POSTGRES_DB:-provenance}
    volumes:
      - pgdata:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-provenance} -d ${POSTGRES_DB:-provenance}"]
      interval: 5s
      timeout: 5s
      retries: 10
    restart: unless-stopped

  minio:
    image: minio/minio:latest
    command: server /data --console-address ":9001"
    environment:
      MINIO_ROOT_USER: ${MINIO_ROOT_USER:-provenance}
      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-change-me-too}
    volumes:
      - miniodata:/data
    healthcheck:
      test: ["CMD-SHELL", "mc ready local || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 10
    restart: unless-stopped

  # One-shot schema migration: runs `alembic upgrade head` and exits. Backend
  # and worker wait for it to finish, so on `docker compose up` the schema is
  # always current before the app serves traffic — no manual migrate step.
  # NOTE: a pure Watchtower image-swap recreates only the long-running
  # containers, not this one-shot job, so Watchtower deploys should be paired
  # with a `compose up` (see deploy docs) to re-run migrations.
  migrate:
    image: git.jpaul.io/justin/provenance-backend:${IMAGE_TAG:-test-main}
    command: ["uv", "run", "--no-dev", "alembic", "upgrade", "head"]
    labels:
      com.centurylinklabs.watchtower.enable: "true"
    # All app config comes from .env (twelve-factor) — no per-setting allow-list
    # to maintain. The `environment:` block below only pins values that must NOT
    # come from .env. See the backend service for the full rationale.
    env_file:
      - path: .env
        required: false
    environment:
      DATABASE_URL: ${DATABASE_URL:-postgresql+asyncpg://provenance:provenance@postgres:5432/provenance}
    depends_on:
      postgres:
        condition: service_healthy
    restart: "no"

  backend:
    image: git.jpaul.io/justin/provenance-backend:${IMAGE_TAG:-test-main}
    labels:
      com.centurylinklabs.watchtower.enable: "true"
    # Twelve-factor: ALL application settings come straight from .env — owner,
    # AI providers, mailer/SMTP, S3, sessions, everything in app/core/config.py.
    # No per-setting allow-list to maintain, so a new setting in .env (and
    # .env.example) reaches the app with no compose edit. The `environment:`
    # block below is only for values that must NOT come from .env:
    #   - RUN_MIGRATIONS: backend-only flag, not an app setting.
    #   - DATABASE_URL: pinned to the compose-internal host as a safety net —
    #     the code default points at localhost, which is wrong inside the
    #     network. (.env normally sets it; this guards against it being absent.)
    # `environment:` wins over `env_file`, so these always take effect.
    # Trade-off (accepted): env_file also exposes infra secrets (POSTGRES_*,
    # MINIO_*, CLOUDFLARE_TUNNEL_TOKEN) to the app process; the app ignores them.
    env_file:
      - path: .env
        required: false
    environment:
      RUN_MIGRATIONS: "1"
      DATABASE_URL: ${DATABASE_URL:-postgresql+asyncpg://provenance:provenance@postgres:5432/provenance}
    depends_on:
      postgres:
        condition: service_healthy
      minio:
        condition: service_healthy
      migrate:
        condition: service_completed_successfully
    healthcheck:
      test:
        - CMD-SHELL
        - >-
          python -c "import urllib.request,sys;
          sys.exit(0 if urllib.request.urlopen('http://localhost:8000/health').status==200 else 1)"
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 20s
    restart: unless-stopped

  # Background worker — same image as the backend, run in worker mode.
  # First job: the scheduled soft-delete purge (and media object cleanup).
  worker:
    image: git.jpaul.io/justin/provenance-backend:${IMAGE_TAG:-test-main}
    command: ["uv", "run", "--no-dev", "python", "-m", "app.worker"]
    labels:
      com.centurylinklabs.watchtower.enable: "true"
    # Same .env-driven config as the backend (see its comment). The worker reads
    # the model-provider settings too, so the upcoming embedding/matching jobs
    # are configured the moment they land — no compose change needed.
    env_file:
      - path: .env
        required: false
    environment:
      DATABASE_URL: ${DATABASE_URL:-postgresql+asyncpg://provenance:provenance@postgres:5432/provenance}
    depends_on:
      postgres:
        condition: service_healthy
      minio:
        condition: service_healthy
      migrate:
        condition: service_completed_successfully
    restart: unless-stopped

  frontend:
    image: git.jpaul.io/justin/provenance-frontend:${IMAGE_TAG:-test-main}
    labels:
      com.centurylinklabs.watchtower.enable: "true"
    environment:
      NODE_ENV: production
    depends_on:
      - backend
    restart: unless-stopped

  caddy:
    image: caddy:2
    ports:
      - "80:80"
      - "443:443"
    environment:
      # Local default ':80' -> http://localhost. Set to a domain in production
      # for automatic HTTPS (or run plain HTTP behind a Cloudflare Tunnel).
      PROVENANCE_SITE_ADDRESS: ${PROVENANCE_SITE_ADDRESS:-:80}
    volumes:
      - ./Caddyfile:/etc/caddy/Caddyfile:ro
      - caddydata:/data
      - caddyconfig:/config
    depends_on:
      - backend
      - frontend
    restart: unless-stopped

  # Cloudflare Tunnel connector. The tunnel/ingress is configured in the
  # Cloudflare dashboard; this container just connects. One public hostname
  # (e.g. provenance.paul.farm) -> http://caddy:80 is enough, because Caddy
  # does the internal path routing (/ -> frontend, /api + /health -> backend).
  #
  # Opt-in via the "tunnel" profile so local dev doesn't start it. On the lab
  # host set COMPOSE_PROFILES=tunnel so `docker compose up -d` includes it.
  cloudflared:
    image: cloudflare/cloudflared:latest
    restart: unless-stopped
    command: tunnel --no-autoupdate run
    environment:
      TUNNEL_TOKEN: ${CLOUDFLARE_TUNNEL_TOKEN:-}
    depends_on:
      - caddy
    profiles:
      - tunnel

# Auto-deploy is handled by the host's global Watchtower (a single
# nickfedor/watchtower instance watches every container labelled
# `com.centurylinklabs.watchtower.enable=true` across all stacks). The backend
# and frontend carry that label above, so a new :test-main image is pulled and
# the container recreated automatically — no per-stack Watchtower needed.

volumes:
  pgdata:
  miniodata:
  caddydata:
  caddyconfig: