neuronetz-gateway/docker-compose.yml

services:
  gateway:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: neuronetz-gateway
    restart: unless-stopped
    # NOTE: deliberately NO `ports:` — the gateway is reached only via the
    # jwilder nginx-proxy on the shared external `proxy` network.
    expose:
      - "8080"
    environment:
      # jwilder/nginx-proxy + acme-companion routing (matches neuro-landing).
      VIRTUAL_HOST: ${GATEWAY_VIRTUAL_HOST:-api.neuronetz.ai}
      VIRTUAL_PORT: "8080"
      LETSENCRYPT_HOST: ${GATEWAY_VIRTUAL_HOST:-api.neuronetz.ai}
      LETSENCRYPT_EMAIL: ${LETSENCRYPT_EMAIL:-admin@neuronetz.ai}
      GATEWAY_BIND_HOST: 0.0.0.0
      GATEWAY_BIND_PORT: "8080"
      GATEWAY_LOG_LEVEL: ${GATEWAY_LOG_LEVEL:-INFO}
      GATEWAY_LOG_FORMAT: ${GATEWAY_LOG_FORMAT:-json}
      GATEWAY_REQUEST_ID_HEADER: ${GATEWAY_REQUEST_ID_HEADER:-X-Request-ID}
      # nginx-proxy forwards from the `proxy` network — trust its IP space.
      GATEWAY_TRUSTED_PROXIES: ${GATEWAY_TRUSTED_PROXIES:-127.0.0.1,nginx-proxy}
      DATABASE_URL: postgresql+asyncpg://${POSTGRES_USER:-gateway}:${POSTGRES_PASSWORD:-changeme}@postgres:5432/${POSTGRES_DB:-neuronetz}
      DATABASE_POOL_SIZE: ${DATABASE_POOL_SIZE:-10}
      DATABASE_POOL_OVERFLOW: ${DATABASE_POOL_OVERFLOW:-20}
      REDIS_URL: redis://redis:6379/0
      REDIS_KEY_CACHE_TTL_S: ${REDIS_KEY_CACHE_TTL_S:-60}
      OLLAMA_BASE_URL: ${OLLAMA_BASE_URL:-http://ollama:11434}
      OLLAMA_CONNECT_TIMEOUT_S: ${OLLAMA_CONNECT_TIMEOUT_S:-5}
      OLLAMA_READ_TIMEOUT_S: ${OLLAMA_READ_TIMEOUT_S:-600}
      OLLAMA_MAX_CONNECTIONS: ${OLLAMA_MAX_CONNECTIONS:-64}
      # Optional Bearer token for an externally-fronted Ollama (default empty:
      # the in-stack ollama service needs no auth on the private network).
      OLLAMA_AUTH_TOKEN: ${OLLAMA_AUTH_TOKEN:-}
      OLLAMA_AUTH_HEADER: ${OLLAMA_AUTH_HEADER:-Authorization}
      OLLAMA_AUTH_SCHEME: ${OLLAMA_AUTH_SCHEME:-Bearer}
      # Multi-backend (opt-in JSON list). See .env.example for the schema.
      OLLAMA_BACKENDS: ${OLLAMA_BACKENDS:-}
      MODEL_DISCOVERY_REFRESH_S: ${MODEL_DISCOVERY_REFRESH_S:-60}
      MODEL_DISCOVERY_CACHE_TTL_S: ${MODEL_DISCOVERY_CACHE_TTL_S:-120}
      DEFAULT_RPM: ${DEFAULT_RPM:-60}
      DEFAULT_TPM: ${DEFAULT_TPM:-100000}
      DEFAULT_CONCURRENT: ${DEFAULT_CONCURRENT:-8}
      MAX_REQUEST_BODY_BYTES: ${MAX_REQUEST_BODY_BYTES:-262144}
      MAX_NUM_PREDICT: ${MAX_NUM_PREDICT:-4096}
      ARGON2_TIME_COST: ${ARGON2_TIME_COST:-3}
      ARGON2_MEMORY_COST_KIB: ${ARGON2_MEMORY_COST_KIB:-65536}
      ARGON2_PARALLELISM: ${ARGON2_PARALLELISM:-4}
      AUTH_FAILURE_RATE_LIMIT_PER_IP_PER_MIN: ${AUTH_FAILURE_RATE_LIMIT_PER_IP_PER_MIN:-20}
      AUDIT_BUFFER_SIZE: ${AUDIT_BUFFER_SIZE:-1000}
      PROMPT_LOG_DEFAULT_RETENTION_DAYS: ${PROMPT_LOG_DEFAULT_RETENTION_DAYS:-30}
      AUDIT_LOG_DEFAULT_RETENTION_DAYS: ${AUDIT_LOG_DEFAULT_RETENTION_DAYS:-365}
      # Playground + auto-docs OFF by default in prod.
      PLAYGROUND_ENABLED: ${PLAYGROUND_ENABLED:-false}
      DOCS_ENABLED: ${DOCS_ENABLED:-false}
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
      ollama:
        condition: service_started
    # Apply migrations, then start the server.
    command: ["sh", "-c", "alembic upgrade head && exec python -m neuronetz_gateway"]
    healthcheck:
      test: ["CMD", "curl", "-fsS", "http://127.0.0.1:8080/healthz"]
      interval: 15s
      timeout: 3s
      retries: 5
      start_period: 30s
    networks:
      - proxy       # for nginx-proxy / acme-companion (TLS-fronted public traffic)
      - internal    # for postgres / redis / ollama (private)

  postgres:
    image: postgres:16-alpine
    container_name: neuronetz-postgres
    restart: unless-stopped
    environment:
      POSTGRES_USER: ${POSTGRES_USER:-gateway}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-changeme}
      POSTGRES_DB: ${POSTGRES_DB:-neuronetz}
    volumes:
      - postgres_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-gateway} -d ${POSTGRES_DB:-neuronetz}"]
      interval: 5s
      timeout: 3s
      retries: 10
    networks:
      - internal

  redis:
    image: redis:7-alpine
    container_name: neuronetz-redis
    restart: unless-stopped
    command: ["redis-server", "--save", "", "--appendonly", "no"]
    # No `ports:` — Redis is internal-only.
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 3s
      retries: 10
    networks:
      - internal

  ollama:
    image: ollama/ollama:latest
    container_name: neuronetz-ollama
    restart: unless-stopped
    volumes:
      - ollama_data:/root/.ollama
    networks:
      - internal

networks:
  # External network managed by the host's jwilder-proxy stack
  # (the same network neuronetz-web / neuronetz-www are attached to).
  proxy:
    external: true
  # Private network for inter-service traffic; not reachable from the host.
  internal:
    driver: bridge

volumes:
  # Pin absolute volume NAMES so the stack can ADOPT an existing volume that was
  # created by a previous deployment under a different compose project. Without
  # an explicit `name:`, compose namespaces volumes by project (directory) name,
  # so a rename or re-clone silently creates fresh, empty volumes alongside the
  # old data. We hit that the first time this stack was deployed (the original
  # models lived in `neuro-ollama_ollama-data` and a fresh `neuro-gateway_
  # ollama_data` was created next to them, leaving the models orphaned).
  #
  # Override via .env if your existing volumes are named differently:
  #   POSTGRES_DATA_VOLUME=neuro-api_postgres-data
  #   OLLAMA_DATA_VOLUME=neuro-ollama_ollama-data
  postgres_data:
    name: ${POSTGRES_DATA_VOLUME:-neuro-gateway_postgres_data}
  ollama_data:
    name: ${OLLAMA_DATA_VOLUME:-neuro-gateway_ollama_data}