deploy/docker-compose.yml

services:
  traefik:
    image: traefik:v3.6
    restart: unless-stopped
    command:
      - "--api.insecure=true"
      - "--api.dashboard=true"
      - "--providers.docker=true"
      - "--providers.docker.exposedbydefault=false"
      - "--entrypoints.web.address=:80"
      - "--metrics.prometheus=true"
      - "--accesslog=true"
      - "--ping=true"
    ports:
      - "8000:80"
      - "8080:8080"  # Traefik dashboard
    environment:
      DOCKER_API_VERSION: "1.45"
    volumes:
      - ${XDG_RUNTIME_DIR}/docker.sock:/var/run/docker.sock:ro
    networks:
      - web
    healthcheck:
      test: ["CMD", "traefik", "healthcheck", "--ping"]
      interval: 10s
      timeout: 5s
      retries: 3
      start_period: 10s

  app:
    build:
      context: ..
      dockerfile: Dockerfile
    restart: unless-stopped
    deploy:
      replicas: 4
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.app.rule=PathPrefix(`/`)"
      - "traefik.http.routers.app.entrypoints=web"
      - "traefik.http.services.app.loadbalancer.server.port=8501"
      - "traefik.http.services.app.loadbalancer.sticky.cookie=true"
      - "traefik.http.services.app.loadbalancer.sticky.cookie.name=streamlit_session"
      - "traefik.http.services.app.loadbalancer.healthcheck.path=/_stcore/health"
      - "traefik.http.services.app.loadbalancer.healthcheck.interval=10s"
    networks:
      - web
    depends_on:
      traefik:
        condition: service_healthy

  prometheus:
    image: prom/prometheus:v2.54.1
    restart: unless-stopped
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus-data:/prometheus
    command:
      - "--config.file=/etc/prometheus/prometheus.yml"
      - "--storage.tsdb.path=/prometheus"
      - "--storage.tsdb.retention.time=15d"
      - "--web.enable-lifecycle"
    ports:
      - "9090:9090"
    networks:
      - web
    healthcheck:
      test: ["CMD", "wget", "-q", "--spider", "http://localhost:9090/-/healthy"]
      interval: 10s
      timeout: 5s
      retries: 3

  grafana:
    image: grafana/grafana:11.3.0
    restart: unless-stopped
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - grafana-data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
    ports:
      - "3000:3000"
    networks:
      - web
    depends_on:
      prometheus:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "wget", "-q", "--spider", "http://localhost:3000/api/health"]
      interval: 10s
      timeout: 5s
      retries: 3

networks:
  web:
    driver: bridge

volumes:
  prometheus-data:
    name: asi-demo_prometheus-data
    external: true
  grafana-data:
    name: asi-demo_grafana-data
    external: true