docker/docker-compose.yml

services:
  hopcroft-api:
    build:
      context: ..
      dockerfile: Dockerfile
    container_name: hopcroft-api
    ports:
      - "8080:8080"
    env_file:
      - ../.env
    environment:
      - PROJECT_NAME=Hopcroft
    volumes:
      # Bind mount: enables live code reloading for development
      - ../hopcroft_skill_classification_tool_competition:/app/hopcroft_skill_classification_tool_competition
      # Named volume: persistent storage for application logs
      - hopcroft-logs:/app/logs
    networks:
      - hopcroft-net
    # Override CMD for development with auto-reload
    command: >
      uvicorn hopcroft_skill_classification_tool_competition.main:app  --host 0.0.0.0  --port 8080  --reload
    restart: unless-stopped
    healthcheck:
      test: [ "CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8080/health', timeout=5)" ]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s

  hopcroft-gui:
    build:
      context: ..
      dockerfile: docker/Dockerfile.streamlit
    container_name: hopcroft-gui
    ports:
      - "8501:8501"
    environment:
      - API_BASE_URL=http://hopcroft-api:8080
    volumes:
      # Bind mount for development hot-reload
      - ../hopcroft_skill_classification_tool_competition/streamlit_app.py:/app/streamlit_app.py
    networks:
      - hopcroft-net
    depends_on:
      hopcroft-api:
        condition: service_healthy
    restart: unless-stopped

  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    volumes:
      - ../monitoring/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
      - ../monitoring/prometheus/alert_rules.yml:/etc/prometheus/alert_rules.yml
    ports:
      - "9090:9090"
    networks:
      - hopcroft-net
    depends_on:
      - alertmanager
    restart: unless-stopped

  alertmanager:
    image: prom/alertmanager:latest
    container_name: alertmanager
    volumes:
      - ../monitoring/alertmanager/config.yml:/etc/alertmanager/config.yml
    ports:
      - "9093:9093"
    networks:
      - hopcroft-net
    restart: unless-stopped

  grafana:
    image: grafana/grafana:latest
    container_name: grafana
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_ROOT_URL=http://localhost:3000
    volumes:
      # Provisioning: auto-configure datasources and dashboards
      - ../monitoring/grafana/provisioning/datasources:/etc/grafana/provisioning/datasources
      - ../monitoring/grafana/provisioning/dashboards:/etc/grafana/provisioning/dashboards
      - ../monitoring/grafana/dashboards:/var/lib/grafana/dashboards
      # Persistent storage for Grafana data
      - grafana-data:/var/lib/grafana
    networks:
      - hopcroft-net
    depends_on:
      - prometheus
    restart: unless-stopped
    healthcheck:
      test: [ "CMD-SHELL", "curl -f http://localhost:3000/api/health || exit 1" ]
      interval: 30s
      timeout: 10s
      retries: 3

  pushgateway:
    image: prom/pushgateway:latest
    container_name: pushgateway
    ports:
      - "9091:9091"
    networks:
      - hopcroft-net
    restart: unless-stopped
    command:
      - '--web.listen-address=:9091'
      - '--persistence.file=/data/pushgateway.data'
      - '--persistence.interval=5m'
    volumes:
      - pushgateway-data:/data

networks:
  hopcroft-net:
    driver: bridge

volumes:
  hopcroft-logs:
    driver: local
  grafana-data:
    driver: local
  pushgateway-data:
    driver: local