version: '3.8'

services:
  # === STANDALONE TRADING SERVICE ===
  # Monolithic service containing trading, risk, and ML components
  foxhunt-trading:
    build:
      context: ../../services/trading_service
      dockerfile: Dockerfile
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
    container_name: foxhunt-trading-service
    hostname: foxhunt-trading
    ports:
      - "8080:8080"   # Main gRPC port
      - "8081:8081"   # Health check port
      - "9090:9090"   # Metrics port
    volumes:
      - /opt/foxhunt/config/trading.toml:/app/config/config.toml:ro
      - /opt/foxhunt/data:/app/data:rw
      - /var/log/foxhunt:/app/logs:rw
      - /dev/shm:/dev/shm  # Shared memory for IPC
    environment:
      - RUST_LOG=info
      - FOXHUNT_ENV=production
      - FOXHUNT_CONFIG=/app/config/config.toml
      - DATABASE_URL=postgresql://foxhunt:foxhunt@postgres:5432/foxhunt
      - REDIS_URL=redis://redis:6379
      # ML framework optimizations
      - OMP_NUM_THREADS=6
      - MKL_NUM_THREADS=6
      - PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:512
      - TF_GPU_MEMORY_GROWTH=true
      # CUDA/GPU environment
      - CUDA_VISIBLE_DEVICES=0
      - NVIDIA_VISIBLE_DEVICES=0
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - NVIDIA_REQUIRE_CUDA=cuda>=11.8
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_started
    networks:
      - foxhunt-net
    # HFT Performance Optimizations
    cpuset: "0-7"  # Dedicated CPU cores for trading
    cpu_count: 8
    cpu_percent: 800  # 8 cores * 100%
    mem_limit: 16g
    memswap_limit: 16g
    mem_swappiness: 1
    oom_kill_disable: true
    shm_size: 2g  # Shared memory for ML frameworks
    # Real-time capabilities
    cap_add:
      - SYS_NICE
      - IPC_LOCK
    ulimits:
      memlock:
        soft: -1
        hard: -1
      nofile:
        soft: 65536
        hard: 65536
      rtprio:
        soft: 90
        hard: 90
    # GPU access for ML
    runtime: nvidia
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    # Network optimizations
    sysctls:
      - net.core.rmem_max=134217728
      - net.core.wmem_max=134217728
      - net.ipv4.tcp_rmem=4096 65536 134217728
      - net.ipv4.tcp_wmem=4096 65536 134217728
      - net.core.netdev_max_backlog=5000
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8081/health"]
      interval: 10s
      timeout: 5s
      retries: 3
      start_period: 30s
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "10"

  # === STANDALONE BACKTESTING SERVICE ===
  # Independent service for strategy testing and validation
  foxhunt-backtesting:
    build:
      context: ../../services/backtesting_service
      dockerfile: Dockerfile
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
    container_name: foxhunt-backtesting-service
    hostname: foxhunt-backtesting
    ports:
      - "8082:8082"   # Main gRPC port
      - "8083:8083"   # Health check port
      - "6006:6006"   # TensorBoard (optional)
    volumes:
      - /opt/foxhunt/config/backtesting.toml:/app/config/config.toml:ro
      - /opt/foxhunt/data:/app/data:ro
      - /opt/foxhunt/backtests:/app/backtests:rw
      - /var/log/foxhunt:/app/logs:rw
    environment:
      - RUST_LOG=info
      - FOXHUNT_ENV=production
      - FOXHUNT_CONFIG=/app/config/config.toml
      - DATABASE_URL=postgresql://foxhunt:foxhunt@postgres:5432/foxhunt
      - INFLUXDB_URL=http://influxdb:8086
      - FOXHUNT_BACKTEST_DATA_DIR=/app/backtests
    depends_on:
      postgres:
        condition: service_healthy
      influxdb:
        condition: service_started
    networks:
      - foxhunt-net
    # Resource allocation for compute-intensive backtesting
    cpuset: "8-15"  # Dedicated cores for backtesting
    cpu_count: 8
    cpu_percent: 800
    mem_limit: 32g
    memswap_limit: 32g
    shm_size: 4g
    # GPU access for ML backtesting
    runtime: nvidia
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8083/health"]
      interval: 15s
      timeout: 10s
      retries: 3
      start_period: 45s
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "5"

  # === TLI CLIENT ===
  # Terminal Line Interface - gRPC client only
  foxhunt-tli:
    build:
      context: ../../tli
      dockerfile: Dockerfile
      args:
        RUST_VERSION: 1.75.0
        BUILD_MODE: release
    container_name: foxhunt-tli-client
    hostname: foxhunt-tli
    # TLI is a client - no ports exposed
    stdin_open: true
    tty: true
    volumes:
      - /opt/foxhunt/config/tli.toml:/app/config/config.toml:ro
      - /var/log/foxhunt:/app/logs:rw
      - /tmp/.X11-unix:/tmp/.X11-unix:rw  # X11 forwarding for GUI
    environment:
      - RUST_LOG=info
      - FOXHUNT_CONFIG=/app/config/config.toml
      - FOXHUNT_TRADING_ENDPOINT=foxhunt-trading:8080
      - FOXHUNT_BACKTESTING_ENDPOINT=foxhunt-backtesting:8082
      - DISPLAY=${DISPLAY}  # For GUI applications
    depends_on:
      foxhunt-trading:
        condition: service_healthy
      foxhunt-backtesting:
        condition: service_healthy
    networks:
      - foxhunt-net
    cpuset: "16-17"
    mem_limit: 2g
    restart: unless-stopped
    command: ["sh", "-c", "sleep infinity"]  # Keep container running
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"

  # === SUPPORTING INFRASTRUCTURE ===

  postgres:
    image: postgres:15-alpine
    container_name: foxhunt-postgres
    ports:
      - "5432:5432"
    environment:
      - POSTGRES_DB=foxhunt
      - POSTGRES_USER=foxhunt
      - POSTGRES_PASSWORD=foxhunt
    volumes:
      - postgres-data:/var/lib/postgresql/data
      - ../sql/init.sql:/docker-entrypoint-initdb.d/init.sql:ro
    networks:
      - foxhunt-net
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U foxhunt -d foxhunt"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s

  redis:
    image: redis:7.0-alpine
    container_name: foxhunt-redis
    ports:
      - "6379:6379"
    volumes:
      - redis-data:/data
      - ../monitoring/redis.conf:/usr/local/etc/redis/redis.conf:ro
    command: redis-server /usr/local/etc/redis/redis.conf
    networks:
      - foxhunt-net
    mem_limit: 2g
    sysctls:
      - net.core.somaxconn=65535
    restart: unless-stopped

  influxdb:
    image: influxdb:2.7-alpine
    container_name: foxhunt-influxdb
    ports:
      - "8086:8086"
    environment:
      - INFLUXDB_DB=foxhunt
      - INFLUXDB_ADMIN_USER=admin
      - INFLUXDB_ADMIN_PASSWORD=admin
    volumes:
      - influxdb-data:/var/lib/influxdb2
    networks:
      - foxhunt-net
    restart: unless-stopped

  # === MONITORING SERVICES ===

  prometheus:
    image: prom/prometheus:v2.45.0
    container_name: foxhunt-prometheus
    ports:
      - "9091:9090"  # Different port to avoid conflict with trading service
    volumes:
      - ../monitoring/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=30d'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--web.enable-lifecycle'
    networks:
      - foxhunt-net
    restart: unless-stopped

  grafana:
    image: grafana/grafana:10.0.0
    container_name: foxhunt-grafana
    ports:
      - "3000:3000"
    volumes:
      - grafana-data:/var/lib/grafana
      - ../monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ../monitoring/grafana/datasources:/etc/grafana/provisioning/datasources:ro
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_ROOT_URL=http://localhost:3000
    networks:
      - foxhunt-net
    restart: unless-stopped

networks:
  foxhunt-net:
    driver: bridge
    driver_opts:
      com.docker.network.bridge.name: foxhunt-br0
    ipam:
      config:
        - subnet: 172.20.0.0/16

volumes:
  postgres-data:
    driver: local
  redis-data:
    driver: local
  influxdb-data:
    driver: local
  prometheus-data:
    driver: local
  grafana-data:
    driver: local