foxhunt/docker-compose.staging.yml

# =============================================================================
# FOXHUNT HFT TRADING SYSTEM - STAGING ENVIRONMENT
# =============================================================================
# Complete staging deployment with all services, databases, and monitoring
# for production-like testing and validation
#
# Usage:
#   docker-compose -f docker-compose.staging.yml up -d
#   docker-compose -f docker-compose.staging.yml down
#
# Health Checks:
#   ./deployment/health_check.sh staging
#
# =============================================================================

version: '3.8'

services:
  # ==========================================================================
  # DATABASE SERVICES
  # ==========================================================================

  postgres:
    image: postgres:15-alpine
    container_name: foxhunt-postgres-staging
    environment:
      POSTGRES_DB: foxhunt_staging
      POSTGRES_USER: foxhunt_staging
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-foxhunt_staging_password}
      POSTGRES_INITDB_ARGS: "--encoding=UTF-8 --lc-collate=C --lc-ctype=C"
    ports:
      - "5433:5432"  # Different port to avoid conflicts
    volumes:
      - postgres_staging_data:/var/lib/postgresql/data
      - ./database/schemas:/docker-entrypoint-initdb.d:ro
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U foxhunt_staging -d foxhunt_staging"]
      interval: 10s
      timeout: 5s
      retries: 5
    networks:
      - foxhunt-staging
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 4G
        reservations:
          cpus: '1.0'
          memory: 2G

  redis:
    image: redis:7-alpine
    container_name: foxhunt-redis-staging
    command: redis-server --appendonly yes --maxmemory 512mb --maxmemory-policy allkeys-lru
    ports:
      - "6380:6379"  # Different port to avoid conflicts
    volumes:
      - redis_staging_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
    networks:
      - foxhunt-staging
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 1G
        reservations:
          cpus: '0.5'
          memory: 512M

  # ==========================================================================
  # FOXHUNT CORE SERVICES
  # ==========================================================================

  trading-service:
    build:
      context: .
      dockerfile: services/trading_service/Dockerfile.production
      args:
        BUILD_MODE: staging
    container_name: foxhunt-trading-service-staging
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
    environment:
      - DATABASE_URL=postgres://foxhunt_staging:${POSTGRES_PASSWORD:-foxhunt_staging_password}@postgres:5432/foxhunt_staging
      - REDIS_URL=redis://redis:6379
      - RUST_LOG=info,trading_service=debug
      - FOXHUNT_ENV=staging
      - SERVICE_NAME=trading-service
      - SERVICE_PORT=50051
      - METRICS_PORT=9001
      - HEALTH_PORT=8081
    ports:
      - "50051:50051"  # gRPC
      - "8081:8081"    # Health/Debug
      - "9001:9001"    # Metrics
    volumes:
      - ./config:/app/config:ro
      - ./logs/staging:/app/logs
      - trading_staging_data:/app/data
    networks:
      - foxhunt-staging
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:8081/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
    deploy:
      resources:
        limits:
          cpus: '4.0'
          memory: 8G
        reservations:
          cpus: '2.0'
          memory: 4G

  backtesting-service:
    build:
      context: .
      dockerfile: services/backtesting_service/Dockerfile.production
      args:
        BUILD_MODE: staging
    container_name: foxhunt-backtesting-service-staging
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
    environment:
      - DATABASE_URL=postgres://foxhunt_staging:${POSTGRES_PASSWORD:-foxhunt_staging_password}@postgres:5432/foxhunt_staging
      - REDIS_URL=redis://redis:6379
      - RUST_LOG=info,backtesting_service=debug
      - FOXHUNT_ENV=staging
      - SERVICE_NAME=backtesting-service
      - SERVICE_PORT=50052
      - METRICS_PORT=9002
      - HEALTH_PORT=8082
    ports:
      - "50052:50052"  # gRPC
      - "8082:8082"    # Health/Debug
      - "9002:9002"    # Metrics
    volumes:
      - ./config:/app/config:ro
      - ./data:/app/data:ro
      - ./logs/staging:/app/logs
      - backtesting_staging_data:/app/backtests
    networks:
      - foxhunt-staging
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:8082/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
    deploy:
      resources:
        limits:
          cpus: '4.0'
          memory: 8G
        reservations:
          cpus: '2.0'
          memory: 4G

  ml-training-service:
    build:
      context: .
      dockerfile: services/ml_training_service/Dockerfile.production
      args:
        BUILD_MODE: staging
    container_name: foxhunt-ml-training-service-staging
    depends_on:
      postgres:
        condition: service_healthy
    environment:
      - DATABASE_URL=postgres://foxhunt_staging:${POSTGRES_PASSWORD:-foxhunt_staging_password}@postgres:5432/foxhunt_staging
      - AWS_ENDPOINT_URL=${AWS_ENDPOINT_URL:-}
      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID:-}
      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY:-}
      - AWS_DEFAULT_REGION=${AWS_DEFAULT_REGION:-us-east-1}
      - RUST_LOG=info,ml_training_service=debug
      - FOXHUNT_ENV=staging
      - SERVICE_NAME=ml-training-service
      - SERVICE_PORT=50053
      - METRICS_PORT=9003
      - HEALTH_PORT=8083
    ports:
      - "50053:50053"  # gRPC
      - "8083:8083"    # Health/Debug
      - "9003:9003"    # Metrics
      - "6006:6006"    # TensorBoard
    volumes:
      - ./config:/app/config:ro
      - ./logs/staging:/app/logs
      - ml_staging_data:/app/models
      - ml_cache_staging:/app/cache
    networks:
      - foxhunt-staging
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:8083/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
    deploy:
      resources:
        limits:
          cpus: '6.0'
          memory: 16G
        reservations:
          cpus: '4.0'
          memory: 8G

  # ==========================================================================
  # MONITORING AND OBSERVABILITY
  # ==========================================================================

  prometheus:
    image: prom/prometheus:v2.48.0
    container_name: foxhunt-prometheus-staging
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=15d'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--web.enable-lifecycle'
      - '--web.enable-admin-api'
      - '--log.level=info'
    ports:
      - "9090:9090"
    volumes:
      - prometheus_staging_data:/prometheus
      - ./config/monitoring/prometheus-staging.yml:/etc/prometheus/prometheus.yml:ro
      - ./config/monitoring/hft-alerts.yml:/etc/prometheus/alerts/hft-alerts.yml:ro
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    networks:
      - foxhunt-staging
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 4G
        reservations:
          cpus: '1.0'
          memory: 2G

  grafana:
    image: grafana/grafana:10.2.0
    container_name: foxhunt-grafana-staging
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_PASSWORD:-foxhunt_staging}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_INSTALL_PLUGINS=grafana-piechart-panel,grafana-clock-panel
      - GF_LOG_LEVEL=info
      - GF_SERVER_ROOT_URL=%(protocol)s://%(domain)s:%(http_port)s/
      - GF_ANALYTICS_REPORTING_ENABLED=false
      - GF_ANALYTICS_CHECK_FOR_UPDATES=false
    ports:
      - "3001:3000"  # Different port to avoid conflicts
    volumes:
      - grafana_staging_data:/var/lib/grafana
      - ./config/monitoring/grafana/dashboards:/var/lib/grafana/dashboards:ro
      - ./config/monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
    depends_on:
      prometheus:
        condition: service_healthy
    healthcheck:
      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    networks:
      - foxhunt-staging
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 2G
        reservations:
          cpus: '0.5'
          memory: 1G

  # ==========================================================================
  # OPTIONAL: TLI CLIENT (for interactive testing)
  # ==========================================================================

  tli:
    build:
      context: .
      dockerfile: tli/Dockerfile.production
    container_name: foxhunt-tli-staging
    depends_on:
      - trading-service
      - backtesting-service
      - ml-training-service
    environment:
      - TRADING_SERVICE_URL=http://trading-service:50051
      - BACKTESTING_SERVICE_URL=http://backtesting-service:50052
      - ML_SERVICE_URL=http://ml-training-service:50053
      - RUST_LOG=info
      - FOXHUNT_ENV=staging
    stdin_open: true
    tty: true
    volumes:
      - ./config:/app/config:ro
      - ./logs/staging:/app/logs
    networks:
      - foxhunt-staging
    profiles:
      - interactive  # Only start when explicitly requested
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 1G

# =============================================================================
# NETWORKS AND VOLUMES
# =============================================================================

networks:
  foxhunt-staging:
    driver: bridge
    name: foxhunt-staging-network
    ipam:
      driver: default
      config:
        - subnet: 172.20.0.0/16

volumes:
  postgres_staging_data:
    name: foxhunt-postgres-staging-data
  redis_staging_data:
    name: foxhunt-redis-staging-data
  trading_staging_data:
    name: foxhunt-trading-staging-data
  backtesting_staging_data:
    name: foxhunt-backtesting-staging-data
  ml_staging_data:
    name: foxhunt-ml-staging-data
  ml_cache_staging:
    name: foxhunt-ml-cache-staging
  prometheus_staging_data:
    name: foxhunt-prometheus-staging-data
  grafana_staging_data:
    name: foxhunt-grafana-staging-data