foxhunt/docker-compose.production.yml

version: '3.8'

# Production Docker Compose Stack for Foxhunt HFT Trading System
# Wave 71 Agent 8: Complete production deployment configuration

# Define custom networks for isolation and controlled access
networks:
  foxhunt_internal:
    driver: bridge
    ipam:
      config:
        - subnet: 172.20.0.0/16
  foxhunt_external:
    driver: bridge

# Define named volumes for persistent data
volumes:
  postgres_data:
  redis_data:
  influxdb_data:
  vault_data:
  prometheus_data:
  grafana_data:

services:
  # =============================================================================
  # Infrastructure Services
  # =============================================================================

  postgres:
    image: postgres:16-alpine
    container_name: foxhunt-postgres
    restart: unless-stopped
    environment:
      POSTGRES_USER: ${POSTGRES_USER:-foxhunt}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
      POSTGRES_DB: ${POSTGRES_DB:-foxhunt}
      POSTGRES_INITDB_ARGS: "-E UTF8 --locale=C"
    volumes:
      - postgres_data:/var/lib/postgresql/data
      - ./database/migrations:/docker-entrypoint-initdb.d:ro
    networks:
      foxhunt_internal:
        ipv4_address: 172.20.0.10
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-foxhunt} -d ${POSTGRES_DB:-foxhunt}"]
      interval: 5s
      timeout: 3s
      retries: 5
      start_period: 10s
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 2G
        reservations:
          cpus: '1.0'
          memory: 1G

  redis:
    image: redis:7-alpine
    container_name: foxhunt-redis
    restart: unless-stopped
    command: redis-server --maxmemory 256mb --maxmemory-policy allkeys-lru --appendonly yes
    volumes:
      - redis_data:/data
    networks:
      foxhunt_internal:
        ipv4_address: 172.20.0.11
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 3s
      retries: 5
      start_period: 10s
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 512M
        reservations:
          cpus: '0.5'
          memory: 256M

  influxdb:
    image: influxdb:2.7-alpine
    container_name: foxhunt-influxdb
    restart: unless-stopped
    environment:
      DOCKER_INFLUXDB_INIT_MODE: setup
      DOCKER_INFLUXDB_INIT_USERNAME: ${INFLUXDB_USER:-admin}
      DOCKER_INFLUXDB_INIT_PASSWORD: ${INFLUXDB_PASSWORD}
      DOCKER_INFLUXDB_INIT_ORG: ${INFLUXDB_ORG:-foxhunt}
      DOCKER_INFLUXDB_INIT_BUCKET: ${INFLUXDB_BUCKET:-trading_metrics}
      DOCKER_INFLUXDB_INIT_ADMIN_TOKEN: ${INFLUXDB_ADMIN_TOKEN}
      DOCKER_INFLUXDB_INIT_RETENTION: ${INFLUXDB_RETENTION:-30d}
    volumes:
      - influxdb_data:/var/lib/influxdb2
    networks:
      foxhunt_internal:
        ipv4_address: 172.20.0.12
    healthcheck:
      test: ["CMD", "influx", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 1G
        reservations:
          cpus: '0.5'
          memory: 512M

  vault:
    image: hashicorp/vault:1.15
    container_name: foxhunt-vault
    restart: unless-stopped
    environment:
      VAULT_ADDR: http://0.0.0.0:8200
      VAULT_API_ADDR: http://0.0.0.0:8200
      # Production: Remove VAULT_DEV_ROOT_TOKEN_ID and use proper initialization
      VAULT_DEV_ROOT_TOKEN_ID: ${VAULT_ROOT_TOKEN}
    cap_add:
      - IPC_LOCK
    volumes:
      - vault_data:/vault/file
    networks:
      foxhunt_internal:
        ipv4_address: 172.20.0.13
    command: vault server -dev -dev-listen-address=0.0.0.0:8200
    healthcheck:
      test: ["CMD", "vault", "status"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 256M
        reservations:
          cpus: '0.25'
          memory: 128M

  prometheus:
    image: prom/prometheus:v2.48.0
    container_name: foxhunt-prometheus
    restart: unless-stopped
    volumes:
      - ./config/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./config/prometheus/rules:/etc/prometheus/rules:ro
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.enable-lifecycle'
      - '--query.max-concurrency=50'
    networks:
      foxhunt_internal:
        ipv4_address: 172.20.0.14
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/ready"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 1G
        reservations:
          cpus: '0.5'
          memory: 512M

  grafana:
    image: grafana/grafana:10.2.3
    container_name: foxhunt-grafana
    restart: unless-stopped
    environment:
      GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD}
      GF_INSTALL_PLUGINS: grafana-piechart-panel
      GF_SERVER_ROOT_URL: ${GRAFANA_ROOT_URL:-http://localhost:3000}
    volumes:
      - grafana_data:/var/lib/grafana
      - ./config/grafana/dashboards:/var/lib/grafana/dashboards:ro
      - ./config/grafana/provisioning:/etc/grafana/provisioning:ro
    networks:
      foxhunt_internal:
        ipv4_address: 172.20.0.15
    depends_on:
      prometheus:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3000/api/health"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s
    deploy:
      resources:
        limits:
          cpus: '0.5'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 256M

  # =============================================================================
  # API Gateway (Wave 70 - New Service)
  # =============================================================================

  api_gateway:
    build:
      context: .
      dockerfile: services/api_gateway/Dockerfile
      args:
        RUST_VERSION: 1.83
    container_name: foxhunt-api-gateway
    restart: unless-stopped
    environment:
      # Service configuration
      API_GATEWAY_HOST: 0.0.0.0
      API_GATEWAY_PORT: ${API_GATEWAY_PORT:-50050}
      METRICS_PORT: ${API_GATEWAY_METRICS_PORT:-9091}

      # Authentication
      JWT_SECRET: ${JWT_SECRET}
      JWT_EXPIRY_SECONDS: ${JWT_EXPIRY_SECONDS:-3600}

      # Rate limiting
      RATE_LIMIT_REQUESTS: ${RATE_LIMIT_REQUESTS:-100}
      RATE_LIMIT_WINDOW_SECS: ${RATE_LIMIT_WINDOW_SECS:-60}

      # Database and cache
      DATABASE_URL: postgresql://${POSTGRES_USER:-foxhunt}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-foxhunt}
      REDIS_URL: redis://redis:6379

      # Backend service endpoints
      TRADING_SERVICE_URL: http://trading_service:50051
      BACKTESTING_SERVICE_URL: http://backtesting_service:50052
      ML_TRAINING_SERVICE_URL: http://ml_training_service:50053

      # Logging
      RUST_LOG: ${RUST_LOG:-info,api_gateway=debug}
      RUST_BACKTRACE: ${RUST_BACKTRACE:-1}
    ports:
      - "${API_GATEWAY_EXTERNAL_PORT:-50050}:${API_GATEWAY_PORT:-50050}"
      - "${API_GATEWAY_METRICS_EXTERNAL_PORT:-9091}:${API_GATEWAY_METRICS_PORT:-9091}"
    networks:
      - foxhunt_internal
      - foxhunt_external
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
      vault:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "/usr/local/bin/grpc_health_probe", "-addr=localhost:${API_GATEWAY_PORT:-50050}"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 1G
        reservations:
          cpus: '1.0'
          memory: 512M

  # =============================================================================
  # Backend Services
  # =============================================================================

  trading_service:
    build:
      context: .
      dockerfile: services/trading_service/Dockerfile
      args:
        RUST_VERSION: 1.83
    container_name: foxhunt-trading-service
    restart: unless-stopped
    environment:
      # Service configuration
      TRADING_SERVICE_HOST: 0.0.0.0
      TRADING_SERVICE_PORT: ${TRADING_SERVICE_PORT:-50051}
      METRICS_PORT: ${TRADING_METRICS_PORT:-9092}

      # Database and cache
      DATABASE_URL: postgresql://${POSTGRES_USER:-foxhunt}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-foxhunt}
      REDIS_URL: redis://redis:6379
      VAULT_ADDR: http://vault:8200
      VAULT_TOKEN: ${VAULT_ROOT_TOKEN}

      # Logging
      RUST_LOG: ${RUST_LOG:-info,trading_service=debug}
      RUST_BACKTRACE: ${RUST_BACKTRACE:-1}
    networks:
      foxhunt_internal:
        ipv4_address: 172.20.0.20
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
      vault:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "/usr/local/bin/grpc_health_probe", "-addr=localhost:${TRADING_SERVICE_PORT:-50051}"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          cpus: '4.0'
          memory: 4G
        reservations:
          cpus: '2.0'
          memory: 2G

  backtesting_service:
    build:
      context: .
      dockerfile: services/backtesting_service/Dockerfile
      args:
        RUST_VERSION: 1.83
    container_name: foxhunt-backtesting-service
    restart: unless-stopped
    environment:
      # Service configuration
      BACKTESTING_SERVICE_HOST: 0.0.0.0
      BACKTESTING_SERVICE_PORT: ${BACKTESTING_SERVICE_PORT:-50052}
      METRICS_PORT: ${BACKTESTING_METRICS_PORT:-9093}

      # Database and cache
      DATABASE_URL: postgresql://${POSTGRES_USER:-foxhunt}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-foxhunt}
      REDIS_URL: redis://redis:6379
      VAULT_ADDR: http://vault:8200
      VAULT_TOKEN: ${VAULT_ROOT_TOKEN}

      # Logging
      RUST_LOG: ${RUST_LOG:-info,backtesting_service=debug}
      RUST_BACKTRACE: ${RUST_BACKTRACE:-1}
    networks:
      foxhunt_internal:
        ipv4_address: 172.20.0.21
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
      vault:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "/usr/local/bin/grpc_health_probe", "-addr=localhost:${BACKTESTING_SERVICE_PORT:-50052}"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 2G
        reservations:
          cpus: '1.0'
          memory: 1G

  ml_training_service:
    build:
      context: .
      dockerfile: services/ml_training_service/Dockerfile
      args:
        RUST_VERSION: 1.83
    container_name: foxhunt-ml-training-service
    restart: unless-stopped
    environment:
      # Service configuration
      ML_TRAINING_SERVICE_HOST: 0.0.0.0
      ML_TRAINING_SERVICE_PORT: ${ML_TRAINING_SERVICE_PORT:-50053}
      METRICS_PORT: ${ML_TRAINING_METRICS_PORT:-9094}

      # Database and cache
      DATABASE_URL: postgresql://${POSTGRES_USER:-foxhunt}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-foxhunt}
      REDIS_URL: redis://redis:6379
      VAULT_ADDR: http://vault:8200
      VAULT_TOKEN: ${VAULT_ROOT_TOKEN}

      # S3 configuration for model storage
      AWS_ACCESS_KEY_ID: ${AWS_ACCESS_KEY_ID}
      AWS_SECRET_ACCESS_KEY: ${AWS_SECRET_ACCESS_KEY}
      AWS_REGION: ${AWS_REGION:-us-east-1}
      S3_MODEL_BUCKET: ${S3_MODEL_BUCKET:-foxhunt-models}

      # Logging
      RUST_LOG: ${RUST_LOG:-info,ml_training_service=debug}
      RUST_BACKTRACE: ${RUST_BACKTRACE:-1}
    networks:
      foxhunt_internal:
        ipv4_address: 172.20.0.22
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
      vault:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "/usr/local/bin/grpc_health_probe", "-addr=localhost:${ML_TRAINING_SERVICE_PORT:-50053}"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          cpus: '4.0'
          memory: 8G
        reservations:
          cpus: '2.0'
          memory: 4G

  # =============================================================================
  # TLI (Terminal Interface Client) - Optional for debugging
  # =============================================================================

  tli:
    build:
      context: .
      dockerfile: tli/Dockerfile
      args:
        RUST_VERSION: 1.83
    container_name: foxhunt-tli
    stdin_open: true
    tty: true
    environment:
      # API Gateway connection
      API_GATEWAY_URL: http://api_gateway:${API_GATEWAY_PORT:-50050}

      # Logging
      RUST_LOG: ${RUST_LOG:-info,tli=debug}
      RUST_BACKTRACE: ${RUST_BACKTRACE:-1}
    networks:
      - foxhunt_internal
    depends_on:
      api_gateway:
        condition: service_healthy
    # No restart policy - TLI is interactive
    profiles:
      - debug