prod/docker-compose.yml

services:
  # Prometheus Monitoring
  prometheus:
    image: prom/prometheus:latest
    container_name: bots_prometheus
    restart: unless-stopped
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--storage.tsdb.retention.time=${PROMETHEUS_RETENTION_DAYS:-30}d'
      - '--web.enable-lifecycle'
    ports:
      - "9090:9090"
    volumes:
      - ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus_data:/prometheus
    networks:
      - bots_network
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

  # Grafana Dashboard
  grafana:
    image: grafana/grafana:latest
    container_name: bots_grafana
    restart: unless-stopped
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource
    ports:
      - "3000:3000"
    volumes:
      - grafana_data:/var/lib/grafana
      - ./infra/grafana/provisioning:/etc/grafana/provisioning:ro
    networks:
      - bots_network
    depends_on:
      - prometheus
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:3000/api/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3

  # Server Monitoring Service
  server_monitor:
    build: .
    container_name: bots_server_monitor
    restart: unless-stopped
    ports:
      - "9091:9091"
    environment:
      - TELEGRAM_BOT_TOKEN=${TELEGRAM_MONITORING_BOT_TOKEN}
      - GROUP_FOR_LOGS=${GROUP_MONITORING_FOR_LOGS}
      - IMPORTANT_LOGS=${IMPORTANT_MONITORING_LOGS}
      - THRESHOLD=${THRESHOLD:-80.0}
      - RECOVERY_THRESHOLD=${RECOVERY_THRESHOLD:-75.0}
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /var/run:/host/var/run:ro
    networks:
      - bots_network
    depends_on:
      - prometheus
    healthcheck:
      test: ["CMD-SHELL", "ps aux | grep python | grep server_monitor || exit 1"]
      interval: 60s
      timeout: 10s
      retries: 3

  # Telegram Helper Bot
  telegram-bot:
    build:
      context: ./bots/telegram-helper-bot
      dockerfile: Dockerfile.bot
    container_name: bots_telegram_bot
    restart: unless-stopped
    env_file:
      - ./bots/telegram-helper-bot/.env
    ports:
      - "8080:8080"
    environment:
      - PYTHONPATH=/app
      - DOCKER_CONTAINER=true
      - LOG_LEVEL=${LOG_LEVEL:-INFO}
      - LOG_RETENTION_DAYS=${LOG_RETENTION_DAYS:-30}
      - METRICS_HOST=${METRICS_HOST:-0.0.0.0}
      - METRICS_PORT=${METRICS_PORT:-8080}
      # Telegram settings
      - TELEGRAM_BOT_TOKEN=${BOT_TOKEN}
      - TELEGRAM_LISTEN_BOT_TOKEN=${LISTEN_BOT_TOKEN}
      - TELEGRAM_TEST_BOT_TOKEN=${TEST_BOT_TOKEN}
      - TELEGRAM_PREVIEW_LINK=${PREVIEW_LINK:-false}
      - TELEGRAM_MAIN_PUBLIC=${MAIN_PUBLIC}
      - TELEGRAM_GROUP_FOR_POSTS=${GROUP_FOR_POSTS}
      - TELEGRAM_GROUP_FOR_MESSAGE=${GROUP_FOR_MESSAGE}
      - TELEGRAM_GROUP_FOR_LOGS=${GROUP_FOR_LOGS}
      - TELEGRAM_IMPORTANT_LOGS=${IMPORTANT_LOGS}
      - TELEGRAM_ARCHIVE=${ARCHIVE}
      - TELEGRAM_TEST_GROUP=${TEST_GROUP}
      # Bot settings
      - SETTINGS_LOGS=${LOGS:-false}
      - SETTINGS_TEST=${TEST:-false}
      # Database
      - DATABASE_PATH=${DATABASE_PATH:-database/tg-bot-database.db}
    volumes:
      - ./bots/telegram-helper-bot/database:/app/database:rw
      - ./bots/telegram-helper-bot/logs:/app/logs:rw
      - ./bots/telegram-helper-bot/.env:/app/.env:ro
    networks:
      - bots_network
    depends_on:
      - prometheus
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
    deploy:
      resources:
        limits:
          memory: 512M
          cpus: '0.5'
        reservations:
          memory: 256M
          cpus: '0.25'

volumes:
  prometheus_data:
    driver: local
  grafana_data:
    driver: local

networks:
  bots_network:
    driver: bridge
    ipam:
      config:
        - subnet: 192.168.100.0/24