bootnode/infra/do-app-platform/hanzo-platform-stack.yml

version: '3.8'

networks:
  hanzo-network:
    driver: overlay
    attachable: true
  platform-network:
    external: true

volumes:
  postgres_data:
  redis_data:
  traefik_certs:

services:
  traefik:
    image: traefik:v2.11
    deploy:
      mode: global
      placement:
        constraints:
          - node.role == manager
      update_config:
        parallelism: 1
        delay: 10s
      restart_policy:
        condition: on-failure
        delay: 5s
    command:
      - --api.dashboard=true
      - --api.insecure=true
      - --providers.docker=true
      - --providers.docker.swarmMode=true
      - --providers.docker.exposedbydefault=false
      - --providers.docker.network=hanzo_hanzo-network
      - --providers.file.directory=/etc/platform/traefik/dynamic
      - --providers.file.watch=true
      - --entrypoints.web.address=:80
      - --entrypoints.websecure.address=:443
      - --[email protected]
      - --certificatesresolvers.letsencrypt.acme.storage=/etc/traefik/acme.json
      - --certificatesresolvers.letsencrypt.acme.httpchallenge.entrypoint=web
      - --entrypoints.web.http.redirections.entrypoint.to=websecure
      - --entrypoints.web.http.redirections.entrypoint.scheme=https
    ports:
      - "80:80"
      - "443:443"
      - "8080:8080"
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - traefik_certs:/etc/traefik
      - /etc/platform/traefik:/etc/platform/traefik:ro
    networks:
      - hanzo-network
      - platform-network

  postgres:
    image: postgres:16-alpine
    deploy:
      mode: replicated
      replicas: 1
      placement:
        constraints:
          - node.role == manager
      restart_policy:
        condition: on-failure
    environment:
      POSTGRES_USER: hanzo
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-changeme}
      POSTGRES_DB: platform
    volumes:
      - postgres_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U hanzo"]
      interval: 5s
      timeout: 5s
      retries: 5
    networks:
      - hanzo-network

  redis:
    image: redis:7-alpine
    deploy:
      mode: replicated
      replicas: 1
      placement:
        constraints:
          - node.role == manager
      restart_policy:
        condition: on-failure
    command: redis-server --requirepass ${REDIS_PASSWORD:-changeme} --appendonly yes
    volumes:
      - redis_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "-a", "${REDIS_PASSWORD:-changeme}", "ping"]
      interval: 5s
      timeout: 5s
      retries: 5
    networks:
      - hanzo-network

  # ==========================================================================
  # Platform - Production (Scalable)
  # ==========================================================================
  platform:
    image: hanzoai/platform:latest
    deploy:
      mode: replicated
      replicas: 2
      update_config:
        parallelism: 1
        delay: 10s
        order: start-first
        failure_action: rollback
      rollback_config:
        parallelism: 1
        delay: 10s
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      labels:
        - "traefik.enable=true"
        - "traefik.http.routers.platform.rule=Host(`platform.hanzo.ai`)"
        - "traefik.http.routers.platform.tls.certresolver=letsencrypt"
        - "traefik.http.services.platform.loadbalancer.server.port=3000"
    environment:
      NODE_ENV: production
      DATABASE_URL: postgresql://hanzo:${POSTGRES_PASSWORD:-changeme}@postgres:5432/platform
      REDIS_URL: redis://:${REDIS_PASSWORD:-changeme}@redis:6379
      REDIS_HOST: redis
      REDIS_PORT: "6379"
      REDIS_PASSWORD: ${REDIS_PASSWORD:-changeme}
      NEXTAUTH_URL: https://platform.hanzo.ai
      NEXTAUTH_SECRET: ${NEXTAUTH_SECRET:-changeme}
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock
      - /etc/platform:/etc/platform
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 90s
    networks:
      - hanzo-network

  # ==========================================================================
  # Platform - Staging
  # ==========================================================================
  platform-staging:
    image: hanzoai/platform:latest
    deploy:
      mode: replicated
      replicas: 1
      update_config:
        parallelism: 1
        delay: 10s
        order: start-first
        failure_action: rollback
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      labels:
        - "traefik.enable=true"
        - "traefik.http.routers.platform-staging.rule=Host(`staging.platform.hanzo.ai`)"
        - "traefik.http.routers.platform-staging.tls.certresolver=letsencrypt"
        - "traefik.http.services.platform-staging.loadbalancer.server.port=3000"
    environment:
      NODE_ENV: production
      DATABASE_URL: postgresql://hanzo:${POSTGRES_PASSWORD:-changeme}@postgres:5432/platform_staging
      REDIS_URL: redis://:${REDIS_PASSWORD:-changeme}@redis:6379/1
      REDIS_HOST: redis
      REDIS_PORT: "6379"
      REDIS_PASSWORD: ${REDIS_PASSWORD:-changeme}
      REDIS_DB: "1"
      NEXTAUTH_URL: https://staging.platform.hanzo.ai
      NEXTAUTH_SECRET: ${NEXTAUTH_SECRET:-changeme}
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock
      - /etc/platform:/etc/platform
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 90s
    networks:
      - hanzo-network