social-app/deploy/docker-compose.prod.yml

name: social-app-prod

services:
    redis:
        image: redis:7-alpine
        container_name: social-prod-redis
        restart: unless-stopped
        environment:
            - REDIS_PASSWORD=${SOCIAL_REDIS__PASSWORD}
        command: >
            sh -c 'test -n "$$REDIS_PASSWORD" && exec redis-server --appendonly yes --dir /data --requirepass "$$REDIS_PASSWORD" || (echo "REDIS_PASSWORD is required" >&2; exit 1)'
        volumes:
            - redis_data:/data
        healthcheck:
            test:
                [
                    "CMD",
                    "sh",
                    "-c",
                    'if [ -n "$$REDIS_PASSWORD" ]; then redis-cli -a "$$REDIS_PASSWORD" ping; else redis-cli ping; fi',
                ]
            interval: 5s
            timeout: 3s
            retries: 10

    litellm-config-job:
        image: ${SOCIAL_BACKEND_IMAGE:-social-app-backend:prod}
        container_name: social-prod-litellm-config-job
        restart: "no"
        env_file:
            - ./.env.prod
        environment:
            - PYTHONPATH=/app/backend/src
            - PYTHONDONTWRITEBYTECODE=1
        command: >
            .venv/bin/python backend/scripts/build_litellm_proxy_config.py --output /config/litellm-proxy-config.yaml
        volumes:
            - litellm_config:/config
        depends_on:
            redis:
                condition: service_healthy

    litellm:
        image: ghcr.io/berriai/litellm@sha256:b959a1816fa454a14d2842242d0fa1cd0d39f96fc94d3a1f4e1de4e48e2398c6
        container_name: social-prod-litellm
        restart: unless-stopped
        env_file:
            - ./.env.prod
        command: >
            --config /config/litellm-proxy-config.yaml --host ${SOCIAL_LITELLM__BIND_HOST:-0.0.0.0} --port ${SOCIAL_LITELLM__PORT:-3875}
        volumes:
            - litellm_config:/config:ro
        depends_on:
            redis:
                condition: service_healthy
            litellm-config-job:
                condition: service_completed_successfully
        healthcheck:
            test:
                [
                    "CMD",
                    "python",
                    "-c",
                    "import os,sys,urllib.request;port=os.getenv('SOCIAL_LITELLM__PORT','3875');u=f'http://127.0.0.1:{port}/health';sys.exit(0 if urllib.request.urlopen(u, timeout=3).getcode() < 500 else 1)",
                ]
            interval: 15s
            timeout: 5s
            retries: 10

    web:
        image: ${SOCIAL_BACKEND_IMAGE:-social-app-backend:prod}
        container_name: social-prod-web
        restart: unless-stopped
        env_file:
            - ./.env.prod
        environment:
            - PYTHONPATH=/app/backend/src
            - PYTHONDONTWRITEBYTECODE=1
            - SOCIAL_RUNTIME__SERVICE_NAME=web
            - SOCIAL_RUNTIME__ENVIRONMENT=${SOCIAL_RUNTIME__ENVIRONMENT:-prod}
            - SOCIAL_REDIS__HOST=redis
            - SOCIAL_REDIS__PORT=6379
            - SOCIAL_LITELLM__HOST=litellm
            - SOCIAL_LITELLM__PORT=${SOCIAL_LITELLM__PORT:-3875}
        command: >
            sh -c '.venv/bin/uvicorn app:app --host ${SOCIAL_WEB__HOST:-0.0.0.0} --port ${SOCIAL_WEB__PORT:-5775} --workers ${SOCIAL_WEB__WORKERS:-2} --log-level $(printf "%s" "${SOCIAL_RUNTIME__LOG_LEVEL:-info}" | tr "[:upper:]" "[:lower:]")'
        ports:
            - "127.0.0.1:${SOCIAL_WEB__PORT:-5775}:${SOCIAL_WEB__PORT:-5775}"
        depends_on:
            redis:
                condition: service_healthy
            litellm:
                condition: service_healthy
        volumes:
            - ../logs:/app/logs
            - ./static/releases:/app/deploy/static/releases:ro
        healthcheck:
            test:
                [
                    "CMD",
                    "python",
                    "-c",
                    "import os,sys,urllib.request;port=os.getenv('SOCIAL_WEB__PORT','5775');u=f'http://127.0.0.1:{port}/health';sys.exit(0 if urllib.request.urlopen(u, timeout=3).getcode() < 500 else 1)",
                ]
            interval: 15s
            timeout: 5s
            retries: 10

    worker-critical:
        image: ${SOCIAL_BACKEND_IMAGE:-social-app-backend:prod}
        container_name: social-prod-worker-critical
        restart: unless-stopped
        env_file:
            - ./.env.prod
        environment:
            - PYTHONPATH=/app/backend/src
            - PYTHONDONTWRITEBYTECODE=1
            - SOCIAL_RUNTIME__SERVICE_NAME=worker-critical
            - SOCIAL_RUNTIME__ENVIRONMENT=${SOCIAL_RUNTIME__ENVIRONMENT:-prod}
            - SOCIAL_REDIS__HOST=redis
            - SOCIAL_REDIS__PORT=6379
            - SOCIAL_LITELLM__HOST=litellm
            - SOCIAL_LITELLM__PORT=${SOCIAL_LITELLM__PORT:-3875}
        command: >
            sh -c '.venv/bin/taskiq worker core.taskiq.app:critical_broker core.agentscope.runtime.tasks --workers ${SOCIAL_WORKER__GROUPS__CRITICAL__CONCURRENCY:-2}'
        depends_on:
            redis:
                condition: service_healthy
            litellm:
                condition: service_healthy
        volumes:
            - ../logs:/app/logs
            - ./static/releases:/app/deploy/static/releases:ro

    worker-default:
        image: ${SOCIAL_BACKEND_IMAGE:-social-app-backend:prod}
        container_name: social-prod-worker-default
        restart: unless-stopped
        env_file:
            - ./.env.prod
        environment:
            - PYTHONPATH=/app/backend/src
            - PYTHONDONTWRITEBYTECODE=1
            - SOCIAL_RUNTIME__SERVICE_NAME=worker-default
            - SOCIAL_RUNTIME__ENVIRONMENT=${SOCIAL_RUNTIME__ENVIRONMENT:-prod}
            - SOCIAL_REDIS__HOST=redis
            - SOCIAL_REDIS__PORT=6379
            - SOCIAL_LITELLM__HOST=litellm
            - SOCIAL_LITELLM__PORT=${SOCIAL_LITELLM__PORT:-3875}
        command: >
            sh -c '.venv/bin/taskiq worker core.taskiq.app:default_broker core.agentscope.runtime.tasks --workers ${SOCIAL_WORKER__GROUPS__DEFAULT__CONCURRENCY:-2}'
        depends_on:
            redis:
                condition: service_healthy
            litellm:
                condition: service_healthy
        volumes:
            - ../logs:/app/logs
            - ./static/releases:/app/deploy/static/releases:ro

    worker-bulk:
        image: ${SOCIAL_BACKEND_IMAGE:-social-app-backend:prod}
        container_name: social-prod-worker-bulk
        restart: unless-stopped
        env_file:
            - ./.env.prod
        environment:
            - PYTHONPATH=/app/backend/src
            - PYTHONDONTWRITEBYTECODE=1
            - SOCIAL_RUNTIME__SERVICE_NAME=worker-bulk
            - SOCIAL_RUNTIME__ENVIRONMENT=${SOCIAL_RUNTIME__ENVIRONMENT:-prod}
            - SOCIAL_REDIS__HOST=redis
            - SOCIAL_REDIS__PORT=6379
            - SOCIAL_LITELLM__HOST=litellm
            - SOCIAL_LITELLM__PORT=${SOCIAL_LITELLM__PORT:-3875}
        command: >
            sh -c '.venv/bin/taskiq worker core.taskiq.app:bulk_broker core.agentscope.runtime.tasks --workers ${SOCIAL_WORKER__GROUPS__BULK__CONCURRENCY:-1}'
        depends_on:
            redis:
                condition: service_healthy
            litellm:
                condition: service_healthy
        volumes:
            - ../logs:/app/logs
            - ./static/releases:/app/deploy/static/releases:ro

    init-job:
        image: ${SOCIAL_BACKEND_IMAGE:-social-app-backend:prod}
        container_name: social-prod-init-job
        restart: "no"
        env_file:
            - ./.env.prod
        environment:
            - PYTHONPATH=/app/backend/src
            - PYTHONDONTWRITEBYTECODE=1
            - SOCIAL_RUNTIME__SERVICE_NAME=init-job
            - SOCIAL_RUNTIME__ENVIRONMENT=${SOCIAL_RUNTIME__ENVIRONMENT:-prod}
            - SOCIAL_REDIS__HOST=redis
            - SOCIAL_REDIS__PORT=6379
            - SOCIAL_LITELLM__HOST=litellm
            - SOCIAL_LITELLM__PORT=${SOCIAL_LITELLM__PORT:-3875}
        command: .venv/bin/python -m core.runtime.cli bootstrap
        depends_on:
            redis:
                condition: service_healthy
            litellm:
                condition: service_healthy
        volumes:
            - ../logs:/app/logs
            - ./static/releases:/app/deploy/static/releases:ro
        profiles:
            - job

volumes:
    redis_data:
    litellm_config: