infra/roles/services/templates/docker-compose.yml.j2

# Docker Compose stack — generated by Ansible
# Do not edit manually; re-run ansible-playbook deploy.yml
#
# NOTE: Traefik uses the file provider (routes.yml.j2) — Docker labels on
# containers are intentionally absent. Adding labels here has no effect.

networks:
  # proxy — публичная сеть только для Traefik: нужна для исходящего интернет-доступа
  # (ACME Let's Encrypt, внешние сервисы). backend — internal: true, поэтому
  # сервисы не имеют прямого исходящего доступа в интернет.
  proxy:
    driver: bridge
  backend:
    driver: bridge
    internal: true
  forgejo-db:
    driver: bridge
    internal: true
  forgejo-ssh:
    driver: bridge
  plane-internal:
    driver: bridge
    internal: true
  runner-jobs:
    driver: bridge
  monitoring:
    driver: bridge
    internal: true
  authelia-internal:
    driver: bridge
    internal: true

volumes:
  forgejo_data:
  forgejo_db_data:
  plane_pgdata:
  plane_redis_data:
  plane_minio_data:
  plane_media:
  act_runner_data:
  prometheus_data:
  grafana_data:
  loki_data:
  crowdsec_data:
  authelia_data:
  uptime_kuma_data:

services:

  # ── Traefik ────────────────────────────────────────────────────────────────
  # proxy — для ACME (исходящий интернет), backend — для маршрутизации к сервисам
  traefik:
    image: {{ traefik_image }}
    container_name: traefik
    restart: unless-stopped
    security_opt:
      - no-new-privileges:true
    ports:
      - "80:80"
      - "443:443"
    networks:
      - proxy
      - backend
    volumes:
      - {{ services_root }}/traefik/traefik.yml:/etc/traefik/traefik.yml:ro
      - {{ services_root }}/traefik/dynamic:/etc/traefik/dynamic:ro
      - {{ services_root }}/traefik/acme.json:/acme/acme.json
      - {{ services_root }}/traefik/logs:/var/log/traefik
    # env_file passes CLOUDFLARE_DNS_API_TOKEN (and all secrets) to Traefik
    env_file: .env
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"
    healthcheck:
      test: ["CMD", "traefik", "healthcheck", "--ping"]
      interval: 30s
      timeout: 5s
      retries: 3

  # ── Forgejo ────────────────────────────────────────────────────────────────
  forgejo:
    image: {{ forgejo_image }}
    container_name: forgejo
    restart: unless-stopped
    security_opt:
      - no-new-privileges:true
    depends_on:
      forgejo-db:
        condition: service_healthy
    networks:
      - backend
      - forgejo-db
      - forgejo-ssh
    volumes:
      - forgejo_data:/data
      - /etc/timezone:/etc/timezone:ro
      - /etc/localtime:/etc/localtime:ro
    environment:
      - USER_UID=1000
      - USER_GID=1000
      - FORGEJO__database__DB_TYPE=postgres
      - FORGEJO__database__HOST=forgejo-db:5432
      - FORGEJO__database__NAME=forgejo
      - FORGEJO__database__USER=forgejo
      - FORGEJO__database__PASSWD=${FORGEJO_DB_PASSWORD}
      - FORGEJO__server__DOMAIN={{ domain_git }}
      - FORGEJO__server__ROOT_URL=https://{{ domain_git }}
      - FORGEJO__server__SSH_DOMAIN={{ domain_git }}
      - FORGEJO__server__SSH_PORT=2222
      - FORGEJO__service__DISABLE_REGISTRATION=true
    ports:
      - "2222:22"
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://localhost:3000/"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s

  forgejo-db:
    image: {{ forgejo_db_image }}
    container_name: forgejo-db
    restart: unless-stopped
    networks:
      - forgejo-db
    volumes:
      - forgejo_db_data:/var/lib/postgresql/data
    environment:
      - POSTGRES_USER=forgejo
      - POSTGRES_PASSWORD=${FORGEJO_DB_PASSWORD}
      - POSTGRES_DB=forgejo
      - PGDATA=/var/lib/postgresql/data/pgdata
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U forgejo"]
      interval: 10s
      timeout: 5s
      retries: 5
    mem_limit: 512m

  # ── Plane ──────────────────────────────────────────────────────────────────
  # Маршрутизация через Traefik:
  #   /api/* и /auth/* → plane-api:8000 (Django, на backend + plane-internal)
  #   остальное       → plane-web:3000  (Next.js, на backend + plane-internal)
  # Правило с PathPrefix длиннее → более высокий приоритет у Traefik автоматически.
  #
  # NOTE: Plane не публикует конкретные version tags — используем :stable.
  # Следить за обновлениями: https://github.com/makeplane/plane/releases

  plane-web:
    image: {{ plane_frontend_image }}
    container_name: plane-web
    restart: unless-stopped
    depends_on:
      - plane-api
    environment:
      - WEB_URL=https://{{ domain_plane }}
      - NEXT_PUBLIC_API_BASE_URL=https://{{ domain_plane }}
    networks:
      - backend
      - plane-internal
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://127.0.0.1:3000/"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 30s

  plane-admin:
    image: {{ plane_admin_image }}
    container_name: plane-admin
    restart: unless-stopped
    depends_on:
      - plane-api
      - plane-web
    networks:
      - backend
      - plane-internal
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://127.0.0.1:3000/"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 30s

  plane-space:
    image: {{ plane_space_image }}
    container_name: plane-space
    restart: unless-stopped
    depends_on:
      - plane-api
      - plane-web
    networks:
      - backend
      - plane-internal
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://127.0.0.1:3000/spaces/"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 30s

  plane-api:
    image: {{ plane_backend_image }}
    container_name: plane-api
    restart: unless-stopped
    mem_limit: 512m
    command: ./bin/docker-entrypoint-api.sh
    depends_on:
      plane-db:
        condition: service_healthy
      plane-redis:
        condition: service_started
      plane-minio:
        condition: service_healthy
    networks:
      - backend
      - plane-internal
    volumes:
      - plane_media:/app/media
    environment:
      - DATABASE_URL=postgresql://plane:${PLANE_DB_PASSWORD}@plane-db:5432/plane
      - REDIS_URL=redis://plane-redis:6379/
      - AMQP_URL=redis://plane-redis:6379/
      - SECRET_KEY=${PLANE_SECRET_KEY}
      - DEBUG=0
      - DJANGO_SETTINGS_MODULE=plane.settings.production
      - WEB_URL=https://{{ domain_plane }}
      - FILE_SIZE_LIMIT=5242880
      - USE_MINIO=1
      - AWS_REGION=us-east-1
      - AWS_ACCESS_KEY_ID=plane-minio
      - AWS_SECRET_ACCESS_KEY=${PLANE_MINIO_PASSWORD}
      - AWS_S3_ENDPOINT_URL=http://plane-minio:9000
      - AWS_S3_BUCKET_NAME=uploads
      - MINIO_ROOT_USER=plane-minio
      - MINIO_ROOT_PASSWORD=${PLANE_MINIO_PASSWORD}
      - GUNICORN_WORKERS=2
      - APP_BASE_URL=https://{{ domain_plane }}
      - ADMIN_BASE_URL=https://{{ domain_plane }}/god-mode
      - SPACE_BASE_URL=https://{{ domain_plane }}/spaces
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://127.0.0.1:8000/"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s

  plane-worker:
    image: {{ plane_backend_image }}
    container_name: plane-worker
    restart: unless-stopped
    mem_limit: 512m
    command: ./bin/docker-entrypoint-worker.sh
    depends_on:
      - plane-api
    networks:
      - plane-internal
    volumes:
      - plane_media:/app/media
    environment:
      - DATABASE_URL=postgresql://plane:${PLANE_DB_PASSWORD}@plane-db:5432/plane
      - REDIS_URL=redis://plane-redis:6379/
      - AMQP_URL=redis://plane-redis:6379/
      - SECRET_KEY=${PLANE_SECRET_KEY}
      - DEBUG=0
      - DJANGO_SETTINGS_MODULE=plane.settings.production
      - USE_MINIO=1
      - AWS_REGION=us-east-1
      - AWS_ACCESS_KEY_ID=plane-minio
      - AWS_SECRET_ACCESS_KEY=${PLANE_MINIO_PASSWORD}
      - AWS_S3_ENDPOINT_URL=http://plane-minio:9000
      - AWS_S3_BUCKET_NAME=uploads
      - MINIO_ROOT_USER=plane-minio
      - MINIO_ROOT_PASSWORD=${PLANE_MINIO_PASSWORD}

  plane-beat:
    image: {{ plane_backend_image }}
    container_name: plane-beat
    restart: unless-stopped
    mem_limit: 256m
    command: ./bin/docker-entrypoint-beat.sh
    depends_on:
      - plane-api
    networks:
      - plane-internal
    environment:
      - DATABASE_URL=postgresql://plane:${PLANE_DB_PASSWORD}@plane-db:5432/plane
      - REDIS_URL=redis://plane-redis:6379/
      - AMQP_URL=redis://plane-redis:6379/
      - SECRET_KEY=${PLANE_SECRET_KEY}
      - DEBUG=0
      - DJANGO_SETTINGS_MODULE=plane.settings.production
      - USE_MINIO=1
      - AWS_REGION=us-east-1
      - AWS_ACCESS_KEY_ID=plane-minio
      - AWS_SECRET_ACCESS_KEY=${PLANE_MINIO_PASSWORD}
      - AWS_S3_ENDPOINT_URL=http://plane-minio:9000
      - AWS_S3_BUCKET_NAME=uploads
      - MINIO_ROOT_USER=plane-minio
      - MINIO_ROOT_PASSWORD=${PLANE_MINIO_PASSWORD}

  plane-db:
    image: {{ plane_db_image }}
    container_name: plane-db
    restart: unless-stopped
    mem_limit: 512m
    networks:
      - plane-internal
    volumes:
      - plane_pgdata:/var/lib/postgresql/data
    environment:
      - POSTGRES_USER=plane
      - POSTGRES_PASSWORD=${PLANE_DB_PASSWORD}
      - POSTGRES_DB=plane
      - PGDATA=/var/lib/postgresql/data/pgdata
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U plane"]
      interval: 10s
      timeout: 5s
      retries: 5

  plane-redis:
    image: {{ plane_redis_image }}
    container_name: plane-redis
    restart: unless-stopped
    networks:
      - plane-internal
    volumes:
      - plane_redis_data:/data
    command: redis-server --appendonly yes
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 3s
      retries: 5

  plane-minio:
    image: {{ plane_minio_image }}
    container_name: plane-minio
    restart: unless-stopped
    mem_limit: 512m
    networks:
      - plane-internal
    volumes:
      - plane_minio_data:/data
    environment:
      - MINIO_ROOT_USER=plane-minio
      - MINIO_ROOT_PASSWORD=${PLANE_MINIO_PASSWORD}
    command: server /data --console-address ":9001"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
      interval: 30s
      timeout: 20s
      retries: 3

  # ── Forgejo Actions Runner ─────────────────────────────────────────────────
  # backend — для связи с Forgejo по внутренней сети (http://forgejo:3000)
  # runner-jobs — сеть с интернет-доступом для job-контейнеров
  act_runner:
    image: {{ act_runner_image }}
    container_name: act_runner
    restart: unless-stopped
    depends_on:
      - forgejo
    environment:
      - GITEA_INSTANCE_URL=https://{{ domain_git }}
      - GITEA_RUNNER_REGISTRATION_TOKEN=${FORGEJO_RUNNER_TOKEN}
      - GITEA_RUNNER_NAME=vps-runner
      - CONFIG_FILE=/data/config.yaml
    volumes:
      - act_runner_data:/data
      - /var/run/docker.sock:/var/run/docker.sock
      - {{ services_root }}/act_runner/config.yaml:/data/config.yaml:ro
    networks:
      - backend
      - runner-jobs

  # ── Monitoring Stack ───────────────────────────────────────────────────────
  prometheus:
    image: {{ prometheus_image }}
    container_name: prometheus
    restart: unless-stopped
    networks:
      - monitoring
    volumes:
      - prometheus_data:/prometheus
      - {{ services_root }}/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - {{ services_root }}/prometheus/rules:/etc/prometheus/rules:ro
    command:
      - "--config.file=/etc/prometheus/prometheus.yml"
      - "--storage.tsdb.path=/prometheus"
      - "--storage.tsdb.retention.time=30d"
      - "--web.console.libraries=/usr/share/prometheus/console_libraries"
      - "--web.console.templates=/usr/share/prometheus/consoles"
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 5s
      retries: 3

  alertmanager:
    image: {{ alertmanager_image }}
    container_name: alertmanager
    restart: unless-stopped
    networks:
      - monitoring
    volumes:
      - {{ services_root }}/prometheus/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
    command:
      - "--config.file=/etc/alertmanager/alertmanager.yml"
      - "--storage.path=/alertmanager"
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://localhost:9093/-/healthy"]
      interval: 30s
      timeout: 5s
      retries: 3

  node-exporter:
    image: {{ node_exporter_image }}
    container_name: node-exporter
    restart: unless-stopped
    networks:
      - monitoring
    pid: host
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - "--path.procfs=/host/proc"
      - "--path.sysfs=/host/sys"
      - "--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)"

  cadvisor:
    image: {{ cadvisor_image }}
    container_name: cadvisor
    restart: unless-stopped
    networks:
      - monitoring
    privileged: true
    devices:
      - /dev/kmsg
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker:/var/lib/docker:ro
      - /dev/disk:/dev/disk:ro

  grafana:
    image: {{ grafana_image }}
    container_name: grafana
    restart: unless-stopped
    security_opt:
      - no-new-privileges:true
    depends_on:
      - prometheus
    networks:
      - backend
      - monitoring
    volumes:
      - grafana_data:/var/lib/grafana
      - {{ services_root }}/grafana/provisioning:/etc/grafana/provisioning:ro
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_DOMAIN={{ domain_dashboard }}
      - GF_SERVER_ROOT_URL=https://{{ domain_dashboard }}
      - GF_AUTH_ANONYMOUS_ENABLED=false
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 5s
      retries: 3

  # ── Logging Stack ──────────────────────────────────────────────────────────
  loki:
    image: {{ loki_image }}
    container_name: loki
    restart: unless-stopped
    networks:
      - monitoring
    volumes:
      - loki_data:/loki
      - {{ services_root }}/loki/loki.yml:/etc/loki/local-config.yaml:ro
    command: -config.file=/etc/loki/local-config.yaml
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://localhost:3100/ready"]
      interval: 30s
      timeout: 5s
      retries: 3

  promtail:
    image: {{ promtail_image }}
    container_name: promtail
    restart: unless-stopped
    networks:
      - monitoring
    volumes:
      - /var/log:/var/log:ro
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - {{ services_root }}/loki/promtail.yml:/etc/promtail/config.yml:ro
    command: -config.file=/etc/promtail/config.yml

  # ── Security Stack ─────────────────────────────────────────────────────────
  # CrowdSec: анализирует логи Traefik, банит злоумышленников по IP
  # Использует community-репутацию + локальный анализ поведения
  crowdsec:
    image: {{ crowdsec_image }}
    container_name: crowdsec
    restart: unless-stopped
    networks:
      - monitoring
      - proxy      # needs internet for hub/threat-intel downloads
    environment:
      - COLLECTIONS=crowdsecurity/traefik crowdsecurity/http-cve crowdsecurity/linux
      - GID=1000
    volumes:
      - crowdsec_data:/var/lib/crowdsec/data
      - {{ services_root }}/crowdsec/acquis.yaml:/etc/crowdsec/acquis.yaml:ro
      - {{ services_root }}/traefik/logs:/var/log/traefik:ro
      - /var/log/auth.log:/var/log/auth.log:ro
      - /var/log/syslog:/var/log/syslog:ro


  # ── Authelia: 2FA SSO portal ───────────────────────────────────────────────
  # Защищает: Traefik dashboard, Plane /god-mode/
  # Вход: логин + пароль + TOTP (Google Authenticator)
  authelia:
    image: {{ authelia_image }}
    container_name: authelia
    restart: unless-stopped
    depends_on:
      - authelia-redis
    networks:
      - backend
      - authelia-internal
    volumes:
      - authelia_data:/config
      - {{ services_root }}/authelia/configuration.yml:/config/configuration.yml:ro
      - {{ services_root }}/authelia/users.yml:/config/users.yml:ro
    environment:
      - AUTHELIA_JWT_SECRET=${AUTHELIA_JWT_SECRET}
      - AUTHELIA_SESSION_SECRET=${AUTHELIA_SESSION_SECRET}
      - AUTHELIA_STORAGE_ENCRYPTION_KEY=${AUTHELIA_STORAGE_KEY}
      - TZ=UTC
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://localhost:9091/api/health"]
      interval: 30s
      timeout: 5s
      retries: 3

  authelia-redis:
    image: {{ redis_image }}
    container_name: authelia-redis
    restart: unless-stopped
    networks:
      - authelia-internal
    command: redis-server --appendonly yes --maxmemory 64mb --maxmemory-policy allkeys-lru

  # ── Discord Bot ────────────────────────────────────────────────────────────
  # Infrastructure management bot: /status /logs /restart /deploy /metrics /backup
  # Image is built and pushed by the discord-bot repo CI/CD
  discord-bot:
    image: git.{{ domain_base }}/jack/discord-bot:latest
    container_name: discord-bot
    restart: unless-stopped
    environment:
      DISCORD_TOKEN:  "${DISCORD_BOT_TOKEN}"
      DISCORD_APP_ID: "{{ discord_bot_app_id }}"
      FORGEJO_TOKEN:  "${FORGEJO_RUNNER_TOKEN}"
      FORGEJO_URL:    "https://{{ domain_git }}"
      FORGEJO_REPO:   "jack/infra"
      PROMETHEUS_URL: "http://prometheus:9090"
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
    networks:
      - proxy       # Discord API (internet)
      - monitoring  # Prometheus metrics

  # ── Walava Landing ─────────────────────────────────────────────────────────
  # Landing page for walava.io — image built by walava-web repo CI/CD
  walava-web:
    image: git.{{ domain_base }}/jack/walava-web:latest
    container_name: walava-web
    restart: unless-stopped
    networks:
      - proxy

  # ── Uptime Kuma ────────────────────────────────────────────────────────────
  # Мониторинг доступности сервисов + публичная статус-страница
  # Доступен по адресу: https://{{ domain_status }}
  uptime-kuma:
    image: {{ uptime_kuma_image }}
    container_name: uptime-kuma
    restart: unless-stopped
    security_opt:
      - no-new-privileges:true
    networks:
      - backend
      - proxy  # needs internet access for Discord/Telegram notifications
    volumes:
      - uptime_kuma_data:/app/data
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://localhost:3001/"]
      interval: 30s
      timeout: 5s
      retries: 3