ERP/docker-compose.yml

services:
  postgres:
    image: postgres:18
    container_name: procurement-postgres

    environment:
      POSTGRES_DB: procurement
      POSTGRES_USER: postgres
      # Local dev default; production overrides via .env (required by the
      # prod overlay) — never commit real passwords.
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-postgres}

    ports:
      - "5455:5432"

    networks:
      - default
      - shared # monitoring stack scrapes it (postgres-exporter)

    volumes:
      - postgres_data:/var/lib/postgresql
      - ./sql/migration.sql:/docker-entrypoint-initdb.d/01-migration.sql:ro
      - ./sql/02-casdoor-db.sql:/docker-entrypoint-initdb.d/02-casdoor-db.sql:ro

    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U postgres -d procurement"]
      interval: 5s
      timeout: 5s
      retries: 10

    restart: unless-stopped
    mem_limit: 1g

  # ==========================================================================
  # Traefik v3 — public reverse proxy (replaces nginx as the edge)
  # App is served on http://localhost (port 80) instead of :3000.
  # Production: see docker-compose.prod.yml (real domains + HTTPS via
  # Let's Encrypt, HTTP→HTTPS redirect).
  # ==========================================================================
  traefik:
    # v3.6+ required: Traefik ≤3.3 fails against Docker Engine 29.x
    # ("Error response from daemon" — Docker API version mismatch).
    image: traefik:v3.6
    container_name: procurement-traefik
    restart: unless-stopped
    mem_limit: 128m
    command:
      - --providers.docker=true
      - --providers.docker.exposedbydefault=false
      # Containers are on several networks; Traefik must use the dedicated
      # proxy network IP (otherwise it may pick the default-network IP → 504).
      - --providers.docker.network=traefik_network
      - --providers.file.filename=/etc/traefik/dynamic.yml
      - --entrypoints.web.address=:80
      - --entrypoints.websecure.address=:443
      - --certificatesresolvers.letsencrypt.acme.email=${TRAEFIK_ACME_EMAIL:-admin@example.com}
      - --certificatesresolvers.letsencrypt.acme.storage=/certs/acme.json
      - --certificatesresolvers.letsencrypt.acme.httpchallenge=true
      - --certificatesresolvers.letsencrypt.acme.httpchallenge.entrypoint=web
      - --log.level=INFO
    ports:
      - "80:80"
      - "443:443"
    volumes:
      # NOTE: mounted read-write — Docker Desktop rejects read-only
      # /var/run/docker.sock mounts ("Error response from daemon").
      - /var/run/docker.sock:/var/run/docker.sock
      - ./infra/traefik-dynamic.yml:/etc/traefik/dynamic.yml:ro
      - traefik_certs:/certs
    networks:
      - traefik_network

  minio:
    image: minio/minio:latest
    container_name: procurement-minio

    command: server /data --console-address ":9001"

    environment:
      MINIO_ROOT_USER: ${MINIO_ROOT_USER:-minioadmin}
      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-minioadmin}

    ports:
      - "9000:9000"   # S3 API
      - "9001:9001"   # Web console

    volumes:
      - minio_data:/data

    labels:
      - traefik.enable=true
      # S3 API
      - traefik.http.routers.minio-api.rule=Host(`${S3_HOST:-s3.localhost}`)
      - traefik.http.routers.minio-api.entrypoints=web
      - traefik.http.routers.minio-api.service=minio-api-svc
      - traefik.http.services.minio-api-svc.loadbalancer.server.port=9000
      # Web console
      - traefik.http.routers.minio-console.rule=Host(`${STORAGE_HOST:-storage.localhost}`)
      - traefik.http.routers.minio-console.entrypoints=web
      - traefik.http.routers.minio-console.service=minio-console-svc
      - traefik.http.services.minio-console-svc.loadbalancer.server.port=9001

    networks:
      - traefik_network
      - default

    restart: unless-stopped
    mem_limit: 512m

  # MinIO Client (mc): waits for the server, creates the bucket, exits.
  # Use for ad-hoc ops too: docker compose run --rm minio-init ...
  minio-init:
    image: minio/mc:latest
    container_name: procurement-minio-init

    depends_on:
      minio:
        condition: service_started

    environment:
      MINIO_ENDPOINT: minio:9000
      MINIO_ROOT_USER: ${MINIO_ROOT_USER:-minioadmin}
      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-minioadmin}
      MINIO_BUCKET: procurement-files

    entrypoint: >
      /bin/sh -c "
      until mc alias set local http://$${MINIO_ENDPOINT} $${MINIO_ROOT_USER} $${MINIO_ROOT_PASSWORD}; do
        echo 'waiting for minio server...'; sleep 2;
      done;
      mc mb --ignore-existing local/$${MINIO_BUCKET};
      echo bucket $${MINIO_BUCKET} ready;
      "

    restart: "no"

  # ==========================================================================
  # Scheduled logical backups of BOTH databases (procurement + casdoor).
  # Writes pg_dump -Fc archives to a bind mount (default ./backups, point
  # BACKUP_DIR at /srv/erp/backups on the VPS) and prunes archives older
  # than BACKUP_KEEP_DAYS. Runs on the same postgres:18 image already pulled.
  # ==========================================================================
  db-backup:
    image: postgres:18
    container_name: procurement-db-backup
    depends_on:
      postgres:
        condition: service_healthy
    environment:
      PGPASSWORD: ${POSTGRES_PASSWORD:-postgres}
      BACKUP_INTERVAL_SECONDS: ${BACKUP_INTERVAL_SECONDS:-86400}
      BACKUP_KEEP_DAYS: ${BACKUP_KEEP_DAYS:-14}
    volumes:
      - ${BACKUP_DIR:-./backups}:/backups
    entrypoint: >
      /bin/sh -c "
      echo 'db-backup: dumping every $${BACKUP_INTERVAL_SECONDS}s, keeping $${BACKUP_KEEP_DAYS} days';
      while true; do
        STAMP=$$(date +%Y%m%d-%H%M%S);
        pg_dump -h postgres -U postgres -d procurement -Fc -f /backups/procurement-$${STAMP}.dump &&
          echo \"db-backup: procurement -> /backups/procurement-$${STAMP}.dump\";
        pg_dump -h postgres -U postgres -d casdoor -Fc -f /backups/casdoor-$${STAMP}.dump &&
          echo \"db-backup: casdoor -> /backups/casdoor-$${STAMP}.dump\";
        find /backups -name '*.dump' -mtime +$${BACKUP_KEEP_DAYS} -delete;
        sleep $${BACKUP_INTERVAL_SECONDS};
      done
      "
    restart: unless-stopped
    mem_limit: 256m

  # ==========================================================================
  # v2.6 — Casdoor (OIDC identity provider)
  # Console: http://localhost:8080 (admin / 123)
  # Application "inventory-app" (org "inventory", client inventory-app-client)
  # is created by backend/tools/seed_casdoor.py — run it once after the
  # first boot:
  #   docker compose run --rm -e CASDOOR_BASE=http://casdoor:8000 api python tools/seed_casdoor.py
  #
  # Casdoor uses the SAME postgres instance as the app (database `casdoor`,
  # created by sql/02-casdoor-db.sql on a fresh volume).
  # ==========================================================================
  casdoor:
    image: casbin/casdoor:latest
    container_name: procurement-casdoor
    depends_on:
      postgres:
        condition: service_healthy
    environment:
      RUNNING_IN_DOCKER: "true"
      driverName: postgres
      dataSourceName: "user=casdoor password=casdoor host=postgres port=5432 sslmode=disable dbname=casdoor"
      dbName: casdoor
      origin: "http://localhost:8080"
    ports:
      - "8080:8000"

    labels:
      - traefik.enable=true
      - traefik.http.routers.casdoor.rule=Host(`${AUTH_HOST:-auth.localhost}`)
      - traefik.http.routers.casdoor.entrypoints=web
      - traefik.http.services.casdoor.loadbalancer.server.port=8000

    networks:
      - traefik_network
      - default

    restart: unless-stopped
    mem_limit: 768m

  api:
    image: v15-api:latest
    build:
      context: ./backend
      dockerfile: Dockerfile
    container_name: procurement-api

    environment:
      PROCUREMENT_DATABASE_URL: postgresql+asyncpg://postgres:${POSTGRES_PASSWORD:-postgres}@postgres:5432/procurement
      PROCUREMENT_MINIO_ENDPOINT: minio:9000
      PROCUREMENT_MINIO_ACCESS_KEY: ${MINIO_ROOT_USER:-minioadmin}
      PROCUREMENT_MINIO_SECRET_KEY: ${MINIO_ROOT_PASSWORD:-minioadmin}
      PROCUREMENT_MINIO_BUCKET: procurement-files
      PROCUREMENT_MINIO_SECURE: "false"
      # "dev" enables the local defaults; "prod" turns on the fail-fast
      # startup checks (no wildcard CORS, no default credentials).
      PROCUREMENT_ENVIRONMENT: ${ENVIRONMENT:-dev}
      PROCUREMENT_DEV_LOGIN_ENABLED: ${DEV_LOGIN_ENABLED:-false}
      # Comma-separated browser origins (JSON-free .env friendly).
      PROCUREMENT_CORS_ORIGINS: ${CORS_ORIGINS:-http://localhost,http://localhost:3000,http://localhost:5173}
      # Casdoor: endpoint is the in-network service URL; the issuer must match
      # the origin Casdoor advertises to browsers (its OIDC discovery doc).
      PROCUREMENT_CASDOOR_ENDPOINT: http://casdoor:8000
      PROCUREMENT_CASDOOR_ISSUER: ${CASDOOR_ISSUER:-http://localhost:8080}
      PROCUREMENT_CASDOOR_CLIENT_ID: inventory-app-client
      PROCUREMENT_CASDOOR_CLIENT_SECRET: ${CASDOOR_CLIENT_SECRET:-inventory-app-secret-2026}
      PROCUREMENT_CASDOOR_ORGANIZATION: inventory
      PROCUREMENT_CASDOOR_APP_NAME: inventory-app
      PROCUREMENT_CASDOOR_AUDIENCE: inventory-app-client
      # Console admin used by POST /users/sync (identity mirroring).
      PROCUREMENT_CASDOOR_ADMIN_USER: admin
      PROCUREMENT_CASDOOR_ADMIN_PASSWORD: ${CASDOOR_ADMIN_PASSWORD:-123}
      # Observability (Phase 2) — see monitoring/README.md
      PROCUREMENT_LOG_FORMAT: ${LOG_FORMAT:-text}
      PROCUREMENT_SENTRY_DSN: ${SENTRY_DSN_BACKEND:-}
      PROCUREMENT_OPENPANEL_API_URL: ${OPENPANEL_API_URL:-}
      PROCUREMENT_OPENPANEL_CLIENT_ID: ${OPENPANEL_CLIENT_ID:-}
      PROCUREMENT_OPENPANEL_CLIENT_SECRET: ${OPENPANEL_CLIENT_SECRET:-}

    ports:
      - "8000:8000"

    volumes:
      - ./backend/app:/srv/backend/app

    networks:
      - traefik_network
      - default
      - shared # monitoring stack scrapes api:8000/metrics

    healthcheck:
      test: ["CMD-SHELL", "python -c \"import urllib.request as u; u.urlopen('http://127.0.0.1:8000/health', timeout=3)\""]
      interval: 30s
      timeout: 5s
      retries: 5
      start_period: 40s

    labels:
      - traefik.enable=true
      - traefik.http.routers.api.rule=Host(`${API_HOST:-api.localhost}`)
      - traefik.http.routers.api.entrypoints=web
      - traefik.http.services.api.loadbalancer.server.port=8000

    depends_on:
      postgres:
        condition: service_healthy
      minio-init:
        condition: service_completed_successfully

    restart: unless-stopped
    mem_limit: 768m

  frontend:
    image: v15-frontend:latest
    build:
      context: ./frontend
      args:
        # Developer Mode panel on the login page — dev-only aid. Production
        # builds MUST leave this false (identity comes from Casdoor tokens).
        DEV_LOGIN_ENABLED: ${DEV_LOGIN_ENABLED:-false}
        # Registry overridable for networks where npmmirror is unreachable.
        NPM_REGISTRY: ${NPM_REGISTRY:-https://registry.npmmirror.com}
        # Observability (build-time baked; empty = disabled)
        VITE_OPENPANEL_URL: ${OPENPANEL_PUBLIC_URL:-}
        VITE_OPENPANEL_CLIENT_ID: ${OPENPANEL_CLIENT_ID:-}
        VITE_SENTRY_DSN: ${SENTRY_DSN_FRONTEND:-}
    container_name: procurement-frontend
    # از entrypoint پیش‌فرض image nginx رد می‌شویم: آن اسکریپت `apk manifest`
    # اجرا می‌کند و اگر دسترسی به مخزن بسته‌ها نباشد بی‌نهایت معلق می‌ماند
    # (سرویس بالا نمی‌آید و traefik خطای 502 می‌دهد). کانفیگ ما مستقل است و
    # نیازی به آن اسکریپت‌ها ندارد.
    entrypoint: ["nginx", "-g", "daemon off;"]

    labels:
      - traefik.enable=true
      - traefik.http.routers.frontend.rule=Host(`${APP_HOST:-localhost}`)
      - traefik.http.routers.frontend.entrypoints=web
      - traefik.http.services.frontend.loadbalancer.server.port=80

    networks:
      - traefik_network
      - default

    depends_on:
      - api

    restart: unless-stopped
    mem_limit: 128m

  bot:
    image: v15-bot:latest
    build:
      context: ./bot
      dockerfile: Dockerfile
    container_name: procurement-bot

    volumes:
      - ./bot/app:/srv/bot/app

    environment:
      PROCUREMENT_BOT_BOT_TOKEN: ${BALE_BOT_TOKEN:-1354444845:yhVMnKZBFuKaU3UW5fP1bHmknEHx99mipWw}
      PROCUREMENT_BOT_BALE_API_BASE: ${BALE_API_BASE:-https://tapi.bale.ai}
      PROCUREMENT_BOT_API_BASE_URL: http://api:8000/api/v1
      PROCUREMENT_BOT_DATABASE_URL: postgresql+asyncpg://postgres:${POSTGRES_PASSWORD:-postgres}@postgres:5432/procurement
      PROCUREMENT_BOT_AI_BASE_URL: ${AI_BASE_URL:-https://api.deepseek.com}
      PROCUREMENT_BOT_AI_API_KEY: ${AI_API_KEY:-sk-a671eab15be846d494bf0839070a3b32}
      PROCUREMENT_BOT_LLM_MODEL: ${AI_LLM_MODEL:-deepseek-flash}
      PROCUREMENT_BOT_ADMIN_CHAT_IDS: ${BALE_ADMIN_CHAT_IDS:-1461166742,1839839922}
      PROCUREMENT_BOT_SERVICE_TOKEN: ${BALE_SERVICE_TOKEN:-}
      PROCUREMENT_BOT_FRONTEND_URL: ${APP_HOST:-http://localhost}

    depends_on:
      postgres:
        condition: service_healthy
      api:
        condition: service_started

    networks:
      - default

    restart: unless-stopped
    mem_limit: 512m

networks:
  # شبکه‌ی عمومی: فقط ترافیک و سرویس‌های عمومی. postgres روی شبکه‌ی
  # پیش‌فرض می‌ماند و از بیرون قابل دسترسی نیست.
  traefik_network:
    name: traefik_network
    driver: bridge
  # Fixed-name network shared with the monitoring stack (monitoring compose
  # joins it as external) — carries /metrics scrapes and postgres-exporter.
  shared:
    name: erp_shared
    driver: bridge

volumes:
  postgres_data:
  minio_data:
  traefik_certs: