goodgo-platform/docker-compose.prod.yml

services:
  # ── Application Services ──────────────────────────────────────────────────────
  api:
    build:
      context: .
      dockerfile: apps/api/Dockerfile
      target: production
    image: ${REGISTRY_URL:-ghcr.io/goodgo}/goodgo-api:${IMAGE_TAG:-latest}
    container_name: goodgo-api
    restart: unless-stopped
    ports:
      - '127.0.0.1:${API_PORT:-3001}:3001'
    environment:
      NODE_ENV: production
      DATABASE_URL: postgresql://${DB_USER}:${DB_PASSWORD}@pgbouncer:6432/${DB_NAME}
      # Direct connection for migrations (bypasses PgBouncer — required for DDL)
      DATABASE_URL_DIRECT: postgresql://${DB_USER}:${DB_PASSWORD}@postgres:5432/${DB_NAME}
      REDIS_URL: redis://:${REDIS_PASSWORD}@redis:6379
      TYPESENSE_HOST: typesense
      TYPESENSE_PORT: 8108
      TYPESENSE_API_KEY: ${TYPESENSE_API_KEY}
      JWT_SECRET: ${JWT_SECRET}
      JWT_REFRESH_SECRET: ${JWT_REFRESH_SECRET}
      MINIO_ENDPOINT: minio
      MINIO_PORT: 9000
      MINIO_ACCESS_KEY: ${MINIO_ACCESS_KEY}
      MINIO_SECRET_KEY: ${MINIO_SECRET_KEY}
      AI_SERVICES_URL: http://ai-services:8000
      AI_SERVICES_API_KEY: ${AI_API_KEY}
      RUN_MIGRATIONS: ${RUN_MIGRATIONS:-false}
    depends_on:
      pgbouncer:
        condition: service_healthy
      redis:
        condition: service_healthy
      typesense:
        condition: service_healthy
    healthcheck:
      test: ['CMD', 'node', '-e', "fetch('http://localhost:3001/health').then(r => { if (!r.ok) throw 1 }).catch(() => process.exit(1))"]
      interval: 30s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          memory: 1g
          cpus: '1.0'
        reservations:
          memory: 512m
    security_opt:
      - no-new-privileges:true
    read_only: true
    tmpfs:
      - /tmp
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '5'
    networks:
      - goodgo-net

  web:
    image: ${REGISTRY_URL:-ghcr.io/goodgo}/goodgo-web:${IMAGE_TAG:-latest}
    container_name: goodgo-web
    restart: unless-stopped
    ports:
      - '127.0.0.1:${WEB_PORT:-3000}:3000'
    environment:
      NODE_ENV: production
      NEXT_PUBLIC_API_URL: ${NEXT_PUBLIC_API_URL:-http://api:3001}
    depends_on:
      api:
        condition: service_healthy
    healthcheck:
      test: ['CMD', 'node', '-e', "fetch('http://localhost:3000').then(r => { if (!r.ok) throw 1 }).catch(() => process.exit(1))"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 15s
    deploy:
      resources:
        limits:
          memory: 512m
          cpus: '0.5'
        reservations:
          memory: 256m
    security_opt:
      - no-new-privileges:true
    read_only: true
    tmpfs:
      - /tmp
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '5'
    networks:
      - goodgo-net

  ai-services:
    image: ${REGISTRY_URL:-ghcr.io/goodgo}/goodgo-ai-services:${IMAGE_TAG:-latest}
    container_name: goodgo-ai-services
    restart: unless-stopped
    environment:
      AI_DEBUG: 'false'
      AI_LOG_LEVEL: info
      AI_API_KEY: ${AI_API_KEY}
      AI_RATE_LIMIT: ${AI_RATE_LIMIT:-60/minute}
    healthcheck:
      test: ['CMD', 'python', '-c', 'import httpx; httpx.get("http://localhost:8000/health").raise_for_status()']
      interval: 30s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          memory: 1g
          cpus: '1.0'
        reservations:
          memory: 512m
    security_opt:
      - no-new-privileges:true
    read_only: true
    tmpfs:
      - /tmp
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '5'
    networks:
      - goodgo-net

  # ── Data Services ─────────────────────────────────────────────────────────────
  postgres:
    image: postgis/postgis:16-3.4
    container_name: goodgo-postgres
    restart: unless-stopped
    environment:
      POSTGRES_DB: ${DB_NAME}
      POSTGRES_USER: ${DB_USER}
      POSTGRES_PASSWORD: ${DB_PASSWORD}
    volumes:
      - pgdata:/var/lib/postgresql/data
    healthcheck:
      test: ['CMD-SHELL', 'pg_isready -U ${DB_USER} -d ${DB_NAME}']
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          memory: 2g
          cpus: '2.0'
        reservations:
          memory: 1g
    shm_size: 256m
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '5'
    networks:
      - goodgo-net

  # ── Connection Pooling ─────────────────────────────────────────────────────
  pgbouncer:
    image: edoburu/pgbouncer:1.23.1-p2
    container_name: goodgo-pgbouncer
    restart: unless-stopped
    entrypoint: ['/bin/sh', '/etc/pgbouncer/entrypoint.sh']
    environment:
      DB_USER: ${DB_USER}
      DB_PASSWORD: ${DB_PASSWORD}
      PGBOUNCER_POOL_SIZE: ${PGBOUNCER_POOL_SIZE:-20}
      PGBOUNCER_MAX_CLIENT_CONN: ${PGBOUNCER_MAX_CLIENT_CONN:-200}
      PGBOUNCER_ADMIN_PASSWORD: ${PGBOUNCER_ADMIN_PASSWORD:-pgbouncer_admin_secret}
      PGBOUNCER_STATS_PASSWORD: ${PGBOUNCER_STATS_PASSWORD:-pgbouncer_stats_secret}
    volumes:
      - ./infra/pgbouncer/pgbouncer.ini:/etc/pgbouncer/pgbouncer.ini:ro
      - ./infra/pgbouncer/userlist.txt.template:/etc/pgbouncer/userlist.txt.template:ro
      - ./infra/pgbouncer/entrypoint.sh:/etc/pgbouncer/entrypoint.sh:ro
    depends_on:
      postgres:
        condition: service_healthy
    healthcheck:
      test: ['CMD-SHELL', 'pg_isready -h 127.0.0.1 -p 6432 -U ${DB_USER}']
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s
    deploy:
      resources:
        limits:
          memory: 256m
          cpus: '0.5'
        reservations:
          memory: 64m
    security_opt:
      - no-new-privileges:true
    logging:
      driver: json-file
      options:
        max-size: '5m'
        max-file: '3'
    networks:
      - goodgo-net

  redis:
    image: redis:7-alpine
    container_name: goodgo-redis
    restart: unless-stopped
    command: redis-server --appendonly yes --requirepass ${REDIS_PASSWORD} --maxmemory 512mb --maxmemory-policy allkeys-lru
    volumes:
      - redis_data:/data
    healthcheck:
      test: ['CMD', 'redis-cli', '-a', '${REDIS_PASSWORD}', 'ping']
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s
    deploy:
      resources:
        limits:
          memory: 768m
          cpus: '0.5'
        reservations:
          memory: 256m
    security_opt:
      - no-new-privileges:true
    read_only: true
    tmpfs:
      - /tmp
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '3'
    networks:
      - goodgo-net

  typesense:
    image: typesense/typesense:27.1
    container_name: goodgo-typesense
    restart: unless-stopped
    environment:
      TYPESENSE_API_KEY: ${TYPESENSE_API_KEY}
      TYPESENSE_DATA_DIR: /data
    volumes:
      - typesense_data:/data
    healthcheck:
      test: ['CMD', 'curl', '-sf', 'http://localhost:8108/health']
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s
    deploy:
      resources:
        limits:
          memory: 1g
          cpus: '1.0'
        reservations:
          memory: 512m
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '3'
    networks:
      - goodgo-net

  minio:
    image: minio/minio:latest
    container_name: goodgo-minio
    restart: unless-stopped
    command: server /data --console-address ":9001"
    environment:
      MINIO_ROOT_USER: ${MINIO_ACCESS_KEY}
      MINIO_ROOT_PASSWORD: ${MINIO_SECRET_KEY}
    volumes:
      - minio_data:/data
    healthcheck:
      test: ['CMD', 'curl', '-sf', 'http://localhost:9000/minio/health/live']
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s
    deploy:
      resources:
        limits:
          memory: 1g
          cpus: '0.5'
        reservations:
          memory: 256m
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '3'
    networks:
      - goodgo-net

  # ── Database Backup ───────────────────────────────────────────────────────────
  pg-backup:
    image: postgis/postgis:16-3.4
    container_name: goodgo-pg-backup
    restart: unless-stopped
    entrypoint: /bin/bash
    command:
      - -c
      - |
        apt-get update -qq && apt-get install -y -qq cron > /dev/null 2>&1
        (echo "0 2 * * * PGHOST=postgres PGPORT=5432 PGUSER=${DB_USER} PGDATABASE=${DB_NAME} PGPASSWORD=${DB_PASSWORD} BACKUP_DIR=/backups RETENTION_DAYS=${BACKUP_RETENTION_DAYS:-7} /scripts/pg-backup.sh >> /var/log/pg-backup.log 2>&1"
         echo "0 4 * * * PGHOST=postgres PGPORT=5432 PGUSER=${DB_USER} PGDATABASE=${DB_NAME} PGPASSWORD=${DB_PASSWORD} BACKUP_DIR=/backups REPORT_FILE=/backups/verify-latest.json /scripts/pg-verify-backup.sh >> /var/log/pg-verify.log 2>&1") | crontab -
        /scripts/pg-backup.sh
        cron -f
    environment:
      PGHOST: postgres
      PGPORT: '5432'
      PGUSER: ${DB_USER}
      PGDATABASE: ${DB_NAME}
      PGPASSWORD: ${DB_PASSWORD}
      BACKUP_DIR: /backups
      RETENTION_DAYS: ${BACKUP_RETENTION_DAYS:-7}
    volumes:
      - ./scripts/backup:/scripts:ro
      - pg_backups:/backups
    depends_on:
      postgres:
        condition: service_healthy
    deploy:
      resources:
        limits:
          memory: 512m
          cpus: '0.5'
    logging:
      driver: json-file
      options:
        max-size: '5m'
        max-file: '3'
    networks:
      - goodgo-net

  # ── Monitoring & Logging ──────────────────────────────────────────────────────
  loki:
    image: grafana/loki:3.0.0
    container_name: goodgo-loki
    restart: unless-stopped
    command: -config.file=/etc/loki/loki-config.yml
    volumes:
      - ./monitoring/loki/loki-config.yml:/etc/loki/loki-config.yml:ro
      - loki_data:/loki
    healthcheck:
      test: ['CMD', 'wget', '--spider', '-q', 'http://localhost:3100/ready']
      interval: 15s
      timeout: 5s
      retries: 5
      start_period: 20s
    deploy:
      resources:
        limits:
          memory: 512m
          cpus: '0.5'
        reservations:
          memory: 256m
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '3'
    networks:
      - goodgo-net

  promtail:
    image: grafana/promtail:3.0.0
    container_name: goodgo-promtail
    restart: unless-stopped
    command: -config.file=/etc/promtail/promtail-config.yml
    volumes:
      - ./monitoring/promtail/promtail-config.yml:/etc/promtail/promtail-config.yml:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
    depends_on:
      loki:
        condition: service_healthy
    deploy:
      resources:
        limits:
          memory: 256m
          cpus: '0.25'
        reservations:
          memory: 128m
    logging:
      driver: json-file
      options:
        max-size: '5m'
        max-file: '3'
    networks:
      - goodgo-net

  prometheus:
    image: prom/prometheus:v2.51.0
    container_name: goodgo-prometheus
    restart: unless-stopped
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.retention.time=30d'
      - '--web.enable-lifecycle'
    volumes:
      - ./monitoring/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./monitoring/prometheus/alert-rules.yml:/etc/prometheus/alert-rules.yml:ro
      - prometheus_data:/prometheus
    depends_on:
      alertmanager:
        condition: service_healthy
    healthcheck:
      test: ['CMD', 'wget', '--spider', '-q', 'http://localhost:9090/-/healthy']
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 10s
    deploy:
      resources:
        limits:
          memory: 1g
          cpus: '0.5'
        reservations:
          memory: 512m
    security_opt:
      - no-new-privileges:true
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '3'
    networks:
      - goodgo-net

  alertmanager:
    image: prom/alertmanager:v0.27.0
    container_name: goodgo-alertmanager
    restart: unless-stopped
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
      - '--data.retention=120h'
    environment:
      SLACK_WEBHOOK_URL: ${SLACK_WEBHOOK_URL:-}
    volumes:
      - ./monitoring/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
    healthcheck:
      test: ['CMD', 'wget', '--spider', '-q', 'http://localhost:9093/-/healthy']
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 10s
    deploy:
      resources:
        limits:
          memory: 256m
          cpus: '0.25'
        reservations:
          memory: 64m
    security_opt:
      - no-new-privileges:true
    logging:
      driver: json-file
      options:
        max-size: '5m'
        max-file: '3'
    networks:
      - goodgo-net

  grafana:
    image: grafana/grafana:10.4.1
    container_name: goodgo-grafana
    restart: unless-stopped
    ports:
      - '127.0.0.1:${GRAFANA_PORT:-3002}:3000'
    environment:
      GF_SECURITY_ADMIN_USER__FILE: /run/secrets/grafana_admin_user
      GF_SECURITY_ADMIN_PASSWORD__FILE: /run/secrets/grafana_admin_password
      GF_USERS_ALLOW_SIGN_UP: 'false'
      GF_SERVER_ROOT_URL: ${GRAFANA_ROOT_URL:-http://localhost:3002}
    secrets:
      - grafana_admin_user
      - grafana_admin_password
    volumes:
      - ./monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
      - ./monitoring/grafana/dashboards:/var/lib/grafana/dashboards:ro
      - grafana_data:/var/lib/grafana
    depends_on:
      prometheus:
        condition: service_healthy
      loki:
        condition: service_healthy
      alertmanager:
        condition: service_healthy
    healthcheck:
      test: ['CMD', 'wget', '--spider', '-q', 'http://localhost:3000/api/health']
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 15s
    deploy:
      resources:
        limits:
          memory: 512m
          cpus: '0.5'
        reservations:
          memory: 256m
    security_opt:
      - no-new-privileges:true
    logging:
      driver: json-file
      options:
        max-size: '10m'
        max-file: '3'
    networks:
      - goodgo-net

volumes:
  pgdata:
    driver: local
  redis_data:
    driver: local
  typesense_data:
    driver: local
  minio_data:
    driver: local
  pg_backups:
    driver: local
  loki_data:
    driver: local
  prometheus_data:
    driver: local
  grafana_data:
    driver: local

secrets:
  grafana_admin_user:
    environment: GRAFANA_ADMIN_USER
  grafana_admin_password:
    environment: GRAFANA_ADMIN_PASSWORD

networks:
  goodgo-net:
    driver: bridge
    name: goodgo-net