fix: delete agent 500 error + dynamic personality + deployment guide

- Fix delete agent 500: clean up FK records (agent_llm_logs, permissions,
  schedules, executions, team_members) and unbind goals/tasks before delete
- Remove hardcoded personality templates in Android, replace with dynamic
  system prompt generation from name + description
- Set promptSectionsEnabled=false to bypass PromptComposer for personality
- Add Tencent Cloud Linux deployment guide (Docker Compose)
- Accumulated backend service updates, frontend UI fixes, Android app changes

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

docker-compose.staging.yml

@@ -0,0 +1,246 @@
+version: "3.8"
+
+# 天工智能体平台 — 预发布环境 (Staging)
+# 启动: docker compose -f docker-compose.staging.yml up -d
+# 与 prod 结构一致，但使用限流资源、简单密码，用于上线前验证
+
+services:
+  mysql:
+    image: mysql:8.0
+    container_name: aiagent-staging-mysql
+    restart: always
+    environment:
+      MYSQL_ROOT_PASSWORD: ${MYSQL_ROOT_PASSWORD:-staging-db-pass}
+      MYSQL_DATABASE: agent_db_staging
+      MYSQL_CHARSET: utf8mb4
+      MYSQL_COLLATION: utf8mb4_unicode_ci
+    ports:
+      - "3307:3306"
+    volumes:
+      - staging_mysql_data:/var/lib/mysql
+      - ./backend/init.sql:/docker-entrypoint-initdb.d/init.sql:ro
+    healthcheck:
+      test: ["CMD", "mysqladmin", "ping", "-h", "localhost"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+      start_period: 30s
+    networks:
+      - staging-net
+
+  redis:
+    image: redis:7-alpine
+    container_name: aiagent-staging-redis
+    restart: always
+    command: redis-server --appendonly yes --maxmemory 256mb --maxmemory-policy allkeys-lru
+    ports:
+      - "6380:6379"
+    volumes:
+      - staging_redis_data:/data
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 10s
+      timeout: 3s
+      retries: 5
+    networks:
+      - staging-net
+
+  backend:
+    build:
+      context: ./backend
+      dockerfile: Dockerfile
+    container_name: aiagent-staging-backend
+    restart: always
+    environment:
+      - ENVIRONMENT=staging
+      - DEBUG=False
+      - DATABASE_URL=mysql+pymysql://root:${MYSQL_ROOT_PASSWORD:-staging-db-pass}@mysql:3306/agent_db_staging?charset=utf8mb4
+      - REDIS_URL=redis://redis:6379/0
+      - JWT_SECRET_KEY=${JWT_SECRET_KEY:-staging-jwt-key}
+      - SECRET_KEY=${SECRET_KEY:-staging-secret-key}
+      - CORS_ORIGINS=${CORS_ORIGINS:-http://localhost:8038,http://localhost:3000}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+      - DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY:-}
+      - EXTERNAL_URL=${EXTERNAL_URL:-http://localhost}
+      - WORKFLOW_MAX_STEPS_PER_RUN=500
+    ports:
+      - "8039:8037"
+    depends_on:
+      mysql:
+        condition: service_healthy
+      redis:
+        condition: service_healthy
+    volumes:
+      - staging_agent_workspaces:/app/agent_workspaces
+      - staging_uploads:/app/uploads
+      - staging_logs:/app/logs
+    networks:
+      - staging-net
+
+  celery-worker:
+    build:
+      context: ./backend
+      dockerfile: Dockerfile
+    container_name: aiagent-staging-celery-worker
+    restart: always
+    command: celery -A app.core.celery_app worker --loglevel=info --concurrency=2
+    environment:
+      - ENVIRONMENT=staging
+      - DATABASE_URL=mysql+pymysql://root:${MYSQL_ROOT_PASSWORD:-staging-db-pass}@mysql:3306/agent_db_staging?charset=utf8mb4
+      - REDIS_URL=redis://redis:6379/0
+      - JWT_SECRET_KEY=${JWT_SECRET_KEY:-staging-jwt-key}
+      - SECRET_KEY=${SECRET_KEY:-staging-secret-key}
+      - OPENAI_API_KEY=${OPENAI_API_KEY:-}
+      - DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY:-}
+    depends_on:
+      mysql:
+        condition: service_healthy
+      redis:
+        condition: service_healthy
+    volumes:
+      - staging_agent_workspaces:/app/agent_workspaces
+      - staging_uploads:/app/uploads
+      - staging_logs:/app/logs
+    networks:
+      - staging-net
+
+  celery-beat:
+    build:
+      context: ./backend
+      dockerfile: Dockerfile
+    container_name: aiagent-staging-celery-beat
+    restart: always
+    command: celery -A app.core.celery_app beat --loglevel=info
+    environment:
+      - ENVIRONMENT=staging
+      - DATABASE_URL=mysql+pymysql://root:${MYSQL_ROOT_PASSWORD:-staging-db-pass}@mysql:3306/agent_db_staging?charset=utf8mb4
+      - REDIS_URL=redis://redis:6379/0
+      - JWT_SECRET_KEY=${JWT_SECRET_KEY:-staging-jwt-key}
+      - SECRET_KEY=${SECRET_KEY:-staging-secret-key}
+    depends_on:
+      mysql:
+        condition: service_healthy
+      redis:
+        condition: service_healthy
+    networks:
+      - staging-net
+
+  frontend:
+    build:
+      context: ./frontend
+      dockerfile: Dockerfile
+    container_name: aiagent-staging-frontend
+    restart: always
+    ports:
+      - "8040:80"
+    depends_on:
+      - backend
+    networks:
+      - staging-net
+
+  prometheus:
+    image: prom/prometheus:v2.53.0
+    container_name: aiagent-staging-prometheus
+    restart: always
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--storage.tsdb.retention.time=30d'
+      - '--web.enable-lifecycle'
+    ports:
+      - "9091:9090"
+    volumes:
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - ./prometheus-alert-rules.yml:/etc/prometheus/alert_rules.yml:ro
+      - staging_prometheus_data:/prometheus
+    networks:
+      - staging-net
+
+  grafana:
+    image: grafana/grafana:11.0.0
+    container_name: aiagent-staging-grafana
+    restart: always
+    environment:
+      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
+      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin123}
+      - GF_USERS_ALLOW_SIGN_UP=false
+    ports:
+      - "3001:3000"
+    volumes:
+      - ./grafana/datasources:/etc/grafana/provisioning/datasources:ro
+      - ./grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
+      - ./grafana/dashboards/tiangong-overview.json:/var/lib/grafana/dashboards/tiangong-overview.json:ro
+      - staging_grafana_data:/var/lib/grafana
+    depends_on:
+      - prometheus
+    networks:
+      - staging-net
+
+  # ─── ELK 日志聚合 ─────────────────────────────────────────────────
+  elasticsearch:
+    image: docker.elastic.co/elasticsearch/elasticsearch:8.15.0
+    container_name: aiagent-staging-elasticsearch
+    restart: always
+    environment:
+      - discovery.type=single-node
+      - ES_JAVA_OPTS=-Xms256m -Xmx512m
+      - xpack.security.enabled=false
+    ports:
+      - "9201:9200"
+    volumes:
+      - staging_es_data:/usr/share/elasticsearch/data
+    healthcheck:
+      test: ["CMD-SHELL", "curl -s http://localhost:9200/_cluster/health | grep -q 'green\|yellow'"]
+      interval: 15s
+      timeout: 10s
+      retries: 10
+    networks:
+      - staging-net
+
+  kibana:
+    image: docker.elastic.co/kibana/kibana:8.15.0
+    container_name: aiagent-staging-kibana
+    restart: always
+    environment:
+      - ELASTICSEARCH_HOSTS=http://elasticsearch:9200
+    ports:
+      - "5602:5601"
+    depends_on:
+      elasticsearch:
+        condition: service_healthy
+    networks:
+      - staging-net
+
+  filebeat:
+    image: docker.elastic.co/beats/filebeat:8.15.0
+    container_name: aiagent-staging-filebeat
+    restart: always
+    volumes:
+      - ./filebeat/filebeat.yml:/usr/share/filebeat/filebeat.yml:ro
+      - staging_logs:/app/logs:ro
+    depends_on:
+      - elasticsearch
+    networks:
+      - staging-net
+
+volumes:
+  staging_mysql_data:
+    driver: local
+  staging_redis_data:
+    driver: local
+  staging_agent_workspaces:
+    driver: local
+  staging_uploads:
+    driver: local
+  staging_logs:
+    driver: local
+  staging_prometheus_data:
+    driver: local
+  staging_grafana_data:
+    driver: local
+  staging_es_data:
+    driver: local
+
+networks:
+  staging-net:
+    driver: bridge