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>

test/test_prompt_sections.py

@@ -0,0 +1,82 @@
+# -*- coding: utf-8 -*-
+"""系统提示词分层装配 - 端到端测试"""
+import sys, os, io, json, requests
+
+sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8", errors="replace")
+
+BASE = "http://localhost:8038/api/v1"
+
+def login():
+    r = requests.post(f"{BASE}/auth/login", data={"username": "admin", "password": "123456"})
+    r.raise_for_status()
+    return r.json()["access_token"]
+
+def test_prompt_sections():
+    token = login()
+    headers = {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}
+    print("=== 系统提示词分层装配测试 ===\n")
+
+    # Test 1: Chat with prompt sections enabled (default)
+    print("1. 对话（分层装配 开启）…")
+    r1 = requests.post(f"{BASE}/agent-chat/bare", headers=headers,
+                       json={"message": "你好，请用简短回答介绍一下自己",
+                             "prompt_sections_enabled": True}, timeout=120)
+    r1.raise_for_status()
+    d1 = r1.json()
+    print(f"   会话 ID: {d1['session_id']}")
+    print(f"   回复: {d1['content'][:200]}…")
+    print(f"   迭代: {d1['iterations_used']}, 工具调用: {d1['tool_calls_made']}")
+    ok1 = d1["iterations_used"] >= 1
+    print(f"   {'✓ 通过' if ok1 else '✗ 失败'}\n")
+
+    # Test 2: Chat with prompt sections disabled
+    print("2. 对话（分层装配 关闭）…")
+    r2 = requests.post(f"{BASE}/agent-chat/bare", headers=headers,
+                       json={"message": "你好，请用简短回答介绍一下自己",
+                             "prompt_sections_enabled": False}, timeout=120)
+    r2.raise_for_status()
+    d2 = r2.json()
+    print(f"   会话 ID: {d2['session_id']}")
+    print(f"   回复: {d2['content'][:200]}…")
+    print(f"   迭代: {d2['iterations_used']}, 工具调用: {d2['tool_calls_made']}")
+    ok2 = d2["iterations_used"] >= 1
+    print(f"   {'✓ 通过' if ok2 else '✗ 失败'}\n")
+
+    # Test 3: Agent chat with prompt sections
+    print("3. Agent 对话（分层装配 开启）…")
+    # First find an agent
+    r_agents = requests.get(f"{BASE}/agents", headers=headers, params={"limit": 5}, timeout=10)
+    r_agents.raise_for_status()
+    agents_data = r_agents.json()
+    agents = agents_data if isinstance(agents_data, list) else agents_data.get("items", [])
+    if agents:
+        agent_id = agents[0]["id"]
+        r3 = requests.post(f"{BASE}/agent-chat/{agent_id}", headers=headers,
+                          json={"message": "你好", "prompt_sections_enabled": True}, timeout=120)
+        r3.raise_for_status()
+        d3 = r3.json()
+        print(f"   Agent: {agents[0].get('name', 'N/A')}")
+        print(f"   回复: {d3['content'][:200]}…")
+        ok3 = d3["iterations_used"] >= 1
+        print(f"   {'✓ 通过' if ok3 else '✗ 失败'}")
+    else:
+        print("   ⚠ 跳过（无可用 Agent）")
+        ok3 = True
+    print()
+
+    # Test 4: Verify system prompt composition via health endpoint
+    print("4. 验证分层装配模块加载…")
+    r4 = requests.get(f"http://localhost:8038/health", timeout=10)
+    r4.raise_for_status()
+    d4 = r4.json()
+    print(f"   状态: {d4['status']}")
+    print(f"   工具数: {d4.get('builtin_tools', {}).get('count', 'N/A')}")
+    ok4 = d4["status"] == "healthy"
+    print(f"   {'✓ 通过' if ok4 else '✗ 失败'}\n")
+
+    all_ok = ok1 and ok2 and ok3 and ok4
+    print(f"=== {'全部测试通过' if all_ok else '部分测试失败'} ===")
+    return all_ok
+
+if __name__ == "__main__":
+    test_prompt_sections()