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_swarm.py

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*-
+"""Agent 蜂群 - 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_swarm():
+    token = login()
+    headers = {"Authorization": f"Bearer {token}", "Content-Type": "application/json"}
+    print("=== Agent 蜂群测试 ===\n")
+
+    # Test 1: Simple swarm - leader decides no decomposition needed
+    print("1. 简单问题（Leader 自行处理）…")
+    r1 = requests.post(f"{BASE}/swarm/run", headers=headers,
+                       json={"message": "1+1等于几？", "max_teammates": 3}, timeout=120)
+    r1.raise_for_status()
+    d1 = r1.json()
+    print(f"   模式: {d1['mode']}")
+    print(f"   任务数: {len(d1['tasks'])}")
+    print(f"   回答: {d1['final_answer'][:200]}…")
+    ok1 = d1["success"] and len(d1["final_answer"]) > 0
+    print(f"   {'✓ 通过' if ok1 else '✗ 失败'}\n")
+
+    # Test 2: Complex problem that needs decomposition
+    print("2. 复杂问题（Leader 分解 + Teammates 并行）…")
+    r2 = requests.post(f"{BASE}/swarm/run", headers=headers,
+                       json={
+                           "message": "请帮我同时做三件事：1) 生成一个斐波那契数列前10项 2) 列出Python的5个主要特性 3) 解释什么是REST API",
+                           "max_teammates": 3,
+                           "mode": "parallel",
+                       }, timeout=300)
+    r2.raise_for_status()
+    d2 = r2.json()
+    print(f"   模式: {d2['mode']}")
+    print(f"   任务数: {len(d2['tasks'])}")
+    print(f"   Teammate结果数: {len(d2['teammate_results'])}")
+    for tr in d2['teammate_results']:
+        print(f"   - {tr['agent_name']}: {'✓' if tr['success'] else '✗'} ({tr['duration_ms']}ms)")
+    print(f"   总耗时: {d2['total_duration_ms']}ms")
+    print(f"   总工具调用: {d2['total_tool_calls']}")
+    print(f"   汇总回答: {d2['final_answer'][:300]}…")
+    ok2 = d2["success"]
+    print(f"   {'✓ 通过' if ok2 else '✗ 失败'}\n")
+
+    # Test 3: Swarm with specific agents as teammates
+    print("3. 指定 Agent 作为 Teammate…")
+    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 len(agents) >= 2:
+        agent_ids = [agents[0]["id"], agents[1]["id"]]
+        r3 = requests.post(f"{BASE}/swarm/run", headers=headers,
+                          json={
+                              "message": "请从两个角度分析Python的优势：技术角度和生态角度",
+                              "max_teammates": 2,
+                              "agent_ids": agent_ids,
+                              "mode": "parallel",
+                          }, timeout=300)
+        r3.raise_for_status()
+        d3 = r3.json()
+        print(f"   任务数: {len(d3['tasks'])}")
+        print(f"   Teammate结果数: {len(d3['teammate_results'])}")
+        for tr in d3['teammate_results']:
+            print(f"   - {tr['agent_name']}: {'✓' if tr['success'] else '✗'} ({tr['duration_ms']}ms)")
+        print(f"   汇总回答: {d3['final_answer'][:200]}…")
+        ok3 = d3["success"]
+    else:
+        print("   ⚠ 跳过（Agent 不足）")
+        ok3 = True
+    print(f"   {'✓ 通过' if ok3 else '✗ 失败'}\n")
+
+    # Test 4: Health check
+    print("4. 健康检查…")
+    r4 = requests.get(f"http://localhost:8038/health", timeout=10)
+    r4.raise_for_status()
+    d4 = r4.json()
+    print(f"   状态: {d4['status']}")
+    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_swarm()