feat(engine): 添加MCP连接管理和工具集成功能

- 集成MCP连接管理器，支持MCP服务器连接
- 添加多种内置工具：ClarifyTool、CronTool、DelegateTool、ExecuteCodeTool、
  PatchFileTool、ProcessTool、SendMessageTool、SpawnTool、TerminalTool、
  TodoTool、WebFetchTool、WebSearchTool、WriteFileTool等
- 实现工具注册和装配功能
- 添加技能选择上下文参数
- 支持思考模式控制参数thinking_enabled

feat(coordinator): 重构任务执行计划器参数命名

- 将learning_candidate_enabled重命名为allow_candidate_generation
- 更新TeamGraphScheduler中的参数传递
- 修改LocalAgentRunner中的相关参数处理
- 更新README文档中的相应描述

refactor(context): 标准化工具调用参数格式

- 添加_json导入用于参数序列化
- 实现_provider_tool_calls方法标准化OpenAI兼容的工具调用载荷
- 修复工具调用中参数非字符串类型的序列化问题

refactor(session): 优化消息历史记录过滤逻辑

- 修改get_messages_as_conversation为基于运行状态过滤消息
- 排除未完成、失败或错误结束的运行记录
- 改进对话历史的可见性控制机制

fix(store): 修复FTS索引重建逻辑

- 添加异常处理防止FTS索引创建失败
- 实现_rebuild_fts_index方法重新构建全文搜索索引
- 优化索引触发器和表的维护流程

app-instance/backend/tests/unit/test_litellm_thinking_mode.py

@@ -0,0 +1,145 @@
+from __future__ import annotations
+
+import asyncio
+import pytest
+from types import SimpleNamespace
+
+from beaver.engine.providers.litellm import LiteLLMProvider
+
+
+def test_qwen_thinking_mode_is_sent_as_chat_template_kwargs(monkeypatch: pytest.MonkeyPatch) -> None:
+    captured: dict = {}
+
+    class Message:
+        content = "可以"
+        reasoning_content = ""
+        tool_calls = []
+
+    class Choice:
+        message = Message()
+        finish_reason = "stop"
+
+    class Response:
+        choices = [Choice()]
+        usage = None
+
+    async def fake_acompletion(**kwargs):
+        captured.update(kwargs)
+        return Response()
+
+    monkeypatch.setattr("beaver.engine.providers.litellm.acompletion", fake_acompletion)
+    monkeypatch.setattr("beaver.engine.providers.litellm.litellm", SimpleNamespace())
+
+    provider = LiteLLMProvider(
+        api_key="sk-test",
+        api_base="https://oai.example.com/v1",
+        default_model="Qwen3.6-35B",
+        provider_name="openai",
+    )
+    response = asyncio.run(
+        provider.chat(
+            [{"role": "user", "content": "只回复可以"}],
+            model="Qwen3.6-35B",
+            thinking_enabled=False,
+        )
+    )
+
+    assert response.content == "可以"
+    assert captured["extra_body"] == {"chat_template_kwargs": {"enable_thinking": False}}
+
+
+def test_non_qwen_thinking_mode_is_not_sent(monkeypatch: pytest.MonkeyPatch) -> None:
+    captured: dict = {}
+
+    class Message:
+        content = "ok"
+        reasoning_content = None
+        tool_calls = []
+
+    class Choice:
+        message = Message()
+        finish_reason = "stop"
+
+    class Response:
+        choices = [Choice()]
+        usage = None
+
+    async def fake_acompletion(**kwargs):
+        captured.update(kwargs)
+        return Response()
+
+    monkeypatch.setattr("beaver.engine.providers.litellm.acompletion", fake_acompletion)
+    monkeypatch.setattr("beaver.engine.providers.litellm.litellm", SimpleNamespace())
+
+    provider = LiteLLMProvider(
+        api_key="sk-test",
+        api_base="https://oai.example.com/v1",
+        default_model="gpt-4.1-mini",
+        provider_name="openai",
+    )
+    asyncio.run(
+        provider.chat(
+            [{"role": "user", "content": "reply ok"}],
+            model="gpt-4.1-mini",
+            thinking_enabled=False,
+        )
+    )
+
+    assert "extra_body" not in captured
+
+
+def test_litellm_provider_sanitizes_tool_call_arguments(monkeypatch: pytest.MonkeyPatch) -> None:
+    captured: dict = {}
+
+    class Message:
+        content = "ok"
+        reasoning_content = None
+        tool_calls = []
+
+    class Choice:
+        message = Message()
+        finish_reason = "stop"
+
+    class Response:
+        choices = [Choice()]
+        usage = None
+
+    async def fake_acompletion(**kwargs):
+        captured.update(kwargs)
+        return Response()
+
+    monkeypatch.setattr("beaver.engine.providers.litellm.acompletion", fake_acompletion)
+    monkeypatch.setattr("beaver.engine.providers.litellm.litellm", SimpleNamespace())
+
+    provider = LiteLLMProvider(
+        api_key="sk-test",
+        api_base="https://oai.example.com/v1",
+        default_model="Qwen3.6-35B",
+        provider_name="openai",
+    )
+    asyncio.run(
+        provider.chat(
+            [
+                {
+                    "role": "assistant",
+                    "content": None,
+                    "tool_calls": [
+                        {
+                            "id": "call-1",
+                            "type": "function",
+                            "function": {
+                                "name": "cron",
+                                "arguments": {"action": "add", "mode": "notification"},
+                            },
+                        }
+                    ],
+                },
+                {"role": "tool", "tool_call_id": "call-1", "name": "cron", "content": "done"},
+            ],
+            model="Qwen3.6-35B",
+            thinking_enabled=False,
+        )
+    )
+
+    tool_call = captured["messages"][0]["tool_calls"][0]
+    assert tool_call["function"]["arguments"] == '{"action": "add", "mode": "notification"}'