feat: 添加MinIO文件系统支持并优化外部连接器功能

- 添加MinIO用户文件系统配置选项(BEAVER_MINIO_ROOT_USER等)
- 更新外部连接器配置结构，包括BASE_URL和认证令牌设置
- 改进connector provider支持更多类型(official, feishu_bot等)
- 实现Mistral模型推理模式支持reasoning_effort参数
- 增强外部连接器策略配置和运行时配置管理
- 添加connector bridge事件验证和安全保护机制
- 优化任务路由逻辑，区分simple_chat和new_task场景
- 更新初始技能工具提示配置，分离authoring admin功能

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

@@ -169,6 +169,90 @@ def test_thinking_mode_is_forced_disabled_even_when_requested_enabled(monkeypatc
     }
 
 
+def test_mistral_vllm_uses_reasoning_effort_instead_of_qwen_thinking_body(
+    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="EMPTY",
+        api_base="http://localhost:8000/v1",
+        default_model="mistralai/Mistral-Medium-3.5-128B",
+        provider_name="vllm",
+    )
+    asyncio.run(
+        provider.chat(
+            [{"role": "user", "content": "reply ok"}],
+            model="mistralai/Mistral-Medium-3.5-128B",
+            thinking_enabled=True,
+        )
+    )
+
+    assert captured["model"] == "hosted_vllm/mistralai/Mistral-Medium-3.5-128B"
+    assert captured["extra_body"] == {"reasoning_effort": "high"}
+
+
+def test_mistral_vllm_omits_reasoning_body_when_thinking_mode_is_unspecified(
+    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="EMPTY",
+        api_base="http://localhost:8000/v1",
+        default_model="mistralai/Mistral-Medium-3.5-128B",
+        provider_name="vllm",
+    )
+    asyncio.run(
+        provider.chat(
+            [{"role": "user", "content": "reply ok"}],
+            model="mistralai/Mistral-Medium-3.5-128B",
+        )
+    )
+
+    assert "extra_body" not in captured
+
+
 def test_litellm_provider_sanitizes_tool_call_arguments(monkeypatch: pytest.MonkeyPatch) -> None:
     captured: dict = {}