feat(litellm): 添加 reasoning_content 支持并强制禁用思考模式

- 在 LiteLLMProvider 中添加 "reasoning_content" 到允许的消息键集合中
- 修改 _apply_thinking_mode 方法以强制禁用思考模式，不再基于模型名称判断
- 总是设置 enable_thinking 为 False 并添加 thinking.type: disabled 配置
- 更新相关测试用例验证新的思考模式行为

fix(web): 修复非运行状态下的直接处理逻辑

- 创建 _run_web_direct 辅助函数来处理代理服务的直接提交/处理逻辑
- 当代理服务未运行时使用 process_direct 而不是 submit_direct
- 更新 REST 和 WebSocket 接口以使用新的处理逻辑
- 添加相应的单元测试验证非运行状态下使用直接处理

test(config): 添加代理配置重载功能的测试

- 添加 test_reload_agent_config_updates_booted_loop_config 测试函数
- 验证配置文件更新后代理循环能够正确加载新配置
- 测试模型、API 基础地址和 API 密钥的更新

chore(frontend): 默认禁用前端思考模式偏好

- 将前端思考模式存储的默认值从 true 改为 false
- 确保窗口未定义时返回 false 而不是 true
- 更新本地存储缺失时的默认行为为禁用思考模式

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

@@ -30,6 +30,15 @@ class StubAgentService(AgentService):
         self.fail = fail
         self.calls: list[dict[str, Any]] = []
 
+    async def process_direct(self, message: str, **kwargs: Any) -> StubRunResult:  # type: ignore[override]
+        self.calls.append({"message": message, **kwargs})
+        if self.fail:
+            raise RuntimeError("boom")
+        return StubRunResult(
+            session_id=kwargs.get("session_id") or "web:default",
+            output_text=f"echo:{message}",
+        )
+
     async def submit_direct(self, message: str, **kwargs: Any) -> StubRunResult:  # type: ignore[override]
         self.calls.append({"message": message, **kwargs})
         if self.fail:
@@ -40,6 +49,11 @@ class StubAgentService(AgentService):
         )
 
 
+class DirectModeOnlyAgentService(StubAgentService):
+    async def submit_direct(self, message: str, **kwargs: Any) -> StubRunResult:  # type: ignore[override]
+        raise RuntimeError("submit_direct should not be used when service is not running")
+
+
 def test_websocket_ping_pong() -> None:
     app = create_app(service=StubAgentService(), manage_service_lifecycle=False)
 
@@ -101,6 +115,64 @@ def test_websocket_message_returns_chat_metadata_and_session_updated() -> None:
     }
 
 
+def test_websocket_message_uses_direct_processing_when_loop_is_not_running() -> None:
+    service = DirectModeOnlyAgentService()
+    app = create_app(service=service, manage_service_lifecycle=False)
+
+    with TestClient(app) as client:
+        with client.websocket_connect("/ws/web:alpha") as websocket:
+            websocket.send_json({"type": "message", "content": "hello"})
+            assert websocket.receive_json() == {"type": "status", "status": "thinking"}
+            message = websocket.receive_json()
+
+    assert service.calls == [
+        {
+            "message": "hello",
+            "session_id": "web:alpha",
+            "source": "websocket",
+            "user_id": None,
+            "title": None,
+            "execution_context": None,
+            "model": None,
+            "provider_name": None,
+            "embedding_model": None,
+            "max_tool_iterations": None,
+        }
+    ]
+    assert message["type"] == "message"
+    assert message["content"] == "echo:hello"
+
+
+def test_rest_chat_uses_direct_processing_when_loop_is_not_running() -> None:
+    service = DirectModeOnlyAgentService()
+    app = create_app(service=service, manage_service_lifecycle=False)
+
+    with TestClient(app) as client:
+        response = client.post("/api/chat", json={"session_id": "web:alpha", "message": "hello"})
+
+    assert response.status_code == 200
+    assert service.calls == [
+        {
+            "message": "hello",
+            "session_id": "web:alpha",
+            "source": "web",
+            "user_id": None,
+            "title": None,
+            "execution_context": None,
+            "model": None,
+            "provider_name": None,
+            "embedding_model": None,
+            "temperature": None,
+            "max_tokens": None,
+            "max_tool_iterations": None,
+            "fallback_target": None,
+            "auxiliary_target": None,
+            "embedding_target": None,
+        }
+    ]
+    assert response.json()["output_text"] == "echo:hello"
+
+
 def test_websocket_empty_content_returns_error_without_runtime_call() -> None:
     service = StubAgentService()
     app = create_app(service=service, manage_service_lifecycle=False)