当调试来自ChatLanguageModel的请求/响应时，它太嘈杂了。如果能有一个选项启用简约逻辑，而不是这样，那就更好了：

----------------------------------->
[System]: You are a helpful assistant
[User  ]: Hello
[AI    ]: Hi, how can I help you?
[User  ]: Tell me a joke
----------------------------------->

<-----------------------------------
[AI    ]: Why did the math book look sad? Because it had too many problems.
<-----------------------------------

如果请求包含工具，它们应该格式化得很好：

----------------------------------->
[System]: You are a helpful assistant
[User  ]: What's the weather in Munich?
--------
[Tools ]: getWeather(location)
----------------------------------->

如果响应中有工具执行请求，它们也应该格式化得很好：

<-----------------------------------
[AI    ]: [Tools]: getWeather("Munich")
<-----------------------------------