[Feature Request]: Gemini 2.0 Flash Thinking Mode

[ycd]

Feature Description

It is a new and experimental model from Google, from the Gemini model documentation:

Gemini 2.0 Flash Thinking Mode is an experimental model that’s trained to generate the “thinking process” the model goes through as part of its response. As a result, Thinking Mode is capable of stronger reasoning capabilities in its responses than the base Gemini 2.0 Flash model.

I assume that this will not be easy as #17249 to implement because it is fundamentally different that how it returns the messages and the response, since it also streams the thought process. Also AFAIK it does not supports the structured outputs, yet.

Reason

No response

Value of Feature

No response