[REQUEST] Detect force thinking chat template and send that <think> tag

[Originalimoc]

Problem

Some models' chat template are like this: "{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\n<think>\n' }}". But API client won't see that <think> tag thus breaking parsing and UI.

Solution

Maybe make it optional, but add the ability to detect this and "compensate" that tag at the start of the response.

Acknowledgements

• I have looked for similar requests before submitting this one.
• I understand that the developers have lives and my issue will be answered when possible.
• I understand the developers of this program are human, and I will make my requests politely.