Originally created by @Adhithya03 on GitHub (Oct 6, 2024).
I would like to suggest adding a thinking time indicator that displays the time in seconds it takes for the o1-series (or other similar reasoning models in the future) to generate a response from the API, similar to the feature available in OpenAI's official ChatGPT.
Although this is a minor enhancement, it would significantly improve user experience by providing visual feedback that the model is actively working on the request. Currently, with streaming responses disabled, users might perceive the API request as indefinitely paused. Displaying the processing time would reassure users that progress is being made.
Additional context
Originally created by @Adhithya03 on GitHub (Oct 6, 2024).
I would like to suggest adding a **thinking time indicator** that displays the time in seconds it takes for the o1-series (or other similar reasoning models in the future) to generate a response from the API, similar to the feature available in OpenAI's official ChatGPT.
- Although this is a minor enhancement, it would significantly improve user experience by providing visual feedback that the model is actively working on the request. Currently, with streaming responses disabled, users might perceive the API request as indefinitely paused. Displaying the processing time would reassure users that progress is being made.
**Additional context**

Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @Adhithya03 on GitHub (Oct 6, 2024).
I would like to suggest adding a thinking time indicator that displays the time in seconds it takes for the o1-series (or other similar reasoning models in the future) to generate a response from the API, similar to the feature available in OpenAI's official ChatGPT.
Additional context