Extra Delay After Response Completion Preventing New Query Submission

[JihwanEom]

What happened?

What happened?

• After sending a query, the model responds quickly and the response is displayed as expected. However, even after the model finishes generating the complete answer, there is an additional delay of approximately 3 to 5 seconds before I am allowed to send the next query. During this waiting period, the "Stop Generation" button remains enabled, which prevents me from submitting any new queries.

What did you expect to happen?

• I expected that once the model has finished generating a response, the interface would immediately allow me to send another query. Specifically, the "Stop Generation" button should become disabled (or change state) to clearly indicate that the response is complete and that I can start a new interaction without any unnecessary delay.

Thank you for your attention to this issue!

Version Information

ghcr.io/danny-avila/librechat-dev                latest    558ce6e148da   20 hours ago    873MB
ghcr.io/danny-avila/librechat-rag-api-dev-lite   latest    cf692235882f   2 months ago    1.26GB

Steps to Reproduce

For OpenAI models (gpt-4o, chatgpt-latest, o1, o3-mini), type any query.

What browsers are you seeing the problem on?

Safari

Relevant log output

Screenshots

Stucks about 5~ seconds

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

It can't be reproduced:

chrome_G0ooC2Ltdi.mp4

It could be a networking issue between you and the server, and/or your server and the OpenAI API