This PR is based on https://github.com/huggingface/llm-vscode/pull/103 by @davidpissarra which looks stale without further improvements / changes for a month, but which brings a really neat feature imo :)
As the original PR, it adds the llm.requestDelay setting, representing the minimum time interval between requests, in milliseconds though. It now defaults to 150ms in addition to taking into account the cancellation token.
Hope this helps! I would not mind declining this PR if any changes happen to be made on the other one.
Thanks for your review
Hi @McPatate 👋
This PR is based on https://github.com/huggingface/llm-vscode/pull/103 by @davidpissarra which looks stale without further improvements / changes for a month, but which brings a really neat feature imo :)
As the original PR, it adds the
llm.requestDelay
setting, representing the minimum time interval between requests, in milliseconds though. It now defaults to150ms
in addition to taking into account the cancellation token.Hope this helps! I would not mind declining this PR if any changes happen to be made on the other one. Thanks for your review