Updated base_coder.py #4564
Open
Updated base_coder.py #4564
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Title: fix -Unable to cancel LLM request in the new update Aider-AI#3992 This change fixes a regression where Ctrl+C failed to cancel an LLM request during the initial "Waiting on response..." phase. The cancellation only worked once the response started streaming, leading to a period where the application felt unresponsive. To fix this, I've wrapped the initial, non-streaming litellm.completion call in its own try...except KeyboardInterrupt block. This ensures that user-initiated cancellations are handled immediately and consistently, whether the application is waiting for the first token or streaming the full response.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Title: fix -Unable to cancel LLM request in the new update #3992
This change fixes a regression where Ctrl+C failed to cancel an LLM request during the initial "Waiting on response..." phase. The cancellation only worked once the response started streaming, leading to a period where the application felt unresponsive.
To fix this, I've wrapped the initial, non-streaming litellm.completion call in its own try...except KeyboardInterrupt block. This ensures that user-initiated cancellations are handled immediately and consistently, whether the application is waiting for the first token or streaming the full response.