Repository navigation
Cut generation at stop sequence post generation - #1802
Merged
aymeric-roucher merged 8 commits intoOct 13, 2025
Merged
Conversation
albertvillanova
approved these changes
Oct 13, 2025
albertvillanova
left a comment
albertvillanova
left a comment
Member
There was a problem hiding this comment.
Thanks! Just some suggested improvements below.
3 of 5 tasks
maxwellfet928
pushed a commit
to maxwellfet928/smolagents
that referenced
this pull request
Jun 8, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When models don't support stop sequences, we currently just omit passing them a parameter stop sequence.
For tool calling mode, this generally isn't a problem because models are trained to end generation after generating their tool call.
But for code mode, this creates an issue where the model generates the stop sequence like
</code>, and then keeps generating nonsense, eventually hallucinating its way into failure to solve the user task.This PR fixes this for the
.generate()method by removing anything after a stop sequence post-generation.