Handle None content in stop-sequence trimming
#1826
Merged
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
5 tasks
src/smolagents/models.py
Outdated
| return content | ||
|
|
||
| for stop_seq in stop_sequences: | ||
| if not stop_seq: |
There was a problem hiding this comment.
Why support having one of the stop sequences being None?
Apart from that I agree with the other introduced changes!
There was a problem hiding this comment.
Thanks for spotting that @aymeric-roucher! You’re right, we don’t expect providers to return None inside stop_sequences.
| assert removed_content == "Hello" | ||
|
|
||
|
|
||
| def test_remove_content_after_stop_sequences_handles_none(): |
There was a problem hiding this comment.
Please merge these tests into one with several asserts! After that lgtm !
There was a problem hiding this comment.
Thanks a lot for the feedback and the review @aymeric-roucher.
I've merged the tests as suggested.
Happy to make it less verbose or use a different name if you prefer.
…larity and coverage for None inputs
aymeric-roucher
approved these changes
Oct 27, 2025
|
@aymeric-roucher thanks a lot for your review, support and for merging! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Prevent stop-sequence trimming from crashing on tool-only GPT-5 outputs
Linked Issue
Fixes Bug #1825
Summary
remove_content_after_stop_sequencesfrom crashing when a provider returnscontent=None(e.g.gpt-5tool-only turns).Nonestop list to avoid accidental truncation.Details
content=Noneandstop_sequences=Noneas no-op cases so we only trim when actual text is present.gpt-5tool-calling without changing behavior for normal string outputs.Tests
tests/test_models.py::test_remove_content_after_stop_sequences_handles_none– confirms the helper returnsNonewhen the provider emits tool-only output, mirroring the bug scenario.tests/test_models.py::test_remove_content_after_stop_sequences_ignores_empty_stop_sequences– ensures harmless empty stop strings do not strip valid text.tests/test_models.py::test_remove_content_after_stop_sequences_with_none_stop_sequences– protects the default code path wherestop_sequencesisNone, preserving existing behavior.Thanks a lot for feedback and support!