Fail closed when Qwen3Guard output is unparseable - #64
Closed
fallintoplace wants to merge 1 commit into
Closed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Safety:labels as blocked instead of lettinglabel.lower()crashis_safe()when Qwen3Guard cannot complete the safety checkWhy
Qwen3Guard currently fails open when the moderation output drifts away from the expected
Safety: ...format. A missing label triggers an exception,is_safe()catches it, and returnsTrue, which lets the prompt through even though the guardrail did not finish successfully.Validation
PYTHONPATH=/Users/hoangvu/Code/OSS/cosmos-framework uvx pytest --noconftest /Users/hoangvu/Code/OSS/cosmos-framework/cosmos_framework/auxiliary/guardrail/qwen3guard/qwen3guard_test.py -o addopts=uvx ruff check /Users/hoangvu/Code/OSS/cosmos-framework/cosmos_framework/auxiliary/guardrail/qwen3guard/qwen3guard.py /Users/hoangvu/Code/OSS/cosmos-framework/cosmos_framework/auxiliary/guardrail/qwen3guard/qwen3guard_test.pyuvx ruff format --check /Users/hoangvu/Code/OSS/cosmos-framework/cosmos_framework/auxiliary/guardrail/qwen3guard/qwen3guard.py /Users/hoangvu/Code/OSS/cosmos-framework/cosmos_framework/auxiliary/guardrail/qwen3guard/qwen3guard_test.py