Adding AttackStrategy.MultiTurn
#40828
Open
+1,687
−196
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
github-actions
bot
added
the
Evaluation
There was a problem hiding this comment.
Pull Request Overview
This pull request adds support for a new multi-turn attack strategy in the red team evaluation SDK by introducing the AttackStrategy.MultiTurn enum, updating orchestrator selection logic, and modifying tests and logging details accordingly.
- Added a new enum value AttackStrategy.MultiTurn and updated its converter mapping.
- Updated orchestrator selection, logging, and test assertions to use a separate risk_category_name parameter.
- Modified related files to improve clarity and maintain consistent naming conventions.
Reviewed Changes
Copilot reviewed 9 out of 9 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| sdk/evaluation/azure-ai-evaluation/tests/unittests/test_redteam/test_red_team.py | Updated test imports, assertions, and patching to incorporate risk_category_name changes and multi-turn support. |
| sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/red_team/_utils/strategy_utils.py | Added mapping for AttackStrategy.MultiTurn in the converter mapping. |
| sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/red_team/_utils/metric_mapping.py | Updated metric mapping for RiskCategory.HateUnfairness to use a corrected metric name. |
| sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/red_team/_utils/constants.py | Added a new USER_AGENT constant. |
| sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/red_team/_red_team.py | Updated orchestrator selection and logging to use risk_category_name; introduced a multi-turn orchestrator (_multi_turn_orchestrator). |
| sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/red_team/_attack_strategy.py | Extended the AttackStrategy enum to include MultiTurn. |
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/red_team/_red_team.py
Outdated
Show resolved
Hide resolved
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/red_team/_red_team.py
Outdated
Show resolved
Hide resolved
…m/_red_team.py Co-authored-by: Copilot <[email protected]>
…m/_red_team.py Co-authored-by: Copilot <[email protected]>
|
API change check API changes are not detected in this pull request. |
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.
Description
Please add an informative description that covers that changes made by the pull request and link all relevant issues.
If an SDK is being regenerated based on a new swagger spec, a link to the pull request containing these swagger spec changes has been included above.
All SDK Contribution checklist:
General Guidelines and Best Practices
Testing Guidelines