Repository navigation
MAINT: Remove duplicate adversarial response format instructions - #3505
Open
Richard Lundeen (richlundeen) wants to merge 2 commits into
Open
Richard Lundeen (richlundeen) wants to merge 2 commits into
Richard Lundeen (richlundeen) wants to merge 2 commits into
Conversation
Keep response structure in the shared adversarial_chat schema and retain technique-specific guidance. Add template and schema-delivery regression coverage. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Keep the shared YAML schema assertion without requiring duplicate response field names in prompt prose. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Remove duplicate JSON layouts, key lists, and format-only examples from all 29 built-in prompts that declare the shared
adversarial_chatschema. Keep role-specific guidance and convert PAIR/TAP behavioral examples to prose.The shared schema remains the source of truth for response structure. Targets use native schema metadata or add schema instructions when their capability policy permits adaptation. Schema declarations, prompt metadata, public interfaces, and the prompt editors are unchanged.
Tests and Documentation
Add catalog-wide checks for template loading, rendering, schema resolution, and retained content guidance. Extend schema-forwarding coverage for native and adapted targets, including Red Teaming and simulated next-message generation.
Validation:
uv run --no-sync pytest -q tests\unit\datasets\test_adversarial_prompt_templates.py tests\unit\executor\attack\multi_turn\test_adversarial_chat_schema_forwarding.py tests\unit\executor\attack\component\test_adversarial_conversation_manager.py tests\unit\executor\attack\component\test_simulated_conversation.py tests\unit\message_normalizer\test_json_schema_normalizer.py— passed: 184 tests; 11 deprecation warnings.$env:UV_NO_SYNC = '1'; uv run --no-sync pre-commit run --all-files— all hooks passed.uv.lockare unchanged.No documentation changes are included, as requested. No live-model calls were run.
JupyText was not run; no documentation or notebook files changed.