FEAT: Adding Expectations to Attacks (Scorer Generalization Phase 4) - #2692
Merged
Richard Lundeen (richlundeen) merged 5 commits intoSep 18, 2026
Conversation
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Roman Lutz (romanlutz)
approved these changes
Sep 18, 2026
Validate wrapped scorers before attack execution, preserve component context across async failures, and clarify scoring compatibility and compound outcomes. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Exclude function-local scorer classes from automatic discovery while preserving instance registration. Add regression coverage and clarify the attack configuration example. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Require nodes to use the resolved execution expectation and remove the per-turn fallback. Update direct node fixtures and cover default and explicit expectations through branching. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Richard Lundeen (richlundeen)
deleted the
richlundeen-pyrit-scorer-design
branch
September 18, 2026 22:41
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This implements phase 4 of the scorer generalization design by adding a per-execution
ScoringExpectationto the shared attack contract. Attacks now resolve and forward the effective expectation to objective and auxiliary scorers while preserving attack-specific refusal and preparation criteria. The change also validates condition routing before execution, preserves scoring context through compound attacks, and documents the updated behavior. See the design proposal for the full phase model.