MAINT: Unify adversarial-chat JSON schema across Crescendo, TAP, and PAIR#2039
Merged
rlundeen2 merged 5 commits intoJun 18, 2026
Merged
Conversation
Add a shared `adversarial_chat` JSON schema (next_message, rationale, last_response_summary) and wire the Crescendo, TAP, and PAIR adversarial-chat prompts onto it so their prompts are interchangeable. Parsers now read/return next_message and forward the schema to schema-aware targets via prompt metadata. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The message normalizer already appends the response JSON schema when it is forwarded via prompt metadata, so the hand-written schema block in the Crescendo system prompts duplicated that instruction. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Routes Crescendo and TAP adversarial sends through a real PromptNormalizer and a MockPromptTarget (which lacks native JSON_SCHEMA support) to verify the shared adversarial_chat schema is forwarded via prompt metadata and rendered into the prompt the adversarial chat receives. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
romanlutz
approved these changes
Jun 18, 2026
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add a shared
adversarial_chatJSON schema (next_message, rationale, last_response_summary) and wire the Crescendo, TAP, and PAIR adversarial-chat prompts onto it so their prompts are interchangeable. Parsers now read/return next_message and forward the schema to schema-aware targets via prompt metadata.Value Prop
Next up, it'd be nice to normalize red team attack also, but that requires more since it works differently at the moment. But at that point we could share all attack scenarios (role play, etc)