FIX Crescendo backtrack with same orchestrator ID and handling responses with markdown syntax #340
Conversation
This file contains 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Outdated suggestions cannot be applied.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
Backtracking in Crescendo was failing because it requires duplicating the memory. This, in turn, requires a unique new orchestrator ID which we weren't providing. I've made that optional in this PR since it's not really needed, only a new conversation ID is needed.
Additionally, while running the notebook, I found that responses from the red teaming LLM contain markdown syntax resulting in failed JSON parsing and unnecessary retries. I applied the existing markdown handler and validated it to make sure it works as expected.
Tests and Documentation
reran notebook for crescendo, added test for optional orchestrator ID in memory duplication method