Skip to content

Conversation

@katherineh123
Copy link
Collaborator

Makes the parsing of LLM generated checklist more robust in checklist_prompt_generator.

The issue is that sometimes the parsing fails, throws an error, and stops the entire run.
The error happened when running full morpheus23 test set during evaluation.
Error logs from the failed run were not saved.
This is hard to replicate.

Difficulty in replication also implies that the updated code in this PR does not fix the error (unsure if the updated code actually fixes the error, or if the error was just not replicated correctly).

Issue to track this is here.

This was referenced Oct 19, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant