Skip to content

Fix NOT_NOVEL response parsing - #486

Open
justavibedev wants to merge 1 commit into
algorithmicsuperintelligence:mainfrom
justavibedev:fix/novelty-response-parser
Open

Fix NOT_NOVEL response parsing#486
justavibedev wants to merge 1 commit into
algorithmicsuperintelligence:mainfrom
justavibedev:fix/novelty-response-parser

Conversation

@justavibedev

Copy link
Copy Markdown

Summary

  • normalize the prompted NOT_NOVEL token before classification
  • preserve support for the legacy NOT NOVEL form
  • add regression coverage for plain, explained, and Markdown-wrapped responses

Fixes #483.

Testing

  • python -m unittest discover -s tests -p test_novelty_response_parsing.py -v
  • black --check openevolve/database.py tests/test_novelty_response_parsing.py

@CLAassistant

Copy link
Copy Markdown

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
You have signed the CLA already but the status is still pending? Let us recheck it.

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.

Novelty judge can never reject: prompt asks for NOT_NOVEL, parser matches "NOT NOVEL"

2 participants