Skip to content

Conversation

mikecann
Copy link
Contributor

@mikecann mikecann commented Oct 21, 2025

This PR is 5 of 5, last part was here: #84

The purpose of this PR is to add AI grading to a bunch of tests for cases where its infeasible to test using unit tests.

See the description on the past PR for more info: #83

There are also some changes in here around reporting the results correctly to stdout so that the tests results correctly show up in the local results output log so I can inspect the logs and see exactly why the AI failed the run.

@mikecann mikecann mentioned this pull request Oct 21, 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