- Includes:
- Challenges & Tests
- Benchmarks & Metrics
- #3937 - Adaptability Challenge
- #3936 - Challenge to test web and web form
- #3935 - Another Debug Challenge
- #3917 - Challenge Creator Challenge
- #3912 - Challenge Solver Challenge
- #3907 - Proposal to enforce using default commands when testing
- #3906 - Test Order
- Specifics about how to run these tests/challenges
- #3901 - Regression Test via Simple Contact Form
- #3900 - Proposal to add async tooling to tests
- related to #3871
- #3883 - Proposal to use automatic AutoGPT config by default
- #3871 - Psychological Challenge
- #3863 - Parallel Testing proposal
- #3847 - Proposal to add framework to generate failing tests from debug logs
- #3839 - Proposal to update the wiki to include challenges
- specify what challenges are as opposed to other forms of tests
- #3838 - Memory Challenge
- #3837 - Information Retrieval
- #3836 - Python Debug Challenge
- #3835 - Building Challenges
- #3813 - Python Debug Challenge (Duplicate of #3836)
- #4033 - Sync -> Async Testing of ApiManager
- #3989 - Fix for Memory Challenge Docs
- #3985 - Document Failing Memory Challenge C
- #3982 - Proposal to add benchmarks
- #3969 - (Re-Arch) Hello World
- #3870 - Support for Concurrent Testing with pytest-xdist (fix for #3863)
- #3865 - Python Debug Challenge
- #3804 - Python Debug Challenge
- #3764 - Add challenges to wiki
- #3695 - Add logs for challenges
- #3605 - Add logs for challenges and debugging
- #3554 - Cassette fix on http/prompts
- helps improve reliability of regression tests