😢 The Problem with LLMs and Testing 😢​
- Noisy test output - Raw Vitest output can be extremely verbose eating up tokens/context with useless information.
- Full test suite runs - LLMs sometimes forget to limit the scope of the test run, causing full test suite runs to be executed.
- Buried console logs - Console logs can be hidden in test output, making it inefficient for LLMs to debug test failures.
- Raw coverage files - Raw coverage files are too large for AI to parse.
- Watch mode - LLMs get stuck when vitest runs in watch mode.