HF RL Explorer

We have an issue with benchmark discovery in our tool that prevents cross-commit comparisons when the API of…

We have an issue with benchmark discovery in our tool that prevents cross-commit comparisons when the API of…: a task in LegoFlow-SWE (Harbor dataset). Expected behavior after the fix:

The task

**Expected behavior after the fix:**

Part of Lego-X/LegoFlow-SWE.