HF RL Explorer

Can't chain assertions, and no built-in truthy/falsy check

Can't chain assertions, and no built-in truthy/falsy check: a task in MiMo-V2.6-RL-harbor-code: MiMo-V2.6-RL Code (Harbor) (Harbor dataset). I'm using this library to write tests and ran into two things that feel like they should already work but don't.

Part of FineEnvs/MiMo-V2.6-RL-harbor-code.