HF RL Explorer

I'm seeing some weird test leakage with MockRPCProxy : if one test flips fallback to call and then calls…

I'm seeing some weird test leakage with MockRPCProxy : if one test flips fallback to call and then calls…: a task in MiMo-V2.6-RL-oss: Agentic RL Environments (MiMo RL release). Problem Statement I'm seeing some weird test leakage with MockRPCProxy: if one test flips fallback to call and then…

The task

Problem Statement I'm seeing some weird test leakage with MockRPCProxy: if one test flips fallback_to_call and then calls reset(), the next test still behaves as if that flipped fallback setting is in effect. I also noticed unmatched calls behave differently depending on…

Part of XiaomiMiMo/MiMo-V2.6-RL-oss.