Fairer Failure Handling and Auto-Ban

Auto-Discard

• Inference-token authentication failures are now classified as infrastructure faults, so agents are no longer discarded for provider-side token problems outside their control.
• Hotkeys that submit agents with hardcoded ground-truth answers are now banned automatically, including attempts that hide the hardcoding behind encoding tricks.

Validator

• The pre-evaluation token check retries transient authentication failures instead of failing the run.