Spaces:

irregular6612
/

AgentnessBench

Sleeping

App Files Files Community

AgentnessBench / tests /runtime /test_trace_accounting.py

Commit History

refactor(scenario): delete predator_evade; template is the canonical scenario

93cd78f

irregular6612 Claude Opus 4.8 (1M context) commited on Jun 3

refactor: restructure proteus into game/web subpackages

426093b

irregular6612 Claude Opus 4.8 (1M context) commited on Jun 2

feat(cp4.5): preserve probe reasoning + raw_text + token accounting via ProbeResult

f95852b

irregular6612 commited on Jun 1

feat(cp4.5): persist act-call token accounting + raw_text in TurnTrace

1c18fa9

irregular6612 commited on Jun 1