diff --git a/evalharness/agent/envs/tau2_official.py b/evalharness/agent/envs/tau2_official.py index 3151203..a6e214c 100644 --- a/evalharness/agent/envs/tau2_official.py +++ b/evalharness/agent/envs/tau2_official.py @@ -193,6 +193,10 @@ class Tau2Environment(Environment): return self.reward_info async def run_task(self, adapter, sample, max_turns: int = 40, user_adapter=None, gen_kwargs=None, **kw): + # the runner's generic default (8 turns) is for single-tool benches; + # a tau2 phone call needs greet -> verify -> find -> policy -> act -> + # confirm (official runs use 40+). Floor it, never cap below it. + max_turns = max(int(max_turns or 0), 40) from tau2.data_model.tasks import Task from tau2.run import run_task