↓ 2 callersFunctioncompose_prompt_to_plan(demos, useful_focus_on, task_desc, recent_actions, recent_obs, recent_locs, recent_looks, failed_messages, lo
eval_heldout/science-world/eval_utils.py:711
↓ 2 callersFunctionepisode(model, idx=None, verbose=False, softmax=False, rule=False, bart_model=None)
AgentBench.old/src/tasks/webshop/baseline_models/test.py:71
↓ 2 callersMethodforward(self, state_batch, act_batch, value=False, q=False, act=False)
AgentBench.old/src/tasks/webshop/baseline_models/models/rnn.py:66
↓ 2 callersFunctiongenerate_from_openai_chat_completion(
messages: list[dict[str, str]],
model: str,
temperature: float,
max_tokens: int,
top_p:
eval_heldout/webarena/llms/providers/openai_utils.py:242