diff --git a/evalharness/eval/recipes/agent.py b/evalharness/eval/recipes/agent.py index d28d102..117cc8f 100644 --- a/evalharness/eval/recipes/agent.py +++ b/evalharness/eval/recipes/agent.py @@ -269,7 +269,12 @@ def _official_swebench_eval(instance_meta: dict, patch: str, timeout: int = 1800 image_name = test_spec.instance_image_key container = client.containers.run( image_name, command='tail -f /dev/null', detach=True, - name=f'eh-swe-official-{test_spec.instance_id[:40]}') + name=f'eh-swe-official-{test_spec.instance_id[:40]}', + # the official eval_script runs `pip install -e .[test]`; pypi.org + # is unreachable from this host's containers -> same tuna mirror + # as the agent containers + environment={'PIP_INDEX_URL': + 'https://pypi.tuna.tsinghua.edu.cn/simple'}) try: patch_file = log_dir / 'patch.diff' patch_file.write_text(patch or '')