[Bug]: [SWE-bench] Faild to cd. ModuleNotFoundError

[BIJOY-SUST]

Is there an existing issue for the same bug?

• I have checked the existing issues.

Describe the bug and reproduction steps

I've encountered these following issues—sometimes the process works as expected, sometimes it doesn't. A specific example of this issue occurred when running the following command:

./evaluation/benchmarks/swe_bench/scripts/run_infer.sh llm.qwen_model HEAD CodeActAgent 1 30 1 princeton-nlp/SWE-bench_Lite test

The issue is associated with django__django-12915.

evaluation.utils.shared.EvalException: Failed to cd to /workspace/django__django__3.2: **CmdOutputObservation (source=None, exit code=2)**
---------------------------------
---------------------------------
  File "<frozen importlib._bootstrap>", line 994, in _gcd_import
  File "<frozen importlib._bootstrap>", line 971, in _find_and_load
  File "<frozen importlib._bootstrap>", line 953, in _find_and_load_unlocked
ModuleNotFoundError: No module named '/workspace/django__django__3'
---------------------------------
---------------------------------
ERROR:root:<class 'RuntimeError'>: Maximum error retries reached for instance django__django-12915

OpenHands Installation

Docker command in README

OpenHands Version

0.18.0

Operating System

Linux

Logs, Errors, Screenshots, and Additional Context

No response

[BIJOY-SUST]

Facing this issue for other instances also-

evaluation.utils.shared.EvalException: Failed to cd to /workspace/matplotlib__matplotlib__3.5: **CmdOutputObservation (source=None, exit code=2)**
0
Instance matplotlib__matplotlib-22711 - 2025-01-23 15:53:13,587 - ERROR - Failed to cd to /workspace/matplotlib__matplotlib__3.5: **CmdOutputObservation (source=None, exit code=2)**
0
Traceback (most recent call last):
  File "project_name/evaluation/utils/shared.py", line 330, in _process_instance_wrapper
    result = process_instance_func(instance, metadata, use_mp, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "project_name/evaluation/benchmarks/swe_bench/run_infer.py", line 419, in process_instance
    return_val = complete_runtime(runtime, instance)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "project_name/evaluation/benchmarks/swe_bench/run_infer.py", line 311, in complete_runtime
    assert_and_raise(
  File "project_name/evaluation/utils/shared.py", line 307, in assert_and_raise
    raise EvalException(msg)
evaluation.utils.shared.EvalException: Failed to cd to /workspace/matplotlib__matplotlib__3.5: **CmdOutputObservation (source=None, exit code=2)**
0
Instance matplotlib__matplotlib-23987 - 2025-01-23 15:53:13,589 - INFO - Starting evaluation for instance matplotlib__matplotlib-23987.
Hint: run "tail -f evaluation/evaluation_outputs/outputs/princeton-nlp__SWE-bench_Lite-test/CodeActAgent/_maxiter_30_N_v0.18.0-no-hint-swe_gym_7b_sft_d_1234_e_3_v4_merge-run_1/infer_logs/instance_matplotlib__matplotlib-23987.log" to see live logs in a separate shell
ERROR:root:  File "project_name/evaluation/benchmarks/swe_bench/run_infer.py", line 531, in <module>
    run_evaluation(
  File "project_name/evaluation/utils/shared.py", line 440, in run_evaluation
    for result in results:
                  ^^^^^^^
  File "/home/user_name/.conda/envs/openhands/lib/python3.12/multiprocessing/pool.py", line 873, in next
    raise value

ERROR:root:<class 'RuntimeError'>: Maximum error retries reached for instance matplotlib__matplotlib-22711