[Bug]: Invalid response object from openai compatible service providers

[Vimos]

Is there an existing issue for the same bug? (If one exists, thumbs up or comment on the issue instead).

• [x] I have checked the existing issues.

Describe the bug and reproduction steps

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/app/openhands/controller/agent_controller.py", line 305, in _step_with_exception_handling
    await self._step()
  File "/app/openhands/controller/agent_controller.py", line 827, in _step
    action = self.agent.step(self.state)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/openhands/agenthub/codeact_agent/codeact_agent.py", line 191, in step
    response = self.llm.completion(**params)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 338, in wrapped_f
    return copy(f, *args, **kw)
           ^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 477, in __call__
    do = self.iter(retry_state=retry_state)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 378, in iter
    result = action(retry_state)
             ^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 400, in <lambda>
    self._add_action_func(lambda rs: rs.outcome.result())
                                     ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/concurrent/futures/_base.py", line 449, in result
    return self.__get_result()
           ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
    raise self._exception
  File "/app/.venv/lib/python3.12/site-packages/tenacity/__init__.py", line 480, in __call__
    result = fn(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^
  File "/app/openhands/llm/llm.py", line 282, in wrapper
    resp: ModelResponse = self._completion_unwrapped(*args, **kwargs)
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/utils.py", line 1281, in wrapper
    raise e
  File "/app/.venv/lib/python3.12/site-packages/litellm/utils.py", line 1159, in wrapper
    result = original_function(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/main.py", line 3225, in completion
    raise exception_type(
          ^^^^^^^^^^^^^^^
  File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2232, in exception_type
    raise e
  File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 467, in exception_type
    raise APIError(
litellm.exceptions.APIError: litellm.APIError: APIError: OpenAIException - Invalid response object Traceback (most recent call last):
  File "/app/.venv/lib/python3.12/site-packages/litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py", line 458, in convert_to_model_response_object
    assert response_object["choices"] is not None and isinstance(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError


received_args={'response_object': {'id': None, 'choices': None, 'created': None, 'model': None, 'object': None, 'service_tier': None, 'system_fingerprint': None, 'usage': None, 'code': 20000, 'msg': 'Unknown error []'}, 'model_response_object': ModelResponse(id='chatcmpl-a0e566c2-f626-4cd4-bd0d-26b7d4b30202', created=1748237676, model=None, object='chat.completion', system_fingerprint=None, choices=[Choices(finish_reason='stop', index=0, message=Message(content=None, role='assistant', tool_calls=None, function_call=None, provider_specific_fields=None))], usage=Usage(completion_tokens=0, prompt_tokens=0, total_tokens=0, completion_tokens_details=None, prompt_tokens_details=None)), 'response_type': 'completion', 'stream': False, 'start_time': None, 'end_time': None, 'hidden_params': None, '_response_headers': {'date': 'Mon, 26 May 2025 05:34:41 GMT', 'content-type': 'application/json', 'content-length': '39', 'connection': 'keep-alive', 'traceresponse': '00-2505261334360a059985c5e35e46c0e9-576599d1064c5914-01', 'strict-transport-security': 'max-age=31536000; includeSubDomains'}, 'convert_tool_call_to_json_mode': None}

05:34:41 - openhands:INFO: agent_controller.py:591 - [Agent Controller 7b1f60cfafde45f6847dece31d1a77da] Setting agent(CodeActAgent) state from AgentState.RUNNING to AgentState.ERROR
05:34:41 - openhands:INFO: session.py:253 - Agent status error
05:34:41 - openhands:INFO: agent_controller.py:591 - [Agent Controller 7b1f60cfafde45f6847dece31d1a77da] Setting agent(CodeActAgent) state from AgentState.ERROR to AgentState.ERROR
05:34:41 - openhands:INFO: session.py:312 - Agent status error

OpenHands Installation

Docker command in README

OpenHands Version

No response

Operating System

None

Logs, Errors, Screenshots, and Additional Context

No response

[mamoodi]

Hi there. Can you please mention what LLM you are using?

[enyst]

Yes, as Mamoodi said, your LLM and provider seem to respond in a way that maybe is not, actually, compatible.

It could be useful to disable tool use, if you had it enabled.

[Vimos]

Thank you! I will notice them about the issue.

[github-actions[bot]]

This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.

[github-actions[bot]]

This issue was closed because it has been stalled for over 30 days with no activity.