Error: litellm.APIConnectionError: 'name'

[caussao]

when i use CAI with my local model (in this case qwen3 and llama3) it stops in 1-3 turns and show this error message:

ErrorMessageCai.txt

this is the command i do before start CAI: echo -e 'OPENAI_API_KEY="sk-123"\nOLLAMA_API_BASE="http://127.0.0.1:11434"\nSHODAN_API_KEY="XXXXXXX"' > .env

and the server keep running before and after the connection.

here's the short log only for example:

cai_log.txt

[vmayoral]

@caussao, went through

your error

If you are using private models, there is a error. callback to ollama
Error: litellm.APIConnectionError: 'name'
Traceback (most recent call last):
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/llms/openai/openai.py", line 724, in completion
    raise e
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/llms/openai/openai.py", line 652, in completion
    ) = self.make_sync_openai_chat_completion_request(
        ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        openai_client=openai_client,
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    ...<2 lines>...
        logging_obj=logging_obj,
        ^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/litellm_core_utils/logging_utils.py", line 149, in sync_wrapper
    result = func(*args, **kwargs)
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/llms/openai/openai.py", line 471, in make_sync_openai_chat_completion_request
    raise e
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/llms/openai/openai.py", line 453, in make_sync_openai_chat_completion_request
    raw_response = openai_client.chat.completions.with_raw_response.create(
        **data, timeout=timeout
    )
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/openai/_legacy_response.py", line 364, in wrapped
    return cast(LegacyAPIResponse[R], func(*args, **kwargs))
                                      ~~~~^^^^^^^^^^^^^^^^^
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/openai/_utils/_utils.py", line 287, in wrapper
    return func(*args, **kwargs)
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/openai/resources/chat/completions/completions.py", line 925, in create
    return self._post(
           ~~~~~~~~~~^
        "/chat/completions",
        ^^^^^^^^^^^^^^^^^^^^
    ...<43 lines>...
        stream_cls=Stream[ChatCompletionChunk],
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/openai/_base_client.py", line 1239, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/openai/_base_client.py", line 1034, in request
    raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: 404 page not found

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/main.py", line 1799, in completion
    raise e
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/main.py", line 1772, in completion
    response = openai_chat_completions.completion(
        model=model,
    ...<15 lines>...
        custom_llm_provider=custom_llm_provider,
    )
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/llms/openai/openai.py", line 735, in completion
    raise OpenAIError(
    ...<4 lines>...
    )
litellm.llms.openai.common_utils.OpenAIError: 404 page not found

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/cai/core.py", line 502, in get_chat_completion
    litellm_completion = litellm.completion(**ollama_params)
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/utils.py", line 1255, in wrapper
    raise e
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/utils.py", line 1133, in wrapper
    result = original_function(*args, **kwargs)
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/main.py", line 3184, in completion
    raise exception_type(
          ~~~~~~~~~~~~~~^
        model=model,
        ^^^^^^^^^^^^
    ...<3 lines>...
        extra_kwargs=kwargs,
        ^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2217, in exception_type
    raise e
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 405, in exception_type
    raise NotFoundError(
    ...<5 lines>...
    )
litellm.exceptions.NotFoundError: litellm.NotFoundError: NotFoundError: OpenAIException - 404 page not found

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/main.py", line 2872, in completion
    response = base_llm_http_handler.completion(
        model=model,
    ...<13 lines>...
        client=client,
    )
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/llms/custom_httpx/llm_http_handler.py", line 415, in completion
    return provider_config.transform_response(
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        model=model,
        ^^^^^^^^^^^^
    ...<9 lines>...
        json_mode=json_mode,
        ^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/home/usuario/cai-framework/lib/python3.13/site-packages/litellm/llms/ollama/completion/transformation.py", line 266, in transform_response
    "name": function_call["name"],
            ~~~~~~~~~~~~~^^^^^^^^
KeyError: 'name'

This doesn't tell me much. Essentially, that there is a 404 "page not found" error when trying to make an OpenAI-style API call. qwen3:latest works perfectly fine on my side:

If you'd like assistance, provide a reproducible PoC and I'll have a look at it again.

[vmayoral]

See https://discord.com/channels/1359128560526168224/1359128560991863011/1367178770007592960

Note to self, contribute this to the README’s FAQ.