LMStudio+CLI The wrong API endpoint is being called.

[Unknown3658]

Hi everyone,

I’m looking for help from someone familiar with this setup.

The setup:
I have a local LLM running via LMStudio + a local API.
I have WSL (Ubuntu) running this tool: https://github.com/aliasrobotics/cai#cybersecurity-ai-cai

The API responds to curl requests, but the application is trying to access the wrong path, despite the .env configuration.

LM Studio log:

2026-07-13 09:41:14 [ERROR]
 Unexpected endpoint or method. (GET /api/tags). Returning 200 anyway
2026-07-13 09:44:15 [DEBUG]
 Received request: GET to /api/tags
2026-07-13 09:44:15 [ERROR]
 Unexpected endpoint or method. (GET /api/tags). Returning 200 anyway
2026-07-13 09:44:18 [DEBUG]
 Received request: GET to /api/tags

CAI trace

ERROR:cai.cli:Error in main loop: litellm.AuthenticationError: AuthenticationError: OpenAIException - LiteLLM Virtual Key expected. Received=REDA****_KEY, expected to start with 'sk-'.
Traceback (most recent call last):
  File "/home/username/cai_env/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 790, in acompletion
    headers, response = await self.make_openai_chat_completion_request(
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/username/cai_env/lib/python3.12/site-packages/litellm/litellm_core_utils/logging_utils.py", line 135, in async_wrapper
    result = await func(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/username/cai_env/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 436, in make_openai_chat_completion_request
    raise e
  File "/home/username/cai_env/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 418, in make_openai_chat_completion_request
    await openai_aclient.chat.completions.with_raw_response.create(
  File "/home/username/cai_env/lib/python3.12/site-packages/openai/_legacy_response.py", line 381, in wrapped
    return cast(LegacyAPIResponse[R], await func(*args, **kwargs))
                                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/username/cai_env/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 2032, in create
    return await self._post(
           ^^^^^^^^^^^^^^^^^
  File "/home/username/cai_env/lib/python3.12/site-packages/openai/_base_client.py", line 1805, in post
    return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/username/cai_env/lib/python3.12/site-packages/openai/_base_client.py", line 1495, in request
    return await self._request(
           ^^^^^^^^^^^^^^^^^^^^
  File "/home/username/cai_env/lib/python3.12/site-packages/openai/_base_client.py", line 1600, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.AuthenticationError: Error code: 401 - {'error': {'message': "LiteLLM Virtual Key expected. Received=REDA****_KEY, expected to start with 'sk-'.", 'type': 'auth_error', 'param': 'None', 'code': '401'}}

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/username/cai_env/lib/python3.12/site-packages/litellm/main.py", line 507, in acompletion
    response = await init_response
               ^^^^^^^^^^^^^^^^^^^
  File "/home/username/cai_env/lib/python3.12/site-packages/litellm/llms/openai/openai.py", line 837, in acompletion
    raise OpenAIError(
litellm.llms.openai.common_utils.OpenAIError: Error code: 401 - {'error': {'message': "LiteLLM Virtual Key expected. Received=REDA****_KEY, expected to start with 'sk-'.", 'type': 'auth_error', 'param': 'None', 'code': '401'}}

Trying various .env configurations didn't help; the trace isn't showing up—though only with this specific configuration—yet there is still no load visible, as the LMStudio logs aren't working.

OPENAI_API_KEY="sk-1234"
OLLAMA_API_BASE="//http://172.19.16.1:25000/v1"
OLLAMA=""
ALIAS_API_KEY="sk-lm-(token)"  # note, add yours
CAI_STREAM=False
CAI_MODEL="gemma-4-12b-coder-fable5-composer2.5-v1"

I look forward to your feedback. Thank you.