Ensure api_token is not included in the response on error

[tgaddair]

No description provided.

[noyoshi]

Would also be good to remove it from server logs as well

[tgaddair]

Hmm, not able to repro. This is the error I get when using a bad token:

Traceback (most recent call last):
  File "/data/lorax/clients/python/lorax/client.py", line 342, in generate_stream
    response = StreamResponse(**json_payload)
  File "/opt/conda/lib/python3.10/site-packages/pydantic/main.py", line 176, in __init__
    self.__pydantic_validator__.validate_python(data, self_instance=self)
pydantic_core._pydantic_core.ValidationError: 1 validation error for StreamResponse
token
  Field required [type=missing, input_value={'error': 'Request failed...ror_type': 'generation'}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.7/v/missing

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/data/lorax/test_speculate.py", line 54, in <module>
    for resp in client.generate_stream(
  File "/data/lorax/clients/python/lorax/client.py", line 345, in generate_stream
    raise parse_error(resp.status_code, json_payload)
lorax.errors.GenerationError: Request failed during generation: Server error: 401 Client Error. (Request ID: Root=1-664797a7-3da69d07260da6a91fe42e67;c6bd25da-df19-48cf-bb68-770eb0a94ad7)

Repository Not Found for url: https://huggingface.co/api/models/predibase/test-private-lora.
Please make sure you specified the correct `repo_id` and `repo_type`.
If you are trying to access a private or gated repo, make sure you are authenticated.
Invalid username or password.

[tgaddair]

It's true that the token will show up in logs if provided in the request body, but not if it's inserted into the headers.