[Bug]: fix streaming cached response logging

[krrishdholakia]

What happened?

The streamed cache response yields an async generator. This causes logging to fail as the response is not of the required type (ModelResponse, EmbeddingResponse, ImageResponse)

Relevant log output

2024-02-19 16:57:18 LiteLLM.LoggingError: [Non-Blocking] Exception occurred while success logging Traceback (most recent call last):
2024-02-19 16:57:18   File "/usr/local/lib/python3.9/site-packages/litellm/utils.py", line 1145, in success_handler
2024-02-19 16:57:18     result.choices[0].finish_reason is not None
2024-02-19 16:57:18 AttributeError: 'async_generator' object has no attribute 'choices'

Twitter / LinkedIn details

No response