instructor not working with litellm. AttributeError: 'dict' object has no attribute 'audio_tokens'

[brycedrennan]

Describe the bug
instructor doesn't work with litellm.

Traceback (most recent call last):
  File ".pyenv/versions/3.10.13/envs/job-listing-monitor-3.10.13/lib/python3.10/site-packages/instructor/retry.py", line 158, in retry_sync
    response = update_total_usage(
  File ".pyenv/versions/3.10.13/envs/job-listing-monitor-3.10.13/lib/python3.10/site-packages/instructor/utils.py", line 151, in update_total_usage
    ttd.audio_tokens = (ttd.audio_tokens or 0) + (rtd.audio_tokens or 0)
AttributeError: 'dict' object has no attribute 'audio_tokens'

model: gpt-4o-mini-2024-07-18
versions:

instructor==1.7.2
litellm==1.44.10
openai==1.60.2

To Reproduce

from litellm import completion
from pydantic import BaseModel
import instructor

class ChatClassification(BaseModel):
    relevant: bool
    message: str

client = instructor.from_litellm(completion)

resp = client.chat.completions.create(
    model="gpt-4o-mini-2024-07-18",
    messages=[{"role": "user", "content": "Is a secret answer relevant?"}],
    response_model=ChatClassification,
)

Expected behavior
The I can make llm calls without errors.

Hints
Looks like litellm doesn't fully convert the usage information to objects.
https://github.com/BerriAI/litellm/blob/c17342ac5bf0e9b281ffe2dbf6380411856eaf96/litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py#L511-L514

See also #1332

[villqrd]

Confirm - does not work with litellm. @brycedrennan have you found a work around or another router library that works with Instructor?
Best