LiteLLM Minor Fixes & Improvements (12/27/2024) - p1 (#7448)

* feat(main.py): mock_response() - support 'litellm.ContextWindowExceededError' in mock response

enabled quicker router/fallback/proxy debug on context window errors

* feat(exception_mapping_utils.py): extract special litellm errors from error str if calling `litellm_proxy/` as provider

Closes https://github.com/BerriAI/litellm/issues/7259

* fix(user_api_key_auth.py): specify 'Received Proxy Server Request' is span kind server

Closes https://github.com/BerriAI/litellm/issues/7298
This commit is contained in:
Krish Dholakia 2024-12-27 19:04:39 -08:00 committed by GitHub
parent cca9cfe667
commit 67b39bacf7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 83 additions and 5 deletions

View file

@ -1189,3 +1189,19 @@ def test_exceptions_base_class():
assert isinstance(e, litellm.RateLimitError)
assert e.code == "429"
assert e.type == "throttling_error"
def test_context_window_exceeded_error_from_litellm_proxy():
from httpx import Response
from litellm.litellm_core_utils.exception_mapping_utils import (
extract_and_raise_litellm_exception,
)
args = {
"response": Response(status_code=400, text="Bad Request"),
"error_str": "Error code: 400 - {'error': {'message': \"litellm.ContextWindowExceededError: litellm.BadRequestError: this is a mock context window exceeded error\\nmodel=gpt-3.5-turbo. context_window_fallbacks=None. fallbacks=None.\\n\\nSet 'context_window_fallback' - https://docs.litellm.ai/docs/routing#fallbacks\\nReceived Model Group=gpt-3.5-turbo\\nAvailable Model Group Fallbacks=None\", 'type': None, 'param': None, 'code': '400'}}",
"model": "gpt-3.5-turbo",
"custom_llm_provider": "litellm_proxy",
}
with pytest.raises(litellm.ContextWindowExceededError):
extract_and_raise_litellm_exception(**args)