phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Litellm dev 01 27 2025 p3 (#8047)

Browse source 
* docs(reliability.md): add doc on disabling fallbacks per request

* feat(litellm_pre_call_utils.py): support reading request timeout from request headers - new `x-litellm-timeout` param

Allows setting dynamic model timeouts from vercel's AI sdk

* test(test_proxy_server.py): add simple unit test for reading request timeout

* test(test_fallbacks.py): add e2e test to confirm timeout passed in request headers is correctly read

* feat(main.py): support passing metadata to openai in preview

Resolves https://github.com/BerriAI/litellm/issues/6022#issuecomment-2616119371

* fix(main.py): fix passing openai metadata

* docs(request_headers.md): document new request headers

* build: Merge branch 'main' into litellm_dev_01_27_2025_p3

* test: loosen test
This commit is contained in:
Krish Dholakia 2025-01-28 18:01:27 -08:00 • committed by GitHub
parent 9c20c69915
commit d9eb8f42ff
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 187 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

34
tests/local_testing/test_completion.py
View file

@ -4582,3 +4582,37 @@ def test_provider_specific_header(custom_llm_provider, expected_result):
mock_post.assert_called_once()
print(mock_post.call_args.kwargs["headers"])
assert "anthropic-beta" in mock_post.call_args.kwargs["headers"]
@pytest.mark.parametrize(
"enable_preview_features",
[True, False],
)
def test_completion_openai_metadata(monkeypatch, enable_preview_features):
from openai import OpenAI
client = OpenAI()
litellm.set_verbose = True
monkeypatch.setattr(litellm, "enable_preview_features", enable_preview_features)
with patch.object(
client.chat.completions.with_raw_response, "create", return_value=MagicMock()
) as mock_completion:
try:
resp = litellm.completion(
model="openai/gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello world"}],
metadata={"my-test-key": "my-test-value"},
client=client,
)
except Exception as e:
print(f"Error: {e}")
mock_completion.assert_called_once()
if enable_preview_features:
assert mock_completion.call_args.kwargs["metadata"] == {
"my-test-key": "my-test-value"
}
else:
assert "metadata" not in mock_completion.call_args.kwargs