scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-16 23:41:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

test(router): run the fallback provider-408 cooldown regression inside an event loop

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
yassin 2026-09-15 20:26:46 +00:00
parent 5da497f4ac
commit 2f719fec52
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
tests/test_litellm/router_utils/test_fallback_event_handlers.py
View file

@ -984,7 +984,8 @@ class TestTriggerCooldownForFailedDeployment:
mock_set_cooldown.assert_not_called()
mock_increment.assert_not_called()
def test_still_cools_down_provider_408_before_caller_deadline(self):
@pytest.mark.asyncio
async def test_still_cools_down_provider_408_before_caller_deadline(self):
"""client_side_timeout only records that the caller configured a timeout. A 408
that comes back before that deadline was raised by the provider itself, so it is
a real health signal and must still cool the deployment down."""