scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-07 07:58:09 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 150

test(router): expect a primary stream's stall to cool its deployment (#50261)

Browse source 
The primary stream's mid-stream stall reaches failure_exits as a mapped litellm.Timeout (408), which cools the deployment on the Rust core. Keep that behavior and update the integration test that expected the Python core's exemption. Fallback hops stay exempt through is_stream_stall.
This commit is contained in:
Nate Armstrong 2026-11-05 16:06:59 -08:00 • committed by GitHub
parent 3f13c1ca34
commit 58896e2009
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
tests/integration/providers/test_hosted_vllm_stream_stall_wire.py
View file

@ -299,14 +299,14 @@ def cooldown_rig(tmp_path_factory: pytest.TempPathFactory) -> Iterator[_Cooldown
pytest.param("chat", _BRIDGED, "pause_after_content", id="chat-bridged-to-responses"),
),
)
def test_a_deployment_whose_stream_stalls_stays_out_of_cooldown(
def test_a_deployment_whose_stream_stalls_is_cooled_down(
cooldown_rig: _CooldownRig, endpoint: Endpoint, backend: str, shape: Shape
) -> None:
with _peer(shape) as wire, cooldown_rig.gateway.scenario() as scenario:
group, identity = _deployment(scenario, wire, backend)
response: Final = _streamed(cooldown_rig.gateway, endpoint, group)
error: Final = _failure_row(cooldown_rig.gateway, _ROWS, (group,))
assert not cooled(cooldown_rig.cache, identity), (error, response.text)
assert eventually(lambda: cooled(cooldown_rig.cache, identity), bool, _ROW_SECONDS), (error, response.text)
@_OWNED_PROXY