scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-19 00:01:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 88

test: pin the post-#41289 cooldown contract and scroll the auto-router select spec

Browse source 
test_router_fallbacks_with_cooldowns_and_dynamic_credentials expected a
caller-supplied credential to register its own deployment and cool it down.
#41289 stopped registering it, so cooldown logic skips that id and the
assertion can never hold. The test now asserts what the router guarantees
today: a 429 to a forwarded credential cools down none of the shared
deployments, the next credential is still served, and a 429 owned by a shared
deployment still cools it down. The final live OpenAI call becomes a mock

The auto-router template spec assumed the Add Auto Router form left room
below the Template select at 1280x900. #41315 added classifier fields above
it, so the options opened upward. The spec now scrolls the trigger to the top
of the dialog and asserts it sits in the upper half before checking placement
This commit is contained in:
Yuneng Jiang 2026-09-16 20:52:19 -07:00
parent 02ced74540
commit c6023b4eec
No known key found for this signature in database
2 changed files with 23 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
tests/e2e/ui/tests/modelsPage/autoRouterTemplateSelect.spec.ts
View file

@ -47,9 +47,11 @@ test.describe("Auto Router template select anchoring", () => {
test.use({ storageState: ADMIN_STORAGE_PATH });
test("opens the options below the trigger when there is room below it", async ({ page }) => {
await page.setViewportSize({ width: 1280, height: 900 });
const viewport = { width: 1280, height: 900 };
await page.setViewportSize(viewport);
const trigger = await openTemplateSelect(page);
await trigger.scrollIntoViewIfNeeded();
await trigger.evaluate((element) => element.scrollIntoView({ block: "start" }));
await expect.poll(async () => (await trigger.boundingBox())?.y).toBeLessThan(viewport.height / 2);
await trigger.click();
await expect(page.getByRole("listbox")).toBeVisible();

45
tests/local_testing/test_router_cooldown_handlers.py
View file

@ -833,45 +833,38 @@ def test_router_fallbacks_with_cooldowns_and_model_id():
@pytest.mark.asyncio()
async def test_router_fallbacks_with_cooldowns_and_dynamic_credentials():
"""
Ensure cooldown on credential 1 does not affect credential 2
A 429 answered to a caller-supplied credential cools down none of the shared deployments,
so the next credential still reaches them, while a 429 owned by a shared deployment does
"""
from litellm.router_utils.cooldown_handlers import _async_get_cooldown_deployments
litellm._turn_on_debug()
router = Router(
model_list=[
{
"model_name": "gpt-3.5-turbo",
"litellm_params": {"model": "gpt-3.5-turbo", "rpm": 1},
"model_info": {
"id": "123",
},
"litellm_params": {"model": "gpt-3.5-turbo"},
"model_info": {"id": deployment_id},
}
]
for deployment_id in ("123", "456")
],
num_retries=0,
)
messages = [{"role": "user", "content": "hi"}]
## trigger ratelimit
try:
with pytest.raises(litellm.RateLimitError):
await router.acompletion(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "hi"}],
api_key="my-bad-key-1",
mock_response="litellm.RateLimitError",
model="gpt-3.5-turbo", messages=messages, api_key="my-bad-key-1", mock_response="litellm.RateLimitError"
)
pytest.fail("Expected RateLimitError")
except litellm.RateLimitError:
pass
await asyncio.sleep(1)
assert await _async_get_cooldown_deployments(litellm_router_instance=router, parent_otel_span=None) == []
cooldown_list = await _async_get_cooldown_deployments(
litellm_router_instance=router, parent_otel_span=None
response = await router.acompletion(
model="gpt-3.5-turbo", messages=messages, api_key="my-good-key-2", mock_response="served with credential 2"
)
print("cooldown_list: ", cooldown_list)
assert len(cooldown_list) == 1
assert response.choices[0].message.content == "served with credential 2"
await router.acompletion(
model="gpt-3.5-turbo",
api_key=os.getenv("OPENAI_API_KEY"),
messages=[{"role": "user", "content": "hi"}],
)
with pytest.raises(litellm.RateLimitError):
await router.acompletion(model="gpt-3.5-turbo", messages=messages, mock_response="litellm.RateLimitError")
await asyncio.sleep(1)
cooled_down = await _async_get_cooldown_deployments(litellm_router_instance=router, parent_otel_span=None)
assert len(cooled_down) == 1 and cooled_down[0] in {"123", "456"}