mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-09 22:31:41 +00:00
6a0d03914c
* test: drop the cwd-relative sys.path.insert calls from the test suite
TQ003 stands at 1,077 across 1,058 files, and 1,015 of them are the same shape:
sys.path.insert(0, os.path.abspath("../..")) and its deeper siblings. The
argument resolves against the working directory rather than the file, so from
the repo root, where every job runs pytest, it inserts the directory two levels
above the checkout. It has never pointed at litellm. The package is installed
into the environment anyway, which is what actually makes the import work, and
what the rule's message has said all along.
Removing them leaves 1,634 imports of sys and os with no remaining reference,
and those go too, except where another test module imports the name back out of
the file. The rest of TQ003 is 62 call sites that resolve against __file__ or a
variable, which are a different question and are left alone.
Collection is identical either way: 45,871 tests and the same 51 pre-existing
collection errors before and after, and ruff reports no new undefined name.
* test: drop the duplicate imports the sys.path sweep exposed to F811
* test(pre-call-utils): restore the os import the new bedrock tests need
85 lines
2.7 KiB
Python
85 lines
2.7 KiB
Python
"""
|
|
Regression: Responses API router must register cooldowns on deployment
|
|
failures. Previously the Responses API path built ``litellm_params`` without
|
|
``model_info``, so ``Router.deployment_callback_on_failure`` exited early via
|
|
the "No model_info found" branch and the failing deployment was never added
|
|
to the cooldown set.
|
|
"""
|
|
|
|
from unittest.mock import AsyncMock, patch
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
|
|
import litellm
|
|
from litellm.router_utils.cooldown_handlers import _async_get_cooldown_deployments
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_responses_api_rate_limit_marks_deployment_for_cooldown():
|
|
failing_deployment_id = "deployment-rate-limited"
|
|
|
|
router = litellm.Router(
|
|
model_list=[
|
|
{
|
|
"model_name": "openai.gpt-5.1-codex",
|
|
"litellm_params": {
|
|
"model": "openai/gpt-5.1-codex",
|
|
"api_key": "mock-api-key-1",
|
|
},
|
|
"model_info": {"id": failing_deployment_id},
|
|
},
|
|
{
|
|
"model_name": "openai.gpt-5.1-codex",
|
|
"litellm_params": {
|
|
"model": "openai/gpt-5.1-codex",
|
|
"api_key": "mock-api-key-2",
|
|
},
|
|
"model_info": {"id": "deployment-healthy"},
|
|
},
|
|
],
|
|
num_retries=0,
|
|
cooldown_time=60,
|
|
)
|
|
|
|
rate_limit_error = litellm.RateLimitError(
|
|
message="upstream throttled",
|
|
llm_provider="openai",
|
|
model="openai/gpt-5.1-codex",
|
|
response=httpx.Response(
|
|
status_code=429,
|
|
request=httpx.Request("POST", "https://api.openai.com/v1/responses"),
|
|
),
|
|
)
|
|
|
|
def pin_to_failing_deployment(seq):
|
|
for d in seq:
|
|
if d["model_info"]["id"] == failing_deployment_id:
|
|
return d
|
|
return seq[0]
|
|
|
|
with (
|
|
patch(
|
|
"litellm.llms.custom_httpx.llm_http_handler.BaseLLMHTTPHandler.async_response_api_handler",
|
|
new_callable=AsyncMock,
|
|
side_effect=rate_limit_error,
|
|
),
|
|
patch(
|
|
"litellm.router_strategy.simple_shuffle.random.choice",
|
|
side_effect=pin_to_failing_deployment,
|
|
),
|
|
):
|
|
with pytest.raises(litellm.RateLimitError):
|
|
await router.aresponses(
|
|
model="openai.gpt-5.1-codex",
|
|
input="hi",
|
|
)
|
|
|
|
cooldown_ids = await _async_get_cooldown_deployments(
|
|
litellm_router_instance=router, parent_otel_span=None
|
|
)
|
|
assert failing_deployment_id in cooldown_ids, (
|
|
f"Responses API failure callback did not register cooldown for "
|
|
f"{failing_deployment_id!r}; cooldown set was {cooldown_ids}"
|
|
)
|