mirror of
https://github.com/BerriAI/litellm.git
synced 2026-08-28 05:25:59 +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
105 lines
3.5 KiB
Python
105 lines
3.5 KiB
Python
import asyncio
|
|
import os
|
|
import time
|
|
import traceback
|
|
|
|
import pytest
|
|
|
|
|
|
import logging
|
|
|
|
import litellm
|
|
from litellm import Router
|
|
|
|
# this tests debug logs from litellm router and litellm proxy server
|
|
from litellm._logging import verbose_logger, verbose_proxy_logger, verbose_router_logger
|
|
from litellm.llms.custom_httpx.async_client_cleanup import close_litellm_async_clients
|
|
|
|
|
|
# this tests debug logs from litellm router and litellm proxy server
|
|
def test_async_fallbacks(caplog):
|
|
# THIS IS A PROD TEST - DO NOT DELETE THIS. Used for testing if litellm proxy verbose logs are human readable
|
|
litellm.set_verbose = False
|
|
litellm.success_callback = []
|
|
litellm.failure_callback = []
|
|
verbose_router_logger.setLevel(level=logging.INFO)
|
|
verbose_logger.setLevel(logging.CRITICAL + 1)
|
|
verbose_proxy_logger.setLevel(logging.CRITICAL + 1)
|
|
model_list = [
|
|
{
|
|
"model_name": "azure/gpt-3.5-turbo",
|
|
"litellm_params": {
|
|
"model": "azure/gpt-4.1-mini",
|
|
"api_key": os.getenv("AZURE_AI_API_KEY"),
|
|
"api_version": os.getenv("AZURE_API_VERSION"),
|
|
"api_base": os.getenv("AZURE_AI_API_BASE"),
|
|
"mock_response": "Hello world",
|
|
},
|
|
"tpm": 240000,
|
|
"rpm": 1800,
|
|
},
|
|
{
|
|
"model_name": "gpt-3.5-turbo",
|
|
"litellm_params": {
|
|
"model": "gpt-3.5-turbo",
|
|
"api_key": "bad-key",
|
|
},
|
|
"tpm": 1000000,
|
|
"rpm": 9000,
|
|
},
|
|
]
|
|
|
|
router = Router(
|
|
model_list=model_list,
|
|
fallbacks=[{"gpt-3.5-turbo": ["azure/gpt-3.5-turbo"]}],
|
|
num_retries=1,
|
|
)
|
|
|
|
user_message = "Hello, how are you?"
|
|
messages = [{"content": user_message, "role": "user"}]
|
|
|
|
async def _make_request():
|
|
try:
|
|
await router.acompletion(
|
|
model="gpt-3.5-turbo", messages=messages, max_tokens=1
|
|
)
|
|
router.reset()
|
|
except litellm.Timeout:
|
|
pass
|
|
except Exception as e:
|
|
pytest.fail(f"An exception occurred: {e}")
|
|
finally:
|
|
router.reset()
|
|
# Close cached aiohttp/httpx clients before the event loop ends
|
|
# to prevent "Unclosed client session" / "Unclosed connector" warnings.
|
|
await close_litellm_async_clients()
|
|
|
|
asyncio.run(_make_request())
|
|
captured_logs = [rec.message for rec in caplog.records]
|
|
|
|
# on circle ci the captured logs get async cleanup noise from the gc (leaked
|
|
# task warnings, plus aiohttp "Unclosed client session"/"Unclosed connector"
|
|
# warnings from cached clients other router tests evicted) - filter it out
|
|
captured_logs = [
|
|
log
|
|
for log in captured_logs
|
|
if "Task exception was never retrieved" not in log
|
|
and "Task was destroyed but it is pending" not in log
|
|
and "get_available_deployment" not in log
|
|
and "in the Langfuse queue" not in log
|
|
and "Unclosed client session" not in log
|
|
and "Unclosed connector" not in log
|
|
]
|
|
|
|
print("\n Captured caplog records - ", captured_logs)
|
|
|
|
# Define the expected log messages
|
|
# - error request, falling back notice, success notice
|
|
expected_logs = [
|
|
"Falling back to model_group = azure/gpt-3.5-turbo",
|
|
"litellm.acompletion(model=azure/gpt-4.1-mini)\x1b[32m 200 OK\x1b[0m",
|
|
"Successful fallback b/w models.",
|
|
]
|
|
|
|
# Assert that the captured logs match the expected log messages
|
|
assert captured_logs[-3:] == expected_logs
|