litellm/tests/local_testing/test_acompletion_fallbacks.py
yuneng-jiang 6a0d03914c
test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)
* 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
2026-08-22 09:25:58 -07:00

98 lines
2.9 KiB
Python

import asyncio
import os
import time
import traceback
import pytest
import concurrent
from dotenv import load_dotenv
import litellm
@pytest.mark.asyncio
async def test_acompletion_fallbacks_basic():
response = await litellm.acompletion(
model="openai/unknown-model",
messages=[{"role": "user", "content": "Hello, world!"}],
fallbacks=["openai/gpt-4o-mini"],
)
print(response)
assert response is not None
@pytest.mark.asyncio
async def test_acompletion_fallbacks_bad_models():
"""
Test that the acompletion call times out after 10 seconds - if no fallbacks work
"""
try:
# Wrap the acompletion call with asyncio.wait_for to enforce a timeout
response = await asyncio.wait_for(
litellm.acompletion(
model="openai/unknown-model",
messages=[{"role": "user", "content": "Hello, world!"}],
fallbacks=["openai/bad-model", "openai/unknown-model"],
),
timeout=5.0, # Timeout after 5 seconds
)
assert response is not None
except asyncio.TimeoutError:
pytest.fail("Test timed out - possible infinite loop in fallbacks")
except Exception as e:
print(e)
pass
@pytest.mark.asyncio
async def test_acompletion_fallbacks_with_dict_config():
"""
Test fallbacks with dictionary configuration that includes model-specific settings
"""
response = await litellm.acompletion(
model="openai/gpt-4o-mini",
messages=[{"role": "user", "content": "Hello, world!"}],
api_key="very-bad-api-key",
fallbacks=[{"api_key": os.getenv("OPENAI_API_KEY")}],
)
assert response is not None
@pytest.mark.asyncio
async def test_acompletion_fallbacks_empty_list():
"""
Test behavior when fallbacks list is empty
"""
with pytest.raises(litellm.NotFoundError) as exc_info:
response = await litellm.acompletion(
model="openai/unknown-model",
messages=[{"role": "user", "content": "Hello, world!"}],
fallbacks=[],
)
e = exc_info.value
assert isinstance(e, litellm.NotFoundError)
@pytest.mark.asyncio
async def test_acompletion_fallbacks_none_response():
"""
Test handling when a fallback model returns None
Should continue to next fallback rather than returning None
"""
response = await litellm.acompletion(
model="openai/unknown-model",
messages=[{"role": "user", "content": "Hello, world!"}],
fallbacks=["gpt-3.5-turbo"], # replace with a model you know works
)
assert response is not None
async def test_completion_fallbacks_sync():
response = litellm.completion(
model="openai/unknown-model",
messages=[{"role": "user", "content": "Hello, world!"}],
fallbacks=["openai/gpt-4o-mini"],
)
print(response)
assert response is not None