litellm/tests/local_testing/test_azure_openai.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

102 lines
3 KiB
Python

import json
import os
import traceback
from dotenv import load_dotenv
load_dotenv()
import io
from datetime import datetime
from unittest.mock import AsyncMock, MagicMock, patch
import httpx
import pytest
from openai import OpenAI
from openai.types.chat import ChatCompletionMessage
from openai.types.chat.chat_completion import ChatCompletion, Choice
from respx import MockRouter
import litellm
from litellm import RateLimitError, Timeout, completion, completion_cost, embedding
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
from litellm.litellm_core_utils.prompt_templates.factory import anthropic_messages_pt
from litellm.router import Router
@pytest.mark.asyncio()
@pytest.mark.respx()
async def test_aaaaazure_tenant_id_auth(respx_mock: MockRouter):
"""
Tests when we set tenant_id, client_id, client_secret they don't get sent with the request
PROD Test
"""
litellm.disable_aiohttp_transport = (
True # since this uses respx, we need to set use_aiohttp_transport to False
)
# Clear the HTTP client cache to ensure respx mocking works
# This is critical because respx only intercepts clients created AFTER mocking is active
if hasattr(litellm, "in_memory_llm_clients_cache"):
litellm.in_memory_llm_clients_cache.flush_cache()
router = Router(
model_list=[
{
"model_name": "gpt-3.5-turbo",
"litellm_params": { # params for litellm completion/embedding call
"model": "azure/gpt-4.1-mini",
"api_base": os.getenv("AZURE_AI_API_BASE"),
"tenant_id": os.getenv("AZURE_TENANT_ID"),
"client_id": os.getenv("AZURE_CLIENT_ID"),
"client_secret": os.getenv("AZURE_CLIENT_SECRET"),
},
},
],
)
mock_response = AsyncMock()
obj = ChatCompletion(
id="foo",
model="gpt-4",
object="chat.completion",
choices=[
Choice(
finish_reason="stop",
index=0,
message=ChatCompletionMessage(
content="Hello world!",
role="assistant",
),
)
],
created=int(datetime.now().timestamp()),
)
litellm.set_verbose = True
mock_request = respx_mock.post(url__regex=r".*/chat/completions.*").mock(
return_value=httpx.Response(200, json=obj.model_dump(mode="json"))
)
await router.acompletion(
model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world!"}]
)
# Ensure all mocks were called
respx_mock.assert_all_called()
for call in mock_request.calls:
print(call)
print(call.request.content)
json_body = json.loads(call.request.content)
print(json_body)
assert json_body == {
"messages": [{"role": "user", "content": "Hello world!"}],
"model": "gpt-4.1-mini",
"stream": False,
}