[openai api] log exception in exception handler (1/N) (#31164)

Signed-off-by: Andy Xie <andy.xning@gmail.com>

tests/entrypoints/openai/responses/test_errors.py

@@ -6,7 +6,6 @@ from unittest.mock import MagicMock
 
 import pytest
 
-from vllm.entrypoints.openai.engine.protocol import ErrorResponse
 from vllm.entrypoints.openai.engine.serving import GenerationError, OpenAIServing
 
 
@@ -38,32 +37,6 @@ async def test_raise_if_error_raises_generation_error():
     serving._raise_if_error(None, "test-request-id")  # should not raise
 
 
-@pytest.mark.asyncio
-async def test_convert_generation_error_to_response():
-    """test _convert_generation_error_to_response creates proper ErrorResponse"""
-    mock_engine = MagicMock()
-    mock_engine.model_config = MagicMock()
-    mock_engine.model_config.max_model_len = 100
-    mock_models = MagicMock()
-
-    serving = OpenAIServing(
-        engine_client=mock_engine,
-        models=mock_models,
-        request_logger=None,
-    )
-
-    # create a GenerationError
-    gen_error = GenerationError("Internal server error")
-
-    # convert to ErrorResponse
-    error_response = serving._convert_generation_error_to_response(gen_error)
-
-    assert isinstance(error_response, ErrorResponse)
-    assert error_response.error.type == "InternalServerError"
-    assert error_response.error.message == "Internal server error"
-    assert error_response.error.code == HTTPStatus.INTERNAL_SERVER_ERROR
-
-
 @pytest.mark.asyncio
 async def test_convert_generation_error_to_streaming_response():
     """test _convert_generation_error_to_streaming_response output"""

tests/entrypoints/openai/responses/test_harmony.py

@@ -13,7 +13,7 @@ from typing import Any
 import pytest
 import pytest_asyncio
 import requests
-from openai import BadRequestError, NotFoundError, OpenAI
+from openai import InternalServerError, NotFoundError, OpenAI
 from openai_harmony import Message
 
 from ....utils import RemoteOpenAIServer
@@ -698,7 +698,7 @@ async def test_function_calling_multi_turn(client: OpenAI, model_name: str):
 async def test_function_calling_required(client: OpenAI, model_name: str):
     tools = [GET_WEATHER_SCHEMA]
 
-    with pytest.raises(BadRequestError):
+    with pytest.raises(InternalServerError):
         await client.responses.create(
             model=model_name,
             input="What's the weather like in Paris today?",