[Refactor] Relocate responses API tests (#37241)

Signed-off-by: sfeng33 <4florafeng@gmail.com>

tests/entrypoints/openai/responses/conftest.py

@@ -8,6 +8,9 @@ from collections.abc import Callable
 from typing import Any
 
 import pytest
+import pytest_asyncio
+
+from tests.utils import RemoteOpenAIServer
 
 logger = logging.getLogger(__name__)
 
@@ -361,3 +364,38 @@ def log_response_diagnostics(
     )
 
     return diagnostics
+
+
+@pytest.fixture(scope="module")
+def default_server_args():
+    return [
+        "--max-model-len",
+        "8192",
+        "--enforce-eager",  # For faster startup.
+        "--enable-auto-tool-choice",
+        "--structured-outputs-config.backend",
+        "xgrammar",
+        "--tool-call-parser",
+        "hermes",
+        "--reasoning-parser",
+        "qwen3",
+    ]
+
+
+@pytest.fixture(scope="module")
+def server_with_store(default_server_args):
+    with RemoteOpenAIServer(
+        "Qwen/Qwen3-1.7B",
+        default_server_args,
+        env_dict={
+            "VLLM_ENABLE_RESPONSES_API_STORE": "1",
+            "VLLM_SERVER_DEV_MODE": "1",
+        },
+    ) as remote_server:
+        yield remote_server
+
+
+@pytest_asyncio.fixture
+async def client(server_with_store):
+    async with server_with_store.get_async_client() as async_client:
+        yield async_client

tests/entrypoints/openai/responses/test_harmony.py

@@ -16,7 +16,8 @@ import requests
 from openai import InternalServerError, NotFoundError, OpenAI
 from openai_harmony import Message
 
-from ....utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
+
 from .conftest import (
     BASE_TEST_ENV,
     events_contain_type,

tests/entrypoints/openai/responses/test_mcp_tools.py

@@ -9,9 +9,9 @@ import pytest_asyncio
 from openai import OpenAI
 from openai_harmony import ToolDescription, ToolNamespaceConfig
 
+from tests.utils import RemoteOpenAIServer
 from vllm.entrypoints.mcp.tool_server import MCPToolServer
 
-from ....utils import RemoteOpenAIServer
 from .conftest import (
     BASE_TEST_ENV,
     events_contain_type,

tests/entrypoints/openai/responses/test_parsable_context.py

@@ -9,7 +9,8 @@ import pytest
 import pytest_asyncio
 from openai import OpenAI
 
-from ....utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
+
 from .conftest import (
     BASE_TEST_ENV,
     has_output_type,

tests/entrypoints/openai/responses/test_simple.py

@@ -5,7 +5,8 @@ import pytest
 import pytest_asyncio
 from openai import OpenAI
 
-from ....utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
+
 from .conftest import validate_streaming_event_stack
 
 MODEL_NAME = "Qwen/Qwen3-8B"

tests/v1/entrypoints/openai/serving_responses/conftest.py

-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-import pytest
-import pytest_asyncio
-
-from tests.utils import RemoteOpenAIServer
-
-# Use a small reasoning model to test the responses API.
-MODEL_NAME = "Qwen/Qwen3-1.7B"
-
-
-@pytest.fixture(scope="module")
-def default_server_args():
-    return [
-        "--max-model-len",
-        "8192",
-        "--enforce-eager",  # For faster startup.
-        "--enable-auto-tool-choice",
-        "--structured-outputs-config.backend",
-        "xgrammar",
-        "--tool-call-parser",
-        "hermes",
-        "--reasoning-parser",
-        "qwen3",
-    ]
-
-
-@pytest.fixture(scope="module")
-def server_with_store(default_server_args):
-    with RemoteOpenAIServer(
-        MODEL_NAME,
-        default_server_args,
-        env_dict={
-            "VLLM_ENABLE_RESPONSES_API_STORE": "1",
-            "VLLM_SERVER_DEV_MODE": "1",
-        },
-    ) as remote_server:
-        yield remote_server
-
-
-@pytest_asyncio.fixture
-async def client(server_with_store):
-    async with server_with_store.get_async_client() as async_client:
-        yield async_client