[Refactor] Relocate chat completion and anthropic tests (#36919)

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

.buildkite/test_areas/entrypoints.yaml

@@ -34,7 +34,7 @@ steps:
   - tests/entrypoints/test_chat_utils
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/  --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
+  - pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/test_oot_registration.py --ignore=entrypoints/openai/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/  --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
   - pytest -v -s entrypoints/test_chat_utils.py
   mirror:
     amd:

.github/mergify.yml

@@ -334,7 +334,7 @@ pull_request_rules:
     - or:
       - files~=^tests/tool_use/
       - files~=^tests/entrypoints/openai/tool_parsers/
-      - files=tests/entrypoints/openai/test_chat_with_tool_reasoning.py
+      - files=tests/entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py
       - files~=^vllm/entrypoints/openai/tool_parsers/
       - files=docs/features/tool_calling.md
       - files~=^examples/tool_chat_*

tests/entrypoints/openai/chat_completion/test_chat.py

@@ -14,13 +14,12 @@ import requests
 import torch
 from openai import BadRequestError
 
+from tests.utils import RemoteOpenAIServer
 from vllm.entrypoints.openai.chat_completion.protocol import (
     ChatCompletionRequest,
 )
 from vllm.sampling_params import SamplingParams
 
-from ...utils import RemoteOpenAIServer
-
 # any model with a chat template should work here
 MODEL_NAME = "HuggingFaceH4/zephyr-7b-beta"
 

tests/entrypoints/openai/chat_completion/test_chat_echo.py

@@ -7,10 +7,9 @@ import openai  # use the official client for correctness check
 import pytest
 import pytest_asyncio
 
+from tests.utils import RemoteOpenAIServer
 from vllm.config import ModelConfig
 
-from ...utils import RemoteOpenAIServer
-
 # # any model with a chat template should work here
 MODEL_NAME = "Qwen/Qwen2-1.5B-Instruct"
 

tests/entrypoints/openai/chat_completion/test_chat_logit_bias_validation.py

@@ -5,10 +5,9 @@ import openai
 import pytest
 import pytest_asyncio
 
+from tests.utils import RemoteOpenAIServer
 from vllm.config import ModelConfig
 
-from ...utils import RemoteOpenAIServer
-
 MODEL_NAME = "Qwen/Qwen2.5-1.5B-Instruct"
 
 

tests/entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py

@@ -5,7 +5,7 @@ import openai  # use the official client for correctness check
 import pytest
 import pytest_asyncio
 
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 # a reasoning and tool calling model
 MODEL_NAME = "Qwen/QwQ-32B"

tests/entrypoints/openai/chat_completion/test_completion_with_function_calling.py

@@ -10,7 +10,7 @@ import pytest
 import pytest_asyncio
 
 # downloading lora to test lora requests
-from ...utils import ROCM_ENV_OVERRIDES, ROCM_EXTRA_ARGS, RemoteOpenAIServer
+from tests.utils import ROCM_ENV_OVERRIDES, ROCM_EXTRA_ARGS, RemoteOpenAIServer
 
 # any model with a chat template should work here
 MODEL_NAME = "Qwen/Qwen3-0.6B"

tests/entrypoints/openai/chat_completion/test_enable_force_include_usage.py

@@ -4,7 +4,7 @@ import openai
 import pytest
 import pytest_asyncio
 
-from ...utils import RemoteOpenAIServer
+from tests.utils import RemoteOpenAIServer
 
 
 @pytest.fixture(scope="module")

tests/entrypoints/openai/chat_completion/test_serving_chat.py

@@ -10,6 +10,12 @@ import pytest
 import pytest_asyncio
 from openai import OpenAI
 
+from tests.entrypoints.openai.utils import (
+    accumulate_streaming_response,
+    verify_chat_response,
+    verify_harmony_messages,
+)
+from tests.utils import RemoteOpenAIServer
 from vllm._aiter_ops import is_aiter_found_and_supported
 from vllm.config import MultiModalConfig
 from vllm.entrypoints.openai.chat_completion.protocol import (
@@ -39,13 +45,6 @@ from vllm.tokenizers.registry import tokenizer_args_from_config
 from vllm.tool_parsers import ToolParserManager
 from vllm.v1.engine.async_llm import AsyncLLM
 
-from ...utils import RemoteOpenAIServer
-from .utils import (
-    accumulate_streaming_response,
-    verify_chat_response,
-    verify_harmony_messages,
-)
-
 GPT_OSS_MODEL_NAME = "openai/gpt-oss-20b"
 GPT_OSS_SPECULATOR_NAME = "RedHatAI/gpt-oss-20b-speculator.eagle3"