# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-10-08 13:23:21 -07:00
parent 96886afaca
commit 1e891489a8
13 changed files with 170 additions and 4 deletions

View file

@ -186,3 +186,47 @@ async def test_openai_chat_completion_is_async(vllm_inference_adapter):
assert mock_create_client.call_count == 4 # no cheating
assert total_time < (sleep_time * 2), f"Total time taken: {total_time}s exceeded expected max"
async def test_extra_body_forwarding(vllm_inference_adapter):
"""
Test that extra_body parameters (e.g., chat_template_kwargs) are correctly
forwarded to the underlying OpenAI client.
"""
mock_model = Model(identifier="mock-model", provider_resource_id="mock-model", provider_id="vllm-inference")
vllm_inference_adapter.model_store.get_model.return_value = mock_model
with patch.object(VLLMInferenceAdapter, "client", new_callable=PropertyMock) as mock_client_property:
mock_client = MagicMock()
mock_client.chat.completions.create = AsyncMock(
return_value=OpenAIChatCompletion(
id="chatcmpl-abc123",
created=1,
model="mock-model",
choices=[
OpenAIChoice(
message=OpenAIAssistantMessageParam(
content="test response",
),
finish_reason="stop",
index=0,
)
],
)
)
mock_client_property.return_value = mock_client
# Test with chat_template_kwargs for Granite thinking mode
await vllm_inference_adapter.openai_chat_completion(
"mock-model",
messages=[],
stream=False,
chat_template_kwargs={"thinking": True},
)
# Verify that the client was called with extra_body containing chat_template_kwargs
mock_client.chat.completions.create.assert_called_once()
call_kwargs = mock_client.chat.completions.create.call_args.kwargs
assert "extra_body" in call_kwargs
assert "chat_template_kwargs" in call_kwargs["extra_body"]
assert call_kwargs["extra_body"]["chat_template_kwargs"] == {"thinking": True}