rebase: adapt to vLLM v0.29 APIs

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

tests/entrypoints/openai_api/test_audio_format.py

@@ -248,7 +248,7 @@ class TestResolveAudioFormat:
         assert result == "pcm"
 
     def test_invalid_format_returns_error(self, serving_chat):
-        from vllm.entrypoints.openai.engine.protocol import ErrorResponse
+        from vllm.entrypoints.serve.engine.protocol import ErrorResponse
 
         request = self._make_request({"format": "aac", "voice": "alloy"})
         result = serving_chat._resolve_audio_format(request)
@@ -256,7 +256,7 @@ class TestResolveAudioFormat:
         assert "aac" in result.error.message
 
     def test_all_supported_formats_accepted(self, serving_chat):
-        from vllm.entrypoints.openai.engine.protocol import ErrorResponse
+        from vllm.entrypoints.serve.engine.protocol import ErrorResponse
 
         for fmt in SUPPORTED_CHAT_AUDIO_FORMATS:
             request = self._make_request({"format": fmt, "voice": "alloy"})

tests/entrypoints/openai_api/test_modality_validation.py

@@ -13,7 +13,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
-from vllm.entrypoints.openai.engine.protocol import ErrorResponse
+from vllm.entrypoints.serve.engine.protocol import ErrorResponse
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
 

tests/entrypoints/openai_api/test_serving_chat_metrics.py

@@ -19,7 +19,7 @@ pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
 
 def test_omni_chat_completion_response_metrics():
     """Test OmniChatCompletionResponse metrics field works correctly."""
-    from vllm.entrypoints.openai.engine.protocol import UsageInfo
+    from vllm.entrypoints.serve.engine.protocol import UsageInfo
 
     from vllm_omni.entrypoints.openai.protocol.chat_completion import (
         OmniChatCompletionResponse,

tests/entrypoints/openai_api/test_serving_speech.py

@@ -25,7 +25,7 @@ from fastapi.responses import JSONResponse
 from fastapi.testclient import TestClient
 from pydantic import ValidationError
 from pytest_mock import MockerFixture
-from vllm.entrypoints.openai.engine.protocol import ErrorInfo, ErrorResponse
+from vllm.entrypoints.serve.engine.protocol import ErrorInfo, ErrorResponse
 
 from vllm_omni.diffusion.request import OmniDiffusionRequest
 from vllm_omni.diffusion.sched.request_scheduler import RequestScheduler

tests/entrypoints/openai_api/test_video_stream_handler.py

@@ -281,7 +281,7 @@ class TestHandleQueryErrors:
     @pytest.mark.asyncio
     async def test_query_returns_error_response(self):
         """create_chat_completion returns ErrorResponse → error forwarded."""
-        from vllm.entrypoints.openai.engine.protocol import ErrorInfo, ErrorResponse
+        from vllm.entrypoints.serve.engine.protocol import ErrorInfo, ErrorResponse
 
         err = ErrorResponse(
             error=ErrorInfo(