[Refactor][OutputProcessor 2/8]: OmniRequestOutput should inherit RequestOutput and no nested wrap-up (#5146)

Signed-off-by: Boao Shi <aoibosh@connect.hku.hk>
Signed-off-by: bowieshi <aoibosh@connect.hku.hk>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: R2-Y <ruiruyang2@gmail.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Signed-off-by: Shi Boao Bowie <aoibosh@connect.hku.hk>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: ruirui(rein) yang <73573651+R2-Y@users.noreply.github.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

tests/entrypoints/openai_api/test_serving_video_stream.py

@@ -47,7 +47,7 @@ def _text_result(text: str) -> OmniRequestOutput:
     output.text = text
     request_output = RequestOutput()
     request_output.outputs = [output]
-    return OmniRequestOutput(final_output_type="text", request_output=request_output)
+    return OmniRequestOutput.from_stage_output(request_output, final_output_type="text")
 
 
 def _audio_result(audio_data: Any) -> OmniRequestOutput:
@@ -61,7 +61,7 @@ def _audio_result(audio_data: Any) -> OmniRequestOutput:
     output.multimodal_output = {"audio": audio_data}
     request_output = RequestOutput()
     request_output.outputs = [output]
-    return OmniRequestOutput(final_output_type="audio", request_output=request_output)
+    return OmniRequestOutput.from_stage_output(request_output, final_output_type="audio")
 
 
 class MockWebSocket: