[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_duplex_handler.py

@@ -2156,12 +2156,12 @@ def test_direct_listen_decision_survives_inner_completion_metadata():
     )
     assert decision is not None
     output = attach_duplex_output_decision(
-        OmniRequestOutput(
+        OmniRequestOutput.from_stage_output(
+            inner_output,
             request_id="duplex-direct-listen",
             finished=True,
             stage_id=0,
             final_output_type=decision.final_output_type,
-            request_output=inner_output,
             metrics={
                 "stage_metrics": {
                     "0": {
@@ -3049,12 +3049,12 @@ async def test_minicpmo_auto_response_listen_without_response_does_not_defer_com
     )
     assert decision is not None
     listen_output = attach_duplex_output_decision(
-        OmniRequestOutput(
+        OmniRequestOutput.from_stage_output(
+            inner_output,
             request_id=request_id,
             finished=True,
             stage_id=0,
             final_output_type=decision.final_output_type,
-            request_output=inner_output,
         ),
         decision,
     )