[BugFix] Fix leftovers of the legacy OpenAI realtime API event names (#7426)

Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Codex <noreply@openai.com>

tests/entrypoints/openai_api/test_duplex_handler.py

@@ -2197,9 +2197,7 @@ def test_native_realtime_protocol_audio_delta_preserves_sample_rate_hz():
     )
 
     audio_events = [
-        payload
-        for payload in payloads
-        if payload["type"] in {"response.output_audio.delta", "response.output_audio.delta"}
+        payload for payload in payloads if payload["type"] in {"response.output_audio.delta", "response.audio.delta"}
     ]
     assert {payload["type"] for payload in audio_events} == {"response.output_audio.delta"}
     assert {payload["format"] for payload in audio_events} == {"pcm16"}

tests/entrypoints/openai_api/test_qwen3_omni_realtime_websocket.py

@@ -175,7 +175,7 @@ async def _run_realtime_audio_roundtrip(
             if event_type == "session.created":
                 continue
 
-            if event_type == "response.audio.delta":
+            if event_type == "response.output_audio.delta":
                 delta_events += 1
                 sr = event.get("sample_rate_hz")
                 if isinstance(sr, int) and sr > 0:
@@ -195,7 +195,7 @@ async def _run_realtime_audio_roundtrip(
                 final_text = event.get("text", "") or "".join(text_chunks)
                 continue
 
-            if event_type == "response.audio.done":
+            if event_type == "response.output_audio.done":
                 break
 
             if event_type == "error":
@@ -315,7 +315,7 @@ def _server_vad_pcm16_input() -> bytes:
 def _assert_realtime_smoke(result: dict) -> None:
     out_pcm = result["output_pcm"]
     assert result["delta_events"] >= 1
-    assert out_pcm, "No output PCM from response.audio.delta"
+    assert out_pcm, "No output PCM from response.output_audio.delta"
     assert len(out_pcm) % 2 == 0
     assert len(out_pcm) >= 4096, "Output audio unexpectedly small"
     assert result["output_sample_rate"] > 0
@@ -388,7 +388,7 @@ class TestQwen3OmniRealtimeWebSocket:
     @hardware_test(res={"cuda": "H100", "rocm": "MI325"}, num_cards=2)
     @pytest.mark.parametrize("omni_server", realtime_async_chunk_server_params, indirect=True)
     def test_long_audio_response_completes_async_chunk(self, omni_server) -> None:
-        """Regression for #6474: long async-chunk audio must emit response.audio.done."""
+        """Regression for #6474: long async-chunk audio must emit response.output_audio.done."""
         issue_6474_pcm16 = _synthetic_pcm16_input(
             phrase_text=ISSUE_6474_SYNTH_PHRASE_TEXT,
         )
@@ -450,8 +450,8 @@ class TestQwen3OmniRealtimeWebSocket:
             "input_audio_buffer.speech_stopped",
             "input_audio_buffer.committed",
             "response.created",
-            "response.audio.delta",
-            "response.audio.done",
+            "response.output_audio.delta",
+            "response.output_audio.done",
             "response.done",
         ]
         input_item_ids: list[str] = []
@@ -459,7 +459,7 @@ class TestQwen3OmniRealtimeWebSocket:
         for events in turns:
             event_types = [event["type"] for event in events]
             for event_type in required_sequence:
-                if event_type != "response.audio.delta":
+                if event_type != "response.output_audio.delta":
                     assert event_types.count(event_type) == 1, event_types
             positions = [event_types.index(event_type) for event_type in required_sequence]
             assert positions == sorted(positions)
@@ -486,7 +486,7 @@ class TestQwen3OmniRealtimeWebSocket:
             output_pcm = b"".join(
                 base64.b64decode(event["delta"])
                 for event in events
-                if event["type"] == "response.audio.delta" and event.get("delta")
+                if event["type"] == "response.output_audio.delta" and event.get("delta")
             )
             assert output_pcm
             assert created["id"] == done["id"]

tests/entrypoints/openai_api/test_serving_video_stream.py

@@ -14,6 +14,7 @@ import weakref
 from typing import Any
 
 import pytest
+import torch
 from PIL import Image
 
 from vllm_omni.entrypoints.openai import video_stream_base, video_stream_envs
@@ -457,6 +458,54 @@ async def test_async_chunk_mode_is_read_by_engine_path_at_runtime(monkeypatch):
     assert not any(m.get("type") == "response.text.delta" for m in ws_off.sent)
 
 
+@pytest.mark.asyncio
+@pytest.mark.parametrize("async_chunk_mode", ["on", "off"])
+async def test_audio_events_use_output_audio_names(monkeypatch, async_chunk_mode):
+    class AudioEngine:
+        def generate(self, **_kwargs):
+            async def _gen():
+                yield _audio_result([torch.zeros(1)])
+
+            return _gen()
+
+    class AudioHandler(QwenOmniStreamingVideoHandler):
+        async def _preprocess_to_engine_prompt(self, request):
+            return {"prompt": "x"}
+
+    monkeypatch.setenv("VLLM_VIDEO_ASYNC_CHUNK", async_chunk_mode)
+    monkeypatch.setattr(
+        OmniStreamingVideoHandler,
+        "_encode_audio_wav_b64",
+        staticmethod(lambda _audio: "audio-b64"),
+    )
+
+    ws = MockWebSocket()
+    handler = AudioHandler(chat_service=object(), engine_client=AudioEngine())
+    config = StreamingVideoSessionConfig(model="test", modalities=["text", "audio"])
+
+    await handler._process_query_engine(
+        ws,
+        config,
+        [_b64(_make_jpeg())],
+        bytearray(),
+        [],
+        "describe",
+        "req-audio-events",
+        asyncio.Event(),
+        {},
+    )
+
+    audio_events = [message for message in ws.sent if "audio" in message.get("type", "")]
+    assert audio_events == [
+        {
+            "type": "response.output_audio.delta",
+            "data": "audio-b64",
+            "format": "wav",
+        },
+        {"type": "response.output_audio.done"},
+    ]
+
+
 @pytest.mark.asyncio
 async def test_query_without_engine_client_sends_error():
     ws = MockWebSocket()