[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>
This commit is contained in:
Nick CaoandCodex authored and GitHub committed 2026-09-11 22:28:55 +08:00
1 parent 78e1a0ae5c
commit d3493384cf
10 files changed
+103 -48

No files matched your search

@@ -176,7 +176,7 @@ class RealtimeConnection(VllmRealtimeConnection):
sent_audio = True
await self.send_json(
{
"type": "response.audio.delta",
"type": "response.output_audio.delta",
"audio": self._pcm16_b64(chunk),
"format": "pcm16",
"sample_rate_hz": sample_rate,
@@ -194,7 +194,7 @@ class RealtimeConnection(VllmRealtimeConnection):
await self.send(TranscriptionDone(text=full_text, usage=usage))
if sent_audio:
await self.send_json({"type": "response.audio.done", "has_audio": True})
await self.send_json({"type": "response.output_audio.done", "has_audio": True})
audio_done_sent = True
except Exception as e:
logger.exception("Error in generation: %s", e)
@@ -213,9 +213,9 @@ class RealtimeConnection(VllmRealtimeConnection):
# Always send terminal event so clients don't hang forever.
if self._is_connected and not audio_done_sent:
try:
await self.send_json({"type": "response.audio.done", "has_audio": sent_audio})
await self.send_json({"type": "response.output_audio.done", "has_audio": sent_audio})
except Exception:
logger.exception("Failed to send response.audio.done")
logger.exception("Failed to send response.output_audio.done")
while not self.audio_queue.empty():
self.audio_queue.get_nowait()
@@ -18,8 +18,8 @@ Protocol:
{"type": "response.start"}
{"type": "response.text.delta", "delta": "..."}
{"type": "response.text.done", "text": "..."}
{"type": "response.audio.delta", "data": "...", "format": "wav"}
{"type": "response.audio.done"}
{"type": "response.output_audio.delta", "data": "...", "format": "wav"}
{"type": "response.output_audio.done"}
{"type": "session.done"}
{"type": "error", "message": "..."}
"""
@@ -21,8 +21,8 @@ Protocol:
{"type": "response.start"}
{"type": "response.text.delta", "delta": "..."}
{"type": "response.text.done", "text": "..."}
{"type": "response.audio.delta", "data": "...", "format": "wav"}
{"type": "response.audio.done"}
{"type": "response.output_audio.delta", "data": "...", "format": "wav"}
{"type": "response.output_audio.done"}
{"type": "session.done"}
{"type": "error", "message": "..."}
"""
@@ -763,7 +763,7 @@ class OmniStreamingVideoHandler:
if b64:
await websocket.send_json(
{
"type": "response.audio.delta",
"type": "response.output_audio.delta",
"data": b64,
"format": "wav",
}
@@ -807,7 +807,7 @@ class OmniStreamingVideoHandler:
if b64:
await websocket.send_json(
{
"type": "response.audio.delta",
"type": "response.output_audio.delta",
"data": b64,
"format": "wav",
}
@@ -816,7 +816,7 @@ class OmniStreamingVideoHandler:
logger.exception("Failed to coalesce off-path audio")
if audio_chunk_count > 0:
await websocket.send_json({"type": "response.audio.done"})
await websocket.send_json({"type": "response.output_audio.done"})
response_text = "".join(text_parts)
self.on_turn_complete(message_history, user_message, response_text)