From 6b58477f86ff5d177dedb6079917c301cc3e9c61 Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Thu, 29 Oct 2026 15:20:20 -0700 Subject: [PATCH] fix(realtime): map OpenAI TTS voices before the Live voice check, keep outage spend rows, share the playground session config The Live voice gate now judges the Gemini voice an OpenAI TTS name maps to, so fable and onyx reach Vertex as Umbriel and Orus again. An upstream close before the held setup was sent is logged as a session, not a refusal. The playground sends one server_vad session config for typed and voice turns, and the e2e, integration, and dashboard tests follow lazy setup. --- .../litellm_core_utils/realtime_streaming.py | 6 +- .../llms/gemini/realtime/transformation.py | 3 +- .../realtime/realtime_client.py | 3 + .../realtime/test_realtime_e2e.py | 4 +- ..._transcription_guardrail_session_update.py | 24 +++++-- .../test_realtime_streaming.py | 18 +++++ .../test_vertex_ai_realtime_transformation.py | 18 +++++ .../chat_ui/RealtimePlayground.test.tsx | 18 +++++ .../components/chat_ui/RealtimePlayground.tsx | 65 +++++-------------- 9 files changed, 104 insertions(+), 55 deletions(-) diff --git a/litellm/litellm_core_utils/realtime_streaming.py b/litellm/litellm_core_utils/realtime_streaming.py index aee0ae05738..757be04540d 100644 --- a/litellm/litellm_core_utils/realtime_streaming.py +++ b/litellm/litellm_core_utils/realtime_streaming.py @@ -1568,7 +1568,11 @@ class RealTimeStreaming: return BackendClose(code=1011, reason="proxy failed while relaying the upstream websocket") def _backend_refused_session(self, close: BackendClose) -> bool: - return close.code != 1000 and not self._backend_sent_frames + return ( + close.code != 1000 + and not self._backend_sent_frames + and not self._holds_session_updates_until_first_content() + ) async def _log_session_end(self, transport_refusal: Exception | None) -> None: provider_refusal: Final = None if self.provider_config is None else self.provider_config.session_refusal() diff --git a/litellm/llms/gemini/realtime/transformation.py b/litellm/llms/gemini/realtime/transformation.py index ec1ef4628b0..3134dfa1e4b 100644 --- a/litellm/llms/gemini/realtime/transformation.py +++ b/litellm/llms/gemini/realtime/transformation.py @@ -18,6 +18,7 @@ from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLogging from litellm.litellm_core_utils.url_utils import join_api_base from litellm.llms.base_llm.realtime.transformation import BaseRealtimeConfig, RealtimeSessionUpdateRejection from litellm.llms.vertex_ai.gemini.vertex_and_google_ai_studio_gemini import ( + OPENAI_TO_GEMINI_TTS_VOICES, VertexGeminiConfig, ) from litellm.responses.litellm_completion_transformation.transformation import ( @@ -125,7 +126,7 @@ def _is_undocumented_live_voice(voice: object) -> bool: return ( isinstance(voice, str) and voice.lower() not in OPENAI_STOCK_REALTIME_VOICES - and voice.lower() not in GEMINI_LIVE_DOCUMENTED_VOICES + and OPENAI_TO_GEMINI_TTS_VOICES.get(voice.lower(), voice).lower() not in GEMINI_LIVE_DOCUMENTED_VOICES ) diff --git a/tests/e2e/llm_translation/realtime/realtime_client.py b/tests/e2e/llm_translation/realtime/realtime_client.py index 4d8336775ef..6bd5d61d721 100644 --- a/tests/e2e/llm_translation/realtime/realtime_client.py +++ b/tests/e2e/llm_translation/realtime/realtime_client.py @@ -47,6 +47,7 @@ class RealtimeProvider: id: str alias: str litellm_params: LiteLLMParamsBody + modalities: tuple[str, ...] = ("text",) PROVIDERS = ( @@ -75,6 +76,7 @@ PROVIDERS = ( model="gemini/gemini-3.1-flash-live-preview", api_key="os.environ/GEMINI_API_KEY", ), + modalities=("audio",), ), RealtimeProvider( "vertex_ai", @@ -84,6 +86,7 @@ PROVIDERS = ( vertex_location="us-central1", vertex_credentials="os.environ/VERTEXAI_CREDENTIALS", ), + modalities=("audio",), ), RealtimeProvider( "bedrock", diff --git a/tests/e2e/llm_translation/realtime/test_realtime_e2e.py b/tests/e2e/llm_translation/realtime/test_realtime_e2e.py index f5592abb34d..3b7ba3a2430 100644 --- a/tests/e2e/llm_translation/realtime/test_realtime_e2e.py +++ b/tests/e2e/llm_translation/realtime/test_realtime_e2e.py @@ -124,7 +124,8 @@ def test_text_conversation( session.send( SessionUpdate( session=SessionConfig( - instructions="You are a terse assistant. Reply in one short sentence." + modalities=list(provider.modalities), + instructions="You are a terse assistant. Reply in one short sentence.", ) ) ) @@ -159,6 +160,7 @@ def test_tool_call_round_trip( session.send( SessionUpdate( session=SessionConfig( + modalities=list(provider.modalities), tools=[WEATHER_TOOL], tool_choice="auto", instructions=( diff --git a/tests/integration/providers/test_realtime_transcription_guardrail_session_update.py b/tests/integration/providers/test_realtime_transcription_guardrail_session_update.py index ad58a400cec..2712d6e30cd 100644 --- a/tests/integration/providers/test_realtime_transcription_guardrail_session_update.py +++ b/tests/integration/providers/test_realtime_transcription_guardrail_session_update.py @@ -355,7 +355,13 @@ def _voice_scenario_created_after_the_first_frame(transcript: str) -> RealtimeRe def _live_scenario() -> RealtimeResponse: - return RealtimeResponse(content_type="application/x-realtime", events=()) + return RealtimeResponse( + content_type="application/x-realtime", + events=( + {"serverContent": {"modelTurn": {"parts": [{"text": "scripted $REQUEST_ID"}]}}}, + {"serverContent": {"turnComplete": True}}, + ), + ) def _realtime_update(turn_detection: JsonValue) -> dict[str, JsonValue]: @@ -1348,10 +1354,14 @@ def test_gemini_ai_studio_voice_session_with_vad_tuning_connects_under_the_guard _ws_base(_owned_url(guardrail_proxy)), f"model={model}", key, - (_step(_update_frame(update), until="session.updated"),), + ( + _step(_update_frame(update), until="session.updated"), + _step(_user_text_item(CLEAN_TRANSCRIPT), RESPONSE_CREATE, until=RESPONSE_DONE), + ), ) observed: Final = _observed(upstream_url, handle.scenario_id) - assert session.types == ("session.created", "session.updated"), session + assert session.types[:2] == ("session.created", "session.updated"), session + assert session.types[-1] == RESPONSE_DONE, session assert _setup_detection(observed) == {"disabled": True}, _sent(observed) @@ -1365,10 +1375,14 @@ def test_vertex_live_voice_session_keeps_vad_tuning_under_the_guardrail(guardrai _ws_base(_owned_url(guardrail_proxy)), f"model={model}", key, - (_step(_update_frame(_realtime_update(TUNED_SERVER_VAD)), until="session.updated"),), + ( + _step(_update_frame(_realtime_update(TUNED_SERVER_VAD)), until="session.updated"), + _step(_user_text_item(CLEAN_TRANSCRIPT), RESPONSE_CREATE, until=RESPONSE_DONE), + ), ) observed: Final = _observed(upstream_url, handle.scenario_id) - assert session.types == ("session.created", "session.updated"), session + assert session.types[:2] == ("session.created", "session.updated"), session + assert session.types[-1] == RESPONSE_DONE, session assert _setup_detection(observed) == GEMINI_TUNED_DETECTION, _sent(observed) diff --git a/tests/unit/litellm_core_utils/test_realtime_streaming.py b/tests/unit/litellm_core_utils/test_realtime_streaming.py index 9363ba0ddce..7c4b9d865e1 100644 --- a/tests/unit/litellm_core_utils/test_realtime_streaming.py +++ b/tests/unit/litellm_core_utils/test_realtime_streaming.py @@ -4174,6 +4174,24 @@ async def test_upstream_refusal_after_a_synthetic_session_created_still_logs_a_f assert session.logging.logged_sessions == () +class _LazySetupRealtimeConfig(_PassthroughRealtimeConfig): + def builds_setup_from_session_update(self) -> bool: + return True + + +@pytest.mark.asyncio +async def test_upstream_outage_before_a_held_setup_was_sent_logs_the_session_not_a_refusal(): + upstream_close: Final = ConnectionClosed(Close(1011, "upstream outage"), None) + session: Final = _relay_session( + _client_ws_that_never_sends(), _backend_ws_closing_with(upstream_close), _LazySetupRealtimeConfig() + ) + + await session.run() + + assert session.logging.logged_failures == () + assert len(session.logging.logged_sessions) == 1 + + @pytest.mark.asyncio async def test_upstream_close_after_relayed_events_still_logs_the_session_as_success(): client_ws: Final = _client_ws_that_never_sends() diff --git a/tests/unit/llms/vertex_ai/realtime/test_vertex_ai_realtime_transformation.py b/tests/unit/llms/vertex_ai/realtime/test_vertex_ai_realtime_transformation.py index 9d7fba8b11e..7f0106616ce 100644 --- a/tests/unit/llms/vertex_ai/realtime/test_vertex_ai_realtime_transformation.py +++ b/tests/unit/llms/vertex_ai/realtime/test_vertex_ai_realtime_transformation.py @@ -18,6 +18,7 @@ import websockets.exceptions # registers websockets.exceptions on the websocket import litellm from litellm.llms.vertex_ai.common_utils import get_vertex_base_url +from litellm.llms.vertex_ai.gemini.vertex_and_google_ai_studio_gemini import OPENAI_TO_GEMINI_TTS_VOICES from litellm.llms.vertex_ai.realtime.transformation import VertexAIRealtimeConfig # --------------------------------------------------------------------------- @@ -699,3 +700,20 @@ def test_vertex_drops_an_undocumented_voice_with_drop_params(): json.dumps(session_update), "gemini-live-2.5-flash", session_configuration_request=None ) assert "speechConfig" not in json.loads(messages[0])["setup"].get("generationConfig", {}) + + +@pytest.mark.parametrize("drop_params", [False, True]) +@pytest.mark.parametrize("voice", ["fable", "onyx"]) +def test_vertex_sends_the_documented_voice_an_openai_tts_voice_maps_to(voice, drop_params): + cfg: Final = VertexAIRealtimeConfig( + access_token="tok", project="my-proj", location="us-central1", drop_params=drop_params + ) + session_update: Final = {"type": "session.update", "session": {"voice": voice}} + + assert cfg.setup_session_update_rejection("gemini-live-2.5-flash", session_update["session"], setup_sent=False) is None + messages: Final = cfg.transform_realtime_request( + json.dumps(session_update), "gemini-live-2.5-flash", session_configuration_request=None + ) + assert json.loads(messages[0])["setup"]["generationConfig"]["speechConfig"] == { + "voiceConfig": {"prebuiltVoiceConfig": {"voiceName": OPENAI_TO_GEMINI_TTS_VOICES[voice]}} + } diff --git a/ui/litellm-dashboard/src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.test.tsx b/ui/litellm-dashboard/src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.test.tsx index 117796d658e..56135c779e9 100644 --- a/ui/litellm-dashboard/src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.test.tsx +++ b/ui/litellm-dashboard/src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.test.tsx @@ -173,6 +173,24 @@ describe("RealtimePlayground", () => { expect(update.session.type).toBe("realtime"); }); + it("starts recording on the configuration the session was created with", async () => { + const user = userEvent.setup(); + render(); + + await connect(user); + await act(async () => { + latestSocket().emit({ type: "session.created" }); + }); + await user.click(screen.getByTitle("Start recording")); + + const updates = latestSocket() + .sent.map((raw) => JSON.parse(raw)) + .filter((payload) => payload.type === "session.update"); + expect(updates).toHaveLength(2); + expect(updates[1]).toEqual(updates[0]); + expect(updates[0].session.turn_detection).toEqual({ type: "server_vad" }); + }); + it("sends what was typed and then asks for a response", async () => { const user = userEvent.setup(); render(); diff --git a/ui/litellm-dashboard/src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.tsx b/ui/litellm-dashboard/src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.tsx index 01151203e65..408cbd58593 100644 --- a/ui/litellm-dashboard/src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.tsx +++ b/ui/litellm-dashboard/src/app/(dashboard)/playground/components/chat_ui/RealtimePlayground.tsx @@ -22,6 +22,20 @@ interface RealtimePlaygroundProps { selectedGuardrails?: string[]; } +const sessionUpdate = (voice: string) => + JSON.stringify({ + type: "session.update", + session: { + type: "realtime", + modalities: ["text", "audio"], + voice, + input_audio_format: "pcm16", + output_audio_format: "pcm16", + input_audio_transcription: { model: "gpt-4o-mini-transcribe" }, + turn_detection: { type: "server_vad" }, + }, + }); + const RealtimePlayground: React.FC = ({ accessToken, selectedModel, @@ -125,21 +139,7 @@ const RealtimePlayground: React.FC = ({ const type = data.type; if (type === "session.created") { - // GA: session.type is required ("realtime" | "transcription") - ws.send( - JSON.stringify({ - type: "session.update", - session: { - type: "realtime", - modalities: ["text", "audio"], - voice: selectedVoice, - input_audio_format: "pcm16", - output_audio_format: "pcm16", - input_audio_transcription: { model: "gpt-4o-mini-transcribe" }, - turn_detection: null, - }, - }), - ); + ws.send(sessionUpdate(selectedVoice)); } else if (type === "session.updated") { // session configured } else if ( @@ -231,22 +231,7 @@ const RealtimePlayground: React.FC = ({ const startRecording = useCallback(async () => { if (!wsRef.current || wsRef.current.readyState !== WebSocket.OPEN) return; - // Switch to server VAD mode for voice input - // GA: session.type is required - wsRef.current.send( - JSON.stringify({ - type: "session.update", - session: { - type: "realtime", - modalities: ["text", "audio"], - voice: selectedVoice, - input_audio_format: "pcm16", - output_audio_format: "pcm16", - input_audio_transcription: { model: "gpt-4o-mini-transcribe" }, - turn_detection: { type: "server_vad" }, - }, - }), - ); + wsRef.current.send(sessionUpdate(selectedVoice)); try { const stream = await navigator.mediaDevices.getUserMedia({ audio: true }); @@ -301,7 +286,7 @@ const RealtimePlayground: React.FC = ({ } catch (err: any) { addMessage("status", `Microphone error: ${err.message}`); } - }, [addMessage]); + }, [addMessage, selectedVoice]); const stopRecording = useCallback(() => { processorRef.current?.disconnect(); @@ -317,21 +302,7 @@ const RealtimePlayground: React.FC = ({ if (!wsRef.current || wsRef.current.readyState !== WebSocket.OPEN) return; if (configureSessionRef.current) return; configureSessionRef.current = true; - // GA: session.type is required - wsRef.current.send( - JSON.stringify({ - type: "session.update", - session: { - type: "realtime", - modalities: ["text", "audio"], - voice: selectedVoice, - input_audio_format: "pcm16", - output_audio_format: "pcm16", - input_audio_transcription: { model: "gpt-4o-mini-transcribe" }, - turn_detection: null, - }, - }), - ); + wsRef.current.send(sessionUpdate(selectedVoice)); }, [selectedVoice]); const sendTextMessage = useCallback(() => {