fix(vertex_ai/realtime): normalize all GA-remapped session fields before mapping

Previously _build_vertex_ai_setup_config only lifted nested turn_detection
back to the top level. GA clients' output_modalities and
audio.input.transcription were silently dropped because map_openai_params
only recognises the flat OpenAI-beta keys. Use the parent's
_normalize_session_payload_for_mapping so modalities, transcription, and
turn_detection are all surfaced before mapping.

litellm/llms/vertex_ai/realtime/transformation.py

@@ -150,21 +150,13 @@ class VertexAIRealtimeConfig(GeminiRealtimeConfig):
 
     def _build_vertex_ai_setup_config(self, model: str, session_params: dict) -> dict:
         """Build Vertex AI setup configuration with proper model path and defaults."""
-        # Normalize ``turn_detection`` to the top level so map_openai_params
-        # picks it up whether the client used the flat beta shape or the
-        # GA nested shape (session.audio.input.turn_detection). Without
-        # this, guardrail-injected ``create_response: False`` would be
-        # silently dropped for GA clients because map_openai_params only
-        # looks at top-level keys.
-        extracted_turn_detection = self._extract_turn_detection(session_params)
-        if (
-            extracted_turn_detection is not None
-            and "turn_detection" not in session_params
-        ):
-            session_params = {
-                **session_params,
-                "turn_detection": extracted_turn_detection,
-            }
+        # Normalize GA-remapped fields (``output_modalities``, nested
+        # ``audio.input.transcription``, ``audio.input.turn_detection``) back to
+        # their flat beta keys so ``map_openai_params`` picks them up. Without
+        # this, GA clients' explicit modality / transcription / turn-detection
+        # settings would be silently dropped because ``map_openai_params`` only
+        # recognises the flat OpenAI-beta key names.
+        session_params = self._normalize_session_payload_for_mapping(session_params)
         setup_config = self.map_openai_params(
             optional_params={}, non_default_params=session_params
         )

tests/test_litellm/llms/vertex_ai/realtime/test_vertex_ai_realtime_transformation.py

@@ -120,6 +120,48 @@ def test_vertex_session_update_defaults_to_audio_modality():
     assert setup_payload["generationConfig"]["responseModalities"] == ["AUDIO"]
 
 
+def test_vertex_session_update_normalizes_ga_remapped_fields():
+    """GA-format clients send ``output_modalities`` and nested
+    ``audio.input.transcription`` / ``audio.input.turn_detection``. These must
+    be normalised back to the flat beta keys before ``map_openai_params``
+    runs so client preferences aren't silently dropped.
+    """
+    cfg = VertexAIRealtimeConfig(
+        access_token="tok", project="my-proj", location="us-central1"
+    )
+
+    session_update = {
+        "type": "session.update",
+        "session": {
+            "instructions": "Be concise.",
+            "output_modalities": ["text"],
+            "audio": {
+                "input": {
+                    "transcription": {},
+                    "turn_detection": {"silence_duration_ms": 1500},
+                },
+            },
+        },
+    }
+
+    messages = cfg.transform_realtime_request(
+        json.dumps(session_update),
+        "gemini-live-2.5-flash-native-audio",
+        session_configuration_request=None,
+    )
+    assert len(messages) == 1
+    setup_payload = json.loads(messages[0])["setup"]
+
+    assert setup_payload["generationConfig"]["responseModalities"] == ["TEXT"]
+    assert setup_payload["inputAudioTranscription"] == {}
+    assert (
+        setup_payload["realtimeInputConfig"]["automaticActivityDetection"][
+            "silenceDurationMs"
+        ]
+        == 1500
+    )
+
+
 # ---------------------------------------------------------------------------
 # Round-trip test: text-in / text-out via RealTimeStreaming
 # ---------------------------------------------------------------------------