From 459c1973b4a191aa319248c67e48622587cdc412 Mon Sep 17 00:00:00 2001
From: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Date: Fri, 22 May 2026 22:10:57 +0000
Subject: [PATCH] fix(gemini realtime): deep-merge automaticActivityDetection
 on follow-up session.update

The follow-up setup merge already deep-merged generationConfig and
realtimeInputConfig, but realtimeInputConfig.automaticActivityDetection
itself is a nested dict. A partial VAD update (e.g. the
guardrail-injected disabled=True from create_response=False) silently
dropped unrelated knobs such as silenceDurationMs and prefixPaddingMs
from the original setup. Deep-merge that block too so partial overrides
only touch the fields they specify.
---
 .../llms/gemini/realtime/transformation.py    | 21 +++++++++-
 .../test_gemini_realtime_transformation.py    | 40 +++++++++++++++++++
 2 files changed, 60 insertions(+), 1 deletion(-)

diff --git a/litellm/llms/gemini/realtime/transformation.py b/litellm/llms/gemini/realtime/transformation.py
index 12b7f877579..eef6c503dbd 100644
--- a/litellm/llms/gemini/realtime/transformation.py
+++ b/litellm/llms/gemini/realtime/transformation.py
@@ -368,10 +368,29 @@ class GeminiRealtimeConfig(BaseRealtimeConfig):
         if isinstance(original_realtime_input_config, dict) and isinstance(
             new_realtime_input_config, dict
         ):
-            follow_up_setup["realtimeInputConfig"] = {
+            merged_realtime_input_config = {
                 **original_realtime_input_config,
                 **new_realtime_input_config,
             }
+            # Deep-merge ``automaticActivityDetection`` so a partial VAD
+            # update (e.g. the guardrail-injected ``disabled: True`` from
+            # ``create_response: False``) does not silently drop unrelated
+            # knobs like ``silenceDurationMs`` / ``prefixPaddingMs`` from
+            # the original setup.
+            original_automatic_activity_detection = original_realtime_input_config.get(
+                "automaticActivityDetection"
+            )
+            new_automatic_activity_detection = new_realtime_input_config.get(
+                "automaticActivityDetection"
+            )
+            if isinstance(original_automatic_activity_detection, dict) and isinstance(
+                new_automatic_activity_detection, dict
+            ):
+                merged_realtime_input_config["automaticActivityDetection"] = {
+                    **original_automatic_activity_detection,
+                    **new_automatic_activity_detection,
+                }
+            follow_up_setup["realtimeInputConfig"] = merged_realtime_input_config
         verbose_logger.debug(
             "Gemini Realtime: Forwarding session.update as follow-up setup"
         )
diff --git a/tests/test_litellm/llms/gemini/realtime/test_gemini_realtime_transformation.py b/tests/test_litellm/llms/gemini/realtime/test_gemini_realtime_transformation.py
index 9db244834c8..c5f10075406 100644
--- a/tests/test_litellm/llms/gemini/realtime/test_gemini_realtime_transformation.py
+++ b/tests/test_litellm/llms/gemini/realtime/test_gemini_realtime_transformation.py
@@ -1047,3 +1047,43 @@ def test_gemini_follow_up_session_update_preserves_response_modalities_on_partia
     assert follow_up["generationConfig"]["responseModalities"] == ["AUDIO"]
     assert follow_up["generationConfig"]["maxOutputTokens"] == 2048
     assert follow_up["generationConfig"]["temperature"] == 0.7
+
+
+def test_gemini_subsequent_session_update_preserves_automatic_activity_detection_subfields():
+    """A follow-up turn_detection update that only sets ``create_response``
+    (mapped to ``disabled``) must not drop ``silenceDurationMs`` /
+    ``prefixPaddingMs`` from the original ``automaticActivityDetection``
+    block."""
+    config = GeminiRealtimeConfig()
+
+    original_setup = {
+        "setup": {
+            "model": "models/gemini-2.5-flash-native-audio",
+            "generationConfig": {"responseModalities": ["AUDIO"]},
+            "realtimeInputConfig": {
+                "automaticActivityDetection": {
+                    "disabled": False,
+                    "silenceDurationMs": 500,
+                    "prefixPaddingMs": 100,
+                }
+            },
+        }
+    }
+
+    session_update = {
+        "type": "session.update",
+        "session": {"turn_detection": {"create_response": False}},
+    }
+
+    messages = config.transform_realtime_request(
+        json.dumps(session_update),
+        "gemini-2.5-flash-native-audio",
+        session_configuration_request=json.dumps(original_setup),
+    )
+
+    automatic_activity_detection = json.loads(messages[0])["setup"][
+        "realtimeInputConfig"
+    ]["automaticActivityDetection"]
+    assert automatic_activity_detection["disabled"] is True
+    assert automatic_activity_detection["silenceDurationMs"] == 500
+    assert automatic_activity_detection["prefixPaddingMs"] == 100