diff --git a/vllm_omni/engine/duplex/session/emitter.py b/vllm_omni/engine/duplex/session/emitter.py
index 508bc7ef1ce..6ccfcc142ab 100644
--- a/vllm_omni/engine/duplex/session/emitter.py
+++ b/vllm_omni/engine/duplex/session/emitter.py
@@ -125,7 +125,7 @@ def auto_responds(self) -> bool:
         extra = getattr(self._ctx.session.config, "extra_body", None)
         if not isinstance(extra, dict):
             return False
-        return extra.get("auto_response") is True or extra.get("full_duplex") is True
+        return extra.get("auto_response") is True
 
     def is_stale_model_output(self, payload: dict[str, object]) -> bool:
         """Whether ``payload`` belongs to a turn the session has already moved past."""
diff --git a/vllm_omni/model_executor/models/nemotron_voicechat/duplex/serving_adapter.py b/vllm_omni/model_executor/models/nemotron_voicechat/duplex/serving_adapter.py
index 16a33ec01f3..1b210728709 100644
--- a/vllm_omni/model_executor/models/nemotron_voicechat/duplex/serving_adapter.py
+++ b/vllm_omni/model_executor/models/nemotron_voicechat/duplex/serving_adapter.py
@@ -117,9 +117,7 @@ def _render_tool_response(output: str) -> str:
 
 def _require_native_full_duplex(config: object) -> None:
     extra_body = getattr(config, "extra_body", None)
-    enabled = isinstance(extra_body, dict) and (
-        extra_body.get("auto_response") is True or extra_body.get("full_duplex") is True
-    )
+    enabled = isinstance(extra_body, dict) and extra_body.get("auto_response") is True
     if not enabled:
         raise ServingRuntimeConfigError(
             "Nemotron VoiceChat currently supports model-native full-duplex streaming only; "
diff --git a/vllm_omni/model_executor/models/qwen3_omni/duplex/plugin.py b/vllm_omni/model_executor/models/qwen3_omni/duplex/plugin.py
index 89b2c6ffdf9..09658dfa53f 100644
--- a/vllm_omni/model_executor/models/qwen3_omni/duplex/plugin.py
+++ b/vllm_omni/model_executor/models/qwen3_omni/duplex/plugin.py
@@ -160,7 +160,7 @@ def create_session_state(self):
     def validate_client_extra_body(self, extra_body):
         if not isinstance(extra_body, Mapping):
             return
-        if extra_body.get("auto_response") or extra_body.get("full_duplex"):
+        if extra_body.get("auto_response"):
             raise DuplexRuntimeConfigError(
                 "Qwen requires server VAD or explicit commits; native auto_response is unsupported"
             )