[Bugfix] Reject instructions changes on locked native duplex sessions (#6318)

Signed-off-by: ANURAG KANADE <anuragkanade6@gmail.com>

tests/e2e/features/fullduplex/personaplex/test_unified_runtime.py

@@ -18,6 +18,10 @@ from vllm_omni.experimental.fullduplex.engine.duplex_runtime import (
     DuplexInputMode,
 )
 from vllm_omni.experimental.fullduplex.engine.messages import DuplexFence
+from vllm_omni.experimental.fullduplex.openai.runtime_adapter import (
+    ServingRuntimeConfigError,
+)
+from vllm_omni.experimental.fullduplex.personaplex.config import DEFAULT_PERSONA
 from vllm_omni.experimental.fullduplex.personaplex.data_plane import (
     PersonaPlexDataPlaneContext,
     PersonaPlexDataPlaneSession,
@@ -242,6 +246,53 @@ def test_personaplex_capabilities_are_honest() -> None:
     assert multi.supports_barge_in is False
 
 
+def test_personaplex_runtime_config_update_rejects_changed_persona() -> None:
+    adapter = PersonaPlexServingRuntimeAdapter(lambda *_: None)
+    short_persona = "You are a helpful assistant."
+    longer_persona = (
+        "You are now a swashbuckling pirate captain who speaks entirely in "
+        "nautical slang, references buried treasure constantly, and never "
+        "breaks character no matter what the user asks."
+    )
+    current = {"personaplex_persona": short_persona, "personaplex_voice_prompt": "NATF2.pt"}
+
+    with pytest.raises(ServingRuntimeConfigError, match="persona"):
+        adapter.runtime_config_for_update(
+            SimpleNamespace(instructions=longer_persona, extra_body={}),
+            current,
+        )
+
+    unchanged = adapter.runtime_config_for_update(
+        SimpleNamespace(instructions=short_persona, extra_body={}),
+        current,
+    )
+    assert unchanged["personaplex_persona"] == short_persona
+
+
+def test_personaplex_runtime_config_update_rejects_changed_voice() -> None:
+    adapter = PersonaPlexServingRuntimeAdapter(lambda *_: None)
+    current = {"personaplex_persona": DEFAULT_PERSONA, "personaplex_voice_prompt": "NATF2.pt"}
+
+    with pytest.raises(ServingRuntimeConfigError, match="voice"):
+        adapter.runtime_config_for_update(
+            SimpleNamespace(instructions=None, voice="OtherVoice.pt", extra_body={}),
+            current,
+        )
+
+    unchanged = adapter.runtime_config_for_update(
+        SimpleNamespace(instructions=None, voice="NATF2.pt", extra_body={}),
+        current,
+    )
+    assert unchanged["personaplex_voice_prompt"] == "NATF2.pt"
+
+
+def test_personaplex_rejects_minicpmo_only_opt_out_flag() -> None:
+    adapter = PersonaPlexServingRuntimeAdapter(lambda *_: None)
+
+    with pytest.raises(ServingRuntimeConfigError, match="minicpmo45_native_duplex"):
+        adapter.validate_client_extra_body({"minicpmo45_native_duplex": False})
+
+
 def test_pcm_buffer_emits_one_80ms_frame_transactionally() -> None:
     buffer = PersonaPlexPcmAppendBuffer()
     reservation = buffer.prepare_append(

tests/entrypoints/openai_api/test_duplex_handler.py

@@ -49,6 +49,9 @@ from vllm_omni.experimental.fullduplex.openai.serving import (
 )
 from vllm_omni.experimental.fullduplex.openai.websocket import DuplexWebSocketActor
 from vllm_omni.experimental.fullduplex.output import attach_duplex_output_decision
+from vllm_omni.experimental.fullduplex.personaplex.serving_adapter import (
+    PersonaPlexServingRuntimeAdapter,
+)
 from vllm_omni.outputs import OmniRequestOutput
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu]
@@ -991,6 +994,178 @@ async def test_minicpmo_native_session_update_requires_ref_audio_before_enabling
     assert ("sid-runtime-update-ref-required", "session.update") not in engine.signals
 
 
+def test_personaplex_candidate_update_does_not_leak_minicpmo_ref_audio_check():
+    handler = OmniDuplexSessionHandler(
+        chat_service=SimpleNamespace(engine_client=SimpleNamespace()),
+        serving_runtime_adapter=PersonaPlexServingRuntimeAdapter(lambda *_: None),
+    )
+    session = DuplexSession(
+        session_id="sid-personaplex-voice-change",
+        config=DuplexSessionConfig(modalities=["audio"], voice="NATF2.pt"),
+        capabilities=PersonaPlexServingRuntimeAdapter.capabilities(max_sessions=1),
+    )
+    candidate_config = DuplexSessionConfig(modalities=["audio"], voice="OtherVoice.pt")
+
+    error = handler._runtime_session_candidate_update_error(session, candidate_config)
+
+    assert error is None
+
+
+@pytest.mark.asyncio
+async def test_minicpmo_native_session_update_rejects_instructions_after_native_context_locked():
+    engine = FakeEngineClient()
+    handler = OmniDuplexSessionHandler(
+        chat_service=FakeChatService(engine),
+        config_timeout_s=0.1,
+        idle_timeout_s=1,
+    )
+    ws = TimedWebSocket()
+    ws.put(_native_session_create("sid-instructions-locked", modalities=["text"]))
+    ws.put(
+        {
+            "type": "input_audio_buffer.append",
+            "audio": _pcm_f32_b64(16000, value=0.05),
+            "format": "pcm_f32le",
+            "sample_rate_hz": 16000,
+            "duration_ms": 1000,
+            "is_speech": True,
+        }
+    )
+    ws.put(
+        {
+            "type": "turn.signal",
+            "event": "session.update",
+            "payload": {"instructions": "You are now a pirate."},
+        }
+    )
+    ws.put({"type": "session.close"})
+
+    await handler.handle_session(ws)
+
+    error = next(message for message in ws.sent if message.get("type") == "error")
+    assert error["code"] == "instructions_update_unsupported"
+    assert "session.updated" not in ws.sent_types()
+    assert ("sid-instructions-locked", "session.update") not in engine.signals
+
+
+@pytest.mark.asyncio
+async def test_minicpmo_native_session_update_allows_unchanged_instructions_after_lock():
+    engine = FakeEngineClient()
+    handler = OmniDuplexSessionHandler(
+        chat_service=FakeChatService(engine),
+        config_timeout_s=0.1,
+        idle_timeout_s=1,
+    )
+    ws = TimedWebSocket()
+    ws.put(_native_session_create("sid-instructions-unchanged", modalities=["text"]))
+    ws.put(
+        {
+            "type": "input_audio_buffer.append",
+            "audio": _pcm_f32_b64(16000, value=0.05),
+            "format": "pcm_f32le",
+            "sample_rate_hz": 16000,
+            "duration_ms": 1000,
+            "is_speech": True,
+        }
+    )
+    ws.put(
+        {
+            "type": "turn.signal",
+            "event": "session.update",
+            "payload": {"instructions": "You are a concise assistant.", "temperature": 0.3},
+        }
+    )
+    ws.put({"type": "session.close"})
+
+    await handler.handle_session(ws)
+
+    assert "session.updated" in ws.sent_types()
+    assert not any(
+        message.get("type") == "error" and message.get("code") == "instructions_update_unsupported"
+        for message in ws.sent
+    )
+
+
+@pytest.mark.asyncio
+async def test_minicpmo_native_session_update_rejects_instructions_before_first_real_append():
+    engine = FakeEngineClient()
+    handler = OmniDuplexSessionHandler(
+        chat_service=FakeChatService(engine),
+        config_timeout_s=0.1,
+        idle_timeout_s=1,
+    )
+    ws = TimedWebSocket()
+    ws.put(_native_session_create("sid-buffered-before-lock", modalities=["text"]))
+    ws.put(
+        {
+            "type": "input_audio_buffer.append",
+            "audio": _pcm_f32_b64(3200, value=0.05),
+            "format": "pcm_f32le",
+            "sample_rate_hz": 16000,
+            "duration_ms": 200,
+            "is_speech": True,
+        }
+    )
+    ws.put(
+        {
+            "type": "turn.signal",
+            "event": "session.update",
+            "payload": {
+                "instructions": (
+                    "You are now a swashbuckling pirate captain who speaks entirely in "
+                    "nautical slang, references buried treasure constantly, and never "
+                    "breaks character no matter what the user asks."
+                )
+            },
+        }
+    )
+    ws.put({"type": "input_audio_buffer.commit", "final": True, "response_create": True})
+    ws.put({"type": "session.close"})
+
+    await handler.handle_session(ws)
+
+    error = next(message for message in ws.sent if message.get("type") == "error")
+    assert error["code"] == "instructions_update_unsupported"
+    assert "session.updated" not in ws.sent_types()
+    assert engine.appended, "the commit must still flush the buffered chunk despite the rejected update"
+
+
+@pytest.mark.asyncio
+async def test_minicpmo_native_session_update_rejects_native_duplex_mode_flip():
+    engine = FakeEngineClient()
+    handler = OmniDuplexSessionHandler(
+        chat_service=FakeChatService(engine),
+        config_timeout_s=0.1,
+        idle_timeout_s=1,
+    )
+    ws = TimedWebSocket()
+    ws.put(_native_session_create("sid-native-duplex-flag-flip", modalities=["text"]))
+    ws.put(
+        {
+            "type": "turn.signal",
+            "event": "session.update",
+            "payload": {"extra_body": {"minicpmo45_native_duplex": False}},
+        }
+    )
+    ws.put(
+        {
+            "type": "turn.signal",
+            "event": "session.update",
+            "payload": {"instructions": "You are now a pirate."},
+        }
+    )
+    ws.put({"type": "session.close"})
+
+    await handler.handle_session(ws)
+
+    errors = [message for message in ws.sent if message.get("type") == "error"]
+    assert [error["code"] for error in errors] == [
+        "native_duplex_mode_update_unsupported",
+        "instructions_update_unsupported",
+    ]
+    assert "session.updated" not in ws.sent_types()
+
+
 def test_native_realtime_protocol_audio_delta_preserves_sample_rate_hz():
     ws = TimedWebSocket()
     protocol = NativeRealtimeSessionProtocol(ws)  # type: ignore[arg-type]

vllm_omni/experimental/fullduplex/minicpmo45/adapter.py

@@ -14,6 +14,7 @@ from vllm_omni.experimental.fullduplex.minicpmo45.policy import MiniCPMO45Duplex
 from vllm_omni.experimental.fullduplex.openai.protocol import DuplexSessionConfig
 from vllm_omni.experimental.fullduplex.openai.runtime_adapter import (
     ServingRuntimeConfigError,
+    reject_changed_runtime_value,
 )
 
 
@@ -69,7 +70,13 @@ class MiniCPMO45NativeDuplexServingAdapter:
         current: object,
     ) -> dict[str, object]:
         runtime_config = deepcopy(dict(current)) if isinstance(current, dict) else {}
-        runtime_config["instructions"] = config.instructions
+        reject_changed_runtime_value(
+            config.instructions,
+            runtime_config.get("instructions"),
+            message="instructions cannot be changed after the session is created",
+            code="instructions_update_unsupported",
+            error_cls=MiniCPMO45ClientRuntimeConfigError,
+        )
         stage_max_tokens = runtime_config.get("duplex_stage_max_tokens")
         stage_max_tokens = deepcopy(stage_max_tokens) if isinstance(stage_max_tokens, dict) else {}
         stage_max_tokens["0"] = (

vllm_omni/experimental/fullduplex/minicpmo45/session.py

@@ -16,6 +16,7 @@ class MiniCPMO45ServingSessionState:
     audio_buffer: MiniCPMO45PcmAppendBuffer = field(default_factory=MiniCPMO45PcmAppendBuffer)
     input_since_commit: bool = False
     speech_since_commit: bool = False
+    native_context_locked: bool = False
     committed_audio_payload: dict[str, object] | None = None
     committed_audio_operation_id: str | None = None
     committed_audio_reserved_bytes: int = 0

vllm_omni/experimental/fullduplex/openai/runtime_adapter.py

@@ -14,6 +14,18 @@ class ServingRuntimeConfigError(ValueError):
         self.code = code
 
 
+def reject_changed_runtime_value(
+    new_value: object,
+    current_value: object,
+    *,
+    message: str,
+    code: str,
+    error_cls: type[ServingRuntimeConfigError] = ServingRuntimeConfigError,
+) -> None:
+    if new_value != current_value:
+        raise error_cls(message, code=code)
+
+
 class PcmAppendReservation(Protocol):
     operation_id: str
     payload: dict[str, object] | None
@@ -64,6 +76,7 @@ class ServingRuntimeSessionState(Protocol):
     audio_buffer: PcmAppendBuffer
     input_since_commit: bool
     speech_since_commit: bool
+    native_context_locked: bool
     committed_audio_payload: dict[str, object] | None
     committed_audio_operation_id: str | None
     committed_audio_reserved_bytes: int

vllm_omni/experimental/fullduplex/openai/serving.py

@@ -1156,6 +1156,18 @@ class OmniDuplexSessionHandler(
     ) -> dict[str, object] | None:
         if not self._uses_native_input_append(session):
             return None
+        if (
+            candidate_config.instructions != session.config.instructions
+            and self._runtime_session_state(session).native_context_locked
+        ):
+            return {
+                "type": "error",
+                "session_id": session.session_id,
+                "code": "instructions_update_unsupported",
+                "error": "session.update cannot change instructions after the native duplex context is initialized",
+            }
+        if session.config.extra_body.get("minicpmo45_native_duplex") is not True:
+            return None
         if not self._config_requests_audio_output(candidate_config):
             return None
         if "ref_audio_data" in session.runtime_config:
@@ -1326,6 +1338,19 @@ class OmniDuplexSessionHandler(
                 "code": "ref_audio_update_unsupported",
                 "error": "session.update cannot change ref_audio after the native duplex runtime is open",
             }
+        extra_body_payload = payload.get("extra_body")
+        if isinstance(extra_body_payload, dict) and "minicpmo45_native_duplex" in extra_body_payload:
+            current_native_duplex = session.config.extra_body.get("minicpmo45_native_duplex")
+            if (
+                current_native_duplex is not None
+                and extra_body_payload["minicpmo45_native_duplex"] != current_native_duplex
+            ):
+                return {
+                    "type": "error",
+                    "session_id": session.session_id,
+                    "code": "native_duplex_mode_update_unsupported",
+                    "error": "session.update cannot change minicpmo45_native_duplex after the session is created",
+                }
         if isinstance(payload.get("instructions"), str):
             session.config.instructions = str(payload["instructions"])
         elif "instructions" in payload and payload.get("instructions") is None:

vllm_omni/experimental/fullduplex/openai/session_runner.py

@@ -28,6 +28,7 @@ from vllm_omni.experimental.fullduplex.openai.realtime_session import (
 )
 from vllm_omni.experimental.fullduplex.openai.runtime_adapter import (
     PcmAppendReservation,
+    ServingRuntimeConfigError,
     ServingRuntimeSessionState,
     payload_turn_id,
 )
@@ -357,6 +358,7 @@ class DuplexSessionRunnerMixin:
                         expected_epoch=append_epoch,
                     )
                     if append_ok:
+                        native.native_context_locked = True
                         if pcm_reservation is not None:
                             pcm_reservation.commit()
                             session.release_input_bytes(pcm_reservation.byte_count)
@@ -1072,10 +1074,21 @@ class DuplexSessionRunnerMixin:
                             if runtime_update_error is not None:
                                 await emit_event(runtime_update_error)
                                 continue
-                            candidate_runtime_config = self._runtime_config_for_session_update(
-                                session,
-                                candidate_config,
-                            )
+                            try:
+                                candidate_runtime_config = self._runtime_config_for_session_update(
+                                    session,
+                                    candidate_config,
+                                )
+                            except ServingRuntimeConfigError as exc:
+                                await emit_event(
+                                    {
+                                        "type": "error",
+                                        "session_id": session.session_id,
+                                        "code": exc.code,
+                                        "error": str(exc),
+                                    }
+                                )
+                                continue
                             if not await self._signal_runtime_session(
                                 session,
                                 turn_event,

vllm_omni/experimental/fullduplex/personaplex/serving_adapter.py

@@ -15,6 +15,7 @@ from vllm_omni.experimental.fullduplex.openai.protocol import (
 )
 from vllm_omni.experimental.fullduplex.openai.runtime_adapter import (
     ServingRuntimeConfigError,
+    reject_changed_runtime_value,
 )
 from vllm_omni.experimental.fullduplex.personaplex.config import DEFAULT_PERSONA
 from vllm_omni.experimental.fullduplex.personaplex.data_plane import (
@@ -31,6 +32,7 @@ _PRIVATE_RUNTIME_CONFIG_KEYS = frozenset(
     {
         "personaplex_prefill_slots",
         "personaplex_model_path",
+        "minicpmo45_native_duplex",
     }
 )
 
@@ -40,6 +42,7 @@ class PersonaPlexServingSessionState:
     audio_buffer: PersonaPlexPcmAppendBuffer = field(default_factory=PersonaPlexPcmAppendBuffer)
     input_since_commit: bool = False
     speech_since_commit: bool = False
+    native_context_locked: bool = False
     committed_audio_payload: dict[str, object] | None = None
     committed_audio_operation_id: str | None = None
     committed_audio_reserved_bytes: int = 0
@@ -190,9 +193,23 @@ class PersonaPlexServingRuntimeAdapter:
         current: Mapping[str, object],
     ) -> dict[str, object]:
         cls.validate_client_extra_body(getattr(config, "extra_body", None))
+        new_persona = str(getattr(config, "instructions", None) or DEFAULT_PERSONA)
+        reject_changed_runtime_value(
+            new_persona,
+            current.get("personaplex_persona"),
+            message="PersonaPlex persona (instructions) cannot be changed after the session is created",
+            code="persona_update_unsupported",
+        )
+        new_voice = cls._voice_name(getattr(config, "voice", None))
+        reject_changed_runtime_value(
+            new_voice,
+            current.get("personaplex_voice_prompt"),
+            message="PersonaPlex voice cannot be changed after the session is created",
+            code="voice_update_unsupported",
+        )
         runtime_config = deepcopy(dict(current))
-        runtime_config["personaplex_voice_prompt"] = cls._voice_name(getattr(config, "voice", None))
-        runtime_config["personaplex_persona"] = str(getattr(config, "instructions", None) or DEFAULT_PERSONA)
+        runtime_config["personaplex_voice_prompt"] = new_voice
+        runtime_config["personaplex_persona"] = new_persona
         return runtime_config
 
     @staticmethod