Merge branch 'main' into qwen-image-2.1

Signed-off-by: Isotr0py <Isotr0py@outlook.com>

tests/entrypoints/openai_api/test_serving_speech.py

@@ -505,6 +505,75 @@ class TestSpeechAPI:
         assert voice_info["file_size"] == len(audio_content)
         response = client.delete("/v1/audio/voices/test_voice")
 
+    def test_upload_voice_rejects_builtin_name(self, client):
+        """A name colliding with a built-in or precomputed voice is rejected."""
+        handler = client.app.state.openai_serving_speech
+        handler._adapter.capabilities.supported_speakers = {"vivian"}
+        handler._adapter.capabilities.precomputed_speakers = {"ono_anna": {}}
+
+        files = {"audio_sample": ("test.wav", b"fake audio content" * 1000, "audio/wav")}
+        for reserved in ("Vivian", "ono_anna"):
+            response = client.post("/v1/audio/voices", files=files, data={"consent": "c1", "name": reserved})
+            assert response.status_code == 400
+            assert "reserved" in response.json()["detail"]
+        assert not handler.uploaded_speakers
+
+    def test_upload_voice_overwrites_same_name_by_default(self, client):
+        """Default policy: re-registering an uploaded name replaces it in place."""
+        files = {"audio_sample": ("test.wav", b"first take", "audio/wav")}
+        data = {"consent": "c1", "name": "test_voice_ow"}
+        assert client.post("/v1/audio/voices", files=files, data=data).status_code == 200
+
+        files = {"audio_sample": ("test.wav", b"second take, longer content", "audio/wav")}
+        response = client.post("/v1/audio/voices", files=files, data=data)
+        assert response.status_code == 200
+        assert response.json()["voice"]["file_size"] == len(b"second take, longer content")
+        client.delete("/v1/audio/voices/test_voice_ow")
+
+    def test_upload_voice_immutable_policy_requires_delete(self, client):
+        """VLLM_OMNI_SPEAKER_REGISTRATION_POLICY=immutable rejects duplicates until deleted."""
+        handler = client.app.state.openai_serving_speech
+        handler._registration_policy = "immutable"
+        try:
+            files = {"audio_sample": ("test.wav", b"fake audio content" * 1000, "audio/wav")}
+            data = {"consent": "c1", "name": "test_voice_imm"}
+            assert client.post("/v1/audio/voices", files=files, data=data).status_code == 200
+
+            response = client.post("/v1/audio/voices", files=files, data=data)
+            assert response.status_code == 400
+            assert "immutable" in response.json()["detail"]
+
+            assert client.delete("/v1/audio/voices/test_voice_imm").status_code == 200
+            assert client.post("/v1/audio/voices", files=files, data=data).status_code == 200
+        finally:
+            handler._registration_policy = "overwrite"
+            client.delete("/v1/audio/voices/test_voice_imm")
+
+    def test_invalid_registration_policy_fails_startup(self, mocker, monkeypatch, tmp_path):
+        """An unknown VLLM_OMNI_SPEAKER_REGISTRATION_POLICY is a configuration error, not a silent fallback."""
+        monkeypatch.setenv("SPEAKER_SAMPLES_DIR", str(tmp_path))
+        monkeypatch.setenv("VLLM_OMNI_SPEAKER_REGISTRATION_POLICY", "append")
+        engine_client = mocker.MagicMock()
+        engine_client.default_sampling_params_list = [{}]
+        with pytest.raises(ValueError, match="VLLM_OMNI_SPEAKER_REGISTRATION_POLICY"):
+            OmniOpenAIServingSpeech(
+                engine_client=engine_client, models=mocker.MagicMock(), request_logger=mocker.MagicMock()
+            )
+
+    def test_restored_upload_shadowing_builtin_is_dropped(self, client):
+        """A pre-guard upload restored under a built-in name must not keep shadowing it."""
+        handler = client.app.state.openai_serving_speech
+        handler._adapter.capabilities.supported_speakers = {"vivian"}
+        handler._adapter.capabilities.precomputed_speakers = {}
+        handler.uploaded_speakers["vivian"] = {"name": "vivian", "file_path": "/tmp/vivian.safetensors"}
+        handler.uploaded_speakers["keep_me"] = {"name": "keep_me", "file_path": "/tmp/keep_me.safetensors"}
+
+        handler._drop_shadowing_uploads()
+
+        assert "vivian" not in handler.uploaded_speakers
+        assert "keep_me" in handler.uploaded_speakers
+        handler.uploaded_speakers.pop("keep_me")
+
     def test_upload_voice_with_ref_text(self, client, tmp_path):
         """Test voice upload with ref_text enables in-context cloning."""
         audio_content = b"fake audio content" * 1000

tests/entrypoints/test_async_omni_pause_sleep_routing.py

@@ -33,9 +33,9 @@ def _make_omni(*, stage_types: list[str]) -> AsyncOmni:
     omni._final_output_handler = lambda: None
     omni.reset_mm_cache = AsyncMock()
 
-    stage_clients = [SimpleNamespace(stage_type=stage_type) for stage_type in stage_types]
+    stage_configs = [SimpleNamespace(stage_type=stage_type) for stage_type in stage_types]
     omni.engine = SimpleNamespace(
-        stage_clients=stage_clients,
+        stage_configs=stage_configs,
         stage_vllm_configs=[None] * len(stage_types),
         collective_rpc_async=AsyncMock(return_value=[True]),
     )

tests/entrypoints/test_omni_entrypoints.py

@@ -19,7 +19,7 @@ from vllm.v1.engine.exceptions import EngineDeadError, EngineGenerateError
 
 from vllm_omni.config.omni_config import VllmOmniConfig
 from vllm_omni.config.pipeline_registry import OMNI_PIPELINES
-from vllm_omni.config.stage_config import StageConfig
+from vllm_omni.config.stage_config import StageConfig, StageType
 from vllm_omni.engine.async_omni_engine import StageRuntimeInfo
 from vllm_omni.engine.messages import ErrorMessage, OutputMessage
 from vllm_omni.entrypoints.async_omni import AsyncOmni
@@ -107,7 +107,13 @@ class FakeAsyncOmniEngine:
         self.stage_metadata = stage_metadata or [THREE_STAGE_META[-1]]
         self.num_stages = len(self.stage_metadata)
         self.stage_configs = [
-            StageConfig(stage_id=i, model_stage="dummy-model").to_omegaconf() for i in range(self.num_stages)
+            StageConfig(
+                stage_id=i,
+                model_stage="dummy-model",
+                stage_type=StageType(metadata.stage_type),
+                is_comprehension=getattr(metadata, "is_comprehension", False),
+            ).to_omegaconf()
+            for i, metadata in enumerate(self.stage_metadata)
         ]
         self.default_sampling_params_list = default_sampling_params_list or [
             SamplingParams(max_tokens=8) for _ in range(self.num_stages)
@@ -481,7 +487,7 @@ def test_model_config_and_vllm_config_forward_from_comprehension_stage():
     io_processor = SimpleNamespace(name="io-processor")
     omni = object.__new__(AsyncOmni)
     omni.engine = SimpleNamespace(
-        stage_clients=[SimpleNamespace(is_comprehension=False), SimpleNamespace(is_comprehension=True)],
+        stage_configs=[SimpleNamespace(is_comprehension=False), SimpleNamespace(is_comprehension=True)],
         stage_vllm_configs=[None, vllm_config],
     )
     omni.input_processor = input_processor
@@ -502,7 +508,7 @@ def test_openai_serving_models_can_consume_async_omni_compat_attrs():
     io_processor = SimpleNamespace(name="io-processor")
     omni = object.__new__(AsyncOmni)
     omni.engine = SimpleNamespace(
-        stage_clients=[SimpleNamespace(is_comprehension=True)],
+        stage_configs=[SimpleNamespace(is_comprehension=True)],
         stage_vllm_configs=[vllm_config],
     )
     omni.input_processor = input_processor
@@ -524,10 +530,11 @@ def test_get_diffusion_od_config_returns_diffusion_stage_config():
     diffusion_od_config = object()
     omni = object.__new__(AsyncOmni)
     omni.engine = SimpleNamespace(
+        stage_configs=[SimpleNamespace(stage_type="llm"), SimpleNamespace(stage_type="diffusion")],
         stage_clients=[
             SimpleNamespace(stage_type="llm"),
             SimpleNamespace(stage_type="diffusion", od_config=diffusion_od_config),
-        ]
+        ],
     )
 
     assert omni.get_diffusion_od_config() is diffusion_od_config
@@ -537,15 +544,33 @@ def test_get_diffusion_od_config_falls_back_to_inner_engine():
     diffusion_od_config = object()
     omni = object.__new__(AsyncOmni)
     omni.engine = SimpleNamespace(
+        stage_configs=[SimpleNamespace(stage_type="llm"), SimpleNamespace(stage_type="diffusion")],
         stage_clients=[
             SimpleNamespace(stage_type="llm"),
             SimpleNamespace(stage_type="diffusion", _engine=SimpleNamespace(od_config=diffusion_od_config)),
-        ]
+        ],
     )
 
     assert omni.get_diffusion_od_config() is diffusion_od_config
 
 
+@pytest.mark.asyncio
+async def test_async_omni_rejects_diffusion_list_prompt_without_stage_clients(
+    monkeypatch: pytest.MonkeyPatch,
+):
+    engine = FakeAsyncOmniEngine(stage_metadata=DIFFUSION_ONLY_META)
+    engine.stage_clients = []
+    _patch_engine(monkeypatch, engine)
+
+    app = AsyncOmni("dummy-model")
+    try:
+        with pytest.raises(ValueError, match="single prompt per request"):
+            async for _ in app.generate(prompt=["prompt-1", "prompt-2"], request_id="req-1"):
+                pass
+    finally:
+        app.shutdown()
+
+
 @pytest.mark.asyncio
 async def test_async_omni_yields_only_final_stage_outputs(monkeypatch: pytest.MonkeyPatch):
     engine = FakeAsyncOmniEngine(