[Core] Integrate TrackingArgumentParser (#3369)

Signed-off-by: Alex Brooks <albrooks@redhat.com>

tests/engine/test_async_omni_engine_stage_init.py

@@ -640,38 +640,6 @@ def test_initialize_llm_replica_passes_stage_init_timeout_to_complete_stage_hand
     assert captured_timeout == 302
 
 
-def test_async_omni_engine_reads_tokenizer_from_engine_args(monkeypatch):
-    import vllm_omni.engine.async_omni_engine as engine_mod
-
-    class DummyThread:
-        def __init__(self, *args, **kwargs):
-            pass
-
-        def start(self):
-            pass
-
-        def is_alive(self):
-            return False
-
-    fake_engine_args = types.SimpleNamespace(
-        _explicit_fields=frozenset({"tokenizer"}),
-        explicit_kwargs=lambda: {"tokenizer": "/tokenizer/from-engine-args"},
-    )
-
-    monkeypatch.setattr(engine_mod.threading, "Thread", DummyThread)
-    monkeypatch.setattr(
-        AsyncOmniEngine,
-        "_resolve_stage_configs",
-        lambda self, model, kwargs: ("dummy-config", [types.SimpleNamespace(engine_args={})]),
-    )
-    monkeypatch.setattr(AsyncOmniEngine, "_wait_for_orchestrator_init", lambda *_, **__: None)
-
-    engine = AsyncOmniEngine("dummy-model", engine_args=fake_engine_args)
-
-    assert engine.tokenizer == "/tokenizer/from-engine-args"
-    engine.shutdown()
-
-
 def test_build_engine_args_cli_tokenizer_overrides_inferred_base_tokenizer(tmp_path):
     from vllm_omni.engine.stage_init_utils import build_engine_args_dict
 

tests/engine/test_single_stage_mode.py

@@ -403,39 +403,6 @@ class TestSingleStageModeDetection:
         assert engine.single_stage_mode is True
         assert engine._single_stage_id_filter is None
 
-    def test_engine_args_create_only_forwards_explicit_fields(self, mocker: MockerFixture):
-        from vllm_omni.engine.arg_utils import OmniEngineArgs
-
-        captured: dict[str, Any] = {}
-
-        def fake_resolve(self, model: str, kwargs: dict[str, Any]):
-            captured.update(kwargs)
-            return "/fake/path", [_make_stage_cfg(0)]
-
-        mocker.patch.object(AsyncOmniEngine, "_resolve_stage_configs", fake_resolve)
-        mocker.patch.object(AsyncOmniEngine, "_bootstrap_orchestrator")
-        mock_thread_cls = mocker.patch("threading.Thread")
-        mock_future_cls = mocker.patch("concurrent.futures.Future")
-        mock_future = mocker.Mock()
-        mock_future.result.return_value = mocker.Mock()
-        mock_future_cls.return_value = mock_future
-        mock_thread = mocker.Mock()
-        mock_thread.is_alive.return_value = False
-        mock_thread_cls.return_value = mock_thread
-
-        ea = OmniEngineArgs.create(model="ignored", gpu_memory_utilization=0.5)
-        AsyncOmniEngine(model="fake-model", engine_args=ea)
-
-        assert captured["gpu_memory_utilization"] == 0.5
-        assert "model" not in captured
-        assert "max_num_seqs" not in captured
-
-    def test_bare_engine_args_rejected(self, mocker: MockerFixture):
-        from vllm_omni.engine.arg_utils import OmniEngineArgs
-
-        with pytest.raises(TypeError, match="OmniEngineArgs.create"):
-            self._make_engine_no_thread(mocker, engine_args=OmniEngineArgs(model="fake-model"))
-
     def test_master_address_and_port_stored(self, mocker: MockerFixture):
         engine = self._make_engine_no_thread(
             mocker,