[Core] Integrate TrackingArgumentParser (#3369)

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

tests/entrypoints/test_omni_entrypoints.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import argparse
 import queue
 from collections.abc import Callable
 from types import SimpleNamespace
@@ -176,83 +175,6 @@ def _patch_engine(monkeypatch: pytest.MonkeyPatch, engine: FakeAsyncOmniEngine)
     )
 
 
-def test_direct_omni_with_nullified_parser_only_nulls_untyped_override_fields(
-    monkeypatch: pytest.MonkeyPatch,
-):
-    from vllm_omni.engine.arg_utils import nullify_stage_engine_defaults
-    from vllm_omni.entrypoints.omni import Omni
-
-    captured: dict[str, Any] = {}
-
-    def fake_engine(*args: Any, **kwargs: Any) -> FakeAsyncOmniEngine:
-        captured.update(kwargs)
-        return FakeAsyncOmniEngine()
-
-    monkeypatch.setattr("vllm_omni.entrypoints.omni_base.AsyncOmniEngine", fake_engine)
-    monkeypatch.setattr("vllm_omni.entrypoints.omni_base.omni_snapshot_download", lambda model: model)
-
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--gpu-memory-utilization", type=float, default=0.9)
-    parser.add_argument("--batch-timeout", type=int, default=10)
-    nullify_stage_engine_defaults(parser)
-    args = parser.parse_args([])
-    args.model = "fake-model"
-
-    Omni(**vars(args))
-
-    assert captured["gpu_memory_utilization"] is None
-    assert captured["batch_timeout"] == 10
-    assert "_cli_explicit_keys" not in captured
-
-
-def test_from_cli_args_warns_and_forwards_without_internal_keys(
-    monkeypatch: pytest.MonkeyPatch,
-):
-    captured: dict[str, Any] = {}
-
-    def fake_engine(*args: Any, **kwargs: Any) -> FakeAsyncOmniEngine:
-        captured.update(kwargs)
-        return FakeAsyncOmniEngine()
-
-    monkeypatch.setattr("vllm_omni.entrypoints.omni_base.AsyncOmniEngine", fake_engine)
-    monkeypatch.setattr("vllm_omni.entrypoints.omni_base.omni_snapshot_download", lambda model: model)
-
-    args = argparse.Namespace(model="fake-model", gpu_memory_utilization=0.9, _cli_explicit_keys={"model"})
-    with pytest.deprecated_call(match="from_cli_args"):
-        Omni.from_cli_args(args)
-
-    assert captured["gpu_memory_utilization"] == 0.9
-    assert "_cli_explicit_keys" not in captured
-
-
-def test_deprecated_from_cli_args_preserves_legacy_parser_nulling(
-    monkeypatch: pytest.MonkeyPatch,
-):
-    from vllm_omni.entrypoints.omni import Omni
-
-    captured: dict[str, Any] = {}
-
-    def fake_engine(*args: Any, **kwargs: Any) -> FakeAsyncOmniEngine:
-        captured.update(kwargs)
-        return FakeAsyncOmniEngine()
-
-    monkeypatch.setattr("vllm_omni.entrypoints.omni_base.AsyncOmniEngine", fake_engine)
-    monkeypatch.setattr("vllm_omni.entrypoints.omni_base.omni_snapshot_download", lambda model: model)
-    monkeypatch.setattr("sys.argv", ["prog"])
-
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--gpu-memory-utilization", type=float, default=0.9)
-    parser.add_argument("--batch-timeout", type=int, default=10)
-    args = parser.parse_args([])
-    args.model = "fake-model"
-
-    with pytest.deprecated_call(match="from_cli_args"):
-        Omni.from_cli_args(args, parser=parser)
-
-    assert captured["gpu_memory_utilization"] is None
-    assert captured["batch_timeout"] == 10
-
-
 def _make_base():
     from vllm_omni.entrypoints.omni_base import OmniBase