[Bugfix][MiniCPM-o] Load Daily-Omni QA metadata from the hub cache (#6276)

Signed-off-by: psv666 <2693925048@qq.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>

tests/benchmarks/test_daily_omni_local_source.py

@@ -9,13 +9,17 @@ from pathlib import Path
 import pytest
 
 from vllm_omni.benchmarks.data_modules.daily_omni_dataset import (
+    DailyOmniDataset,
     daily_omni_local_qa_json,
     daily_omni_local_videos_dir,
+    ensure_daily_omni_hub_root,
     resolve_daily_omni_local_root,
 )
 
 pytestmark = [pytest.mark.core_model, pytest.mark.cpu, pytest.mark.benchmark]
 
+_HUB_ID = "liarliar/Daily-Omni"
+
 
 def _write_qa_json(root: Path) -> Path:
     qa = root / "qa.json"
@@ -23,6 +27,28 @@ def _write_qa_json(root: Path) -> Path:
     return qa
 
 
+def _stage_offline_hub_cache(tmp_path: Path, monkeypatch: pytest.MonkeyPatch, *, with_qa: bool = True) -> Path:
+    """Build a hub cache holding ``liarliar/Daily-Omni`` and cut off all network access.
+
+    Reproduces the air-gapped NPU runner: the dataset is pre-staged with ``hf download``, so it
+    only exists in the *hub* cache -- never in the ``datasets`` cache that ``load_dataset`` reads.
+    """
+    constants = pytest.importorskip("huggingface_hub").constants
+
+    cache = tmp_path / "hub"
+    repo_dir = cache / "datasets--liarliar--Daily-Omni"
+    snapshot = repo_dir / "snapshots" / "deadbeef"
+    snapshot.mkdir(parents=True)
+    if with_qa:
+        _write_qa_json(snapshot)
+    (repo_dir / "refs").mkdir()
+    (repo_dir / "refs" / "main").write_text("deadbeef", encoding="utf-8")
+
+    monkeypatch.setattr(constants, "HF_HUB_CACHE", str(cache))
+    monkeypatch.setattr(constants, "HF_HUB_OFFLINE", True)
+    return snapshot
+
+
 def test_resolve_local_root_returns_none_for_hub_id() -> None:
     assert resolve_daily_omni_local_root("liarliar/Daily-Omni") is None
     assert resolve_daily_omni_local_root("") is None
@@ -90,3 +116,37 @@ def test_missing_qa_json_reports_none(tmp_path: Path) -> None:
     root = resolve_daily_omni_local_root(str(tmp_path))
     assert daily_omni_local_qa_json(root) is None
     assert daily_omni_local_videos_dir(root) is None
+
+
+def test_hub_id_resolves_to_offline_cache(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    snapshot = _stage_offline_hub_cache(tmp_path, monkeypatch)
+
+    root = ensure_daily_omni_hub_root(_HUB_ID)
+
+    assert root == snapshot.resolve()
+    assert daily_omni_local_qa_json(root) == (snapshot / "qa.json").resolve()
+
+
+def test_dataset_loads_hub_id_without_network(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    """The regression this file exists for: a Hub id must not require ``load_dataset``."""
+    snapshot = _stage_offline_hub_cache(tmp_path, monkeypatch)
+    # Any use of `datasets` here means we went back to the path that cannot read the hub cache.
+    monkeypatch.setattr("vllm_omni.benchmarks.data_modules.daily_omni_dataset.load_dataset", None)
+
+    dataset = DailyOmniDataset(dataset_path=_HUB_ID, random_seed=0)
+
+    assert dataset.qa_json_path == (snapshot / "qa.json").resolve()
+    assert [row["video_id"] for row in dataset.data] == ["vid0"]
+
+
+def test_uncached_hub_id_reports_both_attempts(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
+    _stage_offline_hub_cache(tmp_path, monkeypatch, with_qa=False)
+    monkeypatch.setattr("vllm_omni.benchmarks.data_modules.daily_omni_dataset.load_dataset", None)
+
+    with pytest.raises(RuntimeError) as excinfo:
+        DailyOmniDataset(dataset_path="someone-else/Daily-Omni", random_seed=0)
+
+    message = str(excinfo.value)
+    assert "someone-else/Daily-Omni" in message
+    assert "snapshot_download failed" in message
+    assert "--daily-omni-qa-json" in message