feat(question_gen): load_benchmark — benchmark JSON 加载

从 JSON 目录 glob *.json 加载题目，stem 作 video_id。
legacy schema 无 difficulty 字段时赋 _LEGACY_DEFAULT_DIFFICULTY 常量。
options/source_nodes 转 tuple 配合 frozen dataclass。

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tests/unit/test_question_loader.py

@@ -0,0 +1,129 @@
+"""app/question_gen/loader.py 单元测试。"""
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+
+import pytest
+
+from app.question_gen.loader import load_benchmark
+from core.types import GeneratedQuestion
+
+
+@pytest.fixture()
+def benchmark_dir(tmp_path: Path) -> Path:
+    """创建包含 benchmark JSON 的临时目录。"""
+    data = [
+        {
+            "question_id": "1-1",
+            "task_type": "Action Reasoning",
+            "question": "What happened?",
+            "options": ["A. X", "B. Y", "C. Z", "D. W"],
+            "answer": "A",
+        },
+        {
+            "question_id": "1-2",
+            "task_type": "OCR Problems",
+            "question": "What text is shown?",
+            "options": ["A. Hello", "B. World", "C. Foo", "D. Bar"],
+            "answer": "B",
+        },
+    ]
+    (tmp_path / "video_abc.json").write_text(json.dumps(data), encoding="utf-8")
+    return tmp_path
+
+
+class TestLoadBenchmark:
+    def test_loads_questions_from_json(self, benchmark_dir: Path) -> None:
+        questions = load_benchmark(benchmark_dir)
+        assert len(questions) == 2
+
+    def test_video_id_from_filename(self, benchmark_dir: Path) -> None:
+        questions = load_benchmark(benchmark_dir)
+        assert all(q.video_id == "video_abc" for q in questions)
+
+    def test_fields_mapped_correctly(self, benchmark_dir: Path) -> None:
+        questions = load_benchmark(benchmark_dir)
+        q = questions[0]
+        assert q.question_id == "1-1"
+        assert q.task_type == "Action Reasoning"
+        assert q.question == "What happened?"
+        assert q.options == ("A. X", "B. Y", "C. Z", "D. W")
+        assert q.answer == "A"
+
+    def test_options_is_tuple(self, benchmark_dir: Path) -> None:
+        questions = load_benchmark(benchmark_dir)
+        assert isinstance(questions[0].options, tuple)
+
+    def test_source_nodes_is_empty_tuple(self, benchmark_dir: Path) -> None:
+        questions = load_benchmark(benchmark_dir)
+        assert questions[0].source_nodes == ()
+
+    def test_difficulty_defaults_to_medium_for_legacy(self, benchmark_dir: Path) -> None:
+        questions = load_benchmark(benchmark_dir)
+        assert questions[0].difficulty == "medium"
+
+    def test_difficulty_from_json_when_present(self, tmp_path: Path) -> None:
+        data = [
+            {
+                "question_id": "2-1",
+                "task_type": "OCR Problems",
+                "question": "Q?",
+                "options": ["A. 1", "B. 2", "C. 3", "D. 4"],
+                "answer": "C",
+                "difficulty": "hard",
+            }
+        ]
+        (tmp_path / "vid.json").write_text(json.dumps(data), encoding="utf-8")
+        questions = load_benchmark(tmp_path)
+        assert questions[0].difficulty == "hard"
+
+    def test_empty_directory_returns_empty_list(self, tmp_path: Path) -> None:
+        questions = load_benchmark(tmp_path)
+        assert questions == []
+
+    def test_sorted_by_filename(self, tmp_path: Path) -> None:
+        for name in ["z_video.json", "a_video.json"]:
+            data = [
+                {
+                    "question_id": f"{name}-1",
+                    "task_type": "T",
+                    "question": "Q?",
+                    "options": ["A", "B", "C", "D"],
+                    "answer": "A",
+                }
+            ]
+            (tmp_path / name).write_text(json.dumps(data), encoding="utf-8")
+        questions = load_benchmark(tmp_path)
+        assert questions[0].video_id == "a_video"
+        assert questions[1].video_id == "z_video"
+
+    def test_returns_generated_question_instances(self, benchmark_dir: Path) -> None:
+        questions = load_benchmark(benchmark_dir)
+        assert all(isinstance(q, GeneratedQuestion) for q in questions)
+
+    def test_loads_real_benchmark(self) -> None:
+        """使用真实 benchmark 数据验证加载正确性。"""
+        real_dir = Path("store/questions/benchmarks/Video-MME")
+        if not real_dir.exists():
+            pytest.skip("真实 benchmark 数据不存在")
+        questions = load_benchmark(real_dir)
+        assert len(questions) > 0
+        for q in questions:
+            assert isinstance(q, GeneratedQuestion)
+            assert len(q.options) == 4
+            assert q.answer in ("A", "B", "C", "D")
+
+    def test_malformed_json_raises(self, tmp_path: Path) -> None:
+        """非法 JSON 文件应抛出 json.JSONDecodeError。"""
+        (tmp_path / "bad.json").write_text("not valid json{{{", encoding="utf-8")
+        with pytest.raises(json.JSONDecodeError):
+            load_benchmark(tmp_path)
+
+    def test_missing_required_field_raises(self, tmp_path: Path) -> None:
+        """缺少必需字段（如 question_id）应抛出 KeyError。"""
+        data = [{"task_type": "T", "question": "Q?", "options": ["A"], "answer": "A"}]
+        (tmp_path / "vid.json").write_text(json.dumps(data), encoding="utf-8")
+        with pytest.raises(KeyError):
+            load_benchmark(tmp_path)