fix(loader): use video_id from JSON data instead of filename

load_benchmark used the JSON filename stem as video_id, which broke
v2-360 questions (all 180 questions got video_id='accepted_questions').
Now uses qa['video_id'] when present, falls back to filename for
Video-MME format compatibility.

app/question_gen/loader.py

@@ -21,8 +21,10 @@ _LEGACY_DEFAULT_DIFFICULTY = "medium"
 def load_benchmark(questions_dir: Path) -> list[GeneratedQuestion]:
     """从 benchmark JSON 目录加载题目列表。
 
-    每个 JSON 文件以文件名（不含扩展名）作为 video_id，
-    文件内容为题目数组。
+    video_id 优先使用题目 JSON 中的 ``video_id`` 字段；若缺失则回退到
+    文件名（不含扩展名）。Video-MME benchmark 按视频拆文件（文件名即
+    video_id），v2 生成题把多视频题目合并在单个 JSON 中（每条记录自带
+    ``video_id``），两种格式均兼容。
 
     参数:
         questions_dir: 包含 *.json 文件的目录路径。
@@ -32,20 +34,21 @@ def load_benchmark(questions_dir: Path) -> list[GeneratedQuestion]:
     """
     results: list[GeneratedQuestion] = []
     for path in sorted(questions_dir.glob("*.json")):
-        video_id = path.stem
+        fallback_video_id = path.stem
         with open(path, encoding="utf-8") as f:
             qa_list: list[dict] = json.load(f)
         for qa in qa_list:
             results.append(
                 GeneratedQuestion(
                     question_id=qa["question_id"],
-                    video_id=video_id,
+                    video_id=qa.get("video_id", fallback_video_id),
                     task_type=qa["task_type"],
                     question=qa["question"],
                     options=tuple(qa["options"]),
                     answer=qa["answer"],
                     source_nodes=tuple(qa.get("source_nodes", ())),
                     difficulty=qa.get("difficulty", _LEGACY_DEFAULT_DIFFICULTY),
+                    family=qa.get("family"),
                     skill_target=qa.get("skill_target"),
                     difficulty_steps=qa.get("difficulty_steps"),
                 )