chore: snapshot in-progress question-gen work before preflight fixes

app/question_gen/families.py

@@ -81,18 +81,11 @@ RETRIEVAL_FAMILY = QuestionFamilySpec(
     ),
     legal_task_types=frozenset(
         [
-            "Action Recognition",
-            "Action Reasoning",
-            "Action Prediction",
-            "Action Sequence",
             "Object Recognition",
             "Object Reasoning",
-            "Object Interaction",
-            "Scene Understanding",
-            "Event Reasoning",
-            "Causal Reasoning",
-            "Temporal Reasoning",
-            "Spatial Reasoning",
+            "Action Recognition",
+            "Attribute Perception",
+            "OCR Problems",
         ]
     ),
     leak_profile=LeakTestProfile(
@@ -116,10 +109,7 @@ REASONING_FAMILY = QuestionFamilySpec(
         [
             "Action Reasoning",
             "Object Reasoning",
-            "Event Reasoning",
-            "Causal Reasoning",
-            "Temporal Reasoning",
-            "Spatial Reasoning",
+            "Information Synopsis",
         ]
     ),
     leak_profile=LeakTestProfile(
@@ -141,10 +131,10 @@ ENUMERATION_FAMILY = QuestionFamilySpec(
     ),
     legal_task_types=frozenset(
         [
-            "Action Sequence",
-            "Object Recognition",
-            "Object Interaction",
-            "Scene Understanding",
+            "Counting Problem",
+            "Temporal Reasoning",
+            "Temporal Perception",
+            "Information Synopsis",
         ]
     ),
     leak_profile=LeakTestProfile(
@@ -166,10 +156,10 @@ VISUAL_FAMILY = QuestionFamilySpec(
     ),
     legal_task_types=frozenset(
         [
-            "Object Recognition",
-            "Scene Understanding",
+            "Attribute Perception",
+            "Counting Problem",
+            "OCR Problems",
             "Action Recognition",
-            "Spatial Reasoning",
         ]
     ),
     leak_profile=LeakTestProfile(
@@ -191,9 +181,8 @@ SPATIAL_FAMILY = QuestionFamilySpec(
     ),
     legal_task_types=frozenset(
         [
+            "Spatial Perception",
             "Spatial Reasoning",
-            "Object Interaction",
-            "Scene Understanding",
         ]
     ),
     leak_profile=LeakTestProfile(

app/question_gen/loader.py

@@ -124,19 +124,6 @@ def stratified_sample(
     return flatten_units(sampled)
 
 
-def _unit_correct(unit: QuestionUnit, correctness: dict[str, bool]) -> bool:
-    """单元级正确性：成员全部答对才算对（缺失按 False，宽松口径）。
-
-    参数:
-        unit: 目标单元（single 1 题，pair 2 题）。
-        correctness: question_id -> 基线是否答对。
-
-    返回:
-        pair 走双向 AND、single 即单题正确性；任一成员缺失或答错即 False。
-    """
-    return all(correctness.get(q.question_id, False) for q in unit.questions)
-
-
 def _ratio_stratified_sample(
     pool: list[QuestionUnit],
     correctness: dict[str, bool],
@@ -158,9 +145,17 @@ def _ratio_stratified_sample(
 
     异常:
         ValueError: 对单元或错单元层不足。
+
+    关键实现:
+        unit_correctness 采用函数内延迟导入：loader 属 question_gen，
+        question_units 属 harness，模块级导入将触发循环依赖（沿用 build_units /
+        flatten_units 的既有做法）。以 strict=False 保持"缺基线对错即视为未答对"的
+        原 loose 语义不变。
     """
-    correct = [u for u in pool if _unit_correct(u, correctness)]
-    wrong = [u for u in pool if not _unit_correct(u, correctness)]
+    from app.harness.question_units import unit_correctness
+
+    correct = [u for u in pool if unit_correctness(u, correctness, strict=False)]
+    wrong = [u for u in pool if not unit_correctness(u, correctness, strict=False)]
     n_correct = round(size * correct_ratio)
     n_wrong = size - n_correct
     if len(correct) < n_correct or len(wrong) < n_wrong: