feat: tier-aware diag/val split with val-power repair (design 5.1)

tests/unit/test_pools_video_atomic.py

@@ -135,3 +135,60 @@ def test_baseline_val_accuracy_reflects_validation():
     assert len(pools.validation) == 2
     assert pools.baseline_val_accuracy == pytest.approx(0.5)
     assert pools.diagnosis == []
+
+
+def test_tier_aware_keeps_high_t2_in_diag():
+    """错题视频组按 T2 含量升序进 val：T2 高的组保留在 diagnosis。"""
+    from app.harness.pools import split_by_video_assignment
+    from core.types import GeneratedQuestion
+
+    def _q(qid, vid):
+        return GeneratedQuestion(
+            question_id=qid, video_id=vid, task_type="X", question="q",
+            options=["A", "B"], answer="A", source_nodes=[], difficulty="easy",
+        )
+
+    # 4 个错题视频（每视频 1 题），T2 数分别 2/1/0/0
+    questions = [_q(f"{v}-1", v) for v in ("vA", "vB", "vC", "vD")]
+    assignment = {v: "trainval" for v in ("vA", "vB", "vC", "vD")}
+    correctness = {f"{v}-1": False for v in ("vA", "vB", "vC", "vD")}
+    wrong_tier = {"vA": 2, "vB": 1, "vC": 0, "vD": 0}
+
+    pools = split_by_video_assignment(
+        questions, assignment, correctness, val_ratio=0.5, seed=7,
+        wrong_tier_by_video=wrong_tier,
+    )
+    diag_vids = {q.video_id for q in pools.diagnosis}
+    # T2 最高的 vA 必留 diag；T2=0 的组优先进 val
+    assert "vA" in diag_vids
+    assert "vB" in diag_vids
+
+
+def test_val_wrong_min_repair_pulls_from_diag():
+    """val 错题不足 val_wrong_min 时从 diag 换入低 T2 错题组补足。"""
+    from app.harness.pools import split_by_video_assignment
+    from core.types import GeneratedQuestion
+
+    def _q(qid, vid, correct):
+        return GeneratedQuestion(
+            question_id=qid, video_id=vid, task_type="X", question="q",
+            options=["A", "B"], answer="A", source_nodes=[], difficulty="easy",
+        )
+
+    # 8 错题视频 + 2 正确视频；val_ratio 小使初分 val 错题不足，触发修复
+    vids_wrong = [f"w{i}" for i in range(8)]
+    vids_correct = ["c0", "c1"]
+    questions = [_q(f"{v}-1", v, False) for v in vids_wrong] + [
+        _q(f"{v}-1", v, True) for v in vids_correct
+    ]
+    assignment = {v: "trainval" for v in vids_wrong + vids_correct}
+    correctness = {f"{v}-1": False for v in vids_wrong}
+    correctness.update({f"{v}-1": True for v in vids_correct})
+    wrong_tier = {v: i for i, v in enumerate(vids_wrong)}  # 递增 T2
+
+    pools = split_by_video_assignment(
+        questions, assignment, correctness, val_ratio=0.1, seed=7,
+        wrong_tier_by_video=wrong_tier, val_wrong_min=4,
+    )
+    val_wrong = sum(1 for q in pools.validation if not correctness[q.question_id])
+    assert val_wrong >= 4, f"功效修复后 val 错题 {val_wrong} < 4"