feat: add selector_scores observation column to question_gen_items

app/question_gen/run_store.py

@@ -125,6 +125,7 @@ CREATE TABLE IF NOT EXISTS question_gen_items (
     gate_reject_reason TEXT,
     final_status      TEXT NOT NULL DEFAULT 'pending',
     difficulty_steps  INTEGER,
+    selector_scores   TEXT,
     created_at        TEXT NOT NULL DEFAULT (datetime('now'))
 );
 """
@@ -177,11 +178,14 @@ class QuestionGenStore:
             self._conn.execute(idx_sql)
         self._conn.commit()
 
-        # 幂等迁移：为已有表加 sub_pattern 列
+        # 幂等迁移：为已有表加 sub_pattern / selector_scores 列
         cols = {r[1] for r in self._conn.execute("PRAGMA table_info(question_gen_items)")}
         if "sub_pattern" not in cols:
             self._conn.execute("ALTER TABLE question_gen_items ADD COLUMN sub_pattern TEXT")
             self._conn.commit()
+        if "selector_scores" not in cols:
+            self._conn.execute("ALTER TABLE question_gen_items ADD COLUMN selector_scores TEXT")
+            self._conn.commit()
 
     def record_run_start(self, run_id: str, git_sha: str, config_snapshot: str) -> None:
         """记录批次开始。
@@ -378,6 +382,29 @@ class QuestionGenStore:
         if cursor.rowcount == 0:
             raise ValueError(f"item_id 不存在: {item_id}")
 
+    def update_selector_scores(self, item_id: str, selector_scores_json: str) -> None:
+        """写入 grounded selector 打分观测（JSON 字符串）。
+
+        Parameters
+        ----------
+        item_id : str
+            题目唯一 ID。
+        selector_scores_json : str
+            观测 JSON：correct_score / chosen / pool_size / anneal_rounds / hard_fail。
+
+        Raises
+        ------
+        ValueError
+            item_id 不存在时抛出。
+        """
+        cursor = self._conn.execute(
+            "UPDATE question_gen_items SET selector_scores=? WHERE item_id=?",
+            (selector_scores_json, item_id),
+        )
+        self._conn.commit()
+        if cursor.rowcount == 0:
+            raise ValueError(f"item_id 不存在: {item_id}")
+
     def get_run_stats(self, run_id: str) -> RunStats:
         """查询批次统计摘要。
 

research-wiki/schemas/question-gen-items.md

@@ -28,8 +28,11 @@ date: 2026-07-12
 | `reject_reason` | TEXT | | 拒因文本（首个拒绝门的判定摘要） |
 | `final_status` | TEXT | NOT NULL | accepted / rejected / pending |
 | `difficulty_steps` | INTEGER | | 重量抽检产出 Agent 步数（NULL=未抽检） |
+| `selector_scores` | TEXT | | grounded selector 打分观测（JSON，见下方结构；NULL=未打分） |
 | `created_at` | TEXT | NOT NULL | ISO8601 |
 
+`selector_scores` JSON 结构：`{correct_score: float, chosen: float[], pool_size: int, anneal_rounds: int, delta_high_final: float, hard_fail: bool}`。
+
 ## DDL
 
 ```sql
@@ -49,6 +52,7 @@ CREATE TABLE IF NOT EXISTS question_gen_items (
     reject_reason     TEXT,
     final_status      TEXT NOT NULL DEFAULT 'pending',
     difficulty_steps  INTEGER,
+    selector_scores   TEXT,
     created_at        TEXT NOT NULL
 );
 

tests/unit/test_run_store_selector_scores.py

@@ -0,0 +1,56 @@
+"""selector_scores 列幂等迁移 + update_selector_scores 写入。"""
+
+import json
+
+from app.question_gen.run_store import QuestionGenStore
+
+
+def _store(tmp_path):
+    return QuestionGenStore(tmp_path / "q.db")
+
+
+def test_selector_scores_column_exists(tmp_path):
+    store = _store(tmp_path)
+    cols = {r[1] for r in store._conn.execute("PRAGMA table_info(question_gen_items)")}
+    assert "selector_scores" in cols
+    store.close()
+
+
+def test_update_selector_scores_writes_json(tmp_path):
+    store = _store(tmp_path)
+    store.record_run_start("run1", "sha", "{}")
+    store.record_item(
+        item_id="it1",
+        run_id="run1",
+        slot_id="s1",
+        video_id="v1",
+        family="ACTION_RECOGNITION",
+        task_type="Action Recognition",
+        skill_target="M1_AR",
+        attempt=1,
+        question_text="?",
+        sub_pattern="temporal_reasoning_failure",
+    )
+    payload = {
+        "correct_score": 0.8,
+        "chosen": [0.7, 0.6, 0.55],
+        "pool_size": 24,
+        "anneal_rounds": 0,
+        "hard_fail": False,
+    }
+    store.update_selector_scores("it1", json.dumps(payload))
+    row = store._conn.execute(
+        "SELECT selector_scores FROM question_gen_items WHERE item_id='it1'"
+    ).fetchone()
+    assert json.loads(row[0])["correct_score"] == 0.8
+    store.close()
+
+
+def test_update_selector_scores_unknown_item_raises(tmp_path):
+    store = _store(tmp_path)
+    try:
+        store.update_selector_scores("missing", "{}")
+        raise AssertionError("应抛 ValueError")
+    except ValueError:
+        pass
+    store.close()