feat: add dedupe_per_question to extract_run_db (canonical 902->900)

app/harness/store.py

@@ -266,7 +266,9 @@ def read_seed(store_dir: Path, name: str) -> dict:
     return json.loads(seed_json.read_text())
 
 
-def extract_run_db(src_db: Path, dst_db: Path, run_id: str) -> None:
+def extract_run_db(
+    src_db: Path, dst_db: Path, run_id: str, *, dedupe_per_question: bool = False
+) -> None:
     """从 src_db 抽出某 run_id 的 _runs + predictions 行，写一个最小 db（种子 baseline.db）。
 
     用源表的**原始 CREATE 语句**重建目标表，保留主键/列类型/约束——
@@ -277,6 +279,9 @@ def extract_run_db(src_db: Path, dst_db: Path, run_id: str) -> None:
         src_db: 源 harness.db。
         dst_db: 目标 db（不得已存在）。
         run_id: 要抽取的 run。
+        dedupe_per_question: True 时 predictions 表每 question_id 仅保留 rowid 最小
+            的首行（对齐 canonical「每 question_id 取第一行 ORDER BY rowid」口径，
+            902→900）。_runs 表不受影响。
 
     异常:
         RuntimeError: 源中无该表或无该 run 的行。
@@ -294,9 +299,17 @@ def extract_run_db(src_db: Path, dst_db: Path, run_id: str) -> None:
             dst.execute(create_sql[0])
             cols = [r[1] for r in src.execute(f"PRAGMA table_info({table})")]
             col_sql = ", ".join(cols)
-            rows = src.execute(
-                f"SELECT {col_sql} FROM {table} WHERE run_id=?", (run_id,)
-            ).fetchall()
+            if table == "predictions" and dedupe_per_question:
+                rows = src.execute(
+                    f"SELECT {col_sql} FROM {table} WHERE run_id=? "
+                    "AND rowid IN (SELECT MIN(rowid) FROM predictions "
+                    "WHERE run_id=? GROUP BY question_id)",
+                    (run_id, run_id),
+                ).fetchall()
+            else:
+                rows = src.execute(
+                    f"SELECT {col_sql} FROM {table} WHERE run_id=?", (run_id,)
+                ).fetchall()
             if not rows:
                 raise RuntimeError(f"{table} 中无 run_id={run_id} 的行")
             ph = ", ".join("?" * len(cols))