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

tests/unit/test_harness_store.py

@@ -338,6 +338,44 @@ class TestExtractRunDb:
         with pytest.raises(RuntimeError, match="无 run_id="):
             extract_run_db(src, dst, "nonexistent")
 
+    def test_dedupe_per_question_keeps_first_row(self, tmp_path):
+        """dedupe_per_question=True 时每 question_id 只保留 rowid 最小的首行。"""
+        import sqlite3
+
+        src = tmp_path / "src.db"
+        conn = sqlite3.connect(src)
+        conn.execute(
+            "CREATE TABLE _runs (run_id TEXT PRIMARY KEY, started_at TEXT)"
+        )
+        conn.execute("INSERT INTO _runs VALUES ('r1', 't0')")
+        conn.execute(
+            "CREATE TABLE predictions (run_id TEXT, question_id TEXT, prediction TEXT)"
+        )
+        # 743-1 三行（模拟 error/budget/finished），首行 prediction=NULL
+        conn.executemany(
+            "INSERT INTO predictions VALUES (?,?,?)",
+            [
+                ("r1", "743-1", None),
+                ("r1", "743-1", None),
+                ("r1", "743-1", "C"),
+                ("r1", "q2", "A"),
+            ],
+        )
+        conn.commit()
+        conn.close()
+
+        dst = tmp_path / "dst.db"
+        from app.harness.store import extract_run_db
+
+        extract_run_db(src, dst, "r1", dedupe_per_question=True)
+
+        out = sqlite3.connect(dst)
+        rows = out.execute(
+            "SELECT question_id, prediction FROM predictions ORDER BY question_id"
+        ).fetchall()
+        out.close()
+        assert rows == [("743-1", None), ("q2", "A")], f"未按 rowid 首行去重: {rows}"
+
 
 # ---------------------------------------------------------------------------
 # promote_to_seed