diff --git a/src/fetcher/kline_fetcher.py b/src/fetcher/kline_fetcher.py
index 523ea58..2f3b9a9 100644
--- a/src/fetcher/kline_fetcher.py
+++ b/src/fetcher/kline_fetcher.py
@@ -76,7 +76,7 @@ class KlineFetcher:
         df.columns = [str(c).lower() for c in df.columns]
         cmap = {}
         for c in df.columns:
-            if c in ('时间', 'bar_time', 'date', '日期'):
+            if c in ('时间', 'bar_time', 'date', '日期', 'day'):
                 cmap[c] = 'bar_time'
             elif c in ('开盘', 'open'):
                 cmap[c] = 'open'
diff --git a/src/web/server.py b/src/web/server.py
index b4ce674..58260b0 100644
--- a/src/web/server.py
+++ b/src/web/server.py
@@ -107,8 +107,30 @@ async def recent_events(_request):
 
 async def quant_recommendations(_request):
     q = _request.app['quant']
-    return web.json_response({'ts': q.last_scored_at,
-                              'list': (q.last_ranking or [])[:50]})
+    if q.last_ranking:
+        return web.json_response({'ts': q.last_scored_at,
+                                  'list': (q.last_ranking or [])[:50]})
+    # 重启后内存为空：回退数据库最近一批推荐
+    import sqlite3
+    db = str(ROOT / 'data' / 'a_stock.db')
+    try:
+        conn = sqlite3.connect(db, check_same_thread=False)
+        latest_ts = conn.execute(
+            "SELECT ts FROM quant_recommendation ORDER BY id DESC LIMIT 1").fetchone()
+        rows = []
+        if latest_ts:
+            rows = conn.execute(
+                "SELECT code,name,price,score,stars,buy_low,buy_high,"
+                "expected_return_pct,reason FROM quant_recommendation "
+                "WHERE ts=? ORDER BY score DESC LIMIT 50", (latest_ts[0],)).fetchall()
+        conn.close()
+    except Exception:
+        rows = []
+    items = [{'code': r[0], 'name': r[1] or r[0], 'price': r[2], 'score': r[3],
+              'stars': r[4], 'buy_low': r[5], 'buy_high': r[6],
+              'expected_return_pct': r[7], 'reason': r[8]} for r in rows]
+    return web.json_response({'ts': latest_ts[0] if rows else None, 'list': items,
+                              'source': 'db'})
 
 
 async def quant_weights(_request):