fix: add retries and timeout for akshare data fetch

data_fetcher.py

@@ -1,5 +1,7 @@
 from datetime import datetime, timedelta
+import os
 import threading
+import time
 
 import akshare as ak
 import pandas as pd
@@ -8,6 +10,9 @@ _TRADE_CALENDAR_CACHE: pd.DatetimeIndex | None = None
 _TRADE_CALENDAR_CACHED_AT: datetime | None = None
 _TRADE_CALENDAR_CACHE_TTL = timedelta(hours=12)
 _TRADE_CALENDAR_LOCK = threading.Lock()
+_AK_RETRY_COUNT = max(1, int(os.environ.get("AK_RETRY_COUNT", "3")))
+_AK_RETRY_BASE_SLEEP = float(os.environ.get("AK_RETRY_BASE_SLEEP", "0.8"))
+_AK_TIMEOUT = float(os.environ.get("AK_TIMEOUT", "15"))
 
 
 def _normalize_symbol(raw_symbol: str) -> str:
@@ -31,6 +36,24 @@ def _normalize_symbol(raw_symbol: str) -> str:
     return symbol
 
 
+def _retry_ak_call(fn, *, call_name: str):
+    """
+    Retry wrapper for AkShare calls to handle transient network disconnects.
+    """
+    last_exc: Exception | None = None
+    for attempt in range(1, _AK_RETRY_COUNT + 1):
+        try:
+            return fn()
+        except Exception as exc:  # pragma: no cover - external IO
+            last_exc = exc
+            if attempt >= _AK_RETRY_COUNT:
+                break
+            time.sleep(_AK_RETRY_BASE_SLEEP * (2 ** (attempt - 1)))
+    raise RuntimeError(
+        f"AkShare call failed after {_AK_RETRY_COUNT} attempts ({call_name}): {last_exc}"
+    ) from last_exc
+
+
 def _get_trade_calendar_cached() -> pd.DatetimeIndex:
     """
     Fetch and cache exchange trading dates in-process to avoid repeated
@@ -47,7 +70,10 @@ def _get_trade_calendar_cached() -> pd.DatetimeIndex:
         ):
             return _TRADE_CALENDAR_CACHE
 
-    cal = ak.tool_trade_date_hist_sina()
+    cal = _retry_ak_call(
+        lambda: ak.tool_trade_date_hist_sina(),
+        call_name="tool_trade_date_hist_sina",
+    )
     cal_col = "trade_date" if "trade_date" in cal.columns else "日期"
     all_dates = pd.to_datetime(cal[cal_col]).sort_values().drop_duplicates()
     cached = pd.DatetimeIndex(all_dates)
@@ -73,12 +99,16 @@ def fetch_stock_data(
     # 4x buffer to account for weekends/long holidays.
     start_date = (datetime.today() - timedelta(days=lookback * 4)).strftime("%Y%m%d")
 
-    df = ak.stock_zh_a_hist(
-        symbol=normalized_symbol,
-        period="daily",
-        start_date=start_date,
-        end_date=end_date,
-        adjust="qfq",
+    df = _retry_ak_call(
+        lambda: ak.stock_zh_a_hist(
+            symbol=normalized_symbol,
+            period="daily",
+            start_date=start_date,
+            end_date=end_date,
+            adjust="qfq",
+            timeout=_AK_TIMEOUT,
+        ),
+        call_name=f"stock_zh_a_hist(symbol={normalized_symbol})",
     )
 
     if df is None or df.empty: