fix(backtest): A股适配层—定寸/做空拦截/真实费用/口径统一(Phase1+2)

审计发现包装层系统性失真(2 CRITICAL+7 HIGH)，vnpy底座可信但A股场景未适配：
- C1 定寸: engine.size=N(满仓手数)，策略volume=1手=N股，开平对称(pos归零)
- C2 做空拦截: SHORT+OPEN拒单，long-only，SHORT+CLOSE平多允许
- H3 A股费用: AShareDailyResult重算(佣金保底5元/印花税卖方/过户费沪市)
- H4 收益口径: simple return从balance算(不再用vnpy log return喂empyrical)
- H5+口径: benchmark ffill对齐不缩样本; sizing_shares_per_lot暴露
- H7 退化检测: 零成交/空数据标degenerate不静默done
- H8 task_id: optimize/factor用uuid4(原id()内存地址)
- 静默except改warning

验证: 容器内真实vnpy DoubleMa 600000 2022-2024, total_return 1e-6→42.3%,
end_balance 100万→142万, SHORT+OPEN成交0笔, N=7800股/手.
22 backtest测试全绿(含集成测试), API健康200.

tests/backtest/test_metrics.py

@@ -1,3 +1,8 @@
+"""metrics.py 纯函数单测。
+
+H4: compute_metrics 从 daily_df["balance"] 自算 simple return（不再用 vnpy log return 列），
+所以测试需构造含 "balance" 列的 daily_df。
+"""
 import sys, os
 _VNPY_SRC = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", "vnpy_v4.4.0"))
 sys.path.insert(0, _VNPY_SRC)
@@ -7,20 +12,36 @@ import numpy as np
 import empyrical
 from sanguo_backtest.metrics import compute_metrics, MetricsResult, BENCHMARK_SYMBOL
 
-def _make_daily(returns):
+
+def _make_daily_balance(returns: np.ndarray) -> pd.DataFrame:
+    """从收益率数组构造含 balance 列的 daily_df。
+
+    compute_metrics 内部算 simple return = balance.pct_change().fillna(0)，
+    所以实际传入 metrics 的 strat = [0, r0, r1, ...]（首项 NaN→0）。
+    """
     idx = pd.date_range("2024-01-01", periods=len(returns), freq="B")
-    return pd.DataFrame({"return": returns}, index=idx)
+    balance = (1 + pd.Series(returns, index=idx)).cumprod()
+    return pd.DataFrame({"balance": balance}, index=idx)
+
+
+def _actual_strat(returns: np.ndarray) -> pd.Series:
+    """compute_metrics 从 balance 推导出的实际 strat 序列（首项=0）。"""
+    idx = pd.date_range("2024-01-01", periods=len(returns), freq="B")
+    balance = (1 + pd.Series(returns, index=idx)).cumprod()
+    return balance.pct_change().fillna(0)
+
 
 def test_compute_metrics_scalars_match_empyrical():
     np.random.seed(42)
-    strat = pd.Series(np.random.normal(0.001, 0.02, 100),
+    raw_returns = np.random.normal(0.001, 0.02, 100)
+    strat = _actual_strat(raw_returns)
+    bench = pd.Series(np.random.normal(0.0005, 0.015, 100),
                       index=pd.date_range("2024-01-01", periods=100, freq="B"))
-    bench = pd.Series(np.random.normal(0.0005, 0.015, 100), index=strat.index)
-    daily_df = pd.DataFrame({"return": strat.values}, index=strat.index)
+    daily_df = _make_daily_balance(raw_returns)
 
     res = compute_metrics(daily_df, bench)
     assert isinstance(res, MetricsResult)
-    # 标量口径与 empyrical 直接计算一致
+    # 标量口径与 empyrical 直接计算一致（用推导出的 strat）
     assert abs(res.scalars["alpha"] - empyrical.alpha(strat, bench)) < 1e-9
     assert abs(res.scalars["beta"] - empyrical.beta(strat, bench)) < 1e-9
     assert abs(res.scalars["sharpe_ratio"] - empyrical.sharpe_ratio(strat)) < 1e-9
@@ -28,26 +49,54 @@ def test_compute_metrics_scalars_match_empyrical():
     assert abs(res.scalars["max_drawdown"] - empyrical.max_drawdown(strat)) < 1e-9
     assert abs(res.scalars["annual_volatility"] - empyrical.annual_volatility(strat)) < 1e-9
 
+
 def test_compute_metrics_has_all_required_scalars():
-    strat = pd.Series([0.01, -0.005, 0.02, 0.0],
+    daily_df = _make_daily_balance([0.01, -0.005, 0.02, 0.0])
+    bench = pd.Series([0.005, 0.001, 0.01, -0.002],
                       index=pd.date_range("2024-01-01", periods=4, freq="B"))
-    bench = pd.Series([0.005, 0.001, 0.01, -0.002], index=strat.index)
-    res = compute_metrics(pd.DataFrame({"return": strat.values}, index=strat.index), bench)
-    required = {"total_return","annual_return","alpha","beta","sharpe_ratio",
-                "sortino_ratio","information_ratio","annual_volatility","max_drawdown",
-                "benchmark_return","benchmark_volatility"}
+    res = compute_metrics(daily_df, bench)
+    required = {"total_return", "annual_return", "alpha", "beta", "sharpe_ratio",
+                "sortino_ratio", "information_ratio", "annual_volatility", "max_drawdown",
+                "benchmark_return", "benchmark_volatility"}
     assert required.issubset(res.scalars.keys())
 
+
 def test_compute_metrics_series_keys_and_length():
-    strat = pd.Series(np.random.normal(0, 0.01, 50),
+    raw_returns = np.random.normal(0, 0.01, 50)
+    daily_df = _make_daily_balance(raw_returns)
+    bench = pd.Series(np.random.normal(0, 0.01, 50),
                       index=pd.date_range("2024-01-01", periods=50, freq="B"))
-    bench = pd.Series(np.random.normal(0, 0.01, 50), index=strat.index)
-    res = compute_metrics(pd.DataFrame({"return": strat.values}, index=strat.index), bench)
-    for key in ["equity_curve","benchmark_curve","alpha","beta","drawdown"]:
+    res = compute_metrics(daily_df, bench)
+    for key in ["equity_curve", "benchmark_curve", "alpha", "beta", "drawdown"]:
         assert key in res.series
         assert len(res.series[key]) == 50
     assert res.series["drawdown"].max() <= 1e-9  # 回撤 <= 0
 
+
 def test_benchmark_symbol_map():
     assert BENCHMARK_SYMBOL["hs300"] == "sh000300"
     assert BENCHMARK_SYMBOL["zz500"] == "sz000905"
+
+
+def test_compute_metrics_ffill_aligns_benchmark():
+    """H5: benchmark 有缺失日期时 ffill 对齐，不丢策略交易日。"""
+    raw_returns = np.random.normal(0, 0.01, 10)
+    daily_df = _make_daily_balance(raw_returns)
+    # benchmark 只有部分日期（模拟停盘日缺失）
+    partial_dates = daily_df.index[::2]  # 隔日取一个
+    bench = pd.Series([0.001] * len(partial_dates), index=partial_dates)
+    res = compute_metrics(daily_df, bench)
+    # 不应崩溃，且 strat 长度 = daily_df 行数（没有被 dropna 削短）
+    assert len(res.series["equity_curve"]) == 10
+
+
+def test_compute_metrics_raises_without_balance():
+    """缺少 balance 列时应抛 ValueError。"""
+    idx = pd.date_range("2024-01-01", periods=5, freq="B")
+    daily_df = pd.DataFrame({"net_pnl": [1, 2, 3, 4, 5]}, index=idx)
+    bench = pd.Series([0.01] * 5, index=idx)
+    try:
+        compute_metrics(daily_df, bench)
+        assert False, "应抛 ValueError"
+    except ValueError as e:
+        assert "balance" in str(e)