feat: 量化引擎加固 — 新增测试 + 数据/因子/回测层优化

- 新增 finance/tests/ 6 个测试套件（agents/backtest/dao_upsert/factors/features/fundamental_lookahead）
- 数据层: data_manager / dao 优化，新增 upsert 逻辑
- 因子层: 基本面因子抽象定位 _mapping、ROE/PE/PB 重构
- 回测层: vectorbt/engine 大改动（251 行），report 增强
- ML 层: features/backtest_integration 特征工程与回测优化
- CLI: agent_cli 重构
- config/settings 扩充配置项

finance/models/backtest_integration.py

@@ -82,34 +82,46 @@ class MLStrategy(BaseStrategy):
 
 
 class MLBenchmark:
-    """ML 模型基准对比测试。"""
+    """ML 模型基准对比测试。
+
+    入参的 feature_engine 应已用模型训练集 fit 过（scaler/winsor/median 已缓存）。
+    run() 对 **样本外测试数据**（test_factor_df/test_price_df）用 fit=False 转换后
+    计算预测 IC，避免"同一时间段既训练又评估"的前视泄漏。
+    """
 
     def __init__(
         self,
         models: list[BaseModel],
         feature_engine: FeatureEngine,
-        price_df: pd.DataFrame,
-        factor_df: pd.DataFrame,
+        test_factor_df: pd.DataFrame,
+        test_price_df: pd.DataFrame,
         bt_engine: VectorBTEngine | None = None,
     ):
         self.models = models
         self.feature_engine = feature_engine
-        self.price_df = price_df
-        self.factor_df = factor_df
+        self.test_factor_df = test_factor_df
+        self.test_price_df = test_price_df
         self.bt_engine = bt_engine or VectorBTEngine()
 
     def run(self) -> pd.DataFrame:
-        """对比各模型的预测质量和回测表现。"""
+        """对比各模型在样本外测试集上的预测质量和回测表现。"""
         rows = []
+        # 标签由规则(前视收益)决定，预测时可直接用同一 build_labels 构造，
+        # 避免依赖 build(fit=False) 不产标签的语义。
+        y_test = self.feature_engine.build_labels(self.test_price_df)
+        X_test, _ = self.feature_engine.build(self.test_factor_df, self.test_price_df, fit=False)
+        if X_test is None or X_test.empty or y_test is None or y_test.dropna().empty:
+            raise RuntimeError(
+                "MLBenchmark: 样本外测试集为空或 feature_engine 未在训练集上 fit。")
+
         for model in self.models:
+            # OOS 回测：MLStrategy 用同一已 fit engine 对测试集生成信号
             strategy = MLStrategy(model, self.feature_engine)
-            report = self.bt_engine.run(strategy, self.price_df, self.factor_df)
+            report = self.bt_engine.run(strategy, self.test_price_df, self.test_factor_df)
 
-            # OOS 预测 vs 真实值
-            X, y_true = self.feature_engine.build(self.factor_df, self.price_df, fit=True)
-            y_pred = model.predict(X)
-
-            ic = y_pred.corr(y_true) if len(y_pred) > 0 else 0
+            preds = model.predict(X_test)
+            common = X_test.index.intersection(y_test.dropna().index)
+            ic = preds.reindex(common).astype(float).corr(y_test.reindex(common).astype(float)) if len(common) > 1 else 0
 
             rows.append({
                 "model": model.name,