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/agents/selection_agent.py

@@ -8,6 +8,10 @@ import numpy as np
 import pandas as pd
 
 from agents.base import BaseAgent
+from config.settings import (
+    SELECTION_CORE_FACTORS, SELECTION_UNIVERSE_SIZE,
+    SELECTION_SCORE_LIMIT, SELECTION_WINSORIZE_ZSCORE,
+)
 
 
 class SelectionAgent(BaseAgent):
@@ -43,18 +47,13 @@ class SelectionAgent(BaseAgent):
                 ts_codes = self.sent.get_scope_stocks()
             else:
                 stocks = self.dm.get_stock_list()
-                ts_codes = list(stocks.index[:100])
+                ts_codes = list(stocks.index[:SELECTION_UNIVERSE_SIZE])
 
         if not ts_codes:
             return {"date": date or self._today(), "top_picks": [], "score_df": pd.DataFrame()}
 
-        # 选择核心因子（覆盖多个维度，减少计算量）
-        core_factors = [
-            "momentum_20", "momentum_60",
-            "rsi_14", "volatility_20",
-            "vol_ratio_5", "ma_dev_20",
-            "turnover_5", "amplitude_5",
-        ]
+        # 选择核心因子（覆盖多个维度，减少计算量；参数来自配置中心）
+        core_factors = list(SELECTION_CORE_FACTORS)
         factor_objects = [get_factor(n) for n in core_factors]
 
         self.log("打分 {} 只股票 (权重={})".format(len(ts_codes), weighting))
@@ -70,7 +69,7 @@ class SelectionAgent(BaseAgent):
             len(available) / len(ts_codes) * 100 if ts_codes else 0))
 
         # 2. 打分（限制上限防止单次太慢）
-        score_limit = min(len(available), 300)
+        score_limit = min(len(available), SELECTION_SCORE_LIMIT)
         scores = {}
         valid_count = 0
         for i, ts_code in enumerate(available[:score_limit]):
@@ -165,23 +164,38 @@ class SelectionAgent(BaseAgent):
         if len(row_clean) < 3:
             return None
 
-        # z-score 标准化
-        z = (row_clean - factor_df[row_clean.index].mean()) / factor_df[row_clean.index].std().replace(0, 1)
+        # z-score 标准化（用历史均值/标准差），可选的去极值避免单股离群主导 Top
+        cols = row_clean.index
+        mu = factor_df[cols].mean()
+        std = factor_df[cols].std().replace(0, 1)
+        z = (row_clean - mu) / std
+        if SELECTION_WINSORIZE_ZSCORE:
+            z = z.clip(-3, 3)
         return float(z.mean())
 
     def _score_ml(self, ts_code: str, factor_df: pd.DataFrame, date: str | None) -> float | None:
-        """ML 模型打分。"""
-        from models.features import FeatureEngine
-        fe = FeatureEngine(lookahead=5)
+        """ML 模型打分。
 
-        daily = self.dm.get_daily(ts_code)
+        要求注入名为 feature_engine 的、已用训练集 fit 过的 FeatureEngine，
+        以及 ml_models（已训练模型）。两者缺一时明确退出，而不是沿用旧的
+        未 fit 引擎静默失败。
+        """
+        fe = self.feature_engine
+        if fe is None:
+            self.log("ML 打分需要注入 feature_engine（已 fit），当前未提供，跳过 ML 打分")
+            return None
+        if not self.ml_models:
+            self.log("ML 打分需要 ml_models（已训练），当前为空，跳过 ML 打分")
+            return None
+
+        daily = self.dm.get_daily(ts_code) if self.dm else None
         if daily is None or daily.empty:
             return None
         daily = daily.set_index("trade_date")
 
         try:
             X, _ = fe.build(factor_df, daily, fit=False)
-            if X.empty:
+            if X is None or X.empty:
                 return None
             if date and date in X.index:
                 X = X.loc[[date]]
@@ -191,5 +205,7 @@ class SelectionAgent(BaseAgent):
             model = self.ml_models.get("lightgbm") or list(self.ml_models.values())[0]
             pred = model.predict(X)
             return float(pred.iloc[0]) if len(pred) > 0 else None
-        except Exception:
+        except Exception as e:
+            # 不再静默返回 None：记录原因，便于定位预测路径问题
+            self.log("[WARN] ML 打分失败 ({}): {}".format(ts_code, e))
             return None