Initial commit: cc-cursor 全链路量化研究平台

7 Sprints 全部完成:
  Sprint 0: 基础设施 (DataManager + MariaDB)
  Sprint 1: 因子引擎 (34因子/12分类)
  Sprint 2: VectorBT 回测 (5策略+截面)
  Sprint 3: Optuna 优化 (+Walk-Forward)
  Sprint 4: ML 模型 (LightGBM+CatBoost)
  Sprint 5: Qwen 情绪因子 (三源新闻+日期对齐)
  Sprint 6: Agent 系统 (4Agent+日报.md/.html)

生产加固 (15项): Tushare双源fallback, SSH自动恢复, pool_pre_ping,
  save_daily先删后插, load_dotenv绝对路径, 日报5d/20d修复,
  RiskAgent改上证指数, 昨日对比+数据截止, mac_report utf8mb4,
  CLAUDE-*.md 9条已知Bug, demo全参数化, djapi数据源归一化,
  indexDatas API修正

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

finance/agents/research_agent.py

@@ -0,0 +1,145 @@
+"""
+ResearchAgent — 因子发现与评估。
+
+遍历注册因子，计算 IC/IC_IR/分层收益，输出 Top 因子。
+"""
+
+import numpy as np
+import pandas as pd
+
+from agents.base import BaseAgent
+
+
+class ResearchAgent(BaseAgent):
+    """因子发现 Agent。"""
+
+    name = "Research"
+    description = "因子发现与评估"
+
+    def execute(
+        self,
+        factor_names: list[str] | None = None,
+        ts_codes: list[str] | None = None,
+        lookahead: int = 5,
+        top_n: int = 10,
+    ) -> dict:
+        """
+        遍历因子，计算评估指标。
+
+        参数:
+            factor_names: 待评估因子列表，None=全部注册因子
+            ts_codes: 股票列表，None=DataManager 全部
+            lookahead: 前向收益窗口
+            top_n: 返回 Top N 因子
+
+        返回:
+            {"top_factors": [...], "all_results": DataFrame, "evaluated": int}
+        """
+        from factors.registry import list_factors, get_factor
+
+        if factor_names is None:
+            # 只评估技术+基本面因子（情绪因子需要额外数据）
+            categories = ["动量", "RSI", "MACD", "量价", "布林", "ATR", "均线", "波动率", "换手率", "振幅", "基本面"]
+            factor_names = []
+            for cat in categories:
+                factor_names.extend(list_factors(cat))
+
+        if ts_codes is None:
+            stocks = self.dm.get_stock_list()
+            # 默认选 50 只代表股（前50只 + 避免API过载）
+            ts_codes = list(stocks.index[:50]) if self.dm else ["000001.SZ", "600519.SH"]
+
+        self.log(f"评估 {len(factor_names)} 个因子 × {len(ts_codes)} 只股票")
+
+        results = []
+        for fn in factor_names:
+            metrics = self._evaluate_factor(fn, ts_codes, lookahead)
+            if metrics:
+                results.append(metrics)
+            self.log(f"  {fn}: IC={metrics.get('ic_mean', 0):.4f}" if metrics else f"  {fn}: SKIP")
+
+        if not results:
+            return {"top_factors": [], "all_results": pd.DataFrame(), "evaluated": 0}
+
+        df = pd.DataFrame(results).sort_values("score", ascending=False)
+        top = df.head(top_n)
+
+        return {
+            "top_factors": top.to_dict("records"),
+            "all_results": df,
+            "evaluated": len(results),
+        }
+
+    def _evaluate_factor(
+        self, factor_name: str, ts_codes: list[str], lookahead: int
+    ) -> dict | None:
+        """对单个因子计算 IC/IC_IR。"""
+        from factors.registry import get_factor
+        from models.features import FeatureEngine
+
+        try:
+            factor = get_factor(factor_name)
+        except KeyError:
+            return None
+
+        fe = FeatureEngine(lookahead=lookahead, label_type="regression")
+
+        ics = []
+        long_rets = []
+        short_rets = []
+        success = 0
+
+        for ts_code in ts_codes:
+            try:
+                daily = self.dm.get_daily(ts_code)
+                if daily is None or daily.empty:
+                    continue
+                daily = daily.set_index("trade_date").sort_index()
+
+                factor_df = self.fe.compute(ts_code, [factor])
+                if factor_df is None or factor_df.empty:
+                    continue
+
+                X, y = fe.build(factor_df, daily, fit=True)
+                if X.empty or y.empty or factor_name not in X.columns:
+                    continue
+
+                fv = X[factor_name].dropna()
+                yv = y.loc[fv.index]
+                if len(fv) < 30:
+                    continue
+
+                ic = fv.corr(yv, method="spearman")
+                ics.append(ic)
+
+                # 分层收益
+                top_idx = fv.nlargest(int(len(fv) * 0.2)).index
+                bot_idx = fv.nsmallest(int(len(fv) * 0.2)).index
+                long_rets.append(yv.loc[top_idx.intersection(yv.index)].mean())
+                short_rets.append(yv.loc[bot_idx.intersection(yv.index)].mean())
+
+                success += 1
+            except Exception:
+                continue
+
+        if success < 3:
+            return None
+
+        ic_series = pd.Series(ics)
+        ic_mean = ic_series.mean()
+        ic_std = ic_series.std()
+        icir = ic_mean / ic_std if ic_std > 0 else 0
+
+        # 综合得分 = IC × IC_IR 加权
+        score = abs(ic_mean) * max(icir, 0)
+
+        return {
+            "name": factor_name,
+            "ic_mean": round(float(ic_mean), 4),
+            "ic_std": round(float(ic_std), 4),
+            "icir": round(float(icir), 4),
+            "long_ret": round(float(np.mean(long_rets)), 2) if long_rets else 0,
+            "short_ret": round(float(np.mean(short_rets)), 2) if short_rets else 0,
+            "stocks_evaluated": success,
+            "score": round(float(score), 4),
+        }