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/backtest/strategies/factor_cross.py

@@ -0,0 +1,51 @@
+"""
+因子阈值交叉策略。
+
+通用策略：任意因子上穿/下穿阈值 → 交易信号。
+
+支持：
+- 上穿买入 (cross_up: close < MA → cross above MA → buy)
+- 下穿买入 (cross_down: RSI > 70 → cross below 30 → buy)
+"""
+
+import pandas as pd
+
+from backtest.base import BaseStrategy
+from backtest.signal import factor_to_threshold_signal
+
+
+class FactorCrossStrategy(BaseStrategy):
+    """
+    因子阈值交叉策略。
+
+    适用场景：
+    - 均线偏离度上穿 0 → 买入（趋势转多）
+    - 波动率下穿阈值 → 买入（波动收敛后突破）
+    """
+
+    category = "trend"
+
+    def __init__(
+        self,
+        factor_column: str,
+        buy_threshold: float,  # 因子大于此值买
+        sell_threshold: float | None = None,
+        cross_direction: str = "up",
+    ):
+        self.factor_column = factor_column
+        self.buy_threshold = buy_threshold
+        self.sell_threshold = sell_threshold
+        self.cross_direction = cross_direction
+        self.name = f"factor_cross_{factor_column}"
+
+    def generate_signals(self, factor_df: pd.DataFrame) -> pd.Series:
+        if self.factor_column not in factor_df.columns:
+            raise ValueError(f"factor_df 缺少 '{self.factor_column}' 列")
+
+        factor = factor_df[self.factor_column]
+        return factor_to_threshold_signal(
+            factor,
+            buy_threshold=self.buy_threshold,
+            sell_threshold=self.sell_threshold,
+            cross_direction=self.cross_direction,
+        )

finance/backtest/strategies/factor_rotation.py

@@ -0,0 +1,58 @@
+"""
+因子排序轮动策略。
+
+定期按因子值排序，买入排名最高的股票（截面策略）。
+"""
+
+import pandas as pd
+
+from backtest.base import BaseStrategy
+
+
+class FactorRotationStrategy(BaseStrategy):
+    """
+    因子排序选股策略。
+
+    适用于多股票截面场景：对每只股票计算因子值，
+    选排名最高的 top_n 只做多。
+    """
+
+    category = "rotation"
+
+    def __init__(self, factor_name: str, top_n: int = 5, bottom_n: int = 0):
+        self.factor_name = factor_name
+        self.top_n = top_n
+        self.bottom_n = bottom_n
+        self.name = f"rotation_{factor_name}_top{top_n}"
+
+    def generate_signals(self, factor_df: pd.DataFrame) -> pd.Series:
+        """
+        单股票/截面模式：factor_df 支持两种输入方式。
+        - 单股票: 对每只股票单次调用
+        - 截面: 通过 run_cross_section 逐股票调用
+        """
+        if self.factor_name not in factor_df.columns:
+            raise ValueError(f"factor_df 缺少 '{self.factor_name}' 列")
+
+        factor = factor_df[self.factor_name]
+        valid = factor.dropna()
+        if len(valid) < self.top_n * 2:
+            return pd.Series(-1, index=factor_df.index)
+
+        threshold = valid.quantile(1 - self.top_n / max(len(valid), self.top_n))
+        signals = pd.Series(-1, index=factor_df.index)
+        signals[factor > threshold] = 1
+
+        return signals
+
+    def rank_stocks(
+        self, factor_values: dict[str, float]
+    ) -> list[str]:
+        """
+        对股票按因子值排序，返回 top N 的 ts_code 列表。
+
+        参数:
+            factor_values: {ts_code: factor_value}
+        """
+        sorted_stocks = sorted(factor_values, key=factor_values.get, reverse=True)
+        return sorted_stocks[: self.top_n]

finance/backtest/strategies/momentum_breakout.py

@@ -0,0 +1,52 @@
+"""
+动量突破策略。
+
+价格突破 N 日新高 → 买入
+价格跌破 N 日均线 → 平仓
+"""
+
+import pandas as pd
+
+from backtest.base import BaseStrategy
+from backtest.signal import factor_to_threshold_signal
+
+
+class MomentumBreakoutStrategy(BaseStrategy):
+    """动量突破策略。"""
+
+    category = "trend"
+
+    def __init__(self, lookback: int = 20, exit_period: int = 10):
+        self.lookback = lookback
+        self.exit_period = exit_period
+        self.name = f"mom_breakout_{lookback}"
+
+    def generate_signals(self, factor_df: pd.DataFrame) -> pd.Series:
+        if "close" not in factor_df.columns:
+            raise ValueError("factor_df 缺少 'close' 列")
+
+        close = factor_df["close"]
+        # 买入信号：突破 N 日新高
+        rolling_high = close.rolling(window=self.lookback, min_periods=self.lookback).max()
+        breakout = close >= rolling_high.shift(1)
+
+        # 平仓信号：跌破 exit 日均线
+        exit_ma = close.rolling(window=self.exit_period, min_periods=self.exit_period).mean()
+
+        signals = pd.Series(0, index=close.index)
+        signals[breakout] = 1
+        signals[close < exit_ma] = 0
+
+        return self._dedup(signals)
+
+    @staticmethod
+    def _dedup(signals: pd.Series) -> pd.Series:
+        """只保留第一个买入和第一个卖出信号。"""
+        result = signals.copy()
+        prev = -1
+        for i in range(len(result)):
+            if result.iloc[i] == prev:
+                result.iloc[i] = -1
+            else:
+                prev = result.iloc[i]
+        return result[result != -1].reindex(signals.index).fillna(-1)

finance/backtest/strategies/rsi_mean_revert.py

@@ -0,0 +1,35 @@
+"""
+RSI 均值回归策略。
+
+RSI 低于超卖线 → 买入
+RSI 高于超买线 → 平仓
+"""
+
+import pandas as pd
+
+from backtest.base import BaseStrategy
+from backtest.signal import factor_to_threshold_signal
+
+
+class RSIMeanRevertStrategy(BaseStrategy):
+    """RSI 超买超卖反转策略。"""
+
+    category = "mean_revert"
+
+    def __init__(self, oversold: float = 30, overbought: float = 70, rsi_column: str = "rsi_14"):
+        self.oversold = oversold
+        self.overbought = overbought
+        self.rsi_column = rsi_column
+        self.name = f"rsi_revert_{int(oversold)}_{int(overbought)}"
+
+    def generate_signals(self, factor_df: pd.DataFrame) -> pd.Series:
+        if self.rsi_column not in factor_df.columns:
+            raise ValueError(f"factor_df 缺少 '{self.rsi_column}' 列")
+
+        rsi = factor_df[self.rsi_column]
+        return factor_to_threshold_signal(
+            rsi,
+            buy_threshold=self.oversold,
+            sell_threshold=self.overbought,
+            cross_direction="down",  # RSI 向下跌破 oversold → 买入
+        )

finance/backtest/strategies/sma_cross.py

@@ -0,0 +1,33 @@
+"""
+均线交叉策略。
+
+短期均线上穿长期均线 → 买入
+短期均线下穿长期均线 → 平仓
+"""
+
+import pandas as pd
+
+from backtest.base import BaseStrategy
+from backtest.signal import cross_signal
+
+
+class SMACrossStrategy(BaseStrategy):
+    """快慢均线交叉策略。"""
+
+    category = "trend"
+
+    def __init__(self, fast: int = 5, slow: int = 20):
+        self.fast = fast
+        self.slow = slow
+        self.name = f"sma_cross_{fast}_{slow}"
+
+    def generate_signals(self, factor_df: pd.DataFrame) -> pd.Series:
+        if "close" not in factor_df.columns:
+            raise ValueError("factor_df 缺少 'close' 列")
+
+        close = factor_df["close"]
+        min_p = min(self.fast, self.slow)
+        ma_fast = close.rolling(window=self.fast, min_periods=self.fast).mean()
+        ma_slow = close.rolling(window=self.slow, min_periods=self.slow).mean()
+
+        return cross_signal(ma_fast, ma_slow)