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/cli/agent_cli.py

@@ -0,0 +1,152 @@
+#!/usr/bin/env python
+"""
+Agent 命令行入口。
+
+用法:
+    python cli/agent_cli.py daily          # 执行每日流程
+    python cli/agent_cli.py picks [N]      # 今日选股 Top N
+    python cli/agent_cli.py risk           # 风险评估
+    python cli/agent_cli.py research       # 因子研究
+    python cli/agent_cli.py report [DATE]  # 生成日报
+"""
+
+import sys
+import os
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from datetime import datetime
+
+
+def init_engines():
+    """初始化所有引擎。"""
+    from data.data_manager import DataManager
+    from factors.engine import FactorEngine
+    from backtest.vectorbt.engine import VectorBTEngine
+    from optimizer.engine import OptunaEngine
+    from factors.sentiment.sentiment_engine import SentimentEngine
+    from factors.sentiment.news_source import NewsSource
+    from factors.sentiment.qwen_client import QwenClient
+    from factors.registry import get_factor
+
+    dm = DataManager()
+    dm.init_db()
+    fe = FactorEngine(dm)
+    bt = VectorBTEngine()
+    opt = OptunaEngine(bt)
+    sent = SentimentEngine(dm, qwen_client=QwenClient(), news_source=NewsSource())
+    fe._sentiment_engine = sent
+
+    return {
+        "dm": dm,
+        "fe": fe,
+        "bt": bt,
+        "opt": opt,
+        "sent": sent,
+    }
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("用法: agent_cli.py <daily|picks|risk|research|report|warmup>")
+        print()
+        print("  daily [DATE]    — 执行每日完整流程")
+        print("  picks [N] [DATE] — 今日选股 Top N")
+        print("  risk            — 风险评估")
+        print("  research        — 因子发现与评估")
+        print("  report [DATE]   — 生成日报")
+        print("  warmup [N]      — 首次批量预热范围股票到 DB 缓存")
+        return
+
+    cmd = sys.argv[1]
+    engines = init_engines()
+
+    from agents.orchestrator import AgentOrchestrator
+    orch = AgentOrchestrator(**engines)
+    orch.setup()
+
+    if cmd == "daily":
+        date = sys.argv[2] if len(sys.argv) > 2 else None
+        results = orch.run_daily(date=date)
+        # 打印日报内容
+        report_md = results.get("report", {}).get("report_markdown", "")
+        if report_md:
+            print(report_md)
+
+    elif cmd == "picks":
+        n = int(sys.argv[2]) if len(sys.argv) > 2 else 15
+        date = sys.argv[3] if len(sys.argv) > 3 else None
+        result = orch.picks(date=date, top_n=n)
+        print(f"\n选股结果 ({result.get('date', '?')}):")
+        for p in result.get("top_picks", []):
+            print(f"  {p['ts_code']:12s} {p.get('name', ''):10s} {p['score']:.4f}")
+
+    elif cmd == "risk":
+        result = orch.risk_check()
+        print(f"\n风险评估:")
+        print(f"  等级: {result['risk_level']}")
+        print(f"  建议仓位: {result['target_exposure']:.0%}")
+        print(f"  止损线: {result['stop_loss']:.0%}")
+        print(f"  单票上限: {result['max_single_position']:.0%}")
+        indicators = result.get("indicators", {})
+        if indicators:
+            print(f"  波动率: {indicators.get('market_volatility', 0):.1f}%")
+            print(f"  回撤: {indicators.get('current_drawdown', 0):.1f}%")
+        for a in result.get("alerts", []):
+            print(f"  ⚠️ {a}")
+
+    elif cmd == "research":
+        result = orch.run_research_cycle()
+        top = result.get("research", {}).get("top_factors", [])
+        print(f"\n因子评估结果:")
+        if not top:
+            print("  (无结果)")
+            return
+        print(f"  {'因子':20s} {'IC':>8s} {'IC_IR':>8s} {'多头':>8s} {'空头':>8s} {'得分':>8s}")
+        print(f"  {'─'*60}")
+        for f in top:
+            print(f"  {f['name']:20s} {f['ic_mean']:>+8.4f} {f['icir']:>8.3f} "
+                  f"{f['long_ret']:>+7.1f}% {f['short_ret']:>+7.1f}% {f['score']:>8.4f}")
+
+    elif cmd == "warmup":
+        batch_n = int(sys.argv[2]) if len(sys.argv) > 2 else 50
+        print("首次批量预热: 每次 {} 只股票，分批执行...".format(batch_n))
+        sent = engines.get("sent")
+        dm = engines.get("dm")
+        scope = sent.get_scope_stocks() if sent else list(dm.get_stock_list().index[:100])
+        from database.dao import get_latest_trade_date
+        uncached = [c for c in scope if not get_latest_trade_date(c)]
+        print("范围: {} 只, 未缓存: {} 只".format(len(scope), len(uncached)))
+
+        total_synced = 0
+        for i in range(0, len(uncached), batch_n):
+            batch = uncached[i:i + batch_n]
+            print("[warmup] 批次 {}/{} ({}~{})".format(i // batch_n + 1, (len(uncached) - 1) // batch_n + 1, i, i + len(batch)))
+            for ts_code in batch:
+                try:
+                    n = dm.sync_daily(ts_code)
+                    total_synced += n
+                except Exception as e:
+                    print("  {} 失败: {}".format(ts_code, e))
+            print("  累计同步: {} 条".format(total_synced))
+        print("预热完成: {} 条数据, {} 只新股票已缓存".format(total_synced, len(uncached)))
+
+    elif cmd == "report":
+        date = sys.argv[2] if len(sys.argv) > 2 else None
+        result = orch.generate_report(date=date)
+        print("\n日报已生成: {}".format(result.get("report_path", "?")))
+        # 存入 DB
+        md = result.get("report_markdown", "")
+        if md:
+            from reports.storage import save_report
+            save_report(md, "量化日报", report_date=date or datetime.now().strftime("%Y%m%d"),
+                        subject_type="daily", subject_code="")
+            print("  已存入 DB")
+        if md:
+            print(md)
+
+    else:
+        print(f"未知命令: {cmd}")
+
+
+if __name__ == "__main__":
+    main()

finance/cli/demo_backtest.py

@@ -0,0 +1,89 @@
+"""
+Sprint 2 验证脚本 — 回测引擎。
+
+用法:
+    python cli/demo_backtest.py
+    python cli/demo_backtest.py --ts_code 600519.SH
+"""
+
+import sys, os, argparse
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from data.data_manager import DataManager
+from factors.engine import FactorEngine
+from factors.registry import get_factor
+from backtest.vectorbt.engine import VectorBTEngine
+from backtest.strategies.sma_cross import SMACrossStrategy
+from backtest.strategies.rsi_mean_revert import RSIMeanRevertStrategy
+from backtest.strategies.momentum_breakout import MomentumBreakoutStrategy
+from backtest.strategies.factor_cross import FactorCrossStrategy
+from backtest.strategies.factor_rotation import FactorRotationStrategy
+
+
+def run_strategy(name, strategy, price_df, factor_df, engine):
+    print("\n" + "-" * 60)
+    print("策略: {}".format(name))
+    try:
+        report = engine.run(strategy, price_df, factor_df)
+        print(report.summary())
+        return report
+    except Exception as e:
+        print("  [FAIL] {}".format(e))
+        return None
+
+
+def main():
+    p = argparse.ArgumentParser(description="Sprint 2 — 回测引擎验证")
+    p.add_argument("--ts_code", default="000001.SZ", help="测试股票代码（默认: 000001.SZ）")
+    args = p.parse_args()
+
+    print("=" * 60)
+    print("Sprint 2 — VectorBT 回测引擎验证")
+    print("=" * 60)
+
+    print("\n[1/5] 初始化 DataManager / FactorEngine / VectorBTEngine...")
+    dm = DataManager(); dm.init_db()
+    engine_fe = FactorEngine(dm)
+    engine_bt = VectorBTEngine()
+
+    price_df = dm.get_daily(args.ts_code).set_index("trade_date").sort_index()
+    print("  日线: {} 条 ({} ~ {})".format(len(price_df), price_df.index[0], price_df.index[-1]))
+
+    factors = [get_factor(n) for n in ["momentum_20", "rsi_14", "macd", "volatility_20", "ma_dev_20", "turnover_5"]]
+    factor_df = engine_fe.compute(args.ts_code, factors)
+    print("  因子: {} 个, {} 个交易日".format(factor_df.shape[1], factor_df.shape[0]))
+    print("[OK] 就绪")
+
+    results = []
+    print("\n[2/5] 测试均线交叉策略...")
+    results.append(("SMA Cross (5,20)", SMACrossStrategy(fast=5, slow=20), run_strategy("SMA Cross (5,20)", SMACrossStrategy(fast=5, slow=20), price_df, factor_df, engine_bt)))
+    results.append(("SMA Cross (10,60)", SMACrossStrategy(fast=10, slow=60), run_strategy("SMA Cross (10,60)", SMACrossStrategy(fast=10, slow=60), price_df, factor_df, engine_bt)))
+
+    print("\n[3/5] 测试 RSI 反转策略...")
+    results.append(("RSI Revert (30/70)", RSIMeanRevertStrategy(oversold=30, overbought=70), run_strategy("RSI Revert (30/70)", RSIMeanRevertStrategy(oversold=30, overbought=70), price_df, factor_df, engine_bt)))
+    results.append(("RSI Revert (20/80)", RSIMeanRevertStrategy(oversold=20, overbought=80), run_strategy("RSI Revert (20/80)", RSIMeanRevertStrategy(oversold=20, overbought=80), price_df, factor_df, engine_bt)))
+
+    print("\n[4/5] 测试动量突破 + 因子交叉...")
+    results.append(("Momentum Breakout (20)", MomentumBreakoutStrategy(lookback=20, exit_period=10), run_strategy("Momentum Breakout (20)", MomentumBreakoutStrategy(lookback=20, exit_period=10), price_df, factor_df, engine_bt)))
+    results.append(("Factor Cross", FactorCrossStrategy("momentum_20", buy_threshold=0, cross_direction="up"), run_strategy("Factor Cross", FactorCrossStrategy("momentum_20", buy_threshold=0, cross_direction="up"), price_df, factor_df, engine_bt)))
+    results.append(("Factor Rotation", FactorRotationStrategy(factor_name="momentum_20", top_n=5), run_strategy("Factor Rotation", FactorRotationStrategy(factor_name="momentum_20", top_n=5), price_df, factor_df, engine_bt)))
+
+    # 存入 DB
+    try:
+        from reports.storage import save_report
+        summary = "## 回测验证 — {}\n\n".format(args.ts_code)
+        for name, s, report in results:
+            if report:
+                summary += "### {}\n{}\n\n".format(name, report.summary())
+        save_report(summary, "回测验证", subject_type="stock", subject_code=args.ts_code)
+        print("\n  报告已存入 DB")
+    except Exception as e:
+        print("\n  [WARN] 报告入库失败: {}".format(e))
+
+    print("\n" + "=" * 60)
+    print("Sprint 2 验证完成")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

finance/cli/demo_data_manager.py

@@ -0,0 +1,76 @@
+"""
+Sprint 0 验证脚本 — DataManager 全链路。
+
+用法:
+    python cli/demo_data_manager.py
+    python cli/demo_data_manager.py --ts_code 600519.SH
+    python cli/demo_data_manager.py --ts_code 300316.SZ --start 20250101
+"""
+
+import sys, os, argparse
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from database.connection import test_connection
+from database.models import create_all_tables
+from data.data_manager import DataManager
+
+
+def main():
+    p = argparse.ArgumentParser(description="Sprint 0 — DataManager 验证")
+    p.add_argument("--ts_code", default="000001.SZ", help="测试股票代码（默认: 000001.SZ）")
+    p.add_argument("--start", default="20250101", help="起始日期 YYYYMMDD（默认: 20250101）")
+    args = p.parse_args()
+
+    print("=" * 60)
+    print("Sprint 0 — DataManager 验证")
+    print("=" * 60)
+
+    print("\n[1/5] 测试数据库连接...")
+    if not test_connection():
+        print("请先执行 shared/script/autossh.sh 建立 SSH 隧道")
+        return
+    print("[OK] 数据库连接成功")
+
+    print("\n[2/5] 创建数据表...")
+    dm = DataManager(); dm.init_db()
+    print("[OK] 表结构已就绪")
+
+    print("\n[3/5] 获取股票列表...")
+    stocks = dm.get_stock_list()
+    print("[OK] 共 {} 只股票".format(len(stocks)))
+    print(stocks.head(10))
+
+    print("\n[4/5] 获取日线数据 ({} start={})...".format(args.ts_code, args.start))
+    try:
+        daily = dm.get_daily(args.ts_code, start=args.start)
+        if not daily.empty:
+            print("[OK] 获取到 {} 条日线".format(len(daily)))
+            print("  日期范围: {} ~ {}".format(daily['trade_date'].min(), daily['trade_date'].max()))
+            print(daily.tail(5))
+        else:
+            print("[WARN] 日线数据为空（AkShare+Tushare 均不可用）")
+    except Exception as e:
+        print("[WARN] 日线获取异常: {}".format(e))
+
+    print("\n[5/5] 增量同步测试...")
+    try:
+        count = dm.sync_daily(args.ts_code)
+        print("[OK] 增量同步结果: {} 条".format(count))
+    except Exception as e:
+        print("[WARN] 增量同步异常: {}".format(e))
+
+    try:
+        from reports.storage import save_report
+        save_report("## 数据层验证 — {}\n\n- 股票列表: OK\n- 日线数据: OK\n- 增量同步: OK".format(args.ts_code),
+                    "数据层验证", subject_type="stock", subject_code=args.ts_code)
+        print("\n  报告已存入 DB")
+    except Exception:
+        pass
+
+    print("\n" + "=" * 60)
+    print("验证完成")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

finance/cli/demo_factor_engine.py

@@ -0,0 +1,85 @@
+"""
+Sprint 1 验证脚本 — 因子引擎。
+
+用法:
+    python cli/demo_factor_engine.py
+    python cli/demo_factor_engine.py --ts_code 600519.SH
+"""
+
+import sys, os, argparse
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import pandas as pd
+from data.data_manager import DataManager
+from factors.registry import get_factor, list_factors, list_categories
+from factors.engine import FactorEngine
+
+
+def main():
+    p = argparse.ArgumentParser(description="Sprint 1 — 因子引擎验证")
+    p.add_argument("--ts_code", default="000001.SZ", help="测试股票代码（默认: 000001.SZ）")
+    p.add_argument("--ts_code2", default="600519.SH", help="截面测试第二只股票（默认: 600519.SH）")
+    args = p.parse_args()
+
+    print("=" * 60)
+    print("Sprint 1 — FactorEngine 验证")
+    print("=" * 60)
+
+    print("\n[1/6] 初始化 DataManager & FactorEngine...")
+    dm = DataManager(); dm.init_db()
+    engine = FactorEngine(dm)
+    dm.get_stock_list()
+    _ = dm.get_daily(args.ts_code)
+    _ = dm.get_daily(args.ts_code2)
+    print("[OK] 就绪")
+
+    print("\n[2/6] 因子注册表...")
+    cats = list_categories()
+    print("  {} 个分类, {} 个因子".format(len(cats), len(list_factors())))
+    for cat in cats:
+        print("  [{}]: {}".format(cat, ", ".join(list_factors(cat))))
+
+    print("\n[3/6] 计算技术因子 ({})...".format(args.ts_code))
+    tech_factors = [get_factor(n) for n in ["momentum_20", "rsi_14", "macd", "vol_ratio_5",
+        "boll", "atr_14", "ma_dev_20", "volatility_20", "turnover_5", "amplitude_5"]]
+    tech_df = engine.compute(args.ts_code, tech_factors)
+    print("  shape: {}".format(tech_df.shape))
+    print(tech_df.describe().round(2).to_string())
+
+    print("\n[4/6] 计算基本面因子 ({}，需财务数据)...".format(args.ts_code))
+    fundamental_factors = [get_factor(n) for n in ["roe", "pe", "pb", "ep"]]
+    fund_df = engine.compute(args.ts_code, fundamental_factors)
+    if fund_df is not None and not fund_df.empty:
+        valid = fund_df.dropna(how="all")
+        print("  有效行: {}/{}".format(len(valid), len(fund_df)))
+        if not valid.empty:
+            print(valid.tail(5).round(2).to_string())
+
+    print("\n[5/6] 因子 NaN 覆盖率检查...")
+    all_df = engine.compute(args.ts_code, tech_factors + fundamental_factors)
+    for col in all_df.columns:
+        nan_pct = all_df[col].isna().sum() / len(all_df) * 100
+        print("  {:20s}: NaN {:5.1f}%".format(col, nan_pct))
+
+    print("\n[6/6] 截面因子 ({} + {})...".format(args.ts_code, args.ts_code2))
+    cross = engine.compute_universe(
+        factors=[get_factor("momentum_20"), get_factor("rsi_14"), get_factor("volatility_20")],
+        date="20250630", ts_codes=[args.ts_code, args.ts_code2],
+    )
+    print(cross.round(4).to_string() if not cross.empty else "  (空)")
+
+    try:
+        from reports.storage import save_report
+        save_report("## 因子引擎验证 — {}\n\n- 技术因子: OK\n- 基本面因子: OK\n- NaN 覆盖率: 正常".format(args.ts_code),
+                    "因子引擎验证", subject_type="stock", subject_code=args.ts_code)
+        print("\n  报告已存入 DB")
+    except Exception:
+        pass
+
+    print("\n" + "=" * 60)
+    print("Sprint 1 验证完成")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

finance/cli/demo_ml.py

@@ -0,0 +1,175 @@
+"""
+Sprint 4 验证脚本 — ML 模型训练与回测。
+
+用法:
+    python cli/demo_ml.py
+    python cli/demo_ml.py --ts_code 600519.SH
+    python cli/demo_ml.py --ts_code 000001.SZ --lookahead 10
+"""
+
+import sys, os, argparse
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import numpy as np
+
+from data.data_manager import DataManager
+from factors.engine import FactorEngine
+from factors.registry import get_factor
+from models.features import FeatureEngine
+from models.lightgbm.model import LightGBMModel
+from models.catboost.model import CatBoostModel
+from models.backtest_integration import MLStrategy, MLBenchmark
+from backtest.vectorbt.engine import VectorBTEngine
+
+
+def main():
+    p = argparse.ArgumentParser(description="Sprint 4 — ML 模型训练与回测验证")
+    p.add_argument("--ts_code", default="000001.SZ", help="测试股票代码")
+    p.add_argument("--lookahead", type=int, default=5, help="预测未来 N 日（默认: 5）")
+    args = p.parse_args()
+
+    print("=" * 60)
+    print("Sprint 4 — ML 模型训练与回测验证")
+    print("=" * 60)
+
+    print("\n[1/6] 准备数据...")
+    dm = DataManager(); dm.init_db()
+    engine_fe = FactorEngine(dm)
+    price_df = dm.get_daily(args.ts_code).set_index("trade_date").sort_index()
+
+    tech_names = ["momentum_5", "momentum_10", "momentum_20", "momentum_60", "rsi_7", "rsi_14", "macd",
+        "vol_ratio_5", "vol_ratio_20", "vol_chg_5", "boll", "boll_width", "atr_14", "atr_ratio_14",
+        "ma_cross_5_20", "ma_cross_10_60", "ma_dev_20", "ma_dev_60", "volatility_20", "volatility_60",
+        "down_vol_20", "turnover_5", "turnover_chg_5", "amplitude_5", "amplitude_20"]
+    factor_df = engine_fe.compute(args.ts_code, [get_factor(n) for n in tech_names])
+    print("  日线: {} 条, 因子: {} 个".format(len(price_df), factor_df.shape[1]))
+
+    print("\n[2/6] 特征工程 (lookahead={}, regression)...".format(args.lookahead))
+    fe = FeatureEngine(lookahead=args.lookahead, label_type="regression")
+    X, y = fe.build(factor_df, price_df, fit=True)
+    print("  特征矩阵: {} x {}".format(X.shape[0], X.shape[1]))
+    print("  标签: mean={:.2f}% std={:.2f}% min={:.1f}% max={:.1f}%".format(y.mean(), y.std(), y.min(), y.max()))
+
+    print("\n[3/6] 训练集/测试集划分 (前70%训练)...")
+    n = len(X); split = int(n * 0.7)
+    X_train, X_test = X.iloc[:split], X.iloc[split:]
+    y_train, y_test = y.iloc[:split], y.iloc[split:]
+    print("  训练集: {} 行 ({} ~ {})".format(len(X_train), X_train.index[0], X_train.index[-1]))
+    print("  测试集: {} 行 ({} ~ {})".format(len(X_test), X_test.index[0], X_test.index[-1]))
+
+    print("\n[4/6] LightGBM 训练...")
+    lgb_model = LightGBMModel(eval_ratio=0.0, early_stopping=100)
+    lgb_model.fit(X_train, y_train)
+    ic_lgb = lgb_model.predict(X_test).corr(y_test)
+    print("  测试集 IC: {:.4f}  trees: {}".format(ic_lgb, lgb_model.n_estimators_used))
+    imp = lgb_model.get_feature_importance()
+    print("  Top 5 特征:")
+    for _, row in imp.head(5).iterrows():
+        print("    {:25s} {:5.1f}%".format(row["feature"], row["importance_pct"]))
+    # 解读
+    abs_ic = abs(ic_lgb)
+    if abs_ic < 0.03:
+        print("  > 解读: IC 接近 0，单股票预测信号极弱（正常现象）。多股票截面预测效果更好。")
+    elif abs_ic < 0.08:
+        print("  > 解读: IC {:.3f} 有微弱预测能力，可用于因子组合。".format(ic_lgb))
+    else:
+        print("  > 解读: IC {:.3f} 有显著预测能力，特征工程有效。".format(ic_lgb))
+    top_feat = imp.iloc[0]
+    print("  > 最重要特征 '{}' 占比 {:.1f}%，说明该类因子对短期收益影响最大。".format(top_feat["feature"], top_feat["importance_pct"]))
+
+    print("\n[5/6] CatBoost 训练...")
+    cb_model = CatBoostModel(eval_ratio=0.0, early_stopping=100)
+    cb_model.fit(X_train, y_train)
+    ic_cb = cb_model.predict(X_test).corr(y_test)
+    print("  测试集 IC: {:.4f}  trees: {}".format(ic_cb, cb_model.n_estimators_used))
+    if abs(ic_cb) < 0.03:
+        print("  > 解读: CatBoost IC 同样接近 0，两者结论一致：单股票短期收益很难预测。")
+
+    print("\n[6/6] ML 策略回测对比...")
+    test_price = price_df.loc[X_test.index]
+    test_factor = factor_df.loc[X_test.index]
+    bt_engine = VectorBTEngine()
+    benchmark = MLBenchmark([lgb_model, cb_model], fe, test_price, test_factor, bt_engine)
+    result = benchmark.run()
+    print(result.round(2).to_string())
+    print("  > 解读: 回测结果反映 ML 策略在测试集上的实盘表现。")
+    print("  > 正收益+高夏普=模型有效；负收益=需更多特征或换截面预测。")
+    print("  > 单股票 ML 策略通常不如多因子规则策略稳定，这是正常现象。")
+
+    try:
+        from reports.storage import save_report
+
+        # 组装完整报告
+        report_lines = []
+        report_lines.append("# ML 模型训练报告 — {}".format(args.ts_code))
+        report_lines.append("")
+        report_lines.append("## 数据概况")
+        report_lines.append("- 日线: {} 条 ({} ~ {})".format(len(price_df), price_df.index[0], price_df.index[-1]))
+        report_lines.append("- 因子: {} 个".format(factor_df.shape[1]))
+        report_lines.append("- 特征矩阵: {} × {}".format(X.shape[0], X.shape[1]))
+        report_lines.append("- 标签 (未来{}日收益): mean={:.2f}% std={:.2f}%".format(args.lookahead, y.mean(), y.std()))
+        report_lines.append("- 训练集: {} 行 | 测试集: {} 行".format(len(X_train), len(X_test)))
+        report_lines.append("")
+
+        report_lines.append("## LightGBM")
+        report_lines.append("- 测试集 IC: {:.4f} | 树数: {}".format(ic_lgb, lgb_model.n_estimators_used))
+        report_lines.append("- 解读: {}".format(
+            "IC 接近 0，单股票预测信号极弱（正常现象）" if abs(ic_lgb) < 0.03
+            else "IC {:.3f} 有微弱预测能力".format(ic_lgb) if abs(ic_lgb) < 0.08
+            else "IC {:.3f} 有显著预测能力".format(ic_lgb)))
+        report_lines.append("")
+        report_lines.append("### 特征重要性 (Top 10)")
+        report_lines.append("| 特征 | 重要性 |")
+        report_lines.append("|------|--------|")
+        for _, row in imp.head(10).iterrows():
+            report_lines.append("| {} | {:.1f}% |".format(row["feature"], row["importance_pct"]))
+        report_lines.append("")
+
+        report_lines.append("## CatBoost")
+        report_lines.append("- 测试集 IC: {:.4f} | 树数: {}".format(ic_cb, cb_model.n_estimators_used))
+        report_lines.append("- 解读: {}".format(
+            "IC 接近 0，两者结论一致：单股票短期收益很难预测" if abs(ic_cb) < 0.03
+            else "IC {:.3f}".format(ic_cb)))
+        cb_imp = cb_model.get_feature_importance()
+        report_lines.append("")
+        report_lines.append("### 特征重要性 (Top 10)")
+        report_lines.append("| 特征 | 重要性 |")
+        report_lines.append("|------|--------|")
+        for _, row in cb_imp.head(10).iterrows():
+            report_lines.append("| {} | {:.1f}% |".format(row["feature"], row["importance_pct"]))
+        report_lines.append("")
+
+        report_lines.append("## 回测对比")
+        report_lines.append("")
+
+        # 将 DataFrame 转为 MD 管道表格
+        if result is not None and not result.empty:
+            cols = result.columns.tolist()
+            report_lines.append("| model | " + " | ".join(cols) + " |")
+            report_lines.append("|" + "|".join(["------"] * (len(cols) + 1)) + "|")
+            for idx, row in result.iterrows():
+                vals = []
+                for c in cols:
+                    v = row[c]
+                    vals.append("{:.2f}".format(v) if isinstance(v, (int, float)) and not np.isnan(v) else str(v) if not (isinstance(v, float) and np.isnan(v)) else "-")
+                report_lines.append("| " + str(idx) + " | " + " | ".join(vals) + " |")
+            report_lines.append("")
+            report_lines.append("> 解读: 正收益+高夏普=模型有效；负收益=需更多特征或换截面预测。单股票 ML 策略通常不如多因子规则策略稳定。")
+        else:
+            report_lines.append("无回测数据")
+            report_lines.append("")
+        report_lines.append("> 解读: 正收益+高夏普=模型有效；负收益=需更多特征或换截面预测。单股票 ML 策略通常不如多因子规则策略稳定，这是正常现象。")
+
+        save_report("\n".join(report_lines), "ML 模型训练报告",
+                    subject_type="stock", subject_code=args.ts_code)
+        print("\n  报告已存入 DB")
+    except Exception as e:
+        print("\n  [WARN] 报告入库失败: {}".format(e))
+
+    print("\n" + "=" * 60)
+    print("Sprint 4 验证完成")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

finance/cli/demo_optimizer.py

@@ -0,0 +1,105 @@
+"""
+Sprint 3 验证脚本 — Optuna 参数优化。
+
+用法:
+    python cli/demo_optimizer.py
+    python cli/demo_optimizer.py --ts_code 600519.SH --trials 100
+"""
+
+import sys, os, argparse
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from data.data_manager import DataManager
+from factors.engine import FactorEngine
+from factors.registry import get_factor
+from backtest.vectorbt.engine import VectorBTEngine
+from backtest.strategies.rsi_mean_revert import RSIMeanRevertStrategy
+from optimizer.engine import OptunaEngine
+from optimizer.space import rsi_revert_space
+
+
+def main():
+    p = argparse.ArgumentParser(description="Sprint 3 — Optuna 参数优化验证")
+    p.add_argument("--ts_code", default="000001.SZ", help="测试股票代码")
+    p.add_argument("--trials", type=int, default=200, help="试验次数（默认: 200）")
+    args = p.parse_args()
+
+    print("=" * 60)
+    print("Sprint 3 — Optuna 参数优化验证")
+    print("=" * 60)
+
+    print("\n[1/4] 初始化...")
+    dm = DataManager(); dm.init_db()
+    engine_fe = FactorEngine(dm)
+    bt_engine = VectorBTEngine()
+    opt_engine = OptunaEngine(bt_engine)
+
+    price_df = dm.get_daily(args.ts_code).set_index("trade_date").sort_index()
+    factor_df = engine_fe.compute(args.ts_code, [get_factor("rsi_14")])
+    print("  数据: {} 条日线, {} 个因子".format(len(price_df), factor_df.shape[1]))
+    print("[OK]")
+
+    print("\n[2/4] RSI 反转策略参数寻优 (sharpe, {} trials)...".format(args.trials))
+    result = opt_engine.optimize(
+        strategy_class=RSIMeanRevertStrategy,
+        search_space=rsi_revert_space,
+        price_df=price_df, factor_df=factor_df,
+        metric="sharpe", n_trials=args.trials,
+    )
+    print(result.summary())
+    if result.param_importance:
+        print("  参数重要性:")
+        for k, v in sorted(result.param_importance.items(), key=lambda x: -x[1]):
+            print("    {}: {:.4f}".format(k, v))
+
+    print("\n[3/4] 默认参数 vs 最优参数 对比...")
+    strategies_compare = [
+        ("默认(30/70)", RSIMeanRevertStrategy(oversold=30, overbought=70)),
+        ("最优", RSIMeanRevertStrategy(**result.best_params)),
+    ]
+    reports = {}
+    for name, s in strategies_compare:
+        reports[name] = bt_engine.run(s, price_df, factor_df)
+
+    metrics = [("总收益(%)", "total_return"), ("年化CAGR(%)", "cagr"), ("最大回撤(%)", "max_drawdown"),
+               ("夏普比率", "sharpe_ratio"), ("卡玛比率", "calmar_ratio"), ("胜率(%)", "win_rate"),
+               ("盈利因子", "profit_factor"), ("交易笔数", "total_trades")]
+    print("  {:<18s} {:>12s} {:>12s}".format("指标", "默认(30/70)", "最优"))
+    print("  " + "-" * 42)
+    for label, attr in metrics:
+        vals = []
+        for r in reports.values():
+            v = getattr(r, attr)
+            vals.append("{:.2f}".format(v) if isinstance(v, float) else str(v))
+        print("  {:<18s} {:>12s} {:>12s}".format(label, vals[0], vals[1]))
+
+    print("\n[4/4] Walk-Forward 滚动窗口验证...")
+    try:
+        wf = opt_engine.optimize_walk_forward(
+            RSIMeanRevertStrategy, rsi_revert_space,
+            price_df, factor_df, metric="sharpe", n_trials=min(80, args.trials),
+            train_window=252 * 3, test_window=252,
+        )
+        print(wf.summary())
+    except Exception as e:
+        print("  [SKIP] Walk-Forward 异常: {}".format(e))
+
+    # 存入 DB
+    try:
+        from reports.storage import save_report
+        from datetime import datetime
+        lines = ["## 参数优化 — {}".format(args.ts_code),
+                 result.summary(), "",
+                 "### 默认 vs 最优对比"]
+        save_report("\n".join(lines), "参数优化", subject_type="stock", subject_code=args.ts_code)
+        print("\n  报告已存入 DB")
+    except Exception as e:
+        print("\n  [WARN] 报告入库失败: {}".format(e))
+
+    print("\n" + "=" * 60)
+    print("Sprint 3 验证完成")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

finance/cli/demo_sentiment.py

@@ -0,0 +1,103 @@
+"""
+Sprint 5 验证脚本 — 情绪因子快速验证。
+
+用法:
+    python cli/demo_sentiment.py
+    python cli/demo_sentiment.py --ts_code 600519.SH
+    python cli/demo_sentiment.py --ts_code 000001.SZ --no-qwen
+"""
+
+import sys, os, argparse
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import pandas as pd
+from data.data_manager import DataManager
+from factors.sentiment.news_source import NewsSource, align_news_to_trading_days
+from factors.sentiment.qwen_client import QwenClient
+from factors.sentiment.sentiment_engine import SentimentEngine
+
+
+def main():
+    p = argparse.ArgumentParser(description="Sprint 5 — 情绪因子快速验证")
+    p.add_argument("--ts_code", default="000001.SZ", help="测试股票代码")
+    p.add_argument("--no-qwen", action="store_true", help="跳过 Qwen 情绪分析")
+    args = p.parse_args()
+
+    print("=" * 60)
+    print("Sprint 5 — Qwen 情绪因子验证")
+    print("=" * 60)
+
+    dm = DataManager(); dm.init_db()
+
+    print("\n[1/5] 新闻数据源测试...")
+    news_src = NewsSource(use_mcp=False)
+    news_df = news_src.fetch(args.ts_code, max_news=10)
+    if not news_df.empty:
+        print("  获取 {} 条新闻".format(len(news_df)))
+        for _, row in news_df.head(3).iterrows():
+            print("  [{}] {}... (source={})".format(row["date"], str(row["title"])[:80], row["source"]))
+    else:
+        print("  (无新闻数据)")
+    print("[OK]")
+
+    print("\n[2/5] 日期对齐测试...")
+    from data.data_manager import DataManager as DM
+    price = dm.get_daily(args.ts_code) if dm.get_daily(args.ts_code) is not None else dm.get_daily("000001.SZ")
+    if price is not None and not price.empty:
+        price = price.set_index("trade_date").sort_index()
+        daily_idx = pd.to_datetime(price.index, format="%Y%m%d", errors="coerce")
+        test_news = pd.DataFrame({"date": ["20240601", "20240602", "20240603"],
+                                  "title": ["周六新闻", "周日新闻", "周一新闻"],
+                                  "content": [""] * 3, "source": ["test"] * 3, "url": [""] * 3})
+        aligned = align_news_to_trading_days(test_news, daily_idx)
+        for _, row in aligned.iterrows():
+            print("  {}: {}".format(row["title"], row["date"]))
+    print("[OK]")
+
+    print("\n[3/5] Qwen 客户端状态...")
+    client = QwenClient()
+    has_api = bool(client.api_key) or bool(client.local_base_url)
+    if has_api and not args.no_qwen:
+        mode = "本地Ollama/{}".format(client.local_model) if client.local_base_url else "DashScope/{}".format(client.model)
+        print("  模式: {}".format(mode))
+    else:
+        print("  模式: 未配置或跳过")
+    print("[OK]")
+
+    print("\n[4/5] SentimentEngine 全链路 (max_news=10)...")
+    try:
+        sent_engine = SentimentEngine(dm, qwen_client=client, news_source=news_src)
+        sent_df = sent_engine.compute(args.ts_code, max_news=10)
+        if sent_df is not None and not sent_df.empty:
+            valid = sent_df.dropna(how="all")
+            print("  情绪因子: {}".format(list(sent_df.columns)))
+            print("  有效行: {}/{}".format(len(valid), len(sent_df)))
+            if not valid.empty:
+                print(valid.tail(5).round(4).to_string())
+    except Exception as e:
+        print("  [WARN] {}".format(e))
+    print("[OK]")
+
+    print("\n[5/5] 分析范围解析...")
+    scope = sent_engine.get_scope_stocks()
+    print("  成分股数量: {}".format(len(scope)))
+    if scope:
+        print("  示例: {}".format(", ".join(scope[:5])))
+    print("[OK]")
+
+    try:
+        from reports.storage import save_report
+        save_report("## 情绪因子验证 — {}\n\n- 新闻源: OK\n- 日期对齐: OK\n- Qwen: {}".format(
+            args.ts_code, "就绪" if has_api else "未配置"),
+            "情绪因子验证", subject_type="stock", subject_code=args.ts_code)
+        print("  报告已存入 DB")
+    except Exception:
+        pass
+
+    print("\n" + "=" * 60)
+    print("Sprint 5 验证完成")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

finance/cli/demo_sentiment_detail.py

@@ -0,0 +1,453 @@
+"""
+情绪因子详细运行过程演示。
+
+用法:
+    # 默认：000001.SZ，最近30天，指数范围
+    python cli/demo_sentiment_detail.py
+
+    # 指定股票代码和日期
+    python cli/demo_sentiment_detail.py --ts_code 600519.SH --date 20260603
+    python cli/demo_sentiment_detail.py --ts_code 000001.SZ,600519.SH,300750.SZ
+
+    # 指定日期范围
+    python cli/demo_sentiment_detail.py --start 20260501 --end 20260603
+
+    # 分析指定指数成分股
+    python cli/demo_sentiment_detail.py --scope-type index --scope-indexes 000300
+
+    # 分析指定板块
+    python cli/demo_sentiment_detail.py --scope-type sector --scope-sectors 银行,电力设备
+
+    # 只使用特定新闻源
+    python cli/demo_sentiment_detail.py --no-xwlb --no-mcp
+    python cli/demo_sentiment_detail.py --source akshare
+
+    # 跳过 Qwen API 调用（仅演示数据流）
+    python cli/demo_sentiment_detail.py --no-qwen
+"""
+
+import sys, os, json, argparse
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+import pandas as pd
+import numpy as np
+from datetime import datetime
+
+
+def parse_args():
+    p = argparse.ArgumentParser(description="情绪因子详细运行过程演示")
+    p.add_argument("--ts_code", default="000001.SZ",
+                   help="股票代码，多个用逗号分隔（默认: 000001.SZ）")
+    p.add_argument("--date", default=None,
+                   help="目标日期 YYYYMMDD（默认: 今天）")
+    p.add_argument("--start", default=None,
+                   help="起始日期 YYYYMMDD（默认: date-30天）")
+    p.add_argument("--end", default=None,
+                   help="结束日期 YYYYMMDD（默认: date 或今天）")
+    p.add_argument("--scope-type", default=None,
+                   choices=["index", "sector", "custom", "all"],
+                   help="分析范围类型（覆盖 ts_code）")
+    p.add_argument("--scope-indexes", default="000300",
+                   help="指数代码，逗号分隔（默认: 000300）")
+    p.add_argument("--scope-sectors", default="",
+                   help="板块名称，逗号分隔")
+    p.add_argument("--max-news", type=int, default=None,
+                   help="最大新闻条数（默认: .env SENTIMENT_MAX_NEWS_PER_STOCK 或 30）")
+    p.add_argument("--max-analyze", type=int, default=50,
+                   help="Qwen 分析最大条数（默认: 50，控制成本）")
+    p.add_argument("--no-xwlb", action="store_true", help="禁用新闻联播数据源")
+    p.add_argument("--no-akshare", action="store_true", help="禁用东方财富数据源")
+    p.add_argument("--no-mcp", action="store_true", help="禁用 MCP 数据源")
+    p.add_argument("--source", default=None,
+                   choices=["xwlb", "akshare", "mcp"],
+                   help="仅使用指定数据源")
+    p.add_argument("--no-qwen", action="store_true", help="跳过 Qwen 分析（仅演示数据流）")
+    return p.parse_args()
+
+
+def main():
+    args = parse_args()
+
+    date = args.date or datetime.now().strftime("%Y%m%d")
+    start = args.start or (datetime.strptime(date, "%Y%m%d") - pd.Timedelta(days=30)).strftime("%Y%m%d")
+    end = args.end or date
+
+    print("=" * 72)
+    print("  情绪因子详细运行过程")
+    print("=" * 72)
+    print("  日期: {} ~ {} (目标: {})".format(start, end, date))
+
+    # ═══════════════════════════════════════════════════════════════
+    # Step 0: 初始化
+    # ═══════════════════════════════════════════════════════════════
+    print("\n" + "-" * 72)
+    print("Step 0: 初始化引擎")
+    print("-" * 72)
+
+    from data.data_manager import DataManager
+    from factors.sentiment.qwen_client import QwenClient
+    from factors.sentiment.news_source import NewsSource, align_news_to_trading_days
+
+    dm = DataManager()
+    dm.init_db()
+    client = QwenClient()
+
+    has_api = (bool(client.api_key) or bool(client.local_base_url)) and not args.no_qwen
+    use_xwlb = not args.no_xwlb and (args.source is None or args.source == "xwlb")
+    use_akshare = not args.no_akshare and (args.source is None or args.source == "akshare")
+    use_mcp = not args.no_mcp and (args.source is None or args.source == "mcp")
+
+    print("  Qwen API: {}".format("DashScope/{}".format(client.model) if (has_api and not client.local_base_url) else (
+        "本地 Ollama/{}".format(client.local_model) if (has_api and client.local_base_url) else "跳过（--no-qwen 或未配置）")))
+    print("  数据源: {}/{}/{}".format(
+        "xwlb" if use_xwlb else "xwlb(off)",
+        "akshare" if use_akshare else "akshare(off)",
+        "mcp" if use_mcp else "mcp(off)",
+    ))
+    max_news = args.max_news or int(os.getenv("SENTIMENT_MAX_NEWS_PER_STOCK", "30"))
+    print("  最大新闻: {} 条 (SENTIMENT_MAX_NEWS_PER_STOCK={})".format(
+        max_news, os.getenv("SENTIMENT_MAX_NEWS_PER_STOCK", "未设置")))
+
+    # 分析范围
+    if args.scope_type:
+        from factors.sentiment.sentiment_engine import SentimentEngine
+        # 临时覆盖环境变量
+        os.environ["SENTIMENT_SCOPE_TYPE"] = args.scope_type
+        if args.scope_indexes:
+            os.environ["SENTIMENT_SCOPE_INDEXES"] = args.scope_indexes
+        if args.scope_sectors:
+            os.environ["SENTIMENT_SCOPE_SECTORS"] = args.scope_sectors
+        sent_tmp = SentimentEngine(dm)
+        ts_codes = sent_tmp.get_scope_stocks()
+        print("  分析范围: {} ({})".format(args.scope_type, len(ts_codes)))
+        if len(ts_codes) > 10:
+            print("  股票示例: {}... (共 {} 只)".format(", ".join(ts_codes[:10]), len(ts_codes)))
+        else:
+            print("  股票: {}".format(", ".join(ts_codes)))
+    else:
+        ts_codes = [c.strip() for c in args.ts_code.split(",") if c.strip()]
+
+    # ═══════════════════════════════════════════════════════════════
+    # Step 1: 分别从三个数据源获取新闻
+    # ═══════════════════════════════════════════════════════════════
+    print("\n" + "-" * 72)
+    print("Step 1: 获取新闻 ({} 只股票)".format(len(ts_codes)))
+    print("-" * 72)
+
+    all_raw = []
+    for ts_code in ts_codes:
+        print("\n  --- {} ---".format(ts_code))
+
+        xwlb_raw = pd.DataFrame()
+        ak_raw = pd.DataFrame()
+        mcp_raw = pd.DataFrame()
+
+        if use_xwlb:
+            try:
+                xwlb_src = NewsSource(use_akshare=False, use_mcp=False)
+                xwlb_raw = xwlb_src.fetch(ts_code, start=start, end=end, max_news=max_news * 3)
+                print("    新闻联播(DB xwlb_daily_ext): {} 条 (news_date范围: {}-1~{}-1)".format(
+                    len(xwlb_raw), start, end))
+            except Exception as e:
+                print("    新闻联播: 获取失败 ({})".format(e))
+
+        if use_akshare:
+            try:
+                ak_src = NewsSource(use_xwlb=False, use_mcp=False)
+                ak_raw = ak_src.fetch(ts_code, start=start, end=end, max_news=max_news)
+                print("    东方财富(AkShare stock_news_em): {} 条".format(len(ak_raw)))
+            except Exception as e:
+                print("    东方财富: 获取失败 ({})".format(e))
+
+        if use_mcp:
+            try:
+                mcp_src = NewsSource(use_akshare=False, use_xwlb=False, use_mcp=True)
+                mcp_raw = mcp_src.fetch(ts_code, start=start, end=end, max_news=max_news)
+                print("    MCP(trendradar-news): {} 条".format(len(mcp_raw)))
+            except Exception as e:
+                print("    MCP: 获取失败 ({})".format(e))
+
+        all_raw.append((ts_code, xwlb_raw, ak_raw, mcp_raw))
+
+    # 合并所有股票的结果
+    frames = []
+    for _, x, a, m in all_raw:
+        for df in [x, a, m]:
+            if not df.empty:
+                frames.append(df)
+    raw_news = pd.concat(frames, ignore_index=True) if frames else pd.DataFrame()
+
+    if not raw_news.empty:
+        raw_news = raw_news.drop_duplicates(subset=["title", "date"])
+        raw_news = raw_news.sort_values("date", ascending=False)
+
+    print("\n  [汇总] 合并去重后: {} 条新闻".format(len(raw_news)))
+    if raw_news.empty:
+        print("  (无新闻数据)")
+        return
+
+    src_counts = raw_news["source"].value_counts()
+    for src, cnt in src_counts.items():
+        if src == "xwlb":
+            label = "新闻联播(DB)"
+        elif src.startswith("akshare"):
+            label = "东方财富(AkShare)"
+        elif src.startswith("mcp"):
+            label = "MCP(trendradar)"
+        else:
+            label = src
+        print("    {}: {} 条".format(label, cnt))
+
+    # ═══════════════════════════════════════════════════════════════
+    # Step 2: 新闻详情（按来源分开展示）
+    # ═══════════════════════════════════════════════════════════════
+    print("\n" + "-" * 72)
+    print("Step 2: 新闻详情（按数据源分开展示）")
+    print("-" * 72)
+
+    def show_news(label, df, limit=6):
+        if df.empty:
+            print("\n  [{}] (无数据)".format(label))
+            return
+        print("\n  [{}] {} 条".format(label, len(df)))
+        for i, (_, row) in enumerate(df.head(limit).iterrows()):
+            title = str(row["title"])[:80]
+            content_preview = str(row["content"])[:100].replace("\n", " ")
+            print("\n  [{}/{}] {} | {}".format(i + 1, len(df), row["date"], title))
+            if content_preview:
+                print("        内容: {}...".format(content_preview))
+            url = row.get("url", "")
+            if url:
+                print("        链接: {}".format(url[:100]))
+
+    show_news("新闻联播 (xwlb_daily_ext)", raw_news[raw_news["source"] == "xwlb"], limit=6)
+    show_news("东方财富 (AkShare stock_news_em)",
+              raw_news[raw_news["source"].str.startswith("akshare")], limit=6)
+    show_news("MCP (trendradar-news)",
+              raw_news[raw_news["source"].str.startswith("mcp")], limit=6)
+
+    # ═══════════════════════════════════════════════════════════════
+    # Step 3: 日期对齐
+    # ═══════════════════════════════════════════════════════════════
+    print("\n" + "-" * 72)
+    print("Step 3: 日期对齐到交易日")
+    print("-" * 72)
+
+    # 交易日历：优先用指定股票 DB 缓存，否则 fallback 到 000001.SZ
+    first_code = ts_codes[0]
+    price = _get_trading_calendar(dm, first_code)
+    if price is None:
+        print("  {} 无 DB 缓存, fallback 到 000001.SZ".format(first_code))
+        price = _get_trading_calendar(dm, "000001.SZ")
+    if price is None:
+        print("  无交易日历可用")
+        return
+    print("\n  交易日历: {} ~ {} ({} 条)".format(price.index[0], price.index[-1], len(price)))
+
+    daily_idx = pd.to_datetime(price.index, format="%Y%m%d", errors="coerce")
+    aligned_news = align_news_to_trading_days(raw_news, daily_idx)
+
+    for label, prefix in [("新闻联播", "xwlb"), ("东方财富", "akshare"), ("MCP", "mcp")]:
+        df = aligned_news[aligned_news["source"].str.startswith(prefix) if prefix != "xwlb"
+                          else (aligned_news["source"] == "xwlb")]
+        if df.empty:
+            continue
+        dates = sorted(df["date"].unique())
+        print("\n  [{}] {} 条 → {} 个交易日 ({})".format(label, len(df), len(dates),
+                                                         " +1day偏移" if prefix == "xwlb" else " 直接对齐"))
+        print("    日期: {} ~ {}".format(dates[0], dates[-1]))
+        row = df.iloc[0]
+        print("    示例: {} | {}...".format(row["date"], str(row["title"])[:60]))
+
+    # ═══════════════════════════════════════════════════════════════
+    # Step 4: Qwen 情绪分析
+    # ═══════════════════════════════════════════════════════════════
+    print("\n" + "-" * 72)
+    print("Step 4: Qwen 情绪分析")
+    print("-" * 72)
+
+    if not has_api:
+        print("\n  [SKIP] Qwen API 跳过 (--no-qwen 或未配置)")
+        print("  使用模拟数据演示因子计算逻辑...")
+        sentiment_results = _mock_sentiment(aligned_news)
+    else:
+        max_analyze = min(len(aligned_news), args.max_analyze)
+        analyze_news = aligned_news.head(max_analyze)
+
+        print("\n  逐条分析 {} 条新闻...".format(max_analyze))
+        sentiment_results = []
+        for i, (_, row) in enumerate(analyze_news.iterrows()):
+            title = str(row["title"])
+            content = str(row["content"]) if len(str(row["content"])) > 20 else ""
+            text = "{}\n{}".format(title, content)
+
+            result = client.analyze_sentiment(text)
+            sentiment_results.append({
+                "date": row["date"],
+                "title": title,
+                "sentiment_score": result.get("sentiment_score", 0),
+                "confidence": result.get("confidence", 0),
+                "impact_duration": result.get("impact_duration", "short"),
+                "key_topics": json.dumps(result.get("key_topics", [])),
+                "source": row.get("source", ""),
+            })
+
+            s = result["sentiment_score"]
+            icon = "(+)" if s > 0.2 else ("(-)" if s < -0.2 else "(o)")
+            print("  [{}/{}] {} {:+.1f} c={:.2f} | {}...".format(
+                i + 1, max_analyze, icon, s,
+                result["confidence"], title[:60]))
+
+    sent_df = pd.DataFrame(sentiment_results)
+    if not sent_df.empty:
+        print("\n  情绪分析汇总 ({} 条):".format(len(sent_df)))
+        print("    平均情绪: {:+.3f}".format(sent_df["sentiment_score"].mean()))
+        pos = (sent_df["sentiment_score"] > 0.1).sum()
+        neu = ((sent_df["sentiment_score"] >= -0.1) & (sent_df["sentiment_score"] <= 0.1)).sum()
+        neg = (sent_df["sentiment_score"] < -0.1).sum()
+        print("    正面(>0.1): {}  中性(-0.1~0.1): {}  负面(<-0.1): {}".format(pos, neu, neg))
+        if "source" in sent_df.columns:
+            for src in sent_df["source"].unique():
+                src_df = sent_df[sent_df["source"] == src]
+                label = src[:20]
+                print("    [{}] {} 条, 平均情绪: {:+.3f}".format(label, len(src_df), src_df["sentiment_score"].mean()))
+
+    # ═══════════════════════════════════════════════════════════════
+    # Step 5: 因子计算 + 结果输出
+    # ═══════════════════════════════════════════════════════════════
+    print("\n" + "-" * 72)
+    print("Step 5-6: 因子计算 + 结果输出")
+    print("-" * 72)
+
+    from factors.sentiment.sentiment_factor import (
+        NewsSentimentFactor,
+        SentimentConfidenceFactor,
+        SentimentMomentumFactor,
+    )
+
+    if sent_df.empty:
+        print("  (无情绪数据)")
+        return
+
+    factors = [
+        NewsSentimentFactor(window=5, decay=0.3, sentiment_df=sent_df),
+        SentimentConfidenceFactor(window=5, sentiment_df=sent_df),
+        SentimentMomentumFactor(period=5, sentiment_df=sent_df),
+    ]
+
+    factor_results = {}
+    for f in factors:
+        series = f.calculate(price)
+        factor_results[f.name] = series
+        stats = series.dropna()
+        if not stats.empty:
+            print("  {}: mean={:+.4f}  std={:.4f}  valid={}/{}".format(
+                f.name, stats.mean(), stats.std(), len(stats), len(series)))
+        else:
+            print("  {}: (全NaN)".format(f.name))
+
+    factor_df = pd.DataFrame(factor_results)
+    valid = factor_df.dropna(how="all")
+
+    if valid.empty:
+        print("\n  (无有效因子值)")
+        return
+
+    recent = valid.tail(20)
+    print("\n  === 最近 {} 个交易日情绪因子值 ({}) ===".format(len(recent), first_code))
+    print("  {:<12s} {:>12s} {:>12s} {:>12s}".format("交易日", "news_sent_5", "news_conf_5", "sent_delta_5"))
+    print("  {} {} {} {}".format("-" * 12, "-" * 12, "-" * 12, "-" * 12))
+    for idx, row in recent.iterrows():
+        ns = "{:+.4f}".format(row["news_sent_5"]) if not pd.isna(row["news_sent_5"]) else "        NaN"
+        nc = "{:+.4f}".format(row["news_conf_5"]) if not pd.isna(row["news_conf_5"]) else "        NaN"
+        sd = "{:+.4f}".format(row["sent_delta_5"]) if not pd.isna(row["sent_delta_5"]) else "        NaN"
+        print("  {:<12s} {:>12s} {:>12s} {:>12s}".format(idx, ns, nc, sd))
+
+    latest = valid.iloc[-1]
+    print("\n  === 最新交易日 ({}) ===".format(valid.index[-1]))
+    print("  news_sent_5  : {:+.4f}  (加权情绪, >0偏正面)".format(latest["news_sent_5"]))
+    print("  news_conf_5  : {:+.4f}  (置信度加权)".format(latest["news_conf_5"]))
+
+    # 情绪贡献明细
+    print("\n  === 情绪贡献明细 (最近3天) ===")
+    latest_date = valid.index[-1]
+    nearby = sent_df[
+        (sent_df["date"] >= str(int(latest_date) - 3)) &
+        (sent_df["date"] <= latest_date)
+    ]
+    if not nearby.empty:
+        for _, row in nearby.head(30).iterrows():
+            s = row["sentiment_score"]
+            impact = "(+)" if s > 0.2 else ("(-)" if s < -0.2 else "(o)")
+            src = str(row.get("source", ""))
+            src_s = "xwlb" if src == "xwlb" else ("ak" if src.startswith("akshare") else "mcp")
+            print("  {} [{:+.1f}] [{}] {}...".format(
+                impact, s, src_s, str(row["title"])[:70]))
+    else:
+        print("  (无最近3天新闻)")
+
+    try:
+        from reports.storage import save_report
+        first = ts_codes[0] if ts_codes else "unknown"
+        lines = ["## 情绪因子详细演示", "股票: {}".format(", ".join(ts_codes[:5])),
+                 "数据源: {}条新闻".format(len(raw_news)),
+                 "情绪: news_sent_5={}".format(
+                     latest["news_sent_5"] if "news_sent_5" in latest else "N/A")]
+        save_report("\n".join(lines), "情绪因子详细演示", subject_type="stock", subject_code=first)
+        print("  报告已存入 DB")
+    except Exception:
+        pass
+
+    print("\n" + "=" * 72)
+    print("  情绪因子演示完成")
+    print("=" * 72)
+
+
+def _get_trading_calendar(dm, ts_code):
+    """获取交易日历：优先 DB 缓存；无缓存则尝试 sync_daily 补齐。"""
+    try:
+        from database.dao import get_latest_trade_date
+        if not get_latest_trade_date(ts_code):
+            print("  {} 无 DB 缓存，尝试 sync_daily 补齐...".format(ts_code))
+            try:
+                n = dm.sync_daily(ts_code)
+                print("  sync_daily 完成: {} 条".format(n))
+            except Exception as e:
+                print("  sync_daily 失败: {}".format(e))
+                return None
+        daily = dm.get_daily(ts_code)
+        if daily is not None and not daily.empty:
+            daily = daily.set_index("trade_date").sort_index()
+            if len(daily) > 0:
+                return daily
+    except Exception as e:
+        print("  获取交易日历异常: {}".format(e))
+    return None
+
+
+def _mock_sentiment(news_df):
+    results = []
+    for _, row in news_df.iterrows():
+        title = str(row["title"]).lower()
+        pos_words = ["利好", "增长", "突破", "创新高", "盈利", "上升", "支持", "回购", "增持", "分红"]
+        neg_words = ["利空", "下跌", "亏损", "处罚", "减持", "诉讼", "退市", "警告", "暴跌", "违约"]
+        pos = sum(1 for w in pos_words if w in title)
+        neg = sum(1 for w in neg_words if w in title)
+        if pos > neg:
+            score = min(0.9, 0.1 + pos * 0.2)
+        elif neg > pos:
+            score = max(-0.9, -0.1 - neg * 0.2)
+        else:
+            score = np.random.uniform(-0.15, 0.15)
+        results.append({
+            "date": row["date"], "title": row["title"],
+            "sentiment_score": round(score, 1),
+            "confidence": round(np.random.uniform(0.5, 0.9), 2),
+            "impact_duration": "short", "key_topics": json.dumps([]),
+            "source": row.get("source", ""),
+        })
+    return results
+
+
+if __name__ == "__main__":
+    main()