Commit Graph

16 Commits

Author SHA1 Message Date
root
0d9dffa44d docs: expand v5.3 weight model and refactor implementation checklist 2026-03-03 09:35:59 +00:00
root
a17c1434b9 docs: add v5.3 development guardrails to gemini analysis 2026-03-03 09:22:59 +00:00
fanziqi
ce0bebd6f5 docs: update v51 gemini analysis 2026-03-03 17:19:27 +08:00
root
b83ab66039 docs: incorporate gemini feedback for labels, ATR snapshot, and release metrics 2026-03-03 09:08:46 +00:00
root
fb4e1e06e5 docs: refine v5.3 with label, execution fallback, btc volatility gate 2026-03-03 09:06:40 +00:00
root
18a2c95e40 docs: add V5.3 design and implementation checklist 2026-03-03 08:58:54 +00:00
fanziqi
4a5d63621f docs: update v51 gemini analysis notes 2026-03-03 16:18:48 +08:00
dev-worker
f3d742fd02 docs: V5.2模拟盘执行分析报告
核心结论:V5.2毛R=-3.27R(负),V5.1毛R=+10.73R(正)
V5.2增加8信号未提升预测质量,BTC胜率35.9%(更差)
152笔样本不足,结论不确定性高
2026-03-03 07:53:15 +00:00
fanziqi
63440efc6d docs: add v51 gemini analysis 2026-03-03 15:48:09 +08:00
dev-worker
511f011aef docs: V5.1分析报告+优化方案
- v51-performance-analysis.md: 完整执行分析(毛R/净R/时段/币种/分数段)
- v51-optimization-plan.md: 优化方案(降频+时段过滤+暂停BTC+拉大TP/SL比)

核心结论:毛R+12R,手续费-109R,净R-97R;信号有微弱优势,费用致亏
2026-03-03 07:28:53 +00:00
dev-worker
42ccbd35d7 docs: 修正V5.1文档参数与实际配置一致
TP/SL修正:
- SL: 2.0×ATR → 1.4×ATR
- TP1: 1.5×ATR → 1.05×ATR
- TP2: 3.0×ATR → 2.1×ATR
- 对应R倍数: tp1_r=0.75, tp2_r=1.5

与backend/strategies/v51_baseline.json和replay脚本完全一致
2026-03-03 05:40:07 +00:00
dev-worker
ffd7bed387 docs: 补充V5.1/V5.2信号系统详细文档
- v51-signal-system.md: V5.1基础信号系统
- v51-signal-enhancement.md: V5.1增强方案
- v52-signal-system.md: V5.2信号系统
- v52-evolution-roadmap.md: V5.2进化路线图
- v52-development.md: V5.2开发文档(完整版)
2026-03-03 05:32:44 +00:00
dev-worker
c8c2d801a2 docs: 同步套利引擎私有文档站内容
从private.darkerilclaw.com同步以下文档:
- requirements-v1.3.md: 需求定稿v1.3
- v5-signal-system.mdx: V5信号系统文档
- v2-v4-plan.mdx: V2-V4方案
- funding-rate-arbitrage-plan.md: 资金费率套利方案
- phase0-progress.md: Phase0进度
- index.mdx: 项目首页

后续工作流:git仓库先写 → 再同步到私有文档站
2026-03-03 05:26:27 +00:00
root
7ebdb98643 feat: store and serve indicators per strategy
- signal_indicators table: added strategy column
- Each strategy gets its own row per cycle
- API /api/signals/latest?strategy=v51_baseline|v52_8signals
- API /api/signals/signal-history?strategy=...
- V5.1 page reads v51_baseline data, V5.2 reads v52_8signals
- Now V5.1 and V5.2 show truly independent scores
2026-03-02 02:52:17 +00:00
root
45bad25156 fix(P0): pnl_r calculation + cooldown bypass + partition month bug
P0-1: Reverse signal now bypasses cooldown - evaluate_signal always
      outputs direction, main loop checks direction+score>=60 for
      closing positions against trend (not blocked by COOLDOWN_MS)

P0-2: pnl_r unified to (exit-entry)/risk_distance across all exit
      scenarios (tp, sl, sl_be, timeout) in both paper_monitor.py
      and signal_engine.py. Old hardcoded values (1.5R/2.25R) were
      ~2x too high vs actual risk_distance basis.

P1-1: ensure_partitions month calculation fixed from timedelta(30d)
      to proper month arithmetic. Also fixed UTC timezone for
      partition boundaries.

docs: V52-TODO.md with full audit backlog for V5.2
2026-03-01 09:29:32 +00:00
root
d8ad87958a docs: add comprehensive project documentation (PROJECT.md)
- Full architecture overview
- All 36 files documented with purpose and line counts
- 5-layer scoring system explained
- Database schema, PM2 processes, signal sources
- Deployment info, version roadmap
- Known issues and improvements
2026-03-01 08:34:56 +00:00