自动刷新改用 tail update 与 scrollToPosition 恢复视窗,避免 setData 后跳到最右;拆分 chart_tv 模块并扩展 analyze/recent API。同步威科夫分析、pipeline 增量构建及相关策略与配置。 Co-authored-by: Cursor <cursoragent@cursor.com>
64 lines
2.0 KiB
Markdown
64 lines
2.0 KiB
Markdown
# Wyckoff BTC System v1 — Decision Rule Locked
|
||
|
||
```
|
||
Architecture: Market State → Decision → Signal
|
||
|
||
Spring: FROZEN
|
||
Gate v1.1: LOCKED DEFAULT Decision rule (PASS)
|
||
Soft-score: REJECTED (no increment)
|
||
Hard-score: REJECTED
|
||
|
||
Minimal rule:
|
||
market_state in {accumulation, markup} -> allow Spring
|
||
else -> block Spring
|
||
|
||
Primary invalidation domain: distribution
|
||
range: observation bucket only (NOT a trading rule)
|
||
|
||
Validity: DEFINED
|
||
Confidence: MEDIUM / defined-domain PASS
|
||
Status: DEFAULT RULES FROZEN
|
||
Next: dry-run / monitoring only(见 operational checklist)
|
||
```
|
||
|
||
## Operational
|
||
|
||
上线前不改规则,只验执行链:
|
||
|
||
→ [`DRY_RUN_DECISION_CHECKLIST.md`](./DRY_RUN_DECISION_CHECKLIST.md)
|
||
|
||
覆盖:信号一致性 · 日志字段 · dry-run 监控 · 报警 · 硬禁 · Go/No-Go。
|
||
|
||
## Locked stack
|
||
|
||
| Layer | File | Status |
|
||
|-------|------|--------|
|
||
| Signal | `Wyckoff_BTC_V1_BASELINE.py` | FROZEN |
|
||
| State | `engine/market_state.py` | causal v1.1 |
|
||
| Decision | `Wyckoff_BTC_GATED.py` | **LOCKED state_set** |
|
||
| Boundary | `VALIDITY_BOUNDARY.md` | active |
|
||
|
||
## Robustness slices (blocked Spring, by year/era)
|
||
|
||
证据:`scripts/wyckoff_gate_robustness_slices_result.json`
|
||
|
||
| Slice | blocked n | dist share | top blocked | blocked PF |
|
||
|-------|-----------|------------|-------------|------------|
|
||
| 2020 | 3 | **1.00** | distribution | 0.73 |
|
||
| 2021 | 4 | **0.75** | distribution | 0.31 |
|
||
| 2022 | 1 | 1.00 | distribution | 0 |
|
||
| 2023 | 1 | 1.00 | distribution | 0 |
|
||
| 2024 | 3 | 0.33 | distribution+range | 0 |
|
||
| 2025 | 1 | 0 | range (obs) | n=1 win |
|
||
| pre_2023 | 8 | **0.875** | distribution | 0.37 |
|
||
| 2023plus | 5 | 0.40 | distribution+range | 1.22 |
|
||
|
||
Verdict: **distribution 归因在多数有样本切片上稳定**(PASS)。
|
||
2023+ / 2024–25 中 range 占比上升 → 保持 **观察标签**,不升格为交易规则。
|
||
|
||
## Do not
|
||
|
||
- 调 Spring / soft-score / Gate 阈值
|
||
- 因 range 小样本正 PF 开放 range 交易
|
||
- 复活 LPS / 默认跨资产
|