autonomous-trading
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAutonomous Trading v6
自主交易 v6
Give your agent a budget, a target, and a deadline — then let it trade. The agent creates a strategy wallet, scans for opportunities, opens positions, protects profits with DSL, and enforces risk controls.
为你的Agent设定预算、目标和期限,之后就可以让它自动开展交易。该Agent会创建策略钱包、扫描交易机会、开仓、通过DSL保护盈利,同时执行风险管控规则。
Prerequisites
前置要求
Install these companion skills first:
- dsl-dynamic-stop-loss — trailing stops, auto-closing, per-tier retrace
- opportunity-scanner — market scanning, scoring, hourly trend gate
- emerging-movers — SM rotation detection, IMMEDIATE_MOVER signals
Minimum budget: $500 (recommend $1k+)
请先安装以下配套skill:
- dsl-dynamic-stop-loss — 移动止损、自动平仓、分层回撤
- opportunity-scanner — 市场扫描、评分、小时级趋势关卡
- emerging-movers — SM轮动检测、IMMEDIATE_MOVER信号
最低预算: 500美元(推荐1000美元以上)
Known Bugs & Gotchas
已知漏洞与注意事项
See references/bugs-and-gotchas.md — critical issues from live trading including the bug, phantom closes, XYZ DEX margin type, Tier 1 lock misconception, and scanner leverage vs actual max.
dryRun请查看 references/bugs-and-gotchas.md — 包含实盘交易中的关键问题,包括漏洞、phantom平仓、XYZ DEX保证金类型、Tier 1锁仓误区,以及扫描器杠杆与实际最大杠杆的差异。
dryRunThe Flow
运行流程
Step 1: Ask the User
步骤1:询问用户
Collect: budget, target, deadline, risk tolerance (conservative/moderate/aggressive), asset preferences.
收集以下信息:预算、目标、期限、风险承受能力(保守/适中/激进)、资产偏好。
Step 2: Calculate the Playbook
步骤2:计算交易方案
See references/risk-rules.md for complete risk rules by profile.
v6 Core Rules:
The #1 Rule — Hourly Trend Alignment. ALL trades must confirm with hourly candle structure. Counter-trend = hard skip, no exceptions. This single rule prevents the majority of losing trades.
Max Leverage Check. Always check before entering. Scanner leverage is conservative, not actual max.
max-leverage.jsonConcentration Over Diversification. At small account sizes ($500-$10k), 2-4 high-conviction positions beat 6 mediocre ones. Cross-margin math: 4 positions → 80.6% margin buffer, 2 positions → 89.7%.
Every Slot Must Maximize ROI. Empty slot > mediocre position. If a position isn't working, cut it and free the slot.
Speed Filter. Best moves happen FAST (XRP hit Tier 3 in 19 min, XMR Tier 2 in 37 min). Slow movers are suspects.
各风险等级对应的完整风控规则请查看 references/risk-rules.md。
v6核心规则:
头号规则 — 小时级趋势对齐。 所有交易必须符合小时K线结构,逆势交易直接跳过,无例外。仅这一条规则就能避免绝大多数亏损交易。
最大杠杆校验。 开仓前必须检查,扫描器给出的杠杆是保守值,并非实际最大可使用杠杆。
max-leverage.json集中持仓优于分散持仓。 小资金账户(500-10000美元)下,2-4个高信心持仓优于6个表现平庸的持仓。跨保证金计算:4个持仓→80.6%保证金缓冲,2个持仓→89.7%保证金缓冲。
每个仓位都要实现ROI最大化。 空仓位好于平庸持仓。如果某一持仓表现不及预期,立即平仓释放仓位。
速度筛选。 最好的行情走势速度极快(XRP仅用19分钟就达到Tier 3,XMR37分钟达到Tier 2),走势缓慢的标的通常存在隐患。
Directional Exposure Guard
方向敞口保护
Before opening, check total LONG vs SHORT notional. Cap at 70% in one direction.
开仓前,检查多头与空头的总名义金额,单方向占比最高不能超过70%。
Position Sizing by Score
按评分确定仓位大小
| Scanner Score | Position Size |
|---|---|
| 250+ | Up to max per-position |
| 200-250 | 75% of max |
| 175-200 | 50% of max |
| < 175 | Skip |
| 扫描器评分 | 仓位大小 |
|---|---|
| 250+ | 最高可达到单仓位上限 |
| 200-250 | 单仓位上限的75% |
| 175-200 | 单仓位上限的50% |
| < 175 | 跳过 |
Step 3: Create the Strategy
步骤3:创建策略
strategy_create_strategy(budgetUsd, leverageType, riskLabel)Returns + . Fund the wallet.
strategyIdwalletAddressstrategy_create_strategy(budgetUsd, leverageType, riskLabel)返回 + ,向该钱包转入资金即可。
strategyIdwalletAddressStep 4: Create the Playbook File
步骤4:创建交易方案文件
JSON config tracking: risk profile, position limits, score thresholds, active positions, trade journal. See references/playbook-schema.md.
JSON配置记录内容包括:风险等级、仓位限制、评分阈值、活跃持仓、交易日志。请查看 references/playbook-schema.md。
Step 5: Set Up Cron Jobs
步骤5:设置定时任务
Race Condition Prevention (v6 — CRITICAL)
Multiple cron jobs (scanner, SM flip, DSL) can all try to close the same position. When ANY job closes a position:
python
undefined竞态条件预防(v6版本 — 核心功能)
多个定时任务(扫描器、SM翻转、DSL)可能会同时尝试平仓同一个仓位。当任意任务平仓某一持仓时:
python
undefined1. Close the position
1. Close the position
result = close_position(wallet, asset)
result = close_position(wallet, asset)
2. Immediately deactivate DSL state file
2. Immediately deactivate DSL state file
state["active"] = False
save_state(state)
state["active"] = False
save_state(state)
3. Disable DSL cron for this asset
3. Disable DSL cron for this asset
disable_cron(f"dsl-{asset}")
All three steps MUST happen in the same action. This prevents phantom closes.
**Cron Schedule:**
| Job | Interval | Purpose |
|---|---|---|
| Opportunity Scanner | 10-30 min (time-aware) | Find setups |
| DSL Monitor | 2-3 min per position | Trailing stops |
| SM Flip Detector | 5 min | Conviction changes |
| Portfolio Update | 15 min | Reporting |
See [references/cron-setup.md](references/cron-setup.md) for detailed cron configuration, time-aware scheduling, and SM flip detection logic.disable_cron(f"dsl-{asset}")
以上三个步骤必须在同一个操作中完成,这样可以避免phantom平仓问题。
**定时任务计划:**
| 任务 | 执行间隔 | 用途 |
|---|---|---|
| 机会扫描器 | 10-30分钟(时间感知) | 寻找交易机会 |
| DSL监控 | 每个持仓每2-3分钟执行一次 | 移动止损 |
| SM翻转检测器 | 5分钟 | 监测持仓信心变化 |
| 投资组合更新 | 15分钟 | 数据报告 |
详细的定时任务配置、时间感知调度、SM翻转检测逻辑请查看 [references/cron-setup.md](references/cron-setup.md)。Step 6: The Trading Loop
步骤6:交易循环
SCAN → EVALUATE → TRADE → PROTECT → REPEAT
For each scan result:
1. Check hourly trend alignment (HARD REQUIREMENT)
2. Check directional exposure guard
3. Check max leverage via max-leverage.json
4. Score ≥ 175? → Size by score tier
5. Open position → Create DSL state → Start DSL cron
6. Journal the trade (scanner snapshot at entry)SCAN → EVALUATE → TRADE → PROTECT → REPEAT
For each scan result:
1. Check hourly trend alignment (HARD REQUIREMENT)
2. Check directional exposure guard
3. Check max leverage via max-leverage.json
4. Score ≥ 175? → Size by score tier
5. Open position → Create DSL state → Start DSL cron
6. Journal the trade (scanner snapshot at entry)v6: Dead Weight Cutting
v6版本:无效持仓清理
| Condition | Action |
|---|---|
| SM conviction drops 4→1 (e.g., 220→24 traders in 10 min) | Cut immediately |
| Dead weight at conviction 0 | Cut immediately — free the slot |
| Position stagnant, better opportunity available | Rotate |
| 触发条件 | 执行操作 |
|---|---|
| SM持仓信心从4跌至1(例如10分钟内评分从220降至24) | 立即平仓 |
| 持仓信心为0的无效持仓 | 立即平仓,释放仓位 |
| 持仓停滞,同时出现更好的交易机会 | 调仓换股 |
Step 7: Safety Rails
步骤7:安全防护
Hard Stops (automatic):
- Daily loss limit hit → stop trading for the day
- Total drawdown hard stop → close all positions, alert user
- DSL breach → auto-close (handled by script)
What the Agent Should NEVER Do:
- Trade counter-trend on hourly
- Exceed position size limits
- Override DSL
- Average down on a losing position
- Ignore the directional exposure guard
硬性止损(自动执行):
- 达到单日亏损上限 → 当日停止交易
- 达到总回撤硬性止损线 → 平仓所有持仓,向用户发送告警
- 触发DSL阈值 → 自动平仓(由脚本处理)
Agent绝对禁止的操作:
- 进行小时级别的逆势交易
- 超出仓位大小限制
- 覆盖DSL规则
- 对亏损持仓加仓摊薄成本
- 忽略方向敞口保护规则
Step 8: Lessons from the Field
步骤8:实盘经验总结
See references/lessons.md for what works, what doesn't, retrace tuning, and fee awareness from live trading.
关于有效策略、无效策略、回撤参数调整、实盘交易手续费注意事项等内容,请查看 references/lessons.md。
API Reference
API参考
See references/api-tools.md for the key Senpi tools used by this recipe.
本方案使用的核心Senpi工具请查看 references/api-tools.md。