pre-trade-discipline-gate

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Pre-Trade Discipline Gate

交易前纪律校验门

Overview

概述

Evaluate whether a planned manual order should proceed before it is placed at the broker. This skill reads a local checklist plus optional market-regime, circuit-breaker, and trader-memory-core artifacts. It produces a

pre_trade_discipline_decision

artifact and can link that artifact back to the related thesis without changing the thesis review schedule.

The gate is intentionally offline. It does not place orders, cancel orders, call a broker API, or fetch market data.

评估计划中的手动订单是否应在提交给经纪商前执行。该Skill会读取本地检查清单以及可选的市场机制、熔断机制和trader-memory-core工件。它会生成一个

pre_trade_discipline_decision

工件，并可将该工件关联到相关的交易论点（thesis），而不会改变论点的审核日程。

该校验门为离线设计，不会下单、取消订单、调用经纪商API或获取市场数据。

When to Use

使用场景

Immediately before placing any manual entry order
When a candidate has passed chart validation and position sizing
After a recent loss, to avoid revenge trades during the cooldown window

When the workflow has an upstream

exposure_decision

and

circuit_breaker_decision

When you want checklist adherence to be visible in later trader-memory-core reviews

下达任何手动入场订单前立即使用
当候选订单通过图表验证和仓位规模确认后
近期出现亏损后，用于避免冷却期内的报复性交易

工作流上游存在

exposure_decision

和

circuit_breaker_decision

时

希望检查清单的遵守情况在后续trader-memory-core审核中可见时

Prerequisites

前置条件

Python 3.9+
A local JSON or YAML answers file with candidate-level checklist answers
Optional trader-memory-core thesis state under
```
state/theses/
```
Optional
```
exposure_decision
```
JSON from market-regime-daily / exposure-coach
Optional
```
circuit_breaker_decision
```
JSON from drawdown-circuit-breaker

Python 3.9+
包含候选订单级检查清单答案的本地JSON或YAML文件
可选：
```
state/theses/
```
下的trader-memory-core交易论点状态
可选：来自market-regime-daily / exposure-coach的
```
exposure_decision
```
JSON文件
可选：来自drawdown-circuit-breaker的
```
circuit_breaker_decision
```
JSON文件

Workflow

工作流程

Step 1: Prepare the Checklist

步骤1：准备检查清单

Create a JSON or YAML file with candidate answers. Only actionable manual-order intents are gated. Watchlist and ignore intents are journaled as

NO_ACTIONABLE_ORDERS

json

{
  "candidates": [
    {
      "symbol": "AAPL",
      "thesis_id": "th_aapl_gm_20260703_0001",
      "order_intent": "ENTRY_READY",
      "entry_in_written_plan": true,
      "stop_predefined": true,
      "size_within_plan": true,
      "planned_risk_dollars": 500,
      "actual_risk_dollars": 500,
      "notes": "Entry matches the journaled breakout plan."
    }
  ]
}

Actionable intents are

ENTRY_READY

ACTIONABLE

ACTIONABLE_DAY1

, and

MANUAL_ORDER

. Non-actionable intents such as

WATCHLIST

DELAYED_EP_WATCH

PEAD_HANDOFF

IGNORE

, and

REJECTED

are recorded but do not create an order permission.

Provide both

planned_risk_dollars

and

actual_risk_dollars

for every actionable candidate. Use a finite, non-negative number or numeric string; zero is valid. Treat missing values, booleans, non-numeric strings,

NaN

, infinities, and negative values as

REVIEW_REQUIRED

inputs and review them before placing an order.

创建包含候选订单答案的JSON或YAML文件。仅对可执行的手动订单意向进行校验。观察列表和忽略意向会被记录为

NO_ACTIONABLE_ORDERS

。

json

{
  "candidates": [
    {
      "symbol": "AAPL",
      "thesis_id": "th_aapl_gm_20260703_0001",
      "order_intent": "ENTRY_READY",
      "entry_in_written_plan": true,
      "stop_predefined": true,
      "size_within_plan": true,
      "planned_risk_dollars": 500,
      "actual_risk_dollars": 500,
      "notes": "Entry matches the journaled breakout plan."
    }
  ]
}

可执行意向包括

ENTRY_READY

、

ACTIONABLE

、

ACTIONABLE_DAY1

和

MANUAL_ORDER

。非可执行意向如

WATCHLIST

、

DELAYED_EP_WATCH

、

PEAD_HANDOFF

、

IGNORE

和

REJECTED

会被记录，但不会生成下单权限。

为每个可执行候选订单同时提供

planned_risk_dollars

和

actual_risk_dollars

。使用有限的非负数或数字字符串；零是有效的。将缺失值、布尔值、非数字字符串、

NaN

、无穷大和负值视为

REVIEW_REQUIRED

输入，需在下单前进行审核。

Step 2: Run the Gate

步骤2：运行校验门

bash

python3 skills/pre-trade-discipline-gate/scripts/check_pre_trade_discipline.py \
  --answers-file state/manual-entry-checklist.json \
  --state-dir state/theses \
  --market-regime-decision reports/exposure_decision_latest.json \
  --circuit-breaker-decision reports/circuit_breaker_decision_latest.json \
  --output-dir reports/pre-trade-discipline \
  --journal-dir state/journal/pre-trade-discipline

Set

--as-of

for deterministic testing or backfills:

bash

python3 skills/pre-trade-discipline-gate/scripts/check_pre_trade_discipline.py \
  --answers-file state/manual-entry-checklist.json \
  --as-of 2026-07-03T12:00:00-04:00

bash

python3 skills/pre-trade-discipline-gate/scripts/check_pre_trade_discipline.py \
  --answers-file state/manual-entry-checklist.json \
  --state-dir state/theses \
  --market-regime-decision reports/exposure_decision_latest.json \
  --circuit-breaker-decision reports/circuit_breaker_decision_latest.json \
  --output-dir reports/pre-trade-discipline \
  --journal-dir state/journal/pre-trade-discipline

设置

--as-of

参数用于确定性测试或回溯填充：

bash

python3 skills/pre-trade-discipline-gate/scripts/check_pre_trade_discipline.py \
  --answers-file state/manual-entry-checklist.json \
  --as-of 2026-07-03T12:00:00-04:00

Step 3: Interpret the Decision

步骤3：解读决策

Decision	Meaning
`GO`	All actionable manual-order candidates passed the checklist and upstream gates
`REVIEW_REQUIRED`	Inputs are missing, unknown, or journaling failed; do not place orders until reviewed
`NO_GO`	At least one actionable candidate violated a discipline rule
`NO_ACTIONABLE_ORDERS`	The file contains no actionable manual orders; nothing should be placed

By default the CLI exits

for every valid decision and exits

only for input or runtime errors. Use

--fail-on-non-go

when a shell pipeline should return

for any non-

GO

decision.

决策结果	含义
`GO`	所有可执行手动订单候选均通过检查清单和上游校验门
`REVIEW_REQUIRED`	输入缺失、未知或记录失败；下单前需先审核
`NO_GO`	至少一个可执行候选违反了纪律规则
`NO_ACTIONABLE_ORDERS`	文件中无任何可执行手动订单；无需下单

默认情况下，CLI对所有有效决策返回退出码

，仅在输入或运行时错误时返回退出码

。当Shell流水线需要对任何非

GO

决策返回退出码

时，使用

--fail-on-non-go

参数。

Rules

规则

The gate blocks an actionable candidate when:

The entry is not confirmed in the written plan
The stop is not predefined
The size is not confirmed within plan
Either risk-dollar field is missing or is not a finite, non-negative number (
```
REVIEW_REQUIRED
```
)
```
actual_risk_dollars
```
exceeds
```
planned_risk_dollars
```
trader-memory-core has a losing exit or partial loss inside the revenge window
exposure-coach recommendation is
```
REDUCE_ONLY
```
or
```
CASH_PRIORITY
```
drawdown-circuit-breaker recommendation is
```
COOLDOWN
```
,
```
HALTED
```
, or
```
TRADING_HALTED
```

Missing or unreadable market-regime or circuit-breaker artifacts produce

REVIEW_REQUIRED

for actionable orders. If no actionable order exists, the result remains

NO_ACTIONABLE_ORDERS

当出现以下情况时，校验门将阻止可执行候选订单：

入场未在书面计划中确认
止损未预先定义
仓位规模未在计划范围内确认
任一风险美元字段缺失或不是有限的非负数（标记为
```
REVIEW_REQUIRED
```
）
```
actual_risk_dollars
```
超过
```
planned_risk_dollars
```
trader-memory-core显示在报复窗口内存在亏损离场或部分亏损
exposure-coach的建议为
```
REDUCE_ONLY
```
或
```
CASH_PRIORITY
```
drawdown-circuit-breaker的建议为
```
COOLDOWN
```
、
```
HALTED
```
或
```
TRADING_HALTED
```

市场机制或熔断机制工件缺失或无法读取时，可执行订单会被标记为

REVIEW_REQUIRED

。如果没有可执行订单，结果仍为

NO_ACTIONABLE_ORDERS

。

Outputs

输出

The script writes:

pre_trade_discipline_decision_YYYY-MM-DD_HHMMSS.json

A matching markdown report unless
```
--json-only
```
is set

A JSONL journal row under

state/journal/pre-trade-discipline/

when

--journal-dir

is provided

Each candidate result includes a

checklist_answers

object with the written-plan, stop, size, risk-dollar, and notes answers used for the decision, so later reviews can audit what was answered at order time. Invalid risk-dollar values are stored as JSON

null

, while valid values retain their original representation.

If a candidate includes

thesis_id

and

--state-dir

is provided, the JSON report is linked into the thesis

linked_reports

list using trader-memory-core

link_report

. The skill does not call

mark_reviewed

and does not change monitoring review dates.

脚本会生成以下内容：

pre_trade_discipline_decision_YYYY-MM-DD_HHMMSS.json

对应的Markdown报告（除非设置了
```
--json-only
```
参数）
当提供
```
--journal-dir
```
参数时，在
```
state/journal/pre-trade-discipline/
```
下生成JSONL格式的记录行

每个候选订单结果包含

checklist_answers

对象，其中包含用于决策的书面计划、止损、仓位规模、风险美元和备注答案，以便后续审核可追溯下单时的回答内容。无效的风险美元值会存储为JSON

null

，有效值则保留其原始格式。

如果候选订单包含

thesis_id

且提供了

--state-dir

参数，JSON报告会通过trader-memory-core的

link_report

方法关联到交易论点的

linked_reports

列表中。该Skill不会调用

mark_reviewed

方法，也不会更改监控审核日期。

Resources

资源

```
scripts/check_pre_trade_discipline.py
```
- Main CLI and rule engine
```
references/discipline_gate_framework.md
```
- Rule definitions and integration notes

skills/trader-memory-core/schemas/thesis.schema.json

- Thesis state schema

```
scripts/check_pre_trade_discipline.py
```
- 主CLI和规则引擎
```
references/discipline_gate_framework.md
```
- 规则定义和集成说明

skills/trader-memory-core/schemas/thesis.schema.json

- 交易论点状态 schema

Key Principles

核心原则

Manual execution only - The output is a pre-broker checklist gate, not an order router.
Written plan first - No written entry plan, stop, or size confirmation means no manual entry.
Producer-compatible state reading - Revenge-risk detection follows trader-memory-core timestamp and outcome behavior.
Journal without review side effects - The gate links reports to theses without advancing review schedules.

仅支持手动执行 - 输出是经纪商下单前的检查清单校验门，而非订单路由工具。
书面计划优先 - 若无书面入场计划、止损或仓位规模确认，则不允许手动下单。
兼容生产者状态读取 - 报复性风险检测遵循trader-memory-core的时间戳和结果行为。
记录但不产生审核副作用 - 校验门将报告关联到交易论点，但不会推进审核日程。