goal-loop
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseGoal Loop
目标循环
Steps
步骤
- Parse goal. Read (default
max_rounds). Reject non-positive integer.5 - Infer completion criteria from goal and repo context. Record uncertainty as blocker only when it prevents safe next action.
- Choose smallest useful next action. Route through existing skill when one fits.
- Verify with narrowest useful check: test, diff, command output, artifact.
- Critique: what proves or disproves completion? What remains? Smallest next action?
- Criteria evidenced: stop . max_rounds reached: stop
completed. Else repeat from 3.max_rounds
- 解析目标。读取 (默认值为
max_rounds)。拒绝非正整数。5 - 根据目标和 repo 上下文推断完成标准。仅当不确定性阻碍安全的下一步操作时,才将其记录为 blocker。
- 选择最小且有用的下一步操作。如果有合适的现有 skill,则通过该 skill 执行。
- 使用范围最小且有用的检查进行验证:test、diff、命令输出、artifact。
- 批判性审视:什么能够证明或推翻完成状态?还剩下什么?下一步最小操作是什么?
- 完成标准已有证据:停止并返回 。达到
completed:停止并返回max_rounds。否则从第 3 步重复。max_rounds
Rules
规则
A round = one state-changing action + verification. Tool calls are not rounds. Do not spend rounds restating goal, polling without change, or speculative cleanup. Pause before commits, pushes, PR, deploy, production, credentials, irreversible ops.
一轮(round)= 一次改变状态的操作 + 一次验证。工具调用不算轮次。不要浪费轮次复述目标、无变化地轮询或进行推测性清理。在 commit、push、PR、deploy、production、credentials 或不可逆操作之前暂停。
Status
状态
End with exactly one: , (name unblocker), (name remaining criteria).
completedblockedmax_rounds最后必须且只能返回以下之一:、(注明解除阻塞所需的条件)、(注明尚未满足的标准)。
completedblockedmax_rounds