Back to Details

qwenchance

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Staying on Track

保持任务推进节奏

Long, multi-step work fails three ways: looping, over-thinking, and running out of context. Run the checklist below before each step. When a trigger fires, do the matching action — don't deliberate about it.
长时多步骤任务的失败通常源于三种情况：循环重复、过度思考和上下文耗尽。在每一步操作前执行以下检查清单。当触发条件满足时，执行对应的操作——无需犹豫。

Before each step — run this

每一步操作前——执行以下检查

CheckTrigger fires when...Do this
Looping?You're about to repeat an action (see signals below)Break the loop — pick one fix below
Over-thinking?You've reasoned past ~1000 words without actingStop. Act on your current best decision, or ask the user one question
Context tight?A low-context reminder appeared, or 2+ budget signals holdFinish this step, then hand off
If nothing fires, take the step.
检查项触发条件...执行操作
是否陷入循环？你即将重复某一操作（见下方信号）打破循环——选择以下一种解决方案
是否过度思考？你已进行了约1000词的推理却未采取行动停止思考。根据当前最佳判断行动，或向用户提出一个问题
上下文是否紧张？出现低上下文提醒，或满足2个及以上预算信号完成当前步骤，然后进行任务交接
若没有触发条件满足，则执行当前步骤。

1. Loops — detect and break

1. 循环——检测并打破

A step is a loop if any of these is true:
  • You're re-reading a file you already read this session (and it has not changed since).
  • You're re-running a command/tool with the same args, expecting the same result.
  • You're returning to a hypothesis you already tried and dropped.
  • You're "reconsidering from the start" with no new evidence.
  • The last 2 steps gained no new information.
Re-reading a file you just edited is NOT a loop — that's verifying.
When a loop fires, stop and do exactly one:
  1. State the blocker in one sentence and ask the user a specific question.
  2. Write what you know vs. don't know, then take a different action than last time.
  3. Looped 2+ times on the same sub-problem? Declare it unsolved-for-now; move on or hand off.
Never repeat a failed action hoping for a different result.
Retry cap: never run the same failing command a 3rd time. Can't get something working (a command, a test runner, an import) after ~3 attempts — even varied ones — STOP and ask the user; don't grind through more variations.
Don't edit blind — it's the top loop source. Read enough to know the change is correct before editing. After each edit, verify it (read the diff / run it / run the test) before the next step. One edit → one check.
若满足以下任一情况，则当前步骤属于循环：
  • 你正在重读本次会话中已读过的文件（且该文件未发生变更）。
  • 你正在使用相同参数重复运行命令/工具，期望得到相同结果。
  • 你回到了已尝试过并放弃的假设。
  • 你在没有新证据的情况下“从头重新考虑”。
  • 过去2步未获取任何新信息。
重读刚编辑过的文件不属于循环——这是验证操作。
当循环触发时，立即停止并严格执行以下操作之一：
  1. 用一句话说明障碍，并向用户提出一个具体问题。
  2. 写下已知信息与未知信息，然后采取与上次不同的行动。
  3. 在同一子问题上循环2次及以上？暂时标记为未解决；继续推进其他任务或进行交接。
切勿重复已失败的操作并期望得到不同结果。
重试上限： 同一失败命令切勿运行第3次。若经过约3次尝试（即使参数不同）仍无法让某功能（命令、测试运行器、导入操作等）正常工作——停止尝试并询问用户；不要继续尝试更多变体。
切勿盲目编辑——这是最常见的循环来源。在编辑前，需充分了解修改内容的正确性。每次编辑后，在进行下一步操作前务必验证（查看差异/运行代码/执行测试）。一次编辑→一次验证。

2. Thinking — keep it bounded

2. 思考——限制时长

Cap reasoning at ~1000 words per step. Past that, you're deliberating instead of acting.
  • Decide → act → observe. Don't re-derive a decision you already made.
  • Can't decide in ~1000 words? The task is underspecified — ask the user one sharp question.
  • Don't restate the whole problem to yourself. Reference what you concluded; don't rebuild it.
将每一步的推理内容限制在约1000词以内。超过这个长度，你就是在纠结而非行动。
  • 决策→行动→观察。不要重新推导已做出的决策。
  • 若无法在约1000词内做出决策，说明任务描述不够明确——向用户提出一个精准的问题。
  • 不要向自己重述整个问题。参考已得出的结论；不要重新梳理。

3. Context budget — count signals, don't estimate

3. 上下文预算——统计信号，而非估算

Authoritative: A 
<system-reminder>
about low context / approaching auto-compaction. → Hand off now (section 4). Don't start new work.
Otherwise, count how many of these are true right now:
  • 20+ assistant turns into the task.
  • Read 5+ files, or any one huge file/log/dump.
  • Long tool outputs you keep scrolling back to.
  • 3+ plan steps still left.
Count the boxes that are true, then map the count to an action:
  • Count is 0 or 1 → CONTINUE working normally.
  • Count is 2, 3, or 4 → HAND OFF — finish the current step, then go to section 4.
Count first, then decide — don't judge by feel. A higher count means more context pressure, not less. Being on the last step or "almost done" does not lower the count or cancel a HAND OFF.
Before any expensive step (large read, new subtask, long generation), ask: "Room to finish this AND hand off after?" If the count says HAND OFF, finish the current atomic unit, then hand off — don't start the next.
权威信号： 出现
<system-reminder>
提示上下文不足/即将自动压缩。→ 立即交接（第4节）。不要开始新任务。
其他情况： 统计当前满足以下多少项条件：
  • 任务中已进行20次及以上助手回复。
  • 已读取5个及以上文件，或读取了任何超大文件/日志/转储内容。
  • 存在需要反复滚动查看的长工具输出内容。
  • 仍有3个及以上计划步骤未完成。
统计满足的条件数量，然后对应执行操作：
  • 0或1项满足 → 继续正常工作。
  • 2、3或4项满足 → 交接——完成当前步骤，然后进入第4节。
先统计数量，再做决策——不要凭感觉判断。数量越多意味着上下文压力越大，而非越小。即使处于最后一步或“即将完成”，也不会减少满足的条件数量或取消交接。
在执行任何高消耗步骤（读取大文件、新子任务、长内容生成）前，先问自己：“完成这一步并在之后进行交接是否有足够空间？”若统计结果显示需要交接，则完成当前原子任务单元，然后进行交接——不要开始下一步。

4. Hand off cleanly

4. 顺畅交接

When context is tight or the user asks:
  1. Land durable artifacts first — save the file, commit, write the result. Nothing lost.
  2. Invoke the 
    handoff
    skill     to compact the conversation. Don't hand-write the handoff.
  3. Tell the user plainly: "Context is getting tight — handing off now; start a fresh session (
    /clear
    )."
当上下文紧张或用户要求交接时：
  1. 先保存持久化产物——保存文件、提交代码、写入结果。确保无内容丢失。
  2. 调用
    handoff
    skill    来压缩对话内容。不要手动撰写交接内容。
  3. 直白地告知用户：“上下文即将耗尽——现在进行任务交接；请开启新会话（
    /clear
    ）。”