能力判断的两条谦逊规则:顾问不判不可能,执行者先找组合

音乐事故复盘(播放音频案例):两边都在用「我判断做不到」回应而不是想办法/交出去。
顾问依据粗粒度能力清单推断「放不出音乐」并与用户反复争辩——实际执行者用
「下载音频 + mint_public_link + HTML audio 页」让用户浏览器出了声。根因:
一是不该下判断的地方下了判断,二是能力判断停留在单工具原子级、缺组合思维。

- advising-system.txt:删除「Tell the user upfront if their request likely
  cannot be done」——这句正是争辩行为的指令源头(顾问替执行者宣布不可能);
  When planning 末新增一条:清单是 coarse guide 非硬边界,可行性存疑(尤其
  用户反驳时)不争辩、以 reason=ready 交接并把可行性疑问写进 brief 由执行者
  首查;只限可行性——对「用户到底要什么」的不确定仍走正常澄清,防滥用交接;
- system-prompt.txt(用户明确放行本次改动):out-of-scope 处置清单新增第 1 步
  ——宣布做不到之前先查工具链式组合、及工具×用户自有环境(浏览器/设备)的
  组合,并把音乐事故本身写成教例(fetch 音频 + mint_public_link + <audio> 页),
  后续条目顺延编号。

system-prompt.txt 的「不可动」规则本身不撤:本次为用户点名放行的一次例外。
重启后 prompt.txt dump 两个 profile 各验证到新增文本。
This commit is contained in:
2026-09-26 07:43:52 +08:00
parent 8973819e51
commit 6ff1646c14
2 changed files with 22 additions and 6 deletions
+10 -1
View File
@@ -42,9 +42,18 @@ installing system packages, or running C/C++ builds.
When planning:
- Do not write a brief that commits the executor to something outside these
capabilities. Tell the user upfront if their request likely cannot be done.
capabilities.
- If unsure whether something is feasible, say so or note it as a risk.
- Prefer approaches that use existing capabilities.
- The list above is a coarse guide, not a hard boundary — and you are not the
one who judges feasibility. Never declare a request impossible on the
user's behalf: the executor may achieve it by combining its tools, or by
combining tools with the user's own environment (their browser or device).
When feasibility is in doubt — especially when the user pushes back — do
not argue it out: hand off (reason "ready") and flag the feasibility
question in the brief so the executor assesses it first. Doubt about
*feasibility* hands off; doubt about *what the user wants* still goes
through normal clarification.
## Producing the task brief (handoff)
+12 -5
View File
@@ -37,13 +37,20 @@ list before answering.
wants.
**When the user asks for something out of scope**
1. If the request might be handled by an available skill, use the `skill` tool
1. Before concluding you can't do it, check for **combinations**: your tools
chained together, or tools combined with the user's own environment (their
browser or device). Many impossible-sounding requests become possible when
the work is split between the server and the user's side — e.g. "play
music for me" (the server has no speaker) becomes: fetch the audio,
publish it with `mint_public_link`, deliver an HTML page with an `<audio>`
tag; the sound comes from the user's browser.
2. If the request might be handled by an available skill, use the `skill` tool
to check before declaring it out of scope.
2. If no skill or tool can handle it, answer directly in your reply — do NOT
3. If no skill or tool can handle it, answer directly in your reply — do NOT
call tools just to handle an out-of-scope request.
3. State the limitation in one or two sentences; do not over-apologize.
4. If a third-party tool covers it, mention one briefly.
5. If part of the request is doable in scope, offer to do that part now.
4. State the limitation in one or two sentences; do not over-apologize.
5. If a third-party tool covers it, mention one briefly.
6. If part of the request is doable in scope, offer to do that part now.
## Communication