docs(concepts): 新增「智能体权限边界」——谁动手按谁的权限算 - #49
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
同伴之间开始互相协作（委派、发消息、插话、打断）后，必须回答一个问题：甲让乙做事， 按谁的权限算？ 本文说明 DesireCore 的选择与理由：**按执行方自己的权限算，越权责任在执行方**。 并解释了为什么没有采用「按发起方权限收窄」的直觉方案——它会让专业分工失效 （权限小的助理无法请权限大的专家干本职工作）、让责任随「谁指使」而变、 且在多层协作下权限一路归零，反而逼用户给每个同伴开更大的权限。 同时说明这不削弱可控性：授权来源仍然唯一（只由用户配置），三层可控性完整生效， 且边界更容易检查——只需回答「我给这个同伴开了什么权限」。 中英双语；委派式交互模型页与两个语种的概念索引同步加了入口。 顺带把英文索引缺失的 Task Orchestration 一行补齐。
yi-ge
force-pushed
the
docs/agent-permission-boundary
branch
from
July 29, 2026 13:09
aec0ab1 to
cbeb784
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
背景 / Context
同伴之间开始互相协作后（委派、发消息、插话、打断），出现一个必须公开回答的问题：
这条规则此前只存在于实现里，没有对用户说明。本 PR 把它写成一页公开概念文档，说明选择与理由。
Once companions collaborate (delegate / message / interject / interrupt), one question must be answered publicly: when A asks B to do something, whose permissions apply? This PR documents the rule and, more importantly, the reasoning.
规则 / The rule
每个智能体做事时只受它自己的权限上限约束；如果发生越权，责任在执行操作的那个智能体，而不是发起请求的那一方。
Every agent acts within its own permission ceiling. Accountability for overreach lies with the agent that acted, not with whoever asked.
为什么不采用「按发起方权限收窄」 / Why not cap by the requester
文档正面回答了这个直觉方案为什么不成立，三条理由：
同时说明这不削弱可控性 / And why controllability is unaffected
改动 / Changes
docs/04-concepts/12-agent-permission-boundary.md+ 英文镜像02-delegation-model.md（中英）新增「同伴之间也能互相委派」小节，指向新页Task Orchestration一行（此前与中文版不同步）Checklist