[bug] background subagents in auto mode flood me with permission prompts for safe…
维护者通常 5 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 4/5
- 预计耗时
- 3-5 天
- 新手友好度
- 18/100
- Issue 类型
- 缺陷
- 描述清晰度
- 基本清楚
- 活跃度
- 活跃
- 技术栈
- bun, shell, typescript
调研方向
Start with the LifeOSHooks tool.call hook and the SubagentGitSandbox class with its wrapInline method, which the report says wrap every subagent Bash command in sandbox-exec. Check how the hook's changed input leads to the "gave no verdict" result in auto mode, and reproduce with a background subagent running ls. Done means safe read-only subagent commands are judged without reaching the human, while the git-internals protection still holds.
由索引模型根据 Issue 内容生成。
描述
What happened
background subagents in auto mode flood me with permission prompts for safe commands, 15-20 clicks in a few minutes
Summary
In auto mode, a background subagent's Bash calls often get no verdict from the auto-mode reviewer and end up as permission prompts for the human, even for read-only commands.
Cause, from reading the code and the message Claude Code returns: the LifeOSHooks tool.call hook wraps every subagent Bash command in sandbox-exec (SubagentGitSandbox, wrapInline). Claude Code then reports "gave no verdict: a hook changed this call's input after the model wrote it, so the review was of different input from what would run", adds "This is not a judgment that the action is unsafe", and tells the model to issue the call again once.
Seen on 8.761.0 with four background subagents: about 15-20 prompts within a few minutes, for work that only read files. The same command type passes in the main session, which is not wrapped. It is intermittent (bun test passed while ls and bun Places.ts did not), and the agents copying the wrapped text into their retry adds more prompts.
Expected: the git-internals protection stays, and safe subagent commands are judged without reaching the human. The current workaround is telling subagents not to use Bash at all, which rules out any subagent that has to run tests, so unattended work is not practical.
Details
- Kind: bug
- LifeOS version: 8.761.0
Filed with the LifeOS /feedback command. The reporter approved this exact text before it was sent; paths, secrets and personal details were stripped locally.
- 主要语言
- TypeScript
- 星标
- 19.9k
- 派生
- 2.5k
- PR 合并指标
- 30 天内没有已合并 PR
环境准备
这个项目没有提供开发容器、Dockerfile 或贡献指南,环境需要你自己搭建:先看它的 README,通用步骤见我们的新手贡献指南。
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
danielmiessler/LifeOS 的其他 Issue
-
难度 2/5 1-3 小时 新手友好度 67/100
danielmiessler/LifeOS#2894 ·
维护者通常 5 天内回复
-
难度 2/5 1-3 小时 新手友好度 82/100
danielmiessler/LifeOS#2891 ·
维护者通常 5 天内回复
-
难度 2/5 1-3 小时 新手友好度 85/100
danielmiessler/LifeOS#2888 ·
维护者通常 5 天内回复
-
难度 2/5 1-3 小时 新手友好度 78/100
danielmiessler/LifeOS#2886 ·
维护者通常 5 天内回复
-
难度 1/5 1 小时以内 新手友好度 68/100
danielmiessler/LifeOS#2848 ·
维护者通常 5 天内回复
查看 danielmiessler/LifeOS 的全部 Issue
相似的 Issue
-
[功能请求] 设置选项语言调整未关闭功能请求
难度 2/5 1-3 小时 新手友好度 66/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 84/100
antithesishq/bombadil#473 ·
维护者通常 2 天内回复
-
The structured output reference promises null results for refusals that carry validation details未关闭bug
难度 2/5 1-3 小时 新手友好度 72/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 74/100
mattermost/mattermost-mobile#10358 ·
维护者通常 1 天内回复
-
ready-for-agent
难度 1/5 1 小时以内 新手友好度 86/100
LucasSantana-Dev/Lucky#3257 ·
维护者通常 1 天内回复