Git worktrees are not an isolation boundary for coding agents
1–10 of 43 posts
Re: Git worktrees are not an isolation boundary for coding agents
#2I haven’t hit these issues when using worktrees. But what’s a pain is having to compile from scratch every time, and not carrying over gitignored files.
Re: Git worktrees are not an isolation boundary for coding agents
#3Worktrees are the obvious pick, and I get why. One command, cheap, and if you're the only one driving, then sharing .git is the point rather than a compromise. I started there too.
An agent in a worktree can reach your hooks, your config, another worktree's stash. Probably not a common problem. But when it does happen you're not debugging your code, you're debugging git, and it's not obvious where to even start looking.
The one that actually bothers me is prompt injection. The agent reads an issue, or a dependency's README, or a web page, and what it's told to do is drop a file in the .git it can already write to. Next time you commit, that runs on your machine as you.
Separate thing - worktrees just get annoying to manage. Can't check out the same branch twice, so you're making up branch names to keep git happy. Every one is another directory to keep track of. Then something goes stale and you're back in git worktree prune.
So has any of it got to you? Or do you hit the annoying parts, shrug, and carry on?
Re: Git worktrees are not an isolation boundary for coding agents
#4I haven’t hit these issues when using worktrees. But what’s a pain is having to compile from scratch every time, and not carrying over gitignored files.
[dead]
Re: Git worktrees are not an isolation boundary for coding agents
#5Worktrees are the obvious pick, and I get why. One command, cheap, and if you're the only one driving, then sharing .git is the point rather than a compromise. I started there too. An agent in a worktree can reach your hooks, your config, another worktree's stash. Probably not a common problem. But when it does happen you're not debugging your code, you're debugging git, and it's not obvious where to even start looki…
Is this an LLM response? If not, take a break, you've assimilated.
Re: Git worktrees are not an isolation boundary for coding agents
#6I haven’t hit these issues when using worktrees. But what’s a pain is having to compile from scratch every time, and not carrying over gitignored files.
.worktreeinclude is probably part of the solution.
https://code.claude.com/docs/en/worktrees#copy-gitignored-fi...
Re: Git worktrees are not an isolation boundary for coding agents
#7I don't think people use it for isolation, but for what the feature enables in the first place: parallel workstreams
Re: Git worktrees are not an isolation boundary for coding agents
#8I haven’t hit these issues when using worktrees. But what’s a pain is having to compile from scratch every time, and not carrying over gitignored files.
Same here, over hundreds of worktrees in months of work.
The only problem I ran into was when Codex or Claude Code were configured to create the worktrees nested into the parent repository.
Then grep would yield results from a worktree and the agent would happily start to work in the wrong worktree.
Re: Git worktrees are not an isolation boundary for coding agents
#9It would be interesting to have a general fix for this in git. Something that more carefully splits the metadata from the working copy, a bit like we used to routinely do with "shadow build trees" with autoconf+make etc.
The parallel trees could have different ownership and access privileges, so that the editable working copy does not require the same filesystem access rights as the metadata tree. The git CLI actions would be performed with the more privileged filesystem role, and it would also have to be audited to make sure it treats all the working copy content as untrusted payload.
Re: Git worktrees are not an isolation boundary for coding agents
#10For me the most pragmatic way to solve this is in the agent harness layer simply prohibiting commands like git force and others in the settings configuration of your harness of choice with pre tool hooks, its quite easy to setup, obvious ones are prohibiting pushes to main, among others.
Unless someone is building their harness from scratch like you this is a 30sec configuration and you could just save your list of blocked commands with wildcards in a file, and copy paste from one harness to the other.