pi-sandbox

I disagree on plan and todo-list, which seem relatively not needed to me. No comment on goals/looping, which I don't have much experience with. To me it's great how minimal the system prompt and tool set is, and I doubt those features are worth the tokens for every model. (Who knows if they improve performance for SOTA models, and they probably harm performance for small local models.) I would add "better sandbox" support, which I think should be included out of the box. Not having a very simple way to get out of "yolo" mode is kinda crazy. Sure, there are plugins, but they do have some issues. pi-bash-approval is good, but manual approval plus allowlist is a "bad" way to run coding agents. The "best" way in my current opinion, is where commands run by default in a sandbox, but commands can be ran unsandboxed as needed, requiring approval

There is a keybindings file. Here's how to configure the "emacs" keybindings https://pi.dev/docs/latest/keybindings#emacs-example It starts up for me in under a second on my M4 mac. (Obviously could be faster, but doesn't bother me personally on my hardware) My one main "issue" is with using the pi-sandbox extension. It's based on a forked claude code sandbox runtime. Not exactly sure why a fork was needed, and the fork is a bit behind now. I also wish the sandbox feature worked a bit more like how Cursor's sandboxing worked. Not familiar with Claude Code sandboxing, so can't compare that. I describe the issue and a (slightly hacky, but productive enough) workaround here: https://github.com/carderne/pi-sandbox/issues/50 Obviously the fact that I can fork a plugin for pi and customize it as needed is quite a plus too. Really all the other

My favorite feature from Claude code is the "auto" mode to dynamically approve permission queries that are reasonably safe. Unfortunately the standard pi sandbox extension doesn't support it. Pi should really build permissions into the agent leve. https://github.com/carderne/pi-sandbox

Decent sandbox + sandbox override experience with pi coding agent... pi-sandbox uses the same sandbox tech that claude code uses, although it uses a fork that's a little behind, and I'm not sure exactly why it uses a fork. You can install pi, then install pi-sandbox locked to the current version. Here it is described how pi-sandbox plus an additional extension allow you to have the experience where a sandbox is used, but you can fall back to unsandboxed with approval required. https://github.com/carderne/pi-sandbox/issues/50

You can add that via an extension: https://github.com/carderne/pi-sandbox The price of flexibility is, pi is not opinionated about adding sandboxing out-of-the-box, it gives you options on how you want to do it. You either do it with linux containers, with a dedicated VM, or just bubblewrap. It is nice that it gives you a way to hook into it in a very easy way though.

I’m surprised it works for you with such a simple config? I’m the one that added the allowRead option to Claude’s underlying sandbox [0] and had quite a job getting my toolchains and skills to work with it [1]. [0] Fun to see the confusing docs I wrote show up more or less verbatim on Claude’s docs. [1] My config is here, may be useful to someone: https://github.com/carderne/pi-sandbox/blob/main/sandbox.jso...

How do agents tend to deal with getting blocked? Messing around with sandboxes, I've quite even seen them get blocked, assume something is wrong, and go _crazy_ trying to get around the block, never stopping to ask for user input. It might be good to add to the error message: "This is deliberate, don't try to get around it." For those using pi, I've built something similar[1] that works on macOS+Linux, using sandbox-exec/bubblewrap. Only benefit over OP is that there's some UX for temporarilily/permanently bypassing blocks. [1] https://github.com/carderne/pi-sandbox

I got pi to write me a very basic sandbox based on an example from the pi github. Added hooks for read/write/edit/bash, some prompts to temp/perm override. Have a look, copy-paste what you like. https://github.com/carderne/pi-sandbox