A harness that controls the sandbox is exactly what I’m after. Tools don’t always need to share the same space, and I can isolate work much better if separate toolchains are isolated in sandboxes. My biggest gripe with the major harnesses is how they sandbox tool calls.
I almost never have to extend permissions of my sandbox. By default it can read/write the project tree, and read most files on the machine with specific secret locations excluded. If I do have to expand permissions and restart, I just resume the session.
Re:OpenCode Browse
by or1gaminal on Tuesday November 17, 2026 @10:21AM
(#50532585)
Offtop: "I agree in principle, but in practice..." do you listen to The Rest is History podcast? I just heard this line for the first time in this episode https://www.youtube.com/watch?v=8QIGseLdLk0 and now it props up second time on the same day!
Nope. Frequency illusion in action :)
Re:OpenCode Browse
by zaptheimpaler on Wednesday November 18, 2026 @12:04AM
(#50542095)
I think this is theoretically doable with Omnigent which i use but i haven’t tried. They just expose tools to modify the sandboxing params that the model can use with a permission prompt
I agree in principle, but in practice most sandboxing technology (like bwrap) is too static for this use case: You grant access once during startup and can't extend/revoke without a restart. That's inconvenient when you realize halfway through your session that you need additional permissions, and it's insufficient for permissions that are only briefly needed (for the duration of one tool call).
A harness that controls the sandbox (e.g. for each individual tool invocation) can manage this much more effectively.