News for hackers. Stuff that matters.
Re:Codex CLI installs a persistent, self-updating background... by InsideOutSanta on Monday October 12, 2026 @03:48PM (#50061976)
Just garbage. Temp files, worktrees that weren't removed after subagents finished, build files... all kinds of things.
Re:Codex CLI installs a persistent, self-updating background... by thdr on Monday October 12, 2026 @03:55PM (#50062069)
But that's agent behavior, and not harness responsibility...?
Re:Codex CLI installs a persistent, self-updating background... by klodolph on Monday October 12, 2026 @06:46PM (#50064134)
Harnesses should be responsible IMO for managing lifecycle stuff, including worktrees and temp files.

It’s simple, deterministic stuff. At least most of the time.

Re:Codex CLI installs a persistent, self-updating background... by TeMPOraL on Tuesday October 13, 2026 @06:07PM (#50079576)
Hence my question.

I assume auto-updates are handled by deterministic code that's far away from anything agents can touch (self-modifying harnesses like Autolith notwithstanding). With the same behavior showing up in multiple high-profile harnesses (Codex, Claude Code), it feels likely there must be some actual reason for doing it this way.

Re:Codex CLI installs a persistent, self-updating background... by klodolph on Friday October 16, 2026 @01:15PM (#50121289)
I didn’t see your reply.

It should be the harness responsibility to create / destroy things like worktrees and scratch spaces, and communicate to the agent (e.g. via system prompt) where the scratch space is and its purge schedule. Harness should also set appropriate env vars to make this work in tools.

> With the same behavior showing up in multiple high-profile harnesses (Codex, Claude Code), it feels likely there must be some actual reason for doing it this way.

I think fixing it is just not high on the priority list.