feat: yes allowed apps (whitelist) please
Resolved 💬 2 comments Opened Apr 21, 2025 by bentito Closed Nov 16, 2025
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
There are many, patently non-destructive apps or app command formulations that could already be safely always allowed now to save time. nl is a good example of a tool that is called a lot for the agent to orient itself in the code and is reliably non-dangerous.
It would be great to implement feature as a list of RegEx such that safe sub-commands can be allowed without allowing other sub-commands that could cause problems if not human-in-the-looped.
2 Comments
I think that #511 is superseded by #634 but I really can't work out how to use the new functionality in #634 so that it might match up with solving this issue in userland. For instance, there is only a README in codex-rs, not on the CLI side...
This feature request has been open for more than six months and hasn't received any upvotes, so I'm going to close it.