Skip to main content
A .probe.config file lists paths Probe must never record. Put one in any folder: it covers that folder and everything below it, in the same syntax as a .gitignore. It works whichever folder your coding agent was started in.
~/code/client-x/.probe.config
A .probe.config stops recording: no run is opened there, and no artifact, note or daemon record is made about those paths. Searching your team’s history still works, and session transcripts are still uploaded.

​
Common setups

In the repo’s root:
.probe.config

​
How a path is decided

1

Walk up from the path

Every .probe.config from the path up to / counts, including files above a repository’s root. A folder without one inherits its parents’ rules.
2

A match wins

If a rule excludes the path, nothing about it is recorded. /probe on cannot override it; edit the file instead.
3

No match: the session decides

Otherwise the session’s /probe on, read or off decides, as before. !pattern re-includes a path, except under a folder that is itself excluded.
To see which line excludes a path:

​
Files above where the agent started

A .probe.config in the folder the agent started in, or below it, always applies. One above that folder is yours to follow or set aside for each session: the agent asks you once, the first time Probe comes up, and follows the file until you answer.

​
What is enforced where

A .probe.config that exists but cannot be read excludes everything under its folder. It needs CLI 0.227.0 and plugin 0.125.0 or later; older clients ignore the file entirely. Update with probe wizard --action update --yes.

​
Replacing folder defaults

probe session default --folder and the .probe/config.json files it wrote are retired. An old one set to off or read still keeps its folder out of Probe in coding-agent sessions, the only place it ever applied. probe doctor lists them, and probe doctor --fix turns each into a .probe.config.