A tool call is a single action Claude takes, such as running a command. Claude Code now labels the reason an action was allowed with its source:
- a person, when approved through a permission prompt
- a classifier, when automatic mode's checker allowed it
- a mode, when automatic mode allowed it
- a hook, when a hook allowed it
A related hook path adds a reason for a person reading the rules. This is tied to a server-controlled flag whose built-in default is on.
It appears to be a way of recording who or what approved each action.
tengu_merry_popcorn Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.288: on
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.288. It isn't a statement about your account. What a flag value here can and cannot tell you
What the related flag actually controls is not known.
New in this build: tengu_merry_popcorn