Before Claude runs a shell command, Claude Code checks whether it is safe and whether it needs your permission. If that check fails with an error, Claude Code now asks you, with the note "The permission check for this command did not finish, so its safety checks did not run." Before, it logged the error and returned whatever decision it had reached so far.
Warnings about dangerous file deletion are also now kept when a command is too complex to analyse fully, and the way several decisions are combined now favours some outcomes differently.
A failure inside the safety check now leads to a prompt instead of possibly letting the command run without one.
tengu_amber_larch On for this account, and not off by defaultThe flag server returned on for the one account this site reads, and nothing in this release compiles it off by default. The compiled default is shown below, and says which it is when we cannot read one: a fifth of gates compile in a string or a number rather than on or off, and most published releases have no gate table behind them at all. No client can see what the server returns for your account.
This account: on · anonymous baseline: on · compiled default in v2.1.312: 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 v2.1.312. It isn't a statement about your account. What a flag value here can and cannot tell you