Unclear It is not clear what happens to a tool call after the accept-edits pre-check is skipped, so the effect on what gets approved is unknown.
What
Auto mode lets Claude act with less asking, with an automatic reviewer checking each action. Accept-edits mode allows file edits without asking.
- When actions keep being refused and no work goes ahead in between, the call is not run and the turn ends. The message says "actions were refused and no work went ahead in between". A subagent (a helper Claude starts for part of a task) gets a version saying it was stopped before it finished and that its output is partial.
- In auto mode, Bash commands are checked as they would be in accept-edits mode. A command that check cannot allow is marked
acceptEditsCannotAllow. This covers the loop case "Only the first pass of a loop in this command could be checked, and its later passes may run something else". - An
rmwith a Git Bash Windows path that the check cannot place now needs approval, with "Git Bash may read this Windows path differently from this check". - Nested command substitutions, commands run inside other commands, are now analysed up to a limit.
- A new plain-line check is recorded. A new pattern and the switch
tengu_lively_cook, which falls back to true, are related, but how they are used was not traced. - The server-controlled switch
tengu_lively_crown, which falls back to "off", runs an experiment on decisions markedacceptEditsCannotAllow, including ones nested insidesubcommandResults. With "count", the call is only marked as counted. With "skip", the call flaggedrunsAloneToolUseIdcan be picked at random to skip the accept-edits pre-check. It does nothing unless the server sets "count" or "skip".
Nothing has been read about tengu_lively_crown, tengu_lively_cook or tengu_iridescent_boot.
Why
Fewer partly checked commands are allowed in auto mode, and you may see more approval prompts for rm and Windows paths. A run that keeps being refused now stops. A server-side experiment can change which pre-check runs for some auto-mode calls.
tengu_lively_crown 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 v2.1.319: not a boolean we can read
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 v2.1.319. It isn't a statement about your account. What a flag value here can and cannot tell you
It is not clear what happens to a tool call after the accept-edits pre-check is skipped, so the effect on what gets approved is unknown.
New in this build: tengu_lively_crown