Claude Code starts in its prompting mode when auto isn't available for the
session's model or backend, so a headless Auto task can still stall. Say so
in the task editor, the task runner comment, and HOW-TO-USE.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude Code now ships `--permission-mode auto`, where a safety classifier
approves routine actions and blocks risky ones without prompting. Expose it
as a fifth mode between Accept Edits and Bypass: terminals, resumed sessions,
the tab badge, and the scheduler's task runner all map it to the flag.
Headless scheduled runs don't stall in Auto (blocked actions are denied, not
prompted), so the task editor shows a softer note instead of the stall warning.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>