Source Intelligence
Follow Discord

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

← All of v2.1.122 Home All releases ←olderv2.1.121 v2.1.123newer→
Claude Code v2.1.122

Background Job Safety Guards

What

Adds upfront validation for --bg jobs that require specific permission modes, preventing silent failures when prerequisites are not met.

Details
  • Running --bg with --permission-mode auto now requires having opted in interactively first. If not, the error message reads: --bg with auto mode requires opting in first. Run 'claude --permission-mode auto' once interactively.
  • Running --bg with --dangerously-skip-permissions now requires having accepted the disclaimer interactively first. The error message reads: --bg with bypassPermissions requires accepting the disclaimer first. Run 'claude --dangerously-skip-permissions' once interactively.
Evidence

New validation function (search for "--bg with auto mode requires" and "--bg with bypassPermissions requires")

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.122 →