Claude Code v2.1.303-305: `/auto-mode-setup`, usage warnings, gateway tool-search retry
What is it?
The useful addition in this week's builds is /auto-mode-setup, a guided setup that teaches auto mode about your environment and works on Bedrock, Vertex, Foundry and other providers. /claude-api managed-agents-secure compares a Managed Agents setup with Anthropic's security guide without changing anything. On Pro and Max, resuming an idle conversation now warns you when it would eat a large share of the 5-hour limit.
Why does it matter?
Many teams left auto mode off because writing allow rules by hand was a chore, and guided setup makes starting easier. If you run behind an internal gateway, tool search now defaults on and retries on its own after a 400 or 422. Read the note on sandbox.allowNestedUserNamespaces in 2.1.305 before enabling it, since it can bypass the sandbox's file protections.
Maturity
GAGeneral release. 2.1.303 is listed only as bug fixes with no detailed notes.
How to track it
- Next builds: see whether 2.1.306 and later keep changing auto mode.
- Security setting: check how the docs word the warning for nested user namespaces.
- Usage: confirm on your own account that the Pro/Max limit warning matches real usage.