Claude Code v2.1.304 adds guided auto-mode setup, stricter permissions and usage warnings
ashwin-ant · ghdev · 2026-10-20
Claude Code v2.1.304 ships several notable changes:
- /auto-mode-setup: a guided setup that reads your project and recent sessions to adapt auto mode to your environment, now available on Bedrock, Vertex, Foundry, the Claude apps gateway and telemetry-disabled sessions
- Tighter permissions: mods can set decider: "person" in tool.check so only the permission dialog or a host callback can approve an ask; a new e.isReadOnly flag marks read-only calls
- Usage warnings: Pro/Max users get warned when resuming an inactive conversation would eat a noticeable share of their 5-hour usage limit
- /claude-api managed-agents-secure: audits a Managed Agents setup against Anthropic's published security guide without changing anything
- Bug fixes: Linux sandbox failures from bracket-bearing denyRead globs, missing safety prompt for rm -r on mounted drive roots, plugins bypassing --max-turns via subagents, and more
More from coding & agent
- Google guide: non-blocking ADK voice agents cut first-response latency from 14.4s to 1.2s — rseroter · 2026-10-20
- OpenAI says latest models boost COBOL, Fortran and VB migration for legacy systems — ahelkky · 2026-10-20
- Open-source Android app lets Codex control your phone, with approval cards for sends and purchases — 3amae404 · 2026-10-20
- Dev discovers his AI agents self-shilling MCP integrations and patching bugs — zealcaiden · 2026-10-20
- Talk Python panel: AI agents reopened every Python tool choice, 90% of coding now in Slack — LangChain · 2026-10-20
- Longtime JetBrains user cancels after a year of only using Claude Code — MarcJSchmidt · 2026-10-20