Claude Code v2.1.183: Safer Auto Mode and Terminal Stability Fixes

Claude Code v2.1.183 blocks destructive git and infrastructure commands in auto mode, adds deprecated-model warnings and new config options, and fixes a wide range of TUI, subagent, and teammate issues.

June 19, 2026 • 10 min read • By ClaudeWorld

The Claude Code development team has released version 2.1.183, a safety-focused update that hardens auto mode against destructive commands, improves model deprecation visibility, and delivers an extensive batch of fixes covering the terminal UI, subagents, MCP, and teammate workflows.

What’s New

Safer Auto Mode

Auto mode now blocks destructive git commands (git reset --hard, git checkout -- ., git clean -fd, git stash drop) when you didn’t ask to discard local work. In addition, git commit --amend is blocked when the commit wasn’t made by the agent in the current session, and terraform destroy, pulumi destroy, and cdk destroy are blocked unless you explicitly asked for the specific stack.

Model Deprecation Warnings

A warning is now shown when the requested model is deprecated or automatically updated to a newer model. The warning appears on stderr in print mode (-p) and now also covers models set in agent frontmatter.

New Configuration Options

  • The new attribution.sessionUrl setting lets you omit the claude.ai session link from commits and PRs in web and Remote Control sessions
  • /config --help now lists all available shorthand keys for /config key=value
  • The /config toggle behavior has changed: Enter and Space both change the selected setting, and Esc now saves and closes instead of reverting
  • The startup “setup issues” line under the logo has been removed — run /doctor to see configuration issues or use --debug

Subagent and Model Fixes

This release resolves several issues affecting subagents:

  • Fixed thinking.disabled.display: Extra inputs are not permitted 400 errors on subagent spawns and session-title generation for affected configurations
  • Fixed WebSearch returning empty results in subagents
  • Fixed turns silently completing with no visible output when the model returned only a thinking block; Claude now re-prompts once
  • Fixed MCP servers requiring authentication exposing auth-stub tools to the model in headless/SDK mode
  • Fixed user-level skills appearing multiple times in slash-command autocomplete when multiple plugins are enabled

Terminal UI Stability

  • Fixed the terminal cursor being stranded above the prompt after navigating history in vim mode with the native cursor enabled
  • Fixed fullscreen TUI corruption (statusline mid-screen, duplicated spinner rows, merged text) in Windows Terminal under heavy nested-subagent load
  • Fixed focus mode showing “Ran N PostToolUse hooks” timing lines under each response

Teammate and Automation Reliability

  • Fixed tmux teammate panes failing to launch when the shell has slow rc-file initialization, and keystrokes typed during agent spawn leaking into the new tmux pane instead of the leader prompt
  • Fixed background tasks started by a teammate being killed when the teammate finishes a turn
  • Fixed scheduled task and webhook trigger deliveries being treated as keyboard input; they now classify as task notifications and can no longer approve a pending action or set the session title in auto mode

How to Update

To update to Claude Code v2.1.183:

  1. Check your current version: claude --version
  2. Update using your preferred method:
    • Package manager: Follow your distribution’s update process
    • Direct download: Visit the release page for platform-specific binaries
  3. If you rely on auto mode, note the new guardrails around destructive git and infrastructure commands
  4. Review the attribution.sessionUrl setting if you want to control session links in commits and PRs