v2.1.183
Claude CodeSummary
This release significantly enhances safety in auto mode by blocking potentially destructive commands unless explicitly intended by the user. It also introduces a warning for deprecated models and improves the usability of the `/config` command. Several bugs related to TUI corruption, subagent communication, and background task handling have also been resolved.
New Features
- Added `/config --help` to list all available shorthand keys for `/config key=value`
- Added `attribution.sessionUrl` setting to omit the claude.ai session link from commits and PRs in web and Remote Control sessions
Bug Fixes
- 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 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 turns silently completing with no visible output when the model returned only a thinking block; Claude now re-prompts once
- Fixed user-level skills appearing multiple times in slash-command autocomplete when multiple plugins are enabled
- Fixed MCP servers requiring authentication exposing auth-stub tools to the model in headless/SDK mode
- 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
- Fixed focus mode showing "Ran N PostToolUse hooks" timing lines under each response
Improvements
- Improved auto mode safety by blocking destructive git commands (like `git reset --hard`, `git clean -fd`) unless discarding local work was explicitly requested, and restricting `git commit --amend` to commits made by the agent this session.
- Improved auto mode safety by blocking `terraform destroy`, `pulumi destroy`, and `cdk destroy` unless the specific stack was requested.
- Added a warning shown on stderr when the requested model is deprecated or automatically updated to a newer model, now covering models set in agent frontmatter.
- Removed the startup "setup issues" line under the logo; users should run `/doctor` or use `--debug` to see configuration issues.
- Changed `/config` toggle behavior: Enter and Space now both change the selected setting, and Esc now saves and closes instead of reverting.