v2.1.71
Claude CodeSummary
This release introduces powerful new scheduling capabilities with the /loop command and cron tools for recurring prompts. Numerous bugs have been resolved, particularly around session stability, startup freezes related to voice mode and OAuth refresh, and issues with forked conversations and plugin management. Performance has also seen improvements, including faster startup by deferring image processor loading.
New Features
- Added /loop command to run a prompt or slash command on a recurring interval (e.g. /loop 5m check the deploy)
- Added cron scheduling tools for recurring prompts within a session
- Added voice:pushToTalk keybinding to make the voice activation key rebindable in keybindings.json (default: space)
- Added bash auto-approval for commands including: fmt, comm, cmp, numfmt, expr, test, printf, getconf, seq, tsort, and pr
Bug Fixes
- Fixed stdin freeze in long-running sessions where keystrokes stop being processed but the process stays alive
- Fixed a 5–8 second startup freeze for users with voice mode enabled, caused by CoreAudio initialization blocking the main thread after system wake
- Fixed startup UI freeze when many claude.ai proxy connectors refresh an expired OAuth token simultaneously
- Fixed forked conversations (/fork) sharing the same plan file, which caused plan edits in one fork to overwrite the other
- Fixed the Read tool putting oversized images into context when image processing failed, breaking subsequent turns in long image-heavy sessions
- Fixed false-positive permission prompts for compound bash commands containing heredoc commit messages
- Fixed plugin installations being lost when running multiple Claude Code instances
- Fixed claude.ai connectors failing to reconnect after OAuth token refresh
- Fixed claude.ai MCP connector startup notifications appearing for every org-configured connector instead of only previously connected ones
- Fixed background agent completion notifications missing the output file path, which made it difficult for parent agents to recover agent results after context compaction
- Fixed duplicate output in Bash tool error messages when commands exit with non-zero status
- Fixed Chrome extension auto-detection getting permanently stuck on "not installed" after running on a machine without local Chrome
- Fixed /plugin marketplace update failing with merge conflicts when the marketplace is pinned to a branch/tag ref
- Fixed /plugin marketplace add owner/repo@ref incorrectly parsing @ — previously only # worked as a ref separator
- Fixed duplicate entries in /permissions Workspace tab when the same directory is added with and without a trailing slash
- Fixed --print hanging forever when team agents are configured — the exit loop no longer waits on long-lived in_process_teammate tasks
- Fixed "❯ Tool loaded." appearing in the REPL after every ToolSearch call
- Fixed prompting for cd <cwd> && git ... on Windows when the model uses a mingw-style path
Improvements
- Improved startup time by deferring native image processor loading to first use
- Improved bridge session reconnection to complete within seconds after laptop wake from sleep, instead of waiting up to 10 minutes
- Improved /plugin uninstall to disable project-scoped plugins in .claude/settings.local.json instead of modifying .claude/settings.json, so changes don't affect teammates
- Improved plugin-provided MCP server deduplication — servers that duplicate a manually-configured server are now skipped
- Updated /debug to toggle debug logging on mid-session, since debug logs are no longer written by default
- Removed startup notification noise for unauthenticated org-registered claude.ai connectors