Claude Code v2.1.169 Major Updates

This is Ishikawa from the Cloud Business Division. Claude Code v2.1.169 (released 2026-06-08) has been released. This release focuses on new features such as a startup mode for troubleshooting and a working directory change command, along with enterprise policy enforcement and security fixes.

Update Summary

v2.1.169 includes 30 changes. The breakdown is 3 new features, 12 improvements, 12 fixes, 2 security patches, and 1 performance improvement. New features include --safe-mode for launching with all customizations disabled, and many of the changes address bugs related to Windows behavior, background sessions, and enterprise management settings. No breaking changes or deprecations are included.

Notable Updates

• New Feature: A --safe-mode flag (and CLAUDE_CODE_SAFE_MODE) has been added to launch Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled (v2.1.169). This is useful for isolating issues during troubleshooting. Additionally, a /cd command to change the working directory and a disableBundledSkills setting to hide bundled skills have also been added.
  
• Bug Fix: An issue where claude -p was slow or appeared to hang on Windows due to waiting for slash command/skill scanning has been fixed (v2.1.169, regression introduced in v2.1.161).
• Security: An issue where untrusted project settings could configure OTEL client certificate paths without trust confirmation has been fixed (v2.1.169). Additionally, an issue where enterprise managed MCP policies (allowedMcpServers/deniedMcpServers) were not being applied through certain code paths has also been fixed.

Update Details

New Features

• A --safe-mode flag (and CLAUDE_CODE_SAFE_MODE environment variable) has been added to launch Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled. This is useful when you want to determine whether an issue is caused by settings or extensions.
• A /cd command has been added to change the session's working directory mid-session without breaking the prompt cache.
• A disableBundledSkills setting and CLAUDE_CODE_DISABLE_BUNDLED_SKILLS environment variable have been added to hide bundled skills, workflows, and built-in slash commands from the model.

Security

• An issue where untrusted project settings could configure OTEL client certificate paths without trust confirmation has been fixed.
• An issue where enterprise managed MCP policies (allowedMcpServers/deniedMcpServers) were not being applied during reconnection, IDE-entered settings, --mcp-config servers during the first session after installation, and before remote settings were loaded has been fixed. Additionally, cold start slowness for organizations without remote settings has also been improved.

Improvements

• /workflows now opens instantly even while a turn is in progress.
• The reliability of TaskCreate has been improved. Invalid inputs are now automatically repaired, and validation errors for unloaded tools now include the schema.
• The error message displayed when an organization has disabled API key authentication has been improved to show guidance based on the source of the API key being used.
• The default 5-minute idle timeout for Vertex/Foundry has been restored, so stalled streams will be interrupted instead of hanging indefinitely. You can opt out with API_FORCE_IDLE_TIMEOUT=0.
• Even if remote management settings contain invalid entries, the remaining valid policies are now applied and validation errors are displayed. The entire payload is no longer silently discarded as it was before.
• Background sessions now retain flags such as --ide, --chrome, --bare, and --remote-control across retire→wake cycles, and state validation on respawn has been strengthened.
• Background sessions are now informed that shared checkout edits are blocked until entering a worktree, avoiding unnecessary edit rejections before EnterWorktree.
• The threshold for the "CLAUDE.md is too long" warning now scales according to the model's context window.
• The Windows auto-updater now stops retrying within a session when claude.exe is being held by another process.
• The color contrast of skill tags in the slash command menu has been improved.
• Apple/Google billing subscribers without a registered payment method are now guided on where to add one when claiming promotional credits.
• A hint suggesting claude agents has been added when multiple sessions are running simultaneously.

Performance

• CPU usage during response streaming and spinner animation has been reduced.

Fixes

• Fixed arrow key history navigation behavior: Fixed an issue where the up/down arrow keys would skip over wrapped lines in long input and navigate to command history. Navigation now moves by visual line, with history recall entering from the nearest end.
• Fixed UI stalls on macOS: Fixed an approximately 30–50ms UI stall that occurred at the start of each turn for macOS users logged in with claude.ai credentials.
• Fixed claude -p hang on Windows: Fixed an issue where claude -p was slow or appeared to hang on Windows due to waiting for slash command/skill scanning (regression introduced in v2.1.161).
• Fixed Remote Control stuck in reconnecting state: Fixed an issue where Remote Control would get stuck in a "reconnecting" state when an OAuth token refresh occurred simultaneously during session resumption.
• Fixed re-display of stale permission prompts: Fixed an issue where stale prompts were re-displayed every time a remote session was reconnected to a worker that had stopped while waiting for a permission/dialog prompt.
• Fixed missing sessions in claude agents --json: Fixed an issue where background sessions dispatched while blocked and immediately after were missing. Additionally, an --all option to include completed sessions and new id and state fields have been added.
• Fixed background agents ignoring environment variables: Fixed an issue where background agents dispatched to pre-warmed workers would ignore env values (e.g., ANTHROPIC_MODEL) from project-level settings.
• Additionally, numerous minor bugs have been fixed, including Git Credential Manager popups on Windows, footer hints when using custom status lines, agents view display issues in WSL (Windows Terminal), MCPB plugin cache on Windows, and accumulation of .in_use lock files for plugins.

Closing Thoughts

v2.1.169 adds new features including --safe-mode for troubleshooting, along with fixes centered around enterprise management settings, security, and issues related to Windows and background sessions. Since there are no breaking changes or deprecations, this is an update with straightforward impact to assess. Those using claude -p on Windows or operating enterprise management policies will particularly benefit from this release. Why not update and give it a try?

Recent Updates

https://dev.classmethod.jp/articles/20260524-claude-code-updates-v2-1-150/

https://dev.classmethod.jp/articles/20260524-claude-code-updates-v2-1-152/

https://dev.classmethod.jp/articles/20260528-claude-code-updates-v2-1-153/

https://dev.classmethod.jp/articles/20260529-cc-updates-v2-1-158/

https://dev.classmethod.jp/articles/20260602-cc-updates-v2-1-160/

https://dev.classmethod.jp/articles/20260603-cc-updates-v2-1-161/

https://dev.classmethod.jp/articles/20260603-cc-updates-v2-1-165/

https://dev.classmethod.jp/articles/20260608-cc-updates-v2-1-168/

References

https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md

https://code.claude.com/docs/en/changelog