← Claude Code changelog
Claude Code 2.1.233
This release significantly enhances integration with GitLab workflows through merge request support for worktrees and agent views. Linux users now have opt-in memory cgroup limits for Bash tool commands, a crucial safeguard against runaway processes. Notable fixes address cloud sessions incorrectly marked as lost, a fix for idle Linux sessions consuming 100% CPU, and a critical Windows regression causing repeated manual approvals for ordinary Bash commands. Further improvements include faster self-hosted runner session starts, better apps gateway error forwarding, and enhanced screen reader accessibility, contributing to overall stability and a smoother user experience.
Added
- Added GitLab merge request URL support to the `--worktree` flag and the `claude agents` view (where MRs display as `!N`)
- Added an opt-in `forward_user_identity` apps gateway setting on Anthropic upstreams that sends the signed-in user's identity as headers, so a proxy behind the gateway can attribute spend per user
- Added opt-in memory cgroup support for Bash tool commands on Linux (`CLAUDE_CODE_TOOL_MEMORY_LIMIT`) so a runaway build can't stall the session
- Added `CLAUDE_CODE_WEBFETCH_CACHE_TTL_MS` environment variable to configure the WebFetch session URL cache TTL (default unchanged: 15 minutes)
Improved
- Improved `claude self-hosted-runner` session start time: the session branch is now created without rewriting the working tree, and two server round trips no longer block the agent's launch
- Improved apps gateway error forwarding: 400/413 errors from Vertex, Foundry, and Claude Platform on AWS upstreams now carry the upstream's own message; fixes a bug with auto-compact on apps gateway
- Improved `claude plugin validate` to check a bare `.claude/skills` directory, reporting SKILL.md files whose frontmatter fails to parse
- Improved screen reader mode: the `/effort` selector renders as a numbered list with a typed-number prompt, and hint and dialog text is no longer clipped
- Improved print mode diagnostics: a `[claude-code:unrecognized_model]` line is written to stderr when a request goes out for a model ID Claude Code doesn't recognize; map it with `modelOverrides` to silence
Changed
- Changed the GitHub app setup tip to no longer appear in repositories whose origin remote is on gitlab.com or bitbucket.org; the enterprise marketplace tip now covers non-GitHub internal git hosts
- Todo/task-tracking tools (TaskCreate/Get/Update/List, TodoWrite) are no longer available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and newer models; set `CLAUDE_CODE_ENABLE_TODO_TOOLS=1` to bring them back
- Reverted the 2.1.232 Bash permission changes for Cygwin-style symlinks on Windows and for input redirections (`< file`); a narrower version will return in a later release
Fixed
- Fixed cloud sessions occasionally being marked as lost when the environment shut down while Claude was waiting on a permission prompt
- Fixed MCP v2 connections endlessly reopening the subscriptions/listen stream against servers that terminate long-held streams on a fixed timeout (e.g. serverless hosts)
- Fixed Notification hooks not firing for permission prompts when running under Claude Desktop or VS Code
- Fixed idle sessions on Linux sometimes keeping one CPU core at 100% when sandboxing is enabled
- Fixed bundled skill aliases like `/checkup` and `/review` reporting "Unknown command" in `-p` mode or with plugins/MCP loaded when a user or project skill shadows the bundled skill
- Fixed skill/command argument substitution to prevent argument values from being re-expanded as template markers
- Fixed Windows paths spelled with the NT `\??\` device prefix bypassing UNC path validation, closing an NTLM credential-leak vector
- Windows: fixed auto mode repeatedly stopping for manual approval on ordinary `cd <dir> && <command> > file` Bash commands (a 2.1.232 regression)