Claude Code 2.1.218
This release refactors /code-review to run as a background subagent, fixes multiple critical bugs affecting file accessibility on Windows, terminal paste behavior, and accessibility features, and improves auto mode intelligence and trust dialog clarity.
- Changed
/code-reviewto run as a background subagent, so review work no longer fills your conversation and keeps stacked slash commands as its review target - Added screen-reader announcements of deleted text for word and line deletions (
Option+Delete,Ctrl+W,Cmd+Backspace,Ctrl+U,Ctrl+K) in--ax-screen-readermode - Fixed Windows paths with
\u-prefixed segments (likeC:\Users\unicorn) being corrupted into CJK characters in tool inputs, which made those files inaccessible - Fixed the left arrow key discarding the conversation with no undo: presses right after editing now ask to confirm, and Esc in the agent view returns to the conversation it backgrounded
- Fixed multi-line paste collapsing into one line with
jin place of newlines in terminals that encode pasted newlines as Ctrl+J - Fixed
/contextreporting stale pre-compact token usage after compacting from the message picker - Fixed
/ultrareviewfailing on descriptive arguments like "review my auth changes" — they now run a review of your current branch with the text applied as a note to the findings - Fixed
/code-review ultrasilently running a local review in non-interactive sessions — it now launches the cloud review - Fixed gateway spend metering to price Bedrock application-inference-profile ARNs and other config-mapped upstream model IDs at the configured model's rates
- Fixed mojibake when a long IDE selection was truncated mid-emoji, and a case where a tool executor error could be silently dropped
- Fixed an engine teardown race that could start and abandon a phantom turn, and made input pushed after close consistently rejected
- Fixed spurious "[Request interrupted by user]" messages after interrupted tool calls, and an unpaired
tool_useblock left in the transcript when a tool aborted mid-response - Fixed VoiceOver reading "new line" instead of echoing the typed space at the end of the input in
--ax-screen-readermode - Fixed plugin and settings panels not moving the terminal cursor to the focused row, so screen readers and magnifiers can follow arrow-key navigation
- Fixed crashes (maximum call stack exceeded) when a deeply nested watched directory tree was deleted or moved, and when rendering deeply nested UI trees
- Fixed pull request events occasionally being lost when a session exited immediately after creating or linking a PR
- Fixed the Bedrock setup wizard failing profile verification for assume-role profiles in partitioned AWS regions and on proxy-only networks
- Fixed rare negative or incorrect turn duration measurements after a system clock adjustment by timing turns with a monotonic clock
- Fixed the "N MCP servers need authentication" startup notice over-counting claude.ai connectors that aren't connected in claude.ai
- Fixed prompt history entries being dropped or duplicated when history writes raced or failed
- Fixed a retry loop that re-sent identical doomed requests after a context-overflow error with a large thinking budget;
Ctrl+Bbackgrounding now applies the same background-shell caps as other paths - Fixed agent frontmatter hooks running from untrusted folders: hooks now require the agent file's own folder to have accepted workspace trust
- Fixed fork-session lineage being lost after compaction in headless and SDK sessions
- Fixed a resumed session failing every turn, or crashing on resume, when its history held a malformed delta attachment
- Improved
/ultrareviewerror feedback so Claude can correct an invalid argument instead of retrying it unchanged - Improved auto mode: the dangerous-rm, background-
&, and suspicious-Windows-path checks no longer open permission dialogs; the auto-mode classifier adjudicates them instead - Improved sandbox command restrictions for IDE interactions
- Improved trust dialogs to name the repository root the grant covers
- Changed
/deep-researchto start only when invoked manually; Claude no longer launches it on its own - Changed plan mode with auto to no longer prompt for Bash commands the static analyzer can't prove read-only; the auto-mode classifier judges them instead
- Added an announcement when fast mode changes as a result of switching models via
/config model=<x>or Remote Control - Changed server-managed settings so benign feature and cost toggles no longer trigger the settings-approval prompt
- Changed agent markdown files to reject agent names containing
:, which is reserved for plugin namespacing - Changed skills with
context: forkto run in the background by default; opt out per skill withbackground: false - Added
yes/no/on/off/1/0(case-insensitive) as accepted values for skill and plugin frontmatter booleans, alongsidetrue/false - Fixed remote sessions continuing to send heartbeats after their worker was replaced, which left long-lived desktop and IDE processes retrying a rejected request every few seconds forever
Source: original entry ↗
More from Claude Code
Follow Claude Code to get its new changes in your feed and email digest.
Claude Code 2.1.296
This release adds new configuration options for managed policies, subagent behavior, workflow models, and retry handling. It includes improvements to the Claude apps gateway, Desktop Code tab settings, file reading capabilities, and session management across cloud and self-hosted environments. Pricing for Sonnet 5.5 cache reads has been updated to $0.10 per million tokens, and various UI and behavior refinements have been made to Claude Tag, VSCode, Chrome, and Slack integrations.
Claude Code 2.1.295 Release
This release adds onFailure blocking for hooks, Program Status Protocol support for terminal status display, upstream timeout configuration, improved tool descriptions, and numerous UX enhancements including file handling in chat, better error messages, and protocol improvements across VSCode, Claude Tag, and MCP integrations.
Claude Code 2.1.287
Claude Code 2.1.287 introduces Claude Mods for deeper plugin behavior customization, adds the "You should know" built-in mod for monitoring, and brings URL prompts from MCP servers, improved filtering in the agents view, and numerous UX enhancements. The update also includes support for 1M context windows, background shell execution in VSCode, and security improvements for file operations.