ClaudeUpdates.dev
Update Claude Code
ClaudeUpdates.dev
368 releases|Latest v2.1.236|Last Update Aug 19, 2026
Update Claude Code
v2.1.217Older
2.1.216
2.1.217
2.1.218
2.1.219
2.1.220
2.1.217
2.1.218
2.1.219
v2.1.219Newer
← Back to all releases

v2.1.218 Claude Code Release Notes

Jul 22, 2026
Claude's Analysisby Sonnet 5
Full Analysis

Major stability pass: 23 fixes for crashes, Windows path corruption, and session-resume failures, plus a breaking agent-name restriction and quieter /code-review defaults.

Changes
36
Total Changes (vs Average)
2.9×
Version Type
Patch
Release Focus
Bug Fixes
Day Since Prior Release
1
Release # This Month
#20 of 22
Bug Fix Ratio
64%
Post-Release Edits
−1
Change Category
Ecosystem Impact
Plugins/Skills has surfaced in 9 of the last 10 releases (5 of 5 most recent), showing sustained investment in extensibility as skill and plugin behavior keeps getting refined.
Key Themes
10Crash & Session Reliability|1Windows Path Corruption Fixed|3Accessibility Improvements|6Slash Command Behavior Overhaul|4MCP & Bedrock Provider Fixes
May Help If You've Noticed
Windows paths with special characters looked corrupted or became inaccessible
Claude crashed when a large nested folder it was watching was deleted or moved
Pressing left arrow wiped your conversation with no way to undo it
Resuming a saved session failed every turn or crashed on load
Screen reader feedback while typing or deleting text was wrong or missing

Changes in Claude Code v2.1.218

Added3 changes

  • •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-reader mode
  • •Added an announcement when fast mode changes as a result of switching models via /config model=<x> or Remote Control
  • •Added yes/no/on/off/1/0 (case-insensitive) as accepted values for skill and plugin frontmatter booleans, alongside true/false

Improved4 changes

  • •Improved /ultrareview error 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

Fixed23 changes

  • •Fixed Windows paths with \u-prefixed segments (like C:\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 j in place of newlines in terminals that encode pasted newlines as Ctrl+J
  • •Fixed /context reporting stale pre-compact token usage after compacting from the message picker
  • •Fixed /ultrareview failing 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 ultra silently 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_use block 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-reader mode
  • •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+B backgrounding 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
  • •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

Changed6 changes

  • •Changed /code-review to run as a background subagent, so review work no longer fills your conversation and keeps stacked slash commands as its review target
  • •Changed /deep-research to 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
  • •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: fork to run in the background by default; opt out per skill with background: false

← v2.1.217
All Releases
v2.1.219 →