Claude Code v2.1.116: Performance improvements, terminal fixes, and security updates

Performance and workflow improvements
The /resume command on large sessions is now significantly faster with up to 67% improvement on 40MB+ sessions. It also handles sessions with many dead-fork entries more efficiently.
MCP startup is faster when multiple stdio servers are configured, and resources/templates/list is now deferred to first @-mention.
Fullscreen scrolling in VS Code, Cursor, and Windsurf terminals is smoother — /terminal-setup now configures the editor's scroll sensitivity.
The thinking spinner now shows progress inline with messages like "still thinking", "thinking more", and "almost done thinking", replacing the separate hint row.
Command and configuration enhancements
/config search now matches option values, so searching for "vim" will find the Editor mode setting.
/doctor can now be opened while Claude is responding, without waiting for the current turn to finish.
/reload-plugins and background plugin auto-update now auto-install missing plugin dependencies from marketplaces you've already added.
The slash command menu now shows "No commands match" when your filter has zero results, instead of disappearing.
Security and reliability fixes
Sandbox auto-allow no longer bypasses the dangerous-path safety check for rm or rmdir targeting /, $HOME, or other critical system directories.
The Bash tool now surfaces a hint when gh commands hit GitHub's API rate limit, so agents can back off instead of retrying.
The Usage tab in Settings now shows your 5-hour and weekly usage immediately and no longer fails when the usage endpoint is rate-limited.
Terminal and UI fixes
Fixed Devanagari and other Indic scripts rendering with broken column alignment in the terminal UI.
Fixed Ctrl+- not triggering undo in terminals using the Kitty keyboard protocol (iTerm2, Ghostty, kitty, WezTerm, Windows Terminal).
Fixed Cmd+Left/Right not jumping to line start/end in terminals that use the Kitty keyboard protocol (Warp fullscreen, kitty, Ghostty, WezTerm).
Fixed Ctrl+Z hanging the terminal when Claude Code is launched via a wrapper process (e.g. npx, bun run).
Fixed scrollback duplication in inline mode where resizing the terminal or large output bursts would repeat earlier conversation history.
Fixed modal search dialogs overflowing the screen at short terminal heights, hiding the search box and keyboard hints.
Fixed scattered blank cells and disappearing composer chrome in the VS Code integrated terminal during scrolling.
Bug fixes and stability improvements
Fixed an intermittent API 400 error related to cache control TTL ordering that could occur when a parallel request completed during request setup.
Fixed /branch rejecting conversations with transcripts larger than 50MB.
Fixed /resume silently showing an empty conversation on large session files instead of reporting the load error.
Fixed /plugin Installed tab showing the same item twice when it appears under Needs attention or Favorites.
Fixed /update and /tui not working after entering a worktree mid-session.
Agent frontmatter hooks now fire when running as a main-thread agent via --agent.
📖 Read the full source: GitHub Claude-Code
👀 See Also

GitHub Copilot Moves to Usage-Based Billing by Token Consumption, Replacing Premium Requests on June 1, 2026
GitHub Copilot transitions from premium request units to token-based GitHub AI Credits, with plan prices unchanged. All paid plans include monthly credits equal to subscription cost; additional usage billed at API rates.

Open Source vs Frontier Models: Single-File Canvas Car Scene Benchmark
A developer tested 12 models including GPT-5.5, Claude Opus 4.7, and Qwen 3.6 Plus on a single-file HTML canvas car driving animation task, with results publicly compared.

Claude-Code v2.1.97 Release: NO_FLICKER Improvements, Permission Fixes, and MCP Updates
Claude-Code v2.1.97 adds a focus view toggle (Ctrl+O) in NO_FLICKER mode, fixes multiple permission and MCP connection issues, and improves sandbox network access. The release addresses 429 retry behavior, transcript persistence problems, and various UI bugs.

Europe Has Two-Year Window to Avoid AI Infrastructure Dependence on US, Mistral CEO Warns
Mistral CEO Arthur Mensch warns Europe has 2 years to build its own AI infrastructure—chips, energy, compute—or risk becoming a permanent 'vassal state' to US tech giants.