Claude Code 2.1.301
51changes- Render LaTeX math, including block and inline notation, in Claude's responses in VS Code.
- Add the % motion to vim mode to jump to the matching bracket, alone or with d/c/y.
- Let a mod's Input field hold several lines, submitting on Enter.
- Summarize an over-long conversation with the previous model before switching to one with a smaller context window.
- Ask before removing a WorktreeCreate hook's worktree that may hold unpushed commits.
New features
8Add % motion to vim mode
Added the % motion to vim mode: jump to the matching bracket, alone or with d/c/y
Add multi-line rows to mod Input
Added rows to a mod's Input: a text field of several lines in the terminal, where Enter submits and Shift+Enter or a backslash before Enter starts a new line
[VSCode] Render LaTeX math in responses
Added LaTeX math rendering in Claude's responses, including $$ and multi-line \[ … \] blocks and inline $…$ and \(…\) math
Add retry watchdog usage-limit wait cap
Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) ends a request at a usage limit that resets too far away instead of waiting
More changes (4) Fewer changes
Add OTel tracing guidance to claude-api skill
Added OpenTelemetry tracing guidance to the claude-api skill, including setting up trace destinations with the ant CLI
Add classifier verdict to tool_decision events
Added classifier_verdict and permission_mode to OpenTelemetry tool_decision events, so auto mode classifier decisions can be told apart from permission rules
Name matched rule in tool_decision events
Added classifier_category to OpenTelemetry tool_decision events, naming the built-in rule a classifier block matched, when OTEL_LOG_TOOL_DETAILS=1
[VSCode] Add Get more usage link
Added a "Get more usage" link to the usage-limit banner for Pro and Max plans in the VS Code and JetBrains panels
Improvements
6Expand mod question dialog tree capacity
Improved mods: in VS Code and the desktop and mobile apps, a tree drawn above the question dialog can now hold Markdown and up to 48 rows; the terminal keeps 12 plain rows
Summarize before switching to smaller context
Improved switching to a model with a smaller context window: a conversation too long for the new model is now summarized by the previous model first
Speed up subagent progress trail rendering
Improved rendering performance while a long-running subagent works: its progress trail now updates incrementally instead of being reprocessed in full on every render
More changes (3) Fewer changes
Paint artifact band above sticky headers
Improved artifacts: pages Claude writes now paint the band above a sticky header, so scrolled text no longer shows there in the mobile apps
Limit mod hook .catch to failures
Changed a mod hook's .catch handler to run only when the hook throws or times out; events raised beneath the hook's own calls now skip that hook without asking its .catch
Report env.set outcomes with deny reasons
Changed a mod's $.env.set to resolve with {} once the variable is set or unset, or with { deny } saying why when the write is not made
Bug fixes
37More changes (36) Fewer changes
Retry fable alias on unavailable model
Fixed the fable (and best) model alias erroring on the Anthropic API when the newest Fable model is not available to your organization: Claude Code now retries once on the previous Fable model
Name the disk in full-disk login errors
Fixed a misleading "Please run /login" error when a full disk keeps the login from being refreshed; the error now names the disk and says to delete files
Report search failures in Grep and Glob
Fixed Grep and Glob reporting no matches when the search program failed unexpectedly before returning any results; they now return an error saying the search failed
Fix workflow agents skipping their step
Fixed workflow agents sometimes skipping their step, and the run still reporting success, after reading the harness note that their task text carries no user authority
Fix artifact updates refused by hooks
Fixed artifact updates being refused where a PreToolUse hook covers Edit or Write; Claude now edits the file and then republishes instead of changing it in the publish call
Fix stalls from many skill argument names
Fixed skills and commands with very many or very long argument names stalling for seconds when invoked; only the first 64 names, each up to 64 characters, are now filled in
Fix high memory use from many arguments
Fixed skills, commands and hooks using very large amounts of memory when their arguments fill many placeholders
Fix stray characters on old VTE terminals
Fixed stray characters such as >0q covering the folder trust prompt, and >4m before the shell prompt at exit, in terminals built on VTE older than 0.53 such as MATE Terminal on RHEL 8
Fix stray GOK text in iTerm2
Fixed stray GOK text appearing in the prompt at startup in some versions of iTerm2
Fix inference-profile switch running AWS auth
Fixed switching to a model whose name contains application-inference-profile running your awsAuthRefresh command and delaying model-switch hooks when the provider is not Bedrock
Fix sign-out from interrupted token refresh
Fixed sign-in refresh timeouts and unexpected sign-outs after a short command such as claude auth status or claude plugin list exited in the middle of a token refresh
Fix tool calls misreported as rejected
Fixed a tool call cut off by a message sent mid-turn during its permission check being reported to the model as rejected by the user
Ask before spending credits on model switch
Fixed a case where switching to a model with a smaller context window could spend usage credits on a summary by the previous model without asking first
Fix repeated compaction behind LLM gateways
Fixed conversations being compacted over and over, on a model you didn't pick, behind an LLM gateway whose responses name a different model than the one requested
Fix vim INSERT stuck after Esc
Fixed vim mode sometimes staying in INSERT after Escape on a slow or busy machine
Fix Esc discarding vim-mode question answers
Fixed Esc discarding a typed AskUserQuestion answer in vim mode: the free-text field now supports vim NORMAL mode, and Esc cancels only from NORMAL
Fix Read misreading binary files as text
Fixed the Read tool reading binary files such as .xlsm, .parquet, .epub and .heic as text
Fix header-only tables drawing nothing
Fixed a Markdown table with only a header row drawing nothing when too wide for the terminal, including in plans on the plan approval card
Fix wrong CMEK availability in claude-api skill
Fixed the /claude-api skill saying CMEK external-key endpoints aren't available on Claude Platform on AWS
Fix skills missing after /rewind
Fixed skills no longer being listed to the model after using /rewind
Fix compaction row's stale ctrl+o hint
Fixed the compaction row in a resumed session offering ctrl+o for history that is not loaded; it now says where the earlier messages are saved, and also shows in fullscreen
Stop /clear hint reappearing after interrupts
Fixed the "new task? /clear to save tokens" hint coming back right after you interrupt a response
Name the plugin in ask prompts
Fixed the permission prompt for a plugin or skill hook's ask decision not showing which plugin or skill the hook comes from
Fix /diff missing conflicts in reftable repos
Fixed /diff not noticing a conflicted cherry-pick or revert in reftable repositories when one of its git checks timed out or failed
Fix workflow permission prompts after cd
Fixed workflow scripts asking for permission or being refused when read, edited or re-run after a Bash cd in the same session
Fix dim text on dark ANSI theme
Fixed dim text on the dark ANSI theme and 16-color terminals: faint inside filled boxes, not faint under selection and search highlights, and list descriptions dimmed like other secondary text
Fix model.fork failing before first response
Fixed a mod's $.model.fork returning nothing-to-fork when called before the first response of a new Claude Code process had finished, as in claude -p runs and cloud sessions
Fix UI freeze during /compact in fullscreen
Fullscreen mode: Fixed /compact and auto-compact briefly freezing the UI while the visible transcript is rebuilt
Fix Slack sessions blocked by MCP restrictions
Self-hosted runner: Fixed sessions started from Slack being unable to find or attach a repository when managed settings restrict MCP servers; use deniedMcpServers to keep those tools off
Fix false deleted-branch retries on failures
Self-hosted runner: Fixed sessions being reported as having a deleted source branch, and not retried, when an unrelated setup or session failure quoted git's missing-ref wording
Count repeated self-hosted release failures
Self-hosted runner: Fixed the log promising a retry of a failed or declined session release for a session that is ending; repeated failures now show a count
Fix missing killed line on Windows
Windows: Fixed stopped background PowerShell commands missing the closing [killed] line in their output file
[VSCode] Stop reopening crashed conversations
Fixed a conversation that crashes or freezes the panel being reopened on every reload
[VSCode] Speed up chat during long thinking
Fixed the chat panel slowing down during long thinking: it no longer re-parses the whole thinking text on every update
[VSCode] Fix object Object in diagnostics
Fixed diagnostics showing "[object Object]" instead of the rule code (e.g. MD013) for some language servers
[VSCode] Skip loading unneeded dictation audio
Fixed the native dictation audio module being loaded, to check microphone permission, where dictation is not offered (non-claude.ai sign-ins, remote windows)