Claude Code 2.1.281
176changes- Add a Fast mode switch to the cloud session model menu.
- Speed up interactive startup by skipping git and telemetry work before the first frame.
- Extend auto mode's server-side safety review to read-only and sandboxed shell commands.
- Fix a recursive rm with a command-substitution-only target running unprompted in auto and skip-permissions mode.
- Fix session restriction settings not being forwarded to spawned teammates, /bg, and worktree sessions.
New features
13[Claude Code on the web] Add Fast mode switch
Added a Fast mode switch to the composer's model menu in cloud sessions, shown when your plan includes fast mode and the selected model supports it
Support newer Desktop policy keys
Added Claude apps gateway support for newer Claude Desktop keys in desktop policy blocks, including blockReadsOutsideWorkingDirectories and disableBypassPermissionsMode
Hide commit and PR attribution
Added "attribution": false in settings.json to hide all commit and PR attribution; older CLI versions skip a settings file that holds it, so keep the object form in files shared across versions
Add auto mode recommendation to /insights
Added an auto mode recommendation to /insights that estimates how many permission prompts auto mode could have handled in your recent sessions
More changes (9) Fewer changes
Add assume_role for Bedrock upstreams
Added assume_role on Claude apps gateway Bedrock upstreams: the gateway calls Bedrock as an IAM role it assumes through STS, in another AWS account if needed, optionally one session per developer
Add Bedrock guardrail config
Added guardrail: {id, version} on Claude apps gateway Bedrock upstreams to apply an Amazon Bedrock guardrail to every request sent through them (set it on all Bedrock upstreams or none)
Add telemetry resource attributes config
Added telemetry.resource_attributes to the Claude apps gateway config, to put fixed labels on the telemetry of Claude Desktop and /login sessions
Add MCP URL-mode elicitation
Added MCP URL-mode elicitation on 2026-07-28 protocol connections, so servers can ask Claude Code to open a browser-based flow; no waiting dialog is left on screen when the server has no way to confirm completion
Add MCP checks to plugin validate
Added MCP server checks to claude plugin validate: it reports .mcp.json entries that would be silently dropped at load, undeclared ${user_config.*} references, and insecure URLs
Add scrollbars to installed lists
Added a scrollbar to the /skills, /mcp and /plugin Installed lists in fullscreen mode, like the one /workflows now has: it appears while the mouse is over the list and can be clicked or dragged
[VSCode] Add Continue/Stop for billed fallback
Added a Continue/Stop prompt in the VS Code and JetBrains panels when auto mode falls back to billed classifier requests, replacing the unanswerable warning line
[Claude Code on the web] Add GitHub connection shortcuts
Added a settings shortcut on the GitHub setup tip and a "Troubleshoot GitHub connection" link in the repository pickers, both opening your GitHub connection page
[Claude Tag] Announce who pressed Stop
Added a short line in the Slack thread after someone presses Stop, naming who stopped Claude's response and saying to mention @Claude to continue
Improvements
50Speed up interactive startup
Improved interactive startup time: git reads, startup telemetry and the Bedrock/Vertex model-upgrade checks no longer run before the first frame
Speed up resuming file-heavy sessions
Improved the time to resume long sessions that read many files; the restored file cache now matches the files as they were read
Review read-only commands in auto mode
Changed auto mode so that, where its classifier review runs server-side, read-only and sandboxed shell commands also wait for that review and are blocked when it flags them
Time out dangerous rm prompts after 2 minutes
Changed the dangerous rm prompt in --dangerously-skip-permissions and auto mode to wait 2 minutes for an answer, then deny the command with a rewrite hint so unattended sessions keep going (CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT=1 turns this off)
More changes (46) Fewer changes
Point Desktop errors at the app
Improved Claude Desktop sign-in and usage-limit error messages to point at the app instead of terminal commands
Stop retrying unrecoverable startup fetches
Improved startup: managed settings and policy fetches no longer retry requests that can never succeed
Speed up resuming compacted long sessions
Improved the time to resume very long sessions that have been compacted, most noticeably through the Agent SDK and Claude Desktop
Summarize oversized first prompts on recovery
Improved "Prompt is too long" recovery in sessions dominated by one very large first prompt: that prompt is now summarized on its own instead of being left out of the summary
Reuse auto mode cache after resume
Improved auto mode after resuming a session in a new process: the permission classifier can now reuse its earlier prompt cache instead of rewriting it
Broaden auto mode denial coverage
Improved the auto mode denial message so Claude treats a denial as covering the outcome, not only the exact command
Flag more dangerous rm patterns
Improved the dangerous-rm check to also flag a removal at a shell variable followed by a top-level directory name, at a variable derived from the working directory, or at a backslash-only target
Point to allowLocalBinding on bind failures
Improved sandbox guidance on macOS: when a local dev server can't bind a port, Claude now points to sandbox.network.allowLocalBinding
▤ In the docsAccept JSON files and empty prompt in --agents
Improved --agents to accept the path to a JSON file (with -p) as well as inline JSON, and to allow an empty prompt
Run /batch outside git repositories
Improved /batch to run where a WorktreeCreate hook provides the agent worktrees, not only inside a git repository
▤ In the docsName plugins in hook errors, warn on unquoted paths
Improved plugin hook-failure errors to name the offending plugin, and added a claude plugin validate warning when a shell-form hook leaves ${CLAUDE_PLUGIN_ROOT} unquoted (it breaks on plugin paths with spaces)
Show synced skills by their short name
Improved the / menu, /skills, /context and the /plugin Installed list to show skills synced from claude.ai by their short name when no other command uses it, not anthropic-skills:<name>
▤ In the docsImprove /deep-research reliability on long briefs
Improved /deep-research reliability on long research briefs by removing unused required fields from the scope step's output
Improve artifact page prose style
Improved the writing in published artifact pages: the bundled artifact-design skill now asks Claude for plain, direct prose
Compress large artifact uploads
Improved artifact publishing on slow connections: large page uploads are now sent compressed
Count combined instruction files in size notice
Improved the large CLAUDE.md startup notice to also count instruction files together, so many mid-sized files and @-imports are caught
Name ignored env vars in debug logs
Improved debug logs to name settings env variables ignored because the session's launch environment already sets them
Improve tabbed dialog keyboard navigation
Improved keyboard navigation in tabbed dialogs such as /permissions and /usage: ↑/↓ move focus between the tab row and the content, and a list responds to keys only while it has focus
Improve tab switching in /help and /sandbox
Improved /help and /sandbox: ←/→ and Tab switch tabs from inside a tab's list, and ↓ on an empty Custom commands tab in /help no longer leaves the keys stuck until Esc
Standardize more prompt dialogs
Improved /install-github-app, /desktop, the /permissions auto mode environment prompts, and the /plugin "Add marketplace?" and "Run this command?" prompts: they now use the standard dialog frame with key hints, and Ctrl+C or Ctrl+D cancels them on the second press like other dialogs
Standardize /workflows and /mcp list controls
Improved the /workflows and /mcp lists: they page (PgUp/PgDn, Home/End) and take j/k and the mouse like other lists, their arrows follow select:previous/select:next rebinds, and x in /workflows stops the run the pointer is on
Add Home/End and clicks to more menus
Improved the /plugin plugin and marketplace details menus and the /remote-control already-connected menu: they now support Home/End and clicking a row
Show more detail in background workflow row
Improved the background workflow row below the prompt: it now shows the name, a progress bar, the agent count on wide terminals, elapsed time, total tokens, and the large-workflow warning
Align /plugin Installed list columns
Improved the /plugin Installed list: rows now line up in columns (status, name, type, details) across every section
Simplify /skills row layout
Improved /skills: each row now leads with the skill's name, with a check mark or hollow circle alone showing on or off, and stays on one line in narrow terminals
Improve narrow-terminal list row layout
Improved narrow list rows (/skills, /workflows, /feedback): a name keeps 20 columns beside its first detail, and details are shown whole or not at all
Add scrollbar and fix wrapping in /diff
Improved /diff: a scrollbar shows where you are in a long list of changed files, and long paths no longer wrap their rows
Clarify /hooks detail and status notices
Improved /hooks: a hook's detail screen now says what kind of hook it is and where to change it, instead of always pointing at settings.json, and the hooks-disabled, safe mode and managed-hooks-only notices each say what is happening in one plain sentence
Fix screen-reader wording for disabled servers
Improved screen-reader output in /mcp: a disabled server is read as "off" instead of "pending"
Debounce Remote Control confirm on refocus
Improved the Remote Control confirmation: its options are briefly inactive again after the terminal window regains focus, so a key pressed while switching back cannot answer it
Move tools to background on send now
Changed send now (ctrl+enter or ctrl+x ctrl+s) to move running tools to the background instead of cancelling the turn
Extend CLAUDE_CODE_AUTO_MODE_SERVER to direct API
Changed CLAUDE_CODE_AUTO_MODE_SERVER to also apply on a direct Anthropic API connection: 0 opts out of the server-side auto mode classifier (the local classifier then counts toward usage), 1 opts in
Refuse unsafe envHelper paths at gateway start
Changed Claude apps gateway to refuse to start when a managedMcpServers entry's envHelper path starts with \??\ or /??/, a path form current Claude Desktop refuses to run
Pass system prompts as files on runners
Changed self-hosted runners to pass system prompts to Claude Code as private files instead of command-line text, so large prompts no longer fail the launch; a wrapper or command hook that appends --system-prompt or --append-system-prompt must switch to --system-prompt-file or --append-system-prompt-file
Show queued messages above the spinner
Changed queued messages to show in the conversation above the spinner instead of under it
Combine artifact links into one footer pill
Changed the session artifact links under the prompt into one footer pill (showing a name or a count) that opens /artifacts, which now lists this session's artifacts first
Allow unpkg.com scripts in artifacts
Changed the Artifact tool to let Claude load scripts from unpkg.com in artifact pages
Tint hovered rows instead of a second pointer
Changed hovering a list row in fullscreen mode, including in /config, to tint the row instead of drawing a second pointer beside the focused row's
Simplify /mcp server row layout
Changed /mcp: each server's row now starts with its status icon and name, says its state once, and in a narrow terminal drops trailing facts like "managed" before shortening the name
Reorder /workflows row priorities
Changed /workflows: each run's row leads with its status icon and elapsed time, and a narrow terminal keeps the run's name and time, dropping the agent and token counts first
Reuse connections for attachment downloads
Changed Remote Control attachment downloads to reuse connections and to skip files already downloaded in the session
Hide MCP Apps UI resources from lists
Changed MCP resource lists (the resource list tool and @-mention suggestions) to skip MCP Apps UI resources; reading one by URI still works
Explain when uninstalled plugin data is kept
Changed claude plugin uninstall --json and the /plugin dialog to say a plugin's data was kept when its folder stays because another installed plugin uses it or install records cannot be read
Confirm before stopping /ultrareview
Changed the background tasks list (/tasks): pressing x on a running /ultrareview now asks for confirmation before stopping the review
[Claude Code on the web] Clarify file-open failure reasons
Improved the file card shown when a cloud session can't open a file: it now says whether the file no longer exists or the session's permission settings block reading it
[Claude Tag] Default routine list to thread's own tasks
Changed the routine list Claude gives when asked in a Slack thread to show that thread's own scheduled tasks by default instead of every routine in the channel
Bug fixes
112Prompt for command-substitution rm targets
Fixed a recursive rm whose target is only command-substitution output, such as rm -rf "$(pwd)", running unprompted in auto and --dangerously-skip-permissions mode; it now asks even with a Bash allow rule, unless run with CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT=1
Block reads via macOS special paths before approval
Fixed permission dialogs and attachment checks reading a path under macOS's /.vol, /.nofollow or /.resolve (which can reach a network mount) before approval
Fix NUL byte rules matching everything
Fixed a permission rule containing a NUL byte being expanded into a wildcard match; such a rule now matches nothing
Require workspace trust before --bg hooks
Fixed claude --bg starting a background session, and running its project hooks, in a directory that had not passed the workspace trust prompt; it now asks for trust first, or exits when not run interactively
Forward setting-sources to spawned sessions
Fixed --setting-sources (and SDK settingSources) not being forwarded to spawned sessions: teammates, /bg, claude agents sessions and --worktree --tmux now start with the parent's restriction
Honor Skip in /install-github-app workflow step
Fixed /install-github-app updating the workflow after "Skip workflow update" was chosen, running setup twice on a repeated Enter, and ↑ on the repository step blocking a typed repository name when no repository was detected
More changes (106) Fewer changes
Fix crash during API request retry
Fixed a crash ("unrecoverable interface error") that could end a session while an API request was being retried
Fix infinite retry ignoring --max-turns
Fixed a turn that could retry indefinitely, ignoring --max-turns, when the model alternated unparseable tool calls and output-limit truncation
Fix resumed turns re-sent in changed form
Fixed resumed sessions re-sending earlier turns in a changed form (a parallel tool-call turn, an MCP tool call's input or a tool-search result while its server was still reconnecting, or a tool-search result whose loading turn was interrupted), which could make the API drop the conversation's prior reasoning
Fix large sessions resuming partially
Fixed resuming a very large session sometimes restoring only its last few messages
Fix cache break resuming mid-prompt sessions
Fixed a session resumed after a restart during a pending permission prompt sending a different history than before, which broke the prompt cache from that point
Fix resume after mid-tool-call end
Fixed resuming a session that ended during a tool call: Claude now sees the call and is told its outcome is unknown, and a manual resume no longer adds a hidden "Continue" message
Fix repeated failures from unreadable advisor results
Fixed sessions with an earlier advisor result the API could no longer read failing one request every turn and repeatedly losing earlier reasoning; the history is now repaired once
Fix cache loss on MCP disconnects
Fixed the prompt cache being lost when an MCP server disconnects mid-conversation, or is still connecting after a resume, while tool search is off (for example behind a proxy or gateway)
Fix truncated responses shown as complete
Fixed responses cut short by a proxy or gateway that closes the stream cleanly being shown as complete with no warning, and tool calls running twice on duplicated stream events
Keep partial responses on dropped stream events
Fixed responses failing with "Content block not found" when a proxy drops a stream event mid-response; the partial response is now kept, and web search keeps results that already arrived
Fix duplicate requests on dropped connections
Fixed an empty completed response being requested twice when the connection dropped before the stream's final event
Fix stop reason lost on usage-only frames
Fixed the stop reason being lost when a proxy sends a trailing usage-only frame
Fix retry watchdog failures after rate limits
Fixed CLAUDE_CODE_RETRY_WATCHDOG sessions failing on the first 5xx or dropped connection after a run of 429/529 waits, and sleeping uncapped and silently on a long Retry-After from a 5xx
Fix fast mode retry storm on Retry-After: 0
Fixed fast mode retrying rate-limited requests back to back when the server sent Retry-After: 0
Fix stuck turns from oversized tool images
Fixed a tool that returned an oversized image leaving sibling tool calls unanswered and still running, or ending the turn with no final message
Fix conversations stuck on overlong tool names
Fixed conversations getting permanently stuck on "tool_use.name: String should have at most 200 characters" after the model called a tool by an overlong name
Fix false tool failures on memory-usage errors
Fixed tool calls failing with "Failed to get memory usage", or being reported as failed after they ran, when Claude Code cannot read its own memory usage, for example when it has run out of file descriptors
Fix stream-json failures on plain-string content
Fixed --input-format stream-json sessions (Agent SDK, VS Code extension) and scheduled cloud sessions failing every turn with an error when an earlier assistant message had plain-string content
Fix failures after start directory deletion
Fixed non-interactive sessions (-p, Agent SDK) failing on the next turn after the directory they were started in was deleted mid-session
Fix stalls on unresponsive host-side MCP
Fixed headless sessions with host-side (SDK) MCP servers stalling on the first message when the host stops responding mid-handshake; remote sessions now wait a few seconds at most
Fix startup wait on managed-settings request
Fixed interactive startup waiting on the managed-settings network request (about 80 ms, 17+ seconds when the network is unreachable) when no MCP servers or plugins are configured
Fix delay reading large PDFs
Fixed a delay of up to two minutes before responding when reading or @-mentioning a PDF larger than 3 MB
Fix stuck render after interrupted PDF read
Fixed an interrupted Read of specific PDF pages leaving its page render running for up to two minutes
Fix excludedCommands matching gaps
Fixed sandbox excludedCommands entries not matching git rev-parse --git-dir, programs named like shell builtins, and commit messages containing [WIP] or # lines
Fix sandboxed writes to $TMPDIR
Fixed sandboxed Bash commands being unable to write to $TMPDIR when CLAUDE_CODE_TMPDIR is set
Fail cleanly on null-byte file paths
Fixed Read, Write, Edit and NotebookEdit: a file path containing a null byte now fails that tool call with a clear error instead of ending the whole turn
Allow duplicate-parameter Write calls
Fixed Write refusing a call that gives the file path or content twice under two parameter names with identical values
Fix duplicate CLAUDE.md in headless sessions
Fixed CLAUDE.md and rules files from an --add-dir directory inside the working directory being sent to the model twice in headless and SDK sessions
Fix stale approval state after overlapping prompts
Fixed remote sessions staying on "needs approval" with a stale prompt after a permission prompt and a sandbox network-access prompt overlapped and both were answered
Report agents finished before worker restart
Fixed cloud sessions not telling Claude about background agents that finished just before a worker restart
Fix delayed turn-start notices in remote sessions
Fixed scheduled routine and notification turns in remote sessions not receiving turn-start notices (newly available tools, MCP changes, date, todos) until after the first tool call
Fix repeated wakeups from failed delivery
Fixed scheduled tasks and /loop wakeups being fired again every second when their delivery failed, which could make Claude Code exit at the end of a turn
Fix false org-policy-disabled message
Fixed Remote Control reporting "disabled by your organization's policy" when the org policy simply hadn't loaded yet; it now retries the fetch and says it couldn't verify
Restore Artifact tool in Remote Control sessions
Fixed the Artifact tool missing from Remote Control sessions that claude remote-control starts for you to open from Claude Desktop, claude.ai or the mobile app
Fix OAuth tokens lost on locked keychain
Fixed macOS credential writes dropping stored MCP OAuth tokens or deleting the keychain entry when the login keychain was locked (e.g. right after wake)
Clean up stray auth-refresh processes
Fixed gcpAuthRefresh/awsAuthRefresh login processes being left running (and holding their localhost callback port on Windows) when Claude Code exits or the refresh times out
Fix stale logged-out state after other-process login
Fixed the "Not logged in · Run /login" footer and missing claude.ai connectors persisting in a session after logging in from another Claude Code process
Wait for MCP connect before skipping hooks
Fixed mcp_tool hooks on blocking events (PreToolUse and similar) being skipped while their MCP server was still connecting; they now wait for it, up to the MCP connect timeout
Fix duplicate MCP connections from URL spelling
Fixed the same MCP server being connected twice when a plugin or claude.ai connector and a configured server spell its URL differently (host letter case, default port, trailing slash)
Fix connector timeout ignoring MCP_CONNECT_TIMEOUT_MS
Fixed MCP_CONNECTION_NONBLOCKING=0 giving up on claude.ai connectors after 1s instead of honoring MCP_CONNECT_TIMEOUT_MS
Check plugin name against --channels entries
Fixed --channels plugin entries being checked against the installed plugin's marketplace alone; the installed plugin's name must now match the entry as well
Fix --plugin-dir loading empty plugin
Fixed --plugin-dir on a folder of plugins that also has a .claude-plugin/marketplace.json loading one empty plugin instead of the plugins in it
Fix uninstall refusing disabled project plugins
Fixed claude plugin uninstall refusing to remove a project-scope plugin that isn't enabled, saying it is "enabled at project scope" while claude plugin disable says it is already disabled
Fix plugin update scope resolution
Fixed claude plugin update failing for project-scoped plugins when --scope is omitted: it now resolves the scope the plugin is installed at instead of assuming user
Fix validate flagging listing metadata fields
Fixed claude plugin validate reporting privacyPolicyUrl, supportUrl and other listing metadata keys in plugin.json as unknown fields
Fix false refresh record on unreachable marketplace
Fixed known_marketplaces.json recording a marketplace as refreshed when its remote could not be reached and CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE kept the existing clone
Show confirmation after last error resolved
Fixed the /plugin Errors tab showing no confirmation after its last error is resolved
Fix duplicate uninstall/update from repeat Enter
Fixed /plugin starting a second uninstall or update of the same plugin when Enter was pressed again while the first was still running
Fix held y pre-answering marketplace prompt
Fixed a y held while /plugin checks a marketplace source adding the marketplace the instant the "Add marketplace?" question appears, before it can be read
Fix 1 key confirming Yes regardless of pointer
Fixed 1 answering Yes in /permissions' delete and remove-directory confirms while the pointer is on No, which let a held 1 remove one workspace directory after another
Hide thinking toggle on always-thinking models
Fixed Alt+T and /config offering to turn thinking off on models that can't; thinking now stays on there, with a one-line reason in place of the switch
Fix /context total omitting recent messages
Fixed /context total leaving out messages added since the last response; it now matches its categories and can read higher than the status line
Show plain errors for refused model picks
Fixed /model showing the raw API error JSON and request ID when the API refuses the picked model; it now shows the server's message and says the model was not changed
Fix raw HTML and split-line API error output
Fixed API errors from an HTML error page (such as a proxy's 429 or 502 page) printing the page's raw markup or leaving out the HTTP status, and error messages breaking onto a second line when the server's error text ended in a newline
Honor cancel during report sending
Fixed /feedback, /bug and /share still sending your report after you cancelled it while it was being sent
Fix feedback send failures after Remote Control Stop
Fixed /feedback, /bug and /share failing every send with "Couldn't send feedback" after a Remote Control Stop arrived while the dialog was open
Fix contradictory /ide no-IDE message
Fixed /ide showing "No available IDEs detected" while also listing a running IDE
Fix broken terminal after setup restarts
Fixed the terminal being left in a broken state (crash or garbled input) when /setup-bedrock or /setup-vertex restarts Claude Code to apply new settings
Fix /config exit on null legacy values
Fixed /config exiting when respectGitignore or copyFullResponse in ~/.claude.json holds null
Keep session name during multiple-choice questions
Fixed the session name from /rename disappearing while Claude asks a multiple-choice question, so side-by-side sessions stay identifiable
Fix one-line pastes shown on own line
Fixed one-line pastes showing on their own lines in the sent message for prompts from VS Code or Remote Control and for expanded paste placeholders
Preserve IDE selection on queued messages
Fixed a message queued while Claude is working losing or changing the IDE selection it was written with, and queued messages not showing their selection
Fix rapid Shift+Tab landing on wrong mode
Fixed pressing Shift+Tab twice quickly landing on the wrong permission mode
Fix double Ctrl+C quitting more dialogs
Fixed Ctrl+C or Ctrl+D pressed twice quitting Claude Code instead of closing the dialog in the remaining dialogs and pickers, such as /memory, /hooks, /mcp (including a server's sign-in screen), /export, /copy, /theme, and /teleport's uncommitted-changes and login prompts (where Esc also quit)
Fix burst input acting on stale selection
Fixed keys that arrive in one burst of input (e.g. over Remote Control), such as an arrow key followed by Enter, x or s, acting on the previous selection: a stale effort level in /effort and the model picker, and the previously highlighted row in /skills, the background task rows under the prompt, MCP server prompts and /install-github-app
Fix several vim mode motion bugs
Fixed vim mode: dj/dk/dG/dgg and their c/y forms acting on part of a line; 1G going to the last line; d0/c0/y0 doing nothing; the cursor being off by one after . repeats an insert; and o/p on a !-prefixed line switching to shell mode
Fix more vim mode word-motion bugs
Fixed vim mode cw on a space, an empty line, a word's last letter or a one-letter word also changing the next word; word motions stopping inside words in Hindi, Bengali and other scripts; and ., p or P that inserts text starting with ! switching to shell mode, losing text or editing the wrong character
Fix cursor overshoot after accent keys
Fixed the prompt cursor moving one character too far after an accent typed as its own key
Fix extra blank line above wrapped list items
Fixed an extra blank line above a list item whose text starts on the line after its bullet, in screen-reader mode, quoted lists and long lists
Fix plain-number list items shown wrong
Fixed bulleted lists of plain numbers (like - 316.) showing as letters, roman numerals or the wrong numbers
Fix agent panel footer hint rebind and stray dot
Fixed the agent panel's footer hint ignoring keys rebound in keybindings.json, and showing a stray · when the stop-all-agents shortcut is unbound
Fix redundant agent panel footer hints
Fixed the agent panel footer offering "Enter to view" and "x to stop" on the agent you are already viewing (where x types into its input), and "Enter to view" on the main row when main is already shown
Fix keyboard cursor after mouse click on rows
Fixed a mouse click on an agent-panel row leaving the keyboard cursor on the previously selected row
Fix Esc interrupting turn instead of deselecting
Fixed Esc interrupting the running turn instead of deselecting the selected agent-panel row
Fix PgUp/PgDn doing nothing in dialog lists
Fixed PgUp and PgDn doing nothing in a dialog's list (for example /skills) in fullscreen mode
Fix /heapdump summary misattributing memory
Fixed /heapdump summary saying most memory is native when it is in the JS heap snapshot
Clean up Bash edit-diff snapshot directories
Fixed Bash edit-diff snapshot directories piling up in the temp folder: abandoned ones are now deleted right away and the rest when Claude Code exits
Fix /workflows pointer jumping to new runs
Fixed /workflows moving the pointer to a different run, and x stopping it, when a new run started while the list was open
Fix invisible tab selection with NO_COLOR
Fixed the selected tab in tabbed dialogs (/config, /plugin, /permissions) showing no highlight while the tab bar has focus when color is off (NO_COLOR)
Fix mouse wheel scrolling pane behind list
Fixed the mouse wheel over the /plugin Installed list scrolling the pane behind it instead of the list
Fix stale hover highlight after scroll/filter
Fixed the hover highlight lingering on a list row in fullscreen mode after scrolling or filtering moved it away from the mouse
Truncate long list rows in narrow terminals
Fixed long list rows, such as in the /remote-control menu, wrapping onto a second line in narrow terminals; they're now cut with …
Fix detail view text overlapping in narrow terminals
Fixed /hooks and /mcp detail views printing a long value over the row below it in narrow terminals
Fix number entry not working in screen-reader lists
Fixed lists such as a skill's state options in /plugin not being answerable by typing a number in screen-reader mode
Fix Permission denied on TMPDIR writes
Windows: Fixed Bash commands that write to $TMPDIR/… failing with "Permission denied"
Fix update race deleting claude.exe backup
Windows: Fixed a race in which Claude Code sessions updating at the same moment could delete each other's claude.exe backup, which could leave no claude.exe behind
[VSCode] Fix empty local copy of Web sessions
Fixed opening a Web session with no messages saving an empty local copy that could not be resumed; an error now says where to continue it
[VSCode] Fix silent partial session loads
Fixed a claude.ai/code session opening empty or with only part of its conversation, with no error, when the server failed to return its history, part of it failed to load, or a network sign-in page answered in its place; it now shows an error and can be opened again
[VSCode] Fix silent hangs after host restart
Fixed conversations in editor tabs hanging silently after the extension host restarts; the tab now tells you to reopen it from the session list
[VSCode] Drop unused option previews in chat panel
Fixed Claude attaching option previews to multiple-choice questions in the chat panel, where the question card never shows them
[VSCode] Fix cost block wrap and stale totals
Fixed the session manager's cost and usage block wrapping mid-text on a narrow side bar, and showing totals from a previous login after an account switch
[Claude Code on the web] Fix draft-PR trigger not firing
Fixed routines with a GitHub trigger for a pull request being converted to draft never firing; they now start a run when the pull request is converted
[Claude Code on the web] Hide unusable Create PR button
Fixed cloud sessions on a repository that isn't hosted on GitHub showing a Create PR button that could never work; the button is now hidden there
[Claude Code on the web] Fix setup tip covering picker
Fixed the GitHub setup tip on claude.ai/code covering the repository picker's search box and rows while the picker is open; it now steps aside until the picker closes
[Claude Tag] Fix permanent thread-reply silence
Fixed Slack channels where Claude could permanently stop responding to replies inside threads; affected channels now recover on their own with the next new message to Claude
[Claude Tag] Fix stopped requests resuming unexpectedly
Fixed Claude resuming a stopped request after you press Stop in Slack, for example when a check-in fired or a background task ended; messages sent mid-response are now read
[Claude Tag] Auto-restart after mid-task crashes
Fixed Slack replies arriving many minutes late, or never, after Claude's session crashed mid-task, such as on a failed setup script; it now restarts on its own within minutes
[Claude Tag] Explain oversized-config start failures
Fixed Claude in Slack promising an automatic restart, then failing generically, when a session's configuration is too large to start; the thread now says why and how to retry
[Claude Tag] Fix long-thread reply and context loss
Fixed very long Slack threads: Claude could silently withhold a reply after judging it against weeks-old messages, and a restart deep into the thread could lose recent context
[Claude Tag] Fix channel-check failures after moving
Fixed Claude answering every mention with "Couldn't check this channel just now" in a Slack channel moved from Enterprise Grid org-wide sharing into a single workspace
[Claude Tag] Fix recurring channel-check failures
Fixed very large Enterprise Grid workspaces reached mostly through channels shared across workspaces getting "Couldn't check this channel" again after a quiet hour
[Claude Tag] Show inference hook deny messages
Fixed a Slack request blocked by your organization's inference hook showing a generic retry notice; the thread now shows the hook's deny message and Claude doesn't retry
[Claude Tag] Offer only allowed models
Fixed Claude in Slack offering to switch to models your organization can't use; it now lists and offers only models the switch will actually accept
[Claude Tag] Fix DynamoDB/Kinesis auth failures
Fixed requests to DynamoDB and Kinesis account-based endpoints failing to authenticate when sent through an AWS connection in Claude Tag
[Claude Tag] Fix admin Plugins section load failure
Fixed the Plugins sections in Claude Tag admin settings failing to load for organization admins and listing attached plugins as raw IDs; they now load and show each plugin's name
[Code Review] Fix missed review after force-push retry
Fixed a pull request getting no review when its reviewed commit was force-pushed away while a failed review was being retried in a repository not set to review every push