Skip to content

Claude Code 2.1.282

86changes
  • Attach a repository from another GitHub owner to a running cloud session.
  • Resume very large sessions faster, even ones that were never compacted.
  • Use the server-side auto mode classifier by default when telemetry is off.
  • Fix Bash permission rules with a mid-pattern :* being skipped in settings files.
  • Stop /install-github-app from pushing and saving secrets after you cancel.

New features

8
More changes (6) Fewer changes

Improvements

19
More changes (16) Fewer changes

Clearer Windows resume error for EBADF

Improved the error shown on Windows when a session can't be resumed because its transcript file could not be read (EBADF): it now names possible causes and what to try

Suggest another model on Desktop errors

Improved the Claude Desktop unknown-model error to suggest switching to a different model

Unusual Unicode in permission prompts

Improved rendering of unusual Unicode in permission prompts

Tidier, scrollable /artifacts list

Improved /artifacts: titles line up in one column, details are dropped whole instead of cut mid-word, and the list supports PgUp/PgDn, Home/End, the mouse wheel and clicks

claude-api skill: refusal billing

Updated the claude-api skill: pre-output refusal billing now links to the How refusals are billed docs, mid-stream refusals bill at normal rates, and pre-output refusals count against rate limits

claude-api skill: ant apply for Managed Agents

Updated the claude-api skill to recommend ant apply for keeping Managed Agents resources as version-controlled files

Managed limits on sandbox.excludedCommands

Changed sandbox.excludedCommands to ignore project and local settings entries when managed settings or --settings set allowUnsandboxedCommands: false, or managed allowManagedDomainsOnly: true

Invalid Windows admin policy still takes precedence

Changed Windows/WSL managed settings so an admin policy that is present but invalid or unreadable (HKLM, managed-settings.json) keeps user-writable HKCU and WSL /etc/claude-code from applying

Narrower claude.ai skill allow rules

Changed Skill(anthropic-skills:*) and Skill(claude-ai:*) allow rules to cover only skills synced from claude.ai, not plugins or other skills that merely use such a name

Reserved skill namespaces no longer load

Changed skill folders, command files and workflow commands in the anthropic-skills or claude-ai namespace to no longer load; a plugin so named still loads but yields name ties to synced skills

Reserved MCP server names list no skills

Changed MCP servers configured under the name anthropic-skills or claude-ai to list no skills or prompts (their tools still work); rename the server in your MCP configuration to list them again

Plain ultracode styling

Changed the ultracode visuals in /effort and the prompt input to plain styling (no ripple, border flourish or keyword glimmer) and removed the dynamic-workflows spinner tip

Clawd's feet in the banner

Changed the Clawd mascot's feet in the start-up banner to sit under the corners of his body

[Cloud sessions] Faster Routines page

Improved how quickly the Routines page and the sidebar's Scheduled list load for accounts whose past sessions scheduled many check-in reminders

[Claude Tag] Wide cards in Slack replies

Changed the bordered cards Claude uses in Slack replies for plans, tables and details to render wide by default instead of a narrow width

[Claude Tag] New workspaces follow the default model

Changed newly connected Slack workspaces to follow the current default model instead of keeping whichever model was the default when they were connected

Bug fixes

59

Keep earlier reasoning on resume

Fixed more cases of continued or resumed sessions (--continue, --resume) re-sending earlier messages in a changed form, which could make the API drop Claude's earlier reasoning

[VSCode] Keep up with long streaming replies

Fixed long replies falling behind the stream: the panel no longer re-parses the whole reply on every update

Recover from redacted_thinking API errors

Fixed sessions failing on every turn with an "Invalid data in redacted_thinking block" API error; Claude Code now drops the conversation's thinking blocks and retries once

Cancelled /install-github-app still pushing

Fixed /install-github-app saying "cancelled" and then still pushing the branch and saving the API key secret; leaving now stops the remaining steps and reports what was already done

Bash rules with a mid-pattern :* skipped

Fixed Bash permission rules with a mid-pattern :* being skipped in settings files while --allowedTools honored them; they now work from every source, with a startup warning on how they match

allowed-tools bypassing managed-only rules

Fixed repository, user and --add-dir skills, commands and skills-directory plugin manifests pre-approving their own tools via allowed-tools under managed allowManagedPermissionRulesOnly

Managed settings blocks dropped on one bad value

Fixed managed permissions, autoMode, worktree and attribution settings being ignored entirely when one nested value was invalid; the rest of the block now still applies

Mistyped managed lock keys ignored

Fixed managed settings ignoring a mistyped value for boolean lock keys such as disableClaudeAiConnectors or allowManagedPermissionRulesOnly; the lock now applies and startup names the key

More changes (51) Fewer changes

Undecryptable web search results failing requests

Fixed every request failing with a 400 error in conversations whose history holds web search results the API cannot decrypt (for example, from a turn answered through a third-party gateway)

Keep thinking across immediate slash commands

Fixed earlier extended thinking being dropped when /model, /rename, /artifacts or another immediate slash command was used while Claude was working

Keep thinking when relaunching with --tools

Fixed continued or resumed conversations losing earlier extended thinking when relaunched with a --tools list that leaves out a built-in tool offered earlier in the conversation

Retry refused compaction on a fallback model

Fixed compaction failing when the summarization request is refused; it now retries on a fallback model

xhigh effort failure after a model switch

Fixed a failed turn ("Effort 'xhigh' isn't available with thinking turned off") after a safety-related model switch in sessions with thinking off and effort above high

Unanswered usage-credits prompt switching models

Fixed an unanswered Fable usage-credits prompt switching models in SDK-hosted sessions such as Claude Desktop; the turn now ends instead, and Remote Control clients now see the model-switch notice

/model with a full Fable id erroring

Fixed /model with a full Fable model id stopping at an API error instead of opening the usage-credits prompt when the plan needs usage credits that aren't turned on yet

Stale token refresh lock failing requests

Fixed requests failing for up to a minute with an "another Claude Code process is refreshing it" login error after that other process was closed or killed mid-refresh

Retry organization policy fetch after sign-in refresh

Fixed sessions started while another Claude Code window was refreshing the sign-in (common with several VS Code windows) not retrying their organization policy fetch

CLAUDE.md read through macOS network symlinks

Fixed CLAUDE.md and rules being read at startup through a repository symlink reaching macOS's /Network via .. or a /.vol-style kernel path, or a rules link to macOS's /home being listed

Restored approval running a command twice

Fixed a command approved on a restored permission prompt running twice when a remote session's worker restarted

Request IDs in Bedrock block messages

Fixed safeguard block messages on Amazon Bedrock and Bedrock Mantle not showing a request ID; block messages now also show the message ID

Vertex AI: Web search for new models

Vertex AI: Fixed web search not being offered for models Claude Code doesn't recognize yet, such as newly released ones

Disk quota errors hidden behind exit code 1

Fixed Bash and PowerShell hiding a full disk quota behind "Exit code 1" and leaving large output files in temp

List every invalid tool parameter

Fixed tool input validation errors naming only an unknown, missing or mistyped parameter when other parameters in the same call were also invalid; those are now listed too

Multi-line paste submitted line by line

Fixed pasted multi-line text being submitted line by line after the terminal's bracketed paste mode was reset mid-session

Example prompt text flashing at startup

Fixed the prompt's example text flashing and disappearing at startup in projects with a SessionStart hook

Blank flash when starting fullscreen

Fixed a blank screen flashing before the first frame when starting in fullscreen mode

Garbled rows after the screen shrinks

Fixed garbled, misplaced rows in the non-fullscreen renderer after the screen got shorter while still taller than the terminal, e.g. deleting a prompt line while a shell command streams output

Stale character at the edge of diffs

Fixed a stale character left in the last column of a diff when a redrawn line's CJK character or emoji wrapped to the next row

Cursor position in recalled prompts with tabs

Fixed the cursor landing before the end of a prompt recalled from history when the prompt contains a tab

Correct send-now hint on older Windows Terminal

Fixed the send-now hint showing ctrl+enter on terminals that send it as a newline (Windows Terminal before 1.25); it now shows ctrl+x ctrl+s there

claude remote-control --debug rejected

Fixed claude remote-control --debug failing with "Unknown argument: --debug", although Remote Control's own eligibility error says to run with --debug

Cancelled /feedback still saving the report

Fixed /feedback, /bug and /share on Bedrock, Vertex and other third-party providers still saving the report file after you cancelled during the save

Plugin uninstall with an unreadable settings file

Fixed plugin uninstall reporting success and deleting the plugin's saved options when its settings file still enabled it or could not be read; it now stops and names the file

Keep plugin options when the list is unreadable

Fixed plugin uninstall deleting a plugin's saved options and secrets when the list of installed plugins could not be read after the removal; they are now kept and the uninstall says so

First key after / in /skills search

Fixed a key typed right after / in /skills moving the skill list instead of reaching the search box

Cursor jumping out of the /skills search box

Fixed the terminal cursor jumping from the /skills search box to the skill list while typing, which could hide the caret and put IME input in the wrong place

Narrow scrollable lists outside fullscreen

Fixed lists with a scrollbar, such as /skills and /mcp, being two columns narrower outside fullscreen mode, where the scrollbar can never appear

Agent panel footer with rebound keys

Fixed the agent panel footer wrapping onto two lines with long rebound keys, and its "Esc to collapse" hint ignoring a rebound collapse key

Doubled separator in the /tasks footer

Fixed a doubled · separator in the /tasks dialog footer when the stop-all-agents shortcut is unbound in keybindings.json

Artifact publishes with long labels

Fixed artifact publishes failing when Claude gave the version a label longer than 60 characters; the label is now shortened

Blank lines in list-item code blocks

Fixed screen-reader mode, quoted lists and very long lists dropping the blank lines at the top of a code block that opens a list item, directly or inside a quote

Clearer PDF page-read errors

Fixed PDF page-read error messages: paths with accented or non-Latin characters now appear readably, and a folder named like "password" or "invalid" can no longer make the error name the wrong cause

Vim mode counts and indent fixes

Fixed vim mode >> indenting empty lines, r with a count longer than the line changing text, 2J joining one line too many, and a count on the last line (2dd, 2>>) shifting or deleting it

Vim mode cursor placement

Fixed vim mode cursor placement: after dd, dj, dG or a whole-line p/P it lands on the first non-blank, yy no longer moves it, and Esc after an emoji no longer leaves it inside the emoji

Vim mode dot repeat counts and wrapped lines

Fixed vim mode ignoring a count typed before . when repeating x, s, p, d or c, and whole-line p/P, o, O, J, >> and << acting on the wrong line when a line above wraps

Vim mode cursor past the end of recalled prompts

Fixed vim mode leaving the cursor past the end of a prompt recalled from history or pulled back from the queue in normal mode, so x did nothing

[VSCode] Mic button covering the scrollbar

Fixed the dictation mic button covering the message input's scrollbar when the input is tall enough to scroll

[VSCode] Open local Remote Control sessions

Fixed Remote Control sessions started on this computer not opening from their Web entry in the session list; they now open the local conversation unless it's running elsewhere

[VSCode] Sign-in screen hanging after restart

Fixed an editor tab's sign-in screen hanging silently after the extension host restarts; it now shows the "stopped responding" notice too

[Cloud sessions] Routine times in half-hour zones

Fixed the next run time shown for an hourly routine being 30 minutes off for people in half-hour-offset time zones such as India

[Claude Tag] Grid auto-join channel patterns

Fixed auto-join channel patterns saved for one workspace in Claude Tag admin settings being ignored on an Enterprise Grid org-wide install; Claude now joins matching new channels

[Claude Tag] Silent in cross-workspace channels

Fixed Claude not responding in an Enterprise Grid channel shared between two workspaces of one organization when the channel's Claude Tag version was saved from the other workspace

[Claude Tag] Progress cards for GHES repositories

Fixed the earlier Claude in Slack app's progress card for sessions on a GitHub Enterprise Server repository: it now names the repository and offers a working Create PR button

[Claude Tag] Retired models in Slack threads

Fixed Slack threads whose model has been retired falling back to another model on every reply, slower and with a fallback note each time; the thread now moves to a working model

[Claude Tag] Tables in file captions

Fixed files Claude uploads to Slack not being able to carry a caption containing a table; captions now render with the same formatting as replies

[Claude Tag] Thread names in Agents & tools

Fixed Claude's threads in Slack's Agents & tools view sometimes being listed under their first message instead of their name; later renames now update the list too

[Claude Tag] Removing grants for disconnected orgs

Fixed removing a GitHub organization's grant from an access bundle's Repositories tab in Claude Tag admin settings failing to save after that GitHub organization was disconnected

[Claude Tag] Name the workspace missing the app

Fixed Claude always replying "Couldn't check this channel just now" in a channel shared with a Grid workspace it isn't added to; the notice now says which workspace needs the app

[Claude Tag] Inflated cost totals after restarts

Fixed the cost and token totals in Claude's reply footer reading many times too high after the session's cloud worker restarted

Change details