Claude Code 2.1.284
100changes- Add Claude Sonnet 5.5 as the default Sonnet model on the Anthropic API with 1M context.
- Start interactive terminal and VS Code sessions in auto mode by default when no permission mode is configured.
- Make Ultracode its own toggle in /effort so it no longer forces xhigh effort.
- Compact again with less recent conversation when a compacted request is still too long.
- Fix plugins pre-approving their own tools under managed allowManagedPermissionRulesOnly.
New features
14Add Claude Sonnet 5.5 as default Sonnet
Added Claude Sonnet 5.5 (claude-sonnet-5-5), now the default Sonnet model on the Anthropic API: 1M context, $2/$10 per Mtok with $0.20/Mtok cache reads
Ask-again option for outside reads
Added a "Yes, but ask again next time" answer to auto mode's prompt before a read outside the working directories, so you can allow that one read and still be asked about later ones
▤ In the docsAdd /mcp reconnect all
Added /mcp reconnect all in the interactive terminal to retry every MCP server that failed to connect or needs authentication at once
More changes (11) Fewer changes
Dollar amounts in gateway spend limit
Added dollar amounts to the Claude apps gateway spend limit in /usage and the status line (for example "$271.40 / $500.00 spent this month") when the gateway runs this version or later; the status line's rate_limits.spend_limit also gains used_usd, limit_usd and period
New /effort slider keybinding actions
Added effortSlider:decreaseEffort, increaseEffort and toggleUltracode keybinding actions, so the /effort slider's arrow and Tab keys can be rebound in keybindings.json
Add /rate-limit-options to /help
Added /rate-limit-options to /help and the command menu for claude.ai subscribers, so the usage-limit notices that mention it point to a command you can find
▤ In the docsGateway warnings for empty availableModels
Added Claude apps gateway startup warnings when a managed policy's availableModels is empty, or leaves out the model Claude Code starts on without setting model or enforceAvailableModels
Google auth for gateway telemetry export
Added auth: { google: {} } for Claude apps gateway telemetry.forward_to destinations, so telemetry can be exported straight to Google Cloud's OTLP endpoint using the gateway's Google Cloud credentials
Certificate client auth for gateway
Added certificate client authentication (private_key_jwt) between the Claude apps gateway and its identity provider, for identity providers that issue certificate credentials instead of client secrets
[VSCode] Optional message timestamps
Added an optional time above each prompt and response, with a date line where the day changes (Claude Code: Show Message Timestamps setting, off by default)
[VSCode] Plugin errors in Manage plugins
Added plugin load errors and notes to the Manage plugins rows, with a popup to disable, uninstall or copy the error
[VSCode] Ultracode on/off switch
Added an Ultracode on/off switch under the Effort slider, replacing the slider's Ultracode stop; the model pill shows "· Ultracode" at any effort level
[Claude Tag] Add model family choices
Added model family choices such as "Opus (latest)" for a thread, a channel default or your DM, so the choice follows the newest model in that family
[Claude Tag] Org limit spend in analytics
Added the spend that counts toward your organization-wide limit to the analytics spend projection chart, with how much of the limit is used
Improvements
29Ultracode as separate effort toggle
Changed Ultracode into its own toggle in /effort (Tab, or /effort ultracode [on|off]): it no longer forces xhigh effort and stays on at any effort level
Faster startup, less memory
Improved startup time and memory use by building only the parts of the settings schema that your settings files actually use
Start in auto mode by default
Changed interactive terminal and VS Code sessions to start in auto mode when no permission mode is configured, on every plan and provider; permissions.defaultMode still overrides it
▤ In the docsMore changes (26) Fewer changes
Unified usage-limit wait display
Improved the usage-limit wait: the limit's state and the countdown with the usage-credits option now show as one block under the prompt, and limit messages no longer repeat the countdown
Clearer unprefixed Chrome tool error
Improved the "No such tool available" error for Claude in Chrome tools called without their prefix: it now names the tool to call
Clearer Monitor event rows
Improved Monitor event rows to show what each event printed instead of repeating the description, and stopped repeating an unchanged "Waiting for N ... to finish" line after every event
Harden Workflow sandbox errors
Improved Workflow tool sandbox hardening for errors thrown by async script hooks
Improve /claude-api hillclimb and reports
Improved /claude-api: hillclimb no longer spends rounds on prompt rewordings too small for the eval to measure, and an extra page you ask for beside report.html is built as one local file that loads nothing from the network
Align details in list views
Improved lists such as /tasks, /copy and /hooks: the details after each name now line up in one column when they fit, and otherwise sit at the right edge
Warn when marketplace is replaced
Improved claude plugin marketplace add to say when it replaces a marketplace already added under the same name from a different source, and how to undo it
Clearer forced-login credential refusal
Improved the startup refusal when managed settings require a sign-in (forceLoginMethod or forceLoginOrgUUID) and an API key, token or apiKeyHelper is configured: it now names the credential in use, where it is set, and how to remove it
Neutralize spoofed markup in memory
Improved auto-memory loading: invisible characters and tags that imitate Claude Code's own markup are neutralized in MEMORY.md and recalled memory notes before they reach Claude
Trust prompt in remote-control
Improved claude remote-control: in a folder you haven't trusted yet, it now asks for workspace trust on the terminal instead of exiting
Artifact page design plan and titles
Improved artifact pages: Claude writes its design plan into the page instead of the reply, and uses the name you already gave something as the page title
Handle non-artifact links gracefully
Improved the Artifact tool so that when Claude is given a claude.ai chat or project link, an artifact from a chat, or an artifact id on its own, it asks for the right link or the content instead of stopping
Shared retry budget for dropped connections
Changed retries after a dropped connection mid-response to share one budget with the rest of the request's retries, so a failing request gives up sooner
Clearer Sonnet safeguard notice
Changed the notice shown when a Sonnet model's safeguards flag a message to explain why it happened and to offer editing and retrying
Safety model switch with pinned Opus
Changed safety-related model switches in sessions that pin an Opus model with ANTHROPIC_DEFAULT_OPUS_MODEL or modelOverrides: on the Anthropic API, the API now picks the model to switch to for each kind of flag, not the pinned model
Non-interactive MCP startup wait
Changed the non-interactive first turn to still wait up to 2s for connecting MCP servers named by --allowedTools or an mcp_tool hook, even when CLAUDE_CODE_MCP_STARTUP_WAIT_MS is 0
/recap declines relayed requests
Changed /recap to decline with a short notice when it arrives relayed from a chat thread (your own included) or from a routine or webhook; typed in the terminal, the Claude apps, Remote Control, -p or an SDK host, it runs as before
Filter tabs beside /artifacts title
Changed /artifacts to show its filter tabs beside the title with one-word labels (All, Mine, Shared), using the same tab bar as /config and /plugin
Refuse artifact files on network shares
Changed artifact publishing to refuse a file on a network share (a \\host\share path or a /net automount) unless it is on a mapped network drive added with --add-dir
[VSCode] Require absolute CLAUDE_CONFIG_DIR
Changed CLAUDE_CONFIG_DIR in the claudeCode.environmentVariables setting to apply only when it is an absolute path, and passed it to terminals that continue the chat
[Claude Tag] Repeat sign-in notice on @mention
Changed Claude to post its private sign-in notice at every @mention from someone who hasn't connected their Claude account, instead of going quiet after the first
[Claude Tag] Improve Notify members now
Improved "Notify members now" in admin settings: one press reaches every workspace your organization claimed in an Enterprise Grid, and more members in large workspaces
[Claude Tag] Clearer runner wait notice
Improved Claude's wait notice on self-hosted environments with on-demand runners: it now says whether a runner is starting, a start will be retried, or no runner will start
[Claude Tag] Clearer channel manager error
Improved the error shown when adding a channel manager fails because the channel's Slack workspace can't be confirmed as connected to your organization
[Claude Tag] Show auto-join attachments in access lists
Improved a channel's access lists in admin settings to show the connectors, repositories and plugins an auto-join pattern attaches, and where each comes from
[Claude Tag] Ask GitHub sign-in for repositories
Improved adding repositories as a channel manager: when your GitHub sign-in can't confirm you're a repository admin, the page asks you to sign in with GitHub
Bug fixes
57Fix raw errors from damaged response stream
Fixed a damaged response stream showing raw errors such as "JSON Parse error" or "undefined is not an object", or writing the word "undefined" into an answer, instead of being retried or reported as an interrupted response
Fix prompt-too-long after compacting
Fixed "Prompt is too long" errors that persisted after compacting: when the compacted request is still too long, Claude Code now compacts once more, keeping less of the recent conversation
Fix Remote Control prompt accepting early key
Fixed a key pressed the instant the terminal regained focus answering the Remote Control enable prompt before its short safety delay restarted
Fix plugins pre-approving own tools
Fixed plugins from marketplaces, claude.ai and npm pre-approving their own tools via allowed-tools under managed allowManagedPermissionRulesOnly; only plugins from an official Anthropic source or a source that managed settings vouch for keep that pre-approval
More changes (53) Fewer changes
Retry server errors after thinking block
Fixed an overloaded or server error arriving right after a thinking block ending the turn with an error instead of being retried
Fix bare unavailable-model message
Fixed a session whose model is unavailable, with no fallback model left, showing a bare "is currently unavailable" message (or "Something went wrong" in cloud sessions) instead of the model-unavailable notice and its Learn more link
Fix SDK crash on malformed image
Fixed Agent SDK sessions crashing when a user message contains an image with a malformed source, and failing on every later turn after a malformed document block; a malformed image is now replaced with an explanatory note
Fix MCP calls failing during resume
Fixed MCP tool calls in a resumed session failing with "No such tool available" while their server was still connecting; the call now waits up to 10 seconds for the server
Back off on plan-usage endpoint limits
Fixed repeated calls to the plan-usage endpoint after it rate-limits or rejects your login: /usage, /extra-usage and IDE usage views now back off instead of re-asking
Fix claude mcp add ignoring plugin-only policy
Fixed claude mcp add reporting success when managed settings restrict MCP servers to plugins; it now refuses and says what to do, instead of saving a server that never loads
Fix /plugin configure screen inputs
Fixed the /plugin configure screen: boolean options are now a true/false choice instead of free text, number options refuse invalid input, and the Left and Right arrow keys change an options field instead of switching tabs
Validate ANTHROPIC_FOUNDRY_RESOURCE value
Fixed ANTHROPIC_FOUNDRY_RESOURCE being interpolated into the Foundry endpoint host unvalidated; a value that is not a plain resource name is now refused
Fix missing 1M option in Desktop gateway
Fixed Claude Desktop behind a Claude apps gateway offering no 1M context option: the gateway now marks each 1M-capable model for Desktop automatically
Fix Down key selecting hidden tasks pill
Fixed Down arrow in shell mode selecting a hidden background-tasks pill, which stopped Backspace and Ctrl+U from editing the prompt
Fix Bash tool failing on Windows plugins
Fixed Bash tool failing on Windows with many plugins enabled: plugin bin/ directories that don't exist are no longer added to PATH, and inherited entries aren't added twice
Fix sparsePaths marketplaces on old git
Fixed sparsePaths plugin marketplaces cloning empty and replacing a working local copy on older git (before 2.39), which failed every refresh with "marketplace.json file is no longer present"
Fix fullscreen erasing terminal output above
Fixed fullscreen rendering erasing the terminal output above the session when [ in transcript mode writes the conversation to scrollback (macOS and Linux)
Fix fullscreen scroll jump after streaming
Fixed fullscreen scroll position jumping to the previous message or to the bottom when a reply finished streaming while scrolled up
Fix tab bars breaking mid-word when narrow
Fixed tab bars in dialogs such as /config and /plugin breaking the title and tab labels mid-word in a narrow terminal; a tab that doesn't fit now moves to the next line whole
Fix wrong count in /model picker
Fixed the /model picker showing "+1 model" below the list after scrolling to the last model; the count now covers only the models below the visible rows
Fix /keybindings writing no-op bindings
Fixed /keybindings writing Backspace and Delete bindings for a footer action that does nothing into the generated keybindings.json
Fix rebound footer:close typing x
Fixed a rebound agent panel close key (footer:close) typing "x" instead of itself on the row of the agent you're viewing
Fix vim dot repeat for fast typing
Fixed vim mode . not repeating text typed very fast (for example over ssh or in tmux) or pasted without bracketed paste, and leaving the prompt in INSERT mode after repeating a change with nothing typed (such as cw then Esc)
Fix vim cursor on image placeholder
Fixed vim mode leaving the cursor on an image placeholder's opening bracket after dd on the last line or yy at the end of the prompt, where r or x would break or delete the image
Fix duplicate workspace trust dialog
Fixed the workspace trust dialog appearing a second time after switching renderers or updating when Claude Code was started in the home directory
Fix skipped external .claude/rules symlinks
Fixed rules symlinked into .claude/rules from outside the project being skipped without ever showing the external-imports approval prompt; a .claude directory symlinked from outside the project now asks for the same approval
Fix failed plugin install staying enabled
Fixed a failed first claude plugin install leaving the plugin enabled and recorded when a dependency's version range could not be met
Fix debug log dropping hook stderr
Fixed the debug log dropping a failed hook's stderr when the hook also wrote to stdout, and logging nothing for a failed hook with no output; failed hooks now also log their status code
Honor block decision in Elicitation hooks
Fixed {"decision":"block"} returned by Elicitation and ElicitationResult hooks being ignored; it now declines the MCP elicitation, as exit code 2 does
Fix SendMessage hint without the tool
Fixed sessions launched without the SendMessage tool (such as by Claude Desktop) still being told to message other sessions with it
Fix lost Remote Control photo on edit
Fixed a photo sent from the Claude app over Remote Control being lost when its queued message was pulled back into the terminal prompt to edit, and the cursor moving one character for a photo with no caption
Fix typing during usage-limit wait
Fixed typing a message during an automatic usage-limit wait taking the wait out of the "Continue automatically at usage limit" setting's control when that turn hit the limit again
Fix /upgrade hint for top Max plan
Fixed usage-limit warnings suggesting /upgrade to users already on the highest Max plan; the warnings and /upgrade itself now point at /usage-credits when it is available
Fix Explore subagent switching to Opus
Fixed the Explore subagent switching to Opus on the Claude API when the session runs a model ID Claude Code doesn't recognize, such as a custom model behind a proxy; Explore now inherits that model
Fix hidden /loop status updates
Fixed /loop status updates in self-paced mode often not being shown because Claude wrote them only in its reasoning; Claude now writes each update, and the outcome when the loop stops, as visible text
Fix /ultrareview upload from desktop worktree
Fixed /ultrareview failing to upload the working tree when started from a git worktree that the Claude desktop app created on macOS or Linux
Fix sandboxed Bash start on Linux
Fixed sandboxed Bash commands failing to start on Linux when the working directory is write-denied and contains a read-denied directory
Fix artifact database write results
Fixed artifact database write results telling Claude that every viewer sees a write to a viewer's private data/users/ subtree, and added a "view" level to as_level
Fix gateway 431 with many IdP groups
Fixed the Claude apps gateway answering 431 Request Header Fields Too Large to every request from a sign-in whose identity provider lists many groups; it now accepts request headers up to 256 KiB
[VSCode] Fix Memory reload before save
Fixed Reload Claude from the Memory dialog restarting before an edited file was saved
[VSCode] Ask before restoring open conversations
Fixed a restored tab opening a conversation another Claude process still has open; it now asks first
[VSCode] Keep expanded Focus sections open
Fixed Focus view sections you expanded closing on their own while a sub-agent is working or when the section's first step is trimmed from view
[VSCode] Fix /model printing usage text
Fixed typing /model and Enter printing usage text into the chat instead of opening the model selector
[VSCode] Fix /feedback on cloud providers
Fixed /feedback on Vertex, Bedrock and Foundry being refused after you pressed Send; the report is now saved on this computer, as the terminal does
[VSCode] Fix slow sign-in after reload
Fixed sign-in waiting up to a minute for the Python extension after a window reload
[VSCode] Reopen tabs after Restart Extensions
Fixed Claude Code tabs that stopped responding after Restart Extensions: they now reopen on their conversation
[VSCode] Fix raw XML for unknown sender
Fixed a message from another agent with no recorded sender showing as raw XML in the chat
[VSCode] Keep agent messages after reload
Fixed messages from other agents, sessions or channels disappearing after a reload
[VSCode] Fix shadowed /mcp and /config
Fixed a user's own /mcp, /config or /settings command being shadowed by the extension's dialog
[VSCode] Fix Escape stopping background agents
Fixed Escape stopping every background agent when no turn was running
[VSCode] Keep marketplace on install links
Fixed plugin install links replacing a marketplace you already have that uses the same name
[VSCode] Fix prompt too long after compaction
Fixed "Prompt is too long" errors after compaction when a large text file is attached to a message
[VSCode] Fix links to non-ASCII file paths
Fixed chat links to files with non-ASCII characters, spaces or brackets in their path not opening
[Cloud sessions] Fix offline routine controls
Fixed a routine's Edit and Duplicate controls saying the routine was still loading while you were offline; they now tell you you're offline
[Claude Tag] Fix underscore GitHub Enterprise hosts
Fixed the earlier Claude in Slack app's progress card and link previews omitting the repository and Create PR button when a GitHub Enterprise host name contains an underscore
[Claude Tag] Fix silence when environment declines
Fixed Claude staying silent in a channel whose environment declines to start it; it now posts one notice asking you to contact an admin, and retries when @-mentioned
[Code Review] Retry post over open review
Fixed Code Review giving up without posting a finished review when an unsubmitted review under its GitHub App was open on the pull request; it now retries the post first