Claude updates

Radar Ultra

Releases: 42

2.1.330

Latest
CLIGitHub

AI summary

  • Fixed several hangs and delays: Claude could freeze after compacting a long conversation, WebFetch could stall sessions, and the first prompt after a long sleep could wait on a dead connection on Linux and WSL.
  • Organizations using Anthropic’s Enterprise Admin Console can now sign in with claude auth login; Claude Code then applies the organization’s settings and uses its cloud provider or gateway.
  • Added easel, which can draw charts when requested and for MCP metrics results. It is available on Pro and Max, and where available, Team and Enterprise, on macOS and Linux; automatic charts can be turned off in /config.
  • Recurring scheduled tasks and /loop can now run for up to 30 days while their session stays running. Tasks created before this release still end after 7 days.
  • Several fixes reduce the risk of losing work: concurrent settings saves no longer overwrite each other, resuming sessions with an invalid last-message timestamp works, and exiting a worktree no longer deletes one another Claude Code session is using.

Written by AI from the official notes. The original prevails.

6.28899.6

Latest
AppOfficial notes

AI summary

  • If you manage your own SSH hosts or mirror, install Claude Code 2.1.330 before updating client computers. Otherwise, those computers can’t start SSH sessions on the host and may lose access to sessions already running there.
  • On Windows, some EFS-encrypted files can no longer be attached from drives other than the app’s data drive or from certain sync folders. The task continues without the file, and Claude is told it couldn’t be attached.
  • On macOS and Linux, connected folders stay closed if the app can’t check them. Tasks that use those folders won’t start when file tools run on your computer; the error identifies the folder to fix.
  • In a new SSH session on Amazon Bedrock, /resume can continue a Bedrock-only Claude Code terminal session on the host by copying that session to your computer.
  • New recurring tasks in a Code session, such as /loop, can run for up to 30 days instead of 7. On an SSH host, they can keep using your provider while the app is closed. Setting scheduledTasksEnabled to false disables scheduled tasks from each session’s next start.

Written by AI from the official notes. The original prevails.

2.1.329

CLIGitHub

AI summary

  • Fixed a risk of losing your Claude Code settings: a temporary network stall or file lock should no longer reset ~/.claude.json to defaults.
  • Improved reliability and memory use in long sessions, including sessions with many edited files or large tool results. Code Mode runaway loops are now stopped at a limit.
  • Made scheduled tasks easier to track in /tasks, which now includes tasks and wakeups for the session, the goal, and conversation forks. Choosing “Exit and stop tasks” ends scheduled tasks so they won’t run again on resume, except when you exit while Claude is responding.
  • Improved sign-in reliability: fixed repeated macOS sign-outs when Claude Code could read but not save to Keychain, and made in-place restarts less likely to sign you out while login refreshes.
  • Clarified trust and safety prompts: folder trust dialogs now say where hooks are declared, managed-hook loading failures produce a warning, and the VS Code extension explains why a built-in tool’s safety check asks for permission.

Written by AI from the official notes. The original prevails.

2.1.328

CLIGitHub

AI summary

  • Auto mode is now available for Opus 4.6 and Sonnet 4.6 on Bedrock, Google Cloud Agent Platform, Microsoft Foundry, and the Claude apps gateway. Interactive sessions with no permission mode start in auto mode; plan mode and Bash prompts on third-party providers also offer it unless disableAutoMode is set.
  • Claude Code fixes several session and connection problems: resumed cloud sessions are less likely to lose recent conversation history, large sessions resume faster, and Remote Control and cloud sessions have fixes for lost prompts, tool results, and connection messages.
  • Code Mode has several fixes and usability improvements: scripts are less likely to stop or lose context in the listed situations, show their commands and output while running, and run faster in auto and bypass-permissions modes. It no longer runs UserPromptSubmit hooks on script output; use a PostToolUse hook with updatedToolOutput to redact that output.
  • The update fixes a range of everyday issues, including Bash commands in zsh that contain words beginning with =, occasional screen freezes, lost Esc presses at permission prompts, and clipboard and keyboard problems in several terminals.
  • For self-hosted runners, there are new options for naming a repository folder and passing labels or metadata to hooks. The update also fixes several runner reliability problems, including sessions stopping after certain proxy responses and damage to kept repository data after a temporary disk error.

Written by AI from the official notes. The original prevails.

6.28899.2

AppOfficial notes

AI summary

  • Some administrator retention settings can now permanently delete idle chats, their artifacts, and Cowork tasks that older versions kept. To preserve them, set all three retention periods to 3,650 days before updating. Changing tools or connectors, renaming, pinning, or moving a task no longer resets its idle time; sending a message does.
  • Auto mode has important changes for organizations using gateways or managed settings. On Gateway connections, the provider now runs the safety check; if it returns no result, Code waits five minutes for someone to choose Continue, then ends the turn. Some Auto mode requests also fail if the gateway refuses the session details. Administrators should review the gateway requirements and settings in the notes.
  • The built-in browser now sends every click and drag through Auto mode’s safety check wherever Auto mode is available, in every permission mode. The provider runs each check, which adds usage, and a click is refused if the check gives no verdict. In Cowork, recognized password, one-time code, payment-card, and Social Security number fields are hidden from Claude, but detection can miss fields and screenshots can still show numbers printed on the page.
  • Auto mode rules can now be set for Cowork and Code to tell Claude what an organization trusts, blocks, or allows. Because a model applies the rules, a block is not guaranteed; malformed rules turn Auto mode off until corrected.
  • Several fixes make Cowork tasks more reliable: new tasks are saved sooner, and fixes address workspace startup, downloads interrupted by sleep or updates, and tasks starting on slower or low-memory computers. A task stuck in a loop can still use far more provider tokens under the new 10,000-turn limit; the listed token-window limit does not count cached tokens.

Written by AI from the official notes. The original prevails.

6.6395.1

AppOfficial notes

AI summary

  • This release has no user-facing changes.
  • The bundled Claude Code version is 2.1.326.
  • For SSH host administrators, the SSH helper version is 13047a5194346a68538f5525406bf5f861013d73; launcher contracts are 1 for sessions and 2 for plugin commands.

Written by AI from the official notes. The original prevails.

2.1.327

CLIGitHub

AI summary

  • Claude Code is less likely to lose conversation history or answers when resuming after a crash, restart, or backgrounding. Very long transcripts that end early are also retried once.
  • Several safety checks are clearer or stricter: repository changes through /install-github-app now need confirmation, and Claude asks before removing a worktree that may contain unsaved work. Some path and command permissions have also changed, so certain actions may now require approval or be refused.
  • Some fixes help prevent accidental loss or damage: /export asks before replacing an existing file, project MCP changes preserve unrelated .mcp.json keys, and a Remote Control worktree fix prevents stopping the server from deleting ignored files such as .env.
  • You can now pass MCP server JSON through standard input with claude mcp add-json <name> -, keeping tokens out of the command line. This option is not available inside a Claude Code session.
  • /status now identifies several configuration and setup problems, and /config notes when another setting overrides a row. Resumed sessions also show a message if earlier conversation messages could not be loaded.

Written by AI from the official notes. The original prevails.

6.6395.0

AppOfficial notes

AI summary

  • Claude Desktop on macOS now ignores user-level configuration when a machine-level profile exists. Before updating, move any settings you still need—such as retention periods—to the machine profile; a diagnostic report lists settings that were lost.
  • Cowork can no longer convert or render .eps and .ps files or run Ghostscript tools such as ps2pdf, because Ghostscript was removed.
  • Worktree sessions no longer update your local base branch or checkout files in the background. Use git pull to update the branch.
  • Some SSH and WSL file downloads are now allowed by default when remoteFileDownloads is unset, except for blocked file types. Device policy, a configuration server, Admin Console, or managed settings keep downloads limited; a script-installed setting does not, so set it to limited there if needed.
  • The token limit and Usage figures now count Auto mode’s built-in safety checks and stopped requests, so people—especially those using Auto mode—may reach the limit sooner.

Written by AI from the official notes. The original prevails.

2.1.326

CLIGitHub

AI summary

  • Claude Code strengthens safety checks: more shell and PowerShell commands may ask for approval or be refused, and sandboxed commands have tighter limits on what they can write. Some previously allowed commands may now need approval.
  • Claude Code is more reliable when handling conversations and requests: fixes address lost conversation history after crashes or low memory, failed requests, and cases where Claude’s response or files were not preserved correctly.
  • Many terminal and prompt issues are fixed, including lost typed text, confusing permission prompts, and display problems in long conversations. The update also improves typing, streaming, and resizing responsiveness, especially in long sessions.
  • Remote Control replies now stream to your phone or browser as they are written. The update also fixes several Remote Control issues, including disconnects during replies and sessions showing the wrong activity state.
  • Claude Code gives clearer explanations in several places, including when features are disabled, settings or MCP servers fail, or a sign-in code is rejected. New /status information identifies when a provider or environment variable disables features.

Written by AI from the official notes. The original prevails.

2.1.325

CLIGitHub

AI summary

  • Several security and permission protections were strengthened: some shell commands now require permission instead of running automatically, sandboxed writes to Claude settings and related files in added folders are blocked, and additional gaps in permission checks were fixed. You can keep sandboxed commands running without prompts by enabling sandbox.autoAllowBashIfSandboxed: true.
  • Sign-in and billing behavior is more reliable: background sessions on a claude.ai login no longer use or bill an API key or token from the shell that started them, and some cases that moved sessions to another sign-in are now refused with an explanation.
  • Fixed sessions losing recent turns after an unclean shutdown, and fixed context-length errors on every turn for many third-party gateways and Foundry, which had prevented compaction.
  • Claude Code now asks before running sandboxed Bash commands by default. To keep running them without prompts, set sandbox.autoAllowBashIfSandboxed: true; managed sandbox settings must set this in the highest-ranking managed source.
  • Plugin prompts now warn that plugins can run code on your computer and access files and the shell. Plugin loading also skips some unsafe paths and links.

Written by AI from the official notes. The original prevails.

5.11492.5

AppOfficial notes

AI summary

  • Sandboxed shell commands now ask for approval more often on macOS and Linux. In Manual and Accept edits, most ask first; Auto mode checks many. This can pause a routine at a prompt. You can restore the previous behavior by setting autoAllowBashIfSandboxed to true in the relevant settings file.
  • Some commands that use variable-based shell allow rules, such as Bash(NODE_ENV*), no longer match those rules and will ask for approval.
  • Workflows in local sessions can pause when you reach your plan’s usage limit, then continue after the limit resets—if it resets within a day and Auto-continue when limits reset is enabled.
  • Fixed a problem that could leave a session busy if another session sent it the same message twice or sent many messages at once.
  • Fixed turns failing when a gateway returned 403 for an expired credential-helper token or a sign-in past its stated expiry; Claude now gets a fresh token and retries.

Written by AI from the official notes. The original prevails.

5.11492.2

AppOfficial notes

AI summary

  • This release includes Claude Code version 2.1.321.
  • Administrators of SSH hosts: the SSH helper is version 87375cc7c944eb9d45c8d9267edc70a4b4827961.
  • The notes report no user-facing changes in General, Code, Cowork, or 3P.

Written by AI from the official notes. The original prevails.

2.1.323

CLIGitHub

AI summary

  • Claude Code tightened safety checks: some Bash commands now ask for permission more reliably, and the sandbox blocks additional risky file and worktree changes. Automatic mode also falls back to Manual mode if it is unavailable.
  • Sign-in and background sessions are more dependable. Claude Code fixes several cases where sessions could switch accounts or lose authentication, and now stops with an explanation in some cases where it cannot keep the correct sign-in.
  • Added experimental, opt-in Code Mode, where Claude writes JavaScript to use its tools. You can turn it on or off for an organization.
  • Claude Code fixes issues that could lose or misplace conversation content, including after resuming, compacting, or restarting a cloud session.
  • Usage-limit handling is clearer: a menu offers choices when usage credits are unavailable or exhausted, and limit messages in several session types say when the limit resets and how to continue.

Written by AI from the official notes. The original prevails.

5.11492.0

AppOfficial notes

AI summary

  • Fixed several Windows problems: brief freezes when opening sessions or responding to approvals, blank windows after closing while minimized, and Setup offering some non-admin users an install that would remove their working app.
  • Fixed sign-in and saved-work issues, including Claude.ai sign-in being lost after a proxy error, artifact edits disappearing when leaving too soon, and messages being lost after a slow sign-in refresh.
  • Added a Download option for files from Cowork tasks that run on your computer, so you can save a copy wherever you choose.
  • Some browser and preview sites may stop loading if they require a client certificate: the app now sends one only to sites listed in device management. Behind a proxy that requests a certificate for every site, use *.
  • In local Code Auto sessions, Claude can start additional sessions for a task without approval if Auto's check allows it—up to 10 per message you type and 5 at once.

Written by AI from the official notes. The original prevails.

2.1.322

CLIGitHub

AI summary

  • Fast mode is now available on Vertex in the global, US, and EU regions. If Vertex refuses fast mode, Claude Code falls back to standard speed.

Written by AI from the official notes. The original prevails.

5.1231.2

AppOfficial notes

AI summary

  • The bundled Claude Code version is 2.1.321.
  • The notes report no user-facing changes in General, Code, Cowork, or 3P.
  • The notes report no user-facing changes in General, Code, Cowork, or 3P.

Written by AI from the official notes. The original prevails.

5.1231.0

AppOfficial notes

AI summary

  • Scheduled task cards now explain whether a run failed, needs your input, didn’t run, or is waiting. Tasks may also retry provider or gateway server errors for up to six hours.
  • Claude Code now follows administrators’ MCP server allow and deny rules for servers added in the desktop app. Administrators can also turn off Auto mode without restarting; running sessions and tasks (except WSL sessions) leave Auto mode at the next settings check, usually within 10 minutes.
  • On Windows, Claude now saves its data in a new location for eligible installs and moves existing data there on Windows 10 21H2 or later. The change does not apply to the Microsoft Store version or third-party deployments.
  • Claude now asks before starting a project’s dev server in Auto or Bypass mode on Windows, matching its behavior on macOS and Linux. Cowork’s Auto mode also checks each shell command before running it; blocked commands, or ones the check cannot assess, do not run.
  • Fixed several problems that could interrupt work: edits on network paths could change or remove the wrong content, the Code tab could freeze with many sessions open, and Cowork could lose a comment you were typing when a file updated.

Written by AI from the official notes. The original prevails.

2.1.321

CLIGitHub

AI summary

  • Claude Fable 5.2 is now the default Fable model. It has a 1M-token context window, and its listed prices are $8/$40 per million tokens, with cache reads at $0.20 per million tokens.
  • Several security and permission checks were fixed: MCP sign-in secrets are no longer sent to another host after a server redirect, and fixes address Bash commands or file operations that could bypass or misapply permission prompts and rules.
  • You can now pass --settings <file> to claude remote-control to apply that settings file to every session it starts. If the file changes, Remote Control will not start another session until you restart it.
  • Fast mode now tries standard speed on the same model first when fast serving is rate-limited, overloaded, or failing, instead of losing replies, switching models, or retrying for minutes.
  • Saved Fable 5.1 model selections now move to Fable on Pro and Max plans immediately, and on Team and Enterprise plans once the organization allows it. You can switch back with /model claude-fable-5-1.

Written by AI from the official notes. The original prevails.

4.23118.1

AppOfficial notes

AI summary

  • Replies can now continue after a connection breaks partway through, keeping the response received so far instead of stopping with a TLS handshake error.
  • On Windows, Claude Code no longer finds programs such as Git through network or relative PATH entries, or through links to network shares. If Git is found only that way, sessions use PowerShell instead of Git Bash.
  • When the sandbox is on, skills in a subfolder’s .claude/skills folder no longer load during the session. To use them, start the session in that subfolder.
  • On macOS, Claude Code now uses a newer signing certificate from the same Anthropic team. Team ID-based rules are unaffected; rules that pin the certificate itself need the new certificate added alongside the old one.
  • Plugin code that calls tools directly no longer shows an approval card. These calls run where only user approval or Auto mode would have stopped them, including connector tools without a toolPolicy entry; calls to tools set to ask are refused.

Written by AI from the official notes. The original prevails.

2.1.319

CLIGitHub

AI summary

  • Auto mode’s safety checks now behave more explicitly when server checks aren’t available: actions may be denied or sent to you for approval instead of using the built-in classifier. You can keep the built-in classifier with CLAUDE_CODE_AUTO_MODE_SERVER=0; Bedrock, Vertex and Foundry are unchanged.
  • MCP tool calls that run as tasks can now move to the background immediately, with Claude told when they finish. This works even when feature-flag fetching is unavailable; set CLAUDE_CODE_DISABLE_MCP_TASK_BACKGROUND to keep calls waiting, or CLAUDE_CODE_DISABLE_MCP_TASKS=1 to turn MCP tasks off.
  • You can configure permission prompts to be denied automatically instead of waiting for your response, so the turn can continue. This applies in terminal sessions, subagents and teammates.
  • /tasks now has an “Earlier in this session” list of finished subagents, which you can reopen and message, including after restarting Claude Code.
  • Several reliability fixes address common problems: older MCP servers can connect correctly, /diff works in more cases, and slash commands still run when typed after leading whitespace.

Written by AI from the official notes. The original prevails.

Radar Ultra
An unofficial tool, not affiliated with OpenAI. Compiled from public posts; the original posts are authoritative.