Claude Code v2.1.330
Claude Code v2.1.330 was released on .
Summary
Claude Code 2.1.330 is here: sign in to your org's Enterprise Admin Console, get automatic charts via the new easel tool, and point self-hosted runners at a specific folder. Plus a long list of fixes that stop freezes and lost work. What's the first thing you'll chart?
Release Context
- This was the 268th Claude Code release of 2026 tracked by Havoptic.
- It shipped 1 day after Claude Code v2.1.329 (November 19, 2026).
- Claude Code: ships every 1.8 days — 19 releases in the last month.
Why it matters: Sign in to your org's Claude Code automatically.
Shipped around the same time
Within 3 days of this release, other AI coding tools also shipped:
- Antigravity CLI v1.5.14 (November 21, 2026)
- Cline v4.1.27 (November 21, 2026)
- Amp 2026.11.21 (November 21, 2026)
- Grok Build v1.0.93 (November 20, 2026)
- Zed v1.29.3 (November 20, 2026)
Compare Claude Code
- Claude Code vs OpenAI Codex CLI
- Claude Code vs Cursor
- Claude Code vs Gemini CLI
- Claude Code vs Kiro CLI
- Claude Code vs GitHub Copilot CLI
- Claude Code vs Devin Desktop
- Claude Code vs Antigravity CLI
- Claude Code vs Grok Build
- Claude Code vs Cline
- Claude Code vs OpenCode
- Claude Code vs Zed
- Claude Code vs Factory Droid
- Claude Code vs Devin
- Claude Code vs Lovable
- Claude Code vs Amp
- Claude Code vs GitHub Copilot in VS Code
- Claude Code vs Replit Agent
- Claude Code vs Bolt
- Claude Code vs v0
Release Notes
- Added sign-in to organizations managed in Anthropic's Enterprise Admin Console: after claude auth login, Claude Code applies the organization's settings and uses its cloud provider or gateway
- Added easel, a built-in mod that draws charts when asked and under MCP metrics results, on Pro, Max and, where available, Team and Enterprise on macOS and Linux; turn automatic charts off in /config
- Added CLAUDECODEFULLSIGNINLINK=1 to print the full sign-in link, if the short one shows an error or a script reads values from it
- Self-hosted runner: Added --start-dir / SELFHOSTEDRUNNERSTARTDIR to have Claude start its work in a folder of a repository, while settings and hooks load as without it
- Added a notice in cloud and self-hosted runner sessions when a plugin marketplace can't be fetched because its repository isn't one of the session's
- Self-hosted runner: Added a notice when Anthropic-managed git refuses a plugin's own repository, naming the plugin and what to do
- Added commandPrinted to claude plugin install --json results, true when the plugin's install command wrote to stderr, and commandFailed when it exited with an error, was killed or timed out
- Added claudecodeselfhostedrunnerordertoregisteredseconds to the self-hosted runner's /metrics: seconds from work order issued to registration accepted, on orchestrator-spawned runners
- Added claudecodeselfhostedrunnerordertofirstsessionseconds to the self-hosted runner's /metrics: seconds from work order to first session handed over, on runners started for a session
- Fixed Claude Code freezing for up to several minutes right after compacting a very long conversation
- Fixed WebFetch freezing the session for minutes on some pages, and returning an empty result for some others
- Fixed ExitWorktree and the worktree exit dialog deleting a worktree that another running Claude Code session was working in
- Fixed changes to user settings being lost when several Claude Code processes saved them at the same time
- Fixed --continue and --resume opening an empty session or failing when the last saved message had a missing or invalid timestamp
- Fixed the first prompt after a sleep of two minutes or more waiting three minutes on a connection that had died, on Linux and WSL
- Fixed turns failing with "JSON schema is invalid", and session files growing by many megabytes, when many MCP tools have an input schema that the API refuses
- Linux: Fixed Bash commands waiting seconds and showing no file diff for the rest of a session in slow repositories with large ignored folders such as nodemodules
- Windows: Fixed Bash commands running slower for the rest of a session after Git Bash took 10 to 60 seconds to start, on machines with no custom start-up files
- Fixed /rewind sometimes restoring an older version of a file when two queued prompts, or stacked skills, ran together right after a turn that changed it
- Fixed text and images added when approving a permission prompt being dropped when the approved command or tool then failed
- Fixed MCP resources from claude.ai connectors and plugin servers not being attached when @-mentioned in the terminal's prompt box
- Fixed an MCP server that subagents declare being shut down when one of them finished, while other subagents or the session were still using it
- Fixed Claude in Chrome staying "not connected" after a brief connection problem, even though Chrome was open and signed in
- Fixed terminal sessions on Amazon Bedrock (Mantle) started with no model selected ignoring a pinned Opus model, and still calling an unavailable default model after announcing a fallback
- Fixed the rest of what you were typing being lost when a plan arrived in fullscreen mode
- Fixed claude.ai connectors with different names being dropped when they share a server URL (anthropics/claude-code101856)
- Fixed plugins going missing from the installed list when several claude plugin commands ran at the same time
- Fixed task dependencies and metadata being lost when several task updates ran at the same time
- Fixed incomplete backups of ~/.claude.json being kept, and displacing good ones, when the disk was full
- Fixed a long pause in Code Mode after code that read hundreds of files in projects with path-scoped rules or Read deny rules
- Fixed the built-in chart tool failing when Claude called it in Code Mode
- Fixed Code Mode ignoring an MCP tool's request to end the turn from a script in auto and bypass permissions modes
- Fixed Code Mode in auto mode dropping earlier thinking and rewriting the prompt cache when a mod added a note after a script loaded a skill
- Fixed Code Mode not restoring a file that a script had read after Esc and /compact
- Fixed /context undercounting system tools in Code Mode before Claude's first reply
- Fixed a stopped background subagent sometimes not staying stopped
- Fixed Claude still waiting for a background agent that was stopped just as it finished, in sessions run by an app or the SDK
- Fixed background sessions sometimes waking in their previous permission mode after approving a plan
- Remote Control: Fixed the note about background agents ended by a Stop from a phone or the web showing in the terminal as if you had typed it
- Remote Control: Fixed the mobile apps hiding the Diff and pull request buttons, or showing a stopped session as working, after turning it on mid-conversation
- Fixed environment variables written by a SessionStart hook being lost with claude -p --continue
- Fixed claude -p exiting 0 with no message when its output went to a file on a full disk: it now prints an error and exits 1, though a full NFS export may go unnoticed
- Fixed the system prompt keeping the earlier model's instructions when the model was changed after /context but before the first message
- Fixed Claude sometimes replying to its commit attribution reminder and ending the turn early after the model changed mid-turn; it can still happen where managed settings set the PR attribution line
- Fixed Esc not ending an LSP tool call that was waiting for a slow or stuck language server
- Fixed LSP tool calls and diagnostics failing when several calls or edits arrived while a language server was still starting
- Fixed /mcp listing plugin servers as built-in: they now stand under "Plugin MCPs", --mcp-config and built-in servers under "Other MCPs", and a server's page names its plugin
- Fixed an "MCP server blocked by enterprise policy: easel" warning showing at every start when an MCP allowlist or denylist excludes the built-in chart tool, which stays blocked
- Fixed /stats counting new activity in UTC days instead of your local time zone
- Fixed /ultrareview failing or reviewing the wrong code after the shell moved into another repository: it now stops and names both folders
- Fixed Grep reporting no matches when the pattern held a line break without multiline mode; it now reports the rejected pattern
- Fixed Jupyter notebooks saved with a byte order mark being reported as invalid JSON by the Read and NotebookEdit tools
- Fixed link reference definitions being dropped from CLAUDE.md and memory files that contain an HTML comment
- Fixed running Monitors keeping the earlier conversation in memory until they end
- Fixed some Claude Desktop sessions on third-party providers, other than scheduled tasks, ending a turn with "Prompt is too long" when a PDF larger than the context window followed a long conversation
- Fixed the choice between two user or project agent files declaring the same name depending on the order the file search listed them
- Fixed claude daemon logs never exiting inside a git repository when there is no log file
- Fixed markdown hiding a character or two after bold or italic text when a backslash came before an emoji later in the paragraph
- Fixed Edit refusing some valid hook commands in Claude settings files
- Fixed Read with a page range showing both halves of a scanned two-page spread on each of its pages
- Fixed line breaks and class stereotypes missing from Mermaid diagrams in HTML artifacts
- Fixed the Project instructions picker in /config showing only one of its four choices in a 24-row fullscreen window
- Fixed a subagent's own subagents and forks running on the plan-mode model in plan mode under opusplan or haiku
- Fixed WebFetch page summaries ignoring the /effort level when a gateway refuses the small fast model
- Fixed claude -p on Google Cloud's Agent Platform ignoring --settings '{"fastMode":true}' when the model comes from ANTHROPICMODEL or a settings file; such runs now bill at the fast mode price
- Fixed startup under forceLoginOrgUUID being refused after one temporary server error or dropped connection
- Fixed claude mcp remove giving no way forward for a claude.ai connector: it now says to turn it off in /mcp or remove it on claude.ai
- Fixed the /mcp "Connect on claude.ai" check saying "not connected" when claude.ai has a connector at the server's URL without its query
- Fixed /install-github-app and /design-login showing a generic failure for an account on hold instead of the on-hold notice and appeal link
- Fixed a running MCP task being reported as stopped when you move a session to the background; the background session can now follow the task, but not if its server uses stdio or sets headers
- Fixed self-hosted runners ignoring a session until they exited, after its failure report was lost or the session was given back to the same runner
- Fixed self-hosted sessions losing the prompt cache and earlier thinking when the list of repositories a restart couldn't prepare changed
- Self-hosted runner: Fixed tool calls behind a permission prompt vanishing with no result when a new runner took over the prompt, in sessions with telemetry off
- Fixed resumed self-hosted runner sessions starting without their pushed work in large repositories when --push-outcome-on-release is set
- Fixed self-hosted runner sessions being shown as working when Claude Code hangs at every start and --startup-timeout-min is from 2 to about 6
- Fixed pkill -f in self-hosted runner sessions on Linux ending its own shell with exit code 144, or the runner (needs a pkill with --ignore-ancestors)
- Fixed scheduled tasks on self-hosted runners having no tool to notify their owner when telemetry is off or a third-party provider is used
- Self-hosted runner: Fixed one slow spawn-runner hook keeping the orchestrator from claiming sessions for its free slots; it now polls every 4 to 6 seconds while a slot is free
- Self-hosted runner: Fixed a 403, such as an IP allowlist's, logged as a bad secret or token: most such lines now lead with the server's reason, so update log alerts that match the old words
- Fixed self-hosted runners' warn mode for repository settings stopping at the first finding of most kinds: it now goes on, up to 50 for a session, and says if it stops early
- Self-hosted runner: Fixed runners that start on a full disk taking sessions and failing them; they now wait for room and exit 1 after a minute with no session, unless started from a work order
- Self-hosted runner: Fixed a failed start suggesting a retry when the runner's machine had no git credentials; the error now says whom to ask and what to do if the repository is wrong
- Fixed the self-hosted runner's lastpollageseconds reading 0 while the runner had never polled successfully
- Fixed the notice about a skipped scheduled task that names no organization: it now says to start Claude Code with --resume, because /resume inside a running session doesn't run the task
- Fixed claude plugin validate wrongly warning that a mod's AbovePrompt or AbovePromptList hook never runs in VS Code
- Fixed /design-sync deleting a file it had just uploaded when Claude Design stored that file under a changed name
- Reverted 2.1.329's removal of the automatic retry when maxtokens exceeds a model's or gateway's limit
- Improved the claude.ai sign-in link shown by /login, claude auth login and claude setup-token: it is now much shorter
- Windows: Improved Grep and Glob speed by no longer starting a console host for each built-in ripgrep search on a local path
- Improved the speed of file diffs
- Improved /config search: most settings whose name starts with what you type come first, "effort" finds Model, and "dark" or "light" finds Theme
- Improved /resume: sessions where you only opened a screen such as /model and left are no longer listed
- Improved Reconnect in /mcp and /plugin: a server's page now stays open, with the cause in view, when the server still fails or needs sign-in
- Improved the error on macOS when sandbox deny lists are too long: it now names the long lists and how to shorten them
- Improved /plugin in fullscreen mode: the page of a plugin with errors now starts with those errors
- Improved /ultrareview's cost confirmation on Team and Enterprise plans: it now says how much of your monthly spend limit is left when that is less than a review usually costs
- Improved self-hosted runner sessions on Amazon Bedrock or Google Cloud's Agent Platform to say so when they start on another default model because your account refused the first
- Windows: Improved the error when a session's folder is on a drive Claude Code can't verify: it says why, and whether retrying can help
- Improved Code Mode: Claude is now told how to look at images and PDFs
- Improved Code Mode: after Esc, "Interrupted" now shows under the stopped command in place of a red error
- Improved Code Mode: the terminal freezes for far less time after a subagent's script makes thousands of tool calls
- Changed recurring scheduled tasks and /loop to run up to 30 days instead of 7 while their session keeps running, and say when they end; tasks made before this release still end at 7 days
- Changed more rm commands aimed at the root, home, a top-level folder or the working folder to ask for approval; where nobody can answer, they're refused
- Changed deniedMcpServers name entries to hide only the named claude.ai connector, not others at its URL; to block them all, deny its exact URL
- Changed claude --teleport in some setups to print the git commands for switching branch instead of running them; with -p it exits 1 until you switch
- Changed unrecognized model names containing "sonnet" or "haiku" to use the shorter system prompt, like other unrecognized names; CLAUDECODESIMPLESYSTEMPROMPT=0 gives every model the full one
- Changed skills that Claude runs with a model setting, other than context: fork skills, to leave subagents, forks, compaction and /recap on the session's model
- Changed a subagent's model fallback to carry over: agents with no model and forks it then starts run on the fallback, and the agents they start use its Bedrock region
- Self-hosted runner: Changed spawn-runner hooks to start while earlier ones still run, up to --hook-concurrency per orchestrator (4 by default); set it to 1 if yours can't run beside another
- Self-hosted runner: Changed Bash commands to skip the file diff when nothing needs it, so transcripts can lack it; set bashEditDiffEnabled to true in managed settings to get every diff
- Changed self-hosted runners to stop a session's start at once, without trying other runners, when a checkout hook exits with status 108
- Changed prompt hooks to accept model aliases such as haiku or sonnet in their model field
- Changed /design-sync's fallback build of the reference Storybook to use only a Storybook installed in the project
- Changed subagent progress summaries in terminal sessions signed in to a Claude apps gateway to be written from short notes instead of the whole conversation, using far fewer tokens
- [VSCode] Added /fork to fork a conversation after its last reply (anthropics/claude-code69272)
- [VSCode] Added /workflows, which opens the agent map with running workflows
- [VSCode] Added the claudeCode.escapeStopsClaude setting; turn it off so Escape does not stop Claude (anthropics/claude-code91536)
- [VSCode] Added the claudeCode.pinPrompt setting to let your message scroll away instead of staying pinned
- [VSCode] Added the claudeCode.contextUsageThreshold setting for when the context indicator shows (anthropics/claude-code93036)
- [VSCode] Added a prompt argument to the "Open in Side Bar" command for keybindings and extensions
- [VSCode] Added Move up and Move down to a session group's menu (anthropics/claude-code98654)
- [VSCode] Fixed VS Code opening and focusing its terminal on every prompt of a connected terminal session
- [VSCode] Fixed copying a code block adding a trailing newline that ran the command on paste (anthropics/claude-code96976)
- [VSCode] Fixed holding Enter on /rewind restoring files, and a double click on Remove or Delete removing a memory, MCP server or plugin marketplace, without confirmation
- [VSCode] Fixed Enter on a question card sending your earlier answer instead of picking the focused one, and arrow keys not working after an "Other" answer; answered questions reopen on your pick
- [VSCode] Fixed a held-down Enter key sending a half-written message or running a typed slash command
- [VSCode] Fixed Cmd+A, C, V, X and Z not working in the rename box and dialogs on macOS
- [VSCode] Fixed Ctrl+F and Ctrl+P not moving the caret in the message box on macOS
- [VSCode] Fixed Accept and Reject Proposed Changes showing over the chat, the terminal tab and other files; they now show only on the proposed diff
- [VSCode] Fixed a slow-starting Claude tab taking the keyboard away from the file you had gone on typing in
- [VSCode] Fixed unsaved changes and new problems being missed on macOS and Linux for files whose path contains , ? or %20, such as a C folder
- [VSCode] Fixed whole-line selections counting one line too many in the selection chip, in @-mentions and in what Claude is told, and file links leaving out the last line of a range
- [VSCode] Fixed a conversation forked in the panel re-running an old, unanswered prompt by itself after a window reload
- [VSCode] Fixed a forked conversation running the original conversation's /loop schedules a second time
- [VSCode] Fixed /clear giving no sign that the session still runs without a newly trusted folder's CLAUDE.md and settings
- [VSCode] Fixed dialogs closing, and losing typed text, when a text selection was dragged past their edge
- [VSCode] Fixed advisor calls showing as "Unsupported content type" (anthropics/claude-code73499, anthropics/claude-code64158, anthropics/claude-code90471, anthropics/claude-code73637)
- [VSCode] Fixed the session list showing no status for the sidebar chat's session (anthropics/claude-code93898)
- [VSCode] Fixed the plan preview's Add Comment button vanishing after a fast double click on a word
- [VSCode] Fixed long lines cut off in the Edit Notebook Cell row, permission rules squeezed in a narrow panel, hard-to-see question card marks, and menus moving the chat after a declined trust prompt
- [VSCode] Fixed signing in to an account on hold showing a generic failure instead of the on-hold notice and appeal link
Other Recent Claude Code Releases
- v2.1.328 (November 18, 2026)
- v2.1.327 (November 17, 2026)
- v2.1.326 (November 16, 2026)
- v2.1.325 (November 13, 2026)
- v2.1.323 (November 12, 2026)
All Claude Code releases · All AI coding tool releases on Havoptic