← Back to all releases
v2.1.327 Claude Code Release Notes
Claude's Analysisby Sonnet 5.5
Full AnalysisBig stability pass: data-loss fixes (.mcp.json, /export, resumed sessions), plus /status now listing broken config and claude mcp add-json - for stdin tokens.
Changes
173
Total Changes (vs Average)
7.7×
Version Type
Patch
Release Focus
Bug Fixes
Day Since Prior Release
1
Release # This Month
#9 of 9
Bug Fix Ratio
58%
Post-Release Edits
—
How does this release compare? Release pace, fix share and issue trends since April 2025.See all-time statistics
Change Category
Ecosystem Impact
MCP, Plugins / Skills, Remote Control, Cloud Sessions and VS Code each appeared in 9 of the last 10 releases, so this fix-heavy cadence is spread across the whole product surface rather than concentrated in one area.
Key Themes
5Data-loss and silent-overwrite fixes|9Session resume and recovery reliability|8Better diagnostics and clearer feedback|20Hangs, stalls and terminal rendering|14Agents, plugins and MCP correctness
May Help If You've Noticed
Your .mcp.json lost other keys after adding or removing a server
Changes in Claude Code v2.1.327
Added9 changes
- •Added a confirmation before
/install-github-appchanges a repository - •Added
claude mcp add-json <name> -to read the server's JSON from stdin, so tokens can stay off the command line; not available inside a Claude Code session - •Added a line when a resumed session's earlier messages can't be loaded
- •Added a list in
/statusof broken agent, skill, command and output style files, keybinding errors, an unavailable sandbox, ignored permission settings and hook matchers that never match - •Added a note in
/configwhen other settings override a row - •Added
x-claude-code-managed-settings-checksumto the gateway hint headers; sent where managed settings setCLAUDE_CODE_GATEWAY_HINT_HEADERS=1, including where they already do - •Added support for naming a session's billing group with the
attributionProjectsetting, for Claude apps gateways that setadmin.billing_group_tag - •Added
/tui classicas the name for the non-fullscreen renderer;/tui defaultstill works - •[VSCode] Added "Claude Code: Add to Chat" to the Explorer's right-click menu, which @-mentions the selected files and folders in the chat
Improved26 changes
- •Improved the speed of a session's first Bash command: shell start-up files may now run before it's approved, even if it's refused; set
CLAUDE_CODE_DISABLE_SHELL_HEAD_START=1to turn this off - •Improved commits on newer models and in PowerShell: Claude is now told not to commit files that likely contain secrets
- •Improved sandboxed shell commands: Claude now sees when a command exempt from the sandbox stayed in it because its permission check relied on the sandbox
- •Improved the refusal for shell commands with no
rmthat the dangerousrmcheck can't parse, so Claude can resend harmless ones in plain syntax instead of giving up - •Improved resuming very long sessions: a transcript read that ends early is now retried once, so messages are lost less often
- •Improved subagent answers that hit the output token limit twice: they now more often come back whole or say up front that they are partial
- •Improved long replies on unrecognized models: a reply cut at 32,000 output tokens now continues with a limit of 128,000
- •Improved the reminder about a completed subagent after compaction: if Claude can't read the agent's output file, it is now told to ask the agent with
SendMessage - •Improved the warning shown when an API key and an Anthropic profile are both set: it now says which one is in use and how to switch to the profile
- •Improved
/plugin: the question before removing a marketplace now says that its plugins' settings and saved data are deleted, and a marketplace's page no longer shows another marketplace's error - •Windows: Improved start-up time with no Git Bash and no
pwshon PATH by checking PowerShell's standard install locations at once; System32'spowershell.exenow wins over one earlier on PATH - •Improved startup time on Windows when PATH points to Git for Windows' bin folder, by starting git.exe directly instead of through its launcher
- •Windows: Improved PowerShell tool speed by up to about half a second per command
- •Improved how soon the Bash tool's diff of changed files is ready in auto and bypass permissions modes
- •Improved speed of the Bash permission check on very deeply nested missing paths on macOS and Linux, and of secret masking on very long text with a URL
- •Improved transcript search to find text in edits and written files
- •Improved speed of reading large PNG images, and the quality of the JPEG sent in their place
- •Improved the Artifact tool to read an uploaded file by the address the artifact's page shows; other forms still fail, most with a message that says to read uploads one per call, by id
- •Improved the Artifact tool to ignore
prompt,limitandlabelon some calls that do not use them instead of failing the call - •Improved MCP server pages in
/mcp: local, remote and agent servers share one layout, menus end in Back, and actions are no longer numbered outside screen reader mode; use the arrow keys and Enter - •Improved narrow terminals:
/status, forms and detail screens lay out better,/modeland/effortfit at about 40 columns, and key hints such as←/→ to adjuststay - •Improved
/install-github-app: the repository, secret and API key steps use the standard list and keys, with shorter messages, a spinner and clearer errors - •Improved
/desktop: the download question is a standard list instead of y/n - •[VSCode] Improved speed when Claude makes several edits in a row: queued edits share one wait for new problems; a problem may be reported with a later edit
- •[VSCode] Improved @-mention file search speed in large workspaces when
rgis on yourPATH; results now rank much as in the terminal, with less tolerance for typos - •[VSCode] Improved startup: the model picker is ready at once in folders opened for the first time, empty windows and worktrees, except on third-party providers
Fixed101 changes
- •Remote Control: Fixed stopping the server in worktree mode deleting a running session's git-ignored files, such as
.env - •Fixed self-hosted runners with
--use-anthropic-git-proxydeleting a non-empty directory named byGIT_CONFIG_GLOBALat startup: the runner now keeps it, ignores the variable and warns - •Fixed
claude mcp addandclaude mcp removewith project scope deleting other top-level keys from.mcp.json, such as$schemaor another tool'sservers - •Fixed
/exportoverwriting an existing file without asking: the dialog now asks, and/export <name>keeps the file and says to run/export - •Fixed a command you had allowed still running after you pressed Stop, when the approval arrived after a restart, in cloud and self-hosted runner sessions with no feature flags loaded
- •Fixed Enter closing
/teleport's load error screen - •Fixed a click followed by Enter in
/plugininstalling or disabling a plugin - •Fixed a half-typed
!command running on an extra Enter after the usage limit menu - •Fixed some
--disallowedToolsrules with parentheses in their content - •Fixed auto mode ignoring some wildcard PowerShell allow rules that name a script with
.\, such asPowerShell(.\scripts\build.ps1 *) - •Fixed a running Code Mode script in auto mode getting permission prompts and denials once Claude started a second script that auto mode also allowed
- •Fixed a nested
claudewith its own token being refused byforceLoginOrgUUID: commands that don't get the session's token no longer get itsCLAUDE_CODE_OAUTH_SCOPES; set it on any that need it - •Fixed headless sessions losing stored messages on resume when a message was sent again with the same UUID after the process was killed
- •Fixed cases where a session resumed after an empty reply or a killed command lost an answer, or brought back a rewound prompt, after another crash or a move to the background
- •Fixed a remote session forgetting messages sent after Stop was pressed during a restart, if Claude Code then crashed
- •Fixed tasks created after
/clearbeing lost, and cleared tasks coming back, when a cloud or self-hosted runner session with no feature flags loaded resumed later - •Fixed a compaction right after a reply cut at the output token limit losing that reply's tool call and its result
- •Fixed a settings change from
/configand similar commands failing to save with no warning; a line under the prompt now says so - •Fixed
/rewindclosing without a word when some files could not be restored - •Fixed pasted images being dropped when the prompt starts with a file path such as
/tmp/a.txt - •Fixed agents passed with
--agentsbeing lost once plugins loaded or reloaded - •Fixed a plugin's agent being dropped when resuming a session from the
--resumepicker - •Fixed Claude Code refusing to start when
https_proxyorHTTPS_PROXYis a barehost:portand neither its input nor its output is a terminal (the desktop app, an SDK, cron) - •Fixed Claude Code on Linux sometimes returning to the shell while restarting itself at startup, such as after the first sign-in to a Claude apps gateway or when turning on Code Mode
- •Fixed
claude -phanging before its first request when the fetch of a model's settings stalled, such as at a proxy; it now goes on without them after 10 seconds - •Fixed the screen staying blank or frozen after a brief out-of-memory error
- •Fixed a rare display fault that could freeze the screen or end the session
- •Fixed cloud sessions breaking when a program left thousands of connections open to the session's network proxy
- •Fixed a turn hanging when a mod's
$.model.completeor$.model.classifycall met a usage limit: the call now gets the API's error at once; mods should handle that error - •Fixed stalls on a compaction reply with thousands of unclosed tags and on some very long WebFetch URLs; WebFetch now refuses a URL over 2,000 characters before any permission prompt
- •Fixed a message with thousands of
@mentions stalling before Claude replies; only the first 100 mentions are now looked up as files - •Fixed the prompt freezing after rejecting a write to a very large file; a rejected write now shows a short preview
- •Fixed a crash when a burst of keys reached the search box in
/plugin - •Fixed a false crash report and exit code when a suspended session resumes, or at exit, where a Linux security policy blocks a process from signalling itself
- •Fixed remote MCP servers staying disconnected after a longer outage such as a VPN drop: most servers on other machines reached by hostname over https are now retried in the background for about a day
- •Fixed Edit refusing with "File has not been read yet" after a compaction on unchanged files outside the project that Claude had already read in full
- •Fixed Grep repeating or skipping results when paging with
head_limitandoffset; content and count results are now sorted by file path - •Fixed Read failing on Jupyter notebooks that contain an output of an unknown type
- •Fixed NotebookEdit removing the notebook file's final newline
- •Fixed the Read tool reporting 512KB instead of the real size when a file of 10 MB or more is too large to read at once
- •Fixed the Bash tool's diff of changed files not naming files that are binary, too large or too many to show
- •Fixed artifact publishes failing with "the source file changed between approval and publish" when a synced or remote-backed folder had only changed the file's timestamp
- •Fixed a new artifact that you approved being refused in a cloud scheduled task's session, in organizations that require approval of each new artifact
- •Fixed a new artifact being refused after an app built on the Agent SDK approved it, in organizations that require approval of each new artifact
- •Fixed
/artifactsshowing part of your list, or "No artifacts yet", when a request for more of the list failed: it now tries again, then warns if it can't load the whole list - •Fixed in-process agent teammates on a different model from the lead compacting at the lead's context limit and on the wrong model; they now use their own limit and model, at that model's rate
- •Fixed a finished subagent resuming on the model and effort of a sibling subagent that messaged it
- •Fixed the main conversation not being told a background agent had finished when the subagent that started it ended by itself without reading the result, outside auto mode
- •Fixed Claude reporting a background agent as still running when it had waited 30 seconds or more on a permission prompt in the desktop app, on the web and in the SDK
- •Fixed Claude not being told in auto mode when a background agent's reply to a follow-up message was dropped, and reduced repeat wake-ups there from agents waiting on background commands
- •Fixed the desktop app, Claude Code on the web and VS Code showing a raw task notification as a subagent's prompt after its background task woke it
- •Fixed messages sent from another session with "later" priority joining the running turn, instead of waiting for it to end, in Remote Control and Claude Desktop sessions
- •Fixed messages to cloud and Remote Control sessions being reported as failed with a stale address after a timeout or rate limit; Claude now says when a message may have arrived
- •Fixed cloud sessions giving no error when a
UserPromptSubmithook blocks a message sent while Claude works - •Fixed failing hooks showing nothing: SubagentStop in background agents, SessionEnd at
/clearand/resume, and CwdChanged and FileChanged in fullscreen - •Fixed a Stop hook that failed to run being shown as having reported a problem
- •Fixed focus view keeping a finished reply hidden while a Stop hook was running
- •Fixed Claude getting a long managed PostToolUse hook output twice when a mod added context to the tool call
- •Fixed
/modellisting the wrong models in some terminal sessions when a project's.claude/settings.jsonsetsANTHROPIC_BASE_URLto an LLM gateway - •Fixed
/statuslinewriting to~/.claude/settings.jsonwhenCLAUDE_CONFIG_DIRpoints to another folder - •Fixed
claudeMdExcludespatterns on Windows not matching a path whose drive letter is written in the other case - •Fixed
claude agentsandclaude rmrefusing to remove a fully pushed session ("The worktree has unpushed commits") when its worktree has a file or folder namedHEADat the top level - •Fixed long ListAgents results hiding most sessions on accounts with many cloud or Remote Control sessions: long lists now come in pages
- •Fixed slow turns in resumed sessions for organizations with tens of thousands of connector tool permissions
- •Self-hosted runner: Fixed
claude -pstarted by a session's script or hook waiting out rate limits, because it inherited the session's own retry setting - •Fixed the spend limit menu reporting a changed limit when the server refused it
- •Fixed a second
xon a task's details in/tasksstopping the next task too - •Fixed Esc being ignored on a permission prompt that had just appeared
- •Fixed lists that load their rows late sometimes ignoring Enter and the arrow keys
- •Fixed
/autofix-prholding the keyboard after Esc while it stopped the cloud session; the dialog now closes at once, and a stop that fails is reported afterwards with a link - •Fixed a blank screen and stray mouse codes in the shell after quitting with ctrl+c just after ← opens the agents view
- •Fixed Ctrl+C right after the trust question leaving the terminal in fullscreen
- •Fixed the shell flashing on screen when ← opens the agents view in fullscreen mode
- •Fixed terminal display faults: most scrambled scrollback in Ghostty on resize, link addresses hidden in Windows Terminal under old tmux and in VTE 0.50.0, and no selection highlight with 16 colors
- •Fixed some garbled rows in tmux with
allow-passthroughon inside kitty, Ghostty or iTerm2 - •Fixed
/mcpsaying no servers were configured after one was added during a session or declined; it now says what to do - •Fixed
/hooksleaving out hooks given by--settings - •Fixed the
/menu listing a row for each skill of the same name, though every row ran the first - •Fixed
/teleportshowing no message when the chosen session failed to resume - •Fixed n and N in transcript search skipping matches
- •Fixed cancelling a transcript search (ctrl+o, then /) in a long session landing far from where the search started
- •Fixed up and down losing the cursor's column over a short or blank line
- •Fixed Tab in shell mode filling in a file name after
&&,;or|, where a command goes - •Fixed the selected session leaving the screen in
claude --resumeand/resumewhen branch names or folder paths are long - •Fixed the MCP tool list in
/mcpand/pluginlosing your place when going back from a tool - •Fixed
/resumelisting one session fewer than the window has room for, and a 'Resend your message' hint after most spend caps, where resending can't help - •Fixed an MCP server's long question being cut off after one row, text fields hiding long pastes with no sign, and a doubled divider line in
/plugin's options and/login's Bedrock and Vertex steps - •Fixed the "+N lines" count being too high for command output with links or colors, and the transcript's
?help hiding how to exit in a short window - •Fixed Ctrl+C twice not closing
/chromefrom its browser list - •Fixed a number and Enter typed too early at an agent's plan approval in screen reader mode causing the next number to be dropped too
- •Fixed Claude trying to read design system token files that do not exist when starting a deck or design
- •Fixed exit not saying that a worktree was kept
- •Fixed
/hookshelp naming input fields that do not exist - •Fixed question dialogs naming ctrl+g after the external editor key was rebound
- •Fixed two sign-in error messages that pointed to the Claude subscription option on computers where
forceLoginMethodis set toconsole - •Fixed
/configsaying the dialog was dismissed instead of "Set theme to …" after changing the theme - •Bug fixes and reliability improvements
- •[VSCode] Fixed the permission prompt not showing the reason that a PreToolUse hook gives when it asks for confirmation (anthropics/claude-code#85950)
- •[VSCode] Fixed long tool and file names being cut off in a permission prompt's title
- •[VSCode] Fixed a terminal session's diff showing the previous proposed edit after you typed in it and Claude edited the same file again
- •[VSCode] Fixed Escape also stopping Claude's response when it closes the feedback or "Build a custom style" dialog, the @-mention menu, the model, mode or "+" menu, or another popup
Changed36 changes
- •Changed some pre-started background sessions to be discarded after an account change
- •Changed a workflow paused at a usage limit in the terminal to stay paused after a login, until the earlier login returns or you type a prompt
- •Changed
ExitWorktreeto ask before removing a worktree that may hold unsaved work; refused in don't-ask mode or with nobody to answer, unless an allow rule, auto or bypass permissions mode allows it - •Changed
claude mcp add --scope projectto stop, instead of overwriting the file, when.mcp.jsonlists its servers at the top level with nomcpServerskey - •Changed the arrow keys on most permission prompts to stop at No instead of wrapping around; a number past the last answer moves to No
- •Changed path checks to refuse some symbolic links
- •Changed what counts as inside a working directory, so some paths now ask for permission
- •Changed
permissions.blockReadsOutsideWorkingDirectoriesto ask about more Bash commands in bypass and auto modes, and to deny some in auto mode - •Changed
permissions.blockReadsOutsideWorkingDirectoriesto refuse more Bash commands that name a path under a Read or Edit deny rule, where it used to ask - •Changed auto mode's notice about falling back to billed classifier requests to say that an upcoming release removes the fallback; each action it would have checked will be asked about or denied
- •Changed auto mode to ignore more allow rules that run any package, like
Bash(pnpm dlx *), and path or version forms of ones it already ignored (/usr/bin/npm run:*); the safety check decides those - •Changed
/sandboxand most/configvalue lists to be unnumbered outside screen reader mode; use the arrow keys and Enter - •Changed Bash commands whose variables expand to very long text to be denied, with a message that says to use shorter values or a file
- •Changed the PowerShell tool to ask before one more command, even under a rule naming it; if nothing answers, it's refused unless a whole-tool rule, auto mode or bypass permissions mode allows it
- •Changed a subagent resumed by a sibling's message to follow the session's permission settings; it may now ask, or be refused where nobody can answer
- •Changed
--worktreewith a relative--add-dirbeside the launch folder to give the Bash sandbox that folder, not one beside the worktree - •Changed some
--worktreestarts with a relative--add-dirabove the launch folder, such as.., to give the Bash sandbox, and a--bgsession, only the worktree - •Changed Claude in Chrome to refuse uploading some credential files; attach those to the page yourself
- •Changed artifact approval in organizations that require it for each new artifact: an artifact that only a plugin created or allowed can be refused
- •Changed sessions with nobody to ask to refuse a new artifact at once, with no permission prompt, in organizations that require approval of each one
- •Changed the Artifact tool to refuse calls once settings turn Artifacts off, in sessions already running too
- •Changed the Artifact publish prompt to stop offering "don't ask again" in subagents and after a background task result, someone else's message or a compaction
- •Changed
claude plugin evalto keep its deny rules over a plugin's permission hook, and to flag calls the hook let through - •Changed MCP server logs to record the mode, action, and field names of elicitation requests and hook answers, not their full contents
- •Changed most prompts to ignore answers other than Esc for a moment after resuming with
fg - •Changed Code Mode to no longer refuse to start when an installed mod hooks tool calls; an administrator can still keep Code Mode off in managed settings
- •Changed subagents launched without a model to stay on the model they started on when resumed, including after
/model - •Changed the first subagent on a model to wait up to 1.5 seconds (10 in
claude -p) for that model's settings from Anthropic, instead of starting without them - •Changed restarted background subagents, and turns that start by themselves, to wait for plugins to load
- •Changed prompt history to leave out most launch prompts of sessions that another Claude Code session started, such as
claude --bgrun by Claude - •Changed subagent progress summaries in terminal sessions on Amazon Bedrock, Google Vertex AI and Microsoft Foundry to be written from short notes, not the whole conversation, using far fewer tokens
- •Changed non-interactive (
-p) mode to run fewer git commands before the first request - •Changed first-run setup to skip terminal setup in remote VS Code, Cursor and Devin Desktop sessions, where it cannot change settings
- •Changed fullscreen text selection to leave out the glyph of system, thinking and inbound message lines
- •Changed Anthropic-hosted cloud sessions to ignore more of a repository's flag and plugin delivery settings; its
CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFICnow acts at most asDISABLE_TELEMETRY - •[VSCode] Changed a chat edit's diff to stay open and keep asking for approval when a terminal session in the same window sends a prompt
Removed1 change
- •[VSCode] Removed unused tools from the IDE connection (openFile, saveDocument, getOpenEditors and related)