You can now turn off MCP task support by setting CLAUDE_CODE_DISABLE_MCP_TASKS. This release has 440 entries, and 284 of them are usable today. Accounts offered Life Sciences use cases get a new /use-case command to pick one. That choice is saved for later sessions. A new app:closeSession shortcut action lets you bind a key to close a session shown under session tabs. Programs that launch Claude Code can pass working directories exactly as given with the new permissions.workingDirectoriesAsGiven setting.
There are 12 entries in the build that are not switched on yet. A Wrap up tool would let Claude end a turn with a short recap and up to two next-step buttons. Claude Code now tracks messages for taking back a sent message with Esc, but the take-back does nothing yet. Hooks of type agent and mcp_tool can be read, but a remote allow list keeps them off and is empty by default. A spot is reserved for a live preview sharing dialog, with no way to open it yet.
Updates on macOS no longer delete the app bundle a running session is using. Saving settings no longer overwrites a config file that appeared while Claude Code was creating its own. Cancelling the theme picker no longer quits Claude Code. SDK hooks set to block on failure now stop the action as intended. Reading an unchanged file again no longer returns a short "file unchanged" note. The CLAUDE_CODE_LAZY_ENV_GETTERS environment variable is no longer recognised.
Written by our agent from the shipped bundle, not by Anthropic.
Adds CLAUDE_CODE_DISABLE_SUBAGENT_HANDBACK and CLAUDE_CODE_DEEP_TWILIGHT, and lists PARSED_WILLOW and DAPPER_CUPCAKE in more allowlists
ExtensionsA new ui.backdrop function lets plugins draw a blurred, tinted backdrop, and connecting clients can say they draw a Backdrop
ExtensionsClaude Code now has an app:closeSession shortcut action and a SessionTabs keybinding context for closing a session shown under session tabs
InterfaceRemote sessions gain new CLAUDE_CODE_* settings, such as a stall-check interval and a slow-skills watch, and CLAUDE_CODE_LAZY_ENV_GETTERS is dropped
/use-case command to choose a Life Sciences use caseAccounts offered Life Sciences use cases get a /use-case command and a startup dialog to pick one, saved for later sessions
Want the reasoning? Read walks the 51 entries that probably matter to you, each one opening to what changed and why.
Read this release → Every row →Anything you can use today, anything that visibly changes, and anything worth poking at. One line each, open for detail.
Claude can attach local files to Gmail drafts and messages with your approval, and HIPAA or ZDR policies can block connector file sending
Unclear Whether Gmail attachments are switched on when the server sends nothing is not known.
Remote sessions gain new CLAUDE_CODE_* settings, such as a stall-check interval and a slow-skills watch, and CLAUDE_CODE_LAZY_ENV_GETTERS is dropped
Unclear It is not clear what the check does once it is turned on.
/use-case command to choose a Life Sciences use case#Accounts offered Life Sciences use cases get a /use-case command and a startup dialog to pick one, saved for later sessions
CLAUDE_CODE_PROGRAM_USE_CASE_ID setting labels requests with a use case#Set CLAUDE_CODE_PROGRAM_USE_CASE_ID and Claude Code can attach that use case ID to its requests, if the host accepts it
Unclear It is not clear whether the host feature check is switched on, so the ID may not be sent.
File sends through connectors get a connectorFileSend permission that bypass mode does not skip, with a dialog listing the files and refusing unreadable lists
Unclear Which connectors bring up this dialog, and whether it is switched on for everyone, is not stated.
Claude Code gained an internal setting marking a session as a child of a host-managed runner, off by default
Unclear Nothing shows what turns this setting on or what it changes once on.
mcp_authenticate gains redirectUriOnly, which fails sign-in instead of falling back to a localhost listener when the custom redirect is rejected
Self-hosted runners now skip trusting the workspace when a new server-config check passes, and the --trust-workspace help describes a stricter gate
Unclear It is not clear what condition makes a self-hosted runner skip saving trust.
For some tools, an allow rule ending in (*) or () now means any input, behind a remote switch that is on unless turned off
Unclear Which tools this applies to, and how the old reading differs in practice, is not stated.
What would fix it?
Smaller changes and internals, grouped as the pipeline found them. Nothing is dropped, it is only further down.
14 more of these are in What probably matters to you, above.
Claude Code can report its sandbox state to a host app, including support, locks, restrictions and which managed-settings sources apply
Admins can block /remote-control through managed settings, its status message no longer carries an upgrade prompt, and a follow-on tip is switchable
The gateway now saves each developer's identity provider groups for the day, so cost reports can show spend by group
A label listing which plans can use a feature now reads 'Individual, Team, or Enterprise' instead of 'Pro, Max, Team, or Enterprise'
Self-hosted runners pass agentProxyUrl to the server, park finished code-review sessions, and report their capabilities differently
Claude Code now keeps system cross-certificates a server's certificate chain needs instead of dropping every looping one, and adds an opt-out
Unclear It is not settled exactly what setting CLAUDE_CODE_DISABLE_LOOPED_CROSS_CERT_DROP switches off.
Self-hosted runners now hand CLAUDE_CODE_EXIT_AFTER_STOP_DELAY from the server to sessions and gain checks for restricted and host-managed runs
Unclear It is not clear what being marked as a host-managed runner child changes for a session.
The SDK warning sent when a requested model is refused now carries a model_restriction field naming both models and when it happened
Behind a server switch, the sandbox no longer follows a write-protected symlink that points at another host or cannot be safely checked
Unclear What this switch does when the server sends nothing is not settled, so it is unclear whether the new handling applies to you by default.
Reports about MCP servers in the SDK now leave out the server's host name unless the worker is known to be hosted by Anthropic
Unclear Only the field's description is known to have changed, so it is not clear whether the host name is actually withheld in practice.
Claude Code adds a name for a desktop notice about remotely managed settings, and errors that hold back a saved login now keep a reason
Unclear It is not clear whether or when a desktop notice about remotely managed settings is actually shown to users.
Before a Claude in Chrome action runs, Claude Code now checks the site against your deny rules and refuses the action if one matches
If a request only succeeds without auto mode's safety header, Claude Code stops sending it and turns off the server-side action check
--managed-settings can now be kept out of the policy level#Settings given with --managed-settings may now be kept out of the policy level of settings, and Claude Code logs a warning when that happens
Unclear It is not stated when settings passed with --managed-settings are kept out of the policy level.
The onboarding guide tool no longer deletes your org's newest guide when no short_code is given; it lists your guides and asks which one
Unclear It is unclear whether the tool itself now behaves this way or only its description changed.
Through a proxy, OpenTelemetry exports now get their own connection per protocol, with a timeout from the OTLP settings, 10s by default and 30s at most
Four new error reasons explain when the proxy for outbound traffic is too busy or refuses connections, and tell you to run fewer downloads at once
ALL_PROXY is used and to proxy updates#Claude Code now treats ALL_PROXY differently when no other proxy variables are set and reapplies proxy settings when they change
Unclear It is not settled exactly how traffic is routed when only ALL_PROXY is set.
Claude Code can now skip settings files in added folders when the setting sources they belong to are not enabled
Unclear It is not clear whether this filtering is in use yet or depends on a switch.
Claude Code now warns at startup when an --allowedTools or permissions.allow entry repeats a rule that is always allowed already
Gateway connection failures now say whether the gateway's TLS certificate could not be verified, or suggest joining your organization's network
On certain certificate errors, Claude Code reads the server's certificate chain and restores a missing system certificate if one is needed
Unclear It is not clear whether this repair is switched on for everyone or depends on a setting.
Claude Code now also checks a shell command's raw text against your deny and ask rules, so a match blocks it or asks you first
Unclear The further condition that decides whether this text check runs is not stated.
Claude Code's proxy troubleshooting guidance now covers 429 and 503 responses and suggests running fewer downloads at once
Claude Code's built-in gateway guide says a Bedrock 400 error reading exactly "Input is too long." must reach Claude Code unchanged
With CLAUDE_CODE_USE_FOUNDRY set, recognised errors are now attributed to Azure, as errors were already attributed to AWS or Google Cloud
Deleting a team onboarding guide that was already removed now reports it as already gone, and other failures show a clear error
10 more of these are in What probably matters to you, above.
The security prompt for organisation-managed settings now tracks whether approval is pending, withheld or settled
When the sandbox blocks a domain, it now notes whether a policy caused the block and checks both the original and resolved host
Published verbatim by Anthropic for v2.1.317. Text is unmodified from the upstream changelog. Everything else on this page came out of the bundle instead, which is why the two lists don't match.
Of these 87 bullets, 14 name something an entry on this page also names, 26 name something no entry here does, and 47 name nothing specific enough to line up either way. The pairings are made on names both sides wrote down, a flag or a setting or a slash command, so read one as probably the same thing rather than as a fact, and read the middle number as candidates rather than as a miss count.
/schedule when a new cloud scheduled task gets connectors you did not ask for, with how to remove them
No entry names this onFailure: "block" for Agent SDK hook callbacks, so a callback that fails blocks the action instead of letting it run
No entry names this anthropic.plan, anthropic.seat_type, anthropic.provider and anthropic.custom_base_url to OTel metrics, events and spans
No entry names this GET /v1/organizations/analytics/cost, for reading past spend over a date range in total, per developer, per day or per IdP group
No entry names this admin: set, kept for admin.identity_retention_days, which the cost report groups by
No entry names this CLAUDE_CODE_DISABLE_NESTED_SESSION_ID: set it to 1 on a self-hosted runner to have claude -p run inside a session use that session's ID and transcript, as in earlier versions
Probably new-session-writes-lost-system-message-and-full-disk-exit-ha, nested-session-id-opt-out-env-var-added claude auth status exiting before a slow token refresh was saved, which could sign you out on the next run
No entry names this #95822Short-lived commands (`claude auth status`, `claude --bg …`) start an OAuth refresh at init and exit without saving it, leaving the profile with a spent refresh token Open
effortLevel setting being ignored by sessions that an app starts ahead of time and then opens in the project, such as new sessions in the desktop app's Code tab
No entry names this #104336[BUG] Desktop app (Windows): Code-tab sessions sometimes start at Medium effort, ignoring the High pick and the project's effortLevel Open
#93735Project-scope effortLevel in .claude/settings.json is never applied in desktop-app (Code tab) sessions; effective effort varies per session with no settings change Open
claude --from-pr reporting "No conversations found" in projects with many sessions when the linked session was older than the first page
No entry names this /loop wakeups sometimes not being scheduled when Claude left a field out of its request
No entry names this /schedule leaving a cloud scheduled task's next run time and link out of its results after creating or updating it
No entry names this claude -p exiting 0 when a full disk or quota lost its transcript or ~/.claude.json writes; it now prints an error and, in text and json output, exits 1. Full NFS exports may be missed
Probably new-session-writes-lost-system-message-and-full-disk-exit-ha --setting-sources
Probably added-folder-plugins-follow-setting-sources, runner-passes-empty-setting-sources-when-the-arg-is-explic /team-onboarding guide when asked to delete one without naming which
No entry names this /team-onboarding guide was deleted when the server refused the delete
No entry names this AWS_BEARER_TOKEN_BEDROCK when their env config sets it to empty; the variable is now unset, so the server can use the machine's own AWS credentials
No entry names this DISABLE_PROMPT_CACHING_OPUS and DISABLE_PROMPT_CACHING_SONNET having no effect on [1m], other-region and undated spellings of the default model
Probably prompt-caching-disable-env-vars-now-compare-models-by-identi /artifacts and the Artifact tool's shared list showing no shared artifacts when you have 200 or more of your own
Probably get-artifacts-route-added-to-an-allow-list https:// endpoint through a proxy never being sent when they started while another export was still in progress
Probably only-https-origins-accepted-for-url-origin-helper, fetching-the-servers-certificate-chain-to-repair-tls-verifi http:// endpoint
No entry names this OTEL_EXPORTER_OTLP_TIMEOUT up to 30 seconds
Probably otlp-proxy-tunnel-agent-and-timeouts /remote-control answering "Unknown command" instead of saying that Remote Control is turned off by the disableRemoteControl setting
Probably remote-control-status-message-drops-upgradenudge, remote-control-slash-command-can-be-blocked-by-managed-polic claude -p run inside a cloud or self-hosted runner session sharing that session's ID: it wrote into the session's transcript, and a restart could resume the wrong conversation
Probably new-session-writes-lost-system-message-and-full-disk-exit-ha claude -p run inside a cloud or self-hosted runner session generating a title of its own and sending it to that session
Probably new-session-writes-lost-system-message-and-full-disk-exit-ha cloud_credential_error
No entry names this /design-sync to say up front when your design system has moved to Claude, and stop before building instead of failing at upload
Probably design-sync-messages-for-design-systems-that-moved-to-claud --chrome --debug) ahead of --resume
Probably resume-hint-can-include-launch-flags-file-writes-gain-creat plugin-authoring skill to offer once, after a mod you built works, to help share the mod
No entry names this /usage showing a developer's own spend limit as 100% used after their group's pooled budget ran out
No entry names this CLAUDE_CODE_RESUME_INTERRUPTED_TURN_MAX_AGE_MS
No entry names this claude remote-control a fork of "Name (fork)" is "Name (fork 2)"
Probably fork-name-fallback-for-session-titles-removed chat.fontSize is raised
No entry names this ultrathink not raising effort for its turn or showing its rainbow when telemetry is off
Nothing to match on claude remote-control, when you sent it within a minute of your previous message
No entry names this A model matched these bullets to the GitHub issues they fix, so a link can be wrong.
1 prompt changed.
Claude Code, interactive mode
6 prompt changes in this release could not be quoted from the build, so no entry on this page describes them.
263 documentation changes were recorded within 24 hours either side of this release, nearest first. The closest 12 are below. They're here because they happened near this release in time. That's not a claim that this release caused the edit, or that the page documents anything in it.
The 69 literal strings found in the bundle, with the number of entries that name each one. Picking one searches for it. A name is here because this build's code mentions it, which is not the same as it working or being finished.
What's wrong with this entry?