Claude Code can now use the claude.ai sign-in passed over by the desktop app that started it. That lent sign-in works like CLAUDE_CODE_OAUTH_TOKEN, but plugins cannot use it. You can turn it off by setting CLAUDE_CODE_DISABLE_LAUNCHER_SIGN_IN in the environment or in managed settings. On native Windows, the new claude sandbox uninstall command removes the sandbox account, group, stored password and network filters. Programs using the SDK can now list cloud sessions, fetch one and read its transcript. In VS Code, Team and Enterprise members who hit their spend limit can get a "Request more" button that notifies their admins.
Several features are in the build but not switched on yet. A list of subagents that ran earlier in a session appears only when CLAUDE_CODE_SUBAGENT_HISTORY is set or it is switched on remotely. Resuming an interrupted remote turn with CLAUDE_CODE_RESUME_INTERRUPTED_TURN can now queue an urgent reminder for Claude when something was left unresolved. A check for whether the macOS sandbox allows local test servers exists, but nothing uses it yet. A few new remote switches are registered with no visible purpose so far.
Among the fixes, MCP tool calls are no longer retried after a session expires unless they surely did not run or are safe to repeat. Through an HTTPS proxy, Claude Code now checks the certificate of the site it is reaching, not the proxy. Sandbox setup without a terminal now gives up 150 seconds after Claude Code started instead of waiting forever. A resumed subagent that the main conversation is waiting on now shows its permission prompts. CLAUDE_CODE_ADOPT_UNDERIVABLE_PARKED_PERMISSION is removed and no longer has any effect.
Written by our agent from the shipped bundle, not by Anthropic.
[1m] handling was removedSessions & agentsSelf-hosted runners get a --diff-finds-nested-repository mode, --runner-declares, CLAUDE_CODE_IGNORE_PERSISTED_TRUST and options to update the binary they launch
New SDK requests list cloud sessions and fetch one session or its transcript, with clear refusals when they are not allowed
Sessions & agentsThe bundled Claude Test plugin adds an author agent with a claude_test_write tool, limits its explorer and adds new helper messages
With CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST, a supplied OAuth token now wins over host management, and a new path accepts a sign-in token from the desktop app
Permissions & safetyAuto mode gains a held variant of compact mode, chosen when CLAUDE_CODE_AUTO_MODE_THREAD_ASK_HELD is set or a server flag is on
Want the reasoning? Read walks the 31 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.
Self-hosted runners get a --diff-finds-nested-repository mode, --runner-declares, CLAUDE_CODE_IGNORE_PERSISTED_TRUST and options to update the binary they launch
A new adminRequestOffer lets Team/Enterprise members hitting their own spend limit send a 'Request more' ask to their admin from VS Code
With CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST, a supplied OAuth token now wins over host management, and a new path accepts a sign-in token from the desktop app
Setting CLAUDE_CODE_DISABLE_LAUNCHER_SIGN_IN, in the environment or in managed settings, turns off the launcher sign-in
Unclear What the launcher sign-in does, and whether it runs by default, is not established.
A new policyOnlyLeads result in managed settings merging can override CLAUDE_CODE_DISABLE_ADMIN_ENV_UNION and keep admin env blocks merged
Unclear How policyOnlyLeads gets set in a managed policy is not stated.
A workspace configuration with no base_url now uses a default claude.googleapis.com address built from its project, location and workspace
The self-hosted runner's checkout hook can now be given a time limit with --checkout-hook-timeout-min, and is stopped when it runs over
Unclear Whether there is a default time limit when --checkout-hook-timeout-min is not set is not settled.
Telemetry exporters can now ignore OTEL_EXPORTER_OTLP_HEADERS and use only the headers given in configuration
Unclear It is not clear when the exporters are set to use only configured headers, or whether that is the default.
What would fix it?
Smaller changes and internals, grouped as the pipeline found them. Nothing is dropped, it is only further down.
10 more of these are in What probably matters to you, above.
When Claude Code serves its tools to another app over MCP, it can apply the repository's permission rules and refuse calls if they cannot be read
Unclear It is not clear which apps send the request that turns on this check.
Claude Code now refuses some changes to environment values, keeping them unless they came from its starting environment or from itself
Unclear Which environment variables this applies to, and what triggers the message, is not clear.
The Google Cloud client now raises its "No workspace ID found" error when a request is sent, not when the client is created
When forceLoginOrgUUID pins an organization, Claude Code now also checks a sign-in provided by the desktop app
After an admin grants a request for usage credits, the consent dialog checks the credit status again and continues without a manual retry
Unclear It is not clear whether the server currently sends the granted outcome that this flow depends on.
If your admin's request for more usage comes back pre-approved, Claude Code shows your new limit and lets your next message go through
Unclear Whether the server ever sends back a pre-approved grant is not known.
Self-hosted runners now warn when Claude Code's deny list leaves certificates out of the trust file built for Anthropic-managed git
Messages about switching models now say whether your organization's usage credits are off, capped or used up, or tell you to run /model
Claude Code now uses CLAUDE_CODE_ORGANIZATION_UUID to spot an organisation change when sign-in is managed for it
Unclear Exactly which managed sign-in setups trigger this check is not settled.
When a runner resets its git setup for a session, it now writes a git ignore rule so .claude/settings.local.json is not committed by accident
Claude Code now validates your organization's extra certificates for the agent proxy and drops any bad one instead of failing on the whole set
After you publish a plugin, Claude Code gives you a link to send colleagues and explains how they add your organization's library under /plugin
NO_PROXY is filtered out of the proxy-derived passthrough names and now appears in a separate list alongside SHELL and TRACEPARENT
Unclear It is not clear which programs this proxy variable list is passed to.
When fetching managed settings fails but saved restrictions still apply, Claude Code now says so and tells you to run claude auth logout to clear them
Disabling all plugins now leaves policy-enforced plugins alone and says when --settings keeps plugins on for this session
Changing a plugin your organization's policy turns on is now refused, and a plugin kept on by --settings is shown as still enabled this session
ANTHROPIC_AUTH_TOKEN is sent to a custom address#Claude Code dropped one check that could stop ANTHROPIC_AUTH_TOKEN from being sent to a matching ANTHROPIC_BASE_URL
Unclear It is not stated which setups the removed check used to exclude.
On a self-hosted runner, the checkout hook now runs with a time limit, using a built-in default when none is set
Unclear It is unclear whether you can set the checkout hook timeout yourself through a flag, setting or environment variable.
When fetching remote policy settings fails but a cached copy exists, the status now says the cached policy's restrictions still apply
When the runner cannot write its certificate bundle or find system certificates, the error now mentions a deny-list check and suggests --log-level debug
When managed settings fail to load because of a sign-in problem, the message tells you to run claude auth login to sign in again
Unclear It is not known what condition decides whether this hint is shown, so some users may see a different hint.
Through an HTTPS proxy, Claude Code checks the certificate against the site it is reaching, not against the proxy
2 more of these are in What probably matters to you, above.
Two new host-controlled environment variables, CLAUDE_CODE_DIFF_COPY_ROOT and CLAUDE_CODE_FOUND_REPOSITORY_GIT, are added to Claude Code's protected set
Unclear Whether setting these variables yourself is blocked, allowed or passed through is not clear.
Claude Code now accepts "organization" as a scope value, alongside service, channel and group_pool
Unclear It is not clear what an "organization" scope applies to.
Claude Code now treats CLAUDE_RUNNER_UPDATE_BIN and CLAUDE_RUNNER_ACTIVITY_FD like its other remote session variables
When managed policy settings come from a remote source, Claude Code now treats them as controlled by a machine administrator
The message shown when an organization reaches its usage credit cap now carries the reason code org_cap_reached
The reply saying your organization already has unlimited usage credits is now labelled as such, and error replies can name a model
When you go over a rate limit that applies to the whole organisation, the overage report now leaves out the scope of the limit
Claude Code now sends usage data about each permission decision, recording what kind of rule or check made it
When metrics are sent over OpenTelemetry by gRPC or HTTP protobuf, Claude Code now prepares an extra resource before creating the exporter
Unclear It is not known what the extra step does or whether exported metrics look any different.
Published verbatim by Anthropic for v2.1.307. 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 43 bullets, 7 name something an entry on this page also names, 17 name something no entry here does, and 19 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.
/claude-api api-version to move Claude API code to API version 2026-10-21
No entry names this claude_code.safety_event OpenTelemetry event for each tool call a permission rule, auto mode, a safety check, a hook or the sandbox stopped, prompted or sent back
No entry names this CLAUDE_CODE_DISABLE_1M_CONTEXT is set and the model is an alias with the [1m] suffix, such as opus[1m]
Probably model-context-window-logic-reworked-removing-the-1m-beta-as prompt-caching-scope beta header being sent behind custom ANTHROPIC_BASE_URL gateways and on Foundry, where it has no effect
Probably auth-token-forwarding-to-custom-anthropic-base-url-simplifie claude -p on macOS while the login keychain was locked; they now say why, and the next run after an unlock connects without a new sign-in
No entry names this /autocompact in cloud sessions going back to the default window after the session restarted
No entry names this /clear sometimes coming back when a cloud or self-hosted runner session restarted
Probably clear-can-withdraw-a-resume-checkpoint-from-the-transcript #100474[BUG] Self-hosted runner: resumed session comes back in plan mode although the session wrapper passes --permission-mode auto Open
CLAUDE_STREAM_FIRST_BYTE_TIMEOUT_MS being ignored in Claude apps gateway sessions
No entry names this OTEL_EXPORTER_OTLP_HEADERS is set
Probably otlp-exporters-can-strip-header-env-vars-during-construction #98873[BUG] Claude Desktop Code-tab sessions send an invalid bearer on OTLP exports to the Claude apps gateway (invalid_token), while Cowork from the same Desktop succeeds Closed
/permissions > Recently denied not showing the denied shell command, and auto mode's local classifier ignoring an approval from there when it checks a retried command; approving a row now names the command, not its description
No entry names this #101912[BUG] Read-only Bash search denied as Self-Modification again after native /permissions retry approval Open
#98834[Bug] Permission approval not applied: migration remains denied despite explicit approval Open
/help and the / command menu showing long model-facing descriptions for bundled skills such as /claude-api instead of their short descriptions
No entry names this setModel(), and apps built on it, being refused when the API took more than 5 seconds to confirm the model; Claude Code now waits up to 15 seconds
No entry names this --use-anthropic-git-proxy committing a .claude/settings.local.json left in the clone by an earlier session
Probably plugin-ui-labels-a-built-in-marketplace-and-plugin-disable, runner-git-proxy-sanitize-writes-an-ignore-rule-for-settings axScreenReader setting and CLAUDE_AX_SCREEN_READER in a settings env block to apply only from user, managed or --settings settings (since 2.1.305)
Probably plugin-disable-all-now-accounts-for-policy-managed-plugins-a, plugins-policy-enabled-plugins-dependency-closure-and-se --checkout-hook-timeout-min or set it to 0
Probably self-hosted-runner-gains-diff-finds-nested-repository-supp, checkout-hook-runner-process-tree-stop-timeout-and-pipe-ho [runner:warn] line gives the number left out
No entry names this NODE_EXTRA_CA_CERTS is set only in ~/.claude/settings.json; it now also follows CLAUDE_CODE_CERT_STORE
No entry names this NODE_EXTRA_CA_CERTS file named in the environment or in user settings
No entry names this @claude review stop (also off and pause) to Code Review, ending an @claude review always subscription on a pull request without starting a new review
No entry names this A model matched these bullets to the GitHub issues they fix, so a link can be wrong.
1 of 29 tool descriptions changed.
Claude Code, interactive mode
1267 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 52 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?