Claude docs changes for Oct, 21st 2026 [diff]
Executive Summary
- New API docs for user profiles (attribute requests to end customers so a safety enforcement action hits one profile, not your whole organization), a Verification Portal enrollment link, and beta organization webhooks for enforcement events
- Claude Code 2.1.305 adds
sandbox.allowNestedUserNamespaces, a smarter/usagewith one-key fixes (f), and a retry that keeps requests working when a gateway rejects tool search - Agent view gains
/model,/effortand/fastfor dispatched sessions, a← agentsfooter hint,/resumeto bring back past sessions, and guidance for keeping sessions alive after the supervisor stops - New Code Review features:
@fileincludes inREVIEW.md,@claude review always|stopcomment commands, and a severity line you can parse in CI - Large new troubleshooting coverage in the errors reference, plus Agent SDK docs for MCP startup waits,
StructuredOutputtool calls and context usage
New Claude Code versions
2.1.305
New features
- Added
sandbox.allowNestedUserNamespacesso sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections - Added
CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MSso unattended retry mode notices a usage limit that was lifted before its reset - Added a "Running start-up hooks" spinner status in VS Code while SessionStart or Setup hooks run
- Claude Tag admin Add place search now includes public Slack channels Claude hasn't joined
Existing feature improvements
/usage: each warning is now a one-line fix naming its source, andfapplies the fixes; the same fixes appear in VS Code and/doctor- MCP consent dialogs make it less likely that an Enter meant for the prompt is taken as Accept
- A mod's
Imagenow draws in iTerm2 3.5+ with fullscreen rendering; a mod's docked pane stays within 45% of terminal width - Remote Control spawn-mode messages are clearer about saved modes
- Deleting a self-hosted environment now explains what blocks the delete and what it affects
allowedMcpServersno longer filtersmanaged-mcp.jsonstdio servers that use${VAR}only inenv(usedeniedMcpServersto keep one off)- Plugins mounted by path by Claude Desktop no longer keep their
allowed-toolswhenallowManagedPermissionRulesOnlyis set /artifactsdelete confirmation now uses 1/Enter to keep, 2 to delete, Esc to cancel- Code Review re-reviews no longer open with LGTM while earlier blocking findings remain open
Major bug fixes
- Fixed every request failing on Vertex, Bedrock and other providers when an endpoint or gateway rejects tool search (a 2.1.304 regression): Claude Code now retries without it
- Fixed
/effortand/autocompactsettings not applying when the model name differed from amodelOverridesvalue by case or a[1m]tag - Fixed new worktrees in a bare repository starting from local HEAD instead of the default branch
- Fixed Bash on a full disk failing with a raw
ENOSPCpath; the error now says the disk is full and that nothing ran - Fixed an MCP server passed by a cloud session or SDK
setMcpServersbeing replaced by a same-named server from user settings - Fixed Workflow resume re-running completed
pipeline()andparallel()agents - Fixed self-hosted runner regressions: start scripts failing with
Resource temporarily unavailable, repository access failing withGIT_CONFIGcredential helpers, and spawn-runner hooks falsely reported as timed out - Fixed Code Review sometimes not reviewing the newest commit when several pushes landed during a review
2.1.306
Major bug fixes
- Fixed
claude -pinside cloud sessions reporting "Not logged in" when started without the session's environment variables - Fixed an API error being replaced by "prompt is too long", and an unneeded compaction, in sessions with many MCP tools
Claude Code changes
Note: many files were also reformatted today (notes and tips wrapped in > [!NOTE] callouts, numbered steps rendered as bold lines, diagrams as images). Those formatting-only changes are not listed.
New Documents
None.
Changed documents
admin-setup [Source]
- Managed settings table now lists plist/registry policy and file-based managed locations per platform. [lines 46-47] [Source]
advisor [Source]
- An advisor model that ranks below the main model still starts the session, background or not. [line 82] [Source]
agent-sdk/mcp [Source]
- Detailed rules for how long the first turn waits for MCP servers (stdio/HTTP/SSE servers, tool search, gateways, named servers,
permissionPromptToolName, in-process SDK servers). [lines 139-180] [Source] - New
CLAUDE_CODE_MCP_STARTUP_WAIT_MSsetting to choose the first-turn wait, andMCP_CONNECTION_NONBLOCKING=0/alwaysLoad: trueto make startup itself wait. [lines 147-179] [Source]
agent-sdk/hooks [Source]
agent-sdk/examples [Source]
- New "Fork a complete project" section pointing to the Claude for commerce reference implementation for shopping and merchant agents. [lines 19-22] [Source]
agent-sdk/permissions [Source]
- Allow rules accept tool-name globs only after a literal
mcp__<server>__prefix with a glob-free server segment. [line 77] [Source]
agent-sdk/python [Source]
- New
ClaudeSDKClient.get_context_usage()method returning the context window breakdown that/contextshows. [line 525] [Source] - Clarified
is_errorsemantics on success results and how to tell failures apart viastop_reason,terminal_reason, thensubtype. [lines 1682-1687] [Source]
agent-sdk/streaming-output [Source]
- Structured output with partial messages streams as unvalidated
input_json_deltachunks. [line 311] [Source]
agent-sdk/structured-outputs [Source]
- New section explaining the
StructuredOutputtool call that appears in the message stream, itstool_result, retries on schema mismatch, and why apps should hide it. [lines 359-369] [Source]
agent-sdk/subagents [Source]
skillspreloads at most the first 32 distinct names; subagent messages carryparent_tool_use_idand (TypeScript) agent identifiers. [line 144] [Source]
agent-sdk/tool-search [Source]
- Documents
ENABLE_TOOL_SEARCHvalues (unset,true,autowith a 10% context threshold) and their fallbacks. [lines 35-45] [Source]
agent-sdk/troubleshooting [Source]
- A
successresult can have nostructured_output; treat it as a failure, with causes (declined request, unsatisfiable schema). [lines 139-144] [Source]
agent-sdk/typescript [Source]
- New
getContextUsage()query method andSDKControlGetContextUsageResponsetype. [line 659] [Source] - New "What
readFile()can read" section,peermessage origin details, and a note thatStructuredOutputhas no exported input type.
agent-view [Source]
- Pressing
←on an empty prompt opens agent view; the footer shows← for agents, waiting counts, and finished counts. [lines 57-64] [Source] - What happens to prompts and
!commands entered as a session moves to the background. [lines 287-296] [Source] - Bare
/resumein agent view brings back past sessions as background sessions. [lines 314-325] [Source] /model,/effortand/fastin the dispatch input set defaults for sessions you dispatch next. [lines 647-665] [Source]- Prompts containing
--bgare delivered as typed; ambiguous positions exit with an error. [lines 535-546] [Source] - New "Keep sessions running after the supervisor stops" section (one-minute window; run
claude agents) and stop-failure message table. [lines 847-858] [Source] - New
No LLM gatewaytroubleshooting entry and new version history rows (v2.1.295 to v2.1.299). [lines 990-999] [Source]
artifacts [Source]
- New
dkey in/artifactspermanently deletes an artifact you own. [line 97] [Source] - Compliance API endpoints for listing, fetching versions of, and deleting artifacts. [lines 424-428] [Source]
auto-mode-config [Source]
/auto-mode-setupnow has its own sections: what it reads, how to turn it off, and an "Unknown command" troubleshooting list; new "Edit rules from/permissions" section. [lines 158-210] [Source]
checkpointing [Source]
- Rewound messages can return if you exit before your next prompt, and how to remove them. [lines 43-46] [Source]
chrome [Source]
claude-apps-gateway-config [Source]
- Policy merge rules for deny-lists and hook arrays;
deniedModelsandavailableModelsMatchare now enforced by the gateway and CLI and filter the bootstrap model list.
claude-apps-gateway [Source]
- New "What's enforced on developers" heading and architecture diagram.
claude-code-on-the-web [Source]
claude --cloudclones the GitHub remote at your branch, not your local checkout; new "Branch is not on GitHub" troubleshooting;/configand subagent notes. [lines 96] [Source]
claude-directory [Source]
- The interactive explorer content was removed from the page, leaving the file reference table and a "State files to keep" section. [lines 4-49] [Source]
claude-projects [Source]
- New table of what cloud threads pick up from repositories:
CLAUDE.mdand rules load; skills, agents,.mcp.json, plugins, permission rules, hooks andenvfrom.claude/settings.jsondo not. [lines 330-340] [Source] - Repositories can be added to a project or added by a thread on demand; approvals cover only that thread.
claude-platform-on-aws [Source]
- Page shortened; the first ~170 lines of introductory content were removed. [lines 4-11] [Source]
cli-reference [Source]
- Updated
--name/-nand--permission-prompt-toolflag descriptions. [lines 105-110] [Source]
cloud-environments [Source]
- New "Add network secrets" section: adding a secret (including on Team plans without an admin role), which requests get it, and which never do.
- Hooks and setup scripts behave differently in project cloud threads.
code-review-customize [Source]
- New "Include other files in REVIEW.md":
@review-security.md-style lines pull root-level files in (max eight files, 150,000 bytes combined, 64 links), with protected-branch rules and a checklist when an include isn't applied.
code-review-pull-requests [Source]
- Parse the
bughunter-severityHTML comment from the check run Details withghand jq to gate merges in CI. - New comment commands table:
@claude review,@claude review always,@claude review stop(alsooff/pause), and conditions for them to take effect.
code-review-troubleshooting [Source]
- New check-run messages about
REVIEW.mdbeing skipped because of links or modified files.
commands [Source]
- Added
/auto-mode-setup,/claude-apisubcommands,/design consentand/design revoke,/design-loginand the/design-syncskill.
costs [Source]
/usageon paid plans shows a plan-usage breakdown with recommendations; pressingfapplies those it can (/effortchanges run directly, others become a prompt), with a table of row shapes.
cross-session-messaging [Source]
- Replies from other machines and cloud sessions,
dialogExpiry, and the session inbox socket.
data-usage [Source]
- Telemetry table now lists defaults and opt-out variables per provider, including error reports,
/feedback, surveys and the WebFetch domain check.
desktop [Source]
- Describes the Code tab, auto mode availability, the session details panel with a Context card,
/context, and Dispatch/Cowork links. (The same text was added todesktop-changelog.)
desktop-linux [Source]
- Cowork on Linux requirements (KVM, QEMU, UEFI firmware, virtiofsd), sign-in, and a root/
--no-sandboxerror.
discover-plugins [Source]
- New sections on plugins from your claude.ai account, adding a marketplace from claude.ai, and JetBrains/non-interactive/SDK behavior.
env-vars [Source]
- New:
CLAUDE_CODE_DISABLE_BG_EXIT_HANDOFF,CLAUDE_CODE_FORCE_TERMINAL_IMAGES,CLAUDE_CODE_MCP_STARTUP_WAIT_MS,CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS; updatedAPI_TIMEOUT_MS(0 turns off request timeout),ENABLE_TOOL_SEARCH,ENABLE_PROMPT_CACHING_1H,CLAUDE_CODE_MAX_RETRIES.
errors [Source]
- Many new entries: local sign-in listener failures, release verification and auto-update failures, 128 MB image read limit, disk full (ENOSPC/EDQUOT), artifact publish refusals,
No LLM gateway, shutdown-approval refusals,/feedbackdisabled by policy, plugin path/manifest escape errors, and--bgflag ambiguity. - New gateway guidance for
400errors namingcontext_managementordefer_loading(update to v2.1.304+/v2.1.305 or forward theanthropic-betaheader), plus configuration warnings forCLAUDE_CODE_AUTO_COMPACT_WINDOWand permission rules that never match.
feature-availability [Source]
- Footnotes for cloud-session seat requirements, ZDR enablement, cross-session messaging requirements; new "Partial support" entry for Desktop on 3P.
headless [Source]
- A run without valid structured output has no
structured_outputfield.
hooks [Source]
permissionDecision: "defer"(non-interactive-p): ends the turn with the tool pending and resumes later; no timeout, falls back if tool unavailable, only works with a single tool call per turn.- New
plugin_notificationnotification type. (Same changes inhooks-guide.)
interactive-mode [Source]
- Press
Upto recover a draft cleared withCtrl+C(ten most recent drafts kept).
keybindings [Source]
- New
settings:fixUsageaction (F); warning about a space next to+in key strings.
llm-gateway-protocol [Source]
- Beta body fields and their beta headers must travel together; new automatic retries (thinking type, mid-conversation system messages,
cache_control,context_management) and retry without tool search on v2.1.305+.
mcp [Source]
- Tool search is on by default with
ENABLE_TOOL_SEARCHtable;WaitForMcpServersused without tool search;claude mcp getredacts plugin stdio/WebSocket values; gateway tool-search retry.
model-config [Source]
- Enterprise admins can cap effort level per model per role; capped levels are hidden from
/effort.
monitoring-usage [Source]
- Documents the
tool.outputspan event and a caveat for loweringOTEL_LOGRECORD_ATTRIBUTE_COUNT_LIMIT.
permission-modes [Source]
- Background sessions require bypass-permissions acceptance recorded in user or managed settings; new "Bypass permissions was requested at launch and ignored" notice.
permissions [Source]
- MCP allow-rule glob rules, a startup warning for deny/ask rules matching no tool,
findwith write/exec actions, andReaddeny rules covering@-mentions, pasted images, changed files and IDE context.
plugins/mods/api [Source]
- New
$.ui.notify(text)for terminal notifications, with{ isSent, channel }/{ isSent: false, reason }results.
plugins/mods/events [Source]
- New
tool.checkguidance for approving or refusing tool calls and thee.isReadOnlyfield (v2.1.304+).
plugins/mods/gallery [Source]
Imageterminal support (kitty, Ghostty, iTerm2 3.5+ in fullscreen) and fallbacks.
plugins/troubleshooting [Source]
- Steps to fix
Version: unknownfor git-sourced plugins.
remote-control [Source]
- Saved spawn mode behavior (
wkey,--spawn), cross-session messages over the connection, and auto-connect withDISABLE_TELEMETRY/DO_NOT_TRACK.
sandboxing [Source]
- IPv6 allow/deny spelling, symlinked denied paths on macOS, and a user-settings fallback when no project folder is writable.
self-hosted-environments-configuration [Source]
- New
CLAUDE_RUNNER_ACCOUNT_ID; redirect output of background processes started byspawn-runnerhooks; settings/MCP/skills loading differences inside projects.
self-hosted-environments-deploy [Source]
- Git proxy behavior and new troubleshooting for
Resource temporarily unavailableandThis runner couldn't read.
settings-reference [Source]
- Idle compaction setting and
/configrow; locking thehookssurface (which hooks stop and which keep running); notification channel note.
settings [Source]
- Clarified precedence and which settings files cloud sessions and project threads read.
skills [Source]
- New
managed-agents-securesubcommand; project/nested skills are not loaded in project cloud threads; forked skills in dynamic workflows wait for results. (Mirrored inslash-commands.)
sub-agents [Source]
- Fallback-model warning line in subagent reports; resumed subagents can be messaged by name again (v2.1.299+).
tools-reference [Source]
- Read refuses images larger than 128 MB. [line 503] [Source]
- Web search limit applies per turn in
-pand the Agent SDK. [line 666] [Source]
troubleshoot-install [Source]
- New "Release verification failed" and "Auto-update failed" sections.
vs-code [Source]
- Fix for missing conversations with
claudeProcessWrapper(extension 2.1.304+),/tasksagent map hint, and screen reader status announcements. (Same inide-integrations.)
workflows [Source]
- Resume replay semantics: failed agents and every agent started after them run again.
worktrees [Source]
- Cleanup behavior when another branch is checked out in the worktree.
API changes
New Documents
api/organization/workspaces/rate_limits/update [Source]
Set Workspace Rate Limits: POST /v1/organizations/workspaces/{workspace_id}/rate_limits/{rate_limit_id} sets or clears rate-limit overrides for one group (integer sets, null clears; the lower of workspace and organization limit applies). A beta variant was added under api/beta/organization/workspaces/rate_limits/update.
manage-claude/organization-webhooks [Source]
Beta (webhooks-2026-10-07) Admin API for registering webhook endpoints (up to 32 per organization) that receive user_profile.enforcement_action_opened and user_profile.enforcement_action_resolved. Covers Standard Webhooks signing, retries, automatic disabling, secret rotation and error codes. Event delivery isn't live yet. Reference pages for list, create, retrieve, update, delete and regenerate signing secret were added under api/api/beta/organization/webhooks/.
manage-claude/user-profiles [Source]
Explains registering each end customer with POST /v1/user_profiles and sending the uprof_ ID in the anthropic-user-profile-id header so safety enforcement applies to one end customer instead of the organization. Profiles aren't billable. New endpoint reference pages (create, list, retrieve, update, delete) were added under api/api/user_profiles/ and beta equivalents.
manage-claude/user-profiles-verification-portal [Source]
How to create an enrollment link with POST /v1/user_profiles/{id}/action_urls so end customers can link their profile to their own organization in the Verification Portal, with examples in every SDK. Includes api/api/user_profiles/action_urls reference pages.
Changed documents
about-claude/models/optimizing-for-cost-and-intelligence [Source]
- At
xhighandmax, Claude Sonnet 5.5 can start its own rounds of review after finishing a task, using more time and tokens.
agents-and-tools/agent-skills/claude-api-skill [Source]
- New
managed-agents-securecheck that compares an agent's settings with the Managed Agents security guide using theantCLI.
agents-and-tools/mcp-connector [Source]
- MCP server
urlmust start withhttps://.
agents-and-tools/tool-use/web-search-tool [Source]
- Organization-level web search settings in the Console apply to Messages API requests and Managed Agents sessions, alongside request-level domain restrictions (also noted in
server-tools).
cli-sdks-libraries/overview [Source]
- New table of latest versions: ant CLI 1.44.0, Python 1.17.0, TypeScript 0.137.0, C# 12.60.0, Go 1.84.0, Java 2.75.0, PHP 0.61.0, Ruby 1.82.0, also available as JSON at
/docs/sdk-versions.json. Java dependency snippets across cloud-provider pages now use 2.75.0.
cli-sdks-libraries/cli/authentication [Source]
ANTHROPIC_API_KEYorANTHROPIC_AUTH_TOKENtakes precedence over every profile. (get-startedalso documents--no-browserfor remote hosts.)
manage-claude/claude-code-analytics-api [Source]
- Records cover only usage authenticated against your Console organization; subscription-plan usage isn't included, with alternatives (Enterprise Analytics API, claude.ai dashboard, OpenTelemetry).
manage-claude/cmek [Source]
- Lists features unavailable or not covered under CMEK (artifacts including Claude Design/Slides/Docs, some beta and research preview features, OpenTelemetry destination headers). The provider-specific CMEK pages warn that enabling CMEK is permanent; the AWS KMS page adds workspace-limiting key policy examples and compartment ID guidance, and the Claude Platform on AWS page adds
aws:SourceArnconditions.
manage-claude/inference-hooks [Source]
- Inference hooks are available only to Claude Enterprise organizations and require
organization:manage; system prompts and tool definitions are never included in governed requests. (Same notes in the configuration and endpoint pages;compliance-apilinks to them.)
manage-claude/opentelemetry/api [Source]
- Destinations can be added through the Admin API; documents gzip compression, retries, 5-second timeouts, auto-disable behavior and a failure-reason table. SDK page adds tracer setup for C#, Ruby and Java.
manage-claude/rate-limits-api [Source]
- Workspace limits can now be set via the Set Workspace Rate Limits endpoint; organization limits cannot. Unmatched model strings return 404.
manage-claude/admin-api [Source]
- Links to organization webhooks. (
api-and-data-retentionlists the new/v1/user_profilesendpoints.)