Claude docs changes for October 28th, 2026 [diff]

Executive Summary

  • New CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS environment variable (v2.1.311+) lets bypassPermissions mode run rm/rmdir on critical paths with no prompt, with startup notices and troubleshooting for when it has no effect
  • Claude Code 2.1.312 adds oidc.user_id_claim for the Claude apps gateway, click-to-send for queued messages, and caps concurrent prompt/agent hooks at 24 per session
  • Managed machines can now stop offering the keyless Console sign-in by deploying forceLoginOrgUUID; forceLoginMethod: "claudeai" also removes it
  • Mods docs gain Button variant, role and children, multi-line Input rows, and clearer settings.read hook guidance
  • Claude Desktop and claude.ai settings paths are now documented as Settings > Code or Settings > Claude Code, and cloud routines can pick an effort level

New Claude Code versions

2.1.312

New features

  • Added oidc.user_id_claim to the Claude apps gateway, to identify people by an id_token claim other than sub (such as Microsoft Entra ID's oid)
  • Added click to send: in fullscreen, clicking the "to send now" hint under a queued message sends it right away
  • [Cloud sessions] Added an effort level to the model picker when creating or editing a cloud routine
  • [Cloud sessions] Added a Bash editor with colors, line numbers and a Copy button for the setup script in cloud environment settings

Existing feature improvements

  • Improved the prompt's effort indicator: a mid-task change now says it may wait for your next message
  • Improved WebFetch errors in cloud sessions: an unresolvable host is explained as possibly outside the allowed network domains
  • Bedrock, Vertex, Foundry and Mantle now use the shorter system prompt for unrecognized model names (custom deployments, inference profile ARNs); set CLAUDE_CODE_SIMPLE_SYSTEM_PROMPT=0 to keep the full prompt
  • Automatic model switches after a flagged message now also cover unrecognized model names; set CLAUDE_CODE_DISABLE_REFUSAL_FALLBACK=1 to turn them off
  • Prompt and agent hooks now run at most 24 at a time per session (sub-agents included), plus at most 12 that have waited longer than their event's timeout; a timeout under 1 second counts as 1 second
  • A subagent's autoCompactWindow now lowers the window set by CLAUDE_CODE_AUTO_COMPACT_WINDOW
  • OpenTelemetry mcp_server.name now reports the real name of fixed-URL remote MCP servers declared by official-marketplace plugins; the claude_code.safety_event event is no longer sent
  • Usage limit messages now say "5-hour limit" instead of "session limit"
  • [Cloud sessions] Cloud sessions started from the CLI get names and branch names from the server
  • [Claude Tag] Slack retry notices now name the model in use or say rate limits were hit

Major bug fixes

  • Fixed managed settings and organization policy not being fetched after signing in from the VS Code extension
  • Fixed Claude overwriting a very large CLAUDE.md, rules file or @-included file after seeing only its start; Write now asks Claude to read it all or edit in place
  • Fixed per-directory and paths: skills not being found after a Bash cd deeper into a git repository
  • Fixed a command with an invalid name stopping all commands from loading, which could leave claude -p with no output
  • Fixed the Read tool sometimes failing on PDF pages ("pdftoppm failed") during old session file clean-up
  • Fixed the spinner, OpenTelemetry effort values and transcripts naming a newly picked effort level before the model applied it
  • [Code Review] Fixed Code Review reviewing an outdated commit when GitHub delivered a push event late
  • [Cloud sessions] Fixed resending an unchanged message after a failed send sometimes running it twice
  • [Claude Tag] Fixed Claude in Slack not replying in channels whose environment has network access set to None, and a channel's switch/settings resetting when a private channel goes public

Claude Code changes

New Documents

None.

Changed documents

admin-setup [Source]

  • Added a link to the new "Manage plugins for your organization" page for installing shared plugins through managed settings. [line 190] [Source]

agent-sdk/agent-loop [Source]

  • max_turns now explained as counting each tool-call turn plus one for the final text-only response; otherwise the run ends with an error_max_turns result and no final reply. [line 40] [Source]

agent-sdk/configuration [Source]

  • Switching to a model auto mode doesn't support moves the session to default mode. [line 160] [Source]

agent-sdk/hosting [Source]

  • Node.js requirement for the TypeScript SDK raised to 18.14+. [line 185] [Source]

agent-sdk/permissions [Source]

  • Pointer to the new section on turning off the critical-path removal prompt. [line 42] [Source]

agent-sdk/python [Source]

  • Task alias for the Agent tool is accepted only when the tool is available to the session. [line 2523] [Source]
  • allowAllUnixSockets also allows VM sockets (AF_VSOCK) on Linux. [line 3592] [Source]

agent-sdk/streaming-output [Source]

  • Clarified what a cut-off stream delivers: message_stop always arrives, content_block_stop arrives except for open tool calls, and message_delta may be missing after a dropped connection or non-streaming fallback. [lines 115-118] [Source]

agent-sdk/typescript [Source]

  • startup() keeps only the newest hook_progress message from SessionStart/Setup hooks and delivers held messages once you call .query(). [lines 104-105] [Source]
  • Returning allow with more than 4,096 updatedPermissions items is treated as invalid and denied. [line 1404] [Source]
  • agent_id behavior for nested subagents expanded. [line 1695] [Source]
  • maxTurns now links to the definition of a turn. [line 525] [Source]

agent-view [Source]

  • /resume in agent view no longer documented as needing v2.1.212+. [line 319] [Source]
  • /fork section split into subsections: prompting the copy, where the copy runs, and sessions that can't be forked. [lines 453-472] [Source]

authentication [Source]

  • forceLoginMethod: "claudeai" (or forceLoginOrgUUID) removes the keyless sign-in; "console" alone still allows it after a failed sign-in. [lines 126-127] [Source]
  • New section "Stop offering the keyless sign-in on managed machines", covering migration of keyless, environment/helper and claude.ai logins. [lines 140-149] [Source]

iam [Source]

claude-code-on-the-web [Source]

  • New troubleshooting section for files missing from the diff view (unpushed command-made changes, changes after the last push). [lines 263-271] [Source]
  • /config and sharing settings now point to Settings > Code or Settings > Claude Code (or Privacy). [lines 278-348] [Source]

web-quickstart [Source]

  • Notes that the diff against the base branch can leave out unpushed changes. [line 181] [Source]

claude-projects [Source]

  • Move to project renamed Continue in project throughout. [line 69] [Source]
  • New Keep this computer awake for Remote Control option and restructured recovery steps for a lost folder connection. [lines 274-278] [Source]

cloud-environments [Source]

  • Network secrets: on every plan you can add and delete secrets on your own environments; without an organization admin role, Team and Enterprise users get the shorter single-host form. [lines 98-135] [Source]

cross-session-messaging [Source]

  • Messages Claude hasn't received yet appear under Waiting to be delivered at the end of the transcript (v2.1.309+). [lines 173-175] [Source]

desktop [Source]

  • Settings paths updated to Settings > Code or Settings > Claude Code across the page. [line 68] [Source]
  • Computer use is enabled under This computer > System or Capabilities, depending on the Settings menu. [lines 351-359] [Source]
  • Connectors are managed via Customize > Connectors. [line 584] [Source]
  • Cloud diffs can leave out unpushed changes. [line 163] [Source]

desktop-changelog [Source]

  • Mirrors the desktop page updates (settings paths, computer use, connectors, cloud diff caveat). [line 68] [Source]

desktop-scheduled-tasks [Source]

  • Keep computer awake is under Settings > Desktop app or Settings > This computer > System. [line 134] [Source]

env-vars [Source]

  • New CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS: runs dangerous rm commands with no prompt in bypassPermissions mode. [line 290] [Source]
  • New CLAUDE_CODE_RESUME_SHOWS_CUT_OFF_CALLS: keeps interrupted tool calls, marked as cut off, when a resumed turn continues. [line 368] [Source]

errors [Source]

  • New entry "Feedback payload too large" with the fix (set Send transcript to no). [lines 2211-2222] [Source]
  • New entry "A command-line deny rule cannot be handed to a teammate intact" for split-pane agent teams; switch Teammate mode to in-process. [lines 4691-4703] [Source]
  • "Couldn't send feedback" now means the service didn't confirm receipt; treat the report as not received. [line 2191] [Source]

hooks [Source]

  • Clarified WorktreeCreate path resolution and rejection rules (relative paths, ./.. segments, symlinks). [lines 3195-3197] [Source]

headless [Source]

large-codebases [Source]

  • Local deny rules like Read(./**/vendor/**/*) anchor at the working directory; use //-absolute paths if you start from subdirectories. [lines 157-161] [Source]
  • Plugins can be installed for everyone through managed settings. [line 377] [Source]

mcp [Source]

  • New "Connection failures and unconfigured servers" subsection; failure details are redacted and never include the expanded server URL. [lines 277-283] [Source]

permission-modes [Source]

  • New section "Turn off the critical-path removal prompt in bypassPermissions mode" with per-shell examples, a danger warning, and scope limits (not plan mode; Bash and Monitor only). [lines 959-1015] [Source]
  • Startup notices explain whether the variable is active, and "Why the critical-path removal prompt stays on" lists causes (permission-prompt tools, PermissionRequest hooks, VS Code/Desktop, deny/ask rules). [lines 982-1015] [Source]
  • Other sections now cross-reference the opt-out. [line 30] [Source]

permissions [Source]

  • Compound commands: every subcommand must be allowed to run without a prompt (Bash and PowerShell). [line 215] [Source]
  • Windows network shares: example claude --add-dir Z:\. [line 521] [Source]
  • New "Where output styles, hooks, and local settings load from" section; settings.local.json loads from the git repository root. [lines 708-712] [Source]

plugins/mods/events [Source]

  • New "Send a request to a different model": aliases like haiku in turn.step need v2.1.309+, and next({ ...e, model: 'haiku' }) redirects a request. [lines 312-317] [Source]
  • Reworked settings.read hook explanation: when it first runs, how to detect origin, and what returns do. [lines 320-381] [Source]

plugins/mods/gallery [Source]

  • Input rows set to 2 or more makes a multi-line field; requires v2.1.301+, ignored in the VS Code extension, and keyboard rules apply to the terminal. [lines 245-288] [Source]

plugins/mods/interface [Source]

plugins/mods/reference [Source]

  • Button gains children (v2.1.295+), variant (primary/secondary) and role (dismiss). [lines 266-293] [Source]
  • New limits: $.process.run output capped at 4 MiB with truncation flags, and 28,000-level nesting depth for API call arguments, next events and hook return values (v2.1.299+). [lines 372-394] [Source]
  • $.ui.toast in the classic renderer can replace an older toast. [line 390] [Source]
  • settings.read requirements consolidated into the events table. [line 115] [Source]

plugins/mods/troubleshoot [Source]

  • settings.read refusal messages may come from another mod; added step-by-step procedure to find the offending mod with --debug-file. [lines 363-385] [Source]
  • Returned permission rules and env on Claude Code's own settings read are not applied. [line 340] [Source]

routines [Source]

  • New step "Select a model and effort level" for cloud tasks, and the effort level is selectable in the CLI instructions box. [lines 114-139] [Source]

web-scheduled-tasks [Source]

sandboxing [Source]

  • A git clone naming an absolute, ~ or .. path isn't covered by an entry; use a relative path. [line 319] [Source]

server-managed-settings [Source]

  • Non-interactive runs apply approval-requiring settings for that run only and re-fetch them at each startup until approved interactively. [lines 287-290] [Source]

sessions [Source]

  • Resumed sessions: interrupted tool calls aren't rerun (details moved to CLAUDE_CODE_RESUME_SHOWS_CUT_OFF_CALLS). [line 45] [Source]

settings-reference [Source]

  • forceLoginMethod: "claudeai" also removes the keyless Console sign-in. [line 5172] [Source]
  • CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS is ignored in every settings file. [line 2391] [Source]
  • A <<EOF heredoc counts as a redirection that keeps a Bash call sandboxed. [line 1292] [Source]

skills [Source]

  • The claude-api skill's upgrade subcommand now described as upgrading the Anthropic SDK to a new major version and updating code for breaking changes (not just Python 0.x to 1.x). [line 82] [Source]

slash-commands [Source]

  • Same upgrade subcommand update as in skills. [line 82] [Source]

sub-agents [Source]

  • The per-invocation model parameter on the Agent tool takes only an alias (sonnet, opus, haiku, fable), not a full model ID or inherit. [line 351] [Source]

worktrees [Source]

  • "fresh" base falls back to local HEAD when there's no remote or origin/HEAD can't be fetched. [lines 159-163] [Source]
  • New "Worktree locks and manual removal" heading. [line 138] [Source]
  • New troubleshooting entry: with git replace, created worktrees hold the original objects' content; create the worktree manually instead. [lines 327-332] [Source]

workflows [Source]


API changes

New Documents

None.

Changed documents

about-claude/models/overview [Source]

  • Models API capability fields now link to the API reference; a pointer to the full List Models response was added. [lines 67-81] [Source]

api/claude-platform-on-aws-iam-actions [Source]

  • Added the DeleteUserProfile action (DELETE /v1/user_profiles/{id}) to the action list and route table. [line 175] [Source]
  • Noted that *File wildcards also over-match DeleteUserProfile. [line 180] [Source]

build-with-claude/batch-processing [Source]

  • request_counts is now described as counting requests still processing plus requests with each result type; field references link to the API reference. [lines 704-706] [Source]

build-with-claude/claude-models-on-google-cloud/anthropic-managed [Source]

  • The workspace-less base URL also applies to the user profile routes under /v1/user_profiles. [line 218] [Source]

build-with-claude/refusals-and-fallback [Source]

  • fallback content blocks now include a trigger object (type: "refusal" and category, which can be null); the example now shows Claude Fable 5 declining a request whose fallbacks list names Claude Opus 4.8. [lines 633-651] [Source]

cli-sdks-libraries/overview [Source]

  • ant CLI and Go SDK versions bumped from 2.3.0 to 2.4.0 (also in the CLI quickstart and Managed Agents quickstart/worker docs). [line 59] [Source]

manage-claude/cmek-coverage-claude-enterprise [Source]

  • Removed the "Chat search" and "Project knowledge search" rows from the CMEK coverage list. [line 31] [Source]

manage-claude/compliance-activity-feed [Source]

  • organization_id is null for events not tied to an organization; the examples of such events (sign-in, sign-out, Compliance API calls) were removed. [line 141] [Source]

manage-claude/inference-hooks-configuration [Source]

  • A DlpWebhookStatusError entry can show the HTTP status returned and the request body size (such as HTTP 413 ยท 1.3 MB). [line 124] [Source]

manage-claude/user-profiles [Source]

  • User profiles are now supported on Claude Models on Google Cloud (Anthropic managed): create, retrieve, list and update, with the anthropic-user-profile-id header. Profile IDs are checked on every request there. [lines 41-373] [Source]

manage-claude/workspaces [Source]

  • Workspace Limited Developer role now documented as unable to open or start Claude Managed Agents sessions, open memory stores, manage deployments, or download/delete files in the Console (Console only, not API). [line 42] [Source]

managed-agents/self-hosted-sandboxes [Source]

  • ant CLI install: Homebrew instructions moved up, and a new go install github.com/anthropics/anthropic-cli/v2/cmd/ant@latest option (Go 1.25+) with PATH setup. [lines 180-215] [Source]