Claude docs changes for September 26th, 2026 [diff]

Executive Summary

  • Auto mode is now the built-in starting permission mode for interactive terminal and VS Code sessions on every plan and provider (not just Pro/Max/Team), and critical-path rm/rmdir removals in auto mode now prompt in the terminal with a two-minute countdown instead of always going to the classifier.
  • Projects gained "Run a thread on your own computer": a project thread can now run locally through Remote Control (from the Desktop app or claude remote-control) when a task needs your filesystem, MCP servers, or local tools.
  • New managed model-restriction settings deniedModels and availableModelsMatch let admins block a specific model version (e.g. Opus 5.5) even when a broader availableModels entry would otherwise permit it.
  • Claude Code gained a per-session scratchpad directory for Claude's temporary files (replacing ad hoc use of /tmp), and MCP tool image results are now saved to disk so other tools can reuse the full-resolution file.
  • Anthropic's plugin community marketplace submission process was replaced by a new "directory" submitted through a developer portal, which lists a plugin on claude.ai, Cowork, and Claude Code together.

New Claude Code versions

2.1.283

New features

  • Added x-claude-code-prompt-id to the gateway hint headers so LLM gateways can group the requests that serve one user prompt; opt in with CLAUDE_CODE_GATEWAY_HINT_HEADERS=1
  • Added availableModelsMatch managed setting: with "exact", an availableModels entry allows only the model version it names, so new releases stay blocked until listed
  • Added deniedModels managed setting to block specific models, even when availableModels allows them
  • Added MCP tool, WebFetch, and WebSearch outputs to the tool.output OpenTelemetry span event when OTEL_LOG_TOOL_CONTENT=1
  • Added /doctor prompt-audit (also /checkup prompt-audit) to audit CLAUDE.md files, skills, agents, and commands for prompting patterns written for older models
  • Added click-to-expand for truncated messages from your other sessions in fullscreen mode
  • Added path to --plugin-dir load-failure entries in the stream-json system/init plugin_errors, naming the directory that didn't load
  • Added an opt-in load_test_mode block to the Claude apps gateway config so a deployment can be load tested without calling a model provider
  • Added a mantle upstream provider to the Claude apps gateway for Amazon Bedrock's Mantle endpoint

Existing feature improvements

  • Improved the /mcp tool list: shows more tools at once, scrolls with the page keys and mouse, and marks org-blocked tools
  • Improved MCP tool results: images returned by MCP tools are now also saved to a file so Bash, Read, and other tools can open them
  • Improved /tasks and other pickers (/help, /hooks, /copy, /chrome, /memory, /ide, /release-notes, /rewind, /diff, /remote-env, /plugin, /skills, /artifacts) with page keys, mouse wheel, and clicks
  • Improved the compaction spinner: timer starts when compaction begins and counts the summary's tokens as they stream
  • Improved the Skill tool's reply when a skill's plugin failed to load, so Claude reports the plugin failure instead of calling the skill uninstalled
  • Improved first-reply and first-request latency, and startup time for claude -p, Remote Control, and cold claude.ai accounts
  • Changed interactive sessions on third-party providers or with telemetry off to start in auto mode when no permission mode is configured
  • Changed --system-prompt and --append-system-prompt to accept their text and -file forms together
  • Changed artifact watching: an auto-armed watch now ends after 3.5 hours with no activity

Major bug fixes

  • Fixed SDK sessions losing a deferred tool call or finished tool result when a turn ended early
  • Fixed MCP progress notifications being discarded once a long-running tool call moved to the background
  • Fixed stdio MCP servers being left running when the session ended while they were still starting
  • Fixed a brief HTTP 404 from a stateless remote MCP server leaving that server unusable for the rest of the session
  • Fixed the weekly Fable limit not appearing in /usage and the VS Code usage meters when telemetry is disabled
  • Fixed dynamic workflows started during a model fallback running every agent on the fallback model instead of retrying the configured model
  • Fixed DISABLE_PROMPT_CACHING_HAIKU having no effect when Haiku is the session's main model
  • Fixed several claude plugin bugs: validate accepting names it can't install and skipping outputStyles/lspServers/monitors/themes paths, details showing 0 MCP servers, marketplace remove not naming uninstalled plugins, uninstall removing the wrong of two case-differing plugin ids, and installed_plugins.json losing records or showing no plugins when it holds a bad entry
  • Fixed /context not counting MCP server instructions
  • Fixed claude mcp add, add-json, and remove reporting success when the config file couldn't actually be written
  • Fixed Remote Control being unavailable on paid plans when telemetry is turned off with DISABLE_TELEMETRY or DO_NOT_TRACK
  • Fixed managed sandbox settings being ignored entirely when one nested value was invalid
  • Windows: Fixed the PowerShell tool letting cmd /c rd, rmdir, del, or erase delete drive roots and other protected folders
  • [VSCode] Fixed a session teleported from the web dropping messages sent while Claude was working
  • [Code Review] Fixed "@claude review" requests going silent when GitHub failed to return the pull request
  • [Code Review] Fixed billing for a review that stopped at its time limit with nothing verified

Claude Code changes

Changed documents

accessibility [Source]

  • The screen-reader prompt for menus and permission dialogs changed from Enter selection to Select with numbers. [line 95] [Source]

advisor [Source]

  • Added an Unavailable advisor status line for when the advisor call itself fails, showing the error code. [line 140] [Source]

agent-sdk/hosting [Source]

  • Documented the new TypeScript prewarm() call for pre-warming a container process before a session's working directory is known. [line 105] [Source]

agent-sdk/mcp [Source]

  • In-process SDK MCP servers now have an explicit MCP_TIMEOUT first-turn wait per connect attempt, instead of no documented timeout. [line 134] [Source]

agent-sdk/observability [Source]

  • OTEL_LOG_TOOL_CONTENT=1 now also captures what MCP tools, WebFetch, and WebSearch return (Claude Code v2.1.283+). [line 220] [Source]

agent-sdk/permissions [Source]

  • Clarified that rm/rmdir removals targeting a critical path are never auto-approved and, in an Agent SDK session in auto mode, are denied by default without reaching canUseTool. [lines 35-45] [Source]

agent-sdk/plugins [Source]

  • "Plugin not loading" troubleshooting now points first at the init message's new plugin_errors field. [line 285] [Source]

agent-sdk/python [Source]

  • Added the verbatim_prompts option: deliver every prompt as written (client_composed: True) instead of expanding @ mentions or running / commands. Requires Python Agent SDK 0.2.158+ and Claude Code v2.1.248+. [line 810] [Source]

agent-sdk/typescript [Source]

  • Added a new @anthropic-ai/claude-agent-sdk/core entry point for apps that bundle the Agent SDK, which drops zod/MCP SDK inlining and some root-only exports. [line 44] [Source]
  • Added prewarm(), SpareProcess, and .claim() (alpha): start a spare Claude Code process before you know which session or folder it will serve. [line 117] [Source]
  • Added the verbatimPrompts option and client_composed message field, matching the Python SDK's verbatim_prompts. [line 519] [Source]
  • Added SpareProcess (claim, claimed, exited, close) as the return type of prewarm(). [line 698] [Source]
  • Documented SDKSystemMessage.plugin_errors, listing which plugin failed to load and why. [line 1626] [Source]
  • SDKTaskProgressMessage.summary now also carries an MCP server's latest reported progress for a backgrounded MCP tool call, not just subagent progress summaries. [line 5104] [Source]
  • SDKCommandsChangedMessage is now also emitted when an MCP server's prompts join or leave the command list (v2.1.281+). [line 5255] [Source]
  • SDKConversationResetMessage gained optional trigger, user_message_uuid, and timestamp fields describing what caused the reset (v2.1.281+). [line 5290] [Source]

agent-teams [Source]

  • Teammates now inherit a --setting-sources restriction from the lead; before v2.1.281, split-pane teammates loaded every settings source. [line 283] [Source]

agent-view [Source]

  • Added --setting-sources as a configuration flag agent view carries through to dispatched sessions. [line 428] [Source]
  • claude --bg (and background-session restarts) now check workspace trust for the target directory before starting. [line 428] [Source]
  • A worktree with only uncommitted changes in a verifiable checked-out submodule no longer blocks "delete again to remove the directory anyway". [line 544] [Source]

agents [Source]

  • The "Projects" row now notes threads can run in the cloud or, when asked, on your computer through Remote Control. [line 4] [Source]

authentication [Source] / iam

  • Added Windows PowerShell and CMD examples for setting CLAUDE_CODE_OAUTH_TOKEN, alongside the existing bash example. [line 245] [Source]

best-practices [Source]

  • Auto mode is now the built-in starting permission mode on every plan with Claude Code v2.1.283+, not just Pro/Max/Team. [line 175] [Source]
  • The Stop hook's fixed 8-consecutive-block cap is now described as configurable rather than hardcoded. [line 38] [Source]

claude-apps-gateway-config [Source]

  • Added "Add your own labels": telemetry.resource_attributes lets a gateway operator push fixed OpenTelemetry resource labels (like service.namespace) with every session's telemetry (v2.1.281+ on the gateway server). [line 888] [Source]
  • Clarified load_test_mode: a replica's CPU-per-request estimate reads lower than production since no request actually leaves for the provider. [line 998] [Source]

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

  • In Anthropic-hosted environments, GitHub credentials now stay encrypted on Anthropic's servers and never enter the session VM; traffic goes through a server-side GitHub proxy instead. [line 49] [Source]
  • Added a "Time limits" constraint pointing to the new cloud-environments time-limits section. [line 351] [Source]

claude-directory [Source]

  • Added a Session scratchpad directory: a per-session temp directory Claude uses instead of /tmp for intermediate files, helper scripts, and drafts, without a permission prompt. [line 1342] [Source]
  • tool-results/ now also holds full-size copies of images MCP tools return. [line 1314] [Source]

claude-md [Source] / memory

  • A .claude/rules/ or CLAUDE.md symlink pointed at a network path (UNC share, /net, /Network) is no longer followed, to avoid contacting the host it names. [line 237] [Source]
  • Added a startup/​/status warning when an instruction file exceeds the recommended length, or several files together exceed a combined limit. [line 569] [Source]

claude-projects [Source]

  • Added "Run a thread on your own computer": choose Work locally in a project conversation to run that task's thread through Remote Control on a connected machine (Desktop app or claude remote-control, v2.1.280+), instead of in the cloud. Covers connecting the folder, the approval card, auto mode behavior, and the "Lost contact with your folder" and new error states. [line 245] [Source]

cli-reference [Source]

  • --agents can now take the path to a JSON file (with --print), for definitions too large for the command line (v2.1.281+). [line 324] [Source]
  • --bg now checks workspace trust for the target directory before it starts. [line 334] [Source]

cloud-environments [Source]

  • Added a Time limits section: command timeouts, SessionStart hook's 600s default, the setup-script ~5-minute caching cutoff, and idle-session expiry, plus BASH_DEFAULT_TIMEOUT_MS/BASH_MAX_TIMEOUT_MS to raise them. [line 351] [Source]

code-review [Source]

  • Code Review now automatically retries some interrupted reviews; check the run's summary before manually retriggering. Check-run titles changed to e.g. Code review failed. [line 255] [Source]

costs [Source]

  • New "Subagents and workflows" note: every subagent and workflow-spawned agent sends its own requests, which count toward usage; the attribution breakdown shows the subagent share. [line 344] [Source]

data-usage [Source]

  • Clarified cloud-session data handling: Anthropic stores the session transcript, and GitHub credentials are encrypted server-side and never enter the VM. [line 88] [Source]

discover-plugins [Source]

  • Clarified that committing a project-scope plugin entry turns it on for collaborators but doesn't download it; each collaborator must also run claude plugin install once. [line 125] [Source]

env-vars [Source]

  • Added CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT, CLAUDE_CODE_DISABLE_POWERSHELL_CMD_RM_DENY, and CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT to opt out of the new critical-path removal checks. [line 9] [Source]
  • DISABLE_PROMPT_CACHING_HAIKU now disables caching for the default Haiku model wherever it runs, including as your main model. [line 26] [Source]
  • With feature-flag fetching off, Remote Control's availability now depends on the specific variable set, rather than blanket unavailability. [line 46] [Source]

errors [Source]

  • Documented dozens of new/changed error messages, including: Couldn't save your login (macOS keychain locked) and Could not refresh your login because another Claude Code process is refreshing it; Part of the response never arrived / The response stream was malformed for dropped or duplicated stream events; new disk-quota/temp-filesystem-full errors (EDQUOT/ENOSPC); a reserved-name notice for skills/commands/workflows named inside the anthropic-skills namespace; Claude Code can't start: your organization's managed settings block the default model; and Desktop-app-specific wording for several auth and usage-limit messages. [line 231] [Source]

fullscreen [Source]

  • Overflowing list panels (/skills, /mcp, /plugin's Installed list) now show a clickable/draggable scrollbar (v2.1.281+). [line 91] [Source]
  • A dim Message from @<sender> line from a teammate or other running agent is now click-to-expand. [line 87] [Source]

headless [Source]

  • Resuming a -p/SDK session interrupted by SIGTERM no longer auto-continues the unfinished turn by default; set CLAUDE_CODE_RESUME_INTERRUPTED_TURN=1 to restore the old behavior. [line 75] [Source]
  • Added a new warning message when a -p/SDK session's working directory is deleted mid-session; shell commands fail until it exists again. [line 149] [Source]
  • plugin_errors entries for a failed --plugin-dir directory/archive now include the resolved path (v2.1.283+). [line 165] [Source]

hooks [Source]

  • The Stop hook's 8-consecutive-block cap is now configurable via CLAUDE_CODE_STOP_HOOK_BLOCK_CAP. [line 2491] [Source]

ide-integrations [Source] / vs-code

  • The Resume dialog's Web tab now also lists Remote Control sessions and opens a matching local conversation directly instead of downloading a copy, with clearer download-failure errors. [line 264] [Source]
  • A message queued with an editor selection attached now keeps that selection even if you select something else afterward. [line 295] [Source]

interactive-mode [Source]

  • Added vim-mode commands r{char}, dj/dk, dgg/dG, and d0/c0/y0 (v2.1.281+). [line 27] [Source]
  • Documented that a command reaching its timeout is auto-moved to the background instead of stopped, unless it starts with sleep. [line 296] [Source]

keybindings [Source]

  • Pressing Ctrl+C or Ctrl+D twice in most dialogs now closes the dialog instead of exiting Claude Code. [line 148] [Source]
  • footer:dismiss was removed in v2.1.281 (existing bindings become no-ops). [line 256] [Source]
  • The rewind menu's message list and the diff file list now use the generic Select actions/bindings instead of their own dedicated MessageSelector/diff:viewDetails actions (v2.1.283+). [lines 271-301] [Source]

llm-gateway-protocol [Source]

  • New stricter streaming requirements for gateways: deliver the full event sequence without dropping/duplicating/reordering, and relay each response through its final message_delta/message_stop before closing the body. [line 59] [Source]
  • Added the x-claude-code-prompt-id gateway hint header (v2.1.283+). [line 145] [Source]

managed-settings [Source]

  • Added the new deniedModels and availableModelsMatch managed settings to the merge and fail-closed-enforcement tables. [lines 245-263] [Source]

mcp [Source]

  • Only an SDK host application can register an in-process "type": "sdk" server; such an entry in .mcp.json/settings is now skipped with a clear message. [line 76] [Source]
  • Duplicate-server detection now normalizes URL case, default ports, and trailing slashes when comparing endpoints. [line 587] [Source]
  • Added "Images in tool results": MCP-returned images are now also saved full-resolution to the session's tool-results directory (v2.1.283+). [line 1252] [Source]
  • MCP Apps UI resources (ui:// or text/html;profile=mcp-app) no longer appear in @ suggestions or the resource list tool. [line 1370] [Source]
  • Prompts from a server named anthropic-skills no longer appear, since that name is reserved for synced skills. [line 1463] [Source]

model-config [Source]

  • Added "Block specific models or versions": use deniedModels or availableModelsMatch: "exact" to keep a newer release (e.g. Opus 5.5) blocked even though a broader availableModels entry permits it (v2.1.283+). [line 336] [Source]
  • Opus 5.5 defaults to effort medium, one level below Opus 5's high default; start at medium rather than carrying over an Opus 5 level. [line 614] [Source]

monitoring-usage [Source]

  • Troubleshooting OTEL export now points to claude --debug-file <path> rather than claude --debug. [line 33] [Source]
  • The tool.output span event now also fires for MCP tools, WebFetch, and WebSearch (v2.1.283+). [line 272] [Source]
  • On Amazon Bedrock, request_id now falls back to the x-amzn-requestid header when there's no request-id header (v2.1.282+). [line 651] [Source]

permission-modes [Source]

  • Auto mode is now the built-in starting permission mode for terminal/VS Code sessions on every plan and provider with Claude Code v2.1.283+, not just Pro/Max/Team. [line 4] [Source]
  • Critical-path rm/rmdir handling changed (v2.1.281+): in auto mode Claude Code now asks in the terminal with a two-minute countdown (denying elsewhere, such as -p, SDK, VS Code chat) instead of always routing to the classifier; bypassPermissions also gets a timed terminal prompt. [lines 621-656] [Source]
  • Added new critical-path detection cases: a shell variable followed by a top-level directory name, a variable assigned from a directory-printing substitution in the same command, a backslash-only target, and a target that is entirely a command substitution. [line 656] [Source]
  • Remove-Item's system-path denial now also covers the cmd built-ins rd, rmdir, del, and erase run through cmd /c (v2.1.283+), matching the Windows PowerShell tool security fix. [line 372] [Source]

permissions [Source]

  • Documented the new workspace-trust check before starting or restarting a background session. [line 625] [Source]

platforms [Source]

  • Remote Control now also runs from the Claude Desktop app, not just the CLI and VS Code. [line 43] [Source]

plugin-evals [Source]

  • claude plugin eval now requires git 2.31+ when git is installed, and stops with a new error before running any case on an older git. [line 21] [Source]

plugins-reference [Source] / plugins/manifest-reference

  • claude plugin validate now also checks outputStyles, lspServers, monitors, and themes paths for containment/existence (v2.1.283+). [line 341] [Source]

plugins/create [Source]

  • Added guidance to use Anthropic's plugin-dev plugin (/plugin-dev:create-plugin) to have Claude scaffold and validate a larger plugin. [line 120] [Source]

plugins/publish [Source] (+ plugin-marketplaces, plugins/anthropic-marketplaces, plugins/create-marketplace, plugins.md, plugins/overview)

  • Submitting a plugin to Anthropic's public community marketplace is being replaced by submitting to Anthropic's directory through a new developer portal at claude.ai/directory/manage; a listing there reaches claude.ai, Cowork, and Claude Code together, and requires a paid claude.ai plan. [line 471] [Source]

prompt-caching [Source]

  • Added a table detailing exactly which mid-session MCP server changes (connect, drop out, auto-reconnect, deliberate removal) invalidate the cache when tool definitions load into the prefix. [line 100] [Source]
  • DISABLE_PROMPT_CACHING_HAIKU now covers the main conversation when Haiku is your main model (v2.1.283+). [line 336] [Source]

remote-control [Source]

  • Remote Control can now be started from the Claude Desktop app's Code tab with /remote-control or /rc, in addition to the CLI and VS Code. [line 248] [Source]
  • Server mode gained a -d/--debug[=<filter>] flag (v2.1.282+). [line 232] [Source]
  • DISABLE_TELEMETRY/DO_NOT_TRACK alone no longer block Remote Control unless your organization requires Trusted Devices (v2.1.283+). [line 208] [Source]
  • /focus on/off is now supported from mobile and web (v2.1.281+). [line 389] [Source]

routines [Source] / web-scheduled-tasks

  • A schedule set exactly on the hour can now start several minutes late; pick a few minutes past the hour (e.g. 9:07) to start closer to the scheduled time. [line 130] [Source]

sandboxing [Source]

  • The sandbox's default writable temp directory changed from a per-session directory to a per-user temp directory. [line 34] [Source]

server-managed-settings [Source]

  • Detailed how a startup that reads the cached remote settings now preserves fail-closed (stricter) values, not just dropping invalid entries. [line 188] [Source]

settings-reference [Source]

  • Added availableModelsMatch and deniedModels managed settings for blocking specific model versions (v2.1.283+). [lines 570-833] [Source]
  • Added maxProseWidth to cap the width of prose in Claude's responses in a wide terminal (v2.1.282+). [line 3174] [Source]
  • The trailers (git commit attribution) default now names the subagent's model when a subagent makes the commit, not the session's active model. [line 3796] [Source]

skills [Source] / slash-commands

  • The frontmatter name field now sets the actual invocable command for a personal or project skill directory, not just its display label. [line 383] [Source]
  • Added "Names reserved for synced skills": anthropic-skills and everything inside that namespace is now reserved for claude.ai-synced skills, replacing the earlier claude-ai reservation. [line 231] [Source]
  • Picking up a newly created top-level skills directory now requires running /reload-skills instead of restarting Claude Code. [line 260] [Source]

sub-agents [Source]

  • Subagent requests now count toward the same usage limits as the main conversation, noted alongside model-selection guidance. [line 4] [Source]
  • An --agents JSON definition can now have an empty prompt, which leaves the session's system prompt unchanged when selected with --agent (v2.1.281+). [line 208] [Source]

terminal-config [Source]

  • Added "Cap response width in wide terminals", documenting the new maxProseWidth setting. [line 297] [Source]

troubleshoot-install [Source]

  • Added recovery steps for claude.exe missing after an update on Windows (rename the .old. backup back). [line 546] [Source]
  • Added a new Claude Code access has not been granted for this account entry for Enterprise custom-role sign-in failures. [line 925] [Source]
  • Added macOS-specific PATH fix instructions (~/.bash_profile instead of ~/.bashrc, since Terminal starts Bash as a login shell). [line 124] [Source]

workflows [Source]

  • Clarified that ultracode tokens draw on subscription usage limits, and that turning it on already opts out of the "Large workflow" warning, the concurrent-subagent limit, and the auto-mode first-launch approval. [line 143] [Source]

worktrees [Source]

  • Exiting with unfinished work now prints the exact claude --worktree <name> --resume command to return to it later. [line 44] [Source]

API changes

Changed documents

agent-skills/overview [Source]

  • Noted a Microsoft Foundry-specific exception: the Skill version download endpoint (GET /v1/skills/{skill_id}/versions/{version}/content) isn't supported there. [line 137] [Source]

build-with-claude/claude-platform-on-aws [Source]

  • Agent Skills on Claude Platform on AWS moved out of beta to Available. [line 27] [Source]

build-with-claude/files [Source]

  • The Files API moved from beta to GA on both Claude Platform on AWS and Microsoft Foundry. [line 9] [Source]

build-with-claude/mid-conversation-system-messages [Source]

  • Clarified beta-header requirements for mid-conversation tool changes: inline-tools-2026-09-15 (Claude API) also covers inline tool definitions, and adding an MCP server mid-conversation needs mcp-client-2026-09-15 as a second header on the Claude API. [line 16] [Source]

build-with-claude/overview [Source]

  • Updated the feature-availability table to reflect Agent Skills and Files API reaching GA on Claude Platform on AWS and Microsoft Foundry. [line 82] [Source]

manage-claude/analytics-api [Source]

  • Engagement/adoption endpoint data now typically lands by ~13:00–13:30 UTC the following day, earlier than the previously documented ~17:00 UTC. [line 75] [Source]