Claude docs changes for September 25th, 2026 [diff]
Executive Summary
- Claude Code plugin docs were overhauled: the old single-page guides were rewritten into short overview pages and split into a new
docs-md/claude-code/plugins/section of 20 focused pages (installing, creating, publishing, org controls, dependencies, measuring cost/usage, troubleshooting, and more). - Claude Code 2.1.282 ships a large set of reliability fixes for resumed/continued sessions losing extended thinking or re-sending turns in a changed form, several vim-mode and rendering bugs, a new
maxProseWidthsetting, telemetry-ignored-variable startup warnings, and a big Slack/Claude Tag and cloud-sessions bug-fix batch. - Claude API is resuming billing for pre-output refusals in the
bio,frontier_llm, andreasoning_extractioncategories (previously every pre-output refusal was free); mid-stream refusals are unaffected. - Cache diagnostics graduated from beta to GA on the Claude API — no beta header needed, just send the
diagnosticsobject. - Claude Code Projects threads can now run on your own machine through Remote Control instead of only in the cloud, and auto mode's server-side classifier review now covers read-only/sandboxed shell commands and denies actions when the server gives no verdict.
New Claude Code versions
2.1.282
New features
- Added a
maxProseWidthsetting that caps the width of Claude's prose in wide terminals while tables and code blocks keep the full width - Added a startup notice, and
/statusandclaude doctorentries, listing telemetry variables in a project's settings files that were ignored or that turned telemetry off - Added the
allowClaudeInChromeWithManagedMcpmanaged setting to letclaude --chromerun alongside an exclusivemanaged-mcp.json; the error shown when Chrome is blocked now names it - Added
store.readiness_grace_secondsto the Claude apps gateway so/readyzcan stay ready through a short Postgres outage such as a database failover - Added a scrollbar to the
/feedbackdrafts list in fullscreen mode - [Cloud sessions] Added Claude GitHub App status to Settings › Connectors › GitHub, plus "Open repository"/"Open compare page" links for non-GitHub repositories and support for attaching a repository from a different GitHub owner (such as a fork's upstream) to a running cloud session
Existing feature improvements
- Changed auto mode to use the server-side classifier by default on a direct Anthropic API connection when telemetry is off (
CLAUDE_CODE_AUTO_MODE_SERVER=0opts out) - Changed
sandbox.excludedCommandsto ignore project and local settings entries when managed settings,--settings, orallowManagedDomainsOnlyrestrict unsandboxed commands or domains - Changed project and local settings to ignore OpenTelemetry variables that turn on export, set its endpoint, or capture content (e.g.
CLAUDE_CODE_ENABLE_TELEMETRY,OTEL_LOG_*) - Changed Windows/WSL managed settings so an invalid or unreadable admin policy no longer blocks user-writable HKCU and WSL
/etc/claude-codesettings from applying - Changed
Skill(anthropic-skills:*)/Skill(claude-ai:*)allow rules, skill/command loading, and MCP servers namedanthropic-skillsorclaude-aito only apply to content actually synced from claude.ai, not plugins or MCP servers that merely reuse the name - Improved the time to resume very large sessions, including ones never compacted
- Improved
/artifacts: aligned titles, whole-item detail truncation, and PgUp/PgDn/Home/End/mouse-wheel support - Improved the Windows EBADF resume error and the Claude Desktop unknown-model error messages
- Updated the
claude-apiskill: refusal billing links to the new docs, mid-stream refusals bill at normal rates, pre-output refusals count against rate limits, and it recommendsant applyfor Managed Agents resources - [Cloud sessions] Improved load time for the Routines page and sidebar Scheduled list for accounts with many past scheduled check-ins
- [Claude Tag] Changed bordered Slack cards (plans, tables, details) to render wide by default, and newly connected Slack workspaces now follow the current default model
Major bug fixes
- Fixed every request failing with a 400 when conversation history holds web search results the API can't decrypt (e.g. from a turn answered through a third-party gateway)
- Fixed
--continue/--resumesessions re-sending earlier messages in a changed form, which could make the API drop Claude's earlier reasoning, including when thinking was dropped by an immediate slash command or a--toolslist missing a previously offered built-in tool - Fixed sessions failing every turn with an "Invalid
datainredacted_thinkingblock" error by dropping thinking blocks and retrying once - Fixed compaction failing on a refused summarization request by retrying on a fallback model
- Fixed a failed turn after a safety-related model switch in sessions with thinking off and effort above high
- Fixed model-switch and Fable usage-credit prompt handling in SDK-hosted and Remote Control sessions
- Fixed a login error blocking requests for up to a minute after another Claude Code process refreshing auth was closed or killed mid-refresh
- Fixed CLAUDE.md/rules being read through a repository symlink that reaches macOS's
/Networkor a/.vol-style kernel path - Fixed Bash permission rules with a mid-pattern
:*being skipped in settings files while--allowedToolshonored them - Fixed managed settings ignoring a mistyped boolean lock key (e.g.
disableClaudeAiConnectors,allowManagedPermissionRulesOnly) instead of enforcing the locked value - Fixed managed
permissions,autoMode,worktree, andattributionsettings being ignored entirely when one nested value was invalid - Fixed skills/commands/skills-directory plugin manifests pre-approving their own tools via
allowed-toolsunderallowManagedPermissionRulesOnly - Fixed tool input validation errors naming only one bad parameter when several were invalid in the same call
- Fixed several rendering/input bugs: pasted multi-line text submitted line-by-line after bracketed-paste reset, blank-screen flash before fullscreen's first frame, garbled rows after the terminal shrank, a stale character after a wrapped CJK/emoji redraw, and cursor placement issues in
/skillssearch and vim mode (>>,r,2J,dd/dj/dG/p/P,.repeat counts) - Fixed
/install-github-appcontinuing remaining steps after "cancelled", and/feedback//bug//shareon third-party providers still saving reports after a cancelled save - Fixed plugin uninstall deleting a plugin's saved options/secrets when its settings file was unreadable or the installed-plugins list couldn't be read
- [VSCode] Fixed long replies falling behind the stream, the dictation mic covering the input scrollbar, and Remote Control sessions started locally not opening from the Web session list
- [Claude Tag] Fixed several Slack/Enterprise Grid bugs: auto-join patterns ignored org-wide, cross-workspace channel routing, retired-model fallback loops, table captions on uploaded files, thread naming in Agents & tools view, and inflated cost/token totals after a worker restart
Claude Code changes
New Documents
The plugin documentation was split out of a handful of long top-level pages into a dedicated docs-md/claude-code/plugins/ section:
overview [Source]
What a plugin is, when to use one instead of a standalone skill/subagent/hook/MCP server, and what an enabled plugin costs in context and permissions.
install [Source]
Install and manage plugins on any surface (terminal, desktop, IDE, cloud), choose an install scope, add marketplaces, and keep plugins updated.
create [Source]
Build a plugin with skills, agents, hooks, and MCP servers, and develop it locally with --plugin-dir before publishing.
create-marketplace [Source]
Build and test a marketplace.json locally before hosting it.
host-marketplace [Source]
Host a marketplace, including authenticating archive downloads with a headersHelper command.
publish [Source]
Share a plugin without a marketplace, or submit it to Anthropic's community marketplace.
manifest-reference [Source]
Full plugin.json field reference: types, defaults, path rules, userConfig, channels, and environment variables.
marketplace-reference [Source]
Reference for every field a marketplace entry accepts, including the command plugin source.
components [Source]
Every component type a plugin can hold (skills, agents, hooks, MCP servers, LSP servers, monitors) with an interactive plugin-directory explorer.
loading [Source]
How plugins are found on disk, cached, auto-updated, and synced from claude.ai, plus Node.js package dependencies.
dependencies [Source]
Declare version-constrained plugin dependencies and bundle a curated plugin set behind one install (mirrors the rewritten plugin-dependencies.md).
relevance [Source]
Add a relevance block to marketplace entries so Claude Code suggests plugins based on session signals (mirrors the rewritten plugin-relevance.md).
cli-hints [Source]
Emit a <claude-code-hint /> tag from your own CLI/SDK to prompt users to install your official-marketplace plugin (mirrors the rewritten plugin-hints.md).
measure [Source]
New page: measure a plugin's token cost and usage, and pick telemetry events for org-wide plugin questions.
org [Source]
Managed-settings controls for administrators: require/allowlist marketplaces, pre-install plugins, and restrict what users can install.
security [Source]
Plugin security and trust model, and Anthropic's official marketplace names.
anthropic-marketplaces [Source]
Distinguishes Anthropic's official, community, and demo marketplaces from Claude Marketplace (claude.com/marketplace).
cli-reference [Source]
Reference for every claude plugin shell subcommand.
code-intelligence [Source]
Ship LSP servers and other code-intelligence components in a plugin.
troubleshooting [Source]
Every claude plugin validate message and load/dependency error with its fix.
claude-apps-gateway-config [Source]
New comprehensive reference for every gateway.yaml option: listener/TLS, OIDC, session, Postgres store, per-provider upstreams (Anthropic, Bedrock, Claude Platform on AWS, Google Cloud, Microsoft Foundry), static upstream headers, model routing, managed policies, and telemetry.
Changed documents
claude-projects [Source]
- Project threads can now run on your own machine through Remote Control instead of only as cloud sessions, when a task needs something only your computer has; requires Claude Code v2.1.280+ on that machine and doesn't work with Require trusted devices on.
errors [Source]
- Added The server returned no safety verdict covering auto mode's new denial-on-no-verdict behavior and the 10-in-a-row turn stop
- Added recovery documentation for
role 'system' must precede an 'assistant' message(Claude Code now retries once with the text as a user message) andInvalid encrypted_content in search_result block/Failed to decrypt web search result content
keybindings [Source]
- Added a Text fields section clarifying that a bound bare letter/digit/Space still types normally in a focused text field (e.g. the "Other" answer to a Claude question)
managed-settings [Source]
- Documents that claude.ai now itself enforces the admin console's
strictKnownMarketplaces/blockedMarketplaceslists when a marketplace is added from claude.ai or Cowork's Customize tab - Added a full table of fallback behavior when a managed boolean/allowlist key (e.g.
allowManagedHooksOnly,disableCommandPluginSources,crossSessionInbound) is present but invalid, matching 2.1.282's fix
permission-modes [Source]
- Rewrote Server-side classifier review to cover which session types ask the server by default (now including telemetry-disabled direct-API sessions as of 2.1.282) and the two non-review outcomes (fallback to local classifier vs. denial on no verdict)
- Documents that read-only and sandboxed shell commands now also wait for server-side review and are blocked if flagged
env-vars [Source]
- Documents that project/local settings can no longer set
CLAUDE_CODE_ENABLE_TELEMETRYand other OpenTelemetry variables that turn on export or capture content (requires v2.1.282); the off-values that still apply are listed separately
settings-reference [Source]
- Expanded Variables Claude Code ignores in
envwith the full telemetry-variable ignore list, the startup notice, and how/status/claude doctorreport it
plugins.md, plugins-reference.md, discover-plugins.md, plugin-marketplaces.md
- Rewritten into shorter overview/landing pages (Plugins overview, Plugin manifest reference, Install and manage plugins, Create a marketplace) that route into the new
plugins/section rather than covering everything themselves
plugin-dependencies.md, plugin-relevance.md, plugin-hints.md, plugin-evals.md
- plugin-dependencies, plugin-relevance, and plugin-hints were reworded and now mirror the content of their new
plugins/counterparts - plugin-evals (renamed "Test plugins with evals") got an updated intro; it remains distinct from the new
plugins/measure.mdcost/usage page
Many other pages (claude-directory.md, admin-setup.md, sub-agents.md, settings-example.md, etc.) changed only in the links they use to point at the new plugins/ paths, with no content change.
API changes
New Documents
managed-agents/quickstart [Source]
New end-to-end tutorial for Claude Managed Agents: install the ant CLI and SDKs, create an agent and environment, start a session, and stream its events, plus links to four framework-specific "build a complete app" quickstarts (Chat SDK, assistant-ui, CopilotKit).
Changed documents
about-claude/models/optimizing-for-cost-and-intelligence [Source]
- Added a new Show the model elapsed time technique: a system-prompt instruction plus a per-turn elapsed-time message, benchmarked by Anthropic on DRACO, HLE, and an internal physics set, showing meaningful time/cost cuts for a small, benchmark-dependent score change
build-with-claude/cache-diagnostics [Source]
- Cache diagnostics is now GA on the Claude API: the
cache-diagnosis-2026-04-07beta header is no longer required, sending thediagnosticsobject is itself the opt-in, and the response field is nownull(not omitted) whenever diagnostics wasn't requested
build-with-claude/refusals-and-fallback [Source]
- How refusals are billed now documents that pre-output refusals in the
bio,frontier_llm, andreasoning_extractioncategories are billed at normal rates (to deter attempts to circumvent safeguards at scale); other categories, and mid-stream refusals' existing billing, are unchanged. Applies on every platform.
build-with-claude/mid-conversation-system-messages [Source]
- Mid-conversation tool changes on the Claude API now use a single
inline-tools-2026-09-15beta header (covering both tool-reference changes and inline tool definitions); the oldermid-conversation-tool-changes-2026-07-01header still works for by-reference changes on the Claude API, Amazon Bedrock, and Google Cloud, but not for inline tool definitions
build-with-claude/structured-outputs [Source]
- The deprecated
output_formatparameter now requires thestructured-outputs-2025-11-13beta header again; without it the API returns a 400 (previously accepted without a header during a transition period)
build-with-claude/preserved-thinking [Source]
- Clarifies that
"drop_block"doesn't fix the underlying prefix edit and can increase a session's token usage, since Claude may re-derive the reasoning it lost; recommends alerting onprefix_binding_mismatchentries and fixing the edit instead
manage-claude/compliance-activity-feed [Source]
- Documents that, as of September 24, 2026,
filename/titlefields on file, project-document, and artifact activities are always empty/omitted (including on past activities); names must now be looked up by ID through the metadata endpoints withread:compliance_user_data
manage-claude/compliance-sessions [Source]
- Compliance API local session endpoints are now stable (out of beta) for Claude for Microsoft 365 sessions (Excel, PowerPoint, Word, Outlook), alongside Cowork and Claude Code; Claude Science and Claude in Chrome remain beta
manage-claude/inference-hooks [Source]
- Added Continue a conversation after a denied request with per-app recovery steps (claude.ai/Desktop, Claude Code
/rewind, Cowork, Claude Tag's!restart) for removing denied content before retrying
manage-claude/cmek-aws-kms [Source]
- Expanded key-policy and troubleshooting guidance: locating a workspace's compartment ID, the optional
EncryptionContext/aws:SourceArnconditions that scope a key to specific workspaces, and diagnosing a denied attach via CloudTrail
managed-agents/self-hosted-sandboxes [Source]
- Added Go SDK support for self-hosted workers (
EnvironmentWorker,work.poller()/HandleItem(),agenttoolset.BetaAgentToolset20260401), alongside Python and TypeScript - Documents
memory_sync_interval/memory_sync_deletionsfor tuning how attached memory stores reconcile and handle local deletions, and how to run custom tools or MCP-backed tools through the SDK worker
managed-agents/environments [Source]
- Added
allow_package_managers, which opens outbound access to a maintained list of public package registries/code hosts; required whenever an environment specifiespackages, with a note on the prompt-injection/exfiltration risk of host-level (not per-operation) network access
API reference (all languages)
- The full per-language API reference (
api/api/beta/**undercli,csharp,go,java,php,python,ruby,typescript) was regenerated with expanded parameter documentation and constraints for existing and newbeta.messages.createfields: request-levelcompaction,diagnostics(cache diagnostics, now unconditional),speed: "fast",thinking.block_bindingdrop-on-mismatch controls, responsecontainerinfo, and sparse per-member overrides for agent-team requests. Representative page: api/beta/messages/create.