What changed, on every surface, within minutes.

• Fixed claude -p inside 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

• Added sandbox.allowNestedUserNamespaces so 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_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) notices a usage limit that was lifted before its reset
• Fixed every request failing on Vertex, Bedrock and other providers when the endpoint or a gateway rejects tool search, and behind gateways with ToolSearch disallowed or left out of --tools (a 2.1.304 regression): Claude…
• Fixed /effort and /autocompact settings not applying when the model name differed from a modelOverrides value by letter case or a [1m] tag

• Inference hooks are out of beta for Claude Enterprise organizations.
• We've launched user profiles, so you can tell Anthropic which of your end customers each API request is for. If you operate a platform or gateway, or resell API access, a safety enforcement action can then apply to one…
• We've added organization webhooks to the Admin API, in beta with the webhooks-2026-10-07 beta header. Its /v1/organizations/webhooks endpoints register webhook endpoints for two event types: one for when Anthropic…

• Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin
• Added decider: "person" to a mod's tool.check answer: only the permission dialog or a host's callback can approve the ask, and it is refused with the mod's reason where nobody can be asked
• Added e.isReadOnly to a mod's tool.check event, set when the tool call is read-only
• Added /auto-mode-setup: a guided setup that reads your project and recent sessions to teach auto mode about your environment, now also available on Bedrock, Vertex, Foundry, Claude apps gateway and telemetry-disabled…

The Compliance API now returns the text each organization member saved as Instructions for Claude in claude.ai and as Global instructions in Cowork, in beta for Claude Enterprise organizations. Call GET /v1/compliance/organizations/{org_uuid}/user_preferences with your existing Compliance Access Key and the read:compliance_user_data scope. See List user…

Bug fixes and reliability improvements

• Added CLAUDE_CODE_AUTO_MODE_MODEL to choose the model the client-side auto mode classifier uses; it does not change the model for server-side auto mode
• Added an Idle compaction row to /config for turning idle compaction off or back on; the notices shown after an idle compaction now say how to turn it off
• Added a notice to /design-sync and /design-login that standalone Claude Design (claude.ai/design) closes by December 14, 2026
• Fixed a "Prompt is too long" error when stopping a turn while the conversation was being compacted

• Added CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS so unattended retry mode (CLAUDE_CODE_RETRY_WATCHDOG) ends a request at a usage limit that resets too far away instead of waiting
• Added OpenTelemetry tracing guidance to the claude-api skill, including setting up trace destinations with the ant CLI
• Added the % motion to vim mode: jump to the matching bracket, alone or with d/c/y
• Added rows to a mod's Input: a text field of several lines in the terminal, where Enter submits and Shift+Enter or a backslash before Enter starts a new line

Fast mode for Claude Opus 5.5 is now available on Claude in Microsoft Foundry for deployments hosted on Azure.

Fast mode is out of research preview for Claude Opus 5.5, and you no longer need to request access. Requests to Claude Opus 5.5 no longer require the fast-mode-2026-02-01 beta header, and requests that still send it keep working. Claude Opus 5.5 now has a default fast mode rate limit in every usage tier. Fast mode for Claude Opus 5 and Claude Opus 4.8…

• We've added capabilities.thinking.types.between_tools to the Models API. GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts thinking: {type: "between_tools"}, which turns off up-front…
• The Compliance API now returns the text each organization member saved as Instructions for Claude in claude.ai and as Global instructions in Cowork, in beta for Claude Enterprise organizations. Call GET…
• Fast mode is out of research preview for Claude Opus 5.5, and you no longer need to request access. Requests to Claude Opus 5.5 no longer require the fast-mode-2026-02-01 beta header, and requests that still send it…
• Fast mode for Claude Opus 5.5 is now available on Claude in Microsoft Foundry for deployments hosted on Azure.

• Added virtualText to a mod's prompt decorations: text drawn in the prompt box that never enters the draft or the submitted prompt
• Added cache_creation_5m_tokens and cache_creation_1h_tokens to the OpenTelemetry api_request event, splitting cache writes by lifetime
• Added $.ui.view({ agentId }) for mods: shows an agent's transcript in the main view when you ask, and $.ui.view({}) goes back
• Added a dir prop on a mod's Text for right-to-left text: on Windows and in VS Code's terminal its rows read in that direction and sit flush right

• Added CLAUDE_CODE_DISABLE_FILE_MENTIONS environment variable: Claude gets the paths of @ file mentions to read with its file tools, not the files' contents
• Added idle compaction in the terminal: a 200K+ token conversation left idle for about 54 minutes is compacted before its one-hour prompt cache expires, so your next message doesn't reprocess it all
• Added CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS to change idle compaction's 200K-token minimum; "idleCompaction": false in settings.json turns it off. Both need v2.1.290 or later
• Added $.prompt.media so a prompt.submit hook of a mod installed by managed settings can read the bytes of an image or document attached to the prompt

• We've launched OpenTelemetry export in beta, so you can trace Messages API requests and Claude Managed Agents sessions in your observability backend. The Claude SDK emits spans in Python, TypeScript, C#, Go, Java, PHP…
• Claude Managed Agents scheduled deployments are now available on Claude Platform on AWS.

• MCP server startup timeout can now be configured via MCP_TIMEOUT environment variable
• MCP server startup no longer blocks the app from starting up

New MCP "project" scope now allows you to add MCP servers to .mcp.json files and commit them to your repository

Ask Claude to make a plan with thinking mode: just say 'think' or 'think harder' or even 'ultrathink'

• Copy+paste images directly into your prompt
• Improved progress indicators for bash and fetch tools
• Bugfixes for non-interactive mode (-p)

Vim bindings for text input - enable with /vim or /config

• New /approved-tools command for managing tool permissions
• Word-level diff display for improved code readability
• Fuzzy matching for slash commands

• Print mode (-p) now supports streaming output via --output-format=stream-json
• Fixed issue where pasting could trigger memory or bash mode unexpectedly

• Interactive MCP setup wizard: Run "claude mcp add" to add MCP servers with a step-by-step interface
• Fix for some PersistentShell issues

Fixed an issue where MCP tools were loaded twice, which caused tool call errors

• New web fetch tool lets Claude view URLs that you paste in
• Fixed a bug with JPEG detection

• Quickly add to Memory by starting your message with '#'
• Press ctrl+r to see full output for long tool results
• Added support for MCP SSE transport

Previous MCP server scopes have been renamed: previous "project" scope is now "local" and "global" scope is now "user"

• Press Tab to auto-complete file and folder names
• Press Shift + Tab to toggle auto-accept for file edits
• Automatic conversation compaction for infinite conversation length (toggle with /config)

• Navigate menus with vim-style keys (j/k) or bash/emacs shortcuts (Ctrl+n/p) for faster interaction
• Enhanced image detection for more reliable clipboard paste functionality
• Fixed an issue where ESC key could crash the conversation history selector

Fuzzy matching for /commands

• Custom slash commands: Markdown files in .claude/commands/ directories now appear as custom slash commands to insert prompts into your conversation
• MCP debug mode: Run with --mcp-debug flag to get more information about MCP server errors