Every release, doc update, and news item across the Claude ecosystem. Deduped and sorted by publish date.
Auto mode is now available without CLAUDE_CODE_ENABLE_AUTO_MODE opt-in on Bedrock, Vertex AI, and Foundry; disable via disableAutoMode in settings Fixed the terminal freezing and keystrokes lagging while streaming responses containing very long lists, tables, paragraphs, or code…
Claude Sonnet 5 sessions no longer use the mid-conversation system role for harness reminders
Added CLAUDE_CODE_DISABLE_MOUSE_CLICKS to disable mouse click/drag/hover in fullscreen mode while keeping wheel scroll Fixed hook matchers with hyphenated identifiers (e.g. code-reviewer, mcpbrave-search) accidentally substring-matching — they now exact-match. Use mcpbrave-search…
The stream-stall hint now reads "Waiting for API response · will retry in …" instead of "No response from API · Retrying in …", and triggers after 20s of silence instead of 10s
Added a prompt before writing to shell startup files (.zshenv, .zlogin, .bash_login) and ~/.config/git/, which could otherwise lead to unintended command execution acceptEdits mode now prompts before writing build-tool config files that grant code execution (.npmrc, .yarnrc*, bun…
/code-review --fix now applies review findings to your working tree after the review, surfacing reuse, simplification, and efficiency suggestions; /simplify now invokes /code-review --fix Skills and slash commands can now set disallowed-tools in frontmatter to remove tools from t…
Renamed /simplify to /code-review with an optional effort level (e.g. /code-review high) Auto mode no longer suppresses AskUserQuestion when the user or a skill explicitly relies on it Fixed Windows PowerShell tool failing with "command line is invalid" when pwsh is installed via…
Added agent view (Research Preview): a single list of every Claude Code session — running, blocked on you, or done. Run claude agents to get started. See https://code.claude.com/docs/en/agent-view Added /goal command: set a completion condition and Claude keeps working across tur…
Added CLAUDE_CODE_SESSION_ID environment variable to the Bash tool subprocess environment, matching the session_id passed to hooks Added CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1 env var to opt out of the fullscreen alternate-screen renderer and keep the conversation in the terminal…
Added alwaysLoad option to MCP server config — when true, all tools from that server skip tool-search deferral and are always available Added claude plugin prune to remove orphaned auto-installed plugin dependencies; plugin uninstall --prune cascades Added a type-to-filter search…
Windows: Git for Windows (Git Bash) is no longer required — when absent, Claude Code uses PowerShell as the shell tool Added claude ultrareview [target] subcommand to run /ultrareview non-interactively from CI or scripts — prints findings to stdout (--json for raw output) and exi…
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
Added directory path suggestions to /cd, matching /add-dir behavior Added a /doctor check that proposes trimming checked-in CLAUDE.md files by cutting content Claude could derive from the codebase /commit-push-pr now auto-allows git push to the repo's configured push remote (remo…
Added an auto mode rule that blocks tampering with session transcript files Fixed --json-schema silently producing unstructured output when the schema was invalid, and schemas using the format keyword being rejected Fixed a message sent while Claude was working being silently los…
Fixed hook events not streaming during SessionStart hooks in headless sessions, which could cause remote workers to be idle-reaped mid-hook
Added a warning when your login is about to expire, so you can re-authenticate before background sessions are interrupted Added a grey ⏸ badge to the footer when in manual permission mode, making the active mode always visible Added the session's additional working directories to…
Added a "Dynamic workflow size" setting in /config for controlling how large Claude generally makes dynamic workflows (small/medium/large agent counts) — an advisory guideline, not an enforced cap Added workflow.run_id and workflow.name OpenTelemetry attributes to telemetry emitt…
Changed AskUserQuestion dialogs to no longer auto-continue by default; opt into an idle timeout via /config Changed the "default" permission mode to "Manual" across the CLI, --help, VS Code, and JetBrains; --permission-mode manual and "defaultMode": "manual" are accepted alongsid…
Stacked slash-skill invocations like /skill-a /skill-b do XYZ now load all leading skills (up to 5), not just the first Fixed SSL certificate errors (TLS-inspecting proxies, missing NODE_EXTRA_CA_CERTS, expired certs) burning retries before showing actionable guidance — they now…
Subagents now run in the background by default, so Claude keeps working while they run and is notified when they finish (previously a gradual rollout) Claude in Chrome is now generally available Added background agent notifications in claude agents — sessions that need input or f…
Introducing Claude Sonnet 5: now the default model in Claude Code, with a native 1M-token context window and promotional pricing of $2/$10 per Mtok through August 31. Update to version 2.1.197 for access. https://www.anthropic.com/news/claude-sonnet-5
Added support for organization default models — admins set it in the org console; it shows as "Org default" (or "Role default") in /model when you haven't picked one yourself Added readable default names for sessions at start, making them easier to identify and message Added clic…
Added autoMode.classifyAllShell setting to route all Bash/PowerShell commands through the auto-mode classifier instead of only arbitrary-code-execution patterns Added auto-mode denial reasons to the transcript, the denial toast, and /permissions recent denials Added claude_code.a…
Added /rewind support for resuming a conversation from before /clear was run Fixed scroll position jumping to the bottom while reading earlier output during a streaming response Fixed background agents resurrecting after being stopped — stopping an agent from the tasks panel is n…
Added sandbox.credentials setting to block sandboxed commands from reading credential files and secret environment variables Added org-configured model restrictions to the model picker, --model, /model, and ANTHROPIC_MODEL, with a "restricted by your organization's settings" mess…
Added claude mcp login and claude mcp logout to authenticate MCP servers from the CLI without opening the interactive /mcp menu, with --no-browser stdin redirect support for completing over SSH Added status filtering (press f) to the /workflows agent detail view Added a "Skills"…
Improved auto mode safety: destructive git commands (git reset --hard, git checkout -- ., git clean -fd, git stash drop) are now blocked when you didn't ask to discard local work, git commit --amend is blocked when the commit wasn't made by the agent this session, and terraform d…
Added /config key=value syntax to set any setting from the prompt (e.g. /config thinking=false) — works in interactive, -p, and Remote Control Added sandbox.allowAppleEvents opt-in setting that lets sandboxed commands send Apple Events on macOS Added CLAUDE_CLIENT_PRESENCE_FILE e…
Agent teams: removed the TeamCreate and TeamDelete tools. With CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 set, every session now has one implicit team — spawn teammates directly with the Agent tool's name parameter, no setup step needed. The team_name parameter on the Agent tool is s…
Fixed mid-stream connection drops: partial responses are now preserved instead of showing a raw error, and the spinner no longer gets stuck at "running tool" Fixed mouse-wheel scrolling in WSL2 under Windows Terminal and VS Code (regression in 2.1.172) Fixed a sandbox denyRead/al…
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Fable’s capabilities exceed those of any model we’ve ever made generally available. Update to version 2.1.170 for access. https://www.anthropic.com/news/claude-fable-5-mythos-5 Fixed sessions n…
Self-hosted runner: added a post-session lifecycle hook that runs after the session ends and before the workspace is deleted, so you can snapshot uncommitted work or export logs; also made the child-process SIGTERM→SIGKILL window configurable (default unchanged at 5s) Added --saf…
Sub-agents can now spawn their own sub-agents (up to 5 levels deep) Amazon Bedrock now reads the AWS region from ~/.aws config files when AWS_REGION isn't set, matching AWS SDK precedence; /status shows where the region came from Added a search bar when browsing a marketplace's p…
Fixed Fable 5 model names with a [1m] suffix not being normalized — Fable 5 includes 1M context by default, so the suffix is now stripped automatically Fixed a spurious "sandbox dependencies missing" startup warning on Windows when sandbox was enabled in settings
Added wheelScrollAccelerationEnabled setting to disable mouse-wheel scroll acceleration in fullscreen mode Fixed the /model picker hiding the model family that Default resolves to — Opus now appears as its own row on Max/Team Premium/Enterprise plans, Sonnet on Pro/Team plans, an…
Added enforceAvailableModels managed setting — when enabled, the availableModels allowlist also constrains the Default model (a Default that would resolve to a disallowed model now falls back to the first allowed model), and user or project settings can no longer widen a managed…
Session titles are now generated in the language of your conversation (set the language setting to pin a specific language) Added footerLinksRegexes setting for regex-matched link badges in the footer row, configurable via user or managed settings Improved Bedrock credential cach…
OTEL_RESOURCE_ATTRIBUTES values are now included as labels on metric datapoints, so you can slice usage metrics by custom dimensions like team or repo claude agents rows now show done/total before the detail when work is fanned out; peek shows the longest-running item /mcp now co…
claude agents --json now includes waitingFor showing what a waiting session is blocked on (e.g. permission prompt) --tools: explicitly listing Grep/Glob now provides the dedicated search tools on native builds with embedded search (previously these names were silently ignored) /e…
Added requiredMinimumVersion and requiredMaximumVersion managed settings — Claude Code refuses to start if its version is outside the allowed range and directs the user to an approved version Added /plugin list command to list installed plugins, with --enabled/--disabled filters…
Added fallbackModel setting to configure up to three fallback models tried in order when the primary model is overloaded or unavailable; --fallback-model now also applies to interactive sessions Added glob pattern support in deny rule tool-name position ("*" denies all tools); al…
Added skipLfs option to github/git plugin marketplace sources to skip Git LFS downloads during clone and update Claude Code now shows a one-time notice when your npm global install can't auto-update; /doctor lists the fixes Status line commands now receive COLUMNS and LINES envir…
Opus 4.8 is here! Now defaults to high effort · /effort xhigh for your hardest tasks Introducing dynamic workflows: ask Claude to create a workflow and it orchestrates work across tens to hundreds of agents in the background, so you can take on larger, more complex tasks. Run /wo…
Fixed an issue when using Opus 4.8 where thinking blocks were modified, leading to API errors.
Plugins in .claude/skills directories are now automatically loaded, no marketplace required Added claude plugin init to scaffold a new plugin in .claude/skills Added autocomplete for /plugin arguments: subcommands, installed plugin names, and plugins from known marketplaces claud…
Auto mode is now available on Bedrock, Vertex, and Foundry for Opus 4.7 and Opus 4.8. Opt in by setting CLAUDE_CODE_ENABLE_AUTO_MODE=1
Pinned background sessions (Ctrl+T in claude agents) now stay alive when idle, are restarted in place to apply Claude Code updates, and are shed under memory pressure only after non-pinned sessions Renamed /simplify to /code-review. It now reports correctness bugs at a chosen eff…
Fixed the Bash tool returning exit code 127 on every command for some users (a regression introduced in 2.1.147)
/usage now shows a per-category breakdown of what's driving your limits usage — skills, subagents, plugins, and per-MCP-server cost /diff detail view can now be scrolled with the keyboard (arrows, j/k, PgUp/PgDn, Space, Home/End) Markdown output now renders GFM task list checkbox…
Improved Agent tool subagent_type matching to accept case- and separator-insensitive values (e.g. "Code Reviewer" resolves to code-reviewer) Updated agent color palette Fixed /goal silently hanging when disableAllHooks or allowManagedHooksOnly is set — now shows a clear message i…
Added terminalSequence field to hook JSON output so hooks can emit desktop notifications, window titles, and bells without a controlling terminal Added CLAUDE_CODE_PLUGIN_PREFER_HTTPS to clone GitHub plugin sources over HTTPS instead of SSH, for environments without a GitHub SSH…
Added new claude agents flags: --add-dir, --settings, --mcp-config, --plugin-dir, --permission-mode, --model, --effort, and --dangerously-skip-permissions to configure dispatched background sessions Fast mode now uses Opus 4.7 by default (previously Opus 4.6). Set CLAUDE_CODE_OPU…
Added plugin dependency enforcement: claude plugin disable now refuses when another enabled plugin depends on the target (with a copy-pasteable disable-chain hint), and claude plugin enable force-enables transitive dependencies Added projected context cost (per-turn and per-invoc…
Bare /color (no args) now picks a random session color /mcp now shows the tool count for connected servers and flags servers that connected with 0 tools --plugin-dir now accepts .zip plugin archives in addition to directories --channels now works with console (API key) authentica…
Added --plugin-url flag to fetch a plugin .zip archive from a URL for the current session Added CLAUDE_CODE_FORCE_SYNC_OUTPUT=1 env var to force-enable synchronized output on terminals that auto-detection misses (e.g. Emacs eat) Added CLAUDE_CODE_PACKAGE_MANAGER_AUTO_UPDATE: when…
Fixed VS Code extension failing to activate on Windows due to a hardcoded build path in the bundled SDK (createRequire polyfill bug) Fixed Mantle endpoint authentication failing with missing x-api-key header
Added worktree.baseRef setting (fresh | head) to choose whether --worktree, EnterWorktree, and agent-isolation worktrees branch from origin/ or local HEAD. Note: the default fresh changes EnterWorktree's base back to origin/ (it has been local HEAD since 2.1.128) — set worktree.b…
Added CLAUDE_CODE_ENABLE_FEEDBACK_SURVEY_FOR_OTEL to re-enable the session quality survey for enterprises capturing responses through OpenTelemetry Added settings.autoMode.hard_deny for auto mode classifier rules that block unconditionally regardless of user intent or allow excep…
Added ANTHROPIC_BEDROCK_SERVICE_TIER environment variable to select a Bedrock service tier (default, flex, or priority), sent as the X-Amzn-Bedrock-Service-Tier header Pasting a PR URL into the /resume search box now finds the session that created that PR (GitHub, GitHub Enterpri…
Fixed OAuth authentication failing with a 401 retry loop when CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 is set
The /model picker now lists models from your gateway's /v1/models endpoint when ANTHROPIC_BASE_URL points at an Anthropic-compatible gateway - Added claude project purge [path] to delete all Claude Code state for a project (transcripts, tasks, file history, config entry) — suppor…
Forked subagents can now be enabled on external builds by setting CLAUDE_CODE_FORK_SUBAGENT=1 Agent frontmatter mcpServers are now loaded for main-thread agent sessions via --agent Improved /model: selections now persist across restarts even when the project pins a different mode…
/resume on large sessions is significantly faster (up to 67% on 40MB+ sessions) and handles sessions with many dead-fork entries more efficiently Faster MCP startup when multiple stdio servers are configured; resources/templates/list is now deferred to first @-mention Smoother fu…
Added vim visual mode (v) and visual-line mode (V) with selection, operators, and visual feedback Merged /cost and /stats into /usage — both remain as typing shortcuts that open the relevant tab Create and switch between named custom themes from /theme, or hand-edit JSON files in…
Added ANSI color theme for better terminal compatibility Fixed issue where slash command arguments weren't being sent properly (Mac-only) API keys are now stored in macOS Keychain
New /approved-tools command for managing tool permissions Word-level diff display for improved code readability Fuzzy matching for slash commands
Fixed a crash in the permission dialog when an agent teams teammate requested tool permission
Changed the CLI to spawn a native Claude Code binary (via a per-platform optional dependency) instead of bundled JavaScript Added sandbox.network.deniedDomains setting to block specific domains even when a broader allowedDomains wildcard would otherwise permit them Fullscreen mod…
Interactive MCP setup wizard: Run "claude mcp add" to add MCP servers with a step-by-step interface Fix for some PersistentShell issues
Plan mode: introduced new Plan subagent Subagents: claude can now choose to resume subagents Subagents: claude can dynamically choose the model used by its subagents SDK: added --max-budget-usd flag Discovery of custom slash commands, subagents, and output styles no longer respec…
New UI for permission prompts Added current branch filtering and search to session resume screen for easier navigation Fixed directory @-mention causing "No assistant message found" error VSCode Extension: Add config setting to include .gitignored files in file searches VSCode Ex…
Removed legacy SDK entrypoint. Please migrate to @anthropic-ai/claude-agent-sdk for future SDK updates: https://platform.claude.com/docs/en/agent-sdk/migration-guide
Fixed a bug where project-level skills were not loading when --setting-sources 'project' was specified Claude Code Web: Support for Web -> CLI teleport Sandbox: Releasing a sandbox mode for the BashTool on Linux & Mac Bedrock: Display awsAuthRefresh output when auth is required
Fixed content layout shift when scrolling through slash commands IDE: Add toggle to enable/disable thinking. Fix bug causing duplicate permission prompts with parallel tool calls Add support for enterprise managed MCP allowlist and denylist
Support MCP structuredContent field in tool responses Added an interactive question tool Claude will now ask you questions more often in plan mode Added Haiku 4.5 as a model option for Pro users Fixed an issue where queued commands don't have access to previous messages' output
Auto-background long-running bash commands instead of killing them. Customize with BASH_DEFAULT_TIMEOUT_MS Fixed a bug where Haiku was unnecessarily called in print mode
Added Haiku 4.5 to model selector! Haiku 4.5 automatically uses Sonnet in plan mode, and Haiku for execution (i.e. SonnetPlan by default) 3P (Bedrock and Vertex) are not automatically upgraded yet. Manual upgrading can be done through setting ANTHROPIC_DEFAULT_HAIKU_MODEL Introdu…
Fixed bug with resuming where previously created files needed to be read again before writing Fixed bug with -p mode where @-mentioned files needed to be read again before writing
Fix @-mentioning MCP servers to toggle them on/off Improve permission checks for bash with inline env vars Fix ultrathink + thinking toggle Reduce unnecessary logins Document --system-prompt Several improvements to rendering Plugins UI polish
Plugin System Released: Extend Claude Code with custom commands, agents, hooks, and MCP servers from marketplaces /plugin install, /plugin enable/disable, /plugin marketplace commands for plugin management Repository-level plugin configuration via extraKnownMarketplaces for team…
Reduced system prompt size by 1.4k tokens IDE: Fixed keyboard shortcuts and focus issues for smoother interaction Fixed Opus fallback rate limit errors appearing incorrectly Fixed /add-dir command selecting wrong default tab
Rewrote terminal renderer for buttery smooth UI Enable/disable MCP servers by @mentioning, or in /mcp Added tab completion for shell commands in bash mode PreToolUse hooks can now modify tool inputs Press Ctrl-G to edit your prompt in your system's configured text editor Fixes fo…
Update Bedrock default Sonnet model to global.anthropic.claude-sonnet-4-5-20250929-v1:0 IDE: Add drag-and-drop support for files and folders in chat /context: Fix counting for thinking blocks Improve message rendering for users with light themes on dark terminals Remove deprecate…
IDE: Fix IME unintended message submission with Enter and Tab IDE: Add "Open in Terminal" link in login screen Fix unhandled OAuth expiration 401 API errors SDK: Added SDKUserMessageReplay.isReplay to prevent duplicate messages
Skip Sonnet 4.5 default model setting change for Bedrock and Vertex Various bug fixes and presentation improvements
New native VS Code extension Fresh coat of paint throughout the whole app /rewind a conversation to undo code changes /usage command to see plan limits Tab to toggle thinking (sticky across sessions) Ctrl-R to search history Unshipped claude config command Hooks: Reduced PostTool…
Enable /context command for Bedrock and Vertex Add mTLS support for HTTP-based OpenTelemetry exporters
Set CLAUDE_BASH_NO_LOGIN environment variable to 1 or true to to skip login shell for BashTool Fix Bedrock and Vertex environment variables evaluating all strings as truthy No longer inform Claude of the list of allowed tools when permission is denied Fixed security vulnerability…
Bash permission rules now support output redirections when matching (e.g., Bash(python:*) matches python script.py > output.txt) Fixed thinking mode triggering on negation phrases like "don't think" Fixed rendering performance degradation during token streaming Added SlashCommand…
Fix input lag during typing, especially noticeable with large prompts Improved VSCode extension command registry and sessions dialog user experience Enhanced sessions dialog responsiveness and visual feedback Fixed IDE compatibility issue by removing worktree support check Fixed…
Fix Windows issue where process visually freezes on entering interactive mode Support dynamic headers for MCP servers via headersHelper configuration Fix thinking mode not working in headless sessions Fix slash commands now properly update allowed tools instead of replacing them
Improve thinking mode display with enhanced visual effects Type /t to temporarily disable thinking mode in your prompt Improve path validation for glob and grep tools Show condensed output for post-tool hooks to reduce visual clutter Fix visual feedback when loading state complet…
Deprecated piped input in interactive mode Move Ctrl+R keybinding for toggling transcript to Ctrl+O
Transcript mode (Ctrl+R): Added the model used to generate each assistant message Addressed issue where some Claude Max users were incorrectly recognized as Claude Pro users Hooks: Added systemMessage support for SessionEnd hooks Added spinnerTipsEnabled setting to disable spinne…
/model now validates provided model names Fixed Bash tool crashes caused by malformed shell syntax parsing
/terminal-setup command now supports WezTerm MCP: OAuth tokens now proactively refresh before expiration Fixed reliability issues with background Bash processes
SDK: Added partial message streaming support via --include-partial-messages CLI flag
Windows: Fixed path permission matching to consistently use POSIX format (e.g., Read(//c/Users/...))
Vertex: add support for global endpoints for supported models /memory command now allows direct editing of all imported memory files SDK: Add custom tools as callbacks Added /todos command to list current todo items
Windows: Add alt + v shortcut for pasting images from clipboard Support NO_PROXY environment variable to bypass proxy for specified hostnames and IPs
Fixed issue causing "OAuth authentication is currently not supported" Status line input now includes exceeds_200k_tokens Fixed incorrect usage tracking in /cost. Introduced ANTHROPIC_DEFAULT_SONNET_MODEL and ANTHROPIC_DEFAULT_OPUS_MODEL for controlling model aliases opusplan, opu…
Added /context to help users self-serve debug context issues SDK: Added UUID support for all SDK messages SDK: Added --replay-user-messages to replay user messages back to stdout
Status line input now includes session cost info Hooks: Introduced SessionEnd hook
Fix tool_use/tool_result id mismatch error when network is unstable Fix Claude sometimes ignoring real-time steering when wrapping up a task @-mention: Add ~/.claude/\* files to suggestions for easier agent, output style, and slash command editing Use built-in ripgrep by default;…
SDK: Add request cancellation support SDK: New additionalDirectories option to search custom paths, improved slash command processing Settings: Validation prevents invalid fields in .claude/settings.json files MCP: Improve tool name consistency Bash: Fix crash when Claude tries t…
Released output styles, including new built-in educational output styles "Explanatory" and "Learning". Docs: https://code.claude.com/docs/en/output-styles Agents: Fix custom agent loading when agent files are unparsable
Bash tool: Fix heredoc and multiline string escaping, improve stderr redirection handling SDK: Add session support and permission denial tracking Fix token limit errors in conversation summarization Opus Plan Mode: New setting in /model to run Opus only in plan mode, Sonnet other…
MCP: Support multiple config files with --mcp-config file1.json file2.json MCP: Press Esc to cancel OAuth authentication flows Bash: Improved command validation and reduced false security warnings UI: Enhanced spinner animations and status line visual hierarchy Linux: Added suppo…
Ask permissions: have Claude Code always ask for confirmation to use specific tools with /permissions
Background commands: (Ctrl-b) to run any Bash command in the background so Claude can keep working (great for dev servers, tailing logs, etc.) Customizable status line: add your terminal prompt to Claude Code with /statusline
Performance: Optimized message rendering for better performance with large contexts Windows: Fixed native file search, ripgrep, and subagent functionality Added support for @-mentions in slash command arguments
Fix incorrect model names being used for certain commands like /pr-comments Windows: improve permissions checks for allow / deny tools and project trust. This may create a new project entry in .claude.json - manually merge the history field if desired. Windows: improve sub-proces…
IDE: Fixed connection stability issues and error handling for diagnostics Windows: Fixed shell environment setup for users without .bashrc files
Agents: Added model customization support - you can now specify which model an agent should use Agents: Fixed unintended access to the recursive agent tool Hooks: Added systemMessage field to hook JSON output for displaying warnings and context SDK: Fixed user input tracking acro…
Windows: Fixed file search, @agent mentions, and custom slash commands functionality
Added @-mention support with typeahead for custom agents. @ to invoke it Hooks: Added SessionStart hook for new session initialization /add-dir command now supports typeahead for directory paths Improved network connectivity check reliability
Transcript mode (Ctrl+R): Changed Esc to exit transcript mode rather than interrupt Settings: Added --settings flag to load settings from a JSON file Settings: Fixed resolution of settings files paths that are symlinks OTEL: Fixed reporting of wrong organization after authenticat…
SDK: Added tool confirmation support with canUseTool callback SDK: Allow specifying env for spawned process Hooks: Exposed PermissionDecision to hooks (including "ask") Hooks: UserPromptSubmit now supports additionalContext in advanced JSON output Fixed issue where some Max users…
Added support for reading PDFs MCP: Improved server health status display in 'claude mcp list' Hooks: Added CLAUDE_PROJECT_DIR env var for hook commands
Added support for specifying a model in slash commands Improved permission messages to help Claude understand allowed tools Fix: Remove trailing newlines from bash output in terminal wrapping
Windows: Enabled shift+tab for mode switching on versions of Node.js that support terminal VT mode Fixes for WSL IDE detection Fix an issue causing awsRefreshHelper changes to .aws directory not to be picked up
Clarified knowledge cutoff for Opus 4 and Sonnet 4 models Windows: fixed Ctrl+Z crash SDK: Added ability to capture error logging Add --system-prompt-file option to override system prompt in print mode
Hooks: Added UserPromptSubmit hook and the current working directory to hook inputs Custom slash commands: Added argument-hint to frontmatter Windows: OAuth uses port 45454 and properly constructs browser URL Windows: mode switching now uses alt + m, and plan mode renders properl…
Updated @-mention file truncation from 100 lines to 2000 lines Add helper script settings for AWS token refresh: awsAuthRefresh (for foreground operations like aws sso login) and awsCredentialExport (for background operation with STS-like response).
Added support for native Windows (requires Git for Windows) Added support for Bedrock API keys through environment variable AWS_BEARER_TOKEN_BEDROCK Settings: /doctor can now help you identify and fix invalid setting files --append-system-prompt can now be used in interactive mod…
Fixed a bug in v1.0.45 where the app would sometimes freeze on launch Added progress messages to Bash tool based on the last 5 lines of command output Added expanding variables support for MCP server configuration Moved shell snapshots from /tmp to ~/.claude for more reliable Bas…
Redesigned Search (Grep) tool with new tool input parameters and features Disabled IDE diffs for notebook files, fixing "Timeout waiting after 1000ms" error Fixed config file corruption issue by enforcing atomic writes Updated prompt input undo to Ctrl+\_ to avoid breaking existi…
New /export command lets you quickly export a conversation for sharing MCP: resource_link tool results are now supported MCP: tool annotations and tool titles now display in /mcp view Changed Ctrl+Z to suspend Claude Code. Resume by running fg. Prompt input undo is now Ctrl+U.
Fixed a bug where the theme selector was saving excessively Hooks: Added EPIPE system error handling
Hooks: Split Stop hook triggering into Stop and SubagentStop Hooks: Enabled optional timeout configuration for each command Hooks: Added "hook_event_name" to hook input Fixed a bug where MCP tools would display twice in tool list New tool parameters JSON for Bash tool in tool_dec…
Fixed a bug causing API connection errors with UNABLE_TO_GET_ISSUER_CERT_LOCALLY if NODE_EXTRA_CA_CERTS was set
Released hooks. Special thanks to community input in https://github.com/anthropics/claude-code/issues/712. Docs: https://code.claude.com/docs/en/hooks
Remove ability to set Proxy-Authorization header via ANTHROPIC_AUTH_TOKEN or apiKeyHelper
Web search now takes today's date into context Fixed a bug where stdio MCP servers were not terminating properly on exit
Improved logging functionality with session ID support Added prompt input undo functionality (Ctrl+Z and vim 'u' command) Improvements to plan mode
Updated loopback config for litellm Added forceLoginMethod setting to bypass login selection screen
Custom slash commands: Run bash output, @-mention files, enable thinking with thinking keywords Improved file path autocomplete with filename matching Added timestamps in Ctrl-r mode and fixed Ctrl-c handling Enhanced jq regex support for complex filters with pipes and select
Slash commands: Fix selector display during history navigation Resizes images before upload to prevent API size limit errors Added XDG_CONFIG_HOME support to configuration directory Performance optimizations for memory usage New attributes (terminal.type, language) in OpenTelemet…
Streamable HTTP MCP servers are now supported Remote MCP servers (SSE and HTTP) now support OAuth MCP resources can now be @-mentioned /resume slash command to switch conversations within Claude Code
Slash commands: moved "project" and "user" prefixes to descriptions Slash commands: improved reliability for command discovery Improved support for Ghostty Improved web search reliability
Improved /mcp output Fixed a bug where settings arrays got overwritten instead of merged
Released TypeScript SDK: import @anthropic-ai/claude-code to get started Released Python SDK: pip install claude-code-sdk to get started
Improved editing of files with tab-based indentation Fix for tool_use without matching tool_result errors Fixed a bug where stdio MCP server processes would linger after quitting Claude Code
Improved thinking triggering reliability Improved @mention reliability for images and folders You can now paste multiple large chunks into one prompt
Ask Claude to make a plan with thinking mode: just say 'think' or 'think harder' or even 'ultrathink'
Added --add-dir CLI argument for specifying additional working directories Added streaming input support without require -p flag Improved startup performance and session storage performance Added CLAUDE_BASH_MAINTAIN_PROJECT_WORKING_DIR environment variable to freeze working dire…
We now emit messages from sub-tasks in -p mode (look for the parent_tool_use_id property) Fixed crashes when the VS Code diff tool is invoked multiple times quickly MCP server list UI improvements Update Claude Code process title to display "claude" instead of "node"
Claude Code can now also be used with a Claude Pro subscription Added /upgrade for smoother switching to Claude Max plans Improved UI for authentication from API keys and Bedrock/Vertex/external auth tokens Improved shell configuration error handling Improved todo list handling d…
Fixed Vertex AI region fallback when using CLOUD_ML_REGION Increased default otel interval from 1s -> 5s Fixed edge cases where MCP_TIMEOUT and MCP_TOOL_TIMEOUT weren't being respected Fixed a regression where search tools unnecessarily asked for permissions Added support for tri…
Renamed /allowed-tools -> /permissions Migrated allowedTools and ignorePatterns from .claude.json -> settings.json Deprecated claude config commands in favor of editing settings.json Fixed a bug where --dangerously-skip-permissions sometimes didn't work in --print mode Improved e…
Improved edit reliability for tab-indented files Respect CLAUDE_CONFIG_DIR everywhere Reduced unnecessary tool permission prompts Added support for symlinks in @file typeahead Bugfixes, UI polish, and tool reliability improvements
Added DISABLE_INTERLEAVED_THINKING to give users the option to opt out of interleaved thinking. Improved model references to show provider-specific names (Sonnet 3.7 for Bedrock, Sonnet 4 for Console) Updated documentation links and OAuth process descriptions
Breaking change: Bedrock ARN passed to ANTHROPIC_MODEL or ANTHROPIC_SMALL_FAST_MODEL should no longer contain an escaped slash (specify / instead of %2F) Removed DEBUG=true in favor of ANTHROPIC_LOG=debug, to log all requests
Breaking change: --print JSON output now returns nested message objects, for forwards-compatibility as we introduce new metadata fields Introduced settings.cleanupPeriodDays Introduced CLAUDE_CODE_API_KEY_HELPER_TTL_MS env var Introduced --debug mode
You can now send messages to Claude while it works to steer Claude in real-time Introduced BASH_DEFAULT_TIMEOUT_MS and BASH_MAX_TIMEOUT_MS env vars Fixed a bug where thinking was not working in -p mode Fixed a regression in /cost reporting Deprecated MCP wizard interface in favor…
CLAUDE.md files can now import other files. Add @path/to/file.md to ./CLAUDE.md to load additional files on launch
MCP SSE server configs can now specify custom headers Fixed a bug where MCP permission prompt didn't always show correctly