Releases: anthropics/claude-code
Releases · anthropics/claude-code
v2.1.178
What's changed
- Added
Tool(param:value)syntax for permission rules to match a tool's input parameters (with*wildcard), e.g.Agent(model:opus)to block Opus subagents - Skills in nested
.claude/skillsdirectories now load when working on files there; on a name clash, the nested skill appears as<dir>:<name>so both stay available - Nested
.claude/directories: the agent, workflow, and output-style closest to the working directory now wins when names collide; project-scope workflow saves now target the closest existing.claude/workflows/ - Improved auto mode: subagent spawns are now evaluated by the classifier before launch, closing a gap where a subagent could request a blocked action without review
- Improved
/doctorwith consistent flat tree layout across all sections, clearer section status icons, and highlighted command names - Improved the skill listing truncation warning to show how many skill descriptions are affected
- Changed the workflow prompt keyword to use a purple shimmer highlight and trigger only on explicit phrases like "run a workflow" or "workflow:", not on any mention of the word
- Improved Remote Control error messages: connection failures now show a persistent red "/rc failed" indicator in the footer, and the "not yet enabled" error now explains whether it's a gate, a check failure, stale entitlement, or org policy
/bugnow requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title- Fixed a crash (out-of-memory) when the CLI inherits a stale websocket/OAuth file-descriptor environment variable from a parent process
- Fixed Claude in Chrome silently failing to connect when the OAuth token belongs to a different account than the Claude Code login
- Fixed nested
.claude/skillsskills with directory-qualified names being blocked by permission prompts in non-interactive runs - Fixed several subagent issues: viewing a subagent's transcript now shows tool results and live progress, messages sent while it finishes its turn are no longer dropped, and backgrounding a running subagent (ctrl+b) no longer restarts it from scratch
- Fixed
claude agentsworkers failing with401 Invalid bearer tokenwhen the daemon was started from a shell with a custom API gateway viaANTHROPIC_BASE_URLandANTHROPIC_AUTH_TOKEN - Fixed compaction not honoring
--fallback-model: compaction now falls back to the configured fallback model chain on overload or model-availability errors - Fixed model requests continuing to fail with auth errors after credentials were refreshed outside the session, due to a stale cached request configuration
- Fixed background sessions created with
/bgor←←after a turn finished showing "Working" forever in the agents list - Fixed
CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1preventing fresh marketplace installs from cloning - Fixed MCP server-level specs (
mcp__server,mcp__server__*,mcp__*) in subagentdisallowedToolsbeing silently ignored - Fixed vim mode undo:
unow steps through NORMAL/VISUAL-mode commands one at a time instead of merging commands in quick succession into a single undo step - Fixed statusline links with custom URI schemes (e.g.
vscode://) not opening when clicked inclaude agents - [VSCode] Fixed pressing Esc to dismiss a CJK IME candidate window canceling the running Claude task
v2.1.177
chore: Update CHANGELOG.md and feed.xml
v2.1.176
What's changed
- Session titles are now generated in the language of your conversation (set the
languagesetting to pin a specific language) - Added
footerLinksRegexessetting for regex-matched link badges in the footer row, configurable via user or managed settings - Improved Bedrock credential caching: credentials from
awsCredentialExportare now cached until theirExpirationinstead of a fixed 1 hour - Fixed
availableModelsenforcement: alias model picks can no longer be redirected to a blocked model viaANTHROPIC_DEFAULT_*_MODELenvironment variables, and/fastnow refuses to toggle when it would switch to a model outside the allowlist - Fixed auto mode failing on Fable 5 for organizations without Opus 4.8 enabled — the classifier now falls back to the best available Opus model
- Fixed hook
ifconditions for Read/Edit/Write tool paths: documented patterns likeEdit(src/**),Read(~/.ssh/**), andRead(.env)now match correctly - Fixed Linux sandbox failing to start when
.claude/settings.jsonis a symlink with an absolute target - Fixed
/copyand mouse-selection copy not reaching the system clipboard inside tmux over SSH, and tmux paste buffer not loading on versions older than 3.2 - Fixed Remote Control connecting from web/mobile silently switching the session's model
- Fixed Remote Control disconnect notifications showing a bare numeric code instead of a human-readable reason, and connection failures adding a duplicate line to the conversation transcript
- Fixed Remote Control sessions not disconnecting when you sign in to a different account
- Fixed
/cdand worktree moves leaving the session reporting the previous directory's git branch - Fixed
claude agents: pressing back in one window no longer detaches other windows attached to the same session - Fixed backgrounded sessions showing "Working" forever when
/bgmid-turn had nothing left to continue - Fixed background agent search by PR URL: PRs opened during scheduled wakeups or while a job was blocked now appear in
claude agentssearch - Fixed the agents view input showing no text cursor on Windows
- Fixed
claude --bg -cn <name>not seeding the session name - Fixed background sessions to neutralize Windows network paths in persisted state before respawn
- Fixed background-session respawn rejecting malformed resume IDs from corrupted state files
- Fixed the Windows background-service daemon not starting when
~/.claude/daemonhas the ReadOnly attribute set - Fixed cloud sessions failing with "Could not resolve authentication method" when idle for too long before being claimed
- Background sessions now show clearer guidance when a window left open across an auto-update can't submit a reply, and
claude daemon statusexplains version-skew behavior
v2.1.175
What's changed
- Added
enforceAvailableModelsmanaged setting — when enabled, theavailableModelsallowlist 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 managedavailableModelslist
v2.1.174
What's changed
- Added
wheelScrollAccelerationEnabledsetting to disable mouse-wheel scroll acceleration in fullscreen mode - Fixed the
/modelpicker 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, and Opus on pay-as-you-go API accounts - Fixed
/modelpicker showing a hardcoded Sonnet version label whenANTHROPIC_DEFAULT_SONNET_MODELpins a different Sonnet - Fixed the "Fable 5 is now consuming usage credits" banner incorrectly showing for enterprise accounts with usage-based billing
- Fixed Bedrock GovCloud regions (
us-gov-*) deriving the wrong inference profile prefix (globalinstead ofus-gov), causing 400 errors on derived model IDs - Fixed background sessions inheriting another session's
ANTHROPIC_*provider env (gateway URL, custom headers,/modelaliases) from the shell that started the background daemon - Fixed a 1-2 second pause when exiting Claude Code shortly after a shell command was interrupted or killed on macOS and Linux
- Fixed git commit co-author attribution showing an incorrect model name for some models
- Fixed the
/advisordialog pre-selecting a saved advisor model that is blocked by theavailableModelsallowlist - Fixed skill hot-reload re-sending the entire skill listing when a single skill changed; only changed skills are now re-announced
- Fixed Workflow tool
agent()subagents missing per-agent attribution headers - [VSCode] Added usage attribution to the Account & usage dialog (
/usage) showing cache misses, long context, subagents, and per-skill/agent/plugin/MCP breakdowns over the last 24h or 7d - Fixed pre-warmed background workers failing with "Could not resolve authentication method" when claimed after sitting idle
v2.1.173
What's changed
- 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
v2.1.172
What's changed
- Sub-agents can now spawn their own sub-agents (up to 5 levels deep)
- Amazon Bedrock now reads the AWS region from
~/.awsconfig files whenAWS_REGIONisn't set, matching AWS SDK precedence;/statusshows where the region came from - Added a search bar when browsing a marketplace's plugins in
/plugin - Added
modelattribute to theclaude_code.lines_of_code.countOTEL metric - Fixed sessions using 1M context without usage credits getting permanently stuck — the session now automatically compacts back under the standard context limit
- Fixed a repeating "an image in the conversation could not be processed and was removed" error when the conversation contained multiple images
- Fixed the agents view keeping a session under Working with a busy spinner for up to 30 seconds after the worker replied
- Fixed background agents potentially reading another directory's project settings (
.mcp.jsonapprovals, trust) when dispatched onto a pre-warmed worker - Fixed background-session attach failing with EAUTH for sessions started on an older version after the daemon auto-updated
- Fixed a background sub-agent staying stuck as "active" in the agent panel after a nested agent it spawned was stopped
- Fixed
/modelsuggestions in theclaude agentsdispatch input rendering with a misleading slash prefix and showing models disabled for your org - Fixed
availableModelsrestrictions not being applied to subagent model overrides, the agent dispatch model picker, and the advisor model - Fixed
availableModelsallowlists hiding the/modelpicker's Opus and Sonnet 1M rows when entries use version-specific IDs likeclaude-opus-4-8 - Fixed the
/modelpicker on Bedrock offering models the provider doesn't serve — selecting one silently switched the session model and lit the selection marker on multiple rows - Fixed model IDs getting a doubled 1M-context suffix (e.g.
[1M][1m]) whenANTHROPIC_DEFAULT_OPUS_MODELalready includes one - Fixed
opusplanmodel setting not shipping with 1M context in plan mode for entitled users; theopusplan[1m]workaround now also correctly switches to Opus in plan mode - Fixed
WebFetch(domain:*.example.com)wildcard domain rules never matching subdomains in allow, deny, and ask position, and file permission rules with mid-pattern wildcards (e.g.Read(secrets-*/config.json)) being rejected at startup - Fixed up-arrow prompt history showing the main agent's prompts while a subagent's chat tab is open
- Fixed memory recall not finding mounted team memory stores (
CLAUDE_MEMORY_STORES) in remote sessions - Fixed workflow validation rejecting scripts whose prompt strings or comments merely mention
Date.now()/Math.random() - Disable mouse tracking on Windows consoles that don't fully support it
- Fixed the
/pluginmarketplace list losing its cursor after backing out of a long plugin list, and Esc from the plugin browser returning to the wrong tab - Improved performance in long conversations by removing redundant message normalization and avoiding full message-history transforms when streaming tool-use state is unchanged
- Reduced idle CPU usage:
/goalstatus chip no longer re-renders the terminal at 5 Hz while idle, and fewer UI re-renders while subagents run in parallel - Improved Claude in Chrome tool loading: browser tools now load in a single batched call instead of one per tool
- Improved the non-interactive Usage Policy refusal message to suggest starting a new session or changing your model
/code-reviewnow keeps theultraoption visible when you're not signed in to claude.ai, with an explanation that the cloud review requires a claude.ai account- Shortened the Remote Control footer indicator to "/rc active" and hid it on narrow terminals
- Stopped promoting
/loopin remote sessions, where pending loops don't keep the container alive - [VSCode] Fixed PowerShell tool calls rendering as raw JSON instead of a proper command display and permission dialog, and stripped ANSI escape codes from displayed shell output
v2.1.170
What's changed
- 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 not saving transcripts (and not appearing in --resume) when launched from the VS Code integrated terminal or any shell that inherited Claude Code environment variables.
v2.1.169
What's changed
- Added
--safe-modeflag (andCLAUDE_CODE_SAFE_MODE) to start Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting - Added
/cdcommand to move a session to a new working directory without breaking the prompt cache mid-session - Added a
disableBundledSkillssetting andCLAUDE_CODE_DISABLE_BUNDLED_SKILLSenvironment variable to hide bundled skills, workflows, and built-in slash commands from the model - Fixed Up/Down arrows jumping to command history past the wrapped rows of a long input line — they now move through each visual row first, and history recall enters at the near edge
- Fixed enterprise managed MCP policies (
allowedMcpServers/deniedMcpServers) not being enforced on reconnect, IDE-typed configs,--mcp-configservers during the first session after install, or before remote settings loaded; also fixed slow cold starts for orgs without remote settings - Fixed a ~30-50ms UI stall at the start of each turn for macOS users logged in with claude.ai credentials
- Fixed
claude -pbeing slow or appearing to hang on Windows while waiting for the slash-command/skill scan (regression in 2.1.161) - Fixed Remote Control getting stuck on "reconnecting" after resuming a session when an OAuth token refresh happened at the same time
- Fixed Git Credential Manager's "Connect to GitHub" popup appearing on Windows at startup when background git commands ran without cached credentials
- Fixed footer hints (e.g. "esc to interrupt") not showing for users with a custom statusline
- Fixed stale permission and dialog prompts reappearing every time you reattached to a remote session whose worker had died while waiting on them
- Fixed
claude agents --jsonomitting blocked and just-dispatched background sessions; added--allto include completed sessions, plus newidandstatefields - Fixed agents view leaving a stale/garbled frame after navigating back from an agent on WSL in Windows Terminal
- Fixed background agents ignoring project-level settings
envvalues (e.g.ANTHROPIC_MODEL) when dispatched onto a pre-warmed worker - Fixed MCPB plugin cache being spuriously invalidated on Windows, causing unnecessary re-extraction
- Fixed plugin
.in_usePID lock files accumulating without bound; stale markers from crashed sessions are now swept once per day - Fixed untrusted project settings being able to set OTEL client-certificate paths without trust confirmation
/workflowsnow opens immediately even while a turn is in progress- Improved
TaskCreatereliability: malformed inputs are repaired automatically and validation errors for unloaded tools include the schema - Improved the error message shown when your organization has disabled API key authentication, with guidance based on where the active API key comes from
- Reduced CPU usage while responses stream and during spinner animations
- Restored a default 5-minute idle timeout on Vertex/Foundry so a stalled stream aborts instead of hanging indefinitely; set
API_FORCE_IDLE_TIMEOUT=0to opt out - Remote-managed settings with an invalid entry now apply their remaining valid policies and surface the validation error, instead of silently dropping the whole payload
- Background sessions now preserve
--ide,--chrome,--bare,--remote-control, and other flags across retire→wake, and respawn state validation was hardened - Background sessions are now told that shared-checkout edits are blocked until they enter a worktree, avoiding a wasted rejected edit before
EnterWorktree - The "CLAUDE.md is too long" warning threshold now scales with the model's context window
- Auto-updater on Windows now stops retrying within a session once
claude.exeis held by another process - Improved color contrast for skill tags in the slash-command menu
- Promo credit claims for Apple/Google-billed subscribers without a payment method now explain where to add one
- Added a tip suggesting
claude agentswhen running multiple concurrent sessions
v2.1.168
What's changed
- Bug fixes and reliability improvements