Skip to content

Claude Code 2.1.319

146changes
  • Run MCP tool calls as background tasks in the terminal, with Claude told the result when they finish.
  • Add a permissions.denyInsteadOfPrompting setting that denies rather than waits on a permission prompt.
  • Fix a sandbox escape that let creating a worktree run outside its boundary.
  • Fix a plan-mode consent bypass that let an unapproved turn run after resuming in another permission mode.
  • Fix a sed command that could skip the permission check in accept-edits and auto mode.

New features

18
More changes (14) Fewer changes

Add flag to disable MCP task backgrounding

Added the CLAUDE_CODE_DISABLE_MCP_TASK_BACKGROUND environment variable to make Claude Code wait for an MCP task inside its tool call instead of moving it to the background right away

▤ In the docs

Add flag to disable feature-flag fetching

Added the CLAUDE_CODE_DISABLE_FEATURE_FLAGS environment variable, which stops feature-flag fetching without turning off telemetry; every flag then uses its built-in default

Show spend totals in /usage behind gateway

Added spend for today, this week and this month to /usage for developers behind a Claude apps gateway who have no spend limit, when the gateway runs this version or later

Add pooled budget priority settings to gateway

Added admin.pooled_conflict_rule and admin.pooled_priority_order to the Claude apps gateway, to set which pooled group budget pays first for a developer in several groups

Add login_notice setting to gateway

Added an optional login_notice setting to the Claude apps gateway that shows an operator-defined message on the gateway's browser verification page and on Claude Code's sign-in screen

Add JSON log format to the gateway

Added CLAUDE_GATEWAY_LOG_FORMAT=json to the Claude apps gateway: operational log lines become JSON with severity, time and message, for log collectors that read the level from a field

Warn on duplicate custom model ids

Added a Claude apps gateway boot warning for a case where another policy's availableModels also allows a custom model id that one policy lists by name

Warn on desktopHome-dependent gateway settings

Added start-up warnings to the Claude apps gateway for policies with no desktopHome that rely on coworkTabEnabled: false or chatSessionRetentionDays, ahead of Claude Desktop's November 10 change

Warn on falling back to ant auth

Added a warning when your claude.ai login ends and Claude Code continues on the sign-in from ant auth login, which bills usage to your Claude Console organization

Show the billed organization at startup

Added a line at startup naming the Claude Console organization that is billed in a case where Claude Code uses the sign-in from ant auth login

Note that cloud /loop stops with container

Added a note to /loop confirmations in cloud sessions that a timer stops with its container, with an offer of a loop that survives

Warn on mixed GovCloud upstreams

Gateway: Added startup warnings for upstreams that mix AWS GovCloud with other upstreams, and for base URL variables in the gateway's environment

Warn on unforwarded Bedrock guardrail headers

Gateway: Added a start-up log warning when managed settings name an Amazon Bedrock guardrail in a header, which the gateway doesn't forward, and no bedrock upstream sets a guardrail

[Claude Tag] Add Claude Tag row to Models admin

Added a Claude Tag row to the Models admin page for Enterprise orgs with Claude Tag connected, linking to where its model defaults are managed

Improvements

36
More changes (34) Fewer changes

Allow auto mode server check with betas off

Changed auto mode behind an LLM gateway: CLAUDE_CODE_AUTO_MODE_SERVER=1 turns on the server-side check even with CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS set; if managed settings set the latter, they must set the 1 too

Wait longer for locked files on Windows

Improved config saves on Windows: Claude Code waits longer for a file another program has open, so a kill during a save is less likely to leave ~/.claude.json empty

Wait for the same browser to return

Improved Claude in Chrome after a brief disconnect: it waits up to 6 seconds for the session's own browser to return before picking another

Keep larger javascript_tool results inline

Improved Claude in Chrome: javascript_tool results of up to 60,000 characters now stay in the conversation instead of being saved to a file

Retry failed deletes in claude purge

Improved claude purge and the clean-up of old sessions to retry a folder that could not be fully deleted, and to report it as an error if it remains

Name the case-matching path in refusal messages

Improved the refusal for a path outside the working directories on macOS and Windows: when only its letter case differs from a path inside them, the message names that spelling

Improve contrast of faint secondary text

Improved the contrast of faint gray secondary text, such as hints, details in /stats, /model and /sandbox, and rejected-action messages

Clarify artifact database update errors

Improved the artifact database error when an update targets a document that does not exist, and when the service pauses repeated refused writes

Name the upstream in gateway call warnings

Improved the Claude apps gateway's warnings about a failed upstream call: each now names the upstream, not only its provider

Show reset date in spend limit errors

Improved the Claude apps gateway's spend limit error: it reads "spend limit reached · resets Dec 1", then admin.blocked_message if one is set

Group older models under More models

Improved the /model picker: older models are now grouped under a "More models" row instead of being listed after the current ones

Shrink the /context table Claude reads

Improved /context at the terminal so the table Claude reads stays short: each list keeps its 10 largest rows, and MCP tools that load on demand share one row per server until they're called

Link to claude.ai when limits are hidden

Improved /usage in cloud sessions: it now links to Settings → Usage on claude.ai in a case where plan limits can't be shown

[VSCode] Check installed plugins before marketplace removal

Improved the confirmation for removing a plugin marketplace: it now checks which of its plugins are installed at that moment

▤ In the docs

Enable MCP tasks without feature-flag fetching

Changed MCP tasks to work in the terminal without feature-flag fetching (Bedrock, Vertex, Foundry, LLM gateways, DISABLE_TELEMETRY); set CLAUDE_CODE_DISABLE_MCP_TASKS=1 to turn them off

Stop projects re-enabling auto mode checks

Changed auto mode so that a project's settings files or a plugin can no longer switch its server-side check back on once you have switched it off outside the project

Restrict CLAUDE_CODE_PROXY_RESOLVES_HOSTS to the environment

Changed CLAUDE_CODE_PROXY_RESOLVES_HOSTS so that settings files can no longer set it where the host manages the network; set it in the process environment

Let deny rules override narrower ask rules

Changed a session's exact Bash or PowerShell ask rule to be refused, not asked about, when a broader deny rule covers the command

Ask before which with unusual flags

Changed the Bash tool to ask for permission before running which with flags outside a lookup/display set

Require trust before registering marketplaces

Changed --add-dir directories to register plugin marketplaces only once that directory's own trust dialog has been accepted

Limit nested skill loading under the sandbox

Changed nested skill loading: with the Bash sandbox on, skills in .claude/skills folders below the starting folder load only if you start Claude Code there or /cd there

End self-paced /loop without a fallback wakeup

Changed self-paced /loop to end when a turn finishes without rescheduling, instead of scheduling a fallback wakeup; set CLAUDE_CODE_LOOP_KEEPALIVE=1 to keep the old behavior

Run PostToolUse hooks after interrupted turns

Changed PostToolUse hooks to run, with up to 10 seconds to finish, on tool calls that finish after a new message interrupts the turn

Guide retries after a stopped subagent

Changed what Claude is told after safeguards stop a subagent: retry with a narrower prompt or tell you, instead of doing the work itself

Drop allow rules when deny/ask can't transfer

Changed cloud sessions to drop session-scoped allow rules at a move to a new worker when their deny and ask rules can't all be kept, so you may be asked again

Require HTTPS_PROXY for certificate repair

Changed the automatic certificate repair behind a TLS-inspecting proxy: it no longer runs when ALL_PROXY is the only proxy variable set. Set HTTPS_PROXY to the proxy's http:// URL instead

Mark artifact database export files

Changed artifact database saves of rows others may have written: each file gets a hidden marker file, and existing files without one, earlier versions' exports among them, are left alone and reported

Update managed-agents-onboard templates

Updated /claude-api managed-agents-onboard templates to match the Claude Console: removed Performance tuner, renamed two, and turned off web search and fetch in five whose prompts don't use them

Give each checkout its own folder

Self-hosted runner: Changed CLAUDE_RUNNER_CHECKOUT_PATH so that each repository in a session gets its own folder: a folder name already taken in the session gets -2, -3, … at the end

[VSCode] Improve the not-signed-in gateway message

Improved the "not signed in" message behind a Claude apps gateway: it now looks like an error and has a Sign in link

[VSCode] Show auth links as plain text

Changed links in Claude's replies that point at Claude sign-in, connector or API addresses to show as text with the address, instead of opening in the browser

[VSCode] Shrink diagnostics tool output for large workspaces

Improved the chat panel's diagnostics tool for large workspaces: it leaves out files with no problems, returns compact JSON, and accepts an optional minimum severity

[Cloud sessions] Improve stalled-setup warning links

Improved the stalled-setup warning on self-hosted environments: its link now prefers your organization's default or an environment with a live runner, and names it

[Code Review] Turn off All repositories on unlink

Changed unlinking a GitHub organization to also turn off its All repositories setting in Code Review; it stays off after you relink until you turn it back on

Bug fixes

90

Stop sending /context's full grid every turn

Fixed /context sending its full visual grid to Claude on every later turn; Claude now reads only the table

Run slash commands after leading whitespace

Fixed slash commands typed after a leading space, tab or newline being sent to Claude as plain text instead of running

Exit nonzero when auto mode lacks checks

Fixed claude -p exiting 0 in auto mode when its actions were refused because no safety check was available: text and JSON output now exit 1

Stop replaying unapproved plan-mode turns

Fixed CLAUDE_CODE_RESUME_INTERRUPTED_TURN re-running a turn that was interrupted in plan mode when the session resumes in another permission mode

[VSCode] Stop carrying out unapproved plans

Fixed Claude carrying out an unapproved plan after a window reload: a step interrupted in plan mode now stops with a notice when the session comes back in another permission mode

Fix a sandbox escape creating a worktree

Fixed a sandbox escape when creating a worktree

Fix sed skipping the permission check

Fixed a case where a sed command could skip the permission check in accept-edits and auto mode

Fix environment prefix hiding commands from checks

Fixed a Bash permission bypass where a crafted environment prefix could hide part of a command from permission checks

Block hooks and skills with --trust-workspace false

Fixed self-hosted runners: --trust-workspace false now also stops hooks in the repository's settings files and skills from running

Fix connector tool names ignored in Desktop

Fixed a case where deny and ask rules, hook matchers and disallowedTools entries written with a claude.ai connector's terminal name (mcp__claude_ai_Slack) were ignored in Claude Desktop (takes effect once Claude Desktop includes this version)

Fix /rewind writing through a symlink

Fixed a case where /rewind could restore or delete a file through a directory symlink

Fix quoted words evading Bash deny/ask rules

Fixed a case where Bash deny and ask rules missed commands written with quoted words

Preserve permission rules across worker moves

Fixed cloud sessions losing session-scoped deny and ask permission rules, such as those a PermissionRequest hook adds, when the session moves to a new worker

Fix auto mode setting ignored behind gateway

Fixed a case where CLAUDE_CODE_AUTO_MODE_SERVER=1 in managed settings was ignored behind an LLM gateway when the gateway's URL is set only there and server-managed settings can't be fetched

More changes (76) Fewer changes

Fix older-handshake MCP servers failing

Fixed MCP servers on the older handshake failing to connect, or returning empty results, because Claude Code declared an extension that it only uses with newer servers

Fix lost MCP results after --resume

Fixed a long-running MCP tool call on a claude.ai connector sometimes never reporting its result after --resume

Fix diff failures from a HEAD file

Fixed a session's diff failing to load on claude.ai and the mobile apps when the folder Claude Code runs in has a file or folder named HEAD

Fix /diff unavailable with a HEAD file

Fixed /diff showing "Diff unavailable" when a git repository has a file or folder named HEAD at its top level

Fix blank /diff pane after many edits

Fixed the /diff pane opening blank in sessions where 64 or more turns edited files

Fix repeated login refresh on 401 retries

Fixed a request that kept failing with a 401 refreshing your login on every retry and causing 401s in your other sessions

Fix full file listing on network filesystems

Fixed a case where Claude Code listed every project file at start on Linux for projects on a network file system (NFS, SMB, Lustre and similar)

Fix auto mode refused after model change

Fixed a case where auto mode was wrongly refused when a client sent a model change and a request for auto mode back to back

Fix /status overstating auto mode server state

Fixed /status showing "Auto mode server: Enabled" when the server-side review isn't reaching the session, for example behind an LLM gateway that drops it

Stop feedback prompts after org opt-out

Fixed Claude-drafted feedback, surveys and /feedback continuing to appear after the server refused feedback for your organization

Stop drafting feedback on third-party gateways

Fixed Claude drafting feedback on third-party gateways, where it can't be sent

Explain refusals from oversized permission rules

Fixed auto mode refusing actions without saying why when permission rules or autoMode settings are very large: it now explains and, unless autoMode deny rules are set, asks you in the terminal

Hide subagent hand-back internal markers

Fixed subagent hand-back reports showing an internal marker and provenance note when expanded outside verbose mode

Keep deferred tool calls on missing MCP

Fixed claude -p --resume with a prompt losing a deferred tool call when its MCP server is missing: the run now exits 1, keeps the call and refuses later input

Fix dropped text in SDK informational messages

Fixed a case where text was dropped from informational messages sent to SDK clients

Show real errors for SDK disk-full failures

Fixed a case where Agent SDK hosts got a generic exit-code error instead of a failed run's own error message when the disk was full

Fix settings edits ignored after a write

Fixed edits to a settings file being ignored when made within a few seconds of Claude Code writing that file

Warn about duplicate legacy config files

Fixed a config file left at the legacy name hiding your setup with no warning: Claude Code now says on stderr when a home holds two config files, and which is in use

Fix truncated saves when disk fills mid-write

Fixed ~/.claude.json, settings and edited files ending up empty or cut off when the disk fills during a save in a read-only folder or to a bind-mounted file (one session saving at a time)

Fix Write misreporting unreadable files as refusals

Fixed Write ending the turn as a refusal when it couldn't read the file to overwrite

Fix lost output from near-instant bg commands

Fixed background Bash commands that finish almost instantly losing their output while being reported as completed

Fix Bash diff missing last-written files

Fixed the Bash tool's diff of changed files missing a file that the command wrote just before it ended

Suggest the right model for a typo

Fixed a mistyped model name, such as opus-5-5, telling you to update Claude Code instead of suggesting the model you meant

Fix NotebookEdit targeting the wrong cell

Fixed a case where NotebookEdit changed the wrong cell when the notebook changed while a permission prompt was open

Fix brief hang after login success

Fixed a ~0.5s hang after pressing Enter on the /login success screen: the dialog now dismisses immediately and the post-login refresh runs in the background

Fix Ctrl+G in screen reader mode

Fixed Ctrl+G not opening the external editor while typing an "Other" answer to a question in screen reader mode

Fix Monitor watch DNS failure behind proxy

Fixed Monitor's WebSocket watch failing with "could not resolve" behind a proxy when CLAUDE_CODE_PROXY_RESOLVES_HOSTS is set and the machine has no DNS of its own

Fix impossible max: 0 eval suggestion

Fixed claude plugin eval warnings suggesting max: 0 for a tool that must not be called, which could never pass

Install new dependencies on plugin auto-update

Fixed background plugin auto-update not installing a dependency added by the updated plugin version

Fix Cmd+click links in Ghostty over tmux

Fixed Cmd+click not opening links in Ghostty over tmux in sessions opened from the agents view

Fix mod reload missing quickly deleted files

Fixed a mod's hot reload in .claude/skills missing a file that was deleted just after it appeared, and missing its return

Fix /rewind failing past a /branch point

Fixed /rewind failing with "No files were restored" when restoring code to a checkpoint from before /branch

Fix /claude-api skill's Managed Agents guidance

Fixed the /claude-api skill saying Console web settings don't apply to Managed Agents sessions, and tightened its credential and permission examples

Stop needless prompts for timeout-wrapped commands

Fixed needless permission prompts for read-only commands wrapped in a plain timeout DURATION, such as timeout 30 rg foo

Explain WebFetch limits on shared-chat links

Fixed WebFetch describing claude.ai shared-chat links as empty pages; it now says shared chats can't be read and to paste the conversation instead

Clarify Artifact database errors without a database

Fixed Artifact database calls being re-sent to artifacts without a database; errors now say whether republishing helps

Fix refused artifact database reads to out_dir

Fixed a case where artifact database reads that save to a folder (out_dir) were refused

Send client cert for detailed beta tracing

Fixed detailed beta tracing not presenting CLAUDE_CODE_CLIENT_CERT to collectors that require a client certificate

Fix session count metric over-counting prewarm()

Fixed the OpenTelemetry claude_code.session.count metric counting Agent SDK prewarm() processes that were never claimed; a pre-started process now counts once, when it is claimed

Stop /clear killing surviving background work

Fixed /clear killing running commands of background agents, teammates and workflows that keep running, and foreground subagents of background agents and teammates

Stop requests after gateway sign-in expires

Fixed a terminal whose Claude apps gateway sign-in had expired sending telemetry and managed-settings requests that the gateway refused and logged as invalid_token

Fix replies lost on waiting background sessions

Fixed the agents view appearing to send a reply to a background session waiting on a permission prompt; the reply now stays in the box with a hint to open the session and answer

Fix agent view deleting another view's draft

Fixed agent view removing a draft saved by another agent view in the same directory when exiting

Fix agent view input swapped after update

Fixed a case where agent view came back with another agent view's input text after restarting itself for an update

Fix agents view preview truncation and formatting

Fixed the agents view preview cutting off long commands, results and status lines without an ellipsis, and dropping **, backticks and tags from commands waiting for approval

Fix false disconnect reports in Chrome

Fixed Claude in Chrome reporting the extension as not connected when the connection dropped mid-action; Claude now checks the page before repeating an action that may have run

Clear stale Remote Control limit notices

Fixed Remote Control sessions still showing "Limit reached" on other devices after a usage limit was lifted outside the session

Fix missing iOS file card

Fixed the file card sometimes missing in the Claude iOS app when Claude sent a single file

Explain self-hosted runner model-access failures

Fixed self-hosted runner sessions failing with no explanation when the server keeps refusing to renew model access: the runner now retries sooner and posts a warning in the session

Explain /permissions in cloud sessions

Fixed /permissions in cloud sessions replying only that it isn't available; it now says where the session's rules live and how to change them

Fix mod hot-reload disabled by unanswered question

Fixed mod hot-reloading turning off for the session when you typed three messages instead of answering its question in a cloud session

Fix tasks vanishing after /clear

Fixed background tasks that keep running after /clear disappearing from the task list in Claude Code on the web until another task started or ended

Hide hidden commands in cloud slash menus

Fixed hidden commands appearing in the slash command menu of cloud sessions on mobile and web

Fix idle sessions dropping the shell gateway

Fixed a case where idle background sessions started through a shell-exported LLM gateway left the gateway after an update

Fix wrapped help links opening partial URLs

Fixed help links in /status and the auto mode billing notice opening only part of the address when they wrap

Repair certificates with nonessential traffic off

Fixed a case where certificate errors behind a TLS-inspecting proxy persisted when CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC was set. With it set, Claude Code now makes a TLS handshake with the configured API host after a certificate failure, through your http:// proxy if one is set; it sends no API request

Exit 1 when remote-control's question is unanswered

Fixed claude remote-control exiting silently with status 0 when a first-run question gets no answer (scripts, services, batch jobs, Ctrl+C); it now says why and exits 1

Accept a piped y without a newline

Fixed claude remote-control ignoring a piped y that has no newline after it at the first-run question; it now counts as a yes

Warn when /rename fails to save

Fixed /rename reporting plain success when the new name could not be saved to the session transcript; it now warns that the new name may not last

Substitute CLAUDE_PLUGIN_ROOT in statusline commands

Fixed ${CLAUDE_PLUGIN_ROOT} not being substituted in a plugin-provided subagentStatusLine command, which can now reference the plugin's own scripts

Install new dependencies on plugin update

Fixed claude plugin update and /plugin "Update now" not installing dependencies added by the new plugin version

Fix stray completion notices after compaction

Fixed subagents being told after compaction to expect a completion notice for background agents they neither started nor took over

Explain lost background agent reports

Fixed a case where a background agent's later report was lost silently: the notification now says it was refused and how to ask for it

Hide web search for all-Bedrock upstreams

Gateway: Fixed Claude Desktop offering a web search tool that always failed when every upstream is Amazon Bedrock

Exit before registering on failed startup checks

Self-hosted runner: Fixed a runner started with --use-anthropic-git-proxy or --configure-git registering before a failed startup check made it exit; it now exits first

[VSCode] Fix silent truncation of long prompts

Fixed prompts over 50,000 characters being cut off silently: the prompt now stays in the chat box with a notice, and a paste over the limit is refused with a notice

[VSCode] Stop survey clicks sending draft prompts

Fixed a click on the survey or "Report a problem" buttons sending the unfinished prompt

[VSCode] Fix turns reappearing in Web tab sessions

Fixed cloud sessions opened from the extension's Web tab bringing back turns that /clear, or Retry or Edit of a typed prompt, had removed

[VSCode] Stop renamed sessions restoring deleted files

Fixed a deleted session's file coming back when that session was renamed in the extension

[VSCode] Fix freeze from long slash sequences

Fixed a possible chat panel freeze when a dropped item's path contains a very long run of "/" characters

[VSCode] Fix toggleDictation affecting every view

Fixed the claude-vscode.toggleDictation command starting dictation in every open Claude view at once; it now acts only in the view you are using, and a second press stops it

[VSCode] Fix slowdown from unclosed math fences

Fixed the chat panel slowing down while a reply with many unclosed $$ math fences, each shorter than the last, streams in

[Cloud sessions] Keep a connector named memory

Fixed scheduled tasks silently dropping a connector named memory: runs now keep it, mounted under that name plus a short suffix

[Cloud sessions] Stop Send now killing background agents

Fixed Send now on a waiting message in cloud sessions ending running background agents; they now keep running

[Claude Tag] Allow launch without a channel list

Fixed Claude Tag setup blocking launch when the channel list couldn't fully load; admins can now launch without picking a channel

[Claude Tag] Prevent admin settings from overwriting

Fixed saving auto mode allow rules in Claude Tag admin settings overwriting another admin's changes; the save is now refused with a message

Removed & reverted

2
All changes (2) Fewer changes
Change details