Claude Code 2.1.318
84changes- Add a No repository option so cloud sessions can start without picking a repository.
- Fix --continue sometimes losing the earlier conversation after a malformed tool call's retries ran out.
- Fix non-interactive launches silently replacing an invalid ~/.claude.json with defaults instead of failing safely.
- Stop Claude Code from installing or updating the IDE extension on its own inside an IDE's integrated terminal.
- Fix permission prompts being answered by stray keystrokes typed just before they appeared or right after sending a message.
New features
11[Cloud sessions] Add No repository option
Added a No repository option: a cloud session on an Anthropic-hosted environment can now start without picking a repository
[Cloud sessions] Add New session button on deleted env
Added a New session button to the card shown when a cloud session's environment was deleted, where the message box is hidden
More changes (9) Fewer changes
Remember mod enable answers
Added a record of your answer when Claude Code asks to turn on the mods it writes in a session
Add assume_role on gateway upstreams
Added assume_role on mantle upstreams of the Claude apps gateway, for a role in another AWS account and for per-developer AWS cost attribution
▤ In the docsAdd effort option to model.fork
Added an effort option to a mod's $.model.fork, so a quick side job can run at low whatever effort the session uses; the result reports the effort sent
Show sign-in expiry date in status/JSON
Added the date a stored claude.ai sign-in ends to claude auth status (loginExpiresAt) and to claude -p JSON results (credential_expires_at)
Warn before sign-in expiry in claude -p
Added a one-line stderr warning to claude -p text output, starting 10 days before a stored claude.ai sign-in ends
Warn before federation token expiry
Gateway: Added a log warning when the Google access token from a federation (external_account) credentials file is about to expire
Add CLAUDE_RUNNER_SPAWN_REASON to runner hooks
Self-hosted runner: Added CLAUDE_RUNNER_SPAWN_REASON to the orchestrator's spawn-runner hook environment: why Anthropic sent the request (e.g. runner_lost, resumed); unset when none was sent
Warn on malformed release-idle-session-min
Self-hosted runner: Added a startup warning when --release-idle-session-min is the last argument with no value (still ignored) or has a value of only spaces (still read as 0)
[Cloud sessions] Expose Chrome names for other tools
Added the usual Chrome names to cloud sessions, so tools other than Playwright can find the built-in Chromium through google-chrome and CHROME_PATH
▤ In the docsImprovements
25Speed up remote session reconnects
Improved how fast remote sessions reconnect after a pause or sleep
Improve config survival on network homes
Improved how ~/.claude.json, settings files and the stored login survive saves on shared network home directories: they are less often deleted, briefly emptied or replaced by a near-empty or older copy
Stop auto-installing IDE extension in IDE terminal
Changed Claude Code to no longer install or update the IDE extension when started in an IDE terminal; use /ide from an outside terminal or your editor's extensions view
▤ In the docsDefault new agents to auto permission policy
Changed /claude-api managed-agents-onboard to give a new agent's built-in tools, and a quickstart template's MCP tools, the auto permission policy ("Judge risky actions") by default, matching the Claude Console; say "run without asking" to opt out
More changes (21) Fewer changes
Retry config lookup on network file systems
Improved sessions on network file systems to look again when the configuration file is wrongly reported as missing, so fewer start without your MCP servers and trusted folders
Return input schema on early MCP calls
Improved MCP tool errors: a call made before the tool is loaded now returns its input schema
Improve git/PR reliability on macOS bash
Improved the reliability of git commits and pull request creation when the Bash tool runs macOS's built-in /bin/bash
Send admin usage requests in one step
Improved "Ask your admin for more usage" in the usage limit menu to send the request in one step
Fix You should know toast wording
Improved "You should know" toasts to say "try again" instead of "press 2", which only works in the terminal
Retry auto-update verification right away
Improved auto-update reliability: a brief network failure while verifying a release is now retried right away instead of waiting for the next check
Skip unchanged config rewrites in -p/SDK
Improved unattended runs (claude -p, SDK apps) to stop rewriting ~/.claude.json on every run when nothing in it changed
Stop instead of switching subagent models
Changed subagents to stop instead of switching models when "Switch models when a message is flagged" is set to "Ask each time"
Background slow shell commands on all providers
Changed background subagents to move a shell command to the background after 3 minutes on all providers, so the prompt cache doesn't expire while it runs
Extend subagent summary wait on cold cache
Changed subagent progress summaries on Bedrock, Vertex, Foundry, or with telemetry off: on a cold prompt cache, one can now wait up to 5 minutes for the subagent's pending response
Keep prompt.submit attachments in the user turn
Changed what a mod attaches at prompt.submit to stay in the user's turn rather than go out as a system message
Block connectors by URL in deniedMcpServers
Changed deniedMcpServers URL entries to also block Anthropic-provided servers whose upstream URL matches, and connectors in cloud sessions and on self-hosted runners, where the session is given the connector's own URL; otherwise deny a connector by name
Standardize /permissions dialogs
Changed the /permissions rule details, built-in rules and delete confirmation views to use the standard dialog; pressing Ctrl+C twice there now goes back or cancels instead of quitting
Clarify trusted_proxies log hints
Gateway: Improved the log hints about listen.trusted_proxies: they now say to list only a proxy that adds the connecting address to X-Forwarded-For itself
Clarify Bedrock CountTokens failure warning
Gateway: Improved the warning when AWS CountTokens fails on Amazon Bedrock: it says Claude Code, not the gateway, counts after the 501, and points at IAM only when AWS denies access
Change orchestrator log line format
Self-hosted runner: Changed the orchestrator's log lines: ok session=... now prints at every log level on stdout (was debug only, stderr) with reason=... after jti=..., and nack session=... ends its fields with reason=... after retryable=...; update scripts that match retryable=true: or retryable=false:
Fix titles for forks of forked terminals
Remote Control: Improved the title a fork of a terminal fork is created with when the app doesn't set one: "Name (fork 2)"
[VSCode] Show CLI output on sign-in check failure
Improved the sign-in screen to show what Claude Code printed when its sign-in status check fails
[Cloud sessions] Explain Create PR failures
Improved most Create PR failure messages in cloud and Remote Control sessions: they now give the reason or a link to GitHub instead of saying Try again
[Cloud sessions] Note partial connector search coverage
Changed connector search results to tell Claude that the search covers only part of the connector directory
[Code Review] Retry analytics page on failure
Improved the Code Review analytics page to retry once after a server or network failure, then show a Try again banner instead of empty cards
Bug fixes
47Fix --continue losing conversations
Fixed --continue sometimes losing the earlier conversation after a malformed tool call's retries ran out (regression in 2.1.314)
Stop replacing invalid config with defaults
Fixed non-interactive launches replacing a ~/.claude.json that isn't valid JSON with defaults; the start now fails, says how to restore the file, and leaves it as is (anthropics/claude-code#87551)
Fix stray keys answering permission prompts
Fixed permission prompts being answered by keys typed just after sending a message, or before a slow prompt appeared
More changes (44) Fewer changes
Fix macOS stalls under many Bash commands
Fixed macOS sessions with many running Bash commands stalling while memory grew
Fix silent config failures on network homes
Fixed /logout, claude auth logout and claude mcp remove reporting success, and changes to trust, consent or MCP settings being dropped with no word, when the config file could not be updated on a shared network home directory
Fix false Not logged in exits
Fixed jobs exiting with Not logged in when another terminal or host signs in again to the same account and organization on the same home
Fix mcp add/remove skipping config lock
Fixed claude mcp add and remove writing the config without its lock: they now wait for it or exit 1, though another job's save can still replace a saved server
Fix plugin commands exiting before token save
Fixed claude plugin commands exiting before a slow token refresh was saved, which could sign you out on the next run
Fix plugin validate accepting bad marketplace names
Fixed claude plugin validate passing a custom-named marketplace file that claude plugin marketplace add rejects
Stop re-probing MCP servers that exit
Fixed stdio MCP servers that exit on the version probe being re-probed on every start; a server that dies in under 3s for its own reason is also pinned to the legacy handshake for 7 days
Fix startup refused by stale provider list
Fixed sessions being refused at startup by an allowedProviders list that another login on the same machine had stored
Fix idle compaction with non-summary replies
Fixed idle compaction replacing a conversation with a reply that was not a summary
Fix repeated usage credits notice
Fixed the "Now using usage credits" notice reappearing about every 30 seconds while a background subagent is running
Show output for failed/Claude-only slash commands
Fixed custom slash commands that fail, or that only Claude can invoke, printing nothing in claude -p and SDK sessions
Fix false success on turn.step API errors
Fixed claude -p and Agent SDK sessions reporting success when an API error cut off a reply while a mod hooked turn.step
Fix Stop not cancelling post-model-change messages
Fixed a message sent right after a model change still running after Stop in headless sessions: Stop now cancels or stops it as it would a queued message
Fix deleted transcripts reappearing on exit
Fixed a deleted session transcript being re-created with its last prompt when an idle non-interactive session exited
Fix spawn failures after binary cleanup
Fixed claude remote-control hosts, the background daemon and self-hosted runners failing to start new sessions (spawn ENOENT) after an update or version cleanup removed the binary of a still-running process
Fix cleanup deleting other users' running binaries
Fixed a running Claude Code process owned by another user (for example one left by sudo claude) being treated as dead by version cleanup, which could delete its binary
Fix /remote-control showing failed sessions as available
Fixed /remote-control showing a session as available after a failed connection
Fix /design revoke false success on 404
Fixed /design revoke reporting success when the request failed with a 404
Fix shell commands running in wrong folder
Fixed a shell command approved after a self-hosted runner or cloud session restart running in the session's start folder, not the folder it was asked in; if that folder can't be entered, it is not run
Tell Claude when connector tools are unavailable
Fixed Claude not being told when an approved connector tool was unavailable after a cloud session restart
Fix cloud sessions stopping on upload refusals
Fixed cloud sessions being stopped in the middle of a turn when the service refuses uploads for several minutes
Fix Setup hook vars not reaching Bash
Fixed variables a Setup hook writes to CLAUDE_ENV_FILE not reaching the Bash tool in some cloud sessions
Fix iPhone app showing turns finished early
Fixed the iPhone app showing a cloud session's turn as finished while it kept running, after a response was cut off at a tool call or a refused image or document was removed
Fix restart resending messages out of order
Fixed a restarted session re-sending a message that failed with an API error, ahead of the newer message waiting behind it
Fix restarts dropping interrupted turns
Fixed a restarted session dropping its interrupted turn when the restart came right after Claude read a large image or retried a tool call
Fix connections failing on bad CA certs
Fixed every connection failing when the NODE_EXTRA_CA_CERTS file is empty, not PEM, or starts with a damaged certificate: readable certificates are now used, with a warning on stderr
Fix workflows re-running finished agents on resume
Fixed workflows re-running finished agents when resumed after a usage limit
Fix /mcp counting unavailable tools
Fixed /mcp in cloud sessions counting tools the model can't use; a server's row now shows how many of its tools are available
Fix duplicate PushNotification without status
Fixed a duplicate notification when Claude left the status field out of a PushNotification call
Show correct limit in too-large image errors
Fixed the error for a too-large image in a request with more than 20 images always saying the limit was 2000px; it now shows the API's limit
Update background shell runtime live
Fixed the runtime in background shell details not updating while the dialog is open
Fix turn.step marking stopped replies as success
Fixed a mod's turn.step hook making a stopped reply finish as a success in headless runs
Keep a backup before retention cleanup
Fixed retention cleanup leaving a home that only runs claude -p with no ~/.claude.json backup: it now takes a fresh backup before deleting the last good one
Fix login wiped by out-of-space network homes
Fixed the stored login being replaced by an empty file when a network home directory has no room left for data but still takes new files
Fix setup-token tokens wrongly refused
Fixed tokens from setup-token being refused at start on machines with forceLoginOrgUUID, when the token belongs to a permitted organization
Fix empty config wrongly reported as corrupted
Fixed an empty ~/.claude.json with no backup being reported as corrupted; Claude Code now starts as it does when the file is missing
Fix bad restore commands for damaged config
Fixed the restore command printed for a damaged or missing ~/.claude.json naming an empty or cut-off backup, or failing on a read-only file
Explain expired sign-in failures clearly
Fixed the sign-in failure when a stored claude.ai login reaches its time limit: it now says so, and in claude -p names claude auth login and claude setup-token
Fix misleading spawn error on missing folder
Remote Control: Fixed a misleading "spawn error: ENOENT" when a session's working folder is missing; the error now names the folder
[VSCode] Fix repeated background process starts
Fixed a window whose sign-in the organization's settings refuse starting a new Claude Code process in the background every minute
[VSCode] Fix error banner close button overflow
Fixed a long word in the chat panel's error banner pushing its close button out of view
[Cloud sessions] Fix reading GitHub Actions logs
Fixed reading GitHub Actions logs in cloud sessions: gh run view --log and gh api log requests now get the log in most environments, not an unreachable redirect
[Remote Control] Distinguish side-by-side checkouts
Fixed side-by-side checkouts of one repository looking identical in the environment menu's Remote Control rows; each now shows its own folder name
[Claude Tag] Fix focus and screen reader issues
Fixed keyboard focus and screen reader announcements in Claude Tag admin setup; pressing Escape in the connect form no longer also closes the Add dialog