mirror of
https://github.com/anthropics/claude-code.git
synced 2026-09-14 19:48:39 +08:00
GitHub Actions
841 lines
127 KiB
XML
841 lines
127 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
||
<feed xmlns="http://www.w3.org/2005/Atom">
|
||
<id>https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md</id>
|
||
<title>Claude Code Changelog</title>
|
||
<subtitle>Release notes for Claude Code</subtitle>
|
||
<author><name>Anthropic</name></author>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md"/>
|
||
<link rel="self" type="application/atom+xml" href="https://raw.githubusercontent.com/anthropics/claude-code/main/feed.xml"/>
|
||
<updated>2026-09-04T19:58:03Z</updated>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.261</id>
|
||
<title>Claude Code v2.1.261</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.261"/>
|
||
<updated>2026-09-04T19:58:03Z</updated>
|
||
<content type="html"><p>• Added an "Organization policy" line to /status and claude doctor that says why your organization's policy could not be loaded, such as a proxy not passing the endpoint through</p>
|
||
<p>• Added bashOutputMaxChars and taskOutputMaxChars settings to raise how much command and background-task output Claude receives inline before it is saved to a file, up to 128K characters</p>
|
||
<p>• Added --append-subagent-system-prompt-file to read the subagent system prompt from a file, for prompts too large to pass on the command line</p>
|
||
<p>• Added /skill-doctor to show which loaded skills go unused and what they cost in context, so you can prune them</p>
|
||
<p>• Fixed typed or pasted characters occasionally landing out of order or being dropped during fast input or key repeat</p>
|
||
<p>• Fixed /add-dir &lt;subdirectory&gt; printing a false "couldn't be resolved" error when the working directory is on a /net automount</p>
|
||
<p>• Fixed the Bedrock setup wizard hanging when AWS or an AWS credential helper never responds (it now times out with a clear error), and its model checks failing behind a TLS-inspecting proxy</p>
|
||
<p>• Fixed cloud sessions discarding a plugin synced from claude.ai when managed settings force-enable it in enabledPlugins, then falling back to a marketplace clone that could fail</p>
|
||
<p>• Fixed being unable to delete the character immediately before an inline [Image #N] chip in the prompt input</p>
|
||
<p>• Fixed resuming a session losing hook output and other context around parallel tool calls, which changed the resumed request</p>
|
||
<p>• Fixed Remote Control showing a stale permission mode when a phone, browser, or claude.ai app attaches to a terminal session or after the mode changes in the terminal</p>
|
||
<p>• Fixed Remote Control sessions showing as still working (stuck spinner and Stop button) after stopping a turn from a connected phone or browser, or after a local slash command like /clear</p>
|
||
<p>• Fixed SDK and cloud sessions ignoring a Stop or interrupt sent just after the first prompt, before the turn had started; the turn now stops instead of running to completion</p>
|
||
<p>• Fixed Remote Control uploading a session pulled with /teleport into the connected session, which appeared appended to the original on phone and web</p>
|
||
<p>• Fixed Remote Control's inbound event stream failing behind TLS-inspecting corporate proxies on native Windows</p>
|
||
<p>• Fixed Remote Control sessions showing the default effort level on claude.ai when the effort comes from settings</p>
|
||
<p>• Fixed gcpAuthRefresh opening a browser at startup when the Google credential check was slow, even though the credential was still valid</p>
|
||
<p>• Fixed claude.ai connectors staying absent for the whole session when the startup connector fetch timed out — the CLI now retries in the background</p>
|
||
<p>• Fixed sustained high CPU usage when a background agent could not be resumed and its wake-up was retried in a tight loop</p>
|
||
<p>• Fixed feature flags gated to a newer version occasionally applying to an older Claude Code version running on the same machine</p>
|
||
<p>• Fixed /usage and the VS Code usage panel dropping a model-specific weekly limit row when the usage endpoint is rate limited or when opened right after startup</p>
|
||
<p>• Fixed claude -p --resume &lt;file&gt; adopting a malformed session ID recorded in the transcript; it now resumes under a fresh session ID instead</p>
|
||
<p>• Fixed the terminal progress indicator (iTerm2, Ghostty, ConEmu) showing the session as finished while a background workflow or agent was still running</p>
|
||
<p>• Fixed a rare layout glitch where a box could render with the wrong height after its container switched between row and column direction</p>
|
||
<p>• Fixed Claude apps gateway client IP when a trusted proxy appends a port to X-Forwarded-For; with an access list set, an unreadable entry now gets 403</p>
|
||
<p>• Fixed Claude apps gateway telling Claude Desktop to export OpenTelemetry as JSON even when the terminal CLI uses protobuf, so protobuf-only collectors rejected Desktop's data</p>
|
||
<p>• Fixed Desktop and web showing a session as busy while it only watches an artifact for updates</p>
|
||
<p>• Fixed Claude in Chrome file_upload failing with "paths: expected array, received undefined" in local Cowork sessions run from the Claude Desktop app</p>
|
||
<p>• Fixed SendMessage to an offline Remote Control session on another machine reading as delivered; the result now says delivery is queued until that machine reconnects</p>
|
||
<p>• Fixed plugin install hints from CLIs run in background Bash commands: they are now detected, and the raw &lt;claude-code-hint&gt; tag no longer leaks into the conversation</p>
|
||
<p>• Fixed in-process agent-team teammates re-sending their first-turn tool and skill announcements on the second turn, which changed the request prefix and missed the prompt cache</p>
|
||
<p>• Improved the /model picker and the VS Code model pill to show a model's name instead of its raw Bedrock, Vertex AI, or LLM gateway ID when Claude Code recognizes it</p>
|
||
<p>• Improved startup on Google Vertex AI when GOOGLE_APPLICATION_CREDENTIALS is set: API client creation no longer re-runs Google Cloud project discovery or spawns extra gcloud processes</p>
|
||
<p>• Improved streaming performance: already-rendered blocks are no longer re-checked by layout on each update</p>
|
||
<p>• Improved the dangerous-rm safety prompt to also catch rm -rf on positional parameters and inside double-quoted sh -c scripts</p>
|
||
<p>• Improved handling when the API sends no response headers: the retry now waits up to API_TIMEOUT_MS (10 minutes by default) instead of another 3 minutes, and the messages say what to change</p>
|
||
<p>• Changed a Claude apps gateway 403 on the managed settings load (at startup or after /login) to say Claude Code may not be enabled for the organization, instead of advising a new sign-in</p>
|
||
<p>• Changed machines whose managed settings pin forceLoginMethod: "gateway" to ignore a leftover API key or claude.ai login and ask for /login; Bedrock, Vertex AI, and Foundry sessions are unaffected</p>
|
||
<p>• Changed auto mode to treat a link that packs content into a public diagram renderer's URL as an upload to that site: no longer auto-approved unless you asked for it</p>
|
||
<p>• Changed the prompt's word-editing keys to match Bash: Ctrl+W deletes back to whitespace, Alt+F and Alt+D stop at word end, punctuation separates words; keybindingFlavor no longer has any effect</p>
|
||
<p>• Changed /context token counting to use a local estimate when the token-counting API is unavailable, instead of extra small-model requests</p>
|
||
<p>• [VSCode] Added a "Build a custom style" walkthrough to the Output styles menu that writes a custom output style file and lists it right away</p>
|
||
<p>• [VSCode] Added an Add server form and a Remove action to the MCP servers dialog, so MCP servers can be added and removed without leaving the IDE</p>
|
||
<p>• [VSCode] Added a hollow ring in the session list for sessions open in a terminal, another VS Code window, or Claude Desktop, so they no longer look closed</p>
|
||
<p>• [VSCode] Added a fold button to permission and question prompts so the conversation behind them can be read without dismissing them; the space beside the prompt now scrolls the conversation</p>
|
||
<p>• [VSCode] Added "Archive session" to the session list's right-click menu and gave Unarchive its own icon</p>
|
||
<p>• [VSCode] Fixed a session teleported from Claude Code on the web treating a question that was cut off when the cloud session shut down as declined</p>
|
||
<p>• [VSCode] Fixed the session tab's Rename box opening empty for a tab restored with the window; it now starts with the current name</p>
|
||
<p>• [VSCode] Fixed collapsed sections in the session list panel briefly showing expanded each time the panel loaded</p>
|
||
<p>• [VSCode] Fixed Focus view showing a tool call as still running after Claude had moved on, such as while a question waited for your answer</p>
|
||
<p>• [VSCode] Fixed the session list's active-row highlight going stale when an unfocused Claude tab's session ID is corrected</p>
|
||
<p>• [VSCode] Fixed Cmd/Ctrl+Shift+T reopen and deep-link opens placing the Claude tab outside the Claude editor group when a Claude tab has focus</p>
|
||
<p>• [VSCode] Fixed the session tab's "Add to group" putting a session opened from Claude Code on the Web in two groups; it now moves the entry the session list shows</p>
|
||
<p>• [VSCode] Fixed the model picker showing models an organization has since disabled until the window was reloaded twice</p>
|
||
<p>• [VSCode] Fixed a tab opened from the session list jumping back to that session, and a tab opened from a Web session restarting its teleport or staying empty, after VS Code reloads the tab's view</p>
|
||
<p>• [VSCode] Fixed /btw side-question history from earlier sessions being overwritten when a question is asked right after a window reload or while a settings file has errors</p>
|
||
<p>• [VSCode] Fixed the pending question card not reappearing after the Claude panel reloads when signed in with a Claude.ai or Console account</p>
|
||
<p>• [VSCode] Fixed claude.ai-only features staying visible in a window's other Claude panels after one panel picked up a third-party provider from a settings file</p>
|
||
<p>• [VSCode] Fixed the sign-in screen appearing despite the Disable Login Prompt setting when Claude Code reports no login or a request fails for lack of one</p>
|
||
<p>• [VSCode] Fixed the next queued permission prompt keeping text typed on the previous prompt and accepting an immediate second click</p>
|
||
<p>• [VSCode] Fixed install-plugin links opening the Claude sidebar without the install dialog in a window where only the session list had been shown</p>
|
||
<p>• [VSCode] Fixed the sidebar usage meter staying empty on a new window until the Account &amp; usage dialog was opened, and a 0% usage limit being left out of the meter</p>
|
||
<p>• [VSCode] Fixed "Start new session in this group" losing the group after New conversation, and a missing unread dot for a session that finished before the sidebar's unread list loaded</p>
|
||
<p>• [VSCode] Fixed the editor tab badge showing unread during a running turn or missing on a tab opened from the session list, and "Add Session Tab to Group" doing nothing for an archived session</p>
|
||
<p>• [VSCode] Fixed "Enable Remote Control for all sessions" so flipping it also applies right away to sessions open in other VS Code windows</p>
|
||
<p>• [VSCode] Fixed the session list's Open filter for sessions continued from claude.ai whose tab was still recorded under the web session, and labeled the filter menu's sections for screen readers</p>
|
||
<p>• [VSCode] Changed the model picker to one flat list of every model, with rows kept for older model spellings listed last</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.260</id>
|
||
<title>Claude Code v2.1.260</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.260"/>
|
||
<updated>2026-09-03T23:48:04Z</updated>
|
||
<content type="html"><p>• Added a diff panel that opens beside the conversation in fullscreen mode and shows your uncommitted changes as Claude edits; toggle it with /diff</p>
|
||
<p>• Added a likely cause for prompt-cache misses (e.g. tool definitions or system prompt changed, idle past the TTL) to /cost and the status line's prompt_cache field</p>
|
||
<p>• Added /reload-plugins to headless sessions, so it appears in the Claude Code Desktop and SDK command lists</p>
|
||
<p>• Added a text form of /advisor (/advisor, /advisor &lt;model&gt;, /advisor off) for the desktop app, Remote Control, and other headless (-p/Agent SDK) sessions</p>
|
||
<p>• Added oidc.scope_on_refresh to the Claude apps gateway for IdPs that return an id_token on refresh only when asked for openid again</p>
|
||
<p>• Added Claude apps gateway support for newer Claude Desktop keys in desktop policy blocks, including userPluginMarketplacesEnabled and userPluginUploadsEnabled</p>
|
||
<p>• Fixed Edit/Write/Read permission rules whose path contains parentheses being dropped as invalid or ignored by the Bash sandbox, which left "read-only" folders writable</p>
|
||
<p>• Fixed one file permission rule with an uncompilable pattern (e.g. an unclosed [) making every file edit fail with Invalid regular expression; such a deny rule now guards the literal path it spells</p>
|
||
<p>• Fixed Bash permission checks auto-approving zsh commands that hide a command substitution in a REPORTTIME, REPORTMEMORY or DIRSTACKSIZE assignment; these now prompt for approval</p>
|
||
<p>• Fixed Bedrock model discovery, token counting and AWS SSO/STS credential calls failing with "unable to get local issuer certificate" when the corporate root CA is only in the OS certificate store</p>
|
||
<p>• Fixed permissions.blockReadsOutsideWorkingDirectories on macOS hiding the user's git config from sandboxed git and hiding a worktree-isolated sub-agent's own checkout</p>
|
||
<p>• Fixed managed settings not loading for claude.ai Enterprise/Team users who also had a leftover API key from an earlier /login</p>
|
||
<p>• Fixed /status listing a signed-in claude.ai account and a configured API key as if both were in effect; the credential not in use is now marked</p>
|
||
<p>• Fixed managed skillOverrides entries keyed on a bundled skill's alias (e.g. checkup for /doctor) not applying, and Skill(name) deny rules not covering a nested skill listed as &lt;dir&gt;:name</p>
|
||
<p>• Fixed model: fable agents ignoring the [1m] tag on an ANTHROPIC_DEFAULT_FABLE_MODEL pin and silently running with a 200K context window</p>
|
||
<p>• Fixed the /model picker not showing Fable 5.1 for organizations that can use it, which was only accepted when typed as /model claude-fable-5-1</p>
|
||
<p>• Fixed prompt caching on Claude Fable 5.1 not covering the context attached after tool results, so it was re-sent as uncached input on every tool-call turn</p>
|
||
<p>• Fixed model switching staying blocked for the rest of the session after a plugin hook load failure; each switch now re-checks and the refusal names the cause</p>
|
||
<p>• Fixed model switching being blocked for the session when an organization-managed plugin's marketplace could not be loaded</p>
|
||
<p>• Fixed SDK-provided MCP servers (e.g. Desktop connectors) sometimes missing from the first turn and only appearing on the next one</p>
|
||
<p>• Fixed Claude in Chrome tools failing with "Not connected" mid-task in cloud-hosted claude.ai sessions when a connector was added or removed</p>
|
||
<p>• Fixed flags, joined emoji and accented letters splitting across wrapped lines, and stale text staying on screen when a flag or joined emoji falls in the terminal's last two columns (now shown as …)</p>
|
||
<p>• Fixed Remote Control accepting a model pick that is not a valid model name; it is now refused with an error instead of failing on the next message</p>
|
||
<p>• Fixed /rewind and --rewind-files reporting success when checkpoint backup files were missing and nothing was actually restored</p>
|
||
<p>• Fixed /rewind leaving stale file-read tracking from the rewound-away turns, which caused "File unchanged since last read" stubs and full-file re-injection after external edits</p>
|
||
<p>• Fixed -p --resume/--continue (as used by the desktop app) failing on every retry once a session's worktree directory lost its git metadata; it now fails once, then resumes without the worktree</p>
|
||
<p>• Fixed a subagent that resumed another agent via SendMessage never being woken by that agent's completion (the notification went to the main conversation instead)</p>
|
||
<p>• Fixed agent teams: an in-process teammate's transcript losing messages, or going blank, during long API retry waits (e.g. under CLAUDE_CODE_RETRY_WATCHDOG) as retry notices evicted real messages</p>
|
||
<p>• Fixed a session that moved to the background appearing twice in ListAgents (once as a phantom "interactive" twin with the same name) and receiving SendMessage deliveries in the viewer</p>
|
||
<p>• Fixed intermittent "task output swap refused" errors when many sessions share a project directory</p>
|
||
<p>• Fixed Ctrl+Z in fullscreen leaving the shell on the alternate screen, drawn over the paused interface</p>
|
||
<p>• Fixed Workflow tool subagents being restarted as stalled while a long context compaction was still in progress</p>
|
||
<p>• Fixed plugins from a URL marketplace failing to install with "marketplace entry path does not stay inside the marketplace directory" when a host app (e.g. Claude Desktop) stores it as a directory</p>
|
||
<p>• Fixed an extra browser tab opening when an artifact is published in a session you're driving from claude.ai, the desktop app, or mobile (Remote Control)</p>
|
||
<p>• Fixed the Artifact tool's first call failing with an "Invalid tool parameters" validation error in some Cowork sessions</p>
|
||
<p>• Fixed IDE line selections being dropped when running a skill or slash command (the "N lines selected" context now reaches Claude)</p>
|
||
<p>• Fixed repository detection for GitLab projects in nested subgroups (e.g. gitlab.com/group/subgroup/project)</p>
|
||
<p>• Fixed owner/repo#123 issue references in rendered output linking to github.com when working in a GitLab repository; they now link to the gitlab.com issue</p>
|
||
<p>• Glob/Grep: Fixed the search path being probed on disk before the permission check; a missing path is now reported after permission is decided, as Read does</p>
|
||
<p>• Reverted the 2.1.259 change applying Read() deny rules to Bash arguments; it denied npm run build under a Read(.//build/) rule in every mode and made cd … &amp;&amp; grep prompt even in auto mode</p>
|
||
<p>• Improved structured output: Workflow agent({schema}) rejects a JSON Schema that can never be satisfied up front, and retry-cap errors now include the last validation failure</p>
|
||
<p>• Improved deleting a background session whose worktree has unpushed commits: the message now names the branch and commit count, and deleting again discards the worktree</p>
|
||
<p>• Improved the Claude apps gateway's refresh-failure log to name the step that failed</p>
|
||
<p>• Improved idle CPU usage of non-interactive (-p / SDK) sessions</p>
|
||
<p>• Improved the Claude apps gateway on Amazon Bedrock: input tokens for an aborted request are now counted with AWS's free CountTokens API (grant bedrock:CountTokens) instead of a one-token request</p>
|
||
<p>• Improved the settings error for rules such as Edit(C:\dir\(name)\**), where \( is read as an escaped parenthesis rather than a path separator, to suggest an unambiguous spelling</p>
|
||
<p>• Improved auto-compact for 1M-context models: Opus and Fable sessions now compact shortly before the 1M-token limit, and recovery compaction on very large contexts no longer times out at 10 minutes</p>
|
||
<p>• Improved /ultrareview and claude ultrareview to wait up to 45 minutes (previously 30) for long-running cloud reviews</p>
|
||
<p>• Improved /effort on Claude Fable 5.1 so changing effort mid-session no longer invalidates the prompt cache</p>
|
||
<p>• Updated the bundled claude-api skill so its Go, Java, and C# samples use current-generation model IDs, and clarified that cheaper worker or sub-agent models should be current-generation too</p>
|
||
<p>• Changed ctrl+l / cmd+k in fullscreen mode to clear the transcript view like a terminal clear; scroll up to see earlier messages</p>
|
||
<p>• Changed permission rules with text after the closing parenthesis (e.g. Bash(ls) x), which never matched anything, to be reported as invalid settings instead of being silently ignored</p>
|
||
<p>• Changed server-managed settings so a managed CLAUDE.md (claudeMd) no longer triggers the security approval dialog; hooks, shell-command, sandbox, and unsafe env settings still require approval</p>
|
||
<p>• Changed Claude in Chrome to follow your organization's Claude in Chrome admin setting; when an admin turns it off, --chrome, /chrome and the browser tools are unavailable</p>
|
||
<p>• Changed Claude apps gateway to send orgPluginSettings in the list form read by Claude Desktop 1.15200.0 and later; older desktops ignore it</p>
|
||
<p>• Changed Claude apps gateway to also refuse to start, naming the field, when a desktop policy misspells a field in a nested object of a managedMcpServers or orgPluginSettings entry</p>
|
||
<p>• Changed commands typed at the ! bash-mode prompt to run outside the sandbox even when strict sandbox mode (sandbox.allowUnsandboxedCommands: false) is on, like typing into your own terminal</p>
|
||
<p>• Changed self-hosted runner --kill-session-after-min to release a session that is only waiting on its user (paused, resumable on the next message) instead of killing it and reporting a failure</p>
|
||
<p>• Removed the one-hour time limit on background commands started by subagents; they now run until they exit or are stopped, matching the main session</p>
|
||
<p>• [VSCode] Added the selected effort level to the footer model pill, fixed a stale effort level after switching models, and returned the footer pills to their earlier compact size</p>
|
||
<p>• [VSCode] Added Open and Closed to the session list's status filter menu</p>
|
||
<p>• [VSCode] Fixed the welcome screen disappearing in a new session when Remote Control turns on automatically</p>
|
||
<p>• [VSCode] Fixed the session history picker loading a session a second time when it is already open in another tab; it now switches to that tab</p>
|
||
<p>• [VSCode] Fixed the session tab's Rename command silently doing nothing while the tab's view was reloading; it now always applies</p>
|
||
<p>• [VSCode] Fixed a half-finished message, an empty tool card or an extra "Thought for" line staying on screen after Claude Code retried a dropped response</p>
|
||
<p>• [VSCode] Fixed "Enable Remote Control for all sessions" not applying to a session tab that was still starting when the toggle was flipped</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.259</id>
|
||
<title>Claude Code v2.1.259</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.259"/>
|
||
<updated>2026-09-02T22:33:43Z</updated>
|
||
<content type="html"><p>• Added managedMcpServers managed setting: organizations can provide HTTP/SSE MCP servers to every user (same entry shape as .mcp.json); entries that name a command to run are skipped</p>
|
||
<p>• Added --permission-prompts none for unattended headless hosts: anything that would prompt is denied automatically while the active permission mode (including auto mode) keeps deciding</p>
|
||
<p>• Added recognition of glab mr create/merge/close/reopen/note/update so GitLab merge requests show as MR !N in the collapsed tool summary and refresh the footer MR badge</p>
|
||
<p>• Added --json to claude plugin validate for a machine-readable validation report</p>
|
||
<p>• Fixed concurrent sessions silently reverting each other's ~/.claude.json changes — workspace trust no longer resets and MCP/project state is no longer lost when running many sessions at once</p>
|
||
<p>• Fixed a conversation whose thinking was rejected once being rejected again on every later turn</p>
|
||
<p>• Fixed Bash Read() deny rules not covering files given as option values (--ignore-revs-file=.env, -f.env, @file), git diff/git grep file operands, or cd DIR &amp;&amp; cat FILE compounds; grep -r/cp -r over a directory holding a denied file now asks</p>
|
||
<p>• Fixed the prompt cache being invalidated when the OAuth token refreshed in sessions with telemetry disabled</p>
|
||
<p>• Fixed fullscreen mode showing a blank conversation after a long turn with hundreds of tool calls</p>
|
||
<p>• Fixed auto mode running a turn on a model it doesn't support when a command or skill's frontmatter model: named one; the turn now keeps the session model</p>
|
||
<p>• Fixed CLAUDE_CODE_MAX_CONTEXT_TOKENS being ignored for Vertex-style model IDs (@YYYYMMDD suffix) of model versions Claude Code doesn't recognize</p>
|
||
<p>• Fixed the live output preview of a running shell command hiding its newest lines when an earlier line wrapped</p>
|
||
<p>• Fixed a background GitHub connection check that ran on every launch for claude.ai users; the result is now remembered across launches</p>
|
||
<p>• Fixed --resume failing (and --continue opening an empty conversation) when a saved session contains an attachment entry with no payload</p>
|
||
<p>• Fixed frontmatter model: on custom commands and skills being ignored in interactive sessions</p>
|
||
<p>• Fixed Artifact publishing failing once with an "unexpected parameter note" error in conversations continued from an older version</p>
|
||
<p>• Fixed managed forceRemoteSettingsRefresh being ignored at startup when a policy helper configured by MDM or the managed settings file had already run</p>
|
||
<p>• Fixed worktree isolation refusing hook-created worktrees on machines where git rev-parse fails with a message other than "not a git repository"</p>
|
||
<p>• Fixed OpenTelemetry metrics and events from cloud sessions missing the user.email, organization.id, and user.account_uuid attributes</p>
|
||
<p>• Fixed MCP servers that disconnect while their tools are being listed at startup showing as connected with no tools instead of reporting the error</p>
|
||
<p>• Fixed the file edit permission dialog sometimes showing a changed line cut short with no indication</p>
|
||
<p>• Fixed repository detection dropping a known repo identity after a transient git probe failure</p>
|
||
<p>• Fixed managed settings silently going unenforced when the managed-settings file, a drop-in, the MDM plist, or the HKLM value cannot be parsed: Claude Code now refuses to start and names the source</p>
|
||
<p>• Fixed Stop not actually stopping background agents and workflows in remote-control sessions: killed tasks now stay visible and re-stoppable until their processes exit</p>
|
||
<p>• Fixed resuming a workflow run while its previous stopped run was still exiting, which could run duplicate copies of its agents</p>
|
||
<p>• Fixed marketplace repo URLs on github.com with a trailing slash or dangling ?/# producing an unusable .git clone URL</p>
|
||
<p>• Fixed blocking Stop hooks causing the turn after a block to lose the model's reasoning from that turn and, on some models, miss the prompt cache</p>
|
||
<p>• Fixed remote (claude.ai) sessions taking 60 seconds to start a turn after a browser-hosted MCP server's page had gone away</p>
|
||
<p>• Fixed worktree-isolated sessions refusing common Bash loops, xargs pipelines and launcher-wrapped commands that cannot reach the main checkout</p>
|
||
<p>• Improved terminal resize and first-render performance for long responses by reusing text measurements</p>
|
||
<p>• Improved /workflows agent detail: JSON outcomes are pretty-printed with syntax colors and real line breaks, and long outcomes fold behind an expand toggle</p>
|
||
<p>• Improved headless/SDK session start: the first turn begins up to 50 ms sooner when MCP servers finish connecting</p>
|
||
<p>• Improved /install-github-app to explain it is GitHub-only and point to the GitLab CI/CD docs when run inside a GitLab repository</p>
|
||
<p>• Improved nested background subagent results to be saved in the parent subagent's transcript, so resumed subagents keep them and shared transcripts show the delivery</p>
|
||
<p>• Changed allowedMcpServers to govern only servers users add: a literal managed-mcp.json server your allowlist used to filter out now loads on upgrade; use deniedMcpServers to keep it off</p>
|
||
<p>• [VSCode] Added an Active quick filter and a status filter menu (Needs input, Working, Completed) to the session list sidebar</p>
|
||
<p>• Fixed remote and scheduled sessions doing nothing after a connector-tool permission prompt was approved while the session was paused</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.258</id>
|
||
<title>Claude Code v2.1.258</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.258"/>
|
||
<updated>2026-09-01T22:33:14Z</updated>
|
||
<content type="html"><p>• Fixed Claude Code failing to launch on macOS 12 (Monterey), a regression introduced in 2.1.255</p>
|
||
<p>• Fixed remote and scheduled sessions failing with "user messages must have non-empty content" after a re-sent permission approval could not be applied</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.257</id>
|
||
<title>Claude Code v2.1.257</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.257"/>
|
||
<updated>2026-09-01T17:53:45Z</updated>
|
||
<content type="html"><p>• Added Claude Fable 5.1 (claude-fable-5-1), now the default Fable model — 1M context, $10/$50 per Mtok with $0.25/Mtok cache reads</p>
|
||
<p>• Added "Time format" (timeFormat) and timeZone settings: 12-hour, 24-hour, 24-hour UTC, or a strftime pattern for the turn-end clock and transcript-view timestamps</p>
|
||
<p>• Added a Containment Escape rule to auto mode so cloud metadata-credential fetches, egress evasion, and cross-tenant reach are no longer auto-approved unless your environment marks them expected</p>
|
||
<p>• Added CLAUDE_CODE_SUBAGENT_MODEL_FORCE to apply CLAUDE_CODE_SUBAGENT_MODEL (or the main model) to every subagent, ignoring per-spawn and agent-definition model overrides</p>
|
||
<p>• Added s in /effort to change effort for the current session only, matching /model</p>
|
||
<p>• Added a /doctor warning for stale sandbox mask files left by a killed session</p>
|
||
<p>• Added a one-time prompt in auto mode before the first file read outside the working directories, with the option to block such reads (permissions.blockReadsOutsideWorkingDirectories)</p>
|
||
<p>• Added support for a gateway-supplied description on discovered /model picker entries (CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY); entries without one still read "From gateway"</p>
|
||
<p>• Fixed settings in a .claude/ folder created after startup not being picked up until restart</p>
|
||
<p>• Fixed sessions dispatched from an agent view opened with ← always starting in the original session's permission mode, overriding the target directory's defaultMode and the agent's permissionMode</p>
|
||
<p>• Fixed keybindings.json rebinds of Ctrl+G being ignored in claude agents; its Ctrl+S / Ctrl+T are now rebindable via the new Agents context</p>
|
||
<p>• Fixed background sessions failing to start on macOS npm installs during a self-update, and on Windows when a stale daemon lock file pointed at a reused process id</p>
|
||
<p>• Fixed the working spinner stopping while a response streams behind a slash-command panel</p>
|
||
<p>• Fixed a background session's state.json detail repeating its own dispatch prompt after a scheduled wake-up</p>
|
||
<p>• Fixed claude agents keeping a background session you re-prompted buried in Completed after it finished again; Completed now orders by the latest finish</p>
|
||
<p>• Fixed claude --bg from a directory that was just deleted reporting "backgrounded" and leaving a crashed session row; it now prints the reason and exits 1</p>
|
||
<p>• Fixed Remote Control connecting mid-session re-sending the Bash tool definition, causing a prompt-cache miss</p>
|
||
<p>• Fixed a doubly-listed custom Authorization header overriding the configured credential on Bedrock, Mantle, Vertex, and WIF, and the Vertex setup wizard picking up a leftover Anthropic profile from ~/.config/anthropic</p>
|
||
<p>• Fixed Claude apps gateway sending stray host Authorization or profile headers to Foundry, Vertex, and Bedrock, and Foundry Entra ID upstreams not starting when ANTHROPIC_FOUNDRY_API_KEY is set</p>
|
||
<p>• Fixed a leftover Anthropic API key or auth token being sent alongside your Foundry subscription key in API-key mode</p>
|
||
<p>• Fixed /schedule routines whose prompt was saved without a message role and then ran with nothing to do</p>
|
||
<p>• Fixed claude agents not saying that a background session is waiting for you to approve a message from another session, or who sent it</p>
|
||
<p>• Fixed a prompt stashed with Ctrl+S inside an opened background session being lost when the session went idle or was stopped and then reopened</p>
|
||
<p>• Fixed telemetry (OTEL) settings pushed through server-managed settings being ignored on warm starts, including desktop-app Code sessions</p>
|
||
<p>• Fixed a teammate permission request being answered twice when the leader's mailbox write was briefly locked</p>
|
||
<p>• Fixed a phantom duplicate slash-command row rendering below the in-flight turn while a command's auto-continued response streamed</p>
|
||
<p>• Fixed policyHelper timeoutMs and refreshIntervalMs values above the timer maximum (2147483647) causing failures or re-runs every millisecond; they are now clamped</p>
|
||
<p>• Fixed the token counter freezing or crawling after switching to another subagent's transcript, and made background subagents' and teammates' counters update live while a response streams</p>
|
||
<p>• Fixed sandbox network hosts written with a trailing dot (example.com.): a deniedDomains entry didn't block the host inside the sandbox, and "don't ask again" for such a host kept prompting</p>
|
||
<p>• Fixed dismissing the Remote Control consent prompt (Esc, or n at claude remote-control) counting as consent, so the next request connected without asking</p>
|
||
<p>• Fixed /mcp reconnect and enable still connecting a settings-file MCP server that a managed MCP allow/deny list or strictPluginOnlyCustomization loaded after startup should block</p>
|
||
<p>• Fixed claude mcp remove leaving a remote server's stored OAuth credentials behind when strictPluginOnlyCustomization locks MCP to plugin-only servers</p>
|
||
<p>• Fixed Remote Control (claude remote-control) sessions started from the Claude app ignoring the selected model and running on the machine's default instead</p>
|
||
<p>• Fixed --disallowedTools and session deny rules being dropped after the first settings reload when allowManagedPermissionRulesOnly is enabled</p>
|
||
<p>• Fixed --resume listing a backgrounded conversation twice and --continue reopening its stalled pre-background copy; --continue now also opens finished background sessions</p>
|
||
<p>• Fixed fullscreen mode not letting you click ! shell command output to expand it</p>
|
||
<p>• Fixed background sessions left running an older Claude Code binary piling up across auto-updates instead of being retired</p>
|
||
<p>• Fixed claude agents --json briefly switching the terminal to raw mode and undoing another program's terminal settings on exit</p>
|
||
<p>• Fixed Proactive output style sessions busy-looping with filler messages and repeated log reads instead of idling while a background command or Monitor they started is still running</p>
|
||
<p>• Fixed subagents stopping when a response was cut off mid-stream by a computer sleep, dropped connection, or server error; they now automatically continue instead of ending with an incomplete response</p>
|
||
<p>• Fixed ← doing nothing in the /btw panel inside a claude agents session: it now returns to the agents list (even mid-answer), and the panel comes back when you reopen the session</p>
|
||
<p>• Fixed sessions with an advisor model set missing the prompt cache on background requests (compaction, /recap, prompt suggestions) and re-sending the full conversation uncached each time</p>
|
||
<p>• Fixed claude -p exiting about 5 seconds after its final result while a Monitor the model armed was still running; it now waits for the watch to fire or time out</p>
|
||
<p>• Fixed a permissions.ask rule being skipped in auto mode when the matching command ran inside a compound command or subshell, letting it run without the confirmation prompt</p>
|
||
<p>• Fixed plugins being able to read files outside their own directory through a declared command, agent, skill, hooks or other component path that is a symlink; such paths are now refused with an error</p>
|
||
<p>• Fixed /add-dir rejecting a directory inside the current working directory; it now loads that directory's skills, commands, and agents like --add-dir does at startup</p>
|
||
<p>• Fixed the main agent not being told when you resume a subagent you had stopped from its transcript view</p>
|
||
<p>• Fixed a crash when pasting ANSI-colored text (e.g. a CI log) into dialogs like /feedback</p>
|
||
<p>• Fixed claude mcp add/remove hanging or exhausting memory when the project's .mcp.json is a FIFO or a device-file symlink; it now fails fast with an actionable message</p>
|
||
<p>• Fixed unbounded memory growth when non-JSONL data is piped into claude -p --input-format stream-json; it now fails fast with a clear error</p>
|
||
<p>• Fixed backgrounding a turn (← or Ctrl+B) while a subagent or other tool was running occasionally making the background session treat that tool as rejected instead of re-running it</p>
|
||
<p>• Fixed Bash Read()/Edit() deny rules not applying to &lt; file redirects and reader commands like tac and egrep; a deny rule on any argument or redirect target now refuses the command</p>
|
||
<p>• Fixed resuming or messaging a subagent whose transcript had grown past 5 MB (for example after reading many images) failing with "No transcript found"</p>
|
||
<p>• Fixed worktree-isolated sessions refusing Bash loops, $VAR reads, "$(…)" and heredocs that never touch git as "too complex to verify that it stays inside the worktree"</p>
|
||
<p>• Fixed /model and /effort showing a prompt-cache warning after rewinding a conversation back to empty</p>
|
||
<p>• Fixed prompt-cache misses on every turn in long screenshot-heavy sessions once images exceeded the per-request size cap</p>
|
||
<p>• Fixed the Edit permission prompt's diff view rendering emoji and multi-code-point characters with incorrect widths</p>
|
||
<p>• Fixed WebSocket MCP server connection failures being logged as "[object ErrorEvent]" instead of the underlying error</p>
|
||
<p>• Fixed background sessions failing to open with "Couldn't start the background service" while another Claude Code process was downloading an npm update; the start now waits for it</p>
|
||
<p>• Fixed background commands that detach from their shell (for example under timeout or setsid) surviving a task stop or Claude Code exit</p>
|
||
<p>• Fixed Claude not being told when you stop a background command from the tasks panel or a connected client</p>
|
||
<p>• Fixed stopping a background subagent leaving its monitors running</p>
|
||
<p>• Fixed sandboxed git commands in a linked worktree losing write access to the repository's common .git directory after cd into a subdirectory</p>
|
||
<p>• Fixed Bedrock and Bedrock Mantle requests going silent during long hidden-thinking phases on Opus 4.7 and later, which let idle timeouts cut the connection; the stream now carries progress events</p>
|
||
<p>• Fixed launching Claude Code after a Claude apps gateway expired or revoked your session: it now says the session ended and offers /login instead of reporting a network error</p>
|
||
<p>• Fixed cloud sessions losing git/GitHub credentials for the rest of the session when the session's network proxy failed to start at launch; it now retries in the background and recovers</p>
|
||
<p>• Fixed leftover cc-daemon-* folders in the system temp directory after an interrupted background daemon start; the cleanupPeriodDays retention sweep now removes them</p>
|
||
<p>• Fixed Bash permission checks auto-approving certain [[ ]] conditionals that zsh parses differently from bash; these commands now prompt for approval</p>
|
||
<p>• Fixed the managed-settings approval prompt showing the generic warning instead of its telemetry wording when the settings also turn detailed tracing or raw API body logging off, or trace export on</p>
|
||
<p>• Fixed agent-team teammates in tmux/iTerm2 panes sometimes staying open after acknowledging a shutdown request</p>
|
||
<p>• Fixed the keyless Console sign-in ("Sign in with your Console account") not applying your organization's server-managed settings, and /status not showing the Organization for that sign-in</p>
|
||
<p>• Improved rendering performance: less re-render work per turn in long conversations, streaming no longer slows down as the reply grows, and background-agent updates no longer re-render the whole screen</p>
|
||
<p>• Improved prompt input responsiveness by reducing per-keystroke rendering work</p>
|
||
<p>• Improved policy helper diagnostics — refresh failures now show in /status, declining the managed-settings dialog prints why Claude Code exited, and helper timeouts are reported as timeouts</p>
|
||
<p>• Improved /code-review --comment to post findings on GitLab merge requests via glab mr note instead of reporting the target as unsupported</p>
|
||
<p>• Improved notifications: an MCP elicitation or permission ask queued under another dialog now sends its idle desktop notification at the same delay as a visible ask</p>
|
||
<p>• Improved verbose/transcript output: async hook completion notices that arrive together now appear on one line instead of one line per hook</p>
|
||
<p>• Improved claude self-hosted-runner --configure-git to also enable git push negotiation, so the first push of a new branch from a stale clone uploads only the new commits instead of the whole tree</p>
|
||
<p>• Improved liveness reporting to SDK hosts while a response is held open by gateway keep-alives, so long waits under a raised CLAUDE_STREAM_IDLE_TIMEOUT_MS are not mistaken for a hung session</p>
|
||
<p>• Improved MCP connection and OAuth debug/error logs so credentials carried in a server's URL or request headers are redacted</p>
|
||
<p>• Improved /fork to keep the original conversation's prompt cache in the new background session: its worktree briefing now arrives as a message instead of a system-prompt change</p>
|
||
<p>• Improved emoji autocomplete to accept the remaining GitHub/Slack shortcode aliases (:satisfied:, :telephone:, :collision:, …)</p>
|
||
<p>• Changed --effort to lift a new model's default-effort hold for that session only rather than permanently; an effort picked on claude.ai for a Remote Control session now applies during the hold</p>
|
||
<p>• Changed a policyHelper in MDM or managed-settings.json shadowed at launch by cached server-managed settings to run (or exit) as soon as the fetch reports them removed, not at the next launch</p>
|
||
<p>• Changed managedSourcesBehavior: "merge" to take sandbox.credentials.awsPairs and sandbox.ripgrep whole from the highest managed source that sets them instead of combining the sources' values</p>
|
||
<p>• Changed gateway model discovery (CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1) to run even when CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC is set, since it only queries your gateway</p>
|
||
<p>• Changed claude --resume &lt;session-id&gt; --bg to continue that session under its own ID when nothing is running it, instead of silently starting a copy; a copy is now announced</p>
|
||
<p>• Changed /btw history browsing from ←/→ to Shift+←/Shift+→ (or [/]), stepping through your recent side questions and back to the live answer</p>
|
||
<p>• Changed defaultMode: "bypassPermissions" in .claude/settings.json or .claude/settings.local.json to be ignored, like "auto"; set it in user or managed settings, or pass --permission-mode</p>
|
||
<p>• Changed fable and best in Claude apps gateway sessions to keep resolving to Fable 5 for now, since gateways not yet configured for Fable 5.1 reject it; pick Fable 5.1 in /model to use it</p>
|
||
<p>• Changed --add-dir, /add-dir, and additionalDirectories to refuse network paths (UNC shares, /net/&lt;host&gt; automounts) with a message before touching them; on Windows use a mapped drive letter</p>
|
||
<p>• Changed Claude apps gateway sign-in and token refresh requests to verify the gateway's pinned TLS certificate, as the managed settings fetch already does</p>
|
||
<p>• Changed Cowork and claude.ai cloud sessions: reading an artifact that isn't yours now always asks you first, even in auto mode</p>
|
||
<p>• Removed the Ctrl+E command explanation on Bash and PowerShell permission prompts</p>
|
||
<p>• [VSCode] Added collapsible ACCOUNT &amp; USAGE and SESSION MANAGER section headers to the session list panel, with the account email, the usage meter, and a View details link opening the usage dialog</p>
|
||
<p>• [VSCode] Added a model pill to the input footer that shows the current model and opens the model picker, with an Effort row and a "More models" page</p>
|
||
<p>• [VSCode] Added a collapse toggle to the Ungrouped section of the session list</p>
|
||
<p>• [VSCode] Added output style selection to the command menu, including custom styles</p>
|
||
<p>• [VSCode] Fixed third-party provider deployments (Bedrock, Vertex, and others) still showing claude.ai-only features (remote sessions, dictation, usage) and calling claude.ai with a leftover login</p>
|
||
<p>• [VSCode] Fixed the session list panel's usage meter staying blank after the panel loads; it now shows the last known usage immediately</p>
|
||
<p>• [VSCode] Fixed the "Enable Remote Control for all sessions" toggle so turning it on or off applies to sessions that are already open, not only to new ones</p>
|
||
<p>• [VSCode] Fixed screen reader announcements: a control character before a fence or heading no longer drops visible lines from speech, and bold markers spanning a heading are no longer mis-paired</p>
|
||
<p>• [VSCode] Changed the action menu to list slash commands in a filterable "Slash commands" dialog instead of inline; picking one runs it; the MCP servers dialog gained the same filter box</p>
|
||
<p>• [VSCode] Changed "Delete session" to "Archive session": archived sessions move to a collapsible "Archived sessions" group at the bottom of the list with an Unarchive action</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.252</id>
|
||
<title>Claude Code v2.1.252</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.252"/>
|
||
<updated>2026-08-31T19:46:48Z</updated>
|
||
<content type="html"><p>• Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs</p>
|
||
<p>• Fixed "always allow" not saving in a project that has no .claude/settings.local.json yet</p>
|
||
<p>• Fixed Remote Control sessions hosted by Claude Desktop or VS Code stalling for minutes after a tool finished when the connection to claude.ai was degraded</p>
|
||
<p>• Fixed background task notifications with very large failure output (for example git errors on a full disk) making the conversation exceed the API request size limit</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.251</id>
|
||
<title>Claude Code v2.1.251</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.251"/>
|
||
<updated>2026-08-28T18:19:26Z</updated>
|
||
<content type="html"><p>• Added PreModelSwitch and PostModelSwitch hook events (block, confirm, or annotate a model switch); SessionStart resume hooks now receive session staleness and the estimated re-cache cost</p>
|
||
<p>• Added live streaming of a foreground subagent's tool calls and results to Remote Control clients (background subagents, the default, still show status only)</p>
|
||
<p>• Added a Spend limit bar to /usage and a rate_limits.spend_limit status line field for developers behind a Claude apps gateway with spend limits</p>
|
||
<p>• Added a per-session prompt-cache line to /cost (hit ratio, misses, tokens re-cached, warm/cold) and a matching prompt_cache object for status line scripts</p>
|
||
<p>• Added attach, logs, stop, respawn, and rm to claude --help; the --resume message for a running background session now names the exact claude attach &lt;id&gt; command</p>
|
||
<p>• Fixed file tools (Read, Write, Edit) following a symlink swapped inside the working directory after the permission check, which could read or write outside the approved location</p>
|
||
<p>• Fixed plugin commands declared in a marketplace entry being able to point outside the plugin directory; such paths are now rejected with a path-traversal error</p>
|
||
<p>• Fixed project settings being able to enable detailed beta tracing or raw API body logging, and a lower-scope beta tracing endpoint bypassing an OTLP collector pinned by managed settings or a host app</p>
|
||
<p>• Fixed the Workflow tool reading (and quoting in errors) a scriptPath outside what the session may read before the permission check ran</p>
|
||
<p>• Fixed Grep and Glob not applying Read(...) deny rules to files reached through a symlinked search path</p>
|
||
<p>• Fixed conversations getting stuck on "text content blocks must be non-empty" errors after a turn where the model produced only thinking</p>
|
||
<p>• Fixed the first launch on a fresh install starting in default mode instead of auto mode for accounts whose startup default is auto mode</p>
|
||
<p>• Fixed Opus 5 requests failing with "effort … is not supported when thinking is disabled" when effort was xhigh/max and thinking was turned off; effort is now sent as high in that case</p>
|
||
<p>• Fixed replying to a message Claude Desktop delivered from another session: SendMessage to that session id now delivers through Claude Desktop instead of failing with "not reachable"</p>
|
||
<p>• Fixed TUI lag with many parallel subagents: per-second progress ticks now replace their predecessor instead of piling up in the transcript</p>
|
||
<p>• Fixed agent teams: a teammate's final answer not reaching the team lead — it now arrives in the idle notification instead of a content-free "available" notice</p>
|
||
<p>• Fixed background subagents being unable to reply to a message from an unnamed sibling or parent agent (from was the agent type, which is not an address)</p>
|
||
<p>• Fixed managed-settings disableAutoMode arriving mid-session not moving an already-running auto-mode session back to default mode</p>
|
||
<p>• Fixed a "switch to Opus 1M for 5x more context" tip that appeared even when the current Opus model already has a 1M context window</p>
|
||
<p>• Fixed Claude apps gateway sessions treating a stored Anthropic profile (e.g. a Console sign-in) as active: listing it in /status and retrying gateway 401s with it, though requests never use it</p>
|
||
<p>• Fixed cloud sessions telling Claude the model had changed when the host was only setting the session's initial model</p>
|
||
<p>• Fixed Remote Control reporting a failure when an organization's policy disables it; it now shows a single quiet notice instead</p>
|
||
<p>• Fixed /mcp reconnect on Remote Control showing a generic withheld-detail error instead of the real remedy when a server was disabled in another session</p>
|
||
<p>• Fixed --input-format stream-json: client-injected assistant tool calls sent without a message id were merged into the first one and their results lost, including when resuming older sessions</p>
|
||
<p>• Fixed session transcripts being silently overwritten when a directory change relocated a session onto an existing same-ID transcript</p>
|
||
<p>• Fixed background sessions and their subagents being unable to edit files inside a git worktree they created with git worktree add</p>
|
||
<p>• Fixed background sessions occasionally starting without any plugin skills (and staying that way) when another Claude Code process was refreshing the plugin marketplace at the same moment</p>
|
||
<p>• Fixed selecting text in an opened background session inside tmux over SSH: it now copies to the tmux buffer like a foreground session instead of falling back to OSC 52</p>
|
||
<p>• Fixed SDK and cloud sessions hanging indefinitely when an SDK MCP server's handshake acknowledgment was lost; the wait now times out after 70 seconds and marks only that server failed</p>
|
||
<p>• Fixed self-hosted runner leaving a stuck session's Bash tool processes running after the session was force-stopped</p>
|
||
<p>• Fixed /usage-credits for Team and Enterprise members whose admin set the org's usage-credit limit to $0: it now offers to ask the admin instead of saying a cap was reached</p>
|
||
<p>• Fixed --worktree --tmux with a merge-request number on a gitlab.com origin trying a doomed GitHub-style fetch first instead of fetching the GitLab ref directly</p>
|
||
<p>• Fixed Ctrl+G failing with "Emacs quit unexpectedly" in background sessions for editors that open /dev/tty, such as emacs -nw and micro</p>
|
||
<p>• Fixed an additionalDirectories entry containing a null byte crashing startup, or breaking /add-dir and later settings updates when it came from an SDK host, IDE, or hook; it is now skipped</p>
|
||
<p>• Fixed the MCP server menu's copy shortcut: it now says how the sign-in URL was copied instead of always claiming success</p>
|
||
<p>• Fixed italic text (such as the session recap line) rendering as highlighted blocks in GNU screen and in tmux sessions using a screen terminal type</p>
|
||
<p>• Fixed claude mcp add --header and claude mcp add-json help text naming the wrong transports</p>
|
||
<p>• Fixed claude ultrareview and /ultrareview waiting the full 30 minutes when the cloud session fails to start; they now stop early and report the reason</p>
|
||
<p>• Fixed Bash permission checks auto-approving commands that assign an arithmetic expression to an integer shell variable (e.g. OPTIND=1/0, RANDOM=2+2); these now prompt for approval</p>
|
||
<p>• Fixed backgrounded sessions (←, /background, --bg) losing a Vertex/Bedrock gateway (ANTHROPIC_*_BASE_URL + CLAUDE_CODE_SKIP_*_AUTH) exported in the shell, so every request failed</p>
|
||
<p>• Fixed claude --bg --model fable on Max plans stopping to ask for usage credits while the interactive session on the same account still had Fable allowance</p>
|
||
<p>• Fixed the one-time "make auto mode your default" offer appearing in unattended sessions (e.g. agent-team teammate panes), where a stray keypress could accept it unread</p>
|
||
<p>• Fixed the managed-settings approval prompt re-appearing after signing in again to the same Claude apps gateway when the settings are unchanged</p>
|
||
<p>• Fixed disabled /bug and /share reporting that /feedback was disabled; tips, /help, and refusal messages no longer suggest /feedback when an org policy or env var turns it off</p>
|
||
<p>• Fixed cloud session creation advising GitHub setup after a transient GitHub connection failure — the message now says to retry instead</p>
|
||
<p>• Improved CPU usage during turns in interactive sessions by cutting redundant UI re-renders</p>
|
||
<p>• Improved install size: the native binary is about 5 MB smaller</p>
|
||
<p>• Improved cloud sessions: when the session's network proxy drops a connection during a Bash command, the tool result now names the host and reason instead of only "connection reset"</p>
|
||
<p>• Improved /schedule to explain that MCP servers configured in Claude Code can't be attached to cloud routines, instead of a bare "No MCP connectors" message</p>
|
||
<p>• Improved framing of messages from your own subagents: Claude is told the sender is a worker inside this session, not an unrelated Claude session</p>
|
||
<p>• Improved the prompt placeholder to read "Message @name…" while viewing a background subagent or fork transcript opened from the subagent panel or /tasks</p>
|
||
<p>• Improved sanitization of MCP server names in error messages, menus, and command results</p>
|
||
<p>• Improved Amazon Bedrock session start under CLAUDE_CODE_PROVIDER_MANAGED_BY_HOST (e.g. Claude Desktop): a session given a Bedrock model ID or ARN no longer waits for inference-profile discovery</p>
|
||
<p>• Improved the managed settings approval dialog to list only the settings that changed since you last approved them</p>
|
||
<p>• Improved retry when the model's tool call is malformed: the broken output is now dropped from the retry context, including on Bedrock, Vertex, and Foundry</p>
|
||
<p>• Changed /radio to be available on Bedrock, Vertex AI, Foundry, and Claude Platform on AWS, and when telemetry is disabled</p>
|
||
<p>• Changed Claude in Chrome so browser actions always go through Claude Code's permission checks, including in sessions with telemetry disabled, which previously used the Chrome extension's own prompts</p>
|
||
<p>• Changed CLAUDE_CODE_SUBAGENT_MODEL to set the default subagent model rather than override everything: an agent definition's model: and an explicit per-spawn model now take precedence over it</p>
|
||
<p>• Changed the default commit trailer to Co-Authored-By: Claude Code when the active model isn't a recognized Claude model (e.g. third-party models behind a custom ANTHROPIC_BASE_URL)</p>
|
||
<p>• Changed the default model for seat-based Enterprise subscriptions to Opus 5, matching other premium plans</p>
|
||
<p>• Changed /effort to save your default effort level per model, so each model keeps its own setting when you switch</p>
|
||
<p>• Changed analytics to no longer turn off before sign-in solely because managed settings force gateway login (or cannot be read); they stay off once signed in to the gateway or via DISABLE_TELEMETRY</p>
|
||
<p>• Changed the footer PR badge on Bedrock, Vertex, and Foundry, and when telemetry is off, to call the GitHub API directly (via gh auth token, GH_TOKEN, or GITHUB_TOKEN) instead of gh pr view</p>
|
||
<p>• Changed how Bash command output files are created and read back when commands run in the sandbox, so a sandboxed command cannot redirect or replace them</p>
|
||
<p>• Changed plugin/LSP install suggestions and the auto-mode default offer to wait until you've sent or cleared what you're typing, so the Enter that sends your prompt can't answer them</p>
|
||
<p>• Changed server-managed settings that terminate sandbox TLS, route sandbox traffic through your own proxy, inject credentials, or weaken sandbox isolation to require approval before they apply</p>
|
||
<p>• Changed ANTHROPIC_CUSTOM_HEADERS from managed or project settings to require approval when it sets a credential, org/tenant, routing, or API-behavior header (e.g. Authorization, Host)</p>
|
||
<p>• Changed project-level .claude/settings.json env to no longer set CLAUDE_CONFIG_DIR, CLAUDE_CODE_TMPDIR, or TMPDIR/TMP/TEMP; set them in your shell, user, or managed settings instead</p>
|
||
<p>• Removed syntax highlighting for six rarely used languages (1c, gml, isbl, mathematica, maxima, sqf); the binary is 2.5 MB smaller</p>
|
||
<p>• [VSCode] Fixed the sign-in screen's "Bedrock, Foundry, or Vertex" button opening the docs at the top of the page instead of the third-party provider setup section</p>
|
||
<p>• [VSCode] Changed the Remote Control banner to a footer pill (shown while Remote Control is on or has failed) that opens the session on claude.ai/code; turn it on or off with /remote-control</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.250</id>
|
||
<title>Claude Code v2.1.250</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.250"/>
|
||
<updated>2026-08-28T00:49:09Z</updated>
|
||
<content type="html"><p>• Bug fixes and reliability improvements</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.248</id>
|
||
<title>Claude Code v2.1.248</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.248"/>
|
||
<updated>2026-08-27T22:12:09Z</updated>
|
||
<content type="html"><p>• Added --restricted (or CLAUDE_CODE_RESTRICTED=1): removes the built-in tools that run commands or code and WebFetch (unless named in --tools), keeps file tools inside the working directory, refuses bypassPermissions, and ignores user, project and local settings files</p>
|
||
<p>• Added experimental.cacheTtl ("5m" or "1h") to agent frontmatter: a per-agent prompt cache TTL used when no subagent TTL setting is configured</p>
|
||
<p>• Added claude self-hosted-runner --client-label &lt;label&gt; (or SELF_HOSTED_RUNNER_CLIENT_LABEL) to override the label the runner registers with (default: hostname)</p>
|
||
<p>• Added server-managed settings diagnostics: a startup warning when the settings fail to load, and a /doctor and /status line explaining a load failure or why they weren't fetched (Bedrock/Vertex/third-party provider, custom ANTHROPIC_BASE_URL)</p>
|
||
<p>• Added a warning in /web-setup when the GitHub CLI token lacks the workflow scope, since pushes to very large repositories can be rejected without it</p>
|
||
<p>• Added /usage-credits for Enterprise organizations billed through AWS Marketplace, self-serve Enterprise, and Enterprise trials, so members can request a higher usage limit from their admin</p>
|
||
<p>• Added cross-session messaging (SendMessage / ListAgents) between sessions on the same machine on Bedrock, Vertex, and Foundry, and when telemetry is disabled</p>
|
||
<p>• Fixed a prompt-cache miss (and lost extended-thinking context) roughly once an hour in long sessions, caused by tool definitions being re-rendered after an OAuth token refresh</p>
|
||
<p>• Fixed the ScheduleWakeup tool definition changing between a session and its --resume when the account had entered usage overage, causing a full prompt-cache miss on the resumed session's first turn</p>
|
||
<p>• Fixed Claude Desktop and Cowork sessions disappearing after 30 days: the transcript cleanup now keeps desktop-written sessions while they are in the app (unless org policy manages retention); the new desktopSessionCleanupPeriodDays setting caps the exemption</p>
|
||
<p>• Fixed being sent to the login screen when another Claude Code process held the token refresh lock while the session token had expired; the request now fails with a retryable error instead</p>
|
||
<p>• Windows: Fixed the claude agents list not responding to the keyboard after detaching from a session, or when launched in a terminal tab left in win32-input-mode</p>
|
||
<p>• Fixed the recommended Console sign-in in /login failing with an OAuth error before showing a sign-in URL on machines where it can't be used (for example when ANTHROPIC_API_KEY or an API key helper is set); it now falls back to the API-key sign-in</p>
|
||
<p>• Fixed model names in /model and fast-mode switch notices to render as code, so suffixes like [1m] display literally instead of as a link</p>
|
||
<p>• Fixed claude agents skipping the workspace trust prompt when the CI environment variable is set</p>
|
||
<p>• Fixed claude agents crashing on launch when the PR-status cache held a malformed entry</p>
|
||
<p>• Fixed agent view resurrecting a weeks-old background session after the machine was off: such a session now shows as stopped at its real end, and opening it asks before resuming its saved conversation</p>
|
||
<p>• Fixed agent view sometimes opening an older conversation, and dropping the typed prompt, when starting a new session</p>
|
||
<p>• Fixed claude agents: opening a stopped session that you already resumed in another terminal no longer starts a second process on that conversation; the row now says it is open in a terminal</p>
|
||
<p>• Fixed claude agents and claude rm refusing to delete a session ("has commits that are not pushed anywhere") when its worktree branch was already merged into your checked-out default branch (e.g. local main) but not yet pushed</p>
|
||
<p>• Fixed background sessions waiting silently when a PermissionRequest or PreToolUse hook prints an invalid answer: the claude agents row now names the hook and the schema error</p>
|
||
<p>• Fixed hooks silently treating a stdout {…} object that isn't valid JSON as plain text; it's now reported as a hook error with the parse message</p>
|
||
<p>• Fixed /mcp listing a project .mcp.json entry that declares the claude.ai connector type under the trusted "claude.ai" heading; it now appears under its real scope</p>
|
||
<p>• Fixed MCP servers whose headersHelper supplies the Authorization header falling into OAuth discovery on a 401 instead of re-running the helper and retrying the call as documented</p>
|
||
<p>• Fixed /login to a Claude apps gateway hanging when the managed-settings security approval dialog was required</p>
|
||
<p>• Fixed gateway model discovery (CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY) never running when apiKeyHelper is the only credential</p>
|
||
<p>• Fixed claude logs leaving mouse tracking, bracketed paste and the alternate screen switched on in the terminal it was run from</p>
|
||
<p>• Fixed the trust dialog's list of repo permission rules showing a garbled character when a long rule was cut off in the middle of an emoji</p>
|
||
<p>• Fixed the permission mode indicator staying hidden behind the "Press Ctrl-C again to exit" hint when you press shift+tab right after ctrl+c</p>
|
||
<p>• Fixed /ultrareview and locally seeded cloud sessions uploading uncommitted edits to prod.env-style and *.tfvars files, or to editor swap, temp, and backup copies of credential files (e.g. key.pem.tmp, id_rsa.swo); they now stay on your machine</p>
|
||
<p>• Fixed Remote Control sessions occasionally never showing a permission prompt or the latest messages on the connected device after the CLI silently reconnected</p>
|
||
<p>• Fixed cloud sessions occasionally failing at startup when the container's session credentials were not yet readable</p>
|
||
<p>• Fixed claude remote-control rejecting its own flags (e.g. --spawn, --name) when a global flag or a wrapper-injected option precedes the subcommand</p>
|
||
<p>• Fixed startup warnings (e.g. "N MCP servers need authentication") rendering one column right of the rest of the transcript</p>
|
||
<p>• Fixed a backgrounded worktree session losing its checkout: the background session now holds the worktree's lock while it runs, so cleanup and git worktree remove leave it alone</p>
|
||
<p>• Fixed @-mentions of other sessions not matching names typed with non-Latin characters (for example Korean entered through an IME)</p>
|
||
<p>• Fixed an invalid crossSessionInbound value being silently ignored: it now warns and holds cross-session messages (user settings) or refuses them (managed settings) until fixed</p>
|
||
<p>• Fixed rate-limit, usage, and fast-mode messages telling you to run /usage-credits when that command isn't available for your organization (e.g. hidden with DISABLE_EXTRA_USAGE_COMMAND)</p>
|
||
<p>• [VSCode] Fixed a chat tab getting stuck on "No conversation found" when its session was never saved; it now starts a new conversation instead</p>
|
||
<p>• Improved the Workflow tool's prompt footprint: its description is now about 1k tokens instead of 5.7k, with the script-writing reference moved into a bundled workflow-authoring skill</p>
|
||
<p>• Improved the prompt-footer PR badge to check GitHub less often while the pull request is unchanged; a push or a gh pr command still refreshes it right away</p>
|
||
<p>• Improved managed settings: client-side timeout, MCP startup-mode, and stream-watchdog env vars no longer trigger the settings-approval prompt</p>
|
||
<p>• Improved /ultrareview &lt;PR#&gt; to check before launch that the GitHub account connected to your Claude account can access the repository, and to explain how to fix it, instead of failing after the cloud session starts</p>
|
||
<p>• Improved cross-session messaging: falls back to a private per-user /tmp directory when the default one can't be used, and the notice and /status name the directory to fix</p>
|
||
<p>• Changed shift+enter in the agent view dispatch input to insert a newline (matching the prompt); ctrl+enter now dispatches and attaches</p>
|
||
<p>• Changed /loop: self-paced dynamic mode and the no-prompt autonomous default are now always available, including on Bedrock/Vertex/Foundry</p>
|
||
<p>• Changed Anthropic telemetry export failures to log at debug level as [Anthropic telemetry] instead of [3P telemetry] OTEL diag error, so they are not mistaken for your OTel collector failing</p>
|
||
<p>• Changed cross-session messaging in Linux user namespaces: root-equivalent trust for unmapped owners is limited to canonical system directories</p>
|
||
<p>• Changed SendMessage from a subagent to another session: the result now notes that any reply is delivered to the parent session's conversation, not to the subagent</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.247</id>
|
||
<title>Claude Code v2.1.247</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.247"/>
|
||
<updated>2026-08-26T23:06:33Z</updated>
|
||
<content type="html"><p>• Added the SendFeedback tool: when something goes wrong in a session, Claude can draft a feedback report for you to review and send from /feedback (turn off with the feedbackDrafts setting)</p>
|
||
<p>• Added {id, text, cooldownSessions, priority} entries, tipsFile, and label to spinnerTipsOverride, so organizations can rotate their own tips alongside the built-in ones</p>
|
||
<p>• Added a tip on Bash permission prompts pointing to auto mode, with a one-keystroke "Yes, and switch to auto mode" option</p>
|
||
<p>• Added /claude-api cost-optimize to profile an existing project's Claude API spend and work through cost levers (caching, token hygiene, batch, effort, model choice) one measured change at a time</p>
|
||
<p>• Updated the /claude-api skill with Admin API coverage (organization members, invites, workspaces, API keys, rate limit reports, workload identity federation, CMEK)</p>
|
||
<p>• Fixed fast arrow-key + Enter sequences acting on the row above the one you navigated to in history search, /config, /mcp, /skills, background tasks, and /model</p>
|
||
<p>• Fixed sub-agents dying on a first-call model 404: they now use the session's fallback model chain, and the error returned to the parent includes the error type, status, request id, and model</p>
|
||
<p>• Fixed a hook or background agent that printed megabytes of error output being able to overflow the conversation and wedge the session on "Prompt is too long"</p>
|
||
<p>• Fixed Ctrl keyboard shortcuts not firing under non-Latin (e.g. Cyrillic) keyboard layouts in kitty-protocol terminals</p>
|
||
<p>• Fixed text like &lt;35;150;7M being inserted into the prompt when a mouse report arrived split across reads right after the escape prefix</p>
|
||
<p>• Fixed the Bash sandbox's after-command cleanup deleting a dotfile-managed ~/.claude/settings.json symlink (nix/home-manager, stow) when it is repointed outside the sandbox's writable area</p>
|
||
<p>• Fixed /terminal-setup overwriting your entire Zed keymap.json instead of merging in its keybinding</p>
|
||
<p>• Fixed /rename silently confirming when the session registry could not be updated; it now says other sessions may still show the old name</p>
|
||
<p>• Fixed /compact and "Summarize from here" in sessions started with --agent summarizing under the default system prompt instead of the conversation's own</p>
|
||
<p>• Fixed a background session showing "opening…" forever in claude agents after its terminal host process died; the row now fails within seconds with the reason, and Enter restarts it</p>
|
||
<p>• Fixed unbounded memory growth when a hook's or background task's output file could not be written; the file now notes where output was lost</p>
|
||
<p>• Fixed /install-github-app over SSH: the copy shortcut now says how the sign-in URL was copied instead of always claiming success, and the URL appears immediately when no browser can open</p>
|
||
<p>• Fixed shell commands carried over from the foreground logging an internal error or showing a misleading [exited with code -1] line when they finish in background sessions</p>
|
||
<p>• Fixed a version-less marketplace plugin's live cache directory being deleted and recreated on a second-scope install, which could disrupt a running session using it</p>
|
||
<p>• Fixed Remote Control sessions started with /remote-control not reporting the working-tree diff to connected clients</p>
|
||
<p>• Fixed self-hosted runner sessions reporting running before Claude Code had started, which could trigger a premature "Claude is waiting for your input" notification from the Claude desktop app</p>
|
||
<p>• Fixed first-run setup exiting with "Unable to connect to Anthropic services" when managed settings configure Claude apps gateway sign-in and Anthropic endpoints are unreachable</p>
|
||
<p>• Fixed cloud sessions (Claude Code on the web, desktop and mobile apps) sometimes showing the previous permission mode when you switch modes right after sending a message</p>
|
||
<p>• Fixed cloud sessions going silent when the session's container restarts between turns while a background agent, shell, or monitor is still running — the resumed session now reports the lost work</p>
|
||
<p>• Improved plugin marketplace hardening: names containing control or invisible characters are rejected, and marketplace-supplied text in /plugin and claude plugin output is escape-safe</p>
|
||
<p>• Improved Bedrock, Vertex, and Foundry sessions (and any with telemetry disabled): Claude is now told when a configured MCP server failed to connect, instead of concluding its tools don't exist</p>
|
||
<p>• Changed Sonnet 5's default auto-compact window to its full 1M context, so sessions on the 1M window now auto-compact at about 967K tokens instead of about 934K</p>
|
||
<p>• Changed cross-session peer messages to collapse by default to a one-line Message from @&lt;sender&gt;: &lt;first line&gt; preview; Ctrl+O expands the full body</p>
|
||
<p>• Changed terminal hyperlinks in rendered markdown: link targets that point at a network or automounter path, contain a control character, or lead with an invisible character now render as plain text</p>
|
||
<p>• Changed the prompt-footer PR badge to skip its GitHub re-check on terminal refocus when the last check is under a minute old</p>
|
||
<p>• Changed analytics to stay off from startup, not only after login, when managed settings force gateway login or a custom OAuth deployment is configured</p>
|
||
<p>• Changed Claude apps gateway sign-in requests to identify Claude Code (a surface=claude_code device-authorization parameter and a claude-code/&lt;version&gt; User-Agent)</p>
|
||
<p>• Changed organization sign-in enforcement to exit at start when the administrator's managed settings cannot be read, even if host-supplied or per-user Windows registry settings exist</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.246</id>
|
||
<title>Claude Code v2.1.246</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.246"/>
|
||
<updated>2026-08-25T22:31:43Z</updated>
|
||
<content type="html"><p>• Added a startup warning for Bash allow rules with a wildcard before the subcommand (e.g. Bash(git * main)), since they also match options inserted before the subcommand</p>
|
||
<p>• Added an Auto mode tab to /permissions for viewing and editing auto mode classifier rules</p>
|
||
<p>• Added the turn's completion time to the end-of-turn duration line, e.g. ✻ Sautéed for 23s · done 6:05 PM</p>
|
||
<p>• Fixed fullscreen mode showing a blank transcript after resizing the terminal and jumping to the bottom until the next keypress</p>
|
||
<p>• Fixed a severe transcript slowdown when a diff contained a very long single line (e.g. a base64 string); such lines now render truncated with a marker</p>
|
||
<p>• Fixed erratic fullscreen scrolling when positioned at an earlier message, including jump-to-bottom getting stuck mid-transcript</p>
|
||
<p>• Fixed background sessions failing to open after 45 seconds when Claude Code's starting directory had been deleted, the machine had slept, or the host is slow to start processes</p>
|
||
<p>• Fixed background sessions failing to open with "Couldn't start the background service … EACCES" when another Claude Code process was re-installing the npm package at that moment</p>
|
||
<p>• Fixed markdown rendering being disabled for a whole message when its first 500 characters contained no markdown, and for +/N) lists and setext headings</p>
|
||
<p>• Fixed MCP tool calls interrupted by an incoming message in headless/remote sessions being reported to the model as "completed with no output" instead of an explicit interrupted error</p>
|
||
<p>• Fixed MCP tool arguments being sent as JSON strings when the parameter's schema is empty ({}), instead of their real type</p>
|
||
<p>• Fixed a command interrupted mid-run showing as "Ran 1 shell command" with no sign it was cut</p>
|
||
<p>• Fixed pressing ← or running /background during a dynamic workflow restarting its finished subagents; it now asks first and says how many subagents would restart</p>
|
||
<p>• Fixed opening a just-started session in claude agents while its worker was still booting (common on Windows) stopping it with "was stopped while the respawn was in flight"</p>
|
||
<p>• Fixed claude agents listing a backgrounded named session twice; backgrounding the same conversation again now numbers the new row (e.g. my-session (2))</p>
|
||
<p>• Fixed the background retention sweep removing git worktrees under .claude/worktrees/ that you created yourself when an old background-session record pointed at them</p>
|
||
<p>• Fixed auto mode tool calls being denied as "temporarily unavailable" on very large sessions by scaling the safety-check deadline with prompt size</p>
|
||
<p>• Fixed the plugin cache creating duplicate SHA-named directories for the same plugin</p>
|
||
<p>• Fixed plugin skills whose frontmatter name already includes the &lt;plugin&gt;: prefix showing it doubled in the slash menu (e.g. /plugin:plugin:skill)</p>
|
||
<p>• Fixed claude plugin update failing for an installed plugin given its bare name (only the fully-qualified name worked)</p>
|
||
<p>• Fixed plugin installation failing when plugin.json was saved with a UTF-8 byte-order mark (BOM)</p>
|
||
<p>• Fixed /reload-plugins reporting 0 skills for plugins that define skills under skills/*/SKILL.md</p>
|
||
<p>• Fixed hook error messages showing a literal ${CLAUDE_PLUGIN_ROOT} instead of the resolved plugin path</p>
|
||
<p>• Fixed /rename replacing the theme's prompt border color (including a custom theme's promptBorder) with the default cyan; the border now keeps your theme's color unless you pick one with /color</p>
|
||
<p>• Fixed custom theme diff colors (diffAdded/diffRemoved and their dimmed variants) being ignored in diffs and the /theme preview</p>
|
||
<p>• Fixed a keybindings.json binding with an unknown action name silently deadening that key; it is now skipped so the default binding keeps working, and a warning is logged under --debug</p>
|
||
<p>• Fixed /stats activity heatmap showing each day's activity one cell off (Sunday's count under Monday) in timezones east of UTC</p>
|
||
<p>• Fixed /fork from an already-forked or backgrounded session starting the new session with an empty conversation</p>
|
||
<p>• Fixed prompts beginning with /-- (e.g. Lean doc comments) being rejected as an unknown slash command instead of being sent to Claude</p>
|
||
<p>• Fixed the @ file picker staying open after the typed text stopped matching a real path</p>
|
||
<p>• Fixed the status line's cost and duration resetting to zero after navigating to the agents view and back</p>
|
||
<p>• Fixed fullscreen mode moving keyboard focus onto the control under the pointer when you clicked the terminal window only to bring it back into focus</p>
|
||
<p>• Fixed path completion failing when the completion token or working directory contained a null byte</p>
|
||
<p>• Windows/macOS: Fixed headless sessions not cleaning up stale entries in ~/.claude/sessions left by sessions that exited uncleanly</p>
|
||
<p>• Fixed the UI stopping with a render error on the first tool call when a third-party Anthropic-compatible endpoint (ANTHROPIC_BASE_URL) streams a tool_use block without an id</p>
|
||
<p>• Fixed the Write tool reporting "Out of memory" or freezing for a long time after overwriting a very large existing file, even though the file had been written</p>
|
||
<p>• Fixed claude plugin install &lt;name&gt; exiting silently (or hanging in a terminal) instead of reporting an error when ~/.claude/plugins/known_marketplaces.json is empty or corrupted</p>
|
||
<p>• Fixed resumed sessions failing every turn with a 400 when the saved history contains tool blocks the Anthropic API does not accept (typically written by a third-party API proxy)</p>
|
||
<p>• Fixed curl -fsSL https://claude.ai/install.sh | bash failing with "Raw mode is not supported" for some Team/Enterprise users with server-managed settings</p>
|
||
<p>• Fixed sessions that ended in plan mode resuming outside plan mode in the VS Code extension, and in claude -p --continue/--resume with a permission prompt tool, when no permission mode was set</p>
|
||
<p>• Fixed the Notification hook not firing while the sandbox "Network request outside of sandbox" permission prompt is waiting</p>
|
||
<p>• Fixed Bash permission checks to always require approval for malformed commands with a dangling &amp;&amp; or || operator</p>
|
||
<p>• Fixed --strict-mcp-config sessions prompting to approve .mcp.json servers they would never load, which left background sessions waiting at startup</p>
|
||
<p>• Fixed telemetry and metrics requests to Anthropic carrying the API key configured for a third-party gateway (ANTHROPIC_BASE_URL); a credential is now only sent to its own host</p>
|
||
<p>• Fixed a visible API error on the first prompt after idle when apiKeyHelper returns short-lived JWTs: an expired cached token is now refreshed before sending, and 401/403 auth errors retry quietly</p>
|
||
<p>• Fixed memory growing with session length in the fullscreen and Ctrl+O transcript views: each rendered message row no longer retains a full copy of the transcript-wide tool lookups</p>
|
||
<p>• Fixed /ultrareview runs and cloud sessions launched at the same time from one repository (e.g. from several worktrees) sometimes starting with another launch's uncommitted changes</p>
|
||
<p>• Fixed the task progress count (e.g. 3/5) shown for background cloud sessions such as /autofix-pr occasionally missing a task</p>
|
||
<p>• Fixed Remote Control sessions keeping their placeholder name in claude.ai and the Claude app until the second prompt; the auto-generated title now appears after the first prompt</p>
|
||
<p>• Fixed MCP tools marked requiresUserInteraction still offering "Yes, and don't ask again" in their permission prompt; the option wrote an allow rule the tool then ignored</p>
|
||
<p>• Fixed the self-hosted runner ending its live sessions or exiting when a work-poll response is malformed (e.g. an intercepting proxy's HTML page); it now retries the poll</p>
|
||
<p>• Improved /cd: the new directory's project settings, hooks, .mcp.json servers (behind the usual approval prompt), skills, and agents now take effect right after the move instead of on --resume</p>
|
||
<p>• Improved Bash tool latency on bash shells by replaying snapshot functions without a base64 subshell per function</p>
|
||
<p>• Improved subagent results: a subagent that stops at its maxTurns limit now returns its output marked as partial, with a hint to continue it via SendMessage, instead of appearing finished</p>
|
||
<p>• Improved non-interactive sessions (-p, SDK, cloud sessions) to automatically continue a response cut off mid-stream by a server error, connection loss, or stall instead of ending with an error</p>
|
||
<p>• Improved attribution of usage telemetry to your organization for workload identity federation sessions, events sent while apiKeyHelper runs at startup, and after a login token expired while idle</p>
|
||
<p>• Changed /code-review so Claude can also start it on its own on Bedrock, Vertex AI, and Foundry, through the Claude apps gateway, and when telemetry or non-essential traffic is disabled</p>
|
||
<p>• /goal: Changed idle sessions to start at most three check-ins on long-running background work per goal; your next message allows three more</p>
|
||
<p>• Changed claude install and claude update to defer a pending managed-settings consent prompt to the next interactive session instead of prompting mid-command</p>
|
||
<p>• Changed OpenTelemetry plugin events for plugins synced from claude.ai: plugin_id_hash now reflects the plugin's real marketplace, and enabled_via is admin-install for admin-installed plugins</p>
|
||
<p>• Fixed the command sandbox's filesystem configuration not respecting --setting-sources</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.245</id>
|
||
<title>Claude Code v2.1.245</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.245"/>
|
||
<updated>2026-08-25T05:13:17Z</updated>
|
||
<content type="html"><p>• Fixed a crash on startup on Linux distributions that ship glibc 2.44 (for example Arch Linux, CachyOS and Fedora Rawhide)</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.243</id>
|
||
<title>Claude Code v2.1.243</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.243"/>
|
||
<updated>2026-08-25T05:13:17Z</updated>
|
||
<content type="html"><p>• Added a Loops breakdown to /usage: per-loop run count, total tokens, tokens per run, and last run, so runaway or chatty /loop tasks are easy to spot</p>
|
||
<p>• Added modelPicker setting: curate the /model picker with an ordered, labeled list of models (any id spelling, including Vertex/Bedrock ids), appended to or replacing the built-in lineup</p>
|
||
<p>• Added promptCacheTtl and subagentPromptCacheTtl settings so API-key and cloud-provider users can keep a 1-hour prompt cache on the main conversation while subagents stay at 5 minutes</p>
|
||
<p>• Added modelPricing managed setting so an organization's contracted per-model rates and discount multiplier are used for /cost, the status line, and telemetry cost figures instead of list price</p>
|
||
<p>• Added a keyless sign-in under /login → Anthropic Console: "Sign in with your Console account" (recommended) alongside creating an API key, so organizations that don't allow API keys can sign in</p>
|
||
<p>• Added a Skipped sources line to /status that lists managed settings sources (for example managed-settings.json) present but not applied because a higher-precedence managed source is active</p>
|
||
<p>• Added a managed marker in /mcp and /plugins on claude.ai connectors whose authentication is managed by your organization</p>
|
||
<p>• Added a tip pointing claude.ai users who haven't connected GitHub for Claude Code on the web to /web-setup</p>
|
||
<p>• Added a /status line showing whether GitHub is connected for Claude Code on the web (Pro/Max), pointing to /web-setup when it isn't</p>
|
||
<p>• Added the model (and effort level) each subagent ran on to /tasks and the agent detail dialogs</p>
|
||
<p>• Fixed remote MCP servers in non-interactive (-p) and SDK sessions never recovering after a dropped connection; they now reconnect automatically or report as failed</p>
|
||
<p>• Fixed MCP server sign-in started from the desktop app failing with "Invalid redirect URI" on servers that support client ID metadata documents (for example Linear)</p>
|
||
<p>• Fixed auto mode staying unavailable at startup when a temporary server-side disable was cached and later flag fetches failed</p>
|
||
<p>• Fixed auto mode tool calls being denied as "temporarily unavailable" after about a minute of waiting when the API was briefly overloaded and asked the client to retry</p>
|
||
<p>• Fixed the /model picker silently ignoring an Ultracode selection; picking Ultracode now applies it to the current session</p>
|
||
<p>• Fixed /resume only listing the 50 most recent sessions; the picker now loads more as you scroll</p>
|
||
<p>• Fixed cloud sessions resuming after a mid-turn restart with a pending hook or background-task notification re-sent as the prompt instead of the normal continuation message</p>
|
||
<p>• Fixed cross-session messaging silently turning off inside user namespaces and rootless containers after the 2.1.232 socket-directory hardening</p>
|
||
<p>• Fixed text that hangs outside its container (for example the sign-in URL in /login) losing its leading columns when another part of the screen repaints</p>
|
||
<p>• Fixed spellcheck not underlining a misspelled word typed directly after an emoji</p>
|
||
<p>• Fixed background subagents not waking when their last background Bash task completes</p>
|
||
<p>• Fixed sessions going silent for 10+ minutes when the Anthropic API never starts a response: the request now times out after ~3 minutes, retries once, then shows API Error: No response from API</p>
|
||
<p>• Fixed auth, model-availability, and other client-generated error messages rendering like model output instead of as error lines</p>
|
||
<p>• Fixed workload identity federation in CI: processes in one job share the exchanged token instead of re-exchanging the single-use token; a rejected exchange fails fast with the server's message</p>
|
||
<p>• Fixed server-managed companyAnnouncements not showing at startup in a session that began with signing in (for example the first launch after /logout)</p>
|
||
<p>• Fixed hook if conditions like Bash(cat *) firing on unrelated Bash commands when the command contained $() or backtick command substitution followed by more arguments</p>
|
||
<p>• Fixed plugin dependencies declared with a marketplace field never resolving when both plugins are loaded together via --plugin-dir</p>
|
||
<p>• Fixed /reload-plugins keeping the LSP tool after the last LSP plugin is disabled; it now also warns before an LSP plugin change that would re-read the conversation</p>
|
||
<p>• Fixed --agents silently ignoring invalid JSON or invalid agent definitions; it now exits with a clear error, like --mcp-config</p>
|
||
<p>• Fixed /status showing "Found invalid entries in: ." with no filename when ~/.claude.json has an invalid MCP server entry</p>
|
||
<p>• Fixed /clear removing the /rename session name from the prompt bar even though the name was kept for the new session</p>
|
||
<p>• Fixed Ctrl+R history search and up-arrow history breaking when ~/.claude/history.jsonl contains a malformed entry</p>
|
||
<p>• Fixed Ctrl+[ not leaving vim INSERT mode in terminals that encode modified keys (modifyOtherKeys / kitty protocol)</p>
|
||
<p>• Fixed the local IDE connection being routed through HTTPS_PROXY (and sometimes failing) when localhost was listed in NO_PROXY but not lowercase no_proxy; both casings are now honored</p>
|
||
<p>• Fixed sandbox network-violation details being dropped from the Bash tool result when the blocked command still exited 0 (for example curl printing the proxy's 403 page)</p>
|
||
<p>• Fixed the status line rate_limits fields and /usage still showing a rate-limit window's pre-reset usage percentage after the window reset while the session was idle</p>
|
||
<p>• Fixed claude --teleport &lt;session&gt; exiting on uncommitted changes instead of offering to stash them and continue, as the session picker already does</p>
|
||
<p>• Fixed /web-setup repeatedly asking you to log in when an older GitHub CLI (without gh auth token) was already authenticated</p>
|
||
<p>• Fixed Claude in Chrome losing its connection to Claude Code after an auto-update cleaned up the version it was set up with; the native host now launches via the stable claude launcher</p>
|
||
<p>• [VSCode] Fixed sessions started before feature flags were first fetched (for example right after install) opening in the default permission mode instead of auto mode or your configured default mode</p>
|
||
<p>• [VSCode] Fixed Focus view sections you expanded collapsing on their own during subagent tool activity</p>
|
||
<p>• Improved startup time: sandbox and MCP bring-up no longer block the first frame, bare launches skip subcommand registration, and workflow discovery, settings, and trust-store work is cheaper</p>
|
||
<p>• Improved native install and auto-update download size: the binary is now zstd-compressed (about 75 MB instead of 340 MB on Linux x64)</p>
|
||
<p>• Improved attribution of usage telemetry to your organization for sessions that authenticate with ANTHROPIC_AUTH_TOKEN directly against the Anthropic API, so its data-handling settings apply</p>
|
||
<p>• Improved native binary size: about 2 MB smaller by storing the bundled skill and prompt text more compactly</p>
|
||
<p>• Improved memory usage of native builds: code is now loaded on demand instead of keeping the whole bundle resident (roughly 40–70 MB less memory per session)</p>
|
||
<p>• Improved peak memory usage in long-running sessions (the runtime now garbage-collects sooner as the heap grows)</p>
|
||
<p>• Improved /login over SSH: the sign-in URL appears immediately, pressing c reports how the URL was copied instead of always claiming success, and a hint explains how to select text in fullscreen</p>
|
||
<p>• Improved the error when effort xhigh/max is used with thinking turned off: it now names the level, the setting that disabled thinking, and /effort high as the fix</p>
|
||
<p>• Improved /loop: consecutive wake-ups where Claude has nothing to do now fold into a single line in the terminal instead of printing each one</p>
|
||
<p>• Changed the sandboxed Bash tool prompt to no longer list allowed network hosts, so Claude attempts requests (and you can approve new hosts) instead of assuming unlisted hosts are blocked</p>
|
||
<p>• Updated the /model picker and the bundled claude-api skill to show Sonnet 5's $2/$10 per Mtok pricing as its standard list price rather than a limited-time promo</p>
|
||
<p>• Changed computer use on macOS so clicking the desktop, Dock, or a Finder window requires granting Finder via the access dialog, like any other app</p>
|
||
<p>• Changed /model, /fast, and /effort to also run immediately instead of queueing until the turn ends on Bedrock, Vertex, and Foundry and when telemetry is disabled</p>
|
||
<p>• Fixed claude remote-control exiting and stranding attached Remote Control sessions when the server drops its environment mid-session; it now recovers</p>
|
||
<p>• Fixed Remote Control sessions served by claude remote-control sometimes getting stuck after it was stopped and restarted, for Team and Enterprise members without an admin or owner role</p>
|
||
<p>• Changed the cross-session messaging inbox socket to close connections that send no complete line within 30 seconds; scripts posting to it should connect once their data is ready</p>
|
||
<p>• Improved the notice when resuming a conversation whose Remote Control is held by another terminal: it now says sessions on other machines can't be seen from, or reach, this one</p>
|
||
<p>• [VSCode] Improved history trimming in long sessions: older tool-activity rows are dropped first so your messages and Claude's replies stay visible</p>
|
||
<p>• [VSCode] Improved attribution of the extension's own usage telemetry to your organization when you are signed in with a Claude account, so its data-handling settings apply</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.241</id>
|
||
<title>Claude Code v2.1.241</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.241"/>
|
||
<updated>2026-08-23T00:52:10Z</updated>
|
||
<content type="html"><p>• Bug fixes and reliability improvements</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.240</id>
|
||
<title>Claude Code v2.1.240</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.240"/>
|
||
<updated>2026-08-22T14:45:21Z</updated>
|
||
<content type="html"><p>• Bug fixes and reliability improvements</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.239</id>
|
||
<title>Claude Code v2.1.239</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.239"/>
|
||
<updated>2026-08-21T19:54:16Z</updated>
|
||
<content type="html"><p>• Cost estimates (/cost, status line, --max-budget-usd) now include the 1.1× US-only-inference premium for data-residency workspaces</p>
|
||
<p>• Added the one-time fullscreen renderer offer on Bedrock, Vertex, Foundry and other previously excluded setups; new installs there now start in fullscreen</p>
|
||
<p>• Added /claude-api upgrade to migrate Python projects from anthropic 0.x to 1.x, and updated the skill's Python reference for 1.x (timeouts use anthropic.Timeout, not httpx.Timeout)</p>
|
||
<p>• Cloud sessions: plugins synced from claude.ai now show as name@synced, work with claude plugin enable/disable &lt;name&gt;@synced, and never override a same-named plugin you installed</p>
|
||
<p>• Alpine/musl builds: native image paste, clipboard, and audio-capture add-ons now load (musl-built binaries instead of glibc ones refused by the runtime)</p>
|
||
<p>• The usage-limit message shown when your monthly spend limit is already used up now also says when your session or weekly limit resets</p>
|
||
<p>• Fixed Bedrock streaming behind proxies that strip the response Content-Type header, which silently doubled billed API calls by re-running every turn non-streaming</p>
|
||
<p>• Fixed Claude Code hanging at startup behind an HTTPS proxy when using Bedrock with an SSO profile and awsAuthRefresh — the credential pre-check now honors HTTPS_PROXY</p>
|
||
<p>• Fixed a raw crash dump when starting Claude Code from a directory that no longer exists; it now prints a clear message</p>
|
||
<p>• Fixed Edit and Write calls pausing for about 5 seconds in JetBrains IDE terminals when the Claude Code plugin is connected</p>
|
||
<p>• Fixed a race where pressing Esc with a prompt queued could let the next turn finish early, leaving the session idle while Claude was still working and letting a later resubmit repeat actions</p>
|
||
<p>• Fixed WebFetch retaining expired page content in memory for the whole session instead of the intended 15 minutes</p>
|
||
<p>• Fixed cloud sessions (Claude Code on the web, desktop and mobile apps) resuming out of plan mode after an idle worker restart</p>
|
||
<p>• Fixed MCP elicitation forms taller than the terminal being clipped in fullscreen mode: the form now fits the window, with hidden fields reachable by scrolling and Accept/Decline always visible</p>
|
||
<p>• Fixed remote MCP servers staying failed after a transient 5xx on a mid-session reconnect in cloud sessions or via SDK setMcpServers()</p>
|
||
<p>• Fixed custom session titles disappearing from /resume after more than ~64 KB of conversation was written following the rename</p>
|
||
<p>• Fixed claude -c/resume picking up sessions from a different directory whose path differed only by characters like _, -, or .</p>
|
||
<p>• Fixed /resume and the agents view showing a session as recently changed (and reordering it) when only its file was touched or it was merely reopened</p>
|
||
<p>• Fixed /resume in all-projects mode telling you to cd into a deleted directory (e.g. a removed worktree); such sessions now resume in the current directory</p>
|
||
<p>• Fixed the dark-ansi theme rendering expanded tool results in fullscreen mode with text the same color as the background</p>
|
||
<p>• Fixed the fullscreen renderer prompt reappearing on every launch when it could never be answered; it now stops after being shown on three launches</p>
|
||
<p>• Fixed .worktreeinclude patterns starting with **/ silently matching nothing when the target lived in a gitignored directory</p>
|
||
<p>• Fixed agents, skills, and commands whose .md file starts with a UTF-8 BOM being silently ignored</p>
|
||
<p>• Fixed /insights echoing literal &lt;message&gt; tags in its response on some models</p>
|
||
<p>• Fixed marketplace metadata.pluginRoot having no effect: bare plugin source names now resolve under it as the docs describe</p>
|
||
<p>• Fixed mouse movement in browser-based terminals inserting text like "35;150;7M" into the prompt when a mouse report arrived split across writes</p>
|
||
<p>• Fixed custom theme overrides for the effort/ultracode status badge colors being ignored</p>
|
||
<p>• Fixed OpenTelemetry trace fragmentation: tool executions deferred by a PreToolUse hook now resume in the original turn's trace instead of starting a new trace</p>
|
||
<p>• Fixed vim mode in the agent view: Escape now switches to NORMAL mode and keeps your text instead of clearing the prompt</p>
|
||
<p>• Fixed the selection:copy keybinding silently dropping a text selection that had been extended with Shift+Arrow keys</p>
|
||
<p>• Fixed the /voice startup tip still appearing after voice dictation was enabled via the voice.enabled setting</p>
|
||
<p>• Fixed shell-mode (!) Tab completion dropping the ./ from a ./script path, which left a command the shell couldn't run</p>
|
||
<p>• Fixed fullscreen mode answering a permission prompt or pressing a button when you clicked the terminal window only to bring it back into focus</p>
|
||
<p>• Fixed slash-command panels (e.g. /config, /model) in fullscreen mode covering the latest messages; the conversation now stays pinned above the panel</p>
|
||
<p>• Fixed the /workflows detail dialog overflowing the terminal and losing its header off-screen when opened while Claude is still responding</p>
|
||
<p>• Fixed the Linux sandbox making a nonexistent .git/config.worktree unreadable, which broke every sandboxed git command in repos with extensions.worktreeConfig set</p>
|
||
<p>• Fixed hooks failing with "posix_spawn ENOENT" after the session's working directory was deleted; they now run from the project root or home directory instead</p>
|
||
<p>• Fixed claudeMdExcludes not excluding a symlinked .claude/rules file when the pattern names the rules directory or the symlink rather than its target</p>
|
||
<p>• Fixed runaway session-title syncing to Remote Control when two Claude Code processes shared one background job's state (2.1.232 regression); title updates are now deduplicated and rate-limited</p>
|
||
<p>• Fixed sessions whose title starts with / being unaddressable by SendMessage and shown as "(untitled)" in ListAgents</p>
|
||
<p>• Fixed Ctrl+W, Ctrl+U, Ctrl+K, Option+Backspace, Option+D and vim df/dt leaving a broken [Pasted text #N] placeholder when the cursor was inside it</p>
|
||
<p>• Fixed masked (password-style) inputs such as the login code field letting their text be pasted back with Ctrl+Y elsewhere or saved to prompt history when cleared with double Esc</p>
|
||
<p>• Fixed Ctrl+Backspace deleting one character instead of a word in search boxes</p>
|
||
<p>• Fixed a request rejected by an organization policy check being re-sent before the rejection was shown</p>
|
||
<p>• Improved the reminder shown after compaction so a skill's original arguments are not re-run as a new request</p>
|
||
<p>• Long file paths on tool-use rows now truncate in the middle to stay on one line</p>
|
||
<p>• Remote sessions keep sending keep-alives while a long SessionStart or Setup hook runs, so the container is not idle-reaped mid-hook</p>
|
||
<p>• /goal: repeat check-ins on long-running background work now back off (30 min, then 1 h, then every 2 h) instead of repeating every 30 minutes</p>
|
||
<p>• /goal: resuming a session from the claude --resume picker now restores its active goal</p>
|
||
<p>• ListAgents now tells a session its own name (the one peers use to message it), and SendMessage to your own name says so instead of "no agent named …"</p>
|
||
<p>• ListAgents and /list-agents now list your live teammates (previously only subagents and other sessions appeared, so a reachable teammate looked absent)</p>
|
||
<p>• keybindingFlavor: "readline" now also matches Bash for word keys: Alt+F and Ctrl/Option+→ stop at the end of the word, Alt+D deletes to it (Ctrl+Y pastes it back), and punctuation separates words</p>
|
||
<p>• Persistent retry mode (CLAUDE_CODE_RETRY_WATCHDOG) now fails immediately on organization spend-limit and out-of-credits errors instead of waiting indefinitely for a reset</p>
|
||
<p>• Claude in Chrome: /clear now closes the session's Chrome tab group, and empty groups are closed on /resume and when Claude Code exits</p>
|
||
<p>• Remote sessions: images uploaded from mobile now include their saved file path, so Claude can copy them into files it creates</p>
|
||
<p>• Claude Code on the web: requests from Bash and other tools to non-API anthropic.com hosts (e.g. www, docs) now go through the session's network proxy, so your environment's allowed domains apply</p>
|
||
<p>• Remote Control: clearer message and claude doctor wording when Remote Control isn't enabled for your account</p>
|
||
<p>• Windows: cross-session messaging is now available, so Claude Code sessions across your machines can message each other with SendMessage and find each other with ListAgents, as on macOS and Linux</p>
|
||
<p>• [VSCode] "View usage" in the usage-limit banner now sits inline with the warning text instead of floating mid-banner</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.238</id>
|
||
<title>Claude Code v2.1.238</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.238"/>
|
||
<updated>2026-08-20T20:33:43Z</updated>
|
||
<content type="html"><p>• Added a keybindingFlavor setting: set it to "readline" to make Ctrl+W in the prompt delete back to the previous whitespace, as in Bash; the default ("classic") is unchanged</p>
|
||
<p>• Plugin marketplaces: headersHelper on a url marketplace or a catalog entry runs a command that mints HTTP headers (e.g. a short-lived token) for catalog and same-origin archive fetches</p>
|
||
<p>• A catalog entry's headersHelper runs only when you install or update that plugin, after its command is shown; claude plugin install/update ask [y/N] (or pass -y)</p>
|
||
<p>• Added claude self-hosted-runner --defer-shutdown-max-min &lt;minutes&gt;: on SIGTERM, keep serving attached sessions, park what is left after that many minutes, then exit</p>
|
||
<p>• Added claude self-hosted-runner --proxy-authorization-command / --proxy-authorization-file for egress proxies that require a freshly issued Proxy-Authorization header on every connection</p>
|
||
<p>• Fixed unbounded memory growth in long interactive sessions: subagent tool results are now released once they leave the recent display window</p>
|
||
<p>• Fixed custom, project, and plugin output styles drifting back to the default voice mid-session</p>
|
||
<p>• Fixed CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION=true not keeping prompt suggestions on when your account is near, but not over, its usage limit</p>
|
||
<p>• Fixed worktree-isolation Bash refusals telling you to remove a redirect when the command had none</p>
|
||
<p>• Fixed self-hosted runners occasionally being removed by the server after a single slow or lost poll request, handing their healthy session to another runner</p>
|
||
<p>• Fixed MCP elicitation dialogs showing nothing for URLs longer than 4,096 characters, and permission prompts dropping the "don't ask again" option when the project path didn't fit the terminal width</p>
|
||
<p>• Fixed leftover /tmp/claude-*-cwd files when a Bash command is killed, times out, or is interrupted</p>
|
||
<p>• Fixed held Backspace being ignored on terminals that send Ctrl+H for Backspace when keystrokes arrive in large bursts (slow SSH/mosh links)</p>
|
||
<p>• Fixed text-wrapping in permission prompt diffs: lines containing wide multi-code-point characters (such as emoji) or tabs are no longer clipped</p>
|
||
<p>• Fixed killing a suspended (Ctrl+Z) session sometimes leaving the terminal in bracketed-paste mode with the cursor hidden</p>
|
||
<p>• Fixed stdio MCP servers receiving a server/discover request before initialize, forcing lazy servers to start their backend on every session open</p>
|
||
<p>• Fixed a proxy's refusal of a connection being reported as a generic network error instead of naming the proxy</p>
|
||
<p>• Fixed the /model and /effort cache-miss warning appearing when the prompt cache had already expired</p>
|
||
<p>• Fixed per-task Stop from the Remote Control tasks panel doing nothing on CLI-hosted sessions</p>
|
||
<p>• Fixed remote sessions exiting when a client delivered a user message without a valid role</p>
|
||
<p>• Fixed Remote Control sessions started by claude remote-control inheriting session-scoped environment variables from the launching shell</p>
|
||
<p>• Fixed a Remote Control session whose process crashed staying unavailable until claude remote-control was restarted; it can now be reused when you next message it</p>
|
||
<p>• Fixed Remote Control messages sent from the web or Desktop while Claude is mid-turn disappearing from the transcript after the turn finishes</p>
|
||
<p>• Fixed Remote Control model picks made on a phone or web not updating the model shown in the terminal</p>
|
||
<p>• Fixed Remote Control disconnecting with "login expired" when a brief network hiccup delays renewing your sign-in; it now retries and stays connected</p>
|
||
<p>• Fixed Remote Control reporting a failed reconnect on sign-out; signing out now ends the session with a clear message</p>
|
||
<p>• Fixed ListAgents/SendMessage reporting "Remote Control is not connected" in sessions run by claude remote-control (server mode) or Desktop/IDE hosts; they now list and reach Remote Control peers</p>
|
||
<p>• Fixed ListAgents and SendMessage exposing the idle worker that the agent view pre-warms for your next background session; it now appears only once a task claims it</p>
|
||
<p>• Cross-session messaging: sending to a session on this machine that refuses inbound messages (e.g. crossSessionInbound: "refuse") now reports "refused" to the sender instead of a silent success</p>
|
||
<p>• Cross-session messaging: a session whose inbox drops your messages (rate limit or full queue) now tells your session, instead of the messages vanishing silently</p>
|
||
<p>• Improved startup: bare claude starts sooner on macOS</p>
|
||
<p>• Improved Bash tool permission checking for zsh-specific syntax in shell conditionals</p>
|
||
<p>• Improved Remote Control connection resilience: brief HTTP 403 refusals from a network edge, VPN, or proxy are now tolerated for up to 3 minutes, with the refusing party named when a block persists</p>
|
||
<p>• Improved startup responsiveness: the automatic update check now runs about 10 seconds after launch instead of competing with startup for CPU</p>
|
||
<p>• Updated the bundled claude-api skill for the Managed Agents Aug 19 release: web search/fetch domain settings and memory stores on self-hosted sandboxes</p>
|
||
<p>• Changed Ctrl+L and Cmd+K in fullscreen to always just repaint — the double-press /clear shortcut was removed, and 1-row nvim terminals no longer trigger automatic /clear loops</p>
|
||
<p>• Changed claude mcp list and claude mcp get to show disabled servers as ⊘ Disabled instead of connecting to them for a health check</p>
|
||
<p>• MCP headersHelper in a project .mcp.json, and inline MCP servers in project or --add-dir agent files, now require that folder's trust dialog to have been accepted (also under claude -p)</p>
|
||
<p>• MCP headersHelper from a project .mcp.json, plugin, or agent file runs without inherited credential env vars; user, managed and claude.ai-scope helpers now run from the Claude config dir</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.237</id>
|
||
<title>Claude Code v2.1.237</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.237"/>
|
||
<updated>2026-08-20T00:54:35Z</updated>
|
||
<content type="html"><p>• Fixed prompt caching for sessions using an LLM gateway or custom base URL</p>
|
||
<p>• Added a built-in "Concise" output style: Claude leads with results and skips preamble and narration, while doing the work just as thoroughly. Select it under Output style in /config.</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.236</id>
|
||
<title>Claude Code v2.1.236</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.236"/>
|
||
<updated>2026-08-19T20:01:57Z</updated>
|
||
<content type="html"><p>• Added ANTHROPIC_DEFAULT_MODEL environment variable: sets the model new sessions start on, while a /model pick still overrides it and persists across restarts (unlike ANTHROPIC_MODEL)</p>
|
||
<p>• Added notify_when_idle to cross-session SendMessage: ask another Claude Code session on this machine to send one notice when it next goes idle — opt-in, one-shot, no polling (macOS and Linux)</p>
|
||
<p>• Sandbox: on macOS, wildcard read-deny rules (e.g. **/.env) now take precedence inside allowed read regions, cover matched directories' contents, and can't be bypassed by renaming the denied file</p>
|
||
<p>• Fixed clipboard copy, background housekeeping, background sessions, and local MCP logs breaking after the directory a session had switched into was removed (since 2.1.229)</p>
|
||
<p>• Fixed the fullscreen renderer failing permanently after a single failed start: it now falls back to the classic renderer instead of exiting on every subsequent launch</p>
|
||
<p>• Fixed the /model picker rendering taller than the terminal: it now shows only as many models as fit the window, with the rest reachable by scrolling</p>
|
||
<p>• Fixed SendMessage calls being rejected when a malformed closing tag left the message text inside the summary field</p>
|
||
<p>• Fixed unhandled promise rejections when a subprocess fails to start, for example powershell.exe on WSL with Windows interop disabled (regression in 2.1.234)</p>
|
||
<p>• Fixed fullscreen mode sometimes not showing a newly sent message until the next update after the terminal was resized</p>
|
||
<p>• Fixed a blank band that could remain above the prompt after clearing a multi-line prompt, and panes not repainting after resizing the terminal away and back, in fullscreen mode</p>
|
||
<p>• Fixed the managed-settings approval prompt sometimes not appearing at startup while still capturing the first keypress as approval</p>
|
||
<p>• Fixed terminal tab titles jumping in tmux (iTerm tmux integration): the title is now written only when its text changes instead of animating every 960ms</p>
|
||
<p>• Fixed an unclear error when the cloud environments list came back empty or malformed</p>
|
||
<p>• Fixed the Fable 5 first-time usage-credits prompt auto-selecting the fallback model after 60 seconds with no answer when using Remote Control</p>
|
||
<p>• Fixed spinner tips never appearing, with a repeated background error, when the cached guest-pass reward in ~/.claude.json was malformed</p>
|
||
<p>• Fixed skills hot-reload in SDK/VS Code sessions raising an error on every skills change after the session's working directory was deleted (2.1.229+)</p>
|
||
<p>• Fixed self-hosted runner sessions released on idle, retire, or startup timeout occasionally resuming on another runner before the post-session hook had finished</p>
|
||
<p>• Fixed the Clawd mascot's eyes and feet rendering unevenly in iTerm2 at some font sizes</p>
|
||
<p>• Fixed occasional runaway session recaps: recap text (automatic and /recap) is now capped at 400 characters, cut at a word boundary</p>
|
||
<p>• Improved startup performance: the session counter is now written in the background</p>
|
||
<p>• Improved auto mode: Monitor allow rules are now set aside while auto mode is active, so Monitor commands are reviewed the same way Bash commands are</p>
|
||
<p>• Improved auto mode on Bedrock, Vertex AI, and Foundry, and when telemetry is disabled: the classifier now uses the same defaults as on the Claude API, including severity-scored classification</p>
|
||
<p>• Improved auto mode: the git status check can no longer be fooled by a repo's status.showUntrackedFiles=no setting into reporting a clean tree</p>
|
||
<p>• Changed the /model picker to highlight only the newest model's name, so the highlight marks the new release rather than an arbitrary subset of the list</p>
|
||
<p>• /goal: an idle session whose goal is parked behind long-running background work now checks in automatically after 30 minutes (then 1h, 2h) instead of waiting for you to return</p>
|
||
<p>• /usage now shows the usage-credits spend row for Team and Enterprise members, and shows a capped row at 0% before anything is spent</p>
|
||
<p>• SIGTERM in print/SDK mode no longer records an interrupted turn or synthetic tool denials before exiting; running commands are still terminated and the process still exits with code 143</p>
|
||
<p>• Pressing Enter on a slash-command typo or a command unavailable in this session now reports it instead of running the closest fuzzy match; prefixes and aliases still run</p>
|
||
<p>• Remote Control now marks a session offline within seconds when the CLI exits or its terminal closes</p>
|
||
<p>• SendMessage now refuses further messages to a session up front once a rapid burst would exceed what that session's inbox accepts, instead of reporting them sent while they were dropped</p>
|
||
<p>• Aligned the session title chip on the prompt border with the footer's right edge</p>
|
||
<p>• Right-aligned footer items (goal indicator, session state, background agent status) and truncated notices now share a consistent right margin with the rest of the prompt area</p>
|
||
<p>• [VSCode] Added screen reader support for the transcript: live announcements for replies, permission requests, errors, and status changes, plus per-turn heading navigation</p></content>
|
||
</entry>
|
||
<entry>
|
||
<id>https://github.com/anthropics/claude-code/releases/tag/v2.1.235</id>
|
||
<title>Claude Code v2.1.235</title>
|
||
<link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.235"/>
|
||
<updated>2026-08-18T20:38:47Z</updated>
|
||
<content type="html"><p>• Added an optional spellcheck setting that underlines misspelled words in the prompt input as you type, using your installed aspell, hunspell, or ispell</p>
|
||
<p>• Fixed whole-prompt-cache invalidation when a language server disconnected or reconnected mid-session</p>
|
||
<p>• Fixed nested markdown list items misaligning at depth 3+ and added a hanging indent to wrapped list items in the terminal UI</p>
|
||
<p>• Fixed prompt input highlights (slash commands, keywords, mentions) appearing shifted by one or more characters in some multi-line prompts</p>
|
||
<p>• Fixed Shift+Tab inside the permission prompt's comment field approving the edit and granting session-wide edit permission instead of closing the field</p>
|
||
<p>• Fixed the Agent tool advertising a general-purpose default in sessions where that agent is unavailable: an omitted subagent_type there now gets a clear error listing the available agents</p>
|
||
<p>• Fixed notebook cell delete/replace approval dialogs silently omitting the existing cell content when the notebook or cell could not be read; the dialog now says why</p>
|
||
<p>• Fixed slash commands run while Claude is responding showing HTML entities instead of the actual characters</p>
|
||
<p>• Fixed the prompt footer not showing the "Update installed" restart notice after a background auto-update</p>
|
||
<p>• Fixed the expanded task list (ctrl+t) always starting collapsed when resuming or relaunching into a session that still has open tasks</p>
|
||
<p>• Improved memory and CPU usage while cloud sessions such as /ultrareview or /autofix-pr run in the background — their event streams are no longer re-scanned and re-rendered on every update</p>
|
||
<p>• Improved permission dialogs: display text and "don't ask again" options now always match what a grant would cover, and "don't ask again" is withheld when contents cannot be fully displayed</p>
|
||
<p>• Improved the embedded grep in native macOS/Linux builds: pathological patterns now fail fast instead of exhausting memory, and -m N with -A/-C prints correct context</p>
|
||
<p>• Improved the context-limit error to say when auto-compact is off and point to /config to re-enable it</p>
|
||
<p>• Vim mode: NORMAL mode and cursor position are now preserved when toggling the detailed transcript (ctrl+o) or closing a panel</p>
|
||
<p>• Dialogs: arrow keys and Enter pressed in quick succession now select the option you navigated to instead of the previously highlighted one</p>
|
||
<p>• SendMessage now refuses messages too large for cross-session delivery up front instead of silently dropping them</p>
|
||
<p>• Remote Control: claude rc now applies the same enterprise-gateway availability check as interactive startup</p>
|
||
<p>• [VSCode] Fixed focus jumping between open Claude tabs on its own when a window with several Claude panels is restored or reloaded</p></content>
|
||
</entry>
|
||
</feed>
|