feed.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>2026-06-26T21:29:36Z</updated>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.195</id>
    <title>Claude Code v2.1.195</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.195"/>
    <updated>2026-06-26T21:29:36Z</updated>
    <content type="html">&lt;p&gt;• Added CLAUDE_CODE_DISABLE_MOUSE_CLICKS to disable mouse click/drag/hover in fullscreen mode while keeping wheel scroll&lt;/p&gt;
&lt;p&gt;• Fixed hook matchers with hyphenated identifiers (e.g. code-reviewer, mcp__brave-search) accidentally substring-matching — they now exact-match. Use mcp__brave-search__.* to match all tools from a hyphenated MCP server.&lt;/p&gt;
&lt;p&gt;• Fixed voice dictation on macOS capturing silence in long-running sessions after the default input device changes&lt;/p&gt;
&lt;p&gt;• Fixed voice dictation auto-submit never firing for languages written without spaces (Japanese, Chinese, Thai)&lt;/p&gt;
&lt;p&gt;• Fixed external plugins enabled only by project .claude/settings.json not requiring explicit install consent on every loader path&lt;/p&gt;
&lt;p&gt;• Fixed /plugin Enable/Disable not working when a plugin's plugin.json name differs from its marketplace entry name&lt;/p&gt;
&lt;p&gt;• Fixed background jobs disappearing from claude agents or losing data when written by a newer Claude Code version&lt;/p&gt;
&lt;p&gt;• Fixed reopening a crashed background task showing a blank screen for up to 5 seconds instead of its restart&lt;/p&gt;
&lt;p&gt;• Fixed background agent daemons running unreachable when the control socket fails to start, blocking restarts&lt;/p&gt;
&lt;p&gt;• Improved voice mode on Linux: now distinguishes "no microphone" from "SoX not installed" when SoX is present but no audio capture device exists&lt;/p&gt;
&lt;p&gt;• Improved claude agents completed list to fill available vertical space; on short terminals the header compacts so live sessions stay visible&lt;/p&gt;
&lt;p&gt;• Improved Remote session startup with a provisioning checklist while the container starts&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.193</id>
    <title>Claude Code v2.1.193</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.193"/>
    <updated>2026-06-25T21:45:51Z</updated>
    <content type="html">&lt;p&gt;• Added autoMode.classifyAllShell setting to route all Bash/PowerShell commands through the auto-mode classifier instead of only arbitrary-code-execution patterns&lt;/p&gt;
&lt;p&gt;• Added auto-mode denial reasons to the transcript, the denial toast, and /permissions recent denials&lt;/p&gt;
&lt;p&gt;• Added claude_code.assistant_response OpenTelemetry log event containing the model's response text. Redacted unless OTEL_LOG_ASSISTANT_RESPONSES=1; when that var is unset it follows OTEL_LOG_USER_PROMPTS, so deployments that already log prompt content will start receiving response content on upgrade — set OTEL_LOG_ASSISTANT_RESPONSES=0 to keep prompts-only.&lt;/p&gt;
&lt;p&gt;• Added live file path autocomplete to bash mode (!)&lt;/p&gt;
&lt;p&gt;• Added a startup notice when MCP servers need authentication, pointing at /mcp&lt;/p&gt;
&lt;p&gt;• Added automatic memory-pressure reaping for idle background shell commands (disable with CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP=1)&lt;/p&gt;
&lt;p&gt;• Fixed /model and other client-data-gated UI showing stale/empty state immediately after /login&lt;/p&gt;
&lt;p&gt;• Fixed backgrounding (←←) spuriously cancelling with "N background tasks would be abandoned" when all running tasks carry over to the new session&lt;/p&gt;
&lt;p&gt;• Fixed pinned background agents being re-prompted to "Continue from where you left off" after every auto-update&lt;/p&gt;
&lt;p&gt;• Fixed backgrounding the main turn spawning a phantom "general-purpose (resumed)" subagent that re-ran the main conversation&lt;/p&gt;
&lt;p&gt;• Fixed agent panel hiding sibling agents when viewing a subagent&lt;/p&gt;
&lt;p&gt;• Improved background agents: the launch result no longer instructs Claude to "end your response" — it keeps working on other tasks while the agent runs&lt;/p&gt;
&lt;p&gt;• Improved MCP headersHelper auth: the helper now re-runs and reconnects automatically when a tool call returns 401/403&lt;/p&gt;
&lt;p&gt;• Improved plugin auto-rename: marketplace renames maps are now followed automatically, updating your settings to the new name&lt;/p&gt;
&lt;p&gt;• Improved /add-dir message when the directory is already a working directory&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.191</id>
    <title>Claude Code v2.1.191</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.191"/>
    <updated>2026-06-24T21:58:06Z</updated>
    <content type="html">&lt;p&gt;• Added /rewind support for resuming a conversation from before /clear was run&lt;/p&gt;
&lt;p&gt;• Fixed scroll position jumping to the bottom while reading earlier output during a streaming response&lt;/p&gt;
&lt;p&gt;• Fixed background agents resurrecting after being stopped — stopping an agent from the tasks panel is now permanent&lt;/p&gt;
&lt;p&gt;• Fixed /voice showing a generic "not available" message when disabled by an organization's policy — it now explains the restriction&lt;/p&gt;
&lt;p&gt;• Fixed /login URL opening truncated in Windows Terminal when it wraps across lines&lt;/p&gt;
&lt;p&gt;• Fixed Cmd+click on links in fullscreen mode for Ghostty over ssh/tmux&lt;/p&gt;
&lt;p&gt;• Fixed claude agents sending builtin slash commands like /usage to background sessions as prompt text instead of showing a hint&lt;/p&gt;
&lt;p&gt;• Fixed claude agents job rows showing full filesystem paths for pasted images instead of the [Image #N] placeholder&lt;/p&gt;
&lt;p&gt;• Fixed hooks with comma-separated matchers (e.g. "Bash,PowerShell") silently never firing&lt;/p&gt;
&lt;p&gt;• Fixed /permissions Recently-denied tab: approving a denial now persists on close instead of being silently discarded&lt;/p&gt;
&lt;p&gt;• Fixed the agent panel jumping by one row when scrolling the roster past the overflow cap&lt;/p&gt;
&lt;p&gt;• Fixed the welcome splash art overflowing the default 80×24 macOS Terminal window&lt;/p&gt;
&lt;p&gt;• Fixed managed settings: forceRemoteSettingsRefresh now takes effect when set via MDM or file policy, and the fetch sends Cache-Control: no-cache to prevent proxies from serving stale responses&lt;/p&gt;
&lt;p&gt;• Improved sandbox network permission dialog: hosts you allow with "Yes" are now remembered for the rest of the session instead of re-prompting on every connection&lt;/p&gt;
&lt;p&gt;• Improved MCP server reliability: capability discovery (tools/list, prompts/list, resources/list) now retries transient network errors with short backoff&lt;/p&gt;
&lt;p&gt;• Improved MCP OAuth: discovery and token requests now retry once after transient network errors, and headless environments skip the browser popup and go straight to the paste-the-URL prompt&lt;/p&gt;
&lt;p&gt;• Improved MCP error messages: HTTP 404 errors now show the URL and point to your MCP config&lt;/p&gt;
&lt;p&gt;• Improved vim mode prompt-history search (NORMAL /) to hint how to reach slash commands&lt;/p&gt;
&lt;p&gt;• Reduced CPU usage during streaming responses by ~37% by coalescing text updates to 100ms&lt;/p&gt;
&lt;p&gt;• Reduced long-session memory growth from terminal output cache&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.190</id>
    <title>Claude Code v2.1.190</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.190"/>
    <updated>2026-06-24T15:53:48Z</updated>
    <content type="html">&lt;p&gt;• Bug fixes and reliability improvements&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.187</id>
    <title>Claude Code v2.1.187</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.187"/>
    <updated>2026-06-23T21:03:40Z</updated>
    <content type="html">&lt;p&gt;• Added sandbox.credentials setting to block sandboxed commands from reading credential files and secret environment variables&lt;/p&gt;
&lt;p&gt;• Added org-configured model restrictions to the model picker, --model, /model, and ANTHROPIC_MODEL, with a "restricted by your organization's settings" message when a restricted model is selected&lt;/p&gt;
&lt;p&gt;• Added mouse click support to select menus (permission prompts, /model, /config, etc.) in fullscreen mode&lt;/p&gt;
&lt;p&gt;• Fixed --resume failing with "No conversation found" when the original -p run produced no model turns&lt;/p&gt;
&lt;p&gt;• Fixed --json-schema and workflow agent({schema}) structured output: the model can no longer re-call StructuredOutput indefinitely after a successful call, and follow-up turns now reliably return structured output&lt;/p&gt;
&lt;p&gt;• Fixed remote MCP tool calls that hang with no response for 5 minutes — they now abort with an error instead of blocking indefinitely (override with CLAUDE_CODE_MCP_TOOL_IDLE_TIMEOUT)&lt;/p&gt;
&lt;p&gt;• Fixed Claude Code Remote sessions taking ~2.7s longer to start after the agent proxy CA system-trust install was added&lt;/p&gt;
&lt;p&gt;• Fixed pasted Korean/CJK text turning into mojibake in terminals that deliver paste as per-byte extended-key events&lt;/p&gt;
&lt;p&gt;• Fixed /update over Remote Control hanging when a startup trust dialog would have shown&lt;/p&gt;
&lt;p&gt;• Fixed background jobs in the agents view getting stuck in "working" indefinitely when the agent ended a turn without producing structured output&lt;/p&gt;
&lt;p&gt;• Fixed channel connections dropping after navigating to the agents view and back, and after /bg, /tui, or /update&lt;/p&gt;
&lt;p&gt;• Fixed agent stop notifications not correctly attributing who stopped the agent, and improved wording ("finished"/"stopped" instead of "came to rest")&lt;/p&gt;
&lt;p&gt;• Fixed subagent depth tracking: resumed subagents now restore their original spawn depth, and forked subagents now count toward the depth cap&lt;/p&gt;
&lt;p&gt;• Fixed leaked agent worktree registrations: locked .git/worktrees/ entries from killed agents are now cleaned up automatically&lt;/p&gt;
&lt;p&gt;• Fixed Cmd+click not opening URLs in fullscreen mode in Ghostty on macOS&lt;/p&gt;
&lt;p&gt;• Fixed claude --help not listing the --bg/--background flag&lt;/p&gt;
&lt;p&gt;• Fixed Esc, Ctrl-C, and Ctrl-D not working while /share is uploading&lt;/p&gt;
&lt;p&gt;• Improved /install-github-app: GitHub Actions workflow setup is now optional — you can install just the GitHub App and skip the workflow/secret steps&lt;/p&gt;
&lt;p&gt;• Improved /btw with ←/→ arrow navigation to step through earlier answers&lt;/p&gt;
&lt;p&gt;• Improved /plugin to surface plugins you haven't used recently so you can clean them up&lt;/p&gt;
&lt;p&gt;• [VSCode] Fixed extension becoming unresponsive when resuming a large session&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.186</id>
    <title>Claude Code v2.1.186</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.186"/>
    <updated>2026-06-22T20:37:26Z</updated>
    <content type="html">&lt;p&gt;• Added claude mcp login &amp;lt;name&amp;gt; and claude mcp logout &amp;lt;name&amp;gt; to authenticate MCP servers from the CLI without opening the interactive /mcp menu, with --no-browser stdin redirect support for completing over SSH&lt;/p&gt;
&lt;p&gt;• Added status filtering (press f) to the /workflows agent detail view&lt;/p&gt;
&lt;p&gt;• Added a "Skills" section to the /plugin Installed tab&lt;/p&gt;
&lt;p&gt;• Added teammateMode: "iterm2" setting with a warning when auto mode cannot find the it2 CLI&lt;/p&gt;
&lt;p&gt;• Added "Claude Platform on AWS - refresh credentials" option to /login when awsAuthRefresh is configured&lt;/p&gt;
&lt;p&gt;• ! bash commands now trigger Claude to respond to the output automatically; set "respondToBashCommands": false in settings.json to keep the previous context-only behavior&lt;/p&gt;
&lt;p&gt;• Fixed streaming requests failing with "Content block not found" or JSON parse errors after the machine wakes from sleep&lt;/p&gt;
&lt;p&gt;• Fixed subagent transcript scroll position bleeding into the main transcript on exit&lt;/p&gt;
&lt;p&gt;• Fixed background task previews flashing raw tool names before the agent's plan loaded&lt;/p&gt;
&lt;p&gt;• Fixed Chrome tab-group isolation not applying when the in-product permissions gate is off for concurrent CLI sessions&lt;/p&gt;
&lt;p&gt;• Fixed background session recaps being duplicated; the agent's own end-of-turn summary now shows as the recap line&lt;/p&gt;
&lt;p&gt;• Fixed opening a background session from claude agents leaving the previous screen painted behind it&lt;/p&gt;
&lt;p&gt;• Fixed Agent(type) deny rules and Agent(x,y) allowed-types restrictions not being enforced for named subagent spawns&lt;/p&gt;
&lt;p&gt;• Fixed Esc and Ctrl+C not responding while background agents are still running after the main turn ends&lt;/p&gt;
&lt;p&gt;• Fixed misaligned option numbers in permission prompts when the option text overflows&lt;/p&gt;
&lt;p&gt;• Fixed pressing x on a finished subagent in the agent panel not dismissing it&lt;/p&gt;
&lt;p&gt;• Fixed a misleading "MCP server disconnected" notice for intentionally retired tools when resuming older sessions&lt;/p&gt;
&lt;p&gt;• Fixed /plugin Installed showing a "more above" indicator when already scrolled to the top&lt;/p&gt;
&lt;p&gt;• Fixed ~~strikethrough~~ showing literal tildes in assistant messages instead of rendering as strikethrough&lt;/p&gt;
&lt;p&gt;• Fixed --tools allowing feature-gated tools to slip through before flags loaded on a cold first launch&lt;/p&gt;
&lt;p&gt;• Fixed background job status in claude agents showing a stale "needs input" message after replying&lt;/p&gt;
&lt;p&gt;• Fixed a dark-theme flash when opening a background session from claude agents on a light terminal&lt;/p&gt;
&lt;p&gt;• Fixed mouse-selected text staying highlighted after deleting it in claude agents&lt;/p&gt;
&lt;p&gt;• Fixed session cost not showing for usage-based Enterprise and Team subscribers&lt;/p&gt;
&lt;p&gt;• Fixed agent teams: teammates spawned via tmux/pane backends now inherit the leader's --effort level&lt;/p&gt;
&lt;p&gt;• Fixed Workflow agent({schema}) subagents looping forever on repeated schema validation failures instead of aborting after 5 attempts&lt;/p&gt;
&lt;p&gt;• Improved claude mcp get and claude mcp remove to suggest the closest configured server name on a typo and truncate long server lists&lt;/p&gt;
&lt;p&gt;• Improved memory: the agent is now reminded to compact its MEMORY.md index when nearing the size limit&lt;/p&gt;
&lt;p&gt;• Improved skill frontmatter: display-name, default-enabled, fallback, and metadata.* keys now accept kebab-case, snake_case, and camelCase&lt;/p&gt;
&lt;p&gt;• Improved malformed SKILL.md YAML frontmatter handling: loads the skill body with empty metadata instead of failing silently&lt;/p&gt;
&lt;p&gt;• Changed CLAUDE_CODE_MAX_RETRIES to cap at 15; for unattended sessions, use CLAUDE_CODE_RETRY_WATCHDOG instead&lt;/p&gt;
&lt;p&gt;• Changed background subagents to surface permission prompts in the main session instead of auto-denying; the dialog shows which agent is asking, and Esc denies just that tool&lt;/p&gt;
&lt;p&gt;• Changed /review &amp;lt;pr&amp;gt; to use the same review engine as /code-review medium&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.185</id>
    <title>Claude Code v2.1.185</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.185"/>
    <updated>2026-06-20T20:59:12Z</updated>
    <content type="html">&lt;p&gt;• The stream-stall hint now reads "Waiting for API response · will retry in …" instead of "No response from API · Retrying in …", and triggers after 20s of silence instead of 10s&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.183</id>
    <title>Claude Code v2.1.183</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.183"/>
    <updated>2026-06-19T01:20:44Z</updated>
    <content type="html">&lt;p&gt;• Improved auto mode safety: destructive git commands (git reset --hard, git checkout -- ., git clean -fd, git stash drop) are now blocked when you didn't ask to discard local work, git commit --amend is blocked when the commit wasn't made by the agent this session, and terraform destroy/pulumi destroy/cdk destroy are blocked unless you asked for the specific stack&lt;/p&gt;
&lt;p&gt;• Added a warning when the requested model is deprecated or automatically updated to a newer model, shown on stderr in print mode (-p) and now also covering models set in agent frontmatter&lt;/p&gt;
&lt;p&gt;• Added attribution.sessionUrl setting to omit the claude.ai session link from commits and PRs in web and Remote Control sessions&lt;/p&gt;
&lt;p&gt;• Added /config --help to list all available shorthand keys for /config key=value&lt;/p&gt;
&lt;p&gt;• Changed /config toggle behavior: Enter and Space both change the selected setting, and Esc now saves and closes instead of reverting&lt;/p&gt;
&lt;p&gt;• Removed the startup "setup issues" line under the logo — run /doctor to see configuration issues or use --debug&lt;/p&gt;
&lt;p&gt;• Fixed thinking.disabled.display: Extra inputs are not permitted 400 errors on subagent spawns and session-title generation for affected configurations&lt;/p&gt;
&lt;p&gt;• Fixed WebSearch returning empty results in subagents&lt;/p&gt;
&lt;p&gt;• Fixed the terminal cursor being stranded above the prompt after navigating history in vim mode with the native cursor enabled&lt;/p&gt;
&lt;p&gt;• Fixed fullscreen TUI corruption (statusline mid-screen, duplicated spinner rows, merged text) in Windows Terminal under heavy nested-subagent load&lt;/p&gt;
&lt;p&gt;• Fixed turns silently completing with no visible output when the model returned only a thinking block; Claude now re-prompts once&lt;/p&gt;
&lt;p&gt;• Fixed user-level skills appearing multiple times in slash-command autocomplete when multiple plugins are enabled&lt;/p&gt;
&lt;p&gt;• Fixed MCP servers requiring authentication exposing auth-stub tools to the model in headless/SDK mode&lt;/p&gt;
&lt;p&gt;• Fixed tmux teammate panes failing to launch when the shell has slow rc-file initialization, and keystrokes typed during agent spawn leaking into the new tmux pane instead of the leader prompt&lt;/p&gt;
&lt;p&gt;• Fixed background tasks started by a teammate being killed when the teammate finishes a turn&lt;/p&gt;
&lt;p&gt;• Fixed scheduled task and webhook trigger deliveries being treated as keyboard input; they now classify as task notifications and can no longer approve a pending action or set the session title in auto mode&lt;/p&gt;
&lt;p&gt;• Fixed focus mode showing "Ran N PostToolUse hooks" timing lines under each response&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.181</id>
    <title>Claude Code v2.1.181</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.181"/>
    <updated>2026-06-17T22:07:34Z</updated>
    <content type="html">&lt;p&gt;• Added /config key=value syntax to set any setting from the prompt (e.g. /config thinking=false) — works in interactive, -p, and Remote Control&lt;/p&gt;
&lt;p&gt;• Added sandbox.allowAppleEvents opt-in setting that lets sandboxed commands send Apple Events on macOS&lt;/p&gt;
&lt;p&gt;• Added CLAUDE_CLIENT_PRESENCE_FILE environment variable: point it at a marker file to suppress mobile push notifications while you're at the machine&lt;/p&gt;
&lt;p&gt;• Upgraded the bundled Bun runtime to 1.4&lt;/p&gt;
&lt;p&gt;• Improved streaming of long paragraphs: text now appears line-by-line instead of waiting for the first line break&lt;/p&gt;
&lt;p&gt;• Improved auto-retry: API connection drops mid-thinking now automatically retry instead of showing "Connection closed while thinking"&lt;/p&gt;
&lt;p&gt;• Improved the subagent panel: idle subagents auto-hide after 30s, the list caps at 5 rows with scroll hints, and keyboard hints now show in the footer&lt;/p&gt;
&lt;p&gt;• Improved the MCP OAuth browser page to match Claude Code's visual style and auto-close on success&lt;/p&gt;
&lt;p&gt;• Changed fullscreen mode URL opening to require Cmd+click (macOS) / Ctrl+click, matching native terminal behavior&lt;/p&gt;
&lt;p&gt;• Changed the Improved N memories line to no longer list individual files outside verbose mode&lt;/p&gt;
&lt;p&gt;• Fixed prompt caching not reading on custom ANTHROPIC_BASE_URL and on Foundry due to a per-request attestation token changing every turn&lt;/p&gt;
&lt;p&gt;• Fixed Write/Edit producing 0-byte or truncated files on network drives and cloud-synced folders&lt;/p&gt;
&lt;p&gt;• Fixed open, osascript, and browser-based auth flows failing with error -600 on macOS by adding the Apple Events entitlement&lt;/p&gt;
&lt;p&gt;• Fixed a startup regression (~120ms per launch in fresh environments, introduced in 2.1.169): the first prompt no longer waits for the managed-settings fetch when no MCP servers are configured&lt;/p&gt;
&lt;p&gt;• Fixed startup blocking with a blank terminal for up to 15 seconds when the account settings fetch is slow on a degraded network&lt;/p&gt;
&lt;p&gt;• Fixed startup crash (TypeError: Cannot read properties of null) when .claude.json contains corrupted null project entries&lt;/p&gt;
&lt;p&gt;• Fixed macOS TUI freezing at session start (Ctrl+C unresponsive) when Spotlight is busy reindexing&lt;/p&gt;
&lt;p&gt;• Fixed long-running idle sessions losing their history when another Claude Code process ran the 30-day transcript cleanup&lt;/p&gt;
&lt;p&gt;• Fixed foreground subagents spawning unbounded nested chains; they now respect the same 5-level depth limit as background subagents&lt;/p&gt;
&lt;p&gt;• Fixed /recap and conversation forks using the previous model immediately after a model switch&lt;/p&gt;
&lt;p&gt;• Fixed subagent "Thinking" duration showing the parent agent's elapsed time instead of the subagent's own&lt;/p&gt;
&lt;p&gt;• Fixed subagents blocked on a nested agent showing a ticking elapsed time instead of "waiting" in the agent panel&lt;/p&gt;
&lt;p&gt;• Fixed the API retry indicator ("Retrying in 0s · attempt N/10") staying on screen after the retry succeeded&lt;/p&gt;
&lt;p&gt;• Fixed AWS awsCredentialExport credentials with a short remaining lifetime causing credential refreshes every minute, and now accepts the JSON shape from aws configure export-credentials&lt;/p&gt;
&lt;p&gt;• Fixed claude mcp get/list showing ✓ Connected when tools/list fails; they now show ! Connected · tools fetch failed with the error detail&lt;/p&gt;
&lt;p&gt;• Fixed /remote-control leaving a stale "connecting…" line; it now confirms in the transcript once connected&lt;/p&gt;
&lt;p&gt;• Fixed ExitWorktree refusing to remove a clean worktree with "Could not verify worktree state" when bare git cannot be resolved on Windows&lt;/p&gt;
&lt;p&gt;• Fixed settings changes (such as /effort or /model) failing with ENOENT when ~/.claude/settings.json is a relative symlink under a symlinked ~/.claude&lt;/p&gt;
&lt;p&gt;• Fixed IDE selection line numbers in context reminders being off by one (IntelliJ and VS Code)&lt;/p&gt;
&lt;p&gt;• Fixed Ctrl+C in fullscreen after a native terminal selection (modifier+drag) overwriting the clipboard with the app's prior selection&lt;/p&gt;
&lt;p&gt;• Fixed Ctrl+V showing "No image found in clipboard" instead of pasting when the clipboard contains text&lt;/p&gt;
&lt;p&gt;• Fixed agent creation failing with "EEXIST: file already exists" when the agents directory already exists (Windows/OneDrive)&lt;/p&gt;
&lt;p&gt;• Fixed AskUserQuestion preview content being cut off at the dialog edge instead of word-wrapping&lt;/p&gt;
&lt;p&gt;• Fixed AskUserQuestion multi-select questions silently dropping a typed "Other" free-text answer when submitting&lt;/p&gt;
&lt;p&gt;• Fixed /stats "Most active day" and daily token chart dates showing one day early in UTC-negative timezones&lt;/p&gt;
&lt;p&gt;• Fixed /copy and copy-on-select on Linux not detecting a clipboard utility installed after Claude Code started&lt;/p&gt;
&lt;p&gt;• Fixed tab-indented code rendering with incorrect indentation in the Write (create-file) preview&lt;/p&gt;
&lt;p&gt;• Fixed user prompts queued mid-turn not showing a full-width background highlight in the transcript&lt;/p&gt;
&lt;p&gt;• Fixed the activity spinner's pulse dwelling on the wrong glyph size in Ghostty&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.179</id>
    <title>Claude Code v2.1.179</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.179"/>
    <updated>2026-06-16T20:22:06Z</updated>
    <content type="html">&lt;p&gt;• Fixed mid-stream connection drops: partial responses are now preserved instead of showing a raw error, and the spinner no longer gets stuck at "running tool"&lt;/p&gt;
&lt;p&gt;• Fixed mouse-wheel scrolling in WSL2 under Windows Terminal and VS Code (regression in 2.1.172)&lt;/p&gt;
&lt;p&gt;• Fixed a sandbox denyRead/allowRead glob over a large directory tree making the Bash tool description enormous and the session unusable on Linux&lt;/p&gt;
&lt;p&gt;• Fixed the feedback survey capturing a single-digit reply as a session rating immediately after a turn completes&lt;/p&gt;
&lt;p&gt;• Fixed the welcome screen stacking multiple promotional banners — at most one promo now shows per session&lt;/p&gt;
&lt;p&gt;• Fixed Ctrl+O not showing the subagent's transcript when viewing a subagent&lt;/p&gt;
&lt;p&gt;• Fixed clicking the prompt input not returning focus from the subagent/footer panel&lt;/p&gt;
&lt;p&gt;• Fixed remote session background tasks appearing stuck as "still running" between turns&lt;/p&gt;
&lt;p&gt;• Improved plugin loading performance in remote sessions&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.178</id>
    <title>Claude Code v2.1.178</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.178"/>
    <updated>2026-06-15T21:35:48Z</updated>
    <content type="html">&lt;p&gt;• Agent teams: removed the TeamCreate and TeamDelete tools. With CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 set, every session now has one implicit team — spawn teammates directly with the Agent tool's name parameter, no setup step needed. The team_name parameter on the Agent tool is still accepted but ignored.&lt;/p&gt;
&lt;p&gt;• Added Tool(param:value) syntax for permission rules to match a tool's input parameters (with * wildcard), e.g. Agent(model:opus) to block Opus subagents&lt;/p&gt;
&lt;p&gt;• Skills in nested .claude/skills directories now load when working on files there; on a name clash, the nested skill appears as &amp;lt;dir&amp;gt;:&amp;lt;name&amp;gt; so both stay available&lt;/p&gt;
&lt;p&gt;• Nested .claude/ directories: the agent, workflow, and output-style closest to the working directory now wins when names collide; project-scope workflow saves now target the closest existing .claude/workflows/&lt;/p&gt;
&lt;p&gt;• Improved auto mode: subagent spawns are now evaluated by the classifier before launch, closing a gap where a subagent could request a blocked action without review&lt;/p&gt;
&lt;p&gt;• Improved /doctor with consistent flat tree layout across all sections, clearer section status icons, and highlighted command names&lt;/p&gt;
&lt;p&gt;• Improved the skill listing truncation warning to show how many skill descriptions are affected&lt;/p&gt;
&lt;p&gt;• Changed the workflow prompt keyword to use a purple shimmer highlight and trigger only on explicit phrases like "run a workflow" or "workflow:", not on any mention of the word&lt;/p&gt;
&lt;p&gt;• Improved Remote Control error messages: connection failures now show a persistent red "/rc failed" indicator in the footer, and the "not yet enabled" error now explains whether it's a gate, a check failure, stale entitlement, or org policy&lt;/p&gt;
&lt;p&gt;• /bug now requires a description before submitting, and no longer uses model-refusal text as the GitHub issue title&lt;/p&gt;
&lt;p&gt;• Fixed a crash (out-of-memory) when the CLI inherits a stale websocket/OAuth file-descriptor environment variable from a parent process&lt;/p&gt;
&lt;p&gt;• Fixed Claude in Chrome silently failing to connect when the OAuth token belongs to a different account than the Claude Code login&lt;/p&gt;
&lt;p&gt;• Fixed nested .claude/skills skills with directory-qualified names being blocked by permission prompts in non-interactive runs&lt;/p&gt;
&lt;p&gt;• Fixed several subagent issues: viewing a subagent's transcript now shows tool results and live progress, messages sent while it finishes its turn are no longer dropped, and backgrounding a running subagent (ctrl+b) no longer restarts it from scratch&lt;/p&gt;
&lt;p&gt;• Fixed claude agents workers failing with 401 Invalid bearer token when the daemon was started from a shell with a custom API gateway via ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN&lt;/p&gt;
&lt;p&gt;• Fixed compaction not honoring --fallback-model: compaction now falls back to the configured fallback model chain on overload or model-availability errors&lt;/p&gt;
&lt;p&gt;• Fixed model requests continuing to fail with auth errors after credentials were refreshed outside the session, due to a stale cached request configuration&lt;/p&gt;
&lt;p&gt;• Fixed background sessions created with /bg or ←← after a turn finished showing "Working" forever in the agents list&lt;/p&gt;
&lt;p&gt;• Fixed Linux sandbox failing to start when .claude/skills or .claude/hooks is a symlink&lt;/p&gt;
&lt;p&gt;• Fixed CLAUDE_CODE_PLUGIN_KEEP_MARKETPLACE_ON_FAILURE=1 preventing fresh marketplace installs from cloning&lt;/p&gt;
&lt;p&gt;• Fixed MCP server-level specs (mcp__server, mcp__server__*, mcp__*) in subagent disallowedTools being silently ignored&lt;/p&gt;
&lt;p&gt;• Fixed vim mode undo: u now steps through NORMAL/VISUAL-mode commands one at a time instead of merging commands in quick succession into a single undo step&lt;/p&gt;
&lt;p&gt;• Fixed statusline links with custom URI schemes (e.g. vscode://) not opening when clicked in claude agents&lt;/p&gt;
&lt;p&gt;• [VSCode] Fixed pressing Esc to dismiss a CJK IME candidate window canceling the running Claude task&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.176</id>
    <title>Claude Code v2.1.176</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.176"/>
    <updated>2026-06-12T21:53:21Z</updated>
    <content type="html">&lt;p&gt;• Session titles are now generated in the language of your conversation (set the language setting to pin a specific language)&lt;/p&gt;
&lt;p&gt;• Added footerLinksRegexes setting for regex-matched link badges in the footer row, configurable via user or managed settings&lt;/p&gt;
&lt;p&gt;• Improved Bedrock credential caching: credentials from awsCredentialExport are now cached until their Expiration instead of a fixed 1 hour&lt;/p&gt;
&lt;p&gt;• Fixed availableModels enforcement: alias model picks can no longer be redirected to a blocked model via ANTHROPIC_DEFAULT_*_MODEL environment variables, and /fast now refuses to toggle when it would switch to a model outside the allowlist&lt;/p&gt;
&lt;p&gt;• Fixed auto mode failing on Fable 5 for organizations without Opus 4.8 enabled — the classifier now falls back to the best available Opus model&lt;/p&gt;
&lt;p&gt;• Fixed hook if conditions for Read/Edit/Write tool paths: documented patterns like Edit(src/), Read(~/.ssh/), and Read(.env) now match correctly&lt;/p&gt;
&lt;p&gt;• Fixed Linux sandbox failing to start when .claude/settings.json is a symlink with an absolute target&lt;/p&gt;
&lt;p&gt;• Fixed /copy and mouse-selection copy not reaching the system clipboard inside tmux over SSH, and tmux paste buffer not loading on versions older than 3.2&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control connecting from web/mobile silently switching the session's model&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control disconnect notifications showing a bare numeric code instead of a human-readable reason, and connection failures adding a duplicate line to the conversation transcript&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control sessions not disconnecting when you sign in to a different account&lt;/p&gt;
&lt;p&gt;• Fixed /cd and worktree moves leaving the session reporting the previous directory's git branch&lt;/p&gt;
&lt;p&gt;• Fixed claude agents: pressing back in one window no longer detaches other windows attached to the same session&lt;/p&gt;
&lt;p&gt;• Fixed backgrounded sessions showing "Working" forever when /bg mid-turn had nothing left to continue&lt;/p&gt;
&lt;p&gt;• Fixed background agent search by PR URL: PRs opened during scheduled wakeups or while a job was blocked now appear in claude agents search&lt;/p&gt;
&lt;p&gt;• Fixed the agents view input showing no text cursor on Windows&lt;/p&gt;
&lt;p&gt;• Fixed claude --bg -cn &amp;lt;name&amp;gt; not seeding the session name&lt;/p&gt;
&lt;p&gt;• Fixed background sessions to neutralize Windows network paths in persisted state before respawn&lt;/p&gt;
&lt;p&gt;• Fixed background-session respawn rejecting malformed resume IDs from corrupted state files&lt;/p&gt;
&lt;p&gt;• Fixed the Windows background-service daemon not starting when ~/.claude/daemon has the ReadOnly attribute set&lt;/p&gt;
&lt;p&gt;• Fixed cloud sessions failing with "Could not resolve authentication method" when idle for too long before being claimed&lt;/p&gt;
&lt;p&gt;• Background sessions now show clearer guidance when a window left open across an auto-update can't submit a reply, and claude daemon status explains version-skew behavior&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.175</id>
    <title>Claude Code v2.1.175</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.175"/>
    <updated>2026-06-12T04:23:45Z</updated>
    <content type="html">&lt;p&gt;• Added enforceAvailableModels managed setting — when enabled, the availableModels allowlist also constrains the Default model (a Default that would resolve to a disallowed model now falls back to the first allowed model), and user or project settings can no longer widen a managed availableModels list&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.174</id>
    <title>Claude Code v2.1.174</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.174"/>
    <updated>2026-06-12T01:16:30Z</updated>
    <content type="html">&lt;p&gt;• Added wheelScrollAccelerationEnabled setting to disable mouse-wheel scroll acceleration in fullscreen mode&lt;/p&gt;
&lt;p&gt;• Fixed the /model picker hiding the model family that Default resolves to — Opus now appears as its own row on Max/Team Premium/Enterprise plans, Sonnet on Pro/Team plans, and Opus on pay-as-you-go API accounts&lt;/p&gt;
&lt;p&gt;• Fixed /model picker showing a hardcoded Sonnet version label when ANTHROPIC_DEFAULT_SONNET_MODEL pins a different Sonnet&lt;/p&gt;
&lt;p&gt;• Fixed the "Fable 5 is now consuming usage credits" banner incorrectly showing for enterprise accounts with usage-based billing&lt;/p&gt;
&lt;p&gt;• Fixed Bedrock GovCloud regions (us-gov-*) deriving the wrong inference profile prefix (global instead of us-gov), causing 400 errors on derived model IDs&lt;/p&gt;
&lt;p&gt;• Fixed background sessions inheriting another session's ANTHROPIC_* provider env (gateway URL, custom headers, /model aliases) from the shell that started the background daemon&lt;/p&gt;
&lt;p&gt;• Fixed a 1-2 second pause when exiting Claude Code shortly after a shell command was interrupted or killed on macOS and Linux&lt;/p&gt;
&lt;p&gt;• Fixed git commit co-author attribution showing an incorrect model name for some models&lt;/p&gt;
&lt;p&gt;• Fixed the /advisor dialog pre-selecting a saved advisor model that is blocked by the availableModels allowlist&lt;/p&gt;
&lt;p&gt;• Fixed skill hot-reload re-sending the entire skill listing when a single skill changed; only changed skills are now re-announced&lt;/p&gt;
&lt;p&gt;• Fixed Workflow tool agent() subagents missing per-agent attribution headers&lt;/p&gt;
&lt;p&gt;• [VSCode] Added usage attribution to the Account &amp;amp; usage dialog (/usage) showing cache misses, long context, subagents, and per-skill/agent/plugin/MCP breakdowns over the last 24h or 7d&lt;/p&gt;
&lt;p&gt;• Fixed pre-warmed background workers failing with "Could not resolve authentication method" when claimed after sitting idle&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.173</id>
    <title>Claude Code v2.1.173</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.173"/>
    <updated>2026-06-11T05:41:48Z</updated>
    <content type="html">&lt;p&gt;• Fixed Fable 5 model names with a [1m] suffix not being normalized — Fable 5 includes 1M context by default, so the suffix is now stripped automatically&lt;/p&gt;
&lt;p&gt;• Fixed a spurious "sandbox dependencies missing" startup warning on Windows when sandbox was enabled in settings&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.172</id>
    <title>Claude Code v2.1.172</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.172"/>
    <updated>2026-06-10T20:44:09Z</updated>
    <content type="html">&lt;p&gt;• Sub-agents can now spawn their own sub-agents (up to 5 levels deep)&lt;/p&gt;
&lt;p&gt;• Amazon Bedrock now reads the AWS region from ~/.aws config files when AWS_REGION isn't set, matching AWS SDK precedence; /status shows where the region came from&lt;/p&gt;
&lt;p&gt;• Added a search bar when browsing a marketplace's plugins in /plugin&lt;/p&gt;
&lt;p&gt;• Added model attribute to the claude_code.lines_of_code.count OTEL metric&lt;/p&gt;
&lt;p&gt;• Fixed sessions using 1M context without usage credits getting permanently stuck — the session now automatically compacts back under the standard context limit&lt;/p&gt;
&lt;p&gt;• Fixed a repeating "an image in the conversation could not be processed and was removed" error when the conversation contained multiple images&lt;/p&gt;
&lt;p&gt;• Fixed the agents view keeping a session under Working with a busy spinner for up to 30 seconds after the worker replied&lt;/p&gt;
&lt;p&gt;• Fixed background agents potentially reading another directory's project settings (.mcp.json approvals, trust) when dispatched onto a pre-warmed worker&lt;/p&gt;
&lt;p&gt;• Fixed background-session attach failing with EAUTH for sessions started on an older version after the daemon auto-updated&lt;/p&gt;
&lt;p&gt;• Fixed a background sub-agent staying stuck as "active" in the agent panel after a nested agent it spawned was stopped&lt;/p&gt;
&lt;p&gt;• Fixed /model suggestions in the claude agents dispatch input rendering with a misleading slash prefix and showing models disabled for your org&lt;/p&gt;
&lt;p&gt;• Fixed availableModels restrictions not being applied to subagent model overrides, the agent dispatch model picker, and the advisor model&lt;/p&gt;
&lt;p&gt;• Fixed availableModels allowlists hiding the /model picker's Opus and Sonnet 1M rows when entries use version-specific IDs like claude-opus-4-8&lt;/p&gt;
&lt;p&gt;• Fixed the /model picker on Bedrock offering models the provider doesn't serve — selecting one silently switched the session model and lit the selection marker on multiple rows&lt;/p&gt;
&lt;p&gt;• Fixed model IDs getting a doubled 1M-context suffix (e.g. [1M][1m]) when ANTHROPIC_DEFAULT_OPUS_MODEL already includes one&lt;/p&gt;
&lt;p&gt;• Fixed opusplan model setting not shipping with 1M context in plan mode for entitled users; the opusplan[1m] workaround now also correctly switches to Opus in plan mode&lt;/p&gt;
&lt;p&gt;• Fixed WebFetch(domain:*.example.com) wildcard domain rules never matching subdomains in allow, deny, and ask position, and file permission rules with mid-pattern wildcards (e.g. Read(secrets-*/config.json)) being rejected at startup&lt;/p&gt;
&lt;p&gt;• Fixed up-arrow prompt history showing the main agent's prompts while a subagent's chat tab is open&lt;/p&gt;
&lt;p&gt;• Fixed memory recall not finding mounted team memory stores (CLAUDE_MEMORY_STORES) in remote sessions&lt;/p&gt;
&lt;p&gt;• Fixed workflow validation rejecting scripts whose prompt strings or comments merely mention Date.now()/Math.random()&lt;/p&gt;
&lt;p&gt;• Disable mouse tracking on Windows consoles that don't fully support it&lt;/p&gt;
&lt;p&gt;• Fixed the /plugin marketplace list losing its cursor after backing out of a long plugin list, and Esc from the plugin browser returning to the wrong tab&lt;/p&gt;
&lt;p&gt;• Improved performance in long conversations by removing redundant message normalization and avoiding full message-history transforms when streaming tool-use state is unchanged&lt;/p&gt;
&lt;p&gt;• Reduced idle CPU usage: /goal status chip no longer re-renders the terminal at 5 Hz while idle, and fewer UI re-renders while subagents run in parallel&lt;/p&gt;
&lt;p&gt;• Improved Claude in Chrome tool loading: browser tools now load in a single batched call instead of one per tool&lt;/p&gt;
&lt;p&gt;• Improved the non-interactive Usage Policy refusal message to suggest starting a new session or changing your model&lt;/p&gt;
&lt;p&gt;• /code-review now keeps the ultra option visible when you're not signed in to claude.ai, with an explanation that the cloud review requires a claude.ai account&lt;/p&gt;
&lt;p&gt;• Shortened the Remote Control footer indicator to "/rc active" and hid it on narrow terminals&lt;/p&gt;
&lt;p&gt;• Stopped promoting /loop in remote sessions, where pending loops don't keep the container alive&lt;/p&gt;
&lt;p&gt;• [VSCode] Fixed PowerShell tool calls rendering as raw JSON instead of a proper command display and permission dialog, and stripped ANSI escape codes from displayed shell output&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.170</id>
    <title>Claude Code v2.1.170</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.170"/>
    <updated>2026-06-09T17:23:03Z</updated>
    <content type="html">&lt;p&gt;• Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Fable’s capabilities exceed those of any model we’ve ever made generally available. Update to version 2.1.170 for access. https://www.anthropic.com/news/claude-fable-5-mythos-5&lt;/p&gt;
&lt;p&gt;• Fixed sessions not saving transcripts (and not appearing in --resume) when launched from the VS Code integrated terminal or any shell that inherited Claude Code environment variables.&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.169</id>
    <title>Claude Code v2.1.169</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.169"/>
    <updated>2026-06-08T21:57:10Z</updated>
    <content type="html">&lt;p&gt;• Self-hosted runner: added a post-session lifecycle hook that runs after the session ends and before the workspace is deleted, so you can snapshot uncommitted work or export logs; also made the child-process SIGTERM→SIGKILL window configurable (default unchanged at 5s)&lt;/p&gt;
&lt;p&gt;• Added --safe-mode flag (and CLAUDE_CODE_SAFE_MODE) to start Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting&lt;/p&gt;
&lt;p&gt;• Added /cd command to move a session to a new working directory without breaking the prompt cache mid-session&lt;/p&gt;
&lt;p&gt;• Added a disableBundledSkills setting and CLAUDE_CODE_DISABLE_BUNDLED_SKILLS environment variable to hide bundled skills, workflows, and built-in slash commands from the model&lt;/p&gt;
&lt;p&gt;• Fixed Up/Down arrows jumping to command history past the wrapped rows of a long input line — they now move through each visual row first, and history recall enters at the near edge&lt;/p&gt;
&lt;p&gt;• Fixed enterprise managed MCP policies (allowedMcpServers/deniedMcpServers) not being enforced on reconnect, IDE-typed configs, --mcp-config servers during the first session after install, or before remote settings loaded; also fixed slow cold starts for orgs without remote settings&lt;/p&gt;
&lt;p&gt;• Fixed a ~30-50ms UI stall at the start of each turn for macOS users logged in with claude.ai credentials&lt;/p&gt;
&lt;p&gt;• Fixed claude -p being slow or appearing to hang on Windows while waiting for the slash-command/skill scan (regression in 2.1.161)&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control getting stuck on "reconnecting" after resuming a session when an OAuth token refresh happened at the same time&lt;/p&gt;
&lt;p&gt;• Fixed Git Credential Manager's "Connect to GitHub" popup appearing on Windows at startup when background git commands ran without cached credentials&lt;/p&gt;
&lt;p&gt;• Fixed footer hints (e.g. "esc to interrupt") not showing for users with a custom statusline&lt;/p&gt;
&lt;p&gt;• Fixed stale permission and dialog prompts reappearing every time you reattached to a remote session whose worker had died while waiting on them&lt;/p&gt;
&lt;p&gt;• Fixed claude agents --json omitting blocked and just-dispatched background sessions; added --all to include completed sessions, plus new id and state fields&lt;/p&gt;
&lt;p&gt;• Fixed agents view leaving a stale/garbled frame after navigating back from an agent on WSL in Windows Terminal&lt;/p&gt;
&lt;p&gt;• Fixed background agents ignoring project-level settings env values (e.g. ANTHROPIC_MODEL) when dispatched onto a pre-warmed worker&lt;/p&gt;
&lt;p&gt;• Fixed MCPB plugin cache being spuriously invalidated on Windows, causing unnecessary re-extraction&lt;/p&gt;
&lt;p&gt;• Fixed plugin .in_use PID lock files accumulating without bound; stale markers from crashed sessions are now swept once per day&lt;/p&gt;
&lt;p&gt;• Fixed untrusted project settings being able to set OTEL client-certificate paths without trust confirmation&lt;/p&gt;
&lt;p&gt;• /workflows now opens immediately even while a turn is in progress&lt;/p&gt;
&lt;p&gt;• Improved TaskCreate reliability: malformed inputs are repaired automatically and validation errors for unloaded tools include the schema&lt;/p&gt;
&lt;p&gt;• Improved the error message shown when your organization has disabled API key authentication, with guidance based on where the active API key comes from&lt;/p&gt;
&lt;p&gt;• Reduced CPU usage while responses stream and during spinner animations&lt;/p&gt;
&lt;p&gt;• Restored a default 5-minute idle timeout on Vertex/Foundry so a stalled stream aborts instead of hanging indefinitely; set API_FORCE_IDLE_TIMEOUT=0 to opt out&lt;/p&gt;
&lt;p&gt;• Remote-managed settings with an invalid entry now apply their remaining valid policies and surface the validation error, instead of silently dropping the whole payload&lt;/p&gt;
&lt;p&gt;• Background sessions now preserve --ide, --chrome, --bare, --remote-control, and other flags across retire→wake, and respawn state validation was hardened&lt;/p&gt;
&lt;p&gt;• Background sessions are now told that shared-checkout edits are blocked until they enter a worktree, avoiding a wasted rejected edit before EnterWorktree&lt;/p&gt;
&lt;p&gt;• The "CLAUDE.md is too long" warning threshold now scales with the model's context window&lt;/p&gt;
&lt;p&gt;• Auto-updater on Windows now stops retrying within a session once claude.exe is held by another process&lt;/p&gt;
&lt;p&gt;• Improved color contrast for skill tags in the slash-command menu&lt;/p&gt;
&lt;p&gt;• Promo credit claims for Apple/Google-billed subscribers without a payment method now explain where to add one&lt;/p&gt;
&lt;p&gt;• Added a tip suggesting claude agents when running multiple concurrent sessions&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.168</id>
    <title>Claude Code v2.1.168</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.168"/>
    <updated>2026-06-06T23:41:47Z</updated>
    <content type="html">&lt;p&gt;• Bug fixes and reliability improvements&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.167</id>
    <title>Claude Code v2.1.167</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.167"/>
    <updated>2026-06-06T01:33:29Z</updated>
    <content type="html">&lt;p&gt;• Bug fixes and reliability improvements&lt;/p&gt;</content>
  </entry>
</feed>