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>2026-08-28T18:19:26Z</updated>
  <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">&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Added live streaming of a foreground subagent's tool calls and results to Remote Control clients (background subagents, the default, still show status only)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Added attach, logs, stop, respawn, and rm to claude --help; the --resume message for a running background session now names the exact claude attach &amp;lt;id&amp;gt; command&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed the Workflow tool reading (and quoting in errors) a scriptPath outside what the session may read before the permission check ran&lt;/p&gt;
&lt;p&gt;• Fixed Grep and Glob not applying Read(...) deny rules to files reached through a symlinked search path&lt;/p&gt;
&lt;p&gt;• Fixed conversations getting stuck on "text content blocks must be non-empty" errors after a turn where the model produced only thinking&lt;/p&gt;
&lt;p&gt;• Fixed the first launch on a fresh install starting in default mode instead of auto mode for accounts whose startup default is auto mode&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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"&lt;/p&gt;
&lt;p&gt;• Fixed TUI lag with many parallel subagents: per-second progress ticks now replace their predecessor instead of piling up in the transcript&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• Fixed managed-settings disableAutoMode arriving mid-session not moving an already-running auto-mode session back to default mode&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed cloud sessions telling Claude the model had changed when the host was only setting the session's initial model&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control reporting a failure when an organization's policy disables it; it now shows a single quiet notice instead&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed session transcripts being silently overwritten when a directory change relocated a session onto an existing same-ID transcript&lt;/p&gt;
&lt;p&gt;• Fixed background sessions and their subagents being unable to edit files inside a git worktree they created with git worktree add&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed self-hosted runner leaving a stuck session's Bash tool processes running after the session was force-stopped&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed Ctrl+G failing with "Emacs quit unexpectedly" in background sessions for editors that open /dev/tty, such as emacs -nw and micro&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed the MCP server menu's copy shortcut: it now says how the sign-in URL was copied instead of always claiming success&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed claude mcp add --header and claude mcp add-json help text naming the wrong transports&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed the managed-settings approval prompt re-appearing after signing in again to the same Claude apps gateway when the settings are unchanged&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed cloud session creation advising GitHub setup after a transient GitHub connection failure — the message now says to retry instead&lt;/p&gt;
&lt;p&gt;• Improved CPU usage during turns in interactive sessions by cutting redundant UI re-renders&lt;/p&gt;
&lt;p&gt;• Improved install size: the native binary is about 5 MB smaller&lt;/p&gt;
&lt;p&gt;• 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"&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Improved framing of messages from your own subagents: Claude is told the sender is a worker inside this session, not an unrelated Claude session&lt;/p&gt;
&lt;p&gt;• Improved the prompt placeholder to read "Message @name…" while viewing a background subagent or fork transcript opened from the subagent panel or /tasks&lt;/p&gt;
&lt;p&gt;• Improved sanitization of MCP server names in error messages, menus, and command results&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Improved the managed settings approval dialog to list only the settings that changed since you last approved them&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Changed /radio to be available on Bedrock, Vertex AI, Foundry, and Claude Platform on AWS, and when telemetry is disabled&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• Changed the default model for seat-based Enterprise subscriptions to Opus 5, matching other premium plans&lt;/p&gt;
&lt;p&gt;• Changed /effort to save your default effort level per model, so each model keeps its own setting when you switch&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Removed syntax highlighting for six rarely used languages (1c, gml, isbl, mathematica, maxima, sqf); the binary is 2.5 MB smaller&lt;/p&gt;
&lt;p&gt;• [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&lt;/p&gt;
&lt;p&gt;• [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&lt;/p&gt;</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">&lt;p&gt;• Bug fixes and reliability improvements&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.248</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">&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Added experimental.cacheTtl ("5m" or "1h") to agent frontmatter: a per-agent prompt cache TTL used when no subagent TTL setting is configured&lt;/p&gt;
&lt;p&gt;• Added claude self-hosted-runner --client-label &amp;lt;label&amp;gt; (or SELF_HOSTED_RUNNER_CLIENT_LABEL) to override the label the runner registers with (default: hostname)&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Added cross-session messaging (SendMessage / ListAgents) between sessions on the same machine on Bedrock, Vertex, and Foundry, and when telemetry is disabled&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed claude agents skipping the workspace trust prompt when the CI environment variable is set&lt;/p&gt;
&lt;p&gt;• Fixed claude agents crashing on launch when the PR-status cache held a malformed entry&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed agent view sometimes opening an older conversation, and dropping the typed prompt, when starting a new session&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed /login to a Claude apps gateway hanging when the managed-settings security approval dialog was required&lt;/p&gt;
&lt;p&gt;• Fixed gateway model discovery (CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY) never running when apiKeyHelper is the only credential&lt;/p&gt;
&lt;p&gt;• Fixed claude logs leaving mouse tracking, bracketed paste and the alternate screen switched on in the terminal it was run from&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control sessions occasionally never showing a permission prompt or the latest messages on the connected device after the CLI silently reconnected&lt;/p&gt;
&lt;p&gt;• Fixed cloud sessions occasionally failing at startup when the container's session credentials were not yet readable&lt;/p&gt;
&lt;p&gt;• Fixed claude remote-control rejecting its own flags (e.g. --spawn, --name) when a global flag or a wrapper-injected option precedes the subcommand&lt;/p&gt;
&lt;p&gt;• Fixed startup warnings (e.g. "N MCP servers need authentication") rendering one column right of the rest of the transcript&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed @-mentions of other sessions not matching names typed with non-Latin characters (for example Korean entered through an IME)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• [VSCode] Fixed a chat tab getting stuck on "No conversation found" when its session was never saved; it now starts a new conversation instead&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Improved managed settings: client-side timeout, MCP startup-mode, and stream-watchdog env vars no longer trigger the settings-approval prompt&lt;/p&gt;
&lt;p&gt;• Improved /ultrareview &amp;lt;PR#&amp;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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Changed shift+enter in the agent view dispatch input to insert a newline (matching the prompt); ctrl+enter now dispatches and attaches&lt;/p&gt;
&lt;p&gt;• Changed /loop: self-paced dynamic mode and the no-prompt autonomous default are now always available, including on Bedrock/Vertex/Foundry&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Changed cross-session messaging in Linux user namespaces: root-equivalent trust for unmapped owners is limited to canonical system directories&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;</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">&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• Added {id, text, cooldownSessions, priority} entries, tipsFile, and label to spinnerTipsOverride, so organizations can rotate their own tips alongside the built-in ones&lt;/p&gt;
&lt;p&gt;• Added a tip on Bash permission prompts pointing to auto mode, with a one-keystroke "Yes, and switch to auto mode" option&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Updated the /claude-api skill with Admin API coverage (organization members, invites, workspaces, API keys, rate limit reports, workload identity federation, CMEK)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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"&lt;/p&gt;
&lt;p&gt;• Fixed Ctrl keyboard shortcuts not firing under non-Latin (e.g. Cyrillic) keyboard layouts in kitty-protocol terminals&lt;/p&gt;
&lt;p&gt;• Fixed text like &amp;lt;35;150;7M being inserted into the prompt when a mouse report arrived split across reads right after the escape prefix&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed /terminal-setup overwriting your entire Zed keymap.json instead of merging in its keybinding&lt;/p&gt;
&lt;p&gt;• Fixed /rename silently confirming when the session registry could not be updated; it now says other sessions may still show the old name&lt;/p&gt;
&lt;p&gt;• Fixed /compact and "Summarize from here" in sessions started with --agent summarizing under the default system prompt instead of the conversation's own&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control sessions started with /remote-control not reporting the working-tree diff to connected clients&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Changed cross-session peer messages to collapse by default to a one-line Message from @&amp;lt;sender&amp;gt;: &amp;lt;first line&amp;gt; preview; Ctrl+O expands the full body&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Changed the prompt-footer PR badge to skip its GitHub re-check on terminal refocus when the last check is under a minute old&lt;/p&gt;
&lt;p&gt;• Changed analytics to stay off from startup, not only after login, when managed settings force gateway login or a custom OAuth deployment is configured&lt;/p&gt;
&lt;p&gt;• Changed Claude apps gateway sign-in requests to identify Claude Code (a surface=claude_code device-authorization parameter and a claude-code/&amp;lt;version&amp;gt; User-Agent)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;</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">&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Added an Auto mode tab to /permissions for viewing and editing auto mode classifier rules&lt;/p&gt;
&lt;p&gt;• Added the turn's completion time to the end-of-turn duration line, e.g. ✻ Sautéed for 23s · done 6:05 PM&lt;/p&gt;
&lt;p&gt;• Fixed fullscreen mode showing a blank transcript after resizing the terminal and jumping to the bottom until the next keypress&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed erratic fullscreen scrolling when positioned at an earlier message, including jump-to-bottom getting stuck mid-transcript&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed markdown rendering being disabled for a whole message when its first 500 characters contained no markdown, and for +/N) lists and setext headings&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed MCP tool arguments being sent as JSON strings when the parameter's schema is empty ({}), instead of their real type&lt;/p&gt;
&lt;p&gt;• Fixed a command interrupted mid-run showing as "Ran 1 shell command" with no sign it was cut&lt;/p&gt;
&lt;p&gt;• Fixed pressing ← or running /background during a dynamic workflow restarting its finished subagents; it now asks first and says how many subagents would restart&lt;/p&gt;
&lt;p&gt;• 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"&lt;/p&gt;
&lt;p&gt;• Fixed claude agents listing a backgrounded named session twice; backgrounding the same conversation again now numbers the new row (e.g. my-session (2))&lt;/p&gt;
&lt;p&gt;• Fixed the background retention sweep removing git worktrees under .claude/worktrees/ that you created yourself when an old background-session record pointed at them&lt;/p&gt;
&lt;p&gt;• Fixed auto mode tool calls being denied as "temporarily unavailable" on very large sessions by scaling the safety-check deadline with prompt size&lt;/p&gt;
&lt;p&gt;• Fixed the plugin cache creating duplicate SHA-named directories for the same plugin&lt;/p&gt;
&lt;p&gt;• Fixed plugin skills whose frontmatter name already includes the &amp;lt;plugin&amp;gt;: prefix showing it doubled in the slash menu (e.g. /plugin:plugin:skill)&lt;/p&gt;
&lt;p&gt;• Fixed claude plugin update failing for an installed plugin given its bare name (only the fully-qualified name worked)&lt;/p&gt;
&lt;p&gt;• Fixed plugin installation failing when plugin.json was saved with a UTF-8 byte-order mark (BOM)&lt;/p&gt;
&lt;p&gt;• Fixed /reload-plugins reporting 0 skills for plugins that define skills under skills/*/SKILL.md&lt;/p&gt;
&lt;p&gt;• Fixed hook error messages showing a literal ${CLAUDE_PLUGIN_ROOT} instead of the resolved plugin path&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed custom theme diff colors (diffAdded/diffRemoved and their dimmed variants) being ignored in diffs and the /theme preview&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed /stats activity heatmap showing each day's activity one cell off (Sunday's count under Monday) in timezones east of UTC&lt;/p&gt;
&lt;p&gt;• Fixed /fork from an already-forked or backgrounded session starting the new session with an empty conversation&lt;/p&gt;
&lt;p&gt;• Fixed prompts beginning with /-- (e.g. Lean doc comments) being rejected as an unknown slash command instead of being sent to Claude&lt;/p&gt;
&lt;p&gt;• Fixed the @ file picker staying open after the typed text stopped matching a real path&lt;/p&gt;
&lt;p&gt;• Fixed the status line's cost and duration resetting to zero after navigating to the agents view and back&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed path completion failing when the completion token or working directory contained a null byte&lt;/p&gt;
&lt;p&gt;• Windows/macOS: Fixed headless sessions not cleaning up stale entries in ~/.claude/sessions left by sessions that exited uncleanly&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed claude plugin install &amp;lt;name&amp;gt; exiting silently (or hanging in a terminal) instead of reporting an error when ~/.claude/plugins/known_marketplaces.json is empty or corrupted&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed the Notification hook not firing while the sandbox "Network request outside of sandbox" permission prompt is waiting&lt;/p&gt;
&lt;p&gt;• Fixed Bash permission checks to always require approval for malformed commands with a dangling &amp;amp;&amp;amp; or || operator&lt;/p&gt;
&lt;p&gt;• Fixed --strict-mcp-config sessions prompting to approve .mcp.json servers they would never load, which left background sessions waiting at startup&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed the task progress count (e.g. 3/5) shown for background cloud sessions such as /autofix-pr occasionally missing a task&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Improved Bash tool latency on bash shells by replaying snapshot functions without a base64 subshell per function&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• /goal: Changed idle sessions to start at most three check-ins on long-running background work per goal; your next message allows three more&lt;/p&gt;
&lt;p&gt;• Changed claude install and claude update to defer a pending managed-settings consent prompt to the next interactive session instead of prompting mid-command&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed the command sandbox's filesystem configuration not respecting --setting-sources&lt;/p&gt;</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">&lt;p&gt;• Fixed a crash on startup on Linux distributions that ship glibc 2.44 (for example Arch Linux, CachyOS and Fedora Rawhide)&lt;/p&gt;</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">&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Added a managed marker in /mcp and /plugins on claude.ai connectors whose authentication is managed by your organization&lt;/p&gt;
&lt;p&gt;• Added a tip pointing claude.ai users who haven't connected GitHub for Claude Code on the web to /web-setup&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Added the model (and effort level) each subagent ran on to /tasks and the agent detail dialogs&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• Fixed auto mode staying unavailable at startup when a temporary server-side disable was cached and later flag fetches failed&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed the /model picker silently ignoring an Ultracode selection; picking Ultracode now applies it to the current session&lt;/p&gt;
&lt;p&gt;• Fixed /resume only listing the 50 most recent sessions; the picker now loads more as you scroll&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed cross-session messaging silently turning off inside user namespaces and rootless containers after the 2.1.232 socket-directory hardening&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed spellcheck not underlining a misspelled word typed directly after an emoji&lt;/p&gt;
&lt;p&gt;• Fixed background subagents not waking when their last background Bash task completes&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed auth, model-availability, and other client-generated error messages rendering like model output instead of as error lines&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed server-managed companyAnnouncements not showing at startup in a session that began with signing in (for example the first launch after /logout)&lt;/p&gt;
&lt;p&gt;• Fixed hook if conditions like Bash(cat *) firing on unrelated Bash commands when the command contained $() or backtick command substitution followed by more arguments&lt;/p&gt;
&lt;p&gt;• Fixed plugin dependencies declared with a marketplace field never resolving when both plugins are loaded together via --plugin-dir&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed --agents silently ignoring invalid JSON or invalid agent definitions; it now exits with a clear error, like --mcp-config&lt;/p&gt;
&lt;p&gt;• Fixed /status showing "Found invalid entries in: ." with no filename when ~/.claude.json has an invalid MCP server entry&lt;/p&gt;
&lt;p&gt;• Fixed /clear removing the /rename session name from the prompt bar even though the name was kept for the new session&lt;/p&gt;
&lt;p&gt;• Fixed Ctrl+R history search and up-arrow history breaking when ~/.claude/history.jsonl contains a malformed entry&lt;/p&gt;
&lt;p&gt;• Fixed Ctrl+[ not leaving vim INSERT mode in terminals that encode modified keys (modifyOtherKeys / kitty protocol)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed claude --teleport &amp;lt;session&amp;gt; exiting on uncommitted changes instead of offering to stash them and continue, as the session picker already does&lt;/p&gt;
&lt;p&gt;• Fixed /web-setup repeatedly asking you to log in when an older GitHub CLI (without gh auth token) was already authenticated&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• [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&lt;/p&gt;
&lt;p&gt;• [VSCode] Fixed Focus view sections you expanded collapsing on their own during subagent tool activity&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Improved native install and auto-update download size: the binary is now zstd-compressed (about 75 MB instead of 340 MB on Linux x64)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Improved native binary size: about 2 MB smaller by storing the bundled skill and prompt text more compactly&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• Improved peak memory usage in long-running sessions (the runtime now garbage-collects sooner as the heap grows)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed claude remote-control exiting and stranding attached Remote Control sessions when the server drops its environment mid-session; it now recovers&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• [VSCode] Improved history trimming in long sessions: older tool-activity rows are dropped first so your messages and Claude's replies stay visible&lt;/p&gt;
&lt;p&gt;• [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&lt;/p&gt;</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">&lt;p&gt;• Bug fixes and reliability improvements&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.240</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">&lt;p&gt;• Bug fixes and reliability improvements&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.239</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">&lt;p&gt;• Cost estimates (/cost, status line, --max-budget-usd) now include the 1.1× US-only-inference premium for data-residency workspaces&lt;/p&gt;
&lt;p&gt;• Added the one-time fullscreen renderer offer on Bedrock, Vertex, Foundry and other previously excluded setups; new installs there now start in fullscreen&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• Cloud sessions: plugins synced from claude.ai now show as name@synced, work with claude plugin enable/disable &amp;lt;name&amp;gt;@synced, and never override a same-named plugin you installed&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• The usage-limit message shown when your monthly spend limit is already used up now also says when your session or weekly limit resets&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed a raw crash dump when starting Claude Code from a directory that no longer exists; it now prints a clear message&lt;/p&gt;
&lt;p&gt;• Fixed Edit and Write calls pausing for about 5 seconds in JetBrains IDE terminals when the Claude Code plugin is connected&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed WebFetch retaining expired page content in memory for the whole session instead of the intended 15 minutes&lt;/p&gt;
&lt;p&gt;• Fixed cloud sessions (Claude Code on the web, desktop and mobile apps) resuming out of plan mode after an idle worker restart&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed remote MCP servers staying failed after a transient 5xx on a mid-session reconnect in cloud sessions or via SDK setMcpServers()&lt;/p&gt;
&lt;p&gt;• Fixed custom session titles disappearing from /resume after more than ~64 KB of conversation was written following the rename&lt;/p&gt;
&lt;p&gt;• Fixed claude -c/resume picking up sessions from a different directory whose path differed only by characters like _, -, or .&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed the dark-ansi theme rendering expanded tool results in fullscreen mode with text the same color as the background&lt;/p&gt;
&lt;p&gt;• Fixed the fullscreen renderer prompt reappearing on every launch when it could never be answered; it now stops after being shown on three launches&lt;/p&gt;
&lt;p&gt;• Fixed .worktreeinclude patterns starting with **/ silently matching nothing when the target lived in a gitignored directory&lt;/p&gt;
&lt;p&gt;• Fixed agents, skills, and commands whose .md file starts with a UTF-8 BOM being silently ignored&lt;/p&gt;
&lt;p&gt;• Fixed /insights echoing literal &amp;lt;message&amp;gt; tags in its response on some models&lt;/p&gt;
&lt;p&gt;• Fixed marketplace metadata.pluginRoot having no effect: bare plugin source names now resolve under it as the docs describe&lt;/p&gt;
&lt;p&gt;• Fixed mouse movement in browser-based terminals inserting text like "35;150;7M" into the prompt when a mouse report arrived split across writes&lt;/p&gt;
&lt;p&gt;• Fixed custom theme overrides for the effort/ultracode status badge colors being ignored&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed vim mode in the agent view: Escape now switches to NORMAL mode and keeps your text instead of clearing the prompt&lt;/p&gt;
&lt;p&gt;• Fixed the selection:copy keybinding silently dropping a text selection that had been extended with Shift+Arrow keys&lt;/p&gt;
&lt;p&gt;• Fixed the /voice startup tip still appearing after voice dictation was enabled via the voice.enabled setting&lt;/p&gt;
&lt;p&gt;• Fixed shell-mode (!) Tab completion dropping the ./ from a ./script path, which left a command the shell couldn't run&lt;/p&gt;
&lt;p&gt;• Fixed fullscreen mode answering a permission prompt or pressing a button when you clicked the terminal window only to bring it back into focus&lt;/p&gt;
&lt;p&gt;• Fixed slash-command panels (e.g. /config, /model) in fullscreen mode covering the latest messages; the conversation now stays pinned above the panel&lt;/p&gt;
&lt;p&gt;• Fixed the /workflows detail dialog overflowing the terminal and losing its header off-screen when opened while Claude is still responding&lt;/p&gt;
&lt;p&gt;• Fixed the Linux sandbox making a nonexistent .git/config.worktree unreadable, which broke every sandboxed git command in repos with extensions.worktreeConfig set&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed claudeMdExcludes not excluding a symlinked .claude/rules file when the pattern names the rules directory or the symlink rather than its target&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed sessions whose title starts with / being unaddressable by SendMessage and shown as "(untitled)" in ListAgents&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed Ctrl+Backspace deleting one character instead of a word in search boxes&lt;/p&gt;
&lt;p&gt;• Fixed a request rejected by an organization policy check being re-sent before the rejection was shown&lt;/p&gt;
&lt;p&gt;• Improved the reminder shown after compaction so a skill's original arguments are not re-run as a new request&lt;/p&gt;
&lt;p&gt;• Long file paths on tool-use rows now truncate in the middle to stay on one line&lt;/p&gt;
&lt;p&gt;• Remote sessions keep sending keep-alives while a long SessionStart or Setup hook runs, so the container is not idle-reaped mid-hook&lt;/p&gt;
&lt;p&gt;• /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&lt;/p&gt;
&lt;p&gt;• /goal: resuming a session from the claude --resume picker now restores its active goal&lt;/p&gt;
&lt;p&gt;• 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 …"&lt;/p&gt;
&lt;p&gt;• ListAgents and /list-agents now list your live teammates (previously only subagents and other sessions appeared, so a reachable teammate looked absent)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Claude in Chrome: /clear now closes the session's Chrome tab group, and empty groups are closed on /resume and when Claude Code exits&lt;/p&gt;
&lt;p&gt;• Remote sessions: images uploaded from mobile now include their saved file path, so Claude can copy them into files it creates&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Remote Control: clearer message and claude doctor wording when Remote Control isn't enabled for your account&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• [VSCode] "View usage" in the usage-limit banner now sits inline with the warning text instead of floating mid-banner&lt;/p&gt;</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">&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• Added claude self-hosted-runner --defer-shutdown-max-min &amp;lt;minutes&amp;gt;: on SIGTERM, keep serving attached sessions, park what is left after that many minutes, then exit&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed unbounded memory growth in long interactive sessions: subagent tool results are now released once they leave the recent display window&lt;/p&gt;
&lt;p&gt;• Fixed custom, project, and plugin output styles drifting back to the default voice mid-session&lt;/p&gt;
&lt;p&gt;• Fixed CLAUDE_CODE_ENABLE_PROMPT_SUGGESTION=true not keeping prompt suggestions on when your account is near, but not over, its usage limit&lt;/p&gt;
&lt;p&gt;• Fixed worktree-isolation Bash refusals telling you to remove a redirect when the command had none&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed leftover /tmp/claude-*-cwd files when a Bash command is killed, times out, or is interrupted&lt;/p&gt;
&lt;p&gt;• Fixed held Backspace being ignored on terminals that send Ctrl+H for Backspace when keystrokes arrive in large bursts (slow SSH/mosh links)&lt;/p&gt;
&lt;p&gt;• Fixed text-wrapping in permission prompt diffs: lines containing wide multi-code-point characters (such as emoji) or tabs are no longer clipped&lt;/p&gt;
&lt;p&gt;• Fixed killing a suspended (Ctrl+Z) session sometimes leaving the terminal in bracketed-paste mode with the cursor hidden&lt;/p&gt;
&lt;p&gt;• Fixed stdio MCP servers receiving a server/discover request before initialize, forcing lazy servers to start their backend on every session open&lt;/p&gt;
&lt;p&gt;• Fixed a proxy's refusal of a connection being reported as a generic network error instead of naming the proxy&lt;/p&gt;
&lt;p&gt;• Fixed the /model and /effort cache-miss warning appearing when the prompt cache had already expired&lt;/p&gt;
&lt;p&gt;• Fixed per-task Stop from the Remote Control tasks panel doing nothing on CLI-hosted sessions&lt;/p&gt;
&lt;p&gt;• Fixed remote sessions exiting when a client delivered a user message without a valid role&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control sessions started by claude remote-control inheriting session-scoped environment variables from the launching shell&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control messages sent from the web or Desktop while Claude is mid-turn disappearing from the transcript after the turn finishes&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control model picks made on a phone or web not updating the model shown in the terminal&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control disconnecting with "login expired" when a brief network hiccup delays renewing your sign-in; it now retries and stays connected&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control reporting a failed reconnect on sign-out; signing out now ends the session with a clear message&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Improved startup: bare claude starts sooner on macOS&lt;/p&gt;
&lt;p&gt;• Improved Bash tool permission checking for zsh-specific syntax in shell conditionals&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Improved startup responsiveness: the automatic update check now runs about 10 seconds after launch instead of competing with startup for CPU&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Changed claude mcp list and claude mcp get to show disabled servers as ⊘ Disabled instead of connecting to them for a health check&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;</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">&lt;p&gt;• Fixed prompt caching for sessions using an LLM gateway or custom base URL&lt;/p&gt;
&lt;p&gt;• 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.&lt;/p&gt;</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">&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed SendMessage calls being rejected when a malformed closing tag left the message text inside the summary field&lt;/p&gt;
&lt;p&gt;• 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)&lt;/p&gt;
&lt;p&gt;• Fixed fullscreen mode sometimes not showing a newly sent message until the next update after the terminal was resized&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed the managed-settings approval prompt sometimes not appearing at startup while still capturing the first keypress as approval&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed an unclear error when the cloud environments list came back empty or malformed&lt;/p&gt;
&lt;p&gt;• Fixed the Fable 5 first-time usage-credits prompt auto-selecting the fallback model after 60 seconds with no answer when using Remote Control&lt;/p&gt;
&lt;p&gt;• Fixed spinner tips never appearing, with a repeated background error, when the cached guest-pass reward in ~/.claude.json was malformed&lt;/p&gt;
&lt;p&gt;• 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+)&lt;/p&gt;
&lt;p&gt;• Fixed self-hosted runner sessions released on idle, retire, or startup timeout occasionally resuming on another runner before the post-session hook had finished&lt;/p&gt;
&lt;p&gt;• Fixed the Clawd mascot's eyes and feet rendering unevenly in iTerm2 at some font sizes&lt;/p&gt;
&lt;p&gt;• Fixed occasional runaway session recaps: recap text (automatic and /recap) is now capped at 400 characters, cut at a word boundary&lt;/p&gt;
&lt;p&gt;• Improved startup performance: the session counter is now written in the background&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• /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&lt;/p&gt;
&lt;p&gt;• /usage now shows the usage-credits spend row for Team and Enterprise members, and shows a capped row at 0% before anything is spent&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Remote Control now marks a session offline within seconds when the CLI exits or its terminal closes&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Aligned the session title chip on the prompt border with the footer's right edge&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• [VSCode] Added screen reader support for the transcript: live announcements for replies, permission requests, errors, and status changes, plus per-turn heading navigation&lt;/p&gt;</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">&lt;p&gt;• Added an optional spellcheck setting that underlines misspelled words in the prompt input as you type, using your installed aspell, hunspell, or ispell&lt;/p&gt;
&lt;p&gt;• Fixed whole-prompt-cache invalidation when a language server disconnected or reconnected mid-session&lt;/p&gt;
&lt;p&gt;• Fixed nested markdown list items misaligning at depth 3+ and added a hanging indent to wrapped list items in the terminal UI&lt;/p&gt;
&lt;p&gt;• Fixed prompt input highlights (slash commands, keywords, mentions) appearing shifted by one or more characters in some multi-line prompts&lt;/p&gt;
&lt;p&gt;• Fixed Shift+Tab inside the permission prompt's comment field approving the edit and granting session-wide edit permission instead of closing the field&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Fixed slash commands run while Claude is responding showing HTML entities instead of the actual characters&lt;/p&gt;
&lt;p&gt;• Fixed the prompt footer not showing the "Update installed" restart notice after a background auto-update&lt;/p&gt;
&lt;p&gt;• Fixed the expanded task list (ctrl+t) always starting collapsed when resuming or relaunching into a session that still has open tasks&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• 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&lt;/p&gt;
&lt;p&gt;• Improved the context-limit error to say when auto-compact is off and point to /config to re-enable it&lt;/p&gt;
&lt;p&gt;• Vim mode: NORMAL mode and cursor position are now preserved when toggling the detailed transcript (ctrl+o) or closing a panel&lt;/p&gt;
&lt;p&gt;• Dialogs: arrow keys and Enter pressed in quick succession now select the option you navigated to instead of the previously highlighted one&lt;/p&gt;
&lt;p&gt;• SendMessage now refuses messages too large for cross-session delivery up front instead of silently dropping them&lt;/p&gt;
&lt;p&gt;• Remote Control: claude rc now applies the same enterprise-gateway availability check as interactive startup&lt;/p&gt;
&lt;p&gt;• [VSCode] Fixed focus jumping between open Claude tabs on its own when a window with several Claude panels is restored or reloaded&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.234</id>
    <title>Claude Code v2.1.234</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.234"/>
    <updated>2026-08-17T20:20:52Z</updated>
    <content type="html">&lt;p&gt;• Added the optional CLAUDE_CODE_PROJECT_DIR_NAME environment variable: hosts that give each session its own config directory can choose a short name for the per-project transcript directory&lt;/p&gt;
&lt;p&gt;• Added the selection:clear keybinding action, so a key can be bound to clear an in-app text selection; also works in the agents view&lt;/p&gt;
&lt;p&gt;• Added a GitLab merge request badge to the footer and statusline: repos with a GitLab remote and an authenticated glab CLI show MR !N with draft/pending/green states&lt;/p&gt;
&lt;p&gt;• Claude Code now continues your session automatically when a claude.ai usage limit resets; turn it off in /config ("Continue automatically at usage limit")&lt;/p&gt;
&lt;p&gt;• Claude is now told to use your account email only to identify you, and not to send it to unrelated services unless you ask&lt;/p&gt;
&lt;p&gt;• Security: remote file reads, session restore, CLAUDE.md includes, workflow scripts and file uploads now reject Windows NT-namespace (\??\) paths, hardening the remaining pre-approval file accesses against the NTLM credential-leak vector&lt;/p&gt;
&lt;p&gt;• Fixed auto mode in very long sessions repeatedly re-checking and denying sandboxed commands' network access after the conversation had been compacted&lt;/p&gt;
&lt;p&gt;• Fixed session-scoped permission answers (including denies) being dropped when answering background subagent tool permission prompts&lt;/p&gt;
&lt;p&gt;• Fixed a crash when an API response on the non-streaming fallback path (typically via third-party gateways) contained a thinking block missing its thinking field or a text block missing its text field&lt;/p&gt;
&lt;p&gt;• Fixed markdown rendering becoming extremely slow for some messages containing unusual Unicode sequences&lt;/p&gt;
&lt;p&gt;• Fixed SendMessage rejecting a recipient copied from ListAgents when the session name is at the 200-character cap or emoji-heavy&lt;/p&gt;
&lt;p&gt;• Fixed repository detection mis-reading the host of git remotes with unusual userinfo, producing links and repo-specific behavior for the wrong host&lt;/p&gt;
&lt;p&gt;• Fixed MCP diagnostics printing resolved secrets: scope-conflict warnings now show the configured ${VAR} form, and connection-failure details show only the server origin&lt;/p&gt;
&lt;p&gt;• Fixed strictKnownMarketplaces allowlists accepting SCP-style git marketplace sources whose host differs from the one git would actually connect to&lt;/p&gt;
&lt;p&gt;• Fixed modal text such as the /login OAuth URL losing characters when copied in fullscreen&lt;/p&gt;
&lt;p&gt;• Fixed a --- horizontal rule in rendered markdown running into the line after it&lt;/p&gt;
&lt;p&gt;• Fixed consecutive shell commands splitting into multiple "Ran 1 shell command" rows when todo/task updates were interleaved between them&lt;/p&gt;
&lt;p&gt;• Fixed dialogs like /permissions opened while a ! shell command was running being dismissed when the command finished&lt;/p&gt;
&lt;p&gt;• Fixed a queued ! shell command being sent to the model as plain text after pressing up-arrow to edit the queued input&lt;/p&gt;
&lt;p&gt;• Fixed queued messages reappearing in the prompt history while still queued, Esc while selecting a queued message no longer interrupts the turn, and ! mode no longer sticks after a mid-turn submit&lt;/p&gt;
&lt;p&gt;• Fixed accepting the "Try the new fullscreen renderer?" prompt restarting the session without its permission mode (e.g. --dangerously-skip-permissions), tool allow/deny rules, model or effort flags&lt;/p&gt;
&lt;p&gt;• Fixed /tui dropping launch --allowed-tools/--disallowed-tools rules when it restarts; it now declines to switch, with the reason, when the session has restrictions a restart can't carry over&lt;/p&gt;
&lt;p&gt;• Fixed trust prompts omitting the repository-wide scope warning when the directory was first seen before the repository existed there&lt;/p&gt;
&lt;p&gt;• Fixed a case where an IDE diff tab closing during a permission re-prompt could answer the new prompt with the previous input&lt;/p&gt;
&lt;p&gt;• Fixed: files sent to the user during Remote Control sessions hosted by Claude Code Desktop or VS Code now upload, so they open on phone and web instead of showing an empty card&lt;/p&gt;
&lt;p&gt;• Fixed: after /login while CLAUDE_CODE_OAUTH_TOKEN is set, the stale-token reminder no longer leaks into Claude's automatically resumed turn — it now appears only to you&lt;/p&gt;
&lt;p&gt;• Fixed: permission previews now relay only to channel servers admitted by the inbound trust gate, and a server's explicit permission-capability opt-out is honored&lt;/p&gt;
&lt;p&gt;• Fixed: credential masking on relayed permission previews can no longer hide commands, paths, or destinations from the approver; oversized private-key blocks now redact under full-strength redaction&lt;/p&gt;
&lt;p&gt;• Fixed: provider API tokens that mask on permission previews now mask even when directly followed by shell delimiters&lt;/p&gt;
&lt;p&gt;• Fixed Claude Desktop inter-session messages being silently dropped by the recipient session when cross-session messaging read as disabled, which left the sender's query "thinking" for many minutes&lt;/p&gt;
&lt;p&gt;• Remote Control: signing this computer in to a different claude.ai account or organization now stops the running session within seconds and says why, instead of a misleading HTTP 404 hours later&lt;/p&gt;
&lt;p&gt;• Remote Control sessions started from Claude Code Desktop or VS Code now keep phones and claude.ai/code updated on the session's permission mode (and claude.ai/code on the model) as they change&lt;/p&gt;
&lt;p&gt;• Remote Control: effort picks made on a phone or on claude.ai/code now apply to terminal- and Desktop/VS Code-hosted sessions, and the session publishes its effort level to connected clients&lt;/p&gt;
&lt;p&gt;• SendMessage and ListAgents now say when your account's session list was too long to check completely, instead of treating unseen sessions as absent&lt;/p&gt;
&lt;p&gt;• Expired Anthropic profile credential now points you at /login when a claude.ai login would take precedence&lt;/p&gt;
&lt;p&gt;• Improved the transcript: your own prompts now render markdown (highlighted code blocks, inline code, lists) the same way replies do&lt;/p&gt;
&lt;p&gt;• Improved the "API returned an empty or malformed response" error to say what came back (content type, body kind, size, request ID) and why the original streaming request failed&lt;/p&gt;
&lt;p&gt;• Improved auto-generated session titles to read as short, specific names (e.g. "Login button bug") rather than sentences restating your request (e.g. "Fix the login button on mobile")&lt;/p&gt;
&lt;p&gt;• Reduced the context cost of loading the built-in claude-api skill from ~200k+ tokens to ~25k by loading reference docs on demand&lt;/p&gt;
&lt;p&gt;• /permissions can now be opened while Claude is working — rule changes apply to the rest of the current turn&lt;/p&gt;
&lt;p&gt;• /add-dir &amp;lt;path&amp;gt; can now be used while Claude is working; /add-dir, /autocompact, /theme, /help, /config and /advisor dialogs open mid-turn in the fullscreen TUI&lt;/p&gt;
&lt;p&gt;• /goal now clears itself with a notice when a turn dies on an unrecoverable error (e.g. revoked auth, an exhausted credit balance, or a context overflow) instead of staying armed&lt;/p&gt;
&lt;p&gt;• /goal: when background tasks keep a goal waiting for 30+ minutes, Claude now checks in on them instead of waiting indefinitely (set CLAUDE_CODE_GOAL_CHECKIN_MINUTES=0 to opt out)&lt;/p&gt;
&lt;p&gt;• claude setup-token now rejects unexpected extra arguments instead of silently ignoring them&lt;/p&gt;
&lt;p&gt;• Changed Esc in fullscreen mode to no longer clear a mouse text selection: it interrupts or dismisses as usual and the selection stays highlighted&lt;/p&gt;
&lt;p&gt;• Removed the redundant "Allowed by auto mode classifier" line that auto mode showed under every Agent tool call&lt;/p&gt;
&lt;p&gt;• Removed the "Default teammate model" setting from /config; agent-team teammates now use the leader's model unless the spawn names one&lt;/p&gt;
&lt;p&gt;• Dimmed the elapsed-time counter on the running tool header so it no longer competes with the bold counts&lt;/p&gt;
&lt;p&gt;• Background task notifications delivered between turns are now sent to the model inside &amp;lt;system-reminder&amp;gt; tags, matching mid-turn delivery&lt;/p&gt;
&lt;p&gt;• Mantle: skip the admin-pin availability probe at startup when a main-loop model is already picked&lt;/p&gt;
&lt;p&gt;• Windows: startup no longer stalls on repeated rename retries when ~/.claude.json is read-only&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.233</id>
    <title>Claude Code v2.1.233</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.233"/>
    <updated>2026-08-14T22:20:50Z</updated>
    <content type="html">&lt;p&gt;• Added GitLab merge request URL support to the --worktree flag and the claude agents view (where MRs display as !N)&lt;/p&gt;
&lt;p&gt;• Added an opt-in forward_user_identity apps gateway setting on Anthropic upstreams that sends the signed-in user's identity as headers, so a proxy behind the gateway can attribute spend per user&lt;/p&gt;
&lt;p&gt;• Added opt-in memory cgroup support for Bash tool commands on Linux (CLAUDE_CODE_TOOL_MEMORY_LIMIT) so a runaway build can't stall the session&lt;/p&gt;
&lt;p&gt;• Added CLAUDE_CODE_WEBFETCH_CACHE_TTL_MS environment variable to configure the WebFetch session URL cache TTL (default unchanged: 15 minutes)&lt;/p&gt;
&lt;p&gt;• Fixed cloud sessions occasionally being marked as lost when the environment shut down while Claude was waiting on a permission prompt&lt;/p&gt;
&lt;p&gt;• Fixed MCP v2 connections endlessly reopening the subscriptions/listen stream against servers that terminate long-held streams on a fixed timeout (e.g. serverless hosts)&lt;/p&gt;
&lt;p&gt;• Fixed Notification hooks not firing for permission prompts when running under Claude Desktop or VS Code&lt;/p&gt;
&lt;p&gt;• Fixed idle sessions on Linux sometimes keeping one CPU core at 100% when sandboxing is enabled&lt;/p&gt;
&lt;p&gt;• Fixed bundled skill aliases like /checkup and /review reporting "Unknown command" in -p mode or with plugins/MCP loaded when a user or project skill shadows the bundled skill&lt;/p&gt;
&lt;p&gt;• Fixed skill/command argument substitution to prevent argument values from being re-expanded as template markers&lt;/p&gt;
&lt;p&gt;• Fixed Windows paths spelled with the NT \??\ device prefix bypassing UNC path validation, closing an NTLM credential-leak vector&lt;/p&gt;
&lt;p&gt;• Improved claude self-hosted-runner session start time: the session branch is now created without rewriting the working tree, and two server round trips no longer block the agent's launch&lt;/p&gt;
&lt;p&gt;• Improved apps gateway error forwarding: 400/413 errors from Vertex, Foundry, and Claude Platform on AWS upstreams now carry the upstream's own message; fixes a bug with auto-compact on apps gateway&lt;/p&gt;
&lt;p&gt;• Improved claude plugin validate to check a bare .claude/skills directory, reporting SKILL.md files whose frontmatter fails to parse&lt;/p&gt;
&lt;p&gt;• Improved screen reader mode: the /effort selector renders as a numbered list with a typed-number prompt, and hint and dialog text is no longer clipped&lt;/p&gt;
&lt;p&gt;• Improved print mode diagnostics: a [claude-code:unrecognized_model] line is written to stderr when a request goes out for a model ID Claude Code doesn't recognize; map it with modelOverrides to silence&lt;/p&gt;
&lt;p&gt;• Changed the GitHub app setup tip to no longer appear in repositories whose origin remote is on gitlab.com or bitbucket.org; the enterprise marketplace tip now covers non-GitHub internal git hosts&lt;/p&gt;
&lt;p&gt;• Todo/task-tracking tools (TaskCreate/Get/Update/List, TodoWrite) are no longer available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, and newer models; set CLAUDE_CODE_ENABLE_TODO_TOOLS=1 to bring them back&lt;/p&gt;
&lt;p&gt;• Windows: fixed auto mode repeatedly stopping for manual approval on ordinary cd &amp;lt;dir&amp;gt; &amp;amp;&amp;amp; &amp;lt;command&amp;gt; &amp;gt; file Bash commands (a 2.1.232 regression)&lt;/p&gt;
&lt;p&gt;• Reverted the 2.1.232 Bash permission changes for Cygwin-style symlinks on Windows and for input redirections (&amp;lt; file); a narrower version will return in a later release&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.232</id>
    <title>Claude Code v2.1.232</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.232"/>
    <updated>2026-08-13T23:29:53Z</updated>
    <content type="html">&lt;p&gt;• Subagent forking is now on by default: a subagent_type: "fork" subagent inherits the full conversation and prompt cache, and non-teammate agent spawns in interactive sessions now run in the background by default&lt;/p&gt;
&lt;p&gt;• Type @ in the prompt to mention another Claude session by name; Claude then uses SendMessage to reach that session directly&lt;/p&gt;
&lt;p&gt;• SendMessage now delivers to a bare name that exactly matches one live session, instead of asking to confirm with a ref first&lt;/p&gt;
&lt;p&gt;• Interactive sessions on one machine now keep unique names: starting or renaming a session to a name another live session already uses gives it a name-word-word variant and tells you&lt;/p&gt;
&lt;p&gt;• Added /config rows for "Dialog expiry" and "Messages from your other sessions" (cross-session inbound accept/hold/refuse)&lt;/p&gt;
&lt;p&gt;• Added secret redaction for GitLab token families (glrt-, gloas-, glptt-, glagent-, glimt-, glsoat-, glcbt-, glft-, glffct-) and full redaction of routable glpat-/gldt- tokens; the glab CLI config store gets the same sandbox and credential-path protection as gh&lt;/p&gt;
&lt;p&gt;• Added GitLab support to plugin marketplaces: bare gitlab.com repo URLs (including nested subgroups) now clone like github.com URLs, and clone auth-failure hints name your actual git host&lt;/p&gt;
&lt;p&gt;• Settings: additionalMarketplaces and allowedMarketplaces are now accepted as friendlier aliases for extraKnownMarketplaces and strictKnownMarketplaces&lt;/p&gt;
&lt;p&gt;• Enterprise policy: a url-typed blockedMarketplaces entry for a bare repo URL keeps blocking that URL when the CLI classifies it as a git clone&lt;/p&gt;
&lt;p&gt;• Gateway: the desktop: overlay now accepts every released Desktop setting (was 11 hand-listed keys), validated at boot against Desktop's own schema; unknown or invalid keys fail boot&lt;/p&gt;
&lt;p&gt;• Gateway: empty managed.policies[].match.groups/admin.admin_groups entries and malformed email_domain values (empty, or containing @, whitespace, or commas) now fail at boot instead of silently matching no one or granting admin access&lt;/p&gt;
&lt;p&gt;• Fable 5 is offered as an advisor in /advisor again for organizations with Fable access, with usage-credits consent set up through /model fable&lt;/p&gt;
&lt;p&gt;• Fixed a PowerShell permission bypass where variable-writing parameters could silently overwrite $PSDefaultParameterValues and redirect later commands' file access&lt;/p&gt;
&lt;p&gt;• Fixed a Windows permission bypass where Git Bash followed Cygwin-style symlinks that path validation saw as regular files; writes through them now require permission approval&lt;/p&gt;
&lt;p&gt;• Fixed nested git repositories inheriting trust from a parent directory; each repository now requires its own trust confirmation&lt;/p&gt;
&lt;p&gt;• Fixed MCP connections hanging for the full 30-second connect timeout when a server fails to answer or sends a malformed reply to the protocol-version probe&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control sessions hosted by a bridge inside a cloud session inheriting that session's transcript or credentials&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control sessions started from Claude Desktop or an IDE appearing as a new claude.ai session each time the local session was resumed; they now reattach to the existing one&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control sessions appearing unreachable to newly attached clients while idle&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control bridge sessions not restoring conversation history when the session worker restarts&lt;/p&gt;
&lt;p&gt;• Remote Control: resuming a conversation whose session was deleted from claude.ai or the app now starts a replacement instead of failing with a message about your login (regressed in v2.1.227)&lt;/p&gt;
&lt;p&gt;• Fixed Cloud gateway /login exiting silently or leaving an unresponsive terminal after "Press Enter to continue" when managed settings failed to load; the reason is now shown&lt;/p&gt;
&lt;p&gt;• Fixed voice mode on native builds getting stuck on "listening…" when the voice service rejected the connection; the rejection is now shown immediately&lt;/p&gt;
&lt;p&gt;• Fixed mTLS client certificate rotation requiring a restart; Claude Code now reloads the rotated cert and key automatically on connection errors&lt;/p&gt;
&lt;p&gt;• Fixed malformed AWS or Vertex region values being used to build request URLs; they now fall back to the default region&lt;/p&gt;
&lt;p&gt;• Fixed stream idle timeout errors failing the request instead of recovering on Bedrock, Vertex, and gateway deployments&lt;/p&gt;
&lt;p&gt;• Fixed content-sized overlays containing truncated text rendering one column too wide, and start-truncated text collapsing to an ellipsis&lt;/p&gt;
&lt;p&gt;• Fixed a stray garbled character where a long shell-command or agent-description preview was cut off mid-emoji&lt;/p&gt;
&lt;p&gt;• Fixed a startup race that could silently unregister a plugin marketplace due to concurrent writes to known_marketplaces.json&lt;/p&gt;
&lt;p&gt;• Fixed /update and /tui refusing to restart while work that survives the relaunch was running&lt;/p&gt;
&lt;p&gt;• Fixed usage-limit guidance suggesting unavailable slash commands in SDK and remote sessions&lt;/p&gt;
&lt;p&gt;• Fixed the consent message for interactive --advisor fable launches, which told you to run /model fable in an interactive session that had just exited&lt;/p&gt;
&lt;p&gt;• Improved fullscreen streaming: long sessions stay responsive because the whole conversation is no longer re-normalized on every update&lt;/p&gt;
&lt;p&gt;• Improved the managed settings approval dialog: shows endpoint URLs, uses clearer wording for telemetry-only changes, skips routine OpenTelemetry options, and requires approval for server-managed sandbox binary overrides (sandbox.bwrapPath, sandbox.socatPath, sandbox.ripgrep)&lt;/p&gt;
&lt;p&gt;• /feedback and /bug now open immediately when invoked while Claude is responding, instead of waiting for the turn to finish&lt;/p&gt;
&lt;p&gt;• /plugin install plugin@marketplace now refreshes the marketplace first, so newly published plugins install without a manual marketplace update&lt;/p&gt;
&lt;p&gt;• /code-review at high, xhigh, and max effort now runs in a background agent like the other levels&lt;/p&gt;
&lt;p&gt;• Pasted and clipboard images are read without blocking the event loop&lt;/p&gt;
&lt;p&gt;• Remote Control now keeps reconnecting for about 30 minutes after a network blip and no longer drops after a few blips spread across an hour&lt;/p&gt;
&lt;p&gt;• Remote Control: resuming a conversation no longer silently takes Remote Control away from another Claude Code on the same machine that still has it; run /remote-control there to move it&lt;/p&gt;
&lt;p&gt;• Updated agent panel: completed subagents hide immediately with a /tasks footer hint, and the "↓ N more" overflow indicator moved left for visibility&lt;/p&gt;
&lt;p&gt;• Remote Control: the terminal now says whether a session was taken over by another device, ended from another app, or deleted, and stops suggesting a reconnect that would undo it&lt;/p&gt;
&lt;p&gt;• Bash input redirections (&amp;lt; file) are now permission-checked like their argument spellings on all platforms&lt;/p&gt;
&lt;p&gt;• Shortened the message shown when resuming a completed background agent&lt;/p&gt;
&lt;p&gt;• Cowork sessions no longer inline external @-imports from user-scope memory files&lt;/p&gt;
&lt;p&gt;• Hardened the auto-generated cross-session messaging socket directory on shared /tmp: a pre-planted symlink or another user's directory is now refused instead of used&lt;/p&gt;
&lt;p&gt;• Hardened the Linux filesystem sandbox against a protected-path bypass&lt;/p&gt;
&lt;p&gt;• Changed sandbox.ripgrep to be honored only from user, managed, and --settings settings; project settings can no longer override the sandbox's ripgrep binary&lt;/p&gt;
&lt;p&gt;• Removed the startup tip suggesting you create custom subagents, and the matching nudge in the /powerup tour&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.231</id>
    <title>Claude Code v2.1.231</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.231"/>
    <updated>2026-08-13T08:38:44Z</updated>
    <content type="html">&lt;p&gt;• Fixed MCP OAuth sign-in failing with a redirect URI mismatch for servers that use a pre-registered OAuth client, such as Slack&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.229</id>
    <title>Claude Code v2.1.229</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.229"/>
    <updated>2026-08-12T20:56:14Z</updated>
    <content type="html">&lt;p&gt;• Documented claude remote-control --continue for resuming the most recent Remote Control session&lt;/p&gt;
&lt;p&gt;• Added server-supplied Claude Code hook support for self-hosted runner sessions, matching managed-environment behavior&lt;/p&gt;
&lt;p&gt;• Added SSE keepalive pings to gateway streaming responses during long thinking pauses, preventing idle-timeout disconnects on Vertex and Bedrock upstreams&lt;/p&gt;
&lt;p&gt;• Added plugin marketplace command sources: a local command (e.g. an IDE) prints the plugin directory, which is re-resolved each session and applied without a restart; mode: "link" uses it in place&lt;/p&gt;
&lt;p&gt;• ListAgents now marks disconnected Remote Control sessions as offline and labels your cloud sessions as cloud&lt;/p&gt;
&lt;p&gt;• Fixed long responses partly disappearing while streaming and being printed twice in the terminal&lt;/p&gt;
&lt;p&gt;• Fixed a crash to the error screen (including on --resume of the affected session) when a tool call had a non-string glob, file_path, or command value&lt;/p&gt;
&lt;p&gt;• Fixed a RangeError crash when a progress bar or markdown table rendered in a very narrow terminal window (could also crash claude --continue/--resume at startup)&lt;/p&gt;
&lt;p&gt;• Fixed a crash on Windows when a tool call or message referenced a file by an extended-length (\\?\) or UNC path&lt;/p&gt;
&lt;p&gt;• Fixed auto mode failing on every tool call for users who disable the attribution header via CLAUDE_CODE_ATTRIBUTION_HEADER (direct Anthropic API connections)&lt;/p&gt;
&lt;p&gt;• Fixed /model rejecting Sonnet/Opus 1M for claude.ai subscribers using a custom ANTHROPIC_BASE_URL gateway&lt;/p&gt;
&lt;p&gt;• Fixed MCP OAuth with strict authorization servers by using 127.0.0.1 instead of localhost in the redirect URI&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control clients showing a stuck working spinner after a slash command typed in the laptop terminal&lt;/p&gt;
&lt;p&gt;• Fixed the Claude Code Review workflow generated by /install-github-app completing without posting its review on the pull request&lt;/p&gt;
&lt;p&gt;• Fixed multi-second UI stalls after editing a file with thousands of IDE diagnostics while the IDE extension is connected&lt;/p&gt;
&lt;p&gt;• Fixed one-shot claude plugin commands leaving a stray liveness file that could prevent cleanup of outdated plugin versions&lt;/p&gt;
&lt;p&gt;• Fixed dynamic workflows inside CPU-limited containers using the host machine's core count instead of the container's CPU limit&lt;/p&gt;
&lt;p&gt;• Fixed a file-watcher handle leak after atomic file replacements, and an uncaught error on Windows when the scheduled-tasks watcher failed on a network or virtual filesystem&lt;/p&gt;
&lt;p&gt;• Fixed SDK and --input-format stream-json sessions getting a 400 API error when a whitespace-only message was submitted&lt;/p&gt;
&lt;p&gt;• Fixed conversations whose messages alone exceed the API's 32 MB request limit retrying compaction when no images or documents can be stripped; they now fail once with a clear message&lt;/p&gt;
&lt;p&gt;• Fixed OpenTelemetry export from Claude Desktop sessions being rejected by the Desktop-managed gateway when that gateway is also the telemetry endpoint&lt;/p&gt;
&lt;p&gt;• Fixed self-hosted runner and other remote sessions exiting at startup when managed-mcp.json is deployed and the server delivers MCP servers; those servers are now skipped with a warning&lt;/p&gt;
&lt;p&gt;• Fixed self-hosted runner repository preparation hanging on a Git Credential Manager prompt; git now fails fast when credentials are missing&lt;/p&gt;
&lt;p&gt;• Improved workflow fan-outs to stagger same-prefix sibling agents so subsequent agents read the cached prompt prefix instead of re-paying it (CLAUDE_CODE_WORKFLOW_PREFIX_STAGGER_MS=0 disables)&lt;/p&gt;
&lt;p&gt;• Improved "prompt is too long" errors to explain why automatic compaction could not recover instead of only suggesting /compact&lt;/p&gt;
&lt;p&gt;• Improved sandbox: IPv6 literals in network domain lists are now bracketed ([::1]:443), and ambiguous spellings are enforced fail-closed and flagged by /doctor&lt;/p&gt;
&lt;p&gt;• Updated /login to repeat the CLAUDE_CODE_OAUTH_TOKEN override warning after a successful login&lt;/p&gt;
&lt;p&gt;• Changed /commit-push-pr so git/gh commands with dangerous flags (--force, --amend, --no-verify, etc.) are no longer auto-approved&lt;/p&gt;
&lt;p&gt;• Changed self-hosted runner Windows startup to require an explicit --base-dir; there is no default checkout directory on Windows&lt;/p&gt;
&lt;p&gt;• [VSCode] "Report a problem" and /bug now open the built-in feedback dialog instead of a retired survey link&lt;/p&gt;
&lt;p&gt;• [VSCode] Made the /btw side-question panel resizable by dragging its boundary, in both side-docked and stacked layouts&lt;/p&gt;
&lt;p&gt;• [VSCode] Added session groups in the sidebar — right-click to create, rename, or delete; Cmd/Ctrl- or Shift-click to move several sessions at once&lt;/p&gt;</content>
  </entry>
  <entry>
    <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.228</id>
    <title>Claude Code v2.1.228</title>
    <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.228"/>
    <updated>2026-08-11T19:50:50Z</updated>
    <content type="html">&lt;p&gt;• Fixed interactive sessions that could stop redrawing entirely, while the process kept running, after a rare internal layout error&lt;/p&gt;
&lt;p&gt;• Fixed git / Git Bash not being found on Windows when Claude Code is launched from a parent folder of the git installation&lt;/p&gt;
&lt;p&gt;• Fixed /tui reverting the session to an earlier model when /model had been changed since the last response&lt;/p&gt;
&lt;p&gt;• Fixed cross-session messaging sometimes starting without an inbox in the first session after install or upgrade&lt;/p&gt;
&lt;p&gt;• Fixed Remote Control /resume while connected leaking the resumed conversation's title or history into the connected session&lt;/p&gt;
&lt;p&gt;• Fixed claude self-hosted-runner sessions failing on every fresh runner when the checkout hook fails for a repository the session doesn't push to; that repository is now skipped with a warning&lt;/p&gt;
&lt;p&gt;• Fixed self-hosted runners ending sessions in the gap between a background task finishing and the follow-up turn starting&lt;/p&gt;
&lt;p&gt;• Fixed session cleanup deleting contents inside a project's memory folder&lt;/p&gt;
&lt;p&gt;• Fixed background plugin-cache cleanup deleting a plugin's cache when its only version is a symlinked development checkout&lt;/p&gt;
&lt;p&gt;• Fixed a settings-merge issue where a marketplace entry redefined in a higher-precedence settings tier could inherit another tier's custom headers; marketplace entries now merge as whole entries&lt;/p&gt;
&lt;p&gt;• Fixed the deferred-tools reminder occasionally being sent to the model twice after a skill invocation&lt;/p&gt;
&lt;p&gt;• Hardened skills synced from claude.ai: they no longer shadow local commands or MCP prompts, their descriptions are sanitized and labeled, and on your machine their bodies don't run ! commands or expand @ files&lt;/p&gt;
&lt;p&gt;• Improved cross-session messages: the sender and body now display inline instead of a collapsed line, and messages to Remote Control sessions on other machines show your Remote Control session name as the sender&lt;/p&gt;
&lt;p&gt;• Improved Vertex AI credential handling: expired or missing Google Cloud credentials now fail within seconds instead of retrying for minutes&lt;/p&gt;
&lt;p&gt;• Improved compaction progress: the retry countdown and stall hint now appear during compaction instead of only a progress bar&lt;/p&gt;
&lt;p&gt;• Updated terminal title busy-spinner glyphs to reduce tab-bar jitter on some terminals&lt;/p&gt;
&lt;p&gt;• Changed the Write tool so newer models can overwrite an existing file they haven't read this session, matching the Edit tool's rules; older models still require the read first&lt;/p&gt;
&lt;p&gt;• Removed the outdated note about auto mode sessions costing slightly more from the first-use notice for Pro, Max, and Team plans&lt;/p&gt;</content>
  </entry>
</feed>