Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
TypeScript
chore: Update CHANGELOG.md and feed.xml
GitHub Actionsfbe20e00e285
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 20657faf..a4eabcee 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -1,5 +1,100 @@# Changelog+## 2.1.292++- Added `--marketplace <source>` to `claude plugin install`: adds the marketplace if needed, under the same policy checks as `claude plugin marketplace add`, then installs the plugin from it+- Added an `effort` parameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask for+- Added `CLAUDE_CODE_OVERLOADED_RETRY_BASE_DELAY_MS` environment variable to set a longer base delay for the backoff when retrying an overloaded (529) request+- Added `prompt.autocomplete`, an event a mod hooks to add its own rows to the prompt box's autocomplete list+- Added prompt caching to `$.model.complete` for mods: `prompt` and `system` take blocks of text, and `cache: true` on a block caches the request up to it+- Added workflow agents to the `agent.spawn` mod hook, with their run and index, so a mod can refuse them+- Fixed subagent definitions with `permissionMode: auto` entering auto mode when auto mode is unavailable (disabled by settings, circuit breaker, or a model that doesn't support it)+- Fixed sandboxed commands being able to read the staged file copies of `/ultrareview` uploads under `~/.claude/seed-admin`+- Fixed a managed sandbox read-deny path (and user ones beside it) that appears or re-points mid-session not dropping project grants inside it or ending credential injection from files it covers+- Fixed a notebook or PDF read on macOS and Windows being able to return a file outside what was approved, through a link swapped in mid-read+- Fixed a tampered on-disk cache of server-managed settings being able to switch off or unseat the built-in policy plugin while the settings fetch failed+- Fixed `rm -rf` on the 8.3 short name or another alternate Windows spelling of the home folder or a drive not being treated as removing it+- Security: Fixed PreToolUse hook approvals and auto mode bypassing the permission prompt for file reads from network (UNC) paths+- Fixed a skill's or slash command's `allowed-tools` rule coming back in a later turn when you leave auto mode or plan mode partway through that turn+- Fixed `NO_PROXY` being ignored for Claude Code's own API requests (sign-in, policy, feedback, artifacts) when `HTTPS_PROXY` is set+- Fixed an MCP tool with a name longer than 128 characters making every request fail; that tool is now left out and an MCP error names it+- Fixed `claude plugin` commands such as `marketplace add` and `install` running before an organization's managed settings had loaded on a first run+- Fixed one-shot `claude -p` and Agent SDK runs stopping a background command 5 seconds after the final result, and one-shot `claude -p` runs dropping a scheduled wakeup; both are now waited for+- Fixed plan mode not being restored when resuming a session from the `claude --resume` session picker or with `/resume`+- Fixed saved scheduled tasks created after `/resume`, `/branch` or `/clear` never firing, and saved tasks ignoring later creates and deletes after two writes to the tasks file milliseconds apart+- Fixed a background session's `/loop` silently stopping when the session's process restarted (for example after a crash), because its pending wakeup was lost+- Fixed Grep and Glob reporting no matches when the file or folder they were given could not be read; Claude now retries once or tells you+- Fixed the Read tool returning only the first entry, with no error, when a PDF's `pages` was a list such as "6,9,15"; it now returns an error saying to read each page or range separately+- Fixed @-mentioned text files over 256KB being left out silently: Claude is now told the file's size and to read it in portions+- Fixed the usage limit alert repeating once per background agent when agents failed on a limit that had already stopped the main conversation+- Fixed Remote Control viewers seeing an empty subagent pane for background subagents in sessions hosted by the desktop app or an IDE+- Fixed cross-session delivery notices showing two sessions with similar names as one recipient, and the expiry notice blaming the desktop app when a terminal session let the message lapse+- Fixed Send now in the desktop app ending the subagent a turn was waiting on when another message was already queued+- Fixed `/bug`, `/share` and `/feedback <text>` starting over after Ctrl+O or Ctrl+Z while a report was being sent, and closing as cancelled after it had been sent+- Fixed `/remote-env` replacing your saved default environment when you pressed Enter right away: the list now opens on your default, and no row has a check mark when no default is in effect+- Fixed some pasted text reaching Claude as typed text when several pastes overlapped in one prompt+- Fixed vim mode leaving the cursor past the end of a line, j/k losing their column on shorter lines, and `f`/`t`/`F`/`T`/`;`/`,` jumping to, or deleting up to, a match on another line of the prompt+- Fixed `/add-dir` path box letting Shift+Enter or a paste add a line break, and treating fast-typed "tab", "up" or "down" as those keys+- Fixed fast typing, input-method text and decomposed accents being dropped while a prompt footer row was selected, and `!` leaving the row selected+- Fixed fullscreen mode sending a full-screen clear on every window resize and Ctrl+L when iTerm2 is detected, which may be what filled iTerm2's scrollback with stale pages+- Fixed a spurious "could not be examined" note for @-words that name no file when a Read deny rule is set and the working directory is under a symlink+- Fixed "instruction file not loaded" lines going stale or missing after `/cd` or a permission change, and added a transcript line when a nested one isn't loaded+- Fixed a compaction summary that repeated `/name` letting Claude invoke a skill that is reserved for the user+- Fixed Write, Edit, NotebookEdit and LSP rows, and single Read, Grep and Glob rows, hiding why a mod denied the call: the row now shows the reason+- Fixed a cloud session showing a turn that never ended when its worker was stopped just as the turn finished+- Fixed cloud sessions with a large transcript sometimes asking for a permission again after it was approved+- Fixed scheduled tasks and other queued notifications being lost in cloud sessions when a message was retried or edited while Claude was reading them+- Fixed cloud sessions forgetting the thinking setting chosen in the client when the session's container restarted+- Fixed Cowork cloud sessions saying a proxy blocked artifacts when Anthropic couldn't confirm the organization's settings+- Fixed plugins whose hooks module makes many `$.state` calls through one const taking minutes to load or validate+- Fixed `claude plugin validate` listing a matcher or state value for a hooks module that the engine reads from elsewhere+- Fixed `claude plugin validate` listing a `$.state` value read through a top-level `var` that was declared again or reassigned; such a module is now refused+- Fixed a plugin's served `$` method restarting the hook origin, which could run a guard hook with a `.catch` above it again without end+- Fixed plugin interface calls made while the plugin hooks worker restarts running without the hooks other plugins put on them+- Fixed a mod's `config.set`, `state.set`, `env.set` or `agent.spawn` hook that denies after calling `next(e)` being answered as a refusal: the hook is now reported as failed, by name+- Fixed `/theme`, the `/config` Theme menu and the first-run theme step saving a theme before a plugin's `config.set` hook was asked+- Fixed a plugin's `tool.check` hook answering allow running a tool that requires your answer (a question, a plan approval) without showing its dialog+- Fixed a mod's start-up prompt, command or subagent being queued a second time when the hooks worker was replaced+- Fixed a mod's hook that called `next(e)` and then failed while the turn was interrupted letting the call through; the call is now rejected+- Fixed a plugin's prompt drop or setting deny being ignored when its reason was longer than 4,096 characters+- Fixed an organization's plugin being unloaded on its own reload, or after another plugin crashed, when it returned a `$` name that a user-installed mod had added; the mod is now unloaded instead+- Fixed tool calls made while the plugin hooks worker restarts being answered without the plugins' permission hooks+- Fixed plugin `tool.call` hooks seeing some tool calls before misnamed parameters were repaired; a hook now sees the arguments the tool will run with+- Fixed a mod's guard hook with a `.catch` being skipped silently for calls another mod's hook makes beneath the guard's own `$` call; its `.catch` is now asked+- Improved startup of `claude -p` and SDK sessions: the first turn no longer waits for HTTP and SSE MCP servers to answer `resources/list`+- Improved rendering speed of long bulleted or numbered replies: they stream, resize and re-open in the transcript (ctrl+o) much faster+- Improved Ctrl+C draft recovery: a cleared prompt now stays reachable with Up after a slash command or a sent message+- Improved hook output handling: `<system-reminder>` tags written in a hook's output are escaped before they reach Claude+- Improved tool input handling: Grep accepts `file_path` for `path`, and Write, WebFetch and Read ignore a few stray parameters instead of failing the call+- Improved the steps shown when a marketplace declared in a settings file has a name that looks like an official Anthropic marketplace+- Improved sandbox auto-allow: with strict sandbox mode set in user, managed or --settings settings, an interpreter command with an env var prefix like `FOO=bar python3 app.py` runs unprompted+- Improved the Artifact tool's listing: Claude now sees how many published artifacts you have and can list up to 200 at once instead of 50+- Improved cloud sessions after a restart: Claude is now told which stopped background agents it can resume by id+- Improved the Claude in Chrome message in claude.ai cloud sessions when the browser can't be reached: Claude is now told it may continue with alternatives if the user prefers+- Improved the /focus tip: it now invites you to try focus view mid-turn and shows how to switch back+- Improved startup with local (stdio) MCP servers that ignore the newer protocol check: after one slow connect they are remembered for 7 days and connected the older way without the wait+- Changed local (stdio) MCP server connections to negotiate protocol version 2026-07-28 by default on every install, including Bedrock, Vertex and Foundry; `MCP_PROTOCOL_NEGOTIATION=legacy` opts out+- Changed `claude plugin test`: a failed `expect` inside a hook the test registered, or a stub answer the engine refuses, now fails the test instead of passing silently+- Changed usage limit messages to write claude.ai settings links with https:// so terminals and apps can make them clickable+- Changed scheduled and Run now routine runs to publish a new artifact only you can see without asking for approval; artifacts that request connectors or other access still ask+- Changed agent names to allow at most 256 characters: a longer one is rejected, and a skill's or a plugin file's `name` longer than that is ignored+- [Cloud sessions] Fixed routine runs occasionally staying listed as running for hours after they had finished+- [Cloud sessions] Fixed editing or duplicating a routine turning off its push notifications when the routine had no saved notification setting+- [Cloud sessions] Fixed SVG, HEIC, TIFF and other less common image files failing to attach; they now attach as regular files+- [Cloud sessions] Fixed approval prompts offering "Always allow" for connector tools that an organization set to require approval; the choice had no effect+- [Remote Control] Fixed the first message of a new Remote Control session started from claude.ai/code accepting only images; it now accepts PDFs and other files like later messages+- [Claude Tag] Added an Edit button to the Allowed domains card on a channel's Configure page, so Enterprise admins can open the access bundle that sets the channel's domains+- [Claude Tag] Fixed replies sent in a Slack thread while Claude was still on its first request there being held until that request finished, or missed when sent seconds apart+- [Claude Tag] Fixed Slack threads woken only by GitHub pull request activity or a routine staying on their original model after an admin changed the channel or workspace default model+- [Claude Tag] Fixed Claude sometimes posting a spend limit notice in Slack when the real cause was that your organization had run out of usage credits+- [Claude Tag] Fixed a session hanging until interrupted when a permission prompt that can't be answered from Slack was denied automatically+- [Claude Tag] Improved `@Claude !status` in a channel to say when Claude has stopped reading its untagged messages, why, and that an @-mention starts it reading again+- [Claude Tag] Changed the first message of a Slack thread continued with `!fork` to a card showing where it came from, the request, and who asked, with a link to the original thread+- [Claude Tag] Changed the organization-wide and default spend limit boxes on Claude Tag's spend limits page in admin settings to save only when you press Save or Enter, not when you click away+- [Code Review] Added the period's total with its change from the previous period, and a breakdown by repository, to the PRs reviewed chart in Code Review analytics+- [Code Review] Fixed a queued review failing when the pull request moved to a new base branch and the old one was deleted; the commit is now re-queued for review+- [Code Review] Fixed reviews ignoring a CLAUDE.md's rules when the pull request edits that file; reviews now use its version from the base branch+## 2.1.291- Fixed a regression in 2.1.290 where cloud sessions could drop answers to permission promptsdiff --git a/feed.xml b/feed.xmlindex f3109dde..7605967e 100644--- a/feed.xml+++ b/feed.xml@@ -6,7 +6,105 @@<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>2026-10-06T03:54:58Z</updated>+ <updated>2026-10-06T18:59:09Z</updated>+ <entry>+ <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.292</id>+ <title>Claude Code v2.1.292</title>+ <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.292"/>+ <updated>2026-10-06T18:59:09Z</updated>+ <content type="html"><p>• Added --marketplace &lt;source&gt; to claude plugin install: adds the marketplace if needed, under the same policy checks as claude plugin marketplace add, then installs the plugin from it</p>+<p>• Added an effort parameter to the Agent tool, so Claude runs a sub-agent at the effort level you ask for</p>+<p>• Added CLAUDE_CODE_OVERLOADED_RETRY_BASE_DELAY_MS environment variable to set a longer base delay for the backoff when retrying an overloaded (529) request</p>+<p>• Added prompt.autocomplete, an event a mod hooks to add its own rows to the prompt box's autocomplete list</p>+<p>• Added prompt caching to $.model.complete for mods: prompt and system take blocks of text, and cache: true on a block caches the request up to it</p>+<p>• Added workflow agents to the agent.spawn mod hook, with their run and index, so a mod can refuse them</p>+<p>• Fixed subagent definitions with permissionMode: auto entering auto mode when auto mode is unavailable (disabled by settings, circuit breaker, or a model that doesn't support it)</p>+<p>• Fixed sandboxed commands being able to read the staged file copies of /ultrareview uploads under ~/.claude/seed-admin</p>+<p>• Fixed a managed sandbox read-deny path (and user ones beside it) that appears or re-points mid-session not dropping project grants inside it or ending credential injection from files it covers</p>+<p>• Fixed a notebook or PDF read on macOS and Windows being able to return a file outside what was approved, through a link swapped in mid-read</p>+<p>• Fixed a tampered on-disk cache of server-managed settings being able to switch off or unseat the built-in policy plugin while the settings fetch failed</p>+<p>• Fixed rm -rf on the 8.3 short name or another alternate Windows spelling of the home folder or a drive not being treated as removing it</p>+<p>• Security: Fixed PreToolUse hook approvals and auto mode bypassing the permission prompt for file reads from network (UNC) paths</p>+<p>• Fixed a skill's or slash command's allowed-tools rule coming back in a later turn when you leave auto mode or plan mode partway through that turn</p>+<p>• Fixed NO_PROXY being ignored for Claude Code's own API requests (sign-in, policy, feedback, artifacts) when HTTPS_PROXY is set</p>+<p>• Fixed an MCP tool with a name longer than 128 characters making every request fail; that tool is now left out and an MCP error names it</p>+<p>• Fixed claude plugin commands such as marketplace add and install running before an organization's managed settings had loaded on a first run</p>+<p>• Fixed one-shot claude -p and Agent SDK runs stopping a background command 5 seconds after the final result, and one-shot claude -p runs dropping a scheduled wakeup; both are now waited for</p>+<p>• Fixed plan mode not being restored when resuming a session from the claude --resume session picker or with /resume</p>+<p>• Fixed saved scheduled tasks created after /resume, /branch or /clear never firing, and saved tasks ignoring later creates and deletes after two writes to the tasks file milliseconds apart</p>+<p>• Fixed a background session's /loop silently stopping when the session's process restarted (for example after a crash), because its pending wakeup was lost</p>+<p>• Fixed Grep and Glob reporting no matches when the file or folder they were given could not be read; Claude now retries once or tells you</p>+<p>• Fixed the Read tool returning only the first entry, with no error, when a PDF's pages was a list such as "6,9,15"; it now returns an error saying to read each page or range separately</p>+<p>• Fixed @-mentioned text files over 256KB being left out silently: Claude is now told the file's size and to read it in portions</p>+<p>• Fixed the usage limit alert repeating once per background agent when agents failed on a limit that had already stopped the main conversation</p>+<p>• Fixed Remote Control viewers seeing an empty subagent pane for background subagents in sessions hosted by the desktop app or an IDE</p>+<p>• Fixed cross-session delivery notices showing two sessions with similar names as one recipient, and the expiry notice blaming the desktop app when a terminal session let the message lapse</p>+<p>• Fixed Send now in the desktop app ending the subagent a turn was waiting on when another message was already queued</p>+<p>• Fixed /bug, /share and /feedback &lt;text&gt; starting over after Ctrl+O or Ctrl+Z while a report was being sent, and closing as cancelled after it had been sent</p>+<p>• Fixed /remote-env replacing your saved default environment when you pressed Enter right away: the list now opens on your default, and no row has a check mark when no default is in effect</p>+<p>• Fixed some pasted text reaching Claude as typed text when several pastes overlapped in one prompt</p>+<p>• Fixed vim mode leaving the cursor past the end of a line, j/k losing their column on shorter lines, and f/t/F/T/;/, jumping to, or deleting up to, a match on another line of the prompt</p>+<p>• Fixed /add-dir path box letting Shift+Enter or a paste add a line break, and treating fast-typed "tab", "up" or "down" as those keys</p>+<p>• Fixed fast typing, input-method text and decomposed accents being dropped while a prompt footer row was selected, and ! leaving the row selected</p>+<p>• Fixed fullscreen mode sending a full-screen clear on every window resize and Ctrl+L when iTerm2 is detected, which may be what filled iTerm2's scrollback with stale pages</p>+<p>• Fixed a spurious "could not be examined" note for @-words that name no file when a Read deny rule is set and the working directory is under a symlink</p>+<p>• Fixed "instruction file not loaded" lines going stale or missing after /cd or a permission change, and added a transcript line when a nested one isn't loaded</p>+<p>• Fixed a compaction summary that repeated /name letting Claude invoke a skill that is reserved for the user</p>+<p>• Fixed Write, Edit, NotebookEdit and LSP rows, and single Read, Grep and Glob rows, hiding why a mod denied the call: the row now shows the reason</p>+<p>• Fixed a cloud session showing a turn that never ended when its worker was stopped just as the turn finished</p>+<p>• Fixed cloud sessions with a large transcript sometimes asking for a permission again after it was approved</p>+<p>• Fixed scheduled tasks and other queued notifications being lost in cloud sessions when a message was retried or edited while Claude was reading them</p>+<p>• Fixed cloud sessions forgetting the thinking setting chosen in the client when the session's container restarted</p>+<p>• Fixed Cowork cloud sessions saying a proxy blocked artifacts when Anthropic couldn't confirm the organization's settings</p>+<p>• Fixed plugins whose hooks module makes many $.state calls through one const taking minutes to load or validate</p>+<p>• Fixed claude plugin validate listing a matcher or state value for a hooks module that the engine reads from elsewhere</p>+<p>• Fixed claude plugin validate listing a $.state value read through a top-level var that was declared again or reassigned; such a module is now refused</p>+<p>• Fixed a plugin's served $ method restarting the hook origin, which could run a guard hook with a .catch above it again without end</p>+<p>• Fixed plugin interface calls made while the plugin hooks worker restarts running without the hooks other plugins put on them</p>+<p>• Fixed a mod's config.set, state.set, env.set or agent.spawn hook that denies after calling next(e) being answered as a refusal: the hook is now reported as failed, by name</p>+<p>• Fixed /theme, the /config Theme menu and the first-run theme step saving a theme before a plugin's config.set hook was asked</p>+<p>• Fixed a plugin's tool.check hook answering allow running a tool that requires your answer (a question, a plan approval) without showing its dialog</p>+<p>• Fixed a mod's start-up prompt, command or subagent being queued a second time when the hooks worker was replaced</p>+<p>• Fixed a mod's hook that called next(e) and then failed while the turn was interrupted letting the call through; the call is now rejected</p>+<p>• Fixed a plugin's prompt drop or setting deny being ignored when its reason was longer than 4,096 characters</p>+<p>• Fixed an organization's plugin being unloaded on its own reload, or after another plugin crashed, when it returned a $ name that a user-installed mod had added; the mod is now unloaded instead</p>+<p>• Fixed tool calls made while the plugin hooks worker restarts being answered without the plugins' permission hooks</p>+<p>• Fixed plugin tool.call hooks seeing some tool calls before misnamed parameters were repaired; a hook now sees the arguments the tool will run with</p>+<p>• Fixed a mod's guard hook with a .catch being skipped silently for calls another mod's hook makes beneath the guard's own $ call; its .catch is now asked</p>+<p>• Improved startup of claude -p and SDK sessions: the first turn no longer waits for HTTP and SSE MCP servers to answer resources/list</p>+<p>• Improved rendering speed of long bulleted or numbered replies: they stream, resize and re-open in the transcript (ctrl+o) much faster</p>+<p>• Improved Ctrl+C draft recovery: a cleared prompt now stays reachable with Up after a slash command or a sent message</p>+<p>• Improved hook output handling: &lt;system-reminder&gt; tags written in a hook's output are escaped before they reach Claude</p>+<p>• Improved tool input handling: Grep accepts file_path for path, and Write, WebFetch and Read ignore a few stray parameters instead of failing the call</p>+<p>• Improved the steps shown when a marketplace declared in a settings file has a name that looks like an official Anthropic marketplace</p>+<p>• Improved sandbox auto-allow: with strict sandbox mode set in user, managed or --settings settings, an interpreter command with an env var prefix like FOO=bar python3 app.py runs unprompted</p>+<p>• Improved the Artifact tool's listing: Claude now sees how many published artifacts you have and can list up to 200 at once instead of 50</p>+<p>• Improved cloud sessions after a restart: Claude is now told which stopped background agents it can resume by id</p>+<p>• Improved the Claude in Chrome message in claude.ai cloud sessions when the browser can't be reached: Claude is now told it may continue with alternatives if the user prefers</p>+<p>• Improved the /focus tip: it now invites you to try focus view mid-turn and shows how to switch back</p>+<p>• Improved startup with local (stdio) MCP servers that ignore the newer protocol check: after one slow connect they are remembered for 7 days and connected the older way without the wait</p>+<p>• Changed local (stdio) MCP server connections to negotiate protocol version 2026-07-28 by default on every install, including Bedrock, Vertex and Foundry; MCP_PROTOCOL_NEGOTIATION=legacy opts out</p>+<p>• Changed claude plugin test: a failed expect inside a hook the test registered, or a stub answer the engine refuses, now fails the test instead of passing silently</p>+<p>• Changed usage limit messages to write claude.ai settings links with https:// so terminals and apps can make them clickable</p>+<p>• Changed scheduled and Run now routine runs to publish a new artifact only you can see without asking for approval; artifacts that request connectors or other access still ask</p>+<p>• Changed agent names to allow at most 256 characters: a longer one is rejected, and a skill's or a plugin file's name longer than that is ignored</p>+<p>• [Cloud sessions] Fixed routine runs occasionally staying listed as running for hours after they had finished</p>+<p>• [Cloud sessions] Fixed editing or duplicating a routine turning off its push notifications when the routine had no saved notification setting</p>+<p>• [Cloud sessions] Fixed SVG, HEIC, TIFF and other less common image files failing to attach; they now attach as regular files</p>+<p>• [Cloud sessions] Fixed approval prompts offering "Always allow" for connector tools that an organization set to require approval; the choice had no effect</p>+<p>• [Remote Control] Fixed the first message of a new Remote Control session started from claude.ai/code accepting only images; it now accepts PDFs and other files like later messages</p>+<p>• [Claude Tag] Added an Edit button to the Allowed domains card on a channel's Configure page, so Enterprise admins can open the access bundle that sets the channel's domains</p>+<p>• [Claude Tag] Fixed replies sent in a Slack thread while Claude was still on its first request there being held until that request finished, or missed when sent seconds apart</p>+<p>• [Claude Tag] Fixed Slack threads woken only by GitHub pull request activity or a routine staying on their original model after an admin changed the channel or workspace default model</p>+<p>• [Claude Tag] Fixed Claude sometimes posting a spend limit notice in Slack when the real cause was that your organization had run out of usage credits</p>+<p>• [Claude Tag] Fixed a session hanging until interrupted when a permission prompt that can't be answered from Slack was denied automatically</p>+<p>• [Claude Tag] Improved @Claude !status in a channel to say when Claude has stopped reading its untagged messages, why, and that an @-mention starts it reading again</p>+<p>• [Claude Tag] Changed the first message of a Slack thread continued with !fork to a card showing where it came from, the request, and who asked, with a link to the original thread</p>+<p>• [Claude Tag] Changed the organization-wide and default spend limit boxes on Claude Tag's spend limits page in admin settings to save only when you press Save or Enter, not when you click away</p>+<p>• [Code Review] Added the period's total with its change from the previous period, and a breakdown by repository, to the PRs reviewed chart in Code Review analytics</p>+<p>• [Code Review] Fixed a queued review failing when the pull request moved to a new base branch and the old one was deleted; the commit is now re-queued for review</p>+<p>• [Code Review] Fixed reviews ignoring a CLAUDE.md's rules when the pull request edits that file; reviews now use its version from the base branch</p></content>+ </entry><entry><id>https://github.com/anthropics/claude-code/releases/tag/v2.1.291</id><title>Claude Code v2.1.291</title>@@ -1688,106 +1786,4 @@<updated>2026-09-15T00:42:19Z</updated><content type="html"><p>• Bug fixes and reliability improvements</p></content></entry>- <entry>- <id>https://github.com/anthropics/claude-code/releases/tag/v2.1.271</id>- <title>Claude Code v2.1.271</title>- <link rel="alternate" type="text/html" href="https://github.com/anthropics/claude-code/releases/tag/v2.1.271"/>- <updated>2026-09-14T22:12:48Z</updated>- <content type="html"><p>• Added fast mode in Claude Code Remote sessions (cloud and self-hosted runners): the host's fast-mode setting or /fast typed in the session applies where your organization allows it</p>-<p>• Added mouse support to the /config panel in fullscreen mode: the wheel scrolls the settings list, a click on a setting's value changes it, and the row under the pointer is highlighted</p>-<p>• Added claude self-hosted-runner --drain-marker-file &lt;path&gt;: when that file exists at a SIGTERM drain, the runner reports its exit to the server as a host drain (telemetry only)</p>-<p>• Added per-command allowed_domains to Bash, PowerShell and Monitor in auto mode with sandboxing: the hosts a command needs are reviewed with it and opened for it alone; other hosts are refused</p>-<p>• Added omitClaudeMd to agent frontmatter and --agents JSON, letting custom and plugin subagents run without user, project and local CLAUDE.md files; managed policy files still load</p>-<p>• Added --accept-command &lt;sha256&gt; to claude plugin install and claude plugin update to accept exactly the command a previous --json run displayed, instead of -y</p>-<p>• Added support for a multiplier above 1, up to 10, in the modelPricing managed setting and the Claude apps gateway pricing block, for marked-up internal chargeback rates</p>-<p>• Added a spinner tip pointing Bedrock, Vertex AI, Foundry and LLM gateway users to the Claude desktop app; the claude.ai desktop app tip now suggests /desktop, which offers to download the app</p>-<p>• Fixed a cached organization policy being reused after switching accounts, organizations, or API keys, and the policy not refreshing until the hourly check when the credential changes mid-session</p>-<p>• Fixed the tool and command lists not updating when the organization policy finishes loading after startup or changes mid-session</p>-<p>• Fixed an enterprise managed-mcp.json that can't be read or parsed being ignored: it now keeps exclusive MCP control (user, project and plugin servers don't load) and warns at startup</p>-<p>• Fixed org policy being fetched through, and rejected by, third-party local proxies set via ANTHROPIC_UNIX_SOCKET; they are again treated like other custom gateways, including for Remote Control</p>-<p>• Fixed cloud sessions rejecting every subagent tool call ("updatedInput … failed schema validation") when a workflow or agent approval was applied after the session's worker restarted</p>-<p>• Fixed /fast off answering "Fast mode unavailable" instead of turning fast mode off when the organization has fast mode disabled</p>-<p>• Fixed sessions started with CLAUDE_CODE_SKIP_FAST_MODE_ORG_CHECK re-sending fast requests every turn after the API rejected fast mode; the rejection now stands and its reason is shown</p>-<p>• Fixed fast mode under CLAUDE_CODE_RETRY_WATCHDOG failing the turn on a usage-credits limit, or retrying an overload at fast speed, instead of falling back to standard speed</p>-<p>• Fixed Bash permission checks missing the file that fmt, column and similar commands read when it follows an option the checker doesn't recognize</p>-<p>• Fixed Bash permission checks skipping files a wildcard expands to when the wildcard sits in a command's pattern or option value (for example grep -v dir/* file)</p>-<p>• Fixed Bash permission checks so that shell variable declaration flags cannot misrepresent the command being run</p>-<p>• Fixed Bash commands with two directory changes, a subshell, or a cd+git chain skipping the prompt under permissions.blockReadsOutsideWorkingDirectories in bypass and auto mode</p>-<p>• Fixed a stale .git/config.lock breaking git checkout -b, git push -u and git config for the rest of a session after a sandboxed command failed to start (Linux)</p>-<p>• Fixed settings file changes made outside the session going unnoticed on macOS machines whose system file-event service is saturated; the watcher now falls back to polling</p>-<p>• Fixed resumed claude -p sessions whose tools all come from MCP servers failing with "At least one tool must have defer_loading=false"</p>-<p>• Fixed turns failing with "API returned an empty or malformed response" when an LLM gateway returns the non-streaming reply as text/plain</p>-<p>• Fixed sustained high CPU usage and repeated tool-list requests when an MCP server sends list_changed notifications in a tight loop</p>-<p>• Fixed MCP OAuth mishandling client registrations: denying consent forced a new one, one for another redirect URI was reused, and a concurrent write could delete a valid one or keep a mismatched one</p>-<p>• Fixed tool search returning no match when Claude selects an MCP tool by its bare name instead of its full mcp__server__tool name</p>-<p>• Fixed Ctrl+O cancelling pending MCP server reconnects, and /mcp sent from Remote Control failing while the transcript view is open</p>-<p>• Fixed the Claude in Chrome prompt telling the model to load tools through ToolSearch when ToolSearch is unavailable</p>-<p>• Fixed cross-session messages held by the receiving session's permission-mode policy leaving no trace: headless senders now get a delivery notice, and SendMessage results no longer imply it was read</p>-<p>• Fixed Claude starting a second copy of a background command (such as a watch task or dev server) that was still running after the conversation was compacted</p>-<p>• Fixed /model warning about losing the conversation cache when switching back to the model the conversation actually ran on</p>-<p>• Fixed /reload-skills reporting a skill count that disagreed with the slash menu after /cd</p>-<p>• Fixed /resume and /continue showing only 1-2 sessions in fullscreen mode on short terminals</p>-<p>• Fixed /resume and /teleport keeping the previous conversation's file-read tracking, so Claude could edit files the resumed conversation had never read</p>-<p>• Fixed --resume dropping the 1M context window ([1m]) when the resumed session's model family differs from the configured default model</p>-<p>• Fixed artifacts attached with /artifacts disappearing from the session after --resume</p>-<p>• Fixed background sessions (claude --bg, claude agents) not watching the artifacts they publish for republishes made elsewhere</p>-<p>• Fixed custom agents, slash commands and output styles beyond the first not loading from a virtual drive that reports inode 0, such as an encrypted vault mounted as a Windows drive</p>-<p>• Fixed self-hosted runner sessions silently losing all host config (settings, skills, plugins, MCP servers) when the host config directory exceeds 64 MiB; added --host-config-snapshot disk|memory</p>-<p>• Fixed skills synced from claude.ai staying on disk indefinitely after signing out; copies not refreshed within cleanupPeriodDays now move to the recoverable trash at the next launch</p>-<p>• Fixed spinner tips suggesting commands that aren't available for your account type or are disabled in your session</p>-<p>• Fixed the /add-dir path input: the left and right arrow keys now move the cursor, and Enter adds only the typed path instead of also adding the highlighted completion</p>-<p>• Fixed text fields outside the main prompt moving a leading ! to the end of what you typed (!foo came out as foo!)</p>-<p>• Fixed the interactive /hooks menu crashing when a hook matcher is named after an inherited object property such as __proto__ or constructor</p>-<p>• Fixed a fullscreen rendering glitch where text kept a stale background color after the box around it lost its background</p>-<p>• Fixed Delete in st and Alt+arrow keys in rxvt-unicode not working in attached background sessions</p>-<p>• Fixed the terminal's replies to capability queries (^[[?1;2c) appearing at the shell prompt or in an editor when Claude Code exits, is suspended, or opens an editor right after starting</p>-<p>• Improved terminal rendering performance: large diffs and long transcripts render faster, with fewer slow frames</p>-<p>• Improved startup time slightly by skipping a redundant validation of built-in model data on every launch</p>-<p>• Improved hook feedback: while a SessionStart, UserPromptSubmit, PreToolUse or SessionEnd hook runs, the spinner says so with elapsed time, and Esc cancels a prompt waiting on a SessionStart hook</p>-<p>• Improved the spinner status during long thinking: it now reads "deep in thought" after 45s, and shows "picking the thought back up" while recovering from the output-token limit</p>-<p>• Improved dynamic workflows to pause when you hit your usage limit and continue automatically when it resets, instead of dropping the affected agents</p>-<p>• Improved Remote Control to leave fewer empty sessions on claude.ai when setup fails on a flaky network</p>-<p>• Improved the Claude in Chrome message in cloud sessions when the browser can't be reached: it now says the computer may be asleep before it suggests an install</p>-<p>• Improved claude mcp serve: a running tool call now sends a progress update every 30 seconds, so clients show it is still running and idle timeouts don't abort a long command that prints nothing</p>-<p>• Improved Foundry and Claude Platform on AWS sessions: an alwaysLoad MCP server that finishes connecting mid-conversation is usable on the next turn without a tool-search round trip</p>-<p>• Improved Markdown files published as artifacts: they now render as styled document pages (title header, document typography, syntax-highlighted code)</p>-<p>• Improved Artifact tool publish errors: a publish with no file now says to write the page to a file first, and an unsupported file type is reported before a missing favicon</p>-<p>• Improved the Artifact tool's error when a page declares a capability its contract version lacks: it now lists every supported capability and notes when a newer contract version has it</p>-<p>• Improved artifact watching: a session can now watch up to 10 published artifacts at once for republishes made elsewhere, up from 5</p>-<p>• Improved PDF @-mentions to say "page count unknown" instead of a page count guessed from the file size when pdfinfo cannot count the pages</p>-<p>• Improved /mobile to show a single QR code for claude.ai/mobile, which opens the right app store for your phone</p>-<p>• Changed auto mode so that a skill's or slash command's inline ! shell commands follow default-mode permission rules instead of the classifier; a command no rule decides runs as a reviewed tool call</p>-<p>• Changed auto mode so a subagent reports back to its caller through a dedicated hand-back call that the safety classifier reviews, instead of its last message being reviewed after the fact</p>-<p>• Changed Monitor watches to always have a deadline (at most 30 minutes; 10 in single-prompt -p runs) and notify Claude to re-arm, replacing the no-timeout persistent option</p>-<p>• Changed the IDE selection indicator in the prompt to a [⧉ …] pill that wraps with the text instead of squeezing multi-line prompts; delete it with Backspace to leave the selection out</p>-<p>• Changed the default dynamic workflow size to small on Pro plans and lowered the medium size guideline from 15 to 10 agents</p>-<p>• Changed Claude apps gateway, Bedrock, Vertex AI, and Foundry sessions so that they no longer refresh a leftover claude.ai login that the session does not use</p>-<p>• Updated the bundled claude-api skill to enable eager_input_streaming on streaming custom tools, and to start deliverable-shaped Managed Agents work with user.define_outcome</p>-<p>• [VSCode] Added an Attach Open File setting that, when turned off, stops the open file from being added to messages; selected text is still attached</p>-<p>• [VSCode] Fixed the Hooks and Permission rules dialogs reporting a save that landed as failed, and the Hooks dialog going blank under a plugin-only policy lock or showing color codes in save errors</p>-<p>• [VSCode] Fixed Hooks dialog saves: no duplicate hook on replace, a header name retyped in other capitals keeps its secret, and settings.local.json is gitignored before the save returns</p>-<p>• [VSCode] Fixed session history showing only the current session when the workspace is on a Windows mapped network drive or SUBST drive</p>-<p>• [VSCode] Fixed the session list's Active filter hiding open idle sessions when Open is also checked in the filter menu</p>-<p>• [VSCode] Fixed a new chat switching back to the previous chat when the session list refreshed</p>-<p>• [VSCode] Fixed open tabs and the side bar keeping the old config folder until a window reload after CLAUDE_CONFIG_DIR changed in the environmentVariables setting</p>-<p>• [VSCode] Fixed console windows flashing on Windows when the extension runs background commands such as git, ripgrep, and the sign-in status check</p>-<p>• [VSCode] Fixed the prompt cache clock's hover text appearing only after a delay, and the auto-compact icon showing the browser's own tooltip beside its popup</p>-<p>• [VSCode] Improved the Hooks dialog: a save refused because of the settings file itself now opens a popup with an "Open settings file" button and the reason behind "Copy error"</p>-<p>• [VSCode] Changed the on state of toggle switches from Claude orange to the editor theme's button color</p>-<p>• [Claude Code on the web] Fixed a cloud session sometimes taking about ten minutes to respond after its process exited while the session still looked live; sending a message now restarts it right away</p>-<p>• [Claude Code on the web] Changed the Routines page on claude.ai/code to a new layout with Yours and Templates tabs and two-column routine cards that show run status, and removed its calendar view</p>-<p>• [Claude Code on the web] Added a Custom network access option to the Cloud environments editor in admin settings, with the same allowed-domains list the environment dialog on claude.ai/code offers</p>-<p>• [Claude Code on the web] Improved the Cloud environments admin page: it shows the default environment for Claude Tag and Claude Code, with a link to change it, and marks the recommended kind to create</p>-<p>• [Claude Tag] Fixed Claude in a channel where it stays active losing its working context about once an hour when the conversation is mostly in threads; thread activity now keeps it from being reset</p>-<p>• [Claude Tag] Fixed a thread that asked Claude to watch a pull request no longer hearing about CI failures, comments and reviews after Claude was restarted in that thread</p>-<p>• [Claude Tag] Fixed deleting the first message of a thread Claude had already replied in not ending Claude's work there; it now stops, as it did when a message with no replies was deleted</p>-<p>• [Claude Tag] Fixed Claude holding back a post because of an earlier instruction addressed to a different bot or assistant; only instructions addressed to Claude bind it, and it asks when unsure</p>-<p>• [Claude Tag] Fixed the reply-mode card Claude posts on joining a busy channel saying it "sees a lot of automated posts" when the channel is only chatty or large; the card now names the real reason</p>-<p>• [Claude Tag] Improved the Environment picker in Claude Tag admin settings: options are labeled Anthropic-hosted or self-hosted, with links to edit that environment or create one</p>-<p>• [Code Review] Fixed a pull request in a repository reviewed once per PR sometimes getting no review when a commit arrived while its review was waiting to start; it now reviews the requested commit</p>-<p>• [Code Review] Fixed Code Review occasionally posting the same findings two or three times when GitHub reported an error for a review it had in fact created</p>-<p>• [Code Review] Fixed follow-up reviews re-posting a security finding a person had already resolved when a later push moved the lines it was anchored to</p>-<p>• [Code Review] Fixed reopening a finished /ultrareview cloud session in the Claude app starting the whole review over again unprompted</p>-<p>• Windows: Fixed PowerShell commands failing with "Exit code 1" and no output when the session's temp output path reaches 260 characters</p></content>- </entry></feed>