Follow Discord
Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
Claude Code v2.1.257 ·

Shutdown-request auto-approval helper text for agents

New instructions tell an agent how to approve or refuse a pending shutdown request by tool call rather than plain text.

TierNothing to try yethow much it should matter to you
Useful4my rating, 1 to 5
Signal4worth watching, 1 to 5
AreaAgentswhat it touches
KindIn Developmentin v2.1.257,
Nothing to try yet

New instructions tell an agent how to approve or refuse a pending shutdown request by tool call rather than plain text.

New generated instructions tell an agent exactly how to respond to a pending shutdown_request: call a specific tool with a JSON message containing the shutdown's request_id and approve set to true or false. The text notes that a plain-text acknowledgment does not actually shut the process down.

Read from
Names in the bundleshutdown_requestrequest_idapprove
What the documentation says
Since it was published

The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.

Added since A small documentation edit on Channels reference touched a line naming request_id after this was published. The verdict your server sends back is `notifications/claude/channel/permission` with two fields: `request_id` echoing the ID above, and `behavior` set to `'allow'` or `'deny'`. Allow lets the tool call proceed; deny rejects it. Neither ver… channels-reference see the edit
Confirmed since Anthropic's documentation has since written up request_id, on Agent SDK reference - TypeScript. The control-response wrapper for a successful `initialize` also carries a `pending_permission_requests` array. The field is on the response wrapper itself, not in the `SDKControlInitializeResponse` payload above. Each entry is a complete `… agent-sdk/typescript see the edit
Added since A small documentation edit on How Claude remembers your project touched a line naming approve after this was published. Claude Code treats a symlink whose target is outside your working directory like an [external import](#import-additional-files). The linked rules don't load until you approve external imports for the project, and after that only the ones w… memory see the edit
Confirmed since Anthropic's documentation has since written up approve, on Get started. When the app opens, sign in with your Claude account. On Windows, the app opens claude.ai in your default browser for this and continues in the app window once you approve the sign-in. If the sign-in redirect can't return to the app (for e… claude-science/get-started see the edit
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up approve, on Get started.

See this entry in the whole of v2.1.257 →

Feedback