Follow Discord
Sweep 12 Nov 2026 · 23:00Z Build v2.1.323 540 read Stable v2.1.311 Latest v2.1.323 Next v2.1.323 Feeds RSS JSON llms.txt llms-full.txt Unofficial

Claude Code v2.1.323 ·

Remote Control sends permission prompt details by default and keeps prompts across worker handoffs

Remote Control now builds readable permission prompt details unless the server turns them off, and keeps a waiting prompt alive when a worker is replaced

Group of 2 You'll notice Improvements
JSON All of v2.1.323
You'll noticeTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
Remote ControlArea: what it touches
ImprovementsKind: in v2.1.323,
ImprovementsSection of the release

What

Remote Control lets you follow and steer a Claude Code session from another device, such as a phone or the web. When Claude needs your permission, the session reports a requires_action state to that device.

  • The details sent with requires_action (the tool's display name, a description of the action and the raw command) are now built unless Anthropic's servers turn the tengu_bridge_requires_action_details flag off. Before, they were left out unless the server turned the flag on. The same switch covers the details for request_user_dialog prompts. Whether it applies to a given account is decided by the server. The flag server returned it on for this site's account and for the anonymous baseline, but no reading has been taken under this release yet.
  • A new method, holdForNextWorker, keeps a waiting permission prompt alive when the worker running the session is handed over to a new one. If the answer matches the prompt and it is still open, the prompt is held and a requires_action state change with its details is sent again.

Why

On another device you should see what Claude is asking to do rather than a bare request, and permission prompts should be less likely to vanish or repeat when the worker behind your session is replaced.

Read from
Feature flag
tengu_bridge_requires_action_details On for this account, and not off by default

The flag server returned on for the one account this site reads, and nothing in this release compiles it off by default. The compiled default is shown below, and says which it is when we cannot read one: a fifth of gates compile in a string or a number rather than on or off, and most published releases have no gate table behind them at all. No client can see what the server returns for your account.

This account: on · anonymous baseline: on · compiled default in v2.1.323: on

These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.

Read once, for one account on one subscription tier, against v2.1.323. It isn't a statement about your account. What a flag value here can and cannot tell you

See this entry in the whole of v2.1.323 →

Feedback