When Claude Code wants to do something that needs your approval, it asks a permission question. In a remote session, one running on another machine, that question can be left waiting and the answer can arrive only after the session has restarted.
Claude Code now has a way to handle such a late answer more carefully: before applying it, Claude Code waits until the SDK servers have been read. SDK servers are MCP tool servers supplied by an app that runs Claude Code through its software development kit, or SDK. Without this wait, the answer is applied straight away, as before.
The wait is controlled by the remote setting tengu_steady_wilkes, together with a second check. The built-in fallback, used when the server sends nothing, is off, and with it Claude Code keeps the old behaviour. The flag server returned off for this site's account and for the anonymous baseline.
This changes how a remote session picks up again after a permission prompt was left waiting across a restart. Waiting for the SDK servers means the late answer is applied once the tools it may refer to are available again.
tengu_steady_wilkes Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: off · compiled default in v2.1.321: off
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 v2.1.321. It isn't a statement about your account. What a flag value here can and cannot tell you
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
New in this build: tengu_steady_wilkes