What
When you hit a usage limit, Claude Code can hold a request and wait. A new recheck now runs during that wait. It sends a small test request (a probe), and if the probe is let through, the held request is sent again straight away. A log line reads "[usage limit recheck] probe admitted: the request is sent again now".
The probe is skipped in several cases:
- when its controlling switch is off
- in essential-traffic-only mode
- for accounts that are not first-party or not subscribers
- for low-priority requests
The reason is recorded as usage_limit_wait_recheck, a new value next to the existing usage_limit_wait_heartbeat. Nothing has been read about the gate this runs behind.
Why
If a limit lifts earlier than expected, a waiting request can go through sooner instead of sleeping for the full wait.
tengu_bright_wall 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: no value returned · compiled default in v2.1.305: 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 v2.1.305. It isn't a statement about your account. What a flag value here can and cannot tell you
New in this build: tengu_bright_wall