Claude Code can mark a request to Anthropic as asking for extended usage past a usage limit. Before, this was never done for the main conversation, only for subagents (helpers Claude runs separately for a task). With a new condition passed in, the main conversation is no longer ruled out.
The other conditions are unchanged:
- you must connect to Anthropic directly
- one of two remote conditions must hold
- a remotely controlled setting,
tengu_lantern_spool, must be on; it falls back to off when the server sends nothing
Once switched on, extended usage could cover your main conversation as well as subagents.
tengu_lantern_spool Off in both readingsThe flag server returned off for the account this site reads and for the anonymous baseline. A reading of off cannot rule out a rollout these two readings sit outside of.
This account: off · anonymous baseline: off · compiled default in v2.1.284: 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.
tengu_smooth_harbor 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 v2.1.284: 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 v2.1.284. It isn't a statement about your account. What a flag value here can and cannot tell you
What the new condition that lets the main conversation through represents is not known.