{"name":"tengu_lantern_hinge","slug":"tengu-lantern-hinge","family":"flag","title":"Feature flags","noun":"feature flag","description":"The check that makes Claude Code wait out a usage limit now also covers WebFetch reading a fetched page, under a remote switch that is off by default","description_source":"entry","described_by":{"version":"2.1.292","anchor":"usage-limit-handling-extended-to-web-fetch-apply-fork-new-g"},"presence":{"first_seen":"2.1.292","removed_in":null,"in_current_build":true,"newest_mined":"2.1.295","builds":4,"mined_builds":138,"first_cited":{"version":"2.1.292","released_at":"2026-10-06 17:10:31","spans":1}},"aliases":[],"entries":[{"version":"2.1.292","anchor":"usage-limit-handling-extended-to-web-fetch-apply-fork-new-g","heading":"WebFetch page reading can be held at a usage limit, behind an off switch","line":"The check that makes Claude Code wait out a usage limit now also covers WebFetch reading a fetched page, under a remote switch that is off by default","released_at":"2026-10-06 17:10:31","reason":"gate cited by this entry, found in this entry's text"}],"entries_total":1,"docs":[],"docs_total":0,"gates":[{"version":"2.1.292","state":"unknown","account":null,"baseline":null,"code_default":false}],"related":[{"name":"tengu_lantern","slug":"tengu-lantern","description":"Reading someone else's shared artifact can now be auto-allowed via a remembered consent choice"},{"name":"tengu_lantern_prism","slug":"tengu-lantern-prism","description":"A Stats tab in \/plugin shows skill usage and context costs, with \/skill-doctor redirecting there."},{"name":"tengu_lantern_sconce","slug":"tengu-lantern-sconce","description":"A status bar notice about usage limits and covered extra usage is built but switched off."},{"name":"tengu_lantern_sconce_copy","slug":"tengu-lantern-sconce-copy","description":"Usage-limit banner wording can now be overridden remotely instead of being fixed text"},{"name":"tengu_lantern_snuffer","slug":"tengu-lantern-snuffer","description":"A new remote switch, off by default, can stop extended usage requests for workflows set to wait out a usage limit"},{"name":"tengu_lantern_spool","slug":"tengu-lantern-spool","description":"A server flag can widen when subagent requests send the extended usage-limit header."},{"name":"tengu_lantern_wick","slug":"tengu-lantern-wick","description":"Default `false`. When on, and the usage limit's grace window has just become active, the next main-thread follow-up request in a turn (not the first request of a user turn, and not one resuming incomplete thinking) gets a hidden message saying the usage limit is reached and the grace window is active, ending `Wrap up: finish or checkpoint; don't start subagents or long work.` A new user turn clears the pending notice without adding it."},{"name":"tengu_lantern_wick_braid","slug":"tengu-lantern-wick-braid","description":"A new 'wrap up your work' reminder can be injected near usage limits, currently gated off"},{"name":"tengu_lantern_wick_braid_release","slug":"tengu-lantern-wick-braid-release","description":"A block of text Claude Code inserts for the model can now be configured remotely per model, with separate text for subagents"},{"name":"tengu_lantern_wick_braid_text","slug":"tengu-lantern-wick-braid-text","description":"A block of text Claude Code inserts for the model can now be configured remotely per model, with separate text for subagents"}],"url":"https:\/\/changelogs.core-directive.com\/reference\/flag\/tengu-lantern-hinge","family_url":"https:\/\/changelogs.core-directive.com\/reference\/flag.json"}