{"version":"2.1.284","anchor":"lantern-wick-injected-text-gains-per-model-and-subagent-spec","canonical_anchor":"lantern-wick-injected-text-gains-per-model-and-subagent-spec","heading":"Usage-limit wrap-up messages can be tuned per model and now cover the near-limit notice","tier":"soon","area":"Usage & Limits","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.284\/e\/lantern-wick-injected-text-gains-per-model-and-subagent-spec","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.284","markdown":"### Usage-limit wrap-up messages can be tuned per model and now cover the near-limit notice\n\nUsage-limit grace-window text gains per-model and subagent-specific remote settings, and the near-limit notice now counts as a wrap-up note\n\n**Unclear.** It is not clear what this text says or when Claude Code inserts it.\n\n**What**\n\nThe hidden messages Claude Code can send to the model around a usage limit's grace window (a short period near hitting the limit) changed in two ways.\n\nThe text can now be set per model through remote settings:\n\n- `tengu_lantern_wick_text_by_model`, `tengu_lantern_wick_release_by_model` and `tengu_lantern_wick_resume_by_model` are maps looked up by model id, then its normalized form or model family, then `\"default\"`.\n\n- If no entry matches, they fall back to the existing single-text settings `tengu_lantern_wick_text` and `tengu_lantern_wick_release`.\n\n- New `tengu_lantern_wick_braid_text` and `tengu_lantern_wick_braid_release` are read for agents other than the main conversation, such as subagents (helper agents Claude starts for part of a task).\n\nThe near-limit notice is handled differently:\n\n- The near-limit message is now tagged `usageLimitNote: \"near_limit\"`, where before it carried no tag.\n\n- The code that finds the last usage-limit note now returns which note it was, instead of only whether it was `wrap_up`.\n\n- A `near_limit` note is now treated like `wrap_up`: it prevents a reset and can trigger the \"release\" message. That release step is still controlled by `tengu_lantern_wick_braid` and related settings such as `tengu_lantern_wick_mode`.\n\nNothing has been read about any of these settings, so whether they are active is unknown.\n\n**Why**\n\nThis changes which grace-window messages the model receives when you are close to a usage limit, and lets the wording differ between models and between the main conversation and subagents.\n\n- Area: Usage & Limits\n- Tier: Nothing to try yet\n- Useful: 3\/5\n- Signal: 4\/5\n- Present in the build but not switched on"}