{"version":"2.1.305","anchor":"output-limit-recovery-nudge-and-stop-point-are-driven-by-ten","canonical_anchor":"output-limit-recovery-nudge-and-stop-point-are-driven-by-ten","heading":"Recovery after hitting the output limit can now be adjusted from the server","tier":"soon","area":"Output Limits","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/output-limit-recovery-nudge-and-stop-point-are-driven-by-ten","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305","markdown":"### Recovery after hitting the output limit can now be adjusted from the server\n\nHow Claude Code prompts the model to continue after hitting its output limit, and when it gives up, can now be set by a server switch\n\n**What**\n\nWhen the model's reply runs into its maximum length, Claude Code nudges it to carry on and retries. It used to choose between two fixed nudges. A server switch can now set, separately for the main conversation and for subagents (helper copies of Claude):\n\n- which nudge to send, with a new option for when there was no visible output\n\n- how many retries to allow before stopping early\n\nWhen the server sends nothing, behaviour stays as before. Stopping early is now recorded as its own outcome.\n\n**Why**\n\nNothing changes until the server sends a value. It gives a way to tune how hard Claude Code pushes to recover from a cut-off reply.\n\n- Flag `tengu_tingly_pike`: Not enough to say (read for one account on one subscription tier against v2.1.305; this account: no value returned, anonymous baseline: no value returned, compiled default: not a boolean we can read) 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.\n- Area: Output Limits\n- Tier: Nothing to try yet\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no\n- Present in the build but not switched on"}