{"version":"2.1.319","anchor":"auto-mode-accept-edits-simulation-telemetry-and-gate","canonical_anchor":"auto-mode-accept-edits-simulation-telemetry-and-gate","heading":"Auto mode's quick-approval path now records timing and wrong guesses","tier":"internal","area":"Auto Mode","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319\/e\/auto-mode-accept-edits-simulation-telemetry-and-gate","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319","markdown":"### Auto mode's quick-approval path now records timing and wrong guesses\n\nAuto mode's quick path for approving edits now reports how long it took and when its guess was wrong, and holds some MCP shell calls for a server check\n\n**What**\n\nAuto mode is a permission mode in which Claude Code checks whether an action is safe instead of asking you. It has a quick path that predicts whether an edit would be accepted. That path now:\n\n- records how long it took\n\n- reports when its prediction was wrong\n\n- holds MCP calls that run shell commands in a workspace until a server-side check decides on them\n\nThe quick path stays behind the same server-side switch as before, which is off unless it is switched on remotely. Version 2.1.318 had it off by default, and the flag server returned off both for this site's account and without an account.\n\n**Why**\n\nMost of this is measurement used to tune auto mode's safety check.\n\n- Flag `tengu_radiant_hare`: Off in both readings (read for one account on one subscription tier against v2.1.319; this account: off, anonymous baseline: off, compiled default: 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.\n- Area: Auto Mode\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}