{"version":"2.1.288","anchor":"new-telemetrypermission-source-classifier-gated-by-tengu-me","canonical_anchor":"new-telemetrypermission-source-classifier-gated-by-tengu-me","heading":"Claude Code labels who or what approved a tool call","tier":"internal","area":"Permissions","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.288\/e\/new-telemetrypermission-source-classifier-gated-by-tengu-me","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.288","markdown":"### Claude Code labels who or what approved a tool call\n\nClaude Code can now label each approval of a tool call as coming from a person, a classifier, a mode or a hook\n\n**Unclear.** What the related flag actually controls is not known.\n\n**What**\n\nA tool call is a single action Claude takes, such as running a command. Claude Code now labels the reason an action was allowed with its source:\n\n- a person, when approved through a permission prompt\n\n- a classifier, when automatic mode's checker allowed it\n\n- a mode, when automatic mode allowed it\n\n- a hook, when a hook allowed it\n\nA related hook path adds a reason for a person reading the rules. This is tied to a server-controlled flag whose built-in default is on.\n\n**Why**\n\nIt appears to be a way of recording who or what approved each action.\n\n- Flag `tengu_merry_popcorn`: Not enough to say (read for one account on one subscription tier against v2.1.288; this account: no value returned, anonymous baseline: no value returned, compiled default: on) 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: Permissions\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}