{"version":"2.1.307","anchor":"safety-event-telemetry-tengu-safety-event-for-permission-d","canonical_anchor":"safety-event-telemetry-tengu-safety-event-for-permission-d","heading":"Usage data is now sent for permission decisions","tier":"internal","area":"Telemetry","scope":"both","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.307\/e\/safety-event-telemetry-tengu-safety-event-for-permission-d","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.307","markdown":"### Usage data is now sent for permission decisions\n\nClaude Code now sends usage data about each permission decision, recording what kind of rule or check made it\n\n**What**\n\nClaude Code decides, for each tool Claude wants to use, whether to allow it, and sometimes asks you. It now sends a usage report, called telemetry, about each of those decisions. The report says what kind of tool it was, how many times the sandbox was broken (the sandbox is a walled-off space that limits what commands can reach) and what made the decision:\n\n- a safety check\n\n- a managed policy\n\n- a permission rule\n\n- analysis of the command\n\n- a hook, a script you set up to run at certain moments\n\n- auto mode blocking it\n\n- auto mode giving no verdict\n\n- the permission mode\n\n- a sandbox override\n\nIt also reports when a hook pushes back after a tool has run. A remote switch, `tengu_snoopy_creek`, appears to control this, and it falls back to on when the server sends nothing.\n\n**Why**\n\nThis is a new stream of usage data sent on every permission decision.\n\n- Flag `tengu_snoopy_creek`: Not enough to say (read for one account on one subscription tier against v2.1.307; 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: Telemetry\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: both\n- Heads-up: no"}