Under the hoodTier: how much it should matter to you
2Useful: my rating, 1 to 5
2Signal: worth watching, 1 to 5
TelemetryArea: what it touches
Internal ChangesKind: in v2.1.301,
Internal ChangesSection of the release
What
In auto mode, Claude Code runs a safety check that decides whether an action may go ahead without asking you. Claude Code's usage data (the analytics it reports about how it is used) now records that decision as classifier_verdict, with the value allow or block. Sometimes it also records a category as classifier_category.
Why
This adds detail to the usage data about how auto mode decides. It does not change what auto mode allows.
How sure we are
One source agreesOne thing we can check says the same as this entry.
Anthropic's release notes agreeAdded classifier_verdict and permission_mode to OpenTelemetry tool_decision events, so auto mode classifier decisions can be told apart from…
