{"version":"2.1.265","anchor":"artifact-permission-ask-classifier-reworked-into-five-named","canonical_anchor":"artifact-permission-ask-classifier-reworked-into-five-named","heading":"Artifact permission-ask classifier reworked into five named classes with a rollout gate","tier":"soon","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265\/e\/artifact-permission-ask-classifier-reworked-into-five-named","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265","markdown":"### Artifact permission-ask classifier reworked into five named classes with a rollout gate\n\nArtifact permission prompts now sort into five distinct classes instead of one generic ask\n\n**Unclear.** Whether the `tengu_artifact_five_class_asks` gate is enabled for this site's account is unread, so no reading can be reported.\n\n**What**\n\nArtifacts (Claude Code's generated files\/apps) that need to ask permission before taking some action are now classified into one of five named categories: `delete`, `access_change`, `standing_job`, `public_change`, or `foreign_read`. Each class carries its own metadata about whether and how the answer can be remembered. A new consent cache keyed by account and conversation also remembers past answers within that scope.\n\n**Why**\n\nSorting asks into specific classes instead of one generic permission check lets Claude Code apply different remembering rules to different kinds of risk, for example treating a delete differently from a one-time read.\n\n- Area: Artifacts\n- Tier: Nothing to try yet\n- Useful: 4\/5\n- Signal: 4\/5\n- Present in the build but not switched on"}