{"version":"2.1.265","anchor":"artifact-reads-gain-a-five-class-consent-latch","canonical_anchor":"whole-new-artifact-consent-model-built-behind-claude-code-ar","heading":"New five-class consent model for Artifact permissions (experimental)","tier":"soon","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265\/e\/artifact-reads-gain-a-five-class-consent-latch","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265","markdown":"### New five-class consent model for Artifact permissions (experimental)\n\nAn experimental 'five-class asks' mode reduces repeated Artifact permission prompts for pinning, reading, and commenting\n\n**Unclear.** Whether this consent flow is active depends on the `tengu_lantern` and `tengu_artifact_five_class_asks` gates, which have not been read for this release.\n\n**What**\n\n- A new consent model for the Artifact tool, called \"five-class asks,\" is being built behind the `CLAUDE_CODE_ARTIFACT_FIVE_CLASS_ASKS` environment variable (off by default), which latches the behavior on or off for the life of the process and reports whether it was on via telemetry.\n\n- When enabled, it changes how Claude asks for permission on artifact actions: Pinning someone else's artifact to your own list is now auto-allowed instead of prompting.\n\n- Uploading, reading (`list_assets`\/`read_asset`\/`list_files`\/`read_file`), commenting, and replying all go through a new classification system (`pathAsk`, `readRule`, `flaggedSpelling`, `outsideAsk`, `hardLinked`, plus an `unknown`\/`someone_else`\/`from_type`\/`cowritten` split) and a new ruling flow, instead of always asking.\n\n- Uploads get an \"already approved this session\" fast path.\n\n- Reading someone else's shared artifact can be auto-allowed via a per-conversation \"class consent\" latch, with the message \"Reading ... needs no approval\"; wording also changed from \"another person's artifact\" to \"someone else's artifact.\"\n\n- When the experiment is off, the previous single-path deny\/ask logic is used unchanged.\n\n**Why**\n\nThis reduces how often Claude has to interrupt with a permission prompt for routine, low-risk artifact actions, like pinning or re-reading something already approved, while still asking for genuinely new or risky ones.\n\n- Area: Artifacts\n- Tier: Nothing to try yet\n- Useful: 5\/5\n- Signal: 4\/5\n- Present in the build but not switched on"}