{"version":"2.1.236","anchor":"claude-is-told-when-an-artifact-watch-fails-to-start","canonical_anchor":"claude-is-told-when-an-artifact-watch-fails-to-start","heading":"Claude is told when an artifact watch fails to start","tier":"notice","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.236\/e\/claude-is-told-when-an-artifact-watch-fails-to-start","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.236","markdown":"### Claude is told when an artifact watch fails to start\n\nWhen an artifact watch cannot start, Claude is told the plain reason instead of failing silently.\n\n**What**\n\nIf a live artifact subscription cannot be armed, the session now enqueues a notification stating the artifact is NOT being watched, with a plain reason: \"could not connect\", \"artifact not found\", \"no live credential\", or \"watch limit reached\". Previously this failed quietly.\n\n**Details**\n\n- Notices are de-duplicated per artifact and reason, and cleared once a later arm attempt succeeds.\n- A new status view reports each artifact as `arming` or `backing_off`, with failure counts and the next retry time.\n\n**Evidence**\n\n`watch limit reached`\n\n- Area: Artifacts\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 3\/5"}