{"version":"2.1.233","anchor":"a-model-side-stop-no-longer-discards-your-watch-artifact-fla","canonical_anchor":"a-model-side-stop-no-longer-discards-your-watch-artifact-fla","heading":"A model-side stop no longer discards your --watch-artifact flag","tier":"notice","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.233\/e\/a-model-side-stop-no-longer-discards-your-watch-artifact-fla","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.233","markdown":"### A model-side stop no longer discards your `--watch-artifact` flag\n\nWhen Claude stops a monitor itself, your watch-artifact flags stay on the saved command line.\n\n**What**\n\nWhen Claude itself tears down a live frame or artifact monitor, the `--watch-artifact` and `--watch-artifact-no-autoreact` flags you passed stay on the stored command line. They are only stripped when the stop came from somewhere other than the model.\n\n**Details**\n\n- Kill paths now tag the stop with an origin flag, set when a live frame is torn down internally and when a monitor task is killed with reason \"parent\".\n\n**Evidence**\n\n`modelOrigin: n === \"parent\",`\n\n- Area: Artifacts\n- Names: `--watch-artifact`, `--watch-artifact-no-autoreact`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 3\/5"}