{"version":"2.1.268","anchor":"artifact-store-write-guidance-now-distinguishes-types-with-v","canonical_anchor":"artifact-store-write-guidance-now-distinguishes-types-with-v","heading":"Artifact-store write guidance now distinguishes types with vs. without endpoints","tier":"notice","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.268\/e\/artifact-store-write-guidance-now-distinguishes-types-with-v","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.268","markdown":"### Artifact-store write guidance now distinguishes types with vs. without endpoints\n\nArtifact write guidance now tells the model plainly when a type has no writable store at all\n\n**What**\n\nWhen an Artifact (a piece of generated content Claude Code manages, like a shared document or canvas) declares a shared store, Claude Code gives the model guidance on how to write to it. That guidance now takes into account whether the artifact's type actually declares any endpoints (ways to write to the store). If it doesn't, the model is now told plainly that no store-write call is available for that type, rather than being pointed toward `run_script` as a possible option regardless.\n\n**Why**\n\nThis stops the model from being nudged toward trying `run_script` to write to a store when that path doesn't actually exist for the artifact's type, avoiding wasted or confused attempts.\n\n- Area: Artifacts\n- Names: `run_script`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}