{"version":"2.1.260","anchor":"artifact-file-readslistings-can-now-report-a-from-type-lo","canonical_anchor":"artifacts-tool-results-flag-co-writer-type-published-conte","heading":"Artifact tool results flag cross-artifact copied content as untrusted","tier":"notice","area":"Artifacts","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.260\/e\/artifact-file-readslistings-can-now-report-a-from-type-lo","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.260","markdown":"### Artifact tool results flag cross-artifact copied content as untrusted\n\nArtifact file responses can now flag when content type was locked by the artifact's type.\n\nThe asset-list schema (`ge`) gains a `cowritten` boolean field, and a new schema (`Te`) validates `{ assets: [...].extend({ from_id: ... }) }` capped at a maximum count, laying groundwork for attributing assets copied from another artifact. The artifact `file_list` and `file_read` tool responses can now include a `from_type` flag when the served content type was determined by the artifact's declared type rather than sniffed.\n\nTool-result messages for `asset_list`, `asset_read`, and `file_read` now surface the `cowritten` field (and, for file listings, `from_type`), and the returned text explicitly warns the model to treat such assets or files as untrusted data when a co-writer or an Artifact type's publisher, rather than the user, produced them.\n\n- Area: Artifacts\n- Names: `from_type`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 3\/5"}