{"version":"2.1.248","anchor":"artifact-database-write-prompt-builds-one-reason-instead-of-","canonical_anchor":"artifact-database-write-prompt-builds-one-reason-instead-of-","heading":"Artifact database write prompt builds one reason instead of five","tier":"notice","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248\/e\/artifact-database-write-prompt-builds-one-reason-instead-of-","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.248","markdown":"### Artifact database write prompt builds one reason instead of five\n\nThe artifact database write prompt now gives one combined reason instead of several.\n\n**What**\n\nThe permission prompt for writing to an artifact database used to produce a separate reason for each hazard it detected. It now assembles one reason string and only chooses whether the prompt is a safety check or an ordinary ask.\n\n**Details**\n\n- Hazards folded into the single string: plan mode, flagged spelling, a path resolving outside readable directories, a hard link, and an uninformative name.\n- Safety-check prompts remain non-approvable by the classifier.\n- The wording you see, including the batch summary, source file and persistence warning, is unchanged; one field was added to the recorded input.\n\n**Evidence**\n\n`; approving covers database writes to any artifact for the rest of this session.`\n\n- Area: Artifacts\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}