Group of 3 You'll notice
Artifact database reads/writes and asset actions (delete, create, publish) now compute approval from plan mode, batch size, and call origin instead of always requiring a human, plus a new Windows-path safety check.
What
- Permission checks for the artifact database's
read_db/write_dbactions now consider whether the call is a served/background call, whether it's a multi-entry batch, and the current permission mode, instead of always requiring human approval. - The same actions gained a new safety check that flags a decision with a "suspicious Windows path" classifier when a risky path condition is detected.
- Other artifact actions, deleting an asset (
delete_asset), creating from a type, and publishing, now compute approval the same context-aware way, also factoring in whether the artifact is already owned or consented to, instead of a hardcoded "must be a human" rule.
Why This lets routine, low-risk artifact operations proceed automatically in more cases while still requiring human approval when the context is riskier (unusual paths, non-batch human-initiated calls), reducing unnecessary approval prompts without loosening protection where it matters.