Use recovery workflows before high-risk changes.
Before migration
Capture a boundary before a data model or memory schema change.
Before agent autonomy
Checkpoint state before a long-running automated workflow.
After incident
Inspect what changed and recover from bad durable memory.
Think in checkpoint, diff, restore.
The public package exposes hosted workflows through Cloud surfaces. Recovery should be treated as an operator action with audit context, not a silent background mutation.
Do not use rollback to hide history.
Rollback is for recovery. Audit history should remain available so teams can understand why state changed and what was restored.