Observe view, why-trace and item logs
The idea
A zoomable view over existing records goes from the fleet to a worker, a tool call and a delegation. It adds a 'why' timeline, a diagnostic bundle, the warn and error lines captured for each item, and front-door latency.
- The problem
- Debugging a worker meant reading the database by hand.
- Why it matters
- One connected view, with no execution model of its own and no writes on the hot path.
- Where it stands
- In production as of
A step-by-step replay of this idea is not published yet. The library adds one when a recorded run shows it.