Call manifests and layered observability
The idea
Each metered call records its role, model, layers, files, tokens, cache reads and stage budget, plus a digest of its input taken before the call. A task can be read at any level, from a glance down to these internals.
- The problem
- Nobody could trace context bloat or what was sent to a model.
- Why it matters
- Anyone can see what each call loaded and what it cost, at the depth they need.
- 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.