Collected sources and patterns will appear here. Add from search or the patterns library.
ProviderResponseMetadata -> UsageRecord
Parse response metadata from multiple LLM providers to record token counts and calculate running financial costs.
Problem it solves
Running arbitrary agent loops can lead to runaway API expenses without granular, multi-tenant tracking.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.