Token Logger guides.

This guide explains usage record boundaries, overlapping token categories, incomplete reports, retry accounting, and estimate provenance. Use it after defining the surrounding AI request workflow. The goal is a record that can be reconciled and explained, with missing information left visible and sensitive content kept out of routine accounting.

Token logging here means recording LLM usage metadata. Keep input, output, and any supported detail categories understandable so an application’s usage history can be reconciled without preserving credentials or conversation content. Visit the Token Logger topic guide for the starting questions, a short checklist, and the scope of this collection.