# API
`kcode-intelligence-router` is an in-process typed router for exact-model
operations. `open(Config)` accepts optional OpenAI and Gemini API keys plus the
Codex catalog cache, constructs all provider clients, and returns an
`Intelligence` handle and the configured primary runtime model.
`Intelligence::for_user` binds mandatory per-user accounting before any
provider call.
The user-bound handle supports agent turns, grounded search, page fetches,
ordinary audio transcription, structured Gemini audio inference, media
annotation, and tool-free Codex text generation. Requests carry exact model
identifiers. The router owns provider selection, cancellation, timeouts, error
normalization, and durable usage receipts.
Each actual model call writes one JSON receipt containing the user, operation,
requested and actual model, available provider identifiers, and normalized
metering. `receipts` and `daily_usage` read those files directly; daily totals
deliberately use a linear scan.
Local document extraction and public-page fetching do not create model usage
receipts because they do not call a model provider.