Module provider 

LLM provider abstraction.

Provider is the trait every backend implements. Today there’s one production impl (anthropic::AnthropicProvider) and one test impl ([MockProvider]). OpenAI and Ollama follow-ups will plug in here without touching the rest of the crate (per Phase 7 plan Q4 — Anthropic-first, others later).

The trait is deliberately narrow: one method, sync, one prompt shape in, one parsed response out. Schema-aware prompt construction lives one layer up in crate::prompt, so providers stay generic over what’s being asked.

Modules

anthropic

Anthropic Messages API adapter.

Structs

Request

One LLM call’s worth of input. Mirrors the Anthropic Messages request shape because it’s the most expressive of the three providers we’ll support; OpenAI and Ollama adapters convert to their native shapes inside their own complete impls.

Response

What every provider returns. We keep this minimal — text is the raw string the model produced (the caller parses it), usage surfaces token counts so callers can verify cache hits.

Usage

Token-usage breakdown. Names match Anthropic’s API field names so the mapping stays obvious; OpenAI’s prompt_tokens / completion_tokens will fan into input_tokens / output_tokens when that adapter lands.

Traits

Provider

A single one-shot call. Sync because every supported provider has a sync HTTPS entry point and ask() itself is sync (matches the engine’s surface — Connection::execute etc. are all sync).