Expand description
LLM provider abstraction.
A provider takes a transcript plus tool specs and returns either free-form content, structured tool calls, or both. The trait is the only thing the agent depends on; everything beyond it (HTTP, retries, mocking) lives in adapters.
Re-exports§
pub use mock::MockProvider;pub use openai::OpenAiProvider;
Modules§
- mock
- Deterministic LLM for tests and offline development.
- openai
- OpenAI-compatible chat-completions adapter.
Structs§
- Completion
- One step of model output.
- Tool
Call - A structured request to invoke one of the registered tools.
- Tool
Spec - JSON-schema description of a tool, sent verbatim to the model.