Modules
Entry point for the inference layer.
Inference adapter for the Anthropic Messages API.
Inference adapter for Ollama.
Inference adapter for OpenAI-compatible APIs.
GitHub Copilot OAuth device code authentication.
Single entry point for all inference calls.
Shared HTTP utilities for Arcanum adapters.
Canonical request struct for all inference calls: chat, streaming, embeddings, and media generation.
Declares model capabilities so adapters serialize correctly on the first attempt.
Fetches and caches model capabilities from models.dev.
Resolves a ModelProfile for a given provider and model.
Probes inference providers to determine availability.
Behaviour for inference provider adapters.
Canonical response struct from all inference calls.
Profile-driven post-processing of inference responses.
Shared retry logic for Arcanum adapters.
Shared Server-Sent Events parsing for Arcanum adapters.