a2a-llm 0.1.0

Provider-neutral LLM vocabulary and chat-completion providers (OpenAI-compatible, Gemini)
Documentation

Provider-neutral vocabulary for chat completions, plus the providers that speak it.

[LlmProvider] is the port: chat_completion and chat_completion_stream over [LlmRequest] / [LlmResponse]. [openai] covers OpenAI and every OpenAI-compatible endpoint (OpenRouter, vLLM, llama.cpp); [gemini] covers Google's API. [provider_from_env] picks one from the environment.

The types are deliberately not tied to A2A. [ToolCall] and [ToolDefinition] are the tool-calling vocabulary shared with the MCP bridge, which is why they live in their own crate rather than inside an agent framework.