v4.0.0

Features

• Load models from a direct URL: provide a direct URL to a .gguf model and Paddler downloads and caches it on the agent
• OpenAI Responses API: new /v1/responses endpoint
• Token usage and classification: responses report per-kind token counts, and generated tokens are classified as content, reasoning, tool call, or undeterminable
• Structured tool-call parsing: set parse_tool_calls to get parsed tool calls response
• New endpoint: Get balancer applicable state

Breaking changes

• Inference parameters: batch_n_tokens renamed to n_batch
• Inference parameters now requires embedding_batch_size
• Streamed tokens now arrive under kind-specific keys (ContentToken, ReasoningToken, ToolCallToken, UndeterminableToken) instead of Token, and the stream ends with a Done event carrying token usage
• Minimum supported Rust version is now 1.95.0