LLM 0.32 adds reasoning traces, OpenAI Responses, server-side tools, and smarter logging

LLM 0.32 发布：新增推理轨迹、OpenAI Responses、服务端工具与更智能的日志

Simon Willison shipped LLM 0.32, the biggest update since launch. Reasoning traces now stream to stderr so you can pipe clean output elsewhere. The new default model is GPT-5.6 Luna. Server-side tools like OpenAI's code interpreter and web search are supported, and the Anthropic plugin adds matching tools plus an MCP connector. The Python API drops the forced conversation abstraction—you pass a messages list directly and use stream_events() to separate reasoning, text, and tool calls. Logging switches to a Git-like content-addressable store to avoid duplicating long contexts.

Why it matters: LLM 0.32 is a substantial release with developer-facing improvements that actually matter — reasoning trace isolation and content-addressable logging are real quality-of-life upgrades. Not scored higher because it's a tooling-layer update, not a model capability or industry sh...