New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging
LLM 0.32 adds visible reasoning traces on stderr, server-side provider tools including AnthropicMCP, a Git-style content-addressable message store, and typed streaming events.
Marked important, but published more than 30 days ago, so it moved down to this band.
On this page11 sections
The editors' notes below — why it matters, the context, the learning path — are written in Chinese.
Record
The signal
#I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider tools, redesigned content-addressable SQLite logs, new models, and new features enabled by the OpenAI Responses API. I also released new versions of the llm-anthropic, llm-gemini, and llm-openrouter plugins, each with substantial updates of their own. Headline features for LLM CLI users Running LLM against reasoning models now displays their reasoning traces to standard error, so you can see what they are "thinking" without that information being included in the standard output that you might pipe to another tool. Add -R/--hide-reasoning to turn this off. …
Why now
Why it matters
#推理轨迹打到 stderr、答案留在 stdout，是一个很小却值得抄的设计：可观测性和可组合性通常互相打架，而这一版让两者同时成立，没有引入任何新概念。更大的一层是方向——AnthropicMCP 把 MCP 调用收进与供应商的一次往返，说明工具循环正在往服务端挪；而这个项目本身却走反方向，坚持一个能在本机跑、可审计、能拼接任意 OpenAI 兼容端点的命令行。两者的取舍就是「你必须自己拥有哪一层」。
Background
Technical context
#四条主线：推理轨迹输出到标准错误（-R 可关）；服务端工具（OpenAI 的代码执行与 WebSearch，llm-anthropic 的 WebSearch/WebFetch/CodeExecution/AnthropicMCP）；仿 Git 的内容寻址消息存储，解决「每轮都带完整历史」造成的重复 JSON；以及 stream_events() 返回 reasoning/text/工具调用/图片附件等分型事件，取代原先的字符串序列。另有 model.prompt(messages=[]) 取代会话抽象，以及可对任意 OpenAI 兼容端点跑一次性提示词的 llm openai endpoint。
Audience
Who should care
#Next
Learning path
#- 先读「工具使用与函数调用」，把一次工具调用拆成三段，再回头看服务端工具替你做了哪一段
- 对照 07-31 的无状态 MCP 信号，理解 AnthropicMCP 为什么能收进一次往返
- 用「AI 工具链选型与自建边界评估」的两栏法，判断这条本地路线和托管平台哪个符合你的边界
- 读「智能体可观测性与评测运维」，把推理轨迹接进你自己的轨迹追踪
Network
Where it sits in the network
#How this signal connects to neighbouring technologies, skills and background knowledge. Follow any link to keep exploring.
Further thought
Follow-up questions
#- 服务端工具让供应商代跑循环之后，失败归因还能不能分清「模型选错工具」和「工具执行失败」？
- 内容寻址的消息存储能把长对话的日志体积降到什么量级？
- 「智能体」被写进核心库之后，这个项目还能保持现在这种可拼接的小工具形态吗？
Publication record
Featured in
#The briefings that carried this signal, newest first; the last row is the weekly review of its week. The tag is the section it ran in.
技术简报 - 2026-08-05
Immediate attentionWeekly review · Aug 3 – Aug 9
Worth tracking
Sources