New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging
LLM 0.32 adds visible reasoning traces, server-side tools, and OpenAI Responses API support
“the most significant new version of LLM since the initial launch of the project”
Simon Willison released LLM 0.32, a major update to his popular open-source CLI tool for interacting with language models, adding support for displaying reasoning traces, server-side tools like CodeInterpreter and WebSearch, and MCP connector support via the llm-anthropic plugin. The release also sets GPT-5.6 Luna as the new default model and introduces redesigned content-addressable SQLite logging. This reflects the rapid standardization of reasoning traces and server-side tool APIs across major providers as table-stakes features for developer tooling.