LLM CLI gains reasoning traces and OpenAI Responses support
Simon Willison released LLM 0.32, a major update to his open-source CLI tool that surfaces reasoning traces from frontier models and integrates OpenAI's new Responses API. The release adds server-side tool execution, improved SQLite logging, and synchronized updates across Anthropic, Gemini, and OpenRouter plugins. This matters because LLM has become a critical bridge for developers experimenting with reasoning models and multi-provider workflows, and these features lower friction for teams building on top of reasoning-capable systems without vendor lock-in.
Modelwire context
Analyst takeThe more consequential detail here isn't the reasoning trace support itself but the timing: Willison is shipping multi-provider parity updates across Anthropic, Gemini, and OpenRouter in the same release, which means LLM is actively managing the coordination cost of a fragmented provider landscape rather than drifting toward any single vendor's API conventions.
Two days before this release, Willison published 'Devtools must be open source,' arguing that LLM-assisted code comprehension now makes open-source freedoms practically exercisable rather than theoretical. LLM 0.32 is the product expression of that argument: a tool designed to be inspected, forked, and extended precisely because it sits at the intersection of multiple competing provider APIs. The pattern also connects to the Datasette Apps 0.2a0 release from August 1st, where agent-native tooling was embedded directly into the development loop. Willison is assembling a coherent stack where each layer treats agents and developers as first-class operators, and LLM is the outermost interface in that stack.
Watch whether the OpenAI Responses API integration in LLM 0.32 gets matched by equivalent Anthropic or Gemini server-side tool support within the next two release cycles. If it does, that confirms provider parity is a real design constraint Willison is enforcing. If OpenAI support stays ahead, it signals drift toward de facto vendor preference regardless of stated neutrality.
Coverage we drew on
- Devtools must be open source (exe.dev) · Simon Willison
This analysis is generated by Modelwire’s editorial layer from our archive and the summary above. It is not a substitute for the original reporting. How we write it.
MentionsSimon Willison · LLM · OpenAI · Anthropic · Google Gemini · OpenRouter
Modelwire Editorial
This synthesis and analysis was prepared by the Modelwire editorial team. We use advanced language models to read, ground, and connect the day’s most significant AI developments, providing original strategic context that helps practitioners and leaders stay ahead of the frontier.
Modelwire summarizes, we don’t republish. Simon Willison originally reported this story as “New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging”. The full content lives on simonwillison.net. If you’re a publisher and want a different summarization policy for your work, see our takedown page.