llm-chat-completions-server 0.1a0

<p><strong>Release:</strong> <a href="https://github.com/simonw/llm-chat-completions-server/releases/tag/0.1a0">llm-chat-completions-server 0.1a0</a></p> <p>A key goal of the new content-addressable logs <a href="https://simonwillison.net/2026/Jul/30/llm-rc1/">in LLM 0.32rc1</a> was being able to support OpenAI Chat Completion style requests where each incoming message extends the previous conversation, like this:</p> <pre><code>curl http://localhost:8002/v1/chat/completions \ -H 'Content-Type: application/json' \ -d '{ "model": "qwen3.5-4b", "messages": [ {"role": "user", "content": "Capital of France?"}, {"role": "assistant", "content": "Paris."}, {"role": "user", "content": "Germany?"} ] }' </code></pre> <p>Here the conversation state is tracked by the client, so each of these requests gets longer and longer. The new schema design in LLM is designed to de-duplicate these using hashes of the individual message parts.</p> <p>To test that out, I built this plugin:</p> <pre><code>uv tool install llm --pre llm install llm-chat-completions-server llm chat-completions-server -p 9001 </code></pre> <p>Running this starts a localhost server on port 9001 that exposes your full collection of LLM models (from any plugins you have installed) using a ChatGPT Completions compatible endpoint.</p> <p>GPT-5.6 Sol <a href="https://gist.github.com/simonw/53be513c1bd4a29a7aa480d9bde9b4a5">wrote the whole thing</a> - it turns out it knows the OpenAI Chat Completions API shape really well.</p> <p>Tags: <a href="https://simonwillison.net/tags/projects">projects</a>, <a href="https://simonwillison.net/tags/openai">openai</a>, <a href="https://simonwillison.net/tags/llm">llm</a></p>