Context◆Article
Content-addressable logs in LLM 0.32rc1 are designed to support OpenAI Chat Completion style requests where each incoming message extends the previous conversation.
The key design goal of content-addressable logs in LLM 0.32rc1 was enabling OpenAI Chat Completion style requests with growing, client-tracked conversation state. ✦ AI generated
Author · Simon Willison's Weblog · 2026-07-30 · original ↗
A key goal of the new content-addressable logs in LLM 0.32rc1 was being able to support OpenAI Chat Completion style requests where each incoming message extends the previous conversation
Read full article ↗excerpt · fair-use quotation
- ·New in LLM 0.32rc1
- ·Each incoming message extends prior conversation
- ·Enables OpenAI Chat Completion style requests
- ·Client tracks growing conversation state
- ·Log entries addressable by content, not position
- ·Removes need for server-side conversation management
Around this claim
This moment responds to
extends → The new schema design in llm 0.32rc1 does a much better job capturing the details of prompts and responses from the latest model families.Release author · Simon Willison's Weblogexplains mechanism → The new schema design in LLM de-duplicates conversation messages using hashes of individual message parts.Author · Simon Willison's Weblog