LLM 发布 0.32rc1 版本，采用内容可寻址哈希ID实现消息去重与分叉对话，并新增对多款 GPT-5.6 模型的支持
多源视角
RT Dan McAteer<br>Codex users: here's an amazing way to take advantage of the efficiency and capability of GPT-5.6 Luna Max.<br><br>It's called 'sol-advisor'.<br><br>1. GPT-5.6 Sol…
查看这条来源<p><strong>Release:</strong> <a href="https://github.com/simonw/llm/releases/tag/0.32rc2">llm 0.32rc2</a></p> <p>Hot on the heels of <a href="https://simonwillison.net/2026/Jul/30/…
查看这条来源Incredible price/performance by the GPT-5.6 series on FrontierCode.<br><br>All Devin users should see the cost decreases reflected automatically!<hr style="border:0;border-top:1px …
查看这条来源Re Fast mode for GPT-5.6 Sol in the API delivers up to 2.5x the speed of Standard processing at 2x the Standard price, with no change in intelligence.<br><br>Existing API requests …
查看这条来源<p><strong>Release:</strong> <a href="https://github.com/simonw/llm/releases/tag/0.32rc1">llm 0.32rc1</a></p> <p>This RC for LLM 0.32 finishes the work that <a href="https://simonw…
查看这条来源AI 摘要
LLM 发布 0.32rc1 版本，采用内容可寻址哈希ID实现消息去重与分叉对话，并新增对多款 GPT-5.6 模型的支持。
推荐理由常规快讯，保留列表
原文
This RC for LLM 0.32 finishes the work that started in LLM 0.32a0 - it adds a new schema design that does a much better job of capturing the details of the prompts and responses returned by the latest model families.
The most important change is the use of content-addressable hash IDs for stored messages. This allows de-duplication in the database, and means that LLM can now represent trees of messages for forked conversations.
Since it involves a significant schema change - new tables only, and old data should not be affected at all - it's worth running a backup of your existing logs.db before upgrading to the RC:
llm logs backup logs-backup.dbThe RC also adds support for gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna.
讨论
暂无评论。