• The default model for users who have not set their own default is now GPT-5.6 Luna. It was previously GPT-4o mini. Luna is a much better and more recent model, albeit slightly more expensive - $0.20 per million input tokens and $1.20 per million output tokens, compared to $0.15/$0.60 for 4o mini. You can switch back to 4o mini using llm models default gpt-4o-mini, or switch to GPT-5 nano, an even cheaper default model ($0.05/$0.40), using llm models default gpt-5-nano. #1576
• New llm openai endpoint command for running prompts, chats and model listings against arbitrary OpenAI-compatible endpoints without first configuring a model. These calls are not logged. #1565
• No longer depends on sqlite-migrate, since that functionality is now handled by sqlite-utils 4.0. #1577
• Fixed a bug where server-executed tool calls were incorrectly reported as pending by LogStore.pending_tool_calls(). Thanks, ikatyal2110. #1574
• schema_dsl() now raises a descriptive ValueError instead of an IndexError for malformed fields with no name before the colon. #1466