llm 0.36
Simon Willison has released llm 0.36, an update to the command-line tool and Python library for working with large language models.
The release adds two new OpenAI models: gpt-6-sol for GPT-6 Sol and gpt-6-luna for GPT-6 Luna.
Model plugins can now declare supports_conversation = False for models that only accept single-turn prompts. When such models receive assistant or tool history, LLM raises llm.ConversationNotSupported, and llm chat rejects them before starting a session. The first plugin to use this capability is llm-typesafe.
Reasoning traces in the Markdown output of llm logs are now wrapped in details and summary tags, so they appear collapsed in rendered Markdown.
The release also includes bug fixes from five new contributors.
Based on reporting from the original publisher. Visit the source for full context and later updates.
Publisher excerpt
Release: llm 0.36 New OpenAI models: gpt-6-sol for GPT-6 Sol and gpt-6-luna for GPT-6 Luna . #1702 Model plugins can now declare supports_conversation = False for models that only accept single-turn prompts. LLM raises llm.ConversationNotSupported when these models receive assistant or tool history, and llm chat rejects them before starting a session. See Models that do not support conversations . The first plugin to use this is llm-typesafe . #1692 Reasoning traces in the Markdown output of llm logs are now wrappe