llm 0.36
How-To How to actually use this
What changed: llm 0.36 adds two new OpenAI models and lets model plugins flag single-turn-only support.
How to use it:
- Use gpt-6-sol or gpt-6-luna via llm with their model flags.
- Set supports_conversation = False for single-turn-only models in a plugin.
- Catch llm.ConversationNotSupported when passing history to these models.
- Use llm chat to reject unsupported conversation attempts before a session starts.
Good for: developers working with the llm CLI and OpenAI models.
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…
Read original article on Simon Willison's Weblog →More in Model Releases
