New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging
Read OriginalLLM 0.32, a significant update, introduces visible reasoning traces for reasoning models, server-side provider tools (OpenAI CodeInterpreter, WebSearch, Anthropic tools), new GPT-5.6 models, and redesigned content-addressable SQLite logs. It also adds a new 'llm openai endpoint' command for one-off prompts against compatible endpoints, and a Python API enhancement allowing full message history in a single call via model.prompt(messages=[]). The release includes updates to the llm-anthropic plugin with WebFetch, CodeExecution, and AnthropicMCP support.
Comments
No comments yet
Be the first to share your thoughts!
Browser Extension
Get instant access to AllDevBlogs from your browser