Simon Willison released llm-echo 0.5, a debug plugin for his LLM CLI tool that simulates a model by echoing prompts back without calling any LLM. The update improves simulated token usage counts to account for tool calls, system prompts, and reasoning tokens. It supports testing LLM PRs without API calls.
Simon Willison released LLM 0.32, the most significant update since the project's launch, adding support for visible reasoning traces, server-side provider tools, and redesigned content-addressable SQLite logs. The update also includes new models and features enabled by the OpenAI Responses API, plus a substantial update to the llm-anthropic plugin.
Simon Willison released LLM 0.32, the most significant update since the project's launch, adding support for visible reasoning traces, server-side provider tools, and redesigned content-addressable SQLite logs. The update also includes new models and features enabled by the OpenAI Responses API, plus a substantial update to the llm-anthropic plugin.
Simon Willison released llm-anthropic 0.27, a plugin for the LLM CLI tool, primarily to ensure compatibility with the recently released anthropic v1.0.0 Python library, which switched from httpx to httpx2. This mirrors a similar change OpenAI made in their v3.0.0 release two weeks prior.
Simon Willison released llm-anthropic 0.27, a plugin for the LLM CLI tool, primarily to ensure compatibility with the recently released anthropic v1.0.0 Python library, which switched from httpx to httpx2. This mirrors a similar change OpenAI made in their v3.0.0 release two weeks prior.
Simon Willison released llm-anthropic 0.26, adding support for Claude Fable 5, Sonnet 5, and Opus 5 models, plus new server-side tools for web search, web fetch, code execution, and MCP. The release depends on LLM 0.32 and replaces the old -o web_search options with -T WebSearch.
Simon Willison released llm-anthropic 0.26, adding support for Claude Fable 5, Sonnet 5, and Opus 5 models, plus new server-side tools for web search, web fetch, code execution, and MCP. The release depends on LLM 0.32 and replaces the old -o web_search options with -T WebSearch.
Simon Willison released llm-openrouter 0.7, updating the plugin for compatibility with LLM 0.32 and improving support for reasoning models via OpenRouter's Responses API. The release adds three new server-side tools: Shell, WebFetch, and likely others, expanding the plugin's capabilities for LLM users.
Simon Willison released llm-openrouter 0.7, updating the plugin for compatibility with LLM 0.32 and improving support for reasoning models via OpenRouter's Responses API. The release adds three new server-side tools: Shell, WebFetch, and likely others, expanding the plugin's capabilities for LLM users.
Simon Willison released llm-typesafe 0.1a0, a plugin for his LLM CLI tool that adds support for TypeSafe AI's new Jev model. The plugin supports three answer types — yes/no 'noul' questions, choice questions, and scoring questions — returning structured JSON output. It gives LLM users CLI access to Jev for classification-style tasks.
Simon Willison released llm-typesafe 0.1a0, a plugin for his LLM CLI tool that adds support for TypeSafe AI's new Jev model. The plugin supports three answer types — yes/no 'noul' questions, choice questions, and scoring questions — returning structured JSON output. It gives LLM users CLI access to Jev for classification-style tasks.