llm-echo 0.5

Simon Willison released llm-echo 0.5, an update to the LLM debug plugin that provides a non-LLM "model" which repeats back the prompts fed to it. The 0.5 release updates the plugin's simulated token usage counts to account for tool calls, system prompts, and reasoning tokens, ahead of an upcoming LLM release. In the documented example, running `llm -m echo 'hi there' -o thinking 1 --usage` reports 2 input and 24 output tokens.

Release: llm-echo 0.5 https://github.com/simonw/llm-echo/releases/tag/0.5 I'm working towards a new LLM https://llm.datasette.io/ release, and testing PRs caused me to revisit the llm-echo debug plugin. This plugin provides a "model" which doesn't involve an LLM at all - it just repeats back the prompts that have been fed to it. The new release now updates the simulated token usage counts to take tool calls, system prompts, and reasoning tokens into account. Example usage: uvx --with llm-echo llm -m echo 'hi there' -o thinking 1 --usage Outputs: First I consider the prompt, then I decide what to say. { "prompt": "hi there", "system": "", "attachments": , "stream": true, "previous": } Token usage: 2 input, 24 output Tags: llm https://simonwillison.net/tags/llm