llm-echo 0.5

AI introduction

Simon Willison updated llm-echo, a debugging plugin for LLM that simulates a "model" that simply echoes back the input prompt without calling any LLM. The new version now includes tool calls, system prompts, and reasoning tokens in its simulated token usage counts, and can be run via uvx with -o thinking 1 --usage to view the output.

Article · English

I'm working towards a new LLM 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

Source: Simon Willison · simonwillison.net