Learning to write AI harness old fashioned way. Need help with attention drift and ignoring tool call results!

I've been writing a no-compile no-dependencies node.js based AI Harness for llama.cpp as a learning exercise and can really use some help. I'm basing my code off https://github.com/av/mi and https://pi.dev/ with really basic agentic loops. It basically loop until there are no more tool calls being m

中文全文翻译正在补齐，可先查看下方英文原文。

I've been writing a no-compile no-dependencies node.js based AI Harness for llama.cpp as a learning exercise and can really use some help. I'm basing my code off https://github.com/av/mi and https://pi.dev/ with really basic agentic loops. It basically loop until there are no more tool calls being m