Opencode reading file again and again and fill context.

via

LocalLlama

So I am using 3.6 35B A3B, pretty good for my work, but the first 64k tokens feels bigger like not a problem, but second time onwards it starts to read every file again and fills up context then context is emptied then it tries to read files again and so on, so no production after that, so what is solution of this, or do I have to start new session every time if so then how it gonna know about project and it will still feel the context so pls mention possible solutions.

More from LocalLlama

The Ultimate LLM Fine-Tuning Guide

LocalLlama·6

Persistent memory system for LLMs that actually learns mid-conversation

LocalLlama·4

3xR9700 for semi-autonomous research and development - looking for setup/config ideas.

LocalLlama·2

Upskill: skill registry your agent consults before it starts. 10k+ indexed, free, open source.

LocalLlama·7

[AutoBe] Local LLM Benchmarks about Backend Generation, Monthly (GLM vs Qwen vs DeepSeek)

LocalLlama·4

Bruh

LocalLlama·7