Competence Gate: gating tool-use on a small model's internal confidence signal instead of its verbalised one — Qwen3.5-4B, open weights [P]

Executive Summary

I made a 10MB LoRA adapter for Qwen3.5-4B plus a small orchestration layer. It decides, per query, whether to answer directly, search the web, or retrieve from your own local documents and it refuses to make things up when it can't verify an answer. It runs locally (Apple Silicon / MLX, with a GGUF ...