Aik358/dsh-anchored-monitor

Aik358★ 6JavaScriptLast synced: 2026-08-19

Open on GitHub

Real-time chain-of-thought anchoring monitor & intervention plugin for DeepSeek Harness: three-band (spec/mixed/react) fingerprint detection, L1 hint / L2 reset / L3 restart interventions, liquid-glass web overlay + rheostat bar, standalone monitor process with JSONL experiment logs.

README excerpt

dsh-anchored-monitor English 简体中文 In one sentence (一句话说清): it's a whip for DeepSeek V4 Pro. When the model falls from the focused, high-capability mode ("We need…" / "I will…") into the scattered, low-focus mode ("let me…"), the whip cracks — and pulls it back. 这是给 DeepSeek V4 Pro 加的一根鞭子——当它从「We need / I will」的高专注、高能力模式, 跌落到「let me」的发散、低专注、低效率模式时,就抽它一鞭,让它改回去。 Real-time chain-of-thought anchoring monitor & intervention for DeepSeek Harness. Watch the we / let's / let me fingerprint of every reasoning block, stay in the spec band, and pull the model back automatically when the trajectory drifts. What it is, in one line Don't touch a thing and it's simply a live gauge of how hard your model is thinking right now. Thinking intensity, three-band state and the ECG-style curve, tucked into the corner of your screen — a real-time visualization of your model's thinking efficiency / capability intensity. - Visualization first (default — no intervention until you want it) : a real-time thinking-efficiency / capability-intensity gauge. - Intervention when you need the whip : only cracks when the trajectory drifts into the scattered "let me" band — and it auto-continues the task. - 「滑动变祖器」meme …

View full README on GitHub →
Tools / Devanchoringdeepseek-harnessdsh-pluginmonitoringreasoning

Category