Initial commit: Boltzmann LLM proxy with compression + classifier middleware

- llm-proxy.py v4: aggregator with classify/compress endpoints, gemma4 backend
- classifier-server.py: Llama 3.2 1B query complexity classifier
- compress-server.py: token-budget compression middleware
- start-proxy.sh / start.sh: launcher scripts

start-proxy.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+pkill -f llm-proxy.py 2>/dev/null
+sleep 1
+cd /home/mfritsche/npu
+nohup python3 llm-proxy.py > proxy.log 2>&1 &
+echo "proxy started PID $!"