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

.gitignore

@@ -0,0 +1,5 @@
+*.gguf
+*.log
+llamafile
+*.bak-*
+__pycache__/