Remove LLMLingua: Kompress is the sole text compressor

Format prefix_cache_benchmark.py for ruff 0.15 compatibility

Introducing headroom wrap

Add OSS evaluation suite, universal JSON crush, latency benchmarks

Add quality retention eval and fix linting for Python 3.12

Enhance /stats endpoint and add comprehensive benchmarks

Fix all ruff lint and format errors for CI

Add cache optimization module with scalable dynamic content detection

Prepare for OSS release v0.2.0

Initial commit: Headroom SDK - LLM context optimization toolkit