Fix HeadroomAgnoModel to optimize tool outputs at invoke level

Rewrite README with verified before/after examples

Add persistent memory system with zero-latency inline extraction

v0.2.2: Add CCR Response Handler, Context Tracker, and restructure docs

Fix all ruff lint and format errors for CI

Publish headroom-ai v0.2.0 to PyPI with DevEx fixes

Prepare for OSS release v0.2.0

Initial commit: Headroom SDK - LLM context optimization toolkit