Integrate DynamicContentDetector into CacheAligner (Phase 1)

Add quality retention eval and fix linting for Python 3.12

Add Phase 2 Progressive Summarization and fix Agno integration tests

Implement COMPRESS_FIRST strategy for IntelligentContextManager

Add IntelligentContextManager for semantic-aware context management

Fix test_on_llm_error to pass required run_id argument

Fix HeadroomAgnoModel to extend agno.models.base.Model and add real integration tests

Fix ruff formatting

Add TOIN field-level learning and comprehensive integration tests

Fix mypy type errors in LiteLLM and OpenAI providers

Add Agno agent framework integration

Use LiteLLM for model pricing instead of hardcoded values

Fix flaky JavaScript signature preservation test threshold

Add universal compression module with ML-based content detection

Add persistent memory system with zero-latency inline extraction

Remove unused ProxyConfig import from compression tests

Add tests for compression header removal fix

Add seamless LangChain integration

Add AST-based code compression and custom model configuration

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

Add LLMLingua-2 opt-in support to proxy server

Fix lint errors in text compression utilities

Add opt-in text compression utilities for coding tasks

Fix all mypy type errors and flaky embedding test

Fix all ruff lint and format errors for CI

feat: Add CCR architecture, TOIN telemetry, and DevEx improvements

Add cache optimization module with scalable dynamic content detection

Prepare for OSS release v0.2.0

Initial commit: Headroom SDK - LLM context optimization toolkit