Commit message:

Slim core dependencies: 2.5GB → 195MB install size

fix(wrap): route through proxy, prevent pipe deadlock, bump to 0.4.2

Fixing headroom wrap claude

Fix mypy no-any-return errors in kompress_compressor.py

Format prefix_cache_benchmark.py for ruff 0.15 compatibility

Fix pricing lookup for retired Claude models

Fix proxy backend bugs: env vars, tool forwarding, and provider support

Introducing headroom wrap

Kompress: use argmax for token selection, remove hardcoded 0.5 threshold

Add Kompress: ModernBERT token compressor replacing LLMLingua-2

Updating the README to reflect the right positioning for Headroom

feat: provider-aware prefix cache tracking and combined savings dashboard

fix: dashboard metrics, TTFB tracking, eager LLMLingua loading, and multi-provider consistency

docs: add headroom learn demo GIF to README

Fixing the build AND the perf logs

style: ruff format parser.py, content_router.py, smart_crusher.py

fix(learn): pass explicit model in tests to avoid API key requirement

feat: add `headroom perf` CLI and rewrite `headroom learn` to use LLM analysis

fix: harden edge cases, expand tool exclusions, and fix mypy errors

Merge pull request #40 from smartwatermelon/claude/fix-mcp-startup-and-install-20260306

fix(mcp): fix uninstall symmetry, move subprocess import, add cli-path tests

fix(mcp): use claude mcp add for install and fix startup import

Revert "docs: update README demo GIF to headroom_recording.gif"

docs: update README demo GIF to headroom_recording.gif

feat(router): adaptive compression with Read lifecycle and context-pressure scaling

feat(code): add semantic symbol importance to CodeAwareCompressor

Merge pull request #39 from longtngo/fix/dev-deps-sqlite-vec

fix(ci): add sqlite-vec to dev deps to fix memory tests on CI

Merge pull request #38 from longtngo/fix/docker-example-build-deps

fix(docs): fix Docker example and document hnswlib C++ build requirement

Merge pull request #37 from longtngo/fix/docker-install-hnswlib-core-dep

revert: restore hnswlib to core dependencies

fix: remove hnswlib from core deps and fix package name in docs

Add multi-agent support, quality gates, and integration tests for headroom learn

Add headroom learn: offline failure learning for coding agents

Add Cloud mode to ASGI middleware and LiteLLM callback

Fix LangChain tool_call argument handling for varied message formats

Add Read Lifecycle: event-driven stale/superseded Read detection

Add Memory Bridge: bidirectional sync between markdown files and Headroom memory

Fixing the ruff linting

Add OSS evaluation suite, universal JSON crush, latency benchmarks

Merge pull request #33 from angpt/angpt/any-llm-integration

Update CHANGELOG.md

Bump version to 0.3.7

Fix CI: guard starlette imports, asyncio.run(), deprecate datetime.utcnow()

Fix: guard starlette imports in test_compress_api.py for CI without proxy deps

README: replace plain text architecture with Mermaid diagrams

README: add back proof points — needle-in-haystack demo, benchmarks, architecture detail

README: proxy as the hero quickstart, compress() for Python, integration table for existing proxies