Add observed cache TTL metrics and dashboard coverage

Harden cache validation reporting and TTL analysis

Harden anthropic cache-mode replay stability

Add memory-conscious Claude session benchmark harness

Clarify token vs cache run modes in docs

Rebrand proxy modes to token/cache and harden cache-mode stability

feat(cli): add one-command OpenClaw wrap bootstrap

Update benchmarks with real production telemetry and compression data

Merge remote-tracking branch 'origin/main' into feat/persist-savings-history

feat: add historical rollups and exports

Update Discord invite link across all docs

Merge branch 'main' into feat/persist-savings-history

Merge pull request #60 from gglucass/feat/add-headroom-sdk

feat: add LangGraph compress_tool_messages node for ToolMessage compression

docs: add OpenClaw plugin to README, integration guide, index, and TS SDK docs

feat: persist proxy savings history

feat: allow overriding proxy telemetry sdk via HEADROOM_SDK

Add TypeScript SDK (headroom-ai npm package)

Revamp docs site: new theme, comprehensive landing page, complete nav

Fix docs to match implementation: remove false claims, add Strands guide

Add implementation plan for token headroom mode

Update token headroom mode spec with review fixes

Add design spec for token headroom mode

Add SharedContext for multi-agent, rewrite README, fix proxy cleanup

Updated README and mcp docs

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

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

Add headroom learn: offline failure learning for coding agents

Add OSS evaluation suite, universal JSON crush, latency benchmarks

Rewrite README + add Integration Guide

Add MCP CLI for Claude Code subscription users

Fix mypy errors in html_extraction.py

Add MkDocs GitHub Pages documentation site

docs: update documentation for IntelligentContext TOIN + CCR integration

feat(toin): add TOIN + CCR integration to IntelligentContextManager

feat(toin): extend TOIN integration to all ContentRouter compression strategies

Add image token compression with trained ML router

Remove hardcoded source hint system from ContentRouter

Update memory documentation for HierarchicalMemory system

Add dynamic anchor selection with content deduplication

Add architecture diagrams to README and docs

Merge pull request #8 from nicolabeghin/proxy-custom-openai-api-url

Merge pull request #6 from smartwatermelon/claude/docs-macos-deployment-20260119

docs update

docs(deployment): add macOS LaunchAgent deployment guide and templates

Add IntelligentContextManager for semantic-aware context management

Add feature coverage and known limitations to Agno docs

Add Agno integration documentation

Add universal compression module with ML-based content detection

Add persistent memory system with zero-latency inline extraction