Fix RTK binary path on Windows (.exe extension)

Add TypeScript SDK (headroom-ai npm package)

Fix CI test, bump to 0.5.7

Fix API integration test: use tool output not user message for tags

Remove LLMLingua: Kompress is the sole text compressor

Protect workflow XML tags from text compression

Add notebook for langchain-ai/how_to_fix_your_context PR

Use realistic verbose RAG chunks in demo — triggers Kompress within-item

Diversity-aware SmartCrusher: keep unique items, compress text within

Pass user query context through proxy pipeline (9 call sites)

Fix context-blind compression: pass user query to SmartCrusher relevance scorer

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

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

Fix test failures: update hash test for MD5, handle unicode surrogates

Reduce proxy latency, enrich telemetry, protect Bash output, bump to 0.5.6

Merge pull request #57 from Softizy/fix/forward-ratelimit-headers-streaming

Dedupe telemetry beacon: upsert per session instead of appending

test: verify ratelimit headers are forwarded in streaming responses

fix: forward upstream ratelimit headers in streaming responses

Skip telemetry when no requests have been processed

Reduce compression latency: cache serializations, eager-load all compressors, fix Magika, bump to 0.5.5

Add headroom_read MCP tool with session caching (feature flag)

Fix ruff format for litellm, wrap, test_scanner

Fix ruff lint errors in test files

Add telemetry beacon, fix Starlette 0.41+ crash, bump to 0.5.4

Pin litellm to v1.82.3 and bump version to 0.5.3

Merge pull request #52 from gglucass/fix/learn-with-dots-in-paths

Merge pull request #53 from Lyt060814/fix/bedrock-eu-region-support

fix(bedrock): add EU/AP region support with graceful fallback

Fix failing test for hidden folders

Fix tests

.

Add path "." compatibility for headroom learn

fix: close TOIN feedback loop — retrievals now flow back for learning

feat: add license key validation + phone-home usage reporter

chore: gitignore headroom-saas (lives in separate private repo)

fix: memory handler overwrites system prompt when it's a list of content blocks

feat: add live traffic learning + cross-agent memory writers (--learn flag)

chore: bump version to 0.5.2

fix: use cache-aware pricing from LiteLLM for dashboard cost display

feat: make token_headroom the default mode + fix Gemini handler bug

refactor: centralize error/priority pattern detection into error_detection module

fix: pass through unknown CLI flags to wrapped tools (claude, codex, aider, cursor)

fix: propagate HEADROOM_MODE through wrap CLI and drop cache write premium penalty

.

chore: bump version to 0.5.1

fix: capture Zone 1 + Zone 2 savings in token_headroom stats

chore: bump version to 0.5.0

Merge feat/token-headroom-mode: dual-mode optimization + clean stats

feat: add clean session summary to /stats and MCP headroom_stats