Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
chore: release main (#607)
github-actions[bot]01762b1ec791
diff --git a/.release-please-manifest.json b/.release-please-manifest.jsonindex 97bce112d..fc5553b07 100644--- a/.release-please-manifest.json+++ b/.release-please-manifest.json@@ -1,3 +1,3 @@{- ".": "0.23.0"+ ".": "0.24.0"}diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 33f2c5c10..62a2ec69f 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -6,6 +6,31 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).+## [0.24.0](https://github.com/chopratejas/headroom/compare/v0.23.0...v0.24.0) (2026-06-08)+++### Features++* **perf:** add --format {text,json,csv} to `headroom perf` ([#648](https://github.com/chopratejas/headroom/issues/648)) ([9fe4886](https://github.com/chopratejas/headroom/commit/9fe4886cf6b612452f7271d3204872f804074c1f))+* **proxy:** show resolved upstream API targets in startup banner ([#586](https://github.com/chopratejas/headroom/issues/586)) ([8dbe7ad](https://github.com/chopratejas/headroom/commit/8dbe7ad41b3a1d33c01874be5c1cbc68a5e68111)), closes [#583](https://github.com/chopratejas/headroom/issues/583)+* **relevance:** weight BM25 score_batch by corpus IDF ([#646](https://github.com/chopratejas/headroom/issues/646)) ([88177bd](https://github.com/chopratejas/headroom/commit/88177bd7a680490ac85d244c5fff90f21a3be27c))+* support CLAUDE_CODE_USE_FOUNDRY and custom upstream gateways ([#726](https://github.com/chopratejas/headroom/issues/726)) ([d90cdce](https://github.com/chopratejas/headroom/commit/d90cdce3b69bbf27e0f5feea461766a9d797cf7e))+++### Bug Fixes++* **ci:** restore green lint gate on main ([fe50f9d](https://github.com/chopratejas/headroom/commit/fe50f9daed35151134f79b767733d4be8093e325))+* **codex:** auto-enable fail-open on compression timeout in headroom wrap codex ([#531](https://github.com/chopratejas/headroom/issues/531)) ([5f5f261](https://github.com/chopratejas/headroom/commit/5f5f261a035d12d069eb212eb75c472e2c9edeff))+* **copilot:** restore generic endpoint for non-subscription OAuth ([#610](https://github.com/chopratejas/headroom/issues/610)) ([#612](https://github.com/chopratejas/headroom/issues/612)) ([18925b8](https://github.com/chopratejas/headroom/commit/18925b8c6e343c9d593891cd29ac27fee1cb9836))+* **deps:** move gunicorn to [proxy-prod] extra, add Windows guard ([#537](https://github.com/chopratejas/headroom/issues/537)) ([fa558c5](https://github.com/chopratejas/headroom/commit/fa558c5647a91562f4a8fba0271d27b02c8ae01f))+* **proxy:** fail-open on corrupt golden bytes instead of RuntimeError ([#603](https://github.com/chopratejas/headroom/issues/603)) ([2170a1b](https://github.com/chopratejas/headroom/commit/2170a1b4a00e9c46e845993c9b0f6cb2ef0c0684))+* **proxy:** route Claude Code model metadata to Anthropic ([#627](https://github.com/chopratejas/headroom/issues/627)) ([30c1ac8](https://github.com/chopratejas/headroom/commit/30c1ac8656bcc3d11755daef8d1d27cd8770ebc7))+* **security:** patch loopback guard, retry None raise, async subprocess, and cache race ([06d7cb9](https://github.com/chopratejas/headroom/commit/06d7cb9e6c011711a478864a970f7c87ee853a97))+* **security:** patch loopback guard, retry None raise, blocking subprocess, and cache stats race ([78f3a4d](https://github.com/chopratejas/headroom/commit/78f3a4dd3e8e26525822a3c830d576d702dfed8b))+* **startup:** move HF/httpx log suppression before sentence_transformers init ([#622](https://github.com/chopratejas/headroom/issues/622)) ([176d4c7](https://github.com/chopratejas/headroom/commit/176d4c772a7ca8c9da58ca2403f890ba85e8bad8))+* **startup:** suppress proxy startup log noise ([#619](https://github.com/chopratejas/headroom/issues/619)) ([4555901](https://github.com/chopratejas/headroom/commit/45559011b16a2e084dda22c675c819a4789f961d))+* **wrap:** report unbindable proxy ports ([#602](https://github.com/chopratejas/headroom/issues/602)) ([6dfcaa8](https://github.com/chopratejas/headroom/commit/6dfcaa839f1175518e378963c79cc7bd3ceb7946))+## [Unreleased]### Bug Fixesdiff --git a/plugins/openclaw/package.json b/plugins/openclaw/package.jsonindex 1287da5c5..586e59887 100644--- a/plugins/openclaw/package.json+++ b/plugins/openclaw/package.json@@ -1,6 +1,6 @@{"name": "headroom-openclaw",- "version": "0.23.0",+ "version": "0.24.0","description": "Headroom context compression plugin for OpenClaw — 70-90% token savings with zero LLM calls","type": "module","main": "./dist/index.js",diff --git a/pyproject.toml b/pyproject.tomlindex 06cbf2801..b61b69f4f 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "maturin"[project]name = "headroom-ai"-version = "0.23.0"+version = "0.24.0"description = "The Context Optimization Layer for LLM Applications - Cut costs by 50-90%"readme = "README.md"license = "Apache-2.0"diff --git a/sdk/typescript/package.json b/sdk/typescript/package.jsonindex c781a792e..cd1788a95 100644--- a/sdk/typescript/package.json+++ b/sdk/typescript/package.json@@ -1,6 +1,6 @@{"name": "headroom-ai",- "version": "0.23.0",+ "version": "0.24.0","description": "Compress LLM context. Save tokens. Fit more into every request.","type": "module","main": "./dist/index.cjs",