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 0.36.3 (#3188)
JD Davis87e71dd10057
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.jsonindex 9f5e312d0..617d1dc47 100644--- a/.claude-plugin/marketplace.json+++ b/.claude-plugin/marketplace.json@@ -5,14 +5,14 @@},"metadata": {"description": "Headroom marketplace for Claude Code and GitHub Copilot CLI plugins.",- "version": "0.36.2"+ "version": "0.36.3"},"plugins": [{"name": "headroom","source": "./plugins/headroom-agent-hooks","description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",- "version": "0.36.2",+ "version": "0.36.3","author": {"name": "Headroom Contributors","url": "https://github.com/chopratejas/headroom"diff --git a/.github/plugin/marketplace.json b/.github/plugin/marketplace.jsonindex 9f5e312d0..617d1dc47 100644--- a/.github/plugin/marketplace.json+++ b/.github/plugin/marketplace.json@@ -5,14 +5,14 @@},"metadata": {"description": "Headroom marketplace for Claude Code and GitHub Copilot CLI plugins.",- "version": "0.36.2"+ "version": "0.36.3"},"plugins": [{"name": "headroom","source": "./plugins/headroom-agent-hooks","description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",- "version": "0.36.2",+ "version": "0.36.3","author": {"name": "Headroom Contributors","url": "https://github.com/chopratejas/headroom"diff --git a/.release-please-manifest.json b/.release-please-manifest.jsonindex 377c22bf0..e7e03d092 100644--- a/.release-please-manifest.json+++ b/.release-please-manifest.json@@ -1,3 +1,3 @@{- ".": "0.36.2"+ ".": "0.36.3"}diff --git a/.releasemetadata b/.releasemetadataindex d92cde783..437e97615 100644--- a/.releasemetadata+++ b/.releasemetadata@@ -1,10 +1,10 @@{- "version": "0.36.2",+ "version": "0.36.3","packages": {- "pypi": "0.36.2",- "npm-sdk": "0.36.2",- "npm-openclaw": "0.36.2",- "npm-opencode": "0.36.2",- "agent-hooks-plugin": "0.36.2"+ "pypi": "0.36.3",+ "npm-sdk": "0.36.3",+ "npm-openclaw": "0.36.3",+ "npm-opencode": "0.36.3",+ "agent-hooks-plugin": "0.36.3"}}diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 0623fda3c..2aff07855 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -284,6 +284,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0- **code:** fix two `CodeAwareCompressor` AST-reassembly bugs: an exported JS/TS function or class (`export function foo() {`) produced a duplicated `export export` keyword and invalid syntax, because line-based node slicing (used to preserve indentation) pulled in the preceding `export` sibling's text on top of the `export_statement` handler's own prefix reconstruction. Separately, in every supported language, a doc comment immediately above a top-level function, class, or type was detached from its declaration during extraction and re-emitted in a cluster at the end of the compressed output instead of staying attached to what it documents.- * **proxy:** Buffered upstream responses containing a `server_tool_use` (or any other unrecognized Anthropic content block) no longer turn a fully-generated response into an HTTP 502. `StreamingMixin._response_to_sse` raised `ValueError` on unknown block types after the entire upstream generation had already been buffered, so a slow-but-successful response failed and the client retried the whole multi-minute request. Unknown blocks are now emitted verbatim in `content_block_start` (following the existing redacted_thinking` pattern), so `server_tool_use`, `server_tool_result`, `mcp_tool_use`, and future block types round-trip ([#1806](https://github.com/headroomlabs-ai/headroom/issues/1806)).+## [0.36.3](https://github.com/headroomlabs-ai/headroom/compare/v0.36.2...v0.36.3) (2026-08-21)+++### Bug Fixes++* **proxy/responses:** lift Codex >= 0.149.0 additional_tools into top-level tools ([#3186](https://github.com/headroomlabs-ai/headroom/issues/3186)) ([25ca580](https://github.com/headroomlabs-ai/headroom/commit/25ca580825b6d1eef385042fd9524e2da2b2baee))+## [0.36.2](https://github.com/headroomlabs-ai/headroom/compare/v0.36.1...v0.36.2) (2026-08-21)diff --git a/plugins/headroom-agent-hooks/.claude-plugin/plugin.json b/plugins/headroom-agent-hooks/.claude-plugin/plugin.jsonindex dee8237eb..ae574b5b1 100644--- a/plugins/headroom-agent-hooks/.claude-plugin/plugin.json+++ b/plugins/headroom-agent-hooks/.claude-plugin/plugin.json@@ -1,6 +1,6 @@{"name": "headroom",- "version": "0.36.2",+ "version": "0.36.3","description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.","author": {"name": "Headroom Contributors",diff --git a/plugins/headroom-agent-hooks/.github/plugin/plugin.json b/plugins/headroom-agent-hooks/.github/plugin/plugin.jsonindex 39171a5bb..321bb35b1 100644--- a/plugins/headroom-agent-hooks/.github/plugin/plugin.json+++ b/plugins/headroom-agent-hooks/.github/plugin/plugin.json@@ -1,6 +1,6 @@{"name": "headroom",- "version": "0.36.2",+ "version": "0.36.3","description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.","author": {"name": "Headroom Contributors",diff --git a/plugins/openclaw/package.json b/plugins/openclaw/package.jsonindex 1c9d77978..822091e70 100644--- a/plugins/openclaw/package.json+++ b/plugins/openclaw/package.json@@ -1,6 +1,6 @@{"name": "headroom-openclaw",- "version": "0.36.2",+ "version": "0.36.3","description": "Headroom context compression plugin for OpenClaw — 70-90% token savings with zero LLM calls","type": "module","main": "./dist/index.js",diff --git a/plugins/opencode/package.json b/plugins/opencode/package.jsonindex 093f647b1..2b2f8a431 100644--- a/plugins/opencode/package.json+++ b/plugins/opencode/package.json@@ -1,6 +1,6 @@{"name": "headroom-opencode",- "version": "0.36.2",+ "version": "0.36.3","description": "Headroom proxy integration plugin for OpenCode - routes LLM traffic through the Headroom proxy for token compression","type": "module","main": "./dist/index.js",diff --git a/pyproject.toml b/pyproject.tomlindex 33075a08f..5d1cfe4c8 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "maturin"[project]name = "headroom-ai"-version = "0.36.2"+version = "0.36.3"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 691a4a377..ef502915a 100644--- a/sdk/typescript/package.json+++ b/sdk/typescript/package.json@@ -1,6 +1,6 @@{"name": "headroom-ai",- "version": "0.36.2",+ "version": "0.36.3","description": "Compress LLM context. Save tokens. Fit more into every request.","type": "module","main": "./dist/index.cjs",diff --git a/server.json b/server.jsonindex 97fad0573..c4b074c90 100644--- a/server.json+++ b/server.json@@ -9,13 +9,13 @@"source": "github","id": "1129940957"},- "version": "0.36.2",+ "version": "0.36.3","packages": [{"registryType": "pypi","registryBaseUrl": "https://pypi.org","identifier": "headroom-ai",- "version": "0.36.2",+ "version": "0.36.3","runtimeHint": "uvx","runtimeArguments": [{