chore: release 0.36.2

Author: JerrettDavis

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.36.1"
+  ".": "0.36.2"
 }

CHANGELOG.md

@@ -284,6 +284,16 @@ 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)).
 
+## [0.36.2](https://github.com/headroomlabs-ai/headroom/compare/v0.36.1...v0.36.2) (2026-08-21)
+
+
+### Dependencies
+
+* bump the cargo-minor-patch group with 8 updates ([#3145](https://github.com/headroomlabs-ai/headroom/issues/3145)) ([9c14e3a](https://github.com/headroomlabs-ai/headroom/commit/9c14e3aa9598a01c3cc208c8f483b5dd6398ea1f))
+* bump tiktoken-rs from 0.11.0 to 0.12.0 ([#3147](https://github.com/headroomlabs-ai/headroom/issues/3147)) ([a307c11](https://github.com/headroomlabs-ai/headroom/commit/a307c11109de21b0d5d9648be69b0f08a40d3a4d))
+* bump tokenizers from 0.22.2 to 0.23.1 ([#3149](https://github.com/headroomlabs-ai/headroom/issues/3149)) ([6e2e10f](https://github.com/headroomlabs-ai/headroom/commit/6e2e10f67a737d3b2d844975c1384e02637dbcc3))
+* update mcp requirement from <2.0.0,>=1.28.1 to >=1.28.1,<3.0.0 ([#3144](https://github.com/headroomlabs-ai/headroom/issues/3144)) ([6928d19](https://github.com/headroomlabs-ai/headroom/commit/6928d1932c1136fd1c6bd724ee88d12815ecd2d6))
+
 ## [0.36.1](https://github.com/headroomlabs-ai/headroom/compare/v0.36.0...v0.36.1) (2026-08-20)
 
 

plugins/openclaw/package.json

@@ -1,6 +1,6 @@
 {
   "name": "headroom-openclaw",
-  "version": "0.36.1",
+  "version": "0.36.2",
   "description": "Headroom context compression plugin for OpenClaw — 70-90% token savings with zero LLM calls",
   "type": "module",
   "main": "./dist/index.js",

plugins/opencode/package.json

@@ -1,6 +1,6 @@
 {
   "name": "headroom-opencode",
-  "version": "0.36.1",
+  "version": "0.36.2",
   "description": "Headroom proxy integration plugin for OpenCode - routes LLM traffic through the Headroom proxy for token compression",
   "type": "module",
   "main": "./dist/index.js",

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "headroom-ai"
-version = "0.36.1"
+version = "0.36.2"
 description = "The Context Optimization Layer for LLM Applications - Cut costs by 50-90%"
 readme = "README.md"
 license = "Apache-2.0"

sdk/typescript/package.json

@@ -1,6 +1,6 @@
 {
   "name": "headroom-ai",
-  "version": "0.36.1",
+  "version": "0.36.2",
   "description": "Compress LLM context. Save tokens. Fit more into every request.",
   "type": "module",
   "main": "./dist/index.cjs",