chore: release 0.36.4 (#3189)

🤖 I have created a release *beep* *boop*
---


##
[0.36.4](https://github.com/headroomlabs-ai/headroom/compare/v0.36.3...v0.36.4)
(2026-08-22)


### Bug Fixes

* **dashboard:** pin MIME types for the vendored static assets
([#3193](https://github.com/headroomlabs-ai/headroom/issues/3193))
([b485768](https://github.com/headroomlabs-ai/headroom/commit/b4857685ffca656f8f4f17111b88e80637511f52))
* **proxy/responses:** keep the Codex additional_tools carrier on the
wire ([#3194](https://github.com/headroomlabs-ai/headroom/issues/3194))
([1617f83](https://github.com/headroomlabs-ai/headroom/commit/1617f839a197ed1f17ca2083fbd288ffa2af7820))
* **security:** validate caller-supplied upstreams on every resolution
path ([#3195](https://github.com/headroomlabs-ai/headroom/issues/3195))
([3e3c409](https://github.com/headroomlabs-ai/headroom/commit/3e3c409436792129259cfae3d95179a94321f9ce))
* skip cross-turn dedup pointers on OpenAI chat streaming
([#3191](https://github.com/headroomlabs-ai/headroom/issues/3191))
([9c30b62](https://github.com/headroomlabs-ai/headroom/commit/9c30b629624a42495d82f79fb7df9f21cdac7865))
* **wrap:** make the Serena pre-index stall budget configurable
([#3183](https://github.com/headroomlabs-ai/headroom/issues/3183))
([202c189](https://github.com/headroomlabs-ai/headroom/commit/202c1895e1c2617121f3513054e4a1306d9c573f))

---
This PR was generated with [Release
Please](https://github.com/googleapis/release-please). See
[documentation](https://github.com/googleapis/release-please#release-please).

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
This commit is contained in:
JD Davis
2026-08-21 23:29:15 -07:00
committed by GitHub
co-authored by github-actions[bot]
parent 5d25abd356
commit 91186b40d8
12 changed files with 30 additions and 19 deletions
+2 -2
View File
@@ -5,14 +5,14 @@
},
"metadata": {
"description": "Headroom marketplace for Claude Code and GitHub Copilot CLI plugins.",
"version": "0.36.3"
"version": "0.36.4"
},
"plugins": [
{
"name": "headroom",
"source": "./plugins/headroom-agent-hooks",
"description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",
"version": "0.36.3",
"version": "0.36.4",
"author": {
"name": "Headroom Contributors",
"url": "https://github.com/chopratejas/headroom"
+2 -2
View File
@@ -5,14 +5,14 @@
},
"metadata": {
"description": "Headroom marketplace for Claude Code and GitHub Copilot CLI plugins.",
"version": "0.36.3"
"version": "0.36.4"
},
"plugins": [
{
"name": "headroom",
"source": "./plugins/headroom-agent-hooks",
"description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",
"version": "0.36.3",
"version": "0.36.4",
"author": {
"name": "Headroom Contributors",
"url": "https://github.com/chopratejas/headroom"
+1 -1
View File
@@ -1,3 +1,3 @@
{
".": "0.36.3"
".": "0.36.4"
}
+6 -6
View File
@@ -1,10 +1,10 @@
{
"version": "0.36.3",
"version": "0.36.4",
"packages": {
"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"
"pypi": "0.36.4",
"npm-sdk": "0.36.4",
"npm-openclaw": "0.36.4",
"npm-opencode": "0.36.4",
"agent-hooks-plugin": "0.36.4"
}
}
+11
View File
@@ -284,6 +284,17 @@ 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)).
## [0.36.4](https://github.com/headroomlabs-ai/headroom/compare/v0.36.3...v0.36.4) (2026-08-22)
### Bug Fixes
* **dashboard:** pin MIME types for the vendored static assets ([#3193](https://github.com/headroomlabs-ai/headroom/issues/3193)) ([b485768](https://github.com/headroomlabs-ai/headroom/commit/b4857685ffca656f8f4f17111b88e80637511f52))
* **proxy/responses:** keep the Codex additional_tools carrier on the wire ([#3194](https://github.com/headroomlabs-ai/headroom/issues/3194)) ([1617f83](https://github.com/headroomlabs-ai/headroom/commit/1617f839a197ed1f17ca2083fbd288ffa2af7820))
* **security:** validate caller-supplied upstreams on every resolution path ([#3195](https://github.com/headroomlabs-ai/headroom/issues/3195)) ([3e3c409](https://github.com/headroomlabs-ai/headroom/commit/3e3c409436792129259cfae3d95179a94321f9ce))
* skip cross-turn dedup pointers on OpenAI chat streaming ([#3191](https://github.com/headroomlabs-ai/headroom/issues/3191)) ([9c30b62](https://github.com/headroomlabs-ai/headroom/commit/9c30b629624a42495d82f79fb7df9f21cdac7865))
* **wrap:** make the Serena pre-index stall budget configurable ([#3183](https://github.com/headroomlabs-ai/headroom/issues/3183)) ([202c189](https://github.com/headroomlabs-ai/headroom/commit/202c1895e1c2617121f3513054e4a1306d9c573f))
## [0.36.3](https://github.com/headroomlabs-ai/headroom/compare/v0.36.2...v0.36.3) (2026-08-21)
@@ -1,6 +1,6 @@
{
"name": "headroom",
"version": "0.36.3",
"version": "0.36.4",
"description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",
"author": {
"name": "Headroom Contributors",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "headroom",
"version": "0.36.3",
"version": "0.36.4",
"description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",
"author": {
"name": "Headroom Contributors",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "headroom-openclaw",
"version": "0.36.3",
"version": "0.36.4",
"description": "Headroom context compression plugin for OpenClaw — 70-90% token savings with zero LLM calls",
"type": "module",
"main": "./dist/index.js",
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "headroom-opencode",
"version": "0.36.3",
"version": "0.36.4",
"description": "Headroom proxy integration plugin for OpenCode - routes LLM traffic through the Headroom proxy for token compression",
"type": "module",
"main": "./dist/index.js",
+1 -1
View File
@@ -4,7 +4,7 @@ build-backend = "maturin"
[project]
name = "headroom-ai"
version = "0.36.3"
version = "0.36.4"
description = "The Context Optimization Layer for LLM Applications - Cut costs by 50-90%"
readme = "README.md"
license = "Apache-2.0"
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "headroom-ai",
"version": "0.36.3",
"version": "0.36.4",
"description": "Compress LLM context. Save tokens. Fit more into every request.",
"type": "module",
"main": "./dist/index.cjs",
+2 -2
View File
@@ -9,13 +9,13 @@
"source": "github",
"id": "1129940957"
},
"version": "0.36.3",
"version": "0.36.4",
"packages": [
{
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"identifier": "headroom-ai",
"version": "0.36.3",
"version": "0.36.4",
"runtimeHint": "uvx",
"runtimeArguments": [
{