Skip to content

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.

chore: release 0.43.1 (#4661)

headroom-release[bot]2d3ee5184643
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index 305164245..e1d060272 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": "0.43.0"
+ "version": "0.43.1"
},
"plugins": [
{
"name": "headroom",
"source": "./plugins/headroom-agent-hooks",
"description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",
- "version": "0.43.0",
+ "version": "0.43.1",
"author": {
"name": "Headroom Contributors",
"url": "https://github.com/headroomlabs-ai/headroom"
@@ -30,7 +30,7 @@
"name": "headroom-skill",
"source": "./plugins/headroom-skill",
"description": "Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.",
- "version": "0.43.0",
+ "version": "0.43.1",
"author": {
"name": "Headroom Contributors",
"url": "https://github.com/headroomlabs-ai/headroom"
@@ -52,7 +52,7 @@
"name": "headroom-snip",
"source": "./plugins/headroom-snip",
"description": "Claude Code mod: watch Headroom snip tokens off every request, with an animated band, a /headroom log and a running total.",
- "version": "0.43.0",
+ "version": "0.43.1",
"author": {
"name": "Headroom Contributors",
"url": "https://github.com/headroomlabs-ai/headroom"
diff --git a/.github/plugin/marketplace.json b/.github/plugin/marketplace.json
index 374b92a5e..dd7689170 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": "0.43.0"
+ "version": "0.43.1"
},
"plugins": [
{
"name": "headroom",
"source": "./plugins/headroom-agent-hooks",
"description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",
- "version": "0.43.0",
+ "version": "0.43.1",
"author": {
"name": "Headroom Contributors",
"url": "https://github.com/headroomlabs-ai/headroom"
@@ -30,7 +30,7 @@
"name": "headroom-skill",
"source": "./plugins/headroom-skill",
"description": "Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.",
- "version": "0.43.0",
+ "version": "0.43.1",
"author": {
"name": "Headroom Contributors",
"url": "https://github.com/headroomlabs-ai/headroom"
diff --git a/.release-please-manifest.json b/.release-please-manifest.json
index 2ff8218f3..a02191c5c 100644
--- a/.release-please-manifest.json
+++ b/.release-please-manifest.json
@@ -1,3 +1,3 @@
{
- ".": "0.43.0"
+ ".": "0.43.1"
}
diff --git a/.releasemetadata b/.releasemetadata
index e972b3c33..bd32dbcbe 100644
--- a/.releasemetadata
+++ b/.releasemetadata
@@ -1,10 +1,10 @@
{
- "version": "0.43.0",
+ "version": "0.43.1",
"packages": {
- "pypi": "0.43.0",
- "npm-sdk": "0.43.0",
- "npm-openclaw": "0.43.0",
- "npm-opencode": "0.43.0",
- "agent-hooks-plugin": "0.43.0"
+ "pypi": "0.43.1",
+ "npm-sdk": "0.43.1",
+ "npm-openclaw": "0.43.1",
+ "npm-opencode": "0.43.1",
+ "agent-hooks-plugin": "0.43.1"
}
}
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 51561eb29..9f03a6b67 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -284,6 +284,27 @@ 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)).
+## [0.43.1](https://github.com/headroomlabs-ai/headroom/compare/v0.43.0...v0.43.1) (2026-11-05)
+
+
+### Bug Fixes
+
+* **ccr:** keep the in-memory order queue from evicting re-stored entries ([#4545](https://github.com/headroomlabs-ai/headroom/issues/4545)) ([c6f5bf9](https://github.com/headroomlabs-ai/headroom/commit/c6f5bf9549e9b357e9c2369d4e04bc437f5e180d))
+* **memory:** read the relation key the memory_save schema advertises ([#4647](https://github.com/headroomlabs-ai/headroom/issues/4647)) ([7592e68](https://github.com/headroomlabs-ai/headroom/commit/7592e681459f14a2041eb5f524a658cb6ad1dd92))
+* **memory:** replace the HNSW vector when a memory is re-indexed ([#4649](https://github.com/headroomlabs-ai/headroom/issues/4649)) ([ee638f9](https://github.com/headroomlabs-ai/headroom/commit/ee638f9532b3788bacd13ed8d26dd0faf0740baf))
+* **openclaw:** accept 12-character hashes in headroom_retrieve ([#4640](https://github.com/headroomlabs-ai/headroom/issues/4640)) ([8d3e9e5](https://github.com/headroomlabs-ai/headroom/commit/8d3e9e5ca7cd645eb73084b848edbea5fc796e1a))
+* **ort:** avoid implicit runtime discovery from the workspace ([#4570](https://github.com/headroomlabs-ai/headroom/issues/4570)) ([69fbd23](https://github.com/headroomlabs-ai/headroom/commit/69fbd2390d9c8b0fa1f59fb8314bc9b8f01b1a55))
+* **proxy:** bound the model-keyed tokenizer, beacon and litellm caches ([#4497](https://github.com/headroomlabs-ai/headroom/issues/4497)) ([e51b806](https://github.com/headroomlabs-ai/headroom/commit/e51b8065a4a2aa3a3c7f266c1cb8d8bde6b568d0))
+* **proxy:** use HTTP/1.1 client for ChatGPT streaming and model metadata ([#4006](https://github.com/headroomlabs-ai/headroom/issues/4006)) ([e1becdf](https://github.com/headroomlabs-ai/headroom/commit/e1becdf7329bf4ca03874b9f512ac19837ca29c2))
+* **release:** normalize damaged release PR envelopes before detection ([#4664](https://github.com/headroomlabs-ai/headroom/issues/4664)) ([917edc6](https://github.com/headroomlabs-ai/headroom/commit/917edc62230c3c4a8a415e2053da68dab1f003dd))
+* **router:** keep tagged blocks out of the lossy size-gate fallback ([#4543](https://github.com/headroomlabs-ai/headroom/issues/4543)) ([f333edf](https://github.com/headroomlabs-ai/headroom/commit/f333edf20f0d7acf5ea67e040c1f58539a0edd4d))
+* **router:** log the ONNX fallbacks at info instead of warning ([#4535](https://github.com/headroomlabs-ai/headroom/issues/4535)) ([db30d82](https://github.com/headroomlabs-ai/headroom/commit/db30d82dfffdb3bbe4d60a0e0bfe88640e58470f))
+
+
+### Dependencies
+
+* bump the npm-minor-patch group across 3 directories with 6 updates ([#4662](https://github.com/headroomlabs-ai/headroom/issues/4662)) ([8f104f8](https://github.com/headroomlabs-ai/headroom/commit/8f104f8e298c85ff0005f2fd4848eea95f32b7c7))
+
## [0.43.0](https://github.com/headroomlabs-ai/headroom/compare/v0.42.0...v0.43.0) (2026-11-05)
diff --git a/plugins/headroom-agent-hooks/.claude-plugin/plugin.json b/plugins/headroom-agent-hooks/.claude-plugin/plugin.json
index fd03392b8..5d3c6d22e 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": "0.43.0",
+ "version": "0.43.1",
"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.json
index 03c45b59c..df05fc7de 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": "0.43.0",
+ "version": "0.43.1",
"description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",
"author": {
"name": "Headroom Contributors",
diff --git a/plugins/headroom-skill/.claude-plugin/plugin.json b/plugins/headroom-skill/.claude-plugin/plugin.json
index 9b82ee825..91e40c246 100644
--- a/plugins/headroom-skill/.claude-plugin/plugin.json
+++ b/plugins/headroom-skill/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "headroom-skill",
- "version": "0.43.0",
+ "version": "0.43.1",
"description": "Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.",
"author": {
"name": "Headroom Contributors",
diff --git a/plugins/headroom-skill/.github/plugin/plugin.json b/plugins/headroom-skill/.github/plugin/plugin.json
index 9b82ee825..91e40c246 100644
--- a/plugins/headroom-skill/.github/plugin/plugin.json
+++ b/plugins/headroom-skill/.github/plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "headroom-skill",
- "version": "0.43.0",
+ "version": "0.43.1",
"description": "Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.",
"author": {
"name": "Headroom Contributors",
diff --git a/plugins/headroom-snip/.claude-plugin/plugin.json b/plugins/headroom-snip/.claude-plugin/plugin.json
index 1aa88a4f7..41d803230 100644
--- a/plugins/headroom-snip/.claude-plugin/plugin.json
+++ b/plugins/headroom-snip/.claude-plugin/plugin.json
@@ -1,6 +1,6 @@
{
"name": "headroom-snip",
- "version": "0.43.0",
+ "version": "0.43.1",
"description": "Watch Headroom snip tokens off every Claude Code request: an animated band, a /headroom log and a running total.",
"author": {
"name": "Headroom Contributors",
diff --git a/plugins/openclaw/package.json b/plugins/openclaw/package.json
index 9b82bf63d..2b73e4692 100644
--- a/plugins/openclaw/package.json
+++ b/plugins/openclaw/package.json
@@ -1,6 +1,6 @@
{
"name": "headroom-openclaw",
- "version": "0.43.0",
+ "version": "0.43.1",
"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.json
index e7c2e3f27..cc939b92f 100644
--- a/plugins/opencode/package.json
+++ b/plugins/opencode/package.json
@@ -1,6 +1,6 @@
{
"name": "headroom-opencode",
- "version": "0.43.0",
+ "version": "0.43.1",
"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.toml
index 001179aee..49cf32182 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "maturin"
[project]
name = "headroom-ai"
-version = "0.43.0"
+version = "0.43.1"
description = "Compress tool outputs, logs, JSON and chat history before each LLM call. Fewer input tokens, same answers; in-process, no API key. Library, proxy and MCP server."
# PyPI renders this file; GitHub renders README.md. Keep the two in step on the
# install commands and the savings claim (README.md "Proof" is the source).
diff --git a/sdk/typescript/package.json b/sdk/typescript/package.json
index 14cae80d0..8d8ae6a3f 100644
--- a/sdk/typescript/package.json
+++ b/sdk/typescript/package.json
@@ -1,6 +1,6 @@
{
"name": "headroom-ai",
- "version": "0.43.0",
+ "version": "0.43.1",
"description": "Compress tool outputs, logs, JSON and chat history before each LLM call. Fewer input tokens, same answers. Adapters for OpenAI, Anthropic, Gemini and the Vercel AI SDK. Runs against the local Headroom proxy (pip install \"headroom-ai[proxy]\").",
"keywords": [
"llm",
diff --git a/server.json b/server.json
index 8247bb4a2..3d9ff0447 100644
--- a/server.json
+++ b/server.json
@@ -9,13 +9,13 @@
"source": "github",
"id": "1129940957"
},
- "version": "0.43.0",
+ "version": "0.43.1",
"packages": [
{
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"identifier": "headroom-ai",
- "version": "0.43.0",
+ "version": "0.43.1",
"runtimeHint": "uvx",
"runtimeArguments": [
{
diff --git a/uv.lock b/uv.lock
index d3e9d12b2..afeb53ed9 100644
--- a/uv.lock
+++ b/uv.lock
@@ -1422,7 +1422,7 @@ wheels = [
[[package]]
name = "headroom-ai"
-version = "0.43.0"
+version = "0.43.1"
source = { editable = "." }
dependencies = [
{ name = "ast-grep-cli" },