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 0.43.0 (#4643)
headroom-release[bot]81fa4bdda613
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.jsonindex 4d7beebd8..305164245 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": "0.42.0"+ "version": "0.43.0"},"plugins": [{"name": "headroom","source": "./plugins/headroom-agent-hooks","description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",- "version": "0.42.0",+ "version": "0.43.0","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": "0.42.0",+ "version": "0.43.0","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": "0.42.0",+ "version": "0.43.0","author": {"name": "Headroom Contributors","url": "https://github.com/headroomlabs-ai/headroom"diff --git a/.github/plugin/marketplace.json b/.github/plugin/marketplace.jsonindex d79a99bb8..374b92a5e 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": "0.42.0"+ "version": "0.43.0"},"plugins": [{"name": "headroom","source": "./plugins/headroom-agent-hooks","description": "Headroom startup hooks for Claude Code and GitHub Copilot CLI.",- "version": "0.42.0",+ "version": "0.43.0","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": "0.42.0",+ "version": "0.43.0","author": {"name": "Headroom Contributors","url": "https://github.com/headroomlabs-ai/headroom"diff --git a/.release-please-manifest.json b/.release-please-manifest.jsonindex 57953081c..2ff8218f3 100644--- a/.release-please-manifest.json+++ b/.release-please-manifest.json@@ -1,3 +1,3 @@{- ".": "0.42.0"+ ".": "0.43.0"}diff --git a/.releasemetadata b/.releasemetadataindex 5a13e0332..e972b3c33 100644--- a/.releasemetadata+++ b/.releasemetadata@@ -1,10 +1,10 @@{- "version": "0.42.0",+ "version": "0.43.0","packages": {- "pypi": "0.42.0",- "npm-sdk": "0.42.0",- "npm-openclaw": "0.42.0",- "npm-opencode": "0.42.0",- "agent-hooks-plugin": "0.42.0"+ "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"}}diff --git a/CHANGELOG.md b/CHANGELOG.mdindex e168eba9e..51561eb29 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -284,6 +284,154 @@ 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)).+## [0.43.0](https://github.com/headroomlabs-ai/headroom/compare/v0.42.0...v0.43.0) (2026-11-05)+++### ⚠ BREAKING CHANGES++* **mcp:** port MCP servers to SDK 2.x ([#4603](https://github.com/headroomlabs-ai/headroom/issues/4603))++### Features++* **ccr:** answer headroom_retrieve on streaming chat completions ([#4631](https://github.com/headroomlabs-ai/headroom/issues/4631)) ([31dcaf4](https://github.com/headroomlabs-ai/headroom/commit/31dcaf41f7fafaebec0838a05ff328da456faef0))+* **mcp:** port MCP servers to SDK 2.x ([#4603](https://github.com/headroomlabs-ai/headroom/issues/4603)) ([ee2252a](https://github.com/headroomlabs-ai/headroom/commit/ee2252a3155c87e948c8893b79af5824eb30e64c))+* **plugins:** headroom skill for Claude Code, Codex, Copilot and skills.sh ([#4533](https://github.com/headroomlabs-ai/headroom/issues/4533)) ([66e1467](https://github.com/headroomlabs-ai/headroom/commit/66e14676827366c2bf8d15e252f8766cb27b1a98))+* **savings:** show the proxy's model-routing savings in headroom savings ([#4304](https://github.com/headroomlabs-ai/headroom/issues/4304)) ([aaab338](https://github.com/headroomlabs-ai/headroom/commit/aaab338b64cb55929de904411db65db126e22ec0))+++### Bug Fixes++* [BUG] A timeout in one image compression call resets the shared worker pool and affects concurrent requests ([#4528](https://github.com/headroomlabs-ai/headroom/issues/4528)) ([e9bcfe7](https://github.com/headroomlabs-ai/headroom/commit/e9bcfe73fadf69f0b27b7bc338ea7d2380931054))+* [BUG] DirectMem0Adapter.search_memories calls removed mem0 search API ([#4518](https://github.com/headroomlabs-ai/headroom/issues/4518)) ([d9cee45](https://github.com/headroomlabs-ai/headroom/commit/d9cee452681c79d6f13919e9e651e88a774c0874))+* [BUG] Saved request metrics lose their cache optimization fields ([#4584](https://github.com/headroomlabs-ai/headroom/issues/4584)) ([b4c9bdf](https://github.com/headroomlabs-ai/headroom/commit/b4c9bdf100d97fb038beba95de6d4ad6a8786090))+* [BUG] Volatile SQLite metrics stores lose their schema before the first save ([#4633](https://github.com/headroomlabs-ai/headroom/issues/4633)) ([d8ff0fe](https://github.com/headroomlabs-ai/headroom/commit/d8ff0fe9d2cb2477f6662a90f8fcd7e030a52666))+* Add info about apply to README.md ([#1592](https://github.com/headroomlabs-ai/headroom/issues/1592)) ([4d34680](https://github.com/headroomlabs-ai/headroom/commit/4d34680c34ad379d693820869e77d4a2a6be2cdf))+* **backends/litellm:** keep cache_control on text blocks for Bedrock prompt caching ([#4565](https://github.com/headroomlabs-ai/headroom/issues/4565)) ([23a5bb1](https://github.com/headroomlabs-ai/headroom/commit/23a5bb1c81dc943398f9271f068a02487207f2e7))+* **backends:** forward the standard service_tier param (litellm + anyllm) ([#2468](https://github.com/headroomlabs-ai/headroom/issues/2468)) ([62cc38a](https://github.com/headroomlabs-ai/headroom/commit/62cc38a6b09dbcf723681a0ff56acd02131ad1f1))+* **cache:** build semantic entry before evicting so a failed embedding keeps live entries ([#4581](https://github.com/headroomlabs-ai/headroom/issues/4581)) ([0d4c450](https://github.com/headroomlabs-ai/headroom/commit/0d4c450d774691568b850f0d22ce17e087405281))+* **cache:** count a tool_result with no text as replayable in the frozen prefix ([#4523](https://github.com/headroomlabs-ai/headroom/issues/4523)) ([fba09f6](https://github.com/headroomlabs-ai/headroom/commit/fba09f674c8a9c91b39a563a70ab7727b44d1dbc))+* **cache:** fail closed on SQLite corruption instead of deleting the store online ([#4361](https://github.com/headroomlabs-ai/headroom/issues/4361)) ([9801833](https://github.com/headroomlabs-ai/headroom/commit/98018333f997783487af15efe4d9e631ecd85939))+* **cache:** invalidate configured registry instances on replacement ([#4363](https://github.com/headroomlabs-ai/headroom/issues/4363)) ([1bcdca2](https://github.com/headroomlabs-ai/headroom/commit/1bcdca2d9dd279f49aa4276d523d93c2cfeb5a51))+* **cache:** namespace SemanticCacheLayer by provider, model and metadata ([#4473](https://github.com/headroomlabs-ai/headroom/issues/4473)) ([99cdaaf](https://github.com/headroomlabs-ai/headroom/commit/99cdaaf1c7de2bd81a8e64f198462fd1ceec3a17))+* **cache:** preserve OpenAI tool block metadata on cached replay ([#4334](https://github.com/headroomlabs-ai/headroom/issues/4334)) ([f1035ac](https://github.com/headroomlabs-ai/headroom/commit/f1035ac73788a577fb5495a59eed0fc925d42782))+* **cache:** scope router results to request compression policy ([#4590](https://github.com/headroomlabs-ai/headroom/issues/4590)) ([5d40fe7](https://github.com/headroomlabs-ai/headroom/commit/5d40fe76471b12ffe2a5c81309d9df617ca60b41))+* **ccr:** buffer a stream only for a marker new this turn ([#4607](https://github.com/headroomlabs-ai/headroom/issues/4607)) ([946a70c](https://github.com/headroomlabs-ai/headroom/commit/946a70cfcbdc522f940b01f0aeb2b7a214f54cb5))+* **ccr:** keep proactive expansion out of the cached prefix ([#4300](https://github.com/headroomlabs-ai/headroom/issues/4300)) ([b1f340e](https://github.com/headroomlabs-ai/headroom/commit/b1f340e0b35d4659d7ebc993d9dcc08057da93e9))+* **cli:** document that code-aware compression is enabled by default ([#4616](https://github.com/headroomlabs-ai/headroom/issues/4616)) ([affd17c](https://github.com/headroomlabs-ai/headroom/commit/affd17c5fde174ad78287eef1696251e18363722))+* **client:** close upstream responses when wrapped streams are closed ([#4482](https://github.com/headroomlabs-ai/headroom/issues/4482)) ([3d8dcf4](https://github.com/headroomlabs-ai/headroom/commit/3d8dcf476c148f633e66eb98c478095adfd9354b))+* **client:** honor configured cache optimizer enablement ([#4501](https://github.com/headroomlabs-ai/headroom/issues/4501)) ([d4c0810](https://github.com/headroomlabs-ai/headroom/commit/d4c0810ea3ebdd7e49e5d29f4e0dfd2da1511b02))+* **client:** preserve Anthropic create stream flags ([#4500](https://github.com/headroomlabs-ai/headroom/issues/4500)) ([3910caa](https://github.com/headroomlabs-ai/headroom/commit/3910caabd68311ae99d5659aa2d470eb2c15ea0e))+* **codex:** accept multi-line inline tables in Codex config.toml ([#4436](https://github.com/headroomlabs-ai/headroom/issues/4436)) ([4a851ed](https://github.com/headroomlabs-ai/headroom/commit/4a851ed25469a51de00ccd00d14d0a6ab62a0866))+* **compaction:** reject negative dictionary indices and non-array legends in expand_compacted ([#4470](https://github.com/headroomlabs-ai/headroom/issues/4470)) ([3c1fcbd](https://github.com/headroomlabs-ai/headroom/commit/3c1fcbdfde31069795b03faf9f43fdd73e6941d9))+* **core:** case-insensitive Bearer scheme, clamp SQLite CCR TTLs, redact the Redis URL in logs ([#4561](https://github.com/headroomlabs-ai/headroom/issues/4561)) ([9e8cc64](https://github.com/headroomlabs-ai/headroom/commit/9e8cc64b48ebd4e2fb31332f261464d3bd0550b7))+* **dedup:** bound line-number digit run and never fold into a longer pointer ([#4488](https://github.com/headroomlabs-ai/headroom/issues/4488)) ([21e8867](https://github.com/headroomlabs-ai/headroom/commit/21e8867504df57c8f99aa30bd889e7eed01cd49e))+* **deps:** clear the glob and minimatch npm audit findings ([#4599](https://github.com/headroomlabs-ai/headroom/issues/4599)) ([2e49e53](https://github.com/headroomlabs-ai/headroom/commit/2e49e5304b245fdaca0d2640bb1a59cb1ffa63fc))+* **diff:** keep combined-diff changes made against a later parent ([#4318](https://github.com/headroomlabs-ai/headroom/issues/4318)) ([4b788fd](https://github.com/headroomlabs-ai/headroom/commit/4b788fd04d407cea0113c74f979f7cc3072a0132))+* **docker:** install the redis extra in every image ([#4514](https://github.com/headroomlabs-ai/headroom/issues/4514)) ([8d5dde7](https://github.com/headroomlabs-ai/headroom/commit/8d5dde77656c9bb3daa354a14ffa6904cb8311aa))+* **docker:** pass RUNTIME_HOME=/root for root bake targets ([#4445](https://github.com/headroomlabs-ai/headroom/issues/4445)) ([670767e](https://github.com/headroomlabs-ai/headroom/commit/670767eeb49f224a7a0bcbcc31b3584a35110b7d))+* **doctor:** detect root openai_base_url Codex routing and agent-configured proxy ports ([#4490](https://github.com/headroomlabs-ai/headroom/issues/4490)) ([222f2d1](https://github.com/headroomlabs-ai/headroom/commit/222f2d1df3c6296462bc38c871cd29c221af55bc))+* **evals:** reject changed numeric probe values ([#4502](https://github.com/headroomlabs-ai/headroom/issues/4502)) ([1fe8549](https://github.com/headroomlabs-ai/headroom/commit/1fe8549f9ca77a2bc1280e4319980e0b9b31f5b9))+* **install:** stabilize Windows task lifecycle and eliminate console window popup ([#4627](https://github.com/headroomlabs-ai/headroom/issues/4627)) ([6b903cb](https://github.com/headroomlabs-ai/headroom/commit/6b903cbc81c13f417485f059aa6ef7aca6b0c4ec))+* **install:** tolerate absent Windows tasks in stop_supervisor ([#4465](https://github.com/headroomlabs-ai/headroom/issues/4465)) ([#4468](https://github.com/headroomlabs-ai/headroom/issues/4468)) ([50af2ff](https://github.com/headroomlabs-ai/headroom/commit/50af2ff7a81efb89d6752374a811be4fa2eec6f6))+* **kompress:** keep words past the tokenizer's truncation point ([#4328](https://github.com/headroomlabs-ai/headroom/issues/4328)) ([bb13384](https://github.com/headroomlabs-ai/headroom/commit/bb13384829069e7e0559fccf77620891e0c90be0))+* **kompress:** read the pinned snapshot from Python's one HF cache in the native proxy ([#4438](https://github.com/headroomlabs-ai/headroom/issues/4438)) ([eef44f6](https://github.com/headroomlabs-ai/headroom/commit/eef44f60cc56118a0de98455012cc18ff3eaafbd))+* **langgraph:** replace the compressed ToolMessage in graph state ([#4620](https://github.com/headroomlabs-ai/headroom/issues/4620)) ([70a8f09](https://github.com/headroomlabs-ai/headroom/commit/70a8f0979e585aa4e9b6f663fa7528340fb4efd6))+* **mcp:** confine headroom_read to the workspace (GHSA-8g49-pg6g-xgrf) ([#4525](https://github.com/headroomlabs-ai/headroom/issues/4525)) ([8ab2e91](https://github.com/headroomlabs-ai/headroom/commit/8ab2e914687266f5b602f6d3a78f13026fd5ef88))+* **memory:** bound verb-pattern word runs to stop quadratic backtracking in bridge import ([#4370](https://github.com/headroomlabs-ai/headroom/issues/4370)) ([#4376](https://github.com/headroomlabs-ai/headroom/issues/4376)) ([d232d09](https://github.com/headroomlabs-ai/headroom/commit/d232d097cf33d92f3a5112c14a306ba4a80330ee))+* **memory:** fail close unresolved project operations ([#2637](https://github.com/headroomlabs-ai/headroom/issues/2637)) ([957ab18](https://github.com/headroomlabs-ai/headroom/commit/957ab1830d73a39ba7662ee9b01dd22c7abd403e))+* **memory:** keep learned evidence until persistence succeeds ([#4229](https://github.com/headroomlabs-ai/headroom/issues/4229)) ([662a7f6](https://github.com/headroomlabs-ai/headroom/commit/662a7f6fd836ca87db5f2093c6487b500e8da2eb))+* **memory:** preserve parent scopes when clearing memories ([#4305](https://github.com/headroomlabs-ai/headroom/issues/4305)) ([a8375a1](https://github.com/headroomlabs-ai/headroom/commit/a8375a1d26c5fc6dd619bfa7a50a15bbba18acf3))+* **mixed-content:** do not carve ISO-timestamped log rows as search results ([#4463](https://github.com/headroomlabs-ai/headroom/issues/4463)) ([abbade9](https://github.com/headroomlabs-ai/headroom/commit/abbade9b4c761a82f711d0687703d0409fbe6edc))+* **offline:** guard the learn and memory-eval LLM calls under HEADROOM_OFFLINE ([#4344](https://github.com/headroomlabs-ai/headroom/issues/4344)) ([dd361bb](https://github.com/headroomlabs-ai/headroom/commit/dd361bb7a3a1d3f2e3c7572bf544ea4ea895b0a5))+* **openclaw/release:** ship responsive npm integrations ([#1458](https://github.com/headroomlabs-ai/headroom/issues/1458)) ([33f2044](https://github.com/headroomlabs-ai/headroom/commit/33f204406cc670588b9a873678b74b4af6ca3620))+* **openclaw:** record turn advancements as one marker file per key ([#4212](https://github.com/headroomlabs-ai/headroom/issues/4212)) ([24acbe8](https://github.com/headroomlabs-ai/headroom/commit/24acbe8f32b6d49e3f61097398330e7529729d3e))+* **opencode:** only route POST requests to LLM endpoint paths ([#4464](https://github.com/headroomlabs-ai/headroom/issues/4464)) ([336d462](https://github.com/headroomlabs-ai/headroom/commit/336d46225370c946ad8420ecb3f6bac81193e2f7))+* **opencode:** route Copilot Claude models through the proxy ([#4594](https://github.com/headroomlabs-ai/headroom/issues/4594)) ([3d9a6f2](https://github.com/headroomlabs-ai/headroom/commit/3d9a6f2cf7fefa2cd0d347521e0050d604a50d22))+* **output-savings:** rewrite a pre-rule ledger once instead of warning on every /stats poll ([#4196](https://github.com/headroomlabs-ai/headroom/issues/4196)) ([96e81ac](https://github.com/headroomlabs-ai/headroom/commit/96e81ac6703dcfcf4535f989319d677775e2384d))+* **packaging:** rename the sandbox extra to lean and correct SECURITY.md claims ([#3727](https://github.com/headroomlabs-ai/headroom/issues/3727)) ([09b7e8c](https://github.com/headroomlabs-ai/headroom/commit/09b7e8c1e41779b4c22f1a4ec941b59a61e621f1))+* **packaging:** use direct CLI module entry point ([#2665](https://github.com/headroomlabs-ai/headroom/issues/2665)) ([2892214](https://github.com/headroomlabs-ai/headroom/commit/28922148816b2b6ebf192abfcd6e65db8bb71511))+* **pipeline:** store the pipeline input in CCR behind offload markers ([#4576](https://github.com/headroomlabs-ai/headroom/issues/4576)) ([4d7765c](https://github.com/headroomlabs-ai/headroom/commit/4d7765c84b06d1a8630faa32a897a39a40261cd1))+* **pricing:** add Claude Haiku 5.5 rates, 1M context and its 100K long-prompt card ([#4037](https://github.com/headroomlabs-ai/headroom/issues/4037)) ([703755e](https://github.com/headroomlabs-ai/headroom/commit/703755e873d3af74b89d25792c7c9869322b0467))+* **privacy:** turn off Mem0's PostHog telemetry by default ([#4619](https://github.com/headroomlabs-ai/headroom/issues/4619)) ([fe69f38](https://github.com/headroomlabs-ai/headroom/commit/fe69f381168035ea6527bb7b908d11eeeb01838f))+* **providers:** isolate resolved Anthropic context limits ([#4593](https://github.com/headroomlabs-ai/headroom/issues/4593)) ([51258ef](https://github.com/headroomlabs-ai/headroom/commit/51258ef14a987b2c3137027e0c90f586eb290462))+* **proxy/memory:** harden _extract_tool_calls against malformed choices and blocks ([#2483](https://github.com/headroomlabs-ai/headroom/issues/2483)) ([effa5a5](https://github.com/headroomlabs-ai/headroom/commit/effa5a5886be7e3c5bc553b86da5b506046d461f))+* **proxy:** allow loopback-published container hosts to access /debug/memory ([#4259](https://github.com/headroomlabs-ai/headroom/issues/4259)) ([e546e71](https://github.com/headroomlabs-ai/headroom/commit/e546e71aeb32c355584d37abb61e8d587efce0c3))+* **proxy:** answer /api/hello probes behind the token gate, log rejection context ([#4150](https://github.com/headroomlabs-ai/headroom/issues/4150)) ([673831a](https://github.com/headroomlabs-ai/headroom/commit/673831a456ef0f551de8dc3b2cbb0deae3861c65))+* **proxy:** cap cache_control breakpoints on OpenAI chat path ([#4471](https://github.com/headroomlabs-ai/headroom/issues/4471)) ([#4491](https://github.com/headroomlabs-ai/headroom/issues/4491)) ([55602fc](https://github.com/headroomlabs-ai/headroom/commit/55602fc1e207e7101917e45bf6dba30ce544558c))+* **proxy:** do not book Gemini countTokens as a request outcome ([#4412](https://github.com/headroomlabs-ai/headroom/issues/4412)) ([4d2dd62](https://github.com/headroomlabs-ai/headroom/commit/4d2dd62b7c61724497b4bde33ef8685717f6a682))+* **proxy:** don't fail startup when libc_ver() can't read the interpreter ([#4519](https://github.com/headroomlabs-ai/headroom/issues/4519)) ([28172a9](https://github.com/headroomlabs-ai/headroom/commit/28172a921f4e3945aa43061a9e5cdd0ffd066c0e))+* **proxy:** forward Copilot accounting headers on streaming path ([#4431](https://github.com/headroomlabs-ai/headroom/issues/4431)) ([66023a0](https://github.com/headroomlabs-ai/headroom/commit/66023a0187b3260747ece4e99e6932098805442a))+* **proxy:** handle ClientDisconnect in anthropic_messages ([#3532](https://github.com/headroomlabs-ai/headroom/issues/3532)) ([251d149](https://github.com/headroomlabs-ai/headroom/commit/251d149a13ae482c1a0843d899b0321e175ac66d))+* **proxy:** honor x-headroom-base-url on provider passthrough routes ([#4596](https://github.com/headroomlabs-ai/headroom/issues/4596)) ([5c8772b](https://github.com/headroomlabs-ai/headroom/commit/5c8772b7210caeb291a202a58d4b5e88d51ff35b))+* **proxy:** install SOCKS support for websocket proxies ([#3357](https://github.com/headroomlabs-ai/headroom/issues/3357)) ([79181ca](https://github.com/headroomlabs-ai/headroom/commit/79181ca0fe35798b25104ff93b2c3a6c38baa72c))+* **proxy:** keep Gemini memory context on entries with non-text parts ([#4506](https://github.com/headroomlabs-ai/headroom/issues/4506)) ([35a2b76](https://github.com/headroomlabs-ai/headroom/commit/35a2b763f09bb147888aeeec69f72d1ed3ae872b))+* **proxy:** keep health probes and the Codex attestation out of the proxy log ([#4611](https://github.com/headroomlabs-ai/headroom/issues/4611)) ([78736a1](https://github.com/headroomlabs-ai/headroom/commit/78736a16bc46ee0bd86b7aae8ef04f7f9cfa9d6d))+* **proxy:** keep read maturation out of the provider-confirmed prefix ([#4522](https://github.com/headroomlabs-ai/headroom/issues/4522)) ([526e06b](https://github.com/headroomlabs-ai/headroom/commit/526e06b7e0120820e5b1be44b4ded70698bb86c8))+* **proxy:** keep tool deferral on Copilot Business/Enterprise/Individual hosts ([#4608](https://github.com/headroomlabs-ai/headroom/issues/4608)) ([be456d4](https://github.com/headroomlabs-ai/headroom/commit/be456d4e3f46c7f4dae725c2dd150324000c724f))+* **proxy:** log unknown model ids as one bounded token; skip unparseable PERF lines ([#4374](https://github.com/headroomlabs-ai/headroom/issues/4374)) ([c014bd6](https://github.com/headroomlabs-ai/headroom/commit/c014bd6311742e35c86ef64adfbec88ab264ef28))+* **proxy:** preserve response cache keys across in-place hooks ([#4457](https://github.com/headroomlabs-ai/headroom/issues/4457)) ([03590cd](https://github.com/headroomlabs-ai/headroom/commit/03590cd61e17ad1ef313e38a35932f729ff0c871))+* **proxy:** recognise every local spelling of the proxy in the cc-switch loop guard ([#4405](https://github.com/headroomlabs-ai/headroom/issues/4405)) ([d9958bf](https://github.com/headroomlabs-ai/headroom/commit/d9958bfdff047ff2a7ef26f9e29fc7263f790346))+* **proxy:** reconcile Chat content-block cache markers after prefix replay ([#4333](https://github.com/headroomlabs-ai/headroom/issues/4333)) ([35ca9b8](https://github.com/headroomlabs-ai/headroom/commit/35ca9b835616f7923eab23e99e9561a8da452f9f))+* **proxy:** route /v1/models to the x-headroom-base-url upstream ([#4308](https://github.com/headroomlabs-ai/headroom/issues/4308)) ([6ef52c2](https://github.com/headroomlabs-ai/headroom/commit/6ef52c2047688e41c7903a0331149a915f20d6b3))+* **proxy:** skip memory-context search in cache mode on OpenAI routes ([#4632](https://github.com/headroomlabs-ai/headroom/issues/4632)) ([365f6fe](https://github.com/headroomlabs-ai/headroom/commit/365f6fe5233c4e102584ee4c3e7a140aeccb6a75))+* **proxy:** skip memory-context search on OpenAI paths in cache mode ([#4634](https://github.com/headroomlabs-ai/headroom/issues/4634)) ([3654037](https://github.com/headroomlabs-ai/headroom/commit/36540379e0dee0c071e3a3ff00bea9b16eb3902a))+* **proxy:** skip the memory-context search in cache mode ([#4606](https://github.com/headroomlabs-ai/headroom/issues/4606)) ([053925b](https://github.com/headroomlabs-ai/headroom/commit/053925b03c6cae028731634f0ad3557518f931d5))+* **proxy:** strip only one leading space from SSE field values ([#4306](https://github.com/headroomlabs-ai/headroom/issues/4306)) ([9226eaf](https://github.com/headroomlabs-ai/headroom/commit/9226eaf3852f6d7462ebb95e6d09af3b33eb53c3))+* **proxy:** strip upstream transport framing headers from Gemini response replays ([#4605](https://github.com/headroomlabs-ai/headroom/issues/4605)) ([dfcac78](https://github.com/headroomlabs-ai/headroom/commit/dfcac78119b7038b2e20ad38cead2f4e7fe60c43))+* **read-lifecycle:** keep Reads fresh after a failed Edit or Write ([#4461](https://github.com/headroomlabs-ai/headroom/issues/4461)) ([4c3799f](https://github.com/headroomlabs-ai/headroom/commit/4c3799fd81567cd516cdc5c1463f23cea99d6594))+* **relevance:** cap embedding batch size so ORT's arena stays small ([#4507](https://github.com/headroomlabs-ai/headroom/issues/4507)) ([a2d4fe7](https://github.com/headroomlabs-ai/headroom/commit/a2d4fe72381e186651466ee94e92ce9d8d1396cc))+* **relevance:** hand the embedding arena back after each run on macOS ([#4567](https://github.com/headroomlabs-ai/headroom/issues/4567)) ([2363f83](https://github.com/headroomlabs-ai/headroom/commit/2363f833092052227a9b98a9e21a0b1a69647eab))+* **relevance:** load the Rust default embedder from Python's pinned snapshot ([#4190](https://github.com/headroomlabs-ai/headroom/issues/4190)) ([9bb4b13](https://github.com/headroomlabs-ai/headroom/commit/9bb4b130ff87a2914a8f74dbcc6b49b49c3c87a8))+* **router:** keep small shell results verbatim ([#3590](https://github.com/headroomlabs-ai/headroom/issues/3590)) ([#4426](https://github.com/headroomlabs-ai/headroom/issues/4426)) ([4ee6164](https://github.com/headroomlabs-ai/headroom/commit/4ee616453fcebed5ab7ce847e1da1016c827a4ed))+* **router:** preserve read protection for quiet sed options ([#4521](https://github.com/headroomlabs-ai/headroom/issues/4521)) ([312ffec](https://github.com/headroomlabs-ai/headroom/commit/312ffec8ead5c8c93b8f4c794ca7f588a7b84bd2))+* **router:** validate lossless provider output on the excluded-tool path ([#4486](https://github.com/headroomlabs-ai/headroom/issues/4486)) ([9f068a6](https://github.com/headroomlabs-ai/headroom/commit/9f068a6c135730c1bd4f1d800083f9318a3067a4))+* **scripts:** resolve hooks dir via git so install-git-hooks works in linked worktrees ([#4176](https://github.com/headroomlabs-ai/headroom/issues/4176)) ([0f4275f](https://github.com/headroomlabs-ai/headroom/commit/0f4275f8b331f3db14c41d958c85180a3c70a318))+* **sdk:** carry Vercel AI SDK reasoning parts and provider options through compression ([#4564](https://github.com/headroomlabs-ai/headroom/issues/4564)) ([a26faae](https://github.com/headroomlabs-ai/headroom/commit/a26faaeee34ecfde57608aea4a1ec7ea2b33272f))+* **sdk:** send Anthropic messages to /v1/compress natively so thinking blocks survive ([#4489](https://github.com/headroomlabs-ai/headroom/issues/4489)) ([cd5e2b9](https://github.com/headroomlabs-ai/headroom/commit/cd5e2b9e73eb8bd783ab872bdda71263b941e2d3))+* **security:** lstat before narrowing sqlite files ([#4527](https://github.com/headroomlabs-ai/headroom/issues/4527)) ([2cf64ef](https://github.com/headroomlabs-ai/headroom/commit/2cf64ef0cc918c7cdb3de98d56f48fdc9c4c2b4b))+* **smart-crusher:** preserve unchanged JSON bytes ([#4044](https://github.com/headroomlabs-ai/headroom/issues/4044)) ([93279f3](https://github.com/headroomlabs-ai/headroom/commit/93279f3208b1afffdbba87c2fdecbeea246d5234))+* **tabular:** keep empty records and separator-like Markdown body rows ([#4582](https://github.com/headroomlabs-ai/headroom/issues/4582)) ([5cebb90](https://github.com/headroomlabs-ai/headroom/commit/5cebb90db1f179b00eafdf79568efbc98c8ef366))+* **tabular:** keep interior blank CSV rows instead of dropping them ([#4563](https://github.com/headroomlabs-ai/headroom/issues/4563)) ([8c360ca](https://github.com/headroomlabs-ai/headroom/commit/8c360ca69fd3fc9cd6bc1e4b02109c1e5595385c))+* **thinking:** isolate compaction memo by compressor instance ([#4569](https://github.com/headroomlabs-ai/headroom/issues/4569)) ([5dcb1e4](https://github.com/headroomlabs-ai/headroom/commit/5dcb1e4adec4f6e82d943488d8aecb8967753e4e))+* **thinking:** leave a thinking block with a null or non-string value unchanged ([#4562](https://github.com/headroomlabs-ai/headroom/issues/4562)) ([cc1eb54](https://github.com/headroomlabs-ai/headroom/commit/cc1eb5402aade58204b96b6b4b4d280cdd5456d2))+* **toin:** preserve stores that exceed the byte limit ([#4589](https://github.com/headroomlabs-ai/headroom/issues/4589)) ([f9cae66](https://github.com/headroomlabs-ai/headroom/commit/f9cae66b6b19d6e6acfa4bf6da031642c256404a))+* **toin:** retain pending changes after filesystem save failures ([#4568](https://github.com/headroomlabs-ai/headroom/issues/4568)) ([8b15a15](https://github.com/headroomlabs-ai/headroom/commit/8b15a15799898d8c0a396ca0d39f951be4e0cfcf))+* **toin:** skip a malformed pattern instead of aborting the store load ([#4484](https://github.com/headroomlabs-ai/headroom/issues/4484)) ([8b628d9](https://github.com/headroomlabs-ai/headroom/commit/8b628d968574053b26849b21e5cea2e2593691c5))+* **tokenizers:** coerce structured text values in message token counters ([#4472](https://github.com/headroomlabs-ai/headroom/issues/4472)) ([6cc27a4](https://github.com/headroomlabs-ai/headroom/commit/6cc27a453d9cf69c76dc8134eb6739891471716e))+* **tokenizers:** don't cache token-count inputs larger than max_chars ([#4469](https://github.com/headroomlabs-ai/headroom/issues/4469)) ([aebb729](https://github.com/headroomlabs-ai/headroom/commit/aebb729ef3f03bee8852d067c365f075957638f9))+* **tokenizers:** price Anthropic document blocks by page count, not as ([fc1ba89](https://github.com/headroomlabs-ai/headroom/commit/fc1ba891bff2d1e0cb53c4ffd4037f5066988c8e))+* **tokenizers:** price Anthropic document blocks by page count, not as base64 text ([#4441](https://github.com/headroomlabs-ai/headroom/issues/4441)) ([fc1ba89](https://github.com/headroomlabs-ai/headroom/commit/fc1ba891bff2d1e0cb53c4ffd4037f5066988c8e))+* **tokenizers:** resolve tiktoken encoding for gateway-prefixed model ids ([#4637](https://github.com/headroomlabs-ai/headroom/issues/4637)) ([e9331b6](https://github.com/headroomlabs-ai/headroom/commit/e9331b6b963b5b6554f45943abed2366aaa25ea6))+* **transforms:** enforce role, mutable, and cache zone guards in batch compression ([#4480](https://github.com/headroomlabs-ai/headroom/issues/4480)) ([#4494](https://github.com/headroomlabs-ai/headroom/issues/4494)) ([40cd7e7](https://github.com/headroomlabs-ai/headroom/commit/40cd7e7503c66a903ac88e6a090aa0bdac7b315d))+* **transforms:** honour Subscription toin_read_only when the router calls SmartCrusher ([#4493](https://github.com/headroomlabs-ai/headroom/issues/4493)) ([7c11d46](https://github.com/headroomlabs-ai/headroom/commit/7c11d462e6d8265a2cfdb8a1cf62026fb4d1f401))+* **transforms:** preserve YAML block scalar data during comment elision ([#4498](https://github.com/headroomlabs-ai/headroom/issues/4498)) ([534cec0](https://github.com/headroomlabs-ai/headroom/commit/534cec0e14db48e787ada13535e0763fc7c52e8e))+* **transforms:** recognise code fences whose info string is not a bare word ([#4291](https://github.com/headroomlabs-ai/headroom/issues/4291)) ([a8df6f9](https://github.com/headroomlabs-ai/headroom/commit/a8df6f919f1c4730971fc2481fd18853ddcfe6b9))+* **transforms:** stop an embedded markdown table from dropping the rest of a tool result ([#4216](https://github.com/headroomlabs-ai/headroom/issues/4216)) ([b66c9c7](https://github.com/headroomlabs-ai/headroom/commit/b66c9c7db6fb7314c366fd2c28866d0ab688f211))+* **transforms:** tolerate malformed assistant tool calls in ContentRouter.apply ([#4459](https://github.com/headroomlabs-ai/headroom/issues/4459)) ([cddd2fd](https://github.com/headroomlabs-ai/headroom/commit/cddd2fd60ed711d7fc1df75b1d5e1cac947ae6c8))+* **update-check:** skip releases with no files and do not fall back to an uninstallable version ([#4560](https://github.com/headroomlabs-ai/headroom/issues/4560)) ([c1dae5a](https://github.com/headroomlabs-ai/headroom/commit/c1dae5adae2b93871314143bba4cb03b7b971e05))+* use all user text blocks for relevance scoring ([#4628](https://github.com/headroomlabs-ai/headroom/issues/4628)) ([12dca26](https://github.com/headroomlabs-ai/headroom/commit/12dca26aa11d99b3af6c6d68cdf96ff90ef415aa))+* **wrap:** overwrite drifted selfheal hook command instead of skipping it ([#2723](https://github.com/headroomlabs-ai/headroom/issues/2723)) ([2643f34](https://github.com/headroomlabs-ai/headroom/commit/2643f34a542d944ba3ad4a0a574b5e9e9d9bd474))+* **wrap:** route OMP OpenAI providers through Headroom ([#2755](https://github.com/headroomlabs-ai/headroom/issues/2755)) ([fae1e84](https://github.com/headroomlabs-ai/headroom/commit/fae1e849cb59c85cfbd46e76a05e6c299e446b02))+++### Dependencies++* Bump @anthropic-ai/sdk from 0.133.0 to 1.3.0 in /sdk/typescript ([#4554](https://github.com/headroomlabs-ai/headroom/issues/4554)) ([74277d4](https://github.com/headroomlabs-ai/headroom/commit/74277d47ecfbca349ddb99f81094c4dd30539d43))+* Bump lru from 0.18.5 to 0.19.0 ([#4382](https://github.com/headroomlabs-ai/headroom/issues/4382)) ([038af59](https://github.com/headroomlabs-ai/headroom/commit/038af599e1a3c5e7e6b3047781aaf9ba2bbbf8bd))+* bump ruff from 0.17.0 to 0.17.2 in the pip-minor-patch group across 1 directory ([#4380](https://github.com/headroomlabs-ai/headroom/issues/4380)) ([64f43bd](https://github.com/headroomlabs-ai/headroom/commit/64f43bdf8f2080d5d7c1874fe1572acbb05872b6))+* bump ruff from 0.17.2 to 0.17.3 in the pip-minor-patch group ([#4652](https://github.com/headroomlabs-ai/headroom/issues/4652)) ([cb9602a](https://github.com/headroomlabs-ai/headroom/commit/cb9602aef0e4914f723a33ef6bad3a7c06eb485a))+* Bump the cargo-minor-patch group across 1 directory with 12 updates ([#4553](https://github.com/headroomlabs-ai/headroom/issues/4553)) ([b9049d7](https://github.com/headroomlabs-ai/headroom/commit/b9049d703af340ff90ed867f86e5fafa10c155c9))+* Bump the npm-minor-patch group across 1 directory with 6 updates ([#4621](https://github.com/headroomlabs-ai/headroom/issues/4621)) ([5e4827d](https://github.com/headroomlabs-ai/headroom/commit/5e4827de12c9fdf33d7d36b1939eee73a18fe6c5))+* Bump the npm-minor-patch group across 2 directories with 14 updates ([#4455](https://github.com/headroomlabs-ai/headroom/issues/4455)) ([f10725e](https://github.com/headroomlabs-ai/headroom/commit/f10725e6b9940d8bc2fcde950c86f8ac97543cb6))+* Bump the npm-minor-patch group across 3 directories with 9 updates ([#4495](https://github.com/headroomlabs-ai/headroom/issues/4495)) ([f367728](https://github.com/headroomlabs-ai/headroom/commit/f36772805178e3fed1a95313e8211c57a291b953))+* Bump tsup from 8.5.1 to 9.0.0 in /plugins/openclaw ([#4384](https://github.com/headroomlabs-ai/headroom/issues/4384)) ([9d87151](https://github.com/headroomlabs-ai/headroom/commit/9d871516101ff5428b592acb213aeacd30afc328))+* Bump tsup from 8.5.1 to 9.0.0 in /plugins/opencode ([#4385](https://github.com/headroomlabs-ai/headroom/issues/4385)) ([99e223c](https://github.com/headroomlabs-ai/headroom/commit/99e223c0e2c2ea6eb88ce28b160ae179897a9c67))+* Bump tsup from 8.5.1 to 9.0.0 in /sdk/typescript ([#4386](https://github.com/headroomlabs-ai/headroom/issues/4386)) ([e666fd8](https://github.com/headroomlabs-ai/headroom/commit/e666fd8e35dbe7c0433739297873b6a0a51c26cf))+* qualify latest Anthropic SDK 1.4.0 in docs ([#4556](https://github.com/headroomlabs-ai/headroom/issues/4556)) ([65bcc4c](https://github.com/headroomlabs-ai/headroom/commit/65bcc4c313aadfb609973563573b8bb3f308d81f))+* qualify latest compatible docs and E2E tools ([#4580](https://github.com/headroomlabs-ai/headroom/issues/4580)) ([e42f74e](https://github.com/headroomlabs-ai/headroom/commit/e42f74ebc9a784014ad9799b75f862efe4bf69e3))+* require Python 3.11; clear Dependabot alerts in the 3.10 lock fork ([#4517](https://github.com/headroomlabs-ai/headroom/issues/4517)) ([3c6f82b](https://github.com/headroomlabs-ai/headroom/commit/3c6f82b06091206379106f8fe1a54f2400ed7a93))+* update tomlkit requirement from <1.0,>=0.15.0 to >=0.15.2,<1.0 ([#4653](https://github.com/headroomlabs-ai/headroom/issues/4653)) ([00d5a5c](https://github.com/headroomlabs-ai/headroom/commit/00d5a5ca619f6e23da54d8b7e3fa4cc7af444035))+## [0.42.0](https://github.com/headroomlabs-ai/headroom/compare/v0.41.0...v0.42.0) (2026-10-26)diff --git a/plugins/headroom-agent-hooks/.claude-plugin/plugin.json b/plugins/headroom-agent-hooks/.claude-plugin/plugin.jsonindex ad007ec21..fd03392b8 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": "0.42.0",+ "version": "0.43.0","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 e00c20171..03c45b59c 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": "0.42.0",+ "version": "0.43.0","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.jsonindex 925b6b39b..9b82ee825 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": "0.42.0",+ "version": "0.43.0","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.jsonindex 925b6b39b..9b82ee825 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": "0.42.0",+ "version": "0.43.0","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.jsonindex 47c36a9e0..1aa88a4f7 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": "0.42.0",+ "version": "0.43.0","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.jsonindex 06ae3985a..439d679f4 100644--- a/plugins/openclaw/package.json+++ b/plugins/openclaw/package.json@@ -1,6 +1,6 @@{"name": "headroom-openclaw",- "version": "0.42.0",+ "version": "0.43.0","description": "Headroom context compression plugin for OpenClaw — 70-90% token savings with zero LLM calls","type": "module","main": "./dist/index.js",diff --git a/plugins/opencode/package.json b/plugins/opencode/package.jsonindex 65f2bca03..54f78649c 100644--- a/plugins/opencode/package.json+++ b/plugins/opencode/package.json@@ -1,6 +1,6 @@{"name": "headroom-opencode",- "version": "0.42.0",+ "version": "0.43.0","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 1641699e9..001179aee 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -4,7 +4,7 @@ build-backend = "maturin"[project]name = "headroom-ai"-version = "0.42.0"+version = "0.43.0"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.jsonindex 26e63690c..09e2e3aad 100644--- a/sdk/typescript/package.json+++ b/sdk/typescript/package.json@@ -1,6 +1,6 @@{"name": "headroom-ai",- "version": "0.42.0",+ "version": "0.43.0","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.jsonindex 2b4c9fb70..8247bb4a2 100644--- a/server.json+++ b/server.json@@ -9,13 +9,13 @@"source": "github","id": "1129940957"},- "version": "0.42.0",+ "version": "0.43.0","packages": [{"registryType": "pypi","registryBaseUrl": "https://pypi.org","identifier": "headroom-ai",- "version": "0.42.0",+ "version": "0.43.0","runtimeHint": "uvx","runtimeArguments": [{diff --git a/uv.lock b/uv.lockindex 56ea4d2a0..d3e9d12b2 100644--- a/uv.lock+++ b/uv.lock@@ -1422,7 +1422,7 @@ wheels = [[[package]]name = "headroom-ai"-version = "0.42.0"+version = "0.43.0"source = { editable = "." }dependencies = [{ name = "ast-grep-cli" },