mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
9fd5ae3d53
🤖 I have created a release *beep* *boop* --- <details><summary>0.34.0</summary> ## [0.34.0](https://github.com/headroomlabs-ai/headroom/compare/v0.33.0...v0.34.0) (2026-08-05) ### Features * **claude:** support Claude Code in VS Code ([#2752](https://github.com/headroomlabs-ai/headroom/issues/2752)) ([13a310a](13a310a00d)) * **code:** add PHP support to CodeAwareCompressor ([#2423](https://github.com/headroomlabs-ai/headroom/issues/2423)) ([6d5516d](6d5516dcb8)) * **compress:** accept config.frozen_message_count on /v1/compress ([#2718](https://github.com/headroomlabs-ai/headroom/issues/2718)) ([2797099](2797099bec)) * **compress:** reach the lossless provider seam on the general path and default /v1/compress to marker-free output ([#2691](https://github.com/headroomlabs-ai/headroom/issues/2691)) ([f2c48e2](f2c48e26c6)) * **copilot:** proxy VS Code models transparently ([#2687](https://github.com/headroomlabs-ai/headroom/issues/2687)) ([007446c](007446c73a)) ### Bug Fixes * **ccr:** stop persisting retrieval markers as original content ([#2694](https://github.com/headroomlabs-ai/headroom/issues/2694)) ([#2703](https://github.com/headroomlabs-ai/headroom/issues/2703)) ([3e348f3](3e348f327f)) * **ci:** restrict Codecov shard uploads ([#2745](https://github.com/headroomlabs-ai/headroom/issues/2745)) ([3f2ca99](3f2ca99fe1)) * **compression:** honor qualified CCR names across integrations ([#2698](https://github.com/headroomlabs-ai/headroom/issues/2698)) ([dcb674b](dcb674b5e4)) * **compress:** resolve the /v1/compress tokenizer per model, and document the real contract ([#2743](https://github.com/headroomlabs-ai/headroom/issues/2743)) ([6422a80](6422a80a58)) * **cost:** send litellm the total prompt so --budget stops seeing $0 ([#2757](https://github.com/headroomlabs-ai/headroom/issues/2757)) ([a033ac4](a033ac4176)) * **deps:** bump aiohttp and cryptography to clear the CVEs blocking 0.34.0 ([#2753](https://github.com/headroomlabs-ai/headroom/issues/2753)) ([0221e7f](0221e7f240)) * **kompress:** let orgs run Kompress on their own inference stack ([#2736](https://github.com/headroomlabs-ai/headroom/issues/2736)) ([3d23d76](3d23d76248)) * **kompress:** load merged.pt for the v2 checkpoint instead of the unmerged PEFT safetensors ([#2716](https://github.com/headroomlabs-ai/headroom/issues/2716)) ([46da91b](46da91b2f1)) * **kompress:** reject artifacts that fail at run, and prefetch model files at startup ([#2740](https://github.com/headroomlabs-ai/headroom/issues/2740)) ([224578e](224578e80b)) * **learn:** filter ambient user-role scaffolding ([#2275](https://github.com/headroomlabs-ai/headroom/issues/2275)) ([3eb0122](3eb0122068)) * **learn:** run project discovery off the event loop ([#2731](https://github.com/headroomlabs-ai/headroom/issues/2731)) ([a70e5ff](a70e5ff78d)) * normalize /p/<project> prefix on WebSocket upgrades so the Responses WS route is not rejected with 403 ([#2379](https://github.com/headroomlabs-ai/headroom/issues/2379)) ([789a4f3](789a4f3060)) * **providers:** give every model exactly one tokenizer ([#2761](https://github.com/headroomlabs-ai/headroom/issues/2761)) ([cd92ed5](cd92ed52ff)) * **providers:** stop a shorter model family shadowing a longer one ([#2762](https://github.com/headroomlabs-ai/headroom/issues/2762)) ([0cb72f4](0cb72f45b2)) * **providers:** stop pricing modern content blocks at zero ([#2760](https://github.com/headroomlabs-ai/headroom/issues/2760)) ([06add9e](06add9e9d8)) * **proxy/cost:** mark estimated-basis budget records and add an enforcement policy ([#2713](https://github.com/headroomlabs-ai/headroom/issues/2713)) ([#2725](https://github.com/headroomlabs-ai/headroom/issues/2725)) ([01df245](01df245252)) * **proxy/debug:** reconcile Kompress warmup state in /debug/warmup ([#2711](https://github.com/headroomlabs-ai/headroom/issues/2711)) ([3a27c4d](3a27c4dacb)) * **proxy/openai:** run tool-description compaction on chat-completions ([#2741](https://github.com/headroomlabs-ai/headroom/issues/2741)) ([f9db5b5](f9db5b5060)) * **proxy:** route Codex Live voice through a dedicated /v1/live transport ([#2709](https://github.com/headroomlabs-ai/headroom/issues/2709)) ([232fb49](232fb49c73)) * **proxy:** skip OpenAI tool_search deferral for Codex client ([#2729](https://github.com/headroomlabs-ai/headroom/issues/2729)) ([56b3e4c](56b3e4c1b1)) * **proxy:** stop toggling headroom_retrieve in the Anthropic tools array ([#2672](https://github.com/headroomlabs-ai/headroom/issues/2672)) ([08fce29](08fce29b47)) * remove rtk and lean-ctx CLI context tools ([#2677](https://github.com/headroomlabs-ai/headroom/issues/2677)) ([e0ce4b1](e0ce4b1d48)) * **router:** stop counting an image's base64 payload as suffix tokens ([#2778](https://github.com/headroomlabs-ai/headroom/issues/2778)) ([f03cc6d](f03cc6d88b)) * **savings:** surface request growth the tok_saved clamp swallows ([#2708](https://github.com/headroomlabs-ai/headroom/issues/2708)) ([184146b](184146b688)) * **stats:** report one "Tokens Saved" headline across every harness ([#2737](https://github.com/headroomlabs-ai/headroom/issues/2737)) ([8262a4a](8262a4a321)) * **telemetry:** anonymous compression stats — no prompts, no data ([#2728](https://github.com/headroomlabs-ai/headroom/issues/2728)) ([9cfb008](9cfb00838a)) * **telemetry:** stop mixing tokenizer scales in RequestOutcome, and fix the overhead framing ([#2756](https://github.com/headroomlabs-ai/headroom/issues/2756)) ([04e1517](04e1517ede)) * **tokenizers:** count HuggingFace chat templates, and resolve gpt-5 / gateway-wrapped names ([#2758](https://github.com/headroomlabs-ai/headroom/issues/2758)) ([0ed306b](0ed306b22b)) * **tokenizers:** resolve gpt-5 and mixed-case model names to the right encoding ([#2776](https://github.com/headroomlabs-ai/headroom/issues/2776)) ([fc4680b](fc4680b37a)) * **transforms:** stop ContentRouter recompressing headroom_retrieve results ([#2654](https://github.com/headroomlabs-ai/headroom/issues/2654)) ([677e097](677e09735a)) * **wrap/serena:** stop creating serena_config.yml, unbricking Serena on fresh installs ([#2676](https://github.com/headroomlabs-ai/headroom/issues/2676)) ([759209c](759209cff3)) ### Code Refactoring * **pricing:** make LiteLLM the source of truth, not the hardcoded table ([#2779](https://github.com/headroomlabs-ai/headroom/issues/2779)) ([0e1d6bf](0e1d6bfa79)) * remove the dead headroom/prediction module ([#2692](https://github.com/headroomlabs-ai/headroom/issues/2692)) ([b7a79ac](b7a79ac31a)) </details> --- 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>
9 lines
159 B
Text
9 lines
159 B
Text
{
|
|
"version": "0.34.0",
|
|
"packages": {
|
|
"pypi": "0.34.0",
|
|
"npm-sdk": "0.34.0",
|
|
"npm-openclaw": "0.34.0",
|
|
"agent-hooks-plugin": "0.34.0"
|
|
}
|
|
}
|