mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
Saving release notes
This commit is contained in:
JD Davis
parent
37faf2f247
commit
32afe7692e
1 changed files with 446 additions and 0 deletions
446
release-notes.md
Normal file
446
release-notes.md
Normal file
|
|
@ -0,0 +1,446 @@
|
|||
:robot: I have created a release *beep* *boop*
|
||||
---
|
||||
|
||||
|
||||
## [0.37.0](https://github.com/headroomlabs-ai/headroom/compare/v0.36.1...v0.37.0) (2026-08-21)
|
||||
|
||||
|
||||
### Features
|
||||
|
||||
* 3-layer context compression pipeline (L1+L2+L3) ([#1405](https://github.com/headroomlabs-ai/headroom/issues/1405)) ([3dd9660](https://github.com/headroomlabs-ai/headroom/commit/3dd9660d91abe86b8ea2bb45148a23ad25cbff30))
|
||||
* add CrewAI and AutoGen tool compression integrations ([#1384](https://github.com/headroomlabs-ai/headroom/issues/1384)) ([e8bff1c](https://github.com/headroomlabs-ai/headroom/commit/e8bff1cfe3a65ae2258aecba18916d331d84c1bf))
|
||||
* add deterministic runtime rollout controls ([#1490](https://github.com/headroomlabs-ai/headroom/issues/1490)) ([3077ac8](https://github.com/headroomlabs-ai/headroom/commit/3077ac81e8ef3ddefebbe308ea37a4e9bb2100e6))
|
||||
* **beacon:** allowlist the routing summary key ([#2818](https://github.com/headroomlabs-ai/headroom/issues/2818)) ([7940c05](https://github.com/headroomlabs-ai/headroom/commit/7940c05ebf4486c6b9d00984067ae33cedf4dddb))
|
||||
* **beacon:** hourly R2 compaction, per-strategy savings, and a stack that reports ([#2853](https://github.com/headroomlabs-ai/headroom/issues/2853)) ([e0870ef](https://github.com/headroomlabs-ai/headroom/commit/e0870ef931e5ea6cc6cb52551f5d80cd9e3dc715))
|
||||
* **claude:** support Claude Code in VS Code ([#2752](https://github.com/headroomlabs-ai/headroom/issues/2752)) ([13a310a](https://github.com/headroomlabs-ai/headroom/commit/13a310a00de8e967ebe09502c6b715ef577c5926))
|
||||
* **cli,pricing:** add CLI extension seam and prompt-cache TTL pricing ([#2802](https://github.com/headroomlabs-ai/headroom/issues/2802)) ([6ec3e34](https://github.com/headroomlabs-ai/headroom/commit/6ec3e3478abf058fe1460f91342bcdadf54a1ba8))
|
||||
* **cli:** add `headroom inspect` to view original vs compressed content ([#1595](https://github.com/headroomlabs-ai/headroom/issues/1595)) ([942e916](https://github.com/headroomlabs-ai/headroom/commit/942e916368fea78ba821d10f91ebe7a1b8fc9b19))
|
||||
* **cli:** add `wrap openclaude` for OpenClaude CLI ([#1416](https://github.com/headroomlabs-ai/headroom/issues/1416)) ([5415008](https://github.com/headroomlabs-ai/headroom/commit/541500811fa492f6c6cdca98b8645c3fa501e37e))
|
||||
* **code:** add PHP support to CodeAwareCompressor ([#2423](https://github.com/headroomlabs-ai/headroom/issues/2423)) ([6d5516d](https://github.com/headroomlabs-ai/headroom/commit/6d5516dcb878b6ffd139a1c7b3d480a1c8c1beb9))
|
||||
* **compress:** accept config.frozen_message_count on /v1/compress ([#2718](https://github.com/headroomlabs-ai/headroom/issues/2718)) ([2797099](https://github.com/headroomlabs-ai/headroom/commit/2797099becbd078e55b8a73cf904d2e3cb0d6889))
|
||||
* **compress:** expose frozen_message_count in library-mode compress() ([#2178](https://github.com/headroomlabs-ai/headroom/issues/2178)) ([021a762](https://github.com/headroomlabs-ai/headroom/commit/021a762bf80f67f6b86994d9891624b102031212))
|
||||
* **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](https://github.com/headroomlabs-ai/headroom/commit/f2c48e26c684a31e2802de9f49ce2075ef9cbf4b))
|
||||
* **copilot:** proxy VS Code models transparently ([#2687](https://github.com/headroomlabs-ai/headroom/issues/2687)) ([007446c](https://github.com/headroomlabs-ai/headroom/commit/007446c73a26efa729bf6d6903c828adef730089))
|
||||
* **core:** gate ONNX transforms behind a default-on `ml` feature (static/lexical builds) ([#2165](https://github.com/headroomlabs-ai/headroom/issues/2165)) ([cdba2ec](https://github.com/headroomlabs-ai/headroom/commit/cdba2eccddaaeb469abb05728e902c43954b5a51))
|
||||
* **dashboard:** add settings dashboard for proxy configuration ([#2101](https://github.com/headroomlabs-ai/headroom/issues/2101)) ([96bc4cd](https://github.com/headroomlabs-ai/headroom/commit/96bc4cd1280f327c5714d5350ac57ed5590cc901))
|
||||
* **dashboard:** persist lifetime proxy metrics ([#2198](https://github.com/headroomlabs-ai/headroom/issues/2198)) ([0537cbf](https://github.com/headroomlabs-ai/headroom/commit/0537cbfde4c9d0c6d7aafdb7a56662aee768efbb))
|
||||
* **deploy:** Add turnkey deploy command ([#1404](https://github.com/headroomlabs-ai/headroom/issues/1404)) ([560ffae](https://github.com/headroomlabs-ai/headroom/commit/560ffae103317b3a9925faf34e79751f0710b813))
|
||||
* **evals:** register multilingual multi-wiki-qa (zh/ja/ko) dataset ([#1530](https://github.com/headroomlabs-ai/headroom/issues/1530)) ([f891506](https://github.com/headroomlabs-ai/headroom/commit/f8915067f6e8f3177e3e5f99b6bc612fdeb2fb3a))
|
||||
* **evals:** weekly HotpotQA answer-recall report on the prose path ([#1188](https://github.com/headroomlabs-ai/headroom/issues/1188)) ([46d4378](https://github.com/headroomlabs-ai/headroom/commit/46d4378cf7796836f99933c8f614f84d0a08bf4a))
|
||||
* **grok-build:** add Grok Build wrap command and MCP integration ([#1629](https://github.com/headroomlabs-ai/headroom/issues/1629)) ([420dc90](https://github.com/headroomlabs-ai/headroom/commit/420dc9077b204c1ad75bde25f3f23ff8c11db770))
|
||||
* **install:** add apply flag parity, --env passthrough, and EIO retry ([#2152](https://github.com/headroomlabs-ai/headroom/issues/2152)) ([896454e](https://github.com/headroomlabs-ai/headroom/commit/896454e978952ffdb86c24fbe4983d4c223e1c0a))
|
||||
* **lossless:** factor shared directory prefix in the grep search fold ([#2547](https://github.com/headroomlabs-ai/headroom/issues/2547)) ([7dc9a97](https://github.com/headroomlabs-ai/headroom/commit/7dc9a978ca974a2ed264bb585b187dd11e0a04f2))
|
||||
* **mcp:** add streamable HTTP MCP transport ([#1773](https://github.com/headroomlabs-ai/headroom/issues/1773)) ([4ea96a4](https://github.com/headroomlabs-ai/headroom/commit/4ea96a417ceeaa9a96934a7b4f33f4318cee46d9))
|
||||
* **mcp:** publish canonical server.json ([#1510](https://github.com/headroomlabs-ai/headroom/issues/1510)) ([e9e9cd5](https://github.com/headroomlabs-ai/headroom/commit/e9e9cd55b75e9ac98ba1d204c272e157dc358f02))
|
||||
* **memory:** add explicit supersession repair ([#2217](https://github.com/headroomlabs-ai/headroom/issues/2217)) ([ce52b30](https://github.com/headroomlabs-ai/headroom/commit/ce52b30c8fe2ad16c0a2ec174fea3cb65dad19ea))
|
||||
* **metrics:** export compression-failed and kompress size-gate counters ([#1569](https://github.com/headroomlabs-ai/headroom/issues/1569)) ([d728338](https://github.com/headroomlabs-ai/headroom/commit/d7283387ac232dff89411391caa355fdb5ea6a6e))
|
||||
* **metrics:** record per-extension token savings ([#2371](https://github.com/headroomlabs-ai/headroom/issues/2371)) ([02eb90f](https://github.com/headroomlabs-ai/headroom/commit/02eb90f24318abdfb05438e873c8f2af7023ab91))
|
||||
* **opencode:** ship the transport plugin in pip installs ([#2601](https://github.com/headroomlabs-ai/headroom/issues/2601)) ([f54f04f](https://github.com/headroomlabs-ai/headroom/commit/f54f04f5bfff9ff9f9ec83b452f580447c06254a))
|
||||
* **opencode:** support Copilot subscription backend for headroom models ([#2441](https://github.com/headroomlabs-ai/headroom/issues/2441)) ([#2445](https://github.com/headroomlabs-ai/headroom/issues/2445)) ([9089e7f](https://github.com/headroomlabs-ai/headroom/commit/9089e7f7d394b5a474cc99503b0197c0172f4c9c))
|
||||
* **proxy/hooks:** run fold-only (stream-safe) turn hooks on streaming OpenAI chat ([#2549](https://github.com/headroomlabs-ai/headroom/issues/2549)) ([a6d4921](https://github.com/headroomlabs-ai/headroom/commit/a6d4921e82c1e9fe1a5ca8b90ffd16aa84a698d4))
|
||||
* **proxy/savings:** aggregate tool-schema savings into Metrics + all reporting sinks ([#2546](https://github.com/headroomlabs-ai/headroom/issues/2546)) ([9f1ffef](https://github.com/headroomlabs-ai/headroom/commit/9f1ffefe83845a3af0ecd8013daa732c3cd56b7c))
|
||||
* **proxy:** add opt-in cost-aware model router ([#1706](https://github.com/headroomlabs-ai/headroom/issues/1706)) ([#2205](https://github.com/headroomlabs-ai/headroom/issues/2205)) ([57e8dcb](https://github.com/headroomlabs-ai/headroom/commit/57e8dcb425ca71f8e9ce121d42360c7bd53ce414))
|
||||
* **proxy:** apply output shaper to OpenAI-compatible endpoints ([#1725](https://github.com/headroomlabs-ai/headroom/issues/1725)) ([e65b9b3](https://github.com/headroomlabs-ai/headroom/commit/e65b9b3f92480f092c268b617566c344e06a3512))
|
||||
* **proxy:** label GitHub Copilot traffic as "copilot" in the outcome& ([#2377](https://github.com/headroomlabs-ai/headroom/issues/2377)) ([d7a8cdb](https://github.com/headroomlabs-ai/headroom/commit/d7a8cdbee1c500be35b87c9da8395087a37ff8b9))
|
||||
* **proxy:** let extensions report cost savings and their own latency ([#3051](https://github.com/headroomlabs-ai/headroom/issues/3051)) ([f9807fd](https://github.com/headroomlabs-ai/headroom/commit/f9807fd69e220f43068ec168515ae886dd36166f))
|
||||
* **proxy:** make /v1/compress usable as a gateway/Kong sidecar ([#2458](https://github.com/headroomlabs-ai/headroom/issues/2458)) ([1329ed7](https://github.com/headroomlabs-ai/headroom/commit/1329ed7f1a8d7a018042ecbe41804b0be971792e))
|
||||
* **proxy:** model-aware cold-prefix hook reasoning compaction (Kimi/GLM) + cold recompaction (CC) ([#2555](https://github.com/headroomlabs-ai/headroom/issues/2555)) ([cb8f4b6](https://github.com/headroomlabs-ai/headroom/commit/cb8f4b64367f8b034315db33e451bdbe87af61f2))
|
||||
* **proxy:** opt-in compression for catch-all passthrough routes ([#1699](https://github.com/headroomlabs-ai/headroom/issues/1699)) ([4cbd5da](https://github.com/headroomlabs-ai/headroom/commit/4cbd5da67328d03078bd9c1fbbf10fe738cc0b2b))
|
||||
* **proxy:** route selected external compressors through the content router ([#2388](https://github.com/headroomlabs-ai/headroom/issues/2388)) ([e3c7964](https://github.com/headroomlabs-ai/headroom/commit/e3c7964038116a8df4675840896712e1aa967c45))
|
||||
* **proxy:** select built-in compressors via --compressor + registry inventory ([#2373](https://github.com/headroomlabs-ai/headroom/issues/2373)) ([56c7d4a](https://github.com/headroomlabs-ai/headroom/commit/56c7d4a59e67655cd24040ecf729382c81cdec23))
|
||||
* **proxy:** unify savings attribution across stats, perf, metrics, and dashboard ([1b0b0b8](https://github.com/headroomlabs-ai/headroom/commit/1b0b0b89a4bf751c8bd592890aef9c3b339e8e37)), closes [#2976](https://github.com/headroomlabs-ai/headroom/issues/2976)
|
||||
* **rust:** add structured prose offload plumbing ([#334](https://github.com/headroomlabs-ai/headroom/issues/334)) ([#2378](https://github.com/headroomlabs-ai/headroom/issues/2378)) ([9e07785](https://github.com/headroomlabs-ai/headroom/commit/9e0778553fc505edb2c5bc949b7277f9ffdf3bda))
|
||||
* **rust:** port CodeCompressor AST compressor to Rust (parity-only) ([#1154](https://github.com/headroomlabs-ai/headroom/issues/1154)) ([e530de5](https://github.com/headroomlabs-ai/headroom/commit/e530de5ad22100bcfaa12a463961dcb08d9671c8))
|
||||
* **rust:** port Kompress ML prose compressor to Rust (parity-only) ([#1153](https://github.com/headroomlabs-ai/headroom/issues/1153)) ([83e27e5](https://github.com/headroomlabs-ai/headroom/commit/83e27e50360753cf472acb99f1de992574fa80ae))
|
||||
* **stats:** per-bucket output-shaping savings in /stats-history ([#1819](https://github.com/headroomlabs-ai/headroom/issues/1819)) ([12a9710](https://github.com/headroomlabs-ai/headroom/commit/12a9710665b2495b9fe399e38625a9fa3ad6aa08))
|
||||
* **telemetry:** record provider cache read/write/uncached tokens per request ([#2450](https://github.com/headroomlabs-ai/headroom/issues/2450)) ([bec4cce](https://github.com/headroomlabs-ai/headroom/commit/bec4cce8a9f5623e63dba0a847719a652b47d5dc))
|
||||
* **text-crusher:** CJK-aware segmentation + relevance via ICU ([#1504](https://github.com/headroomlabs-ai/headroom/issues/1504)) ([4035c04](https://github.com/headroomlabs-ai/headroom/commit/4035c041879e422c986d9cf3b352b13bdc73a01c))
|
||||
* **text-crusher:** fold full-width ASCII to half-width in CJK token keys ([#2259](https://github.com/headroomlabs-ai/headroom/issues/2259)) ([844d9ca](https://github.com/headroomlabs-ai/headroom/commit/844d9caaa1c7471cc01b9c900f42c9552421bbe2))
|
||||
* **transforms:** add compressed signal + dispatch code_aware/html/diff via registry ([#2400](https://github.com/headroomlabs-ai/headroom/issues/2400)) ([7ebda67](https://github.com/headroomlabs-ai/headroom/commit/7ebda67ef65fe82803c7fb729c509a1451165f26))
|
||||
* **transforms:** add pluggable compressor registry + headroom.compressor entry point ([#2370](https://github.com/headroomlabs-ai/headroom/issues/2370)) ([a02073e](https://github.com/headroomlabs-ai/headroom/commit/a02073e3327365a0220ba04eeb10039f12d61684))
|
||||
* **transforms:** dispatch kompress/text via the compressor registry + forward question ([#2411](https://github.com/headroomlabs-ai/headroom/issues/2411)) ([446ec26](https://github.com/headroomlabs-ai/headroom/commit/446ec26003c8f661cec175a69e0ab8be0ae9cdea))
|
||||
* **transforms:** dispatch smart_crusher via the compressor registry (defer kompress/text ML boundary) ([#2404](https://github.com/headroomlabs-ai/headroom/issues/2404)) ([7c7bf43](https://github.com/headroomlabs-ai/headroom/commit/7c7bf430576541d0fffdb8fc727b76f3dd038f55))
|
||||
* **transforms:** make built-in compressors real Compressor implementations (adapters) ([#2391](https://github.com/headroomlabs-ai/headroom/issues/2391)) ([981616c](https://github.com/headroomlabs-ai/headroom/commit/981616c60ef04c32b3eb5b51c4f0f4a7ef297ef1))
|
||||
* **wrap/claude:** make the --1m fallback model configurable via HEADROOM_1M_MODEL ([#2983](https://github.com/headroomlabs-ai/headroom/issues/2983)) ([2a84725](https://github.com/headroomlabs-ai/headroom/commit/2a8472525d3a027c95dc38a10c4b6707b482cabc))
|
||||
* **wrap:** add `headroom wrap kimi` for Kimi CLI ([#1426](https://github.com/headroomlabs-ai/headroom/issues/1426)) ([eac4965](https://github.com/headroomlabs-ai/headroom/commit/eac49656a1cd2a72533432f676a693e283c63bf4))
|
||||
* **wrap:** add omp target (Oh My Pi) with models.yml override and unwrap ([#1811](https://github.com/headroomlabs-ai/headroom/issues/1811)) ([fcf455a](https://github.com/headroomlabs-ai/headroom/commit/fcf455a7eb3cf7663067aa6e76655c58685bdb12))
|
||||
* **wrap:** add ZCode desktop app support ([#1845](https://github.com/headroomlabs-ai/headroom/issues/1845)) ([2a954b6](https://github.com/headroomlabs-ai/headroom/commit/2a954b69b4355416fe31341d928c3b03588b660f))
|
||||
* **wrap:** boost Serena symbol-first guidance, wrap-time pre-index, repo-language scoping ([#2425](https://github.com/headroomlabs-ai/headroom/issues/2425)) ([fd0e1a8](https://github.com/headroomlabs-ai/headroom/commit/fd0e1a8afeb60748f65fef8b9197ec95e23b335a))
|
||||
* **wrap:** default code-memory to Serena (dashboard browser off) behind unified --code-memory ([#2413](https://github.com/headroomlabs-ai/headroom/issues/2413)) ([6e4425a](https://github.com/headroomlabs-ai/headroom/commit/6e4425a6bdb2bfc49e1633a24b9c9e96e705e1ff))
|
||||
* **wrap:** reduce-at-source SAFE quiet-CLI env defaults for the launched agent ([#2548](https://github.com/headroomlabs-ai/headroom/issues/2548)) ([c990cfb](https://github.com/headroomlabs-ai/headroom/commit/c990cfb8037e8f355c82eb1cef87f5c4297b612d))
|
||||
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
* add DeepSeek V4/V3.2/R1 tokenizer mappings and context limits ([#912](https://github.com/headroomlabs-ai/headroom/issues/912)) ([0c70875](https://github.com/headroomlabs-ai/headroom/commit/0c7087539d92a9dff2fd7f1923aff529f80201ef))
|
||||
* add Vercel deploy config and workflow for docs site ([#1739](https://github.com/headroomlabs-ai/headroom/issues/1739)) ([b0fa84e](https://github.com/headroomlabs-ai/headroom/commit/b0fa84e84d9c8cb08ebe0320c5baff4553c329c8))
|
||||
* **anthropic:** honor the [1m] 1M-context tier, and price it correctly ([#3073](https://github.com/headroomlabs-ai/headroom/issues/3073)) ([6d2254d](https://github.com/headroomlabs-ai/headroom/commit/6d2254dfb5eb97f92249e0ee7aa04b2697adfa69))
|
||||
* **anthropic:** strip first-party tool search on custom upstreams ([#2539](https://github.com/headroomlabs-ai/headroom/issues/2539)) ([7f6950b](https://github.com/headroomlabs-ai/headroom/commit/7f6950be34e29304deae0fa5138b852491b092fe))
|
||||
* **auth:** support GitHub Enterprise Copilot OAuth domain ([#2192](https://github.com/headroomlabs-ai/headroom/issues/2192)) ([5dbe331](https://github.com/headroomlabs-ai/headroom/commit/5dbe3314a198e6c4381a2280b83ec1629653bedf))
|
||||
* **backend/bedrock:** preserve system-prompt cache_control breakpoint (list form) ([#2225](https://github.com/headroomlabs-ai/headroom/issues/2225)) ([ea0115c](https://github.com/headroomlabs-ai/headroom/commit/ea0115cbdbbf180062cc59e794371f62bf5875c3))
|
||||
* **backends/anyllm:** convert Anthropic tools and tool_choice to OpenAI shape ([0d6866b](https://github.com/headroomlabs-ai/headroom/commit/0d6866b91a3777475abd58cd8b63a10cd0621e7f))
|
||||
* **backends/anyllm:** stream tool_use blocks and map finish_reason on the streaming path ([e4904e2](https://github.com/headroomlabs-ai/headroom/commit/e4904e23a6ba6f5cff2488332946481172446922))
|
||||
* **backends/litellm:** guard None completion_tokens in usage mapping ([#2322](https://github.com/headroomlabs-ai/headroom/issues/2322)) ([44a174f](https://github.com/headroomlabs-ai/headroom/commit/44a174fef4d514eceed20a767dc87d00cfde0eaa))
|
||||
* **backends/litellm:** None-guard core token counts in OpenAI usage block ([#2324](https://github.com/headroomlabs-ai/headroom/issues/2324)) ([12f9f58](https://github.com/headroomlabs-ai/headroom/commit/12f9f58cb3dcfc67af1238424d404d8dd9bad1dd))
|
||||
* **backends:** don't crash the OpenAI->Anthropic converter on empty choices ([#2484](https://github.com/headroomlabs-ai/headroom/issues/2484)) ([43a7b57](https://github.com/headroomlabs-ai/headroom/commit/43a7b578a1377ad34d8a78ba3bcef1c276db0b4d))
|
||||
* **beacon:** report all-layers savings, not context-compression only ([#2796](https://github.com/headroomlabs-ai/headroom/issues/2796)) ([e9a24f3](https://github.com/headroomlabs-ai/headroom/commit/e9a24f3ec1ffd278b0b3ca547a90942c40c99ec8))
|
||||
* **beacon:** split session failures by status code ([#2815](https://github.com/headroomlabs-ai/headroom/issues/2815)) ([2954e37](https://github.com/headroomlabs-ai/headroom/commit/2954e37048f8dcffe16e1c37b8f71afb0094a0a2))
|
||||
* **build:** support Intel macOS (x86_64-apple-darwin) via ort-load-dynamic (fixes [#941](https://github.com/headroomlabs-ai/headroom/issues/941)) ([#1797](https://github.com/headroomlabs-ai/headroom/issues/1797)) ([1590913](https://github.com/headroomlabs-ai/headroom/commit/1590913bb785e0b352d2192b6c595152e01feb14))
|
||||
* **cache-aligner:** hash the frozen conversation prefix so Claude Code cache invalidation is detected ([#2085](https://github.com/headroomlabs-ai/headroom/issues/2085)) ([#2161](https://github.com/headroomlabs-ai/headroom/issues/2161)) ([cc072f0](https://github.com/headroomlabs-ai/headroom/commit/cc072f0821b76618659a2dd6c81a1daee49dbaab))
|
||||
* **cache:** bound compression cache bookkeeping ([0ae948c](https://github.com/headroomlabs-ai/headroom/commit/0ae948c1510735df39317bf0861f8a8750cdbf9d))
|
||||
* **cache:** enforce Anthropic's 1h-before-5m cache_control ordering before forwarding ([#2941](https://github.com/headroomlabs-ai/headroom/issues/2941)) ([3752458](https://github.com/headroomlabs-ai/headroom/commit/3752458022f736c779f7b5a6c2d6d2ef0bc89f72))
|
||||
* **cache:** mirror client cache_control positions instead of single-marker consolidation ([def3d76](https://github.com/headroomlabs-ai/headroom/commit/def3d76e5ab4665e609b51bfba54dd6d25116925))
|
||||
* **cache:** normalize embeddings before the semantic similarity check ([#2122](https://github.com/headroomlabs-ai/headroom/issues/2122)) ([f8eaaeb](https://github.com/headroomlabs-ai/headroom/commit/f8eaaeb26a65b7a92981c7061cb3650cc184f72e))
|
||||
* **cache:** preserve cache_control ttl when re-anchoring a breakpoint ([#2651](https://github.com/headroomlabs-ai/headroom/issues/2651)) ([e0d2cd0](https://github.com/headroomlabs-ai/headroom/commit/e0d2cd0c5a1c3ee813ac225252c9fd8db7c77c12))
|
||||
* **cache:** preserve client cache_control ttl when consolidating breakpoints ([#2382](https://github.com/headroomlabs-ai/headroom/issues/2382)) ([8906d3a](https://github.com/headroomlabs-ai/headroom/commit/8906d3a6761c097bbc9d92a0b41f8c982afc633b))
|
||||
* **cache:** stabilize Anthropic block-growing lineages ([#2917](https://github.com/headroomlabs-ai/headroom/issues/2917)) ([1a04c95](https://github.com/headroomlabs-ai/headroom/commit/1a04c957f53ef25ab1209166f425a7876913c4d3))
|
||||
* **cache:** stable session identity and per-conversation prefix trackers under agentic clients ([#2193](https://github.com/headroomlabs-ai/headroom/issues/2193)) ([7bfb1d7](https://github.com/headroomlabs-ai/headroom/commit/7bfb1d7f38ac3c3cf3f123033c157a17ad0da71a))
|
||||
* **ccr:** avoid injecting tool on chat streaming ([d0c1f5b](https://github.com/headroomlabs-ai/headroom/commit/d0c1f5b8ad68c7a44ed3aaa0fe40e3a656950123))
|
||||
* **ccr:** don't crash tool-call detection on a null function/functionCall ([#2269](https://github.com/headroomlabs-ai/headroom/issues/2269)) ([1612f06](https://github.com/headroomlabs-ai/headroom/commit/1612f06a4c19c53b6d8b02b02cd30d14a1858d28))
|
||||
* **ccr:** guard empty/malformed OpenAI choices in _extract_assistant_message ([#2389](https://github.com/headroomlabs-ai/headroom/issues/2389)) ([89319fb](https://github.com/headroomlabs-ai/headroom/commit/89319fbcaddb4be2ea11e87858ed3bd0fcf9dca5))
|
||||
* **ccr:** lowercase a retrieved hash so an uppercase echo still hits the store ([#2236](https://github.com/headroomlabs-ai/headroom/issues/2236)) ([842d7e1](https://github.com/headroomlabs-ai/headroom/commit/842d7e1ad1869b147ec94903ac87cf1414d86cdb))
|
||||
* **ccr:** make --no-ccr disable server-side response handling too ([#3101](https://github.com/headroomlabs-ai/headroom/issues/3101)) ([131b119](https://github.com/headroomlabs-ai/headroom/commit/131b119c053e66fe825dabb3c242f6dc5c6049d7)), closes [#3082](https://github.com/headroomlabs-ai/headroom/issues/3082)
|
||||
* **ccr:** make StreamingCCRHandler work on OpenAI streams ([#3069](https://github.com/headroomlabs-ai/headroom/issues/3069)) ([7ef736f](https://github.com/headroomlabs-ai/headroom/commit/7ef736fb1a8852a3dee52a362043c47084628a2a))
|
||||
* **ccr:** only buffer a stream when a marker is actually redeemable ([#3092](https://github.com/headroomlabs-ai/headroom/issues/3092)) ([c502087](https://github.com/headroomlabs-ai/headroom/commit/c502087db702e9b6aa1d1736086cf4a69a7775e6))
|
||||
* **ccr:** preserve exact SQLite TTL boundary ([#2669](https://github.com/headroomlabs-ai/headroom/issues/2669)) ([d0a86d4](https://github.com/headroomlabs-ai/headroom/commit/d0a86d409fab377f9c642d1f3680b6ece7f97b8a))
|
||||
* **ccr:** re-inject headroom_retrieve when history references it on the sessionless path ([942af56](https://github.com/headroomlabs-ai/headroom/commit/942af56f11cbd8466e25ae189c65ba56a9ddd602))
|
||||
* **ccr:** relay a successful upstream turn when post-processing fails ([#3094](https://github.com/headroomlabs-ai/headroom/issues/3094)) ([0ec73fa](https://github.com/headroomlabs-ai/headroom/commit/0ec73faa2805502a5c13eab7e4f086f8ae2e175e))
|
||||
* **ccr:** report embedded hashes from compress endpoint ([#717](https://github.com/headroomlabs-ai/headroom/issues/717)) ([685ebe4](https://github.com/headroomlabs-ai/headroom/commit/685ebe457d727922ba4057515556a2d2aac0f616))
|
||||
* **ccr:** resolve <<ccr:...>> markers inline when no retrieve-tool path exists ([#2512](https://github.com/headroomlabs-ai/headroom/issues/2512)) ([ce8ce83](https://github.com/headroomlabs-ai/headroom/commit/ce8ce8313f8cebf060392a62f9adaab18c0df386))
|
||||
* **ccr:** send Accept: application/json on a buffered stream:false turn ([#3102](https://github.com/headroomlabs-ai/headroom/issues/3102)) ([139c7cb](https://github.com/headroomlabs-ai/headroom/commit/139c7cbdde6a68ae3ade24341a79e5ba659c2cf3)), closes [#3078](https://github.com/headroomlabs-ai/headroom/issues/3078)
|
||||
* **ccr:** skip compact summaries for proactive expansion ([#2242](https://github.com/headroomlabs-ai/headroom/issues/2242)) ([3f241e4](https://github.com/headroomlabs-ai/headroom/commit/3f241e472b07c39efd8fd51e35b7070f5d514ea1))
|
||||
* **ccr:** sliding idle-window TTL with max-lifetime ceiling in the Rust core backends ([#2604](https://github.com/headroomlabs-ai/headroom/issues/2604)) ([#2631](https://github.com/headroomlabs-ai/headroom/issues/2631)) ([e825588](https://github.com/headroomlabs-ai/headroom/commit/e825588bfbc59fa9e86085e23b4a078e9a0038ba))
|
||||
* **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](https://github.com/headroomlabs-ai/headroom/commit/3e348f327f05921204329b72a57d3113cf5101c4))
|
||||
* **ccr:** store pre-protection original, not tag placeholder, in CCR ([#1208](https://github.com/headroomlabs-ai/headroom/issues/1208)) ([a61f534](https://github.com/headroomlabs-ai/headroom/commit/a61f534426d98f4467057794fdcb6acdbf28a3bf))
|
||||
* **ccr:** tolerate null/malformed OpenAI data in response handling ([#2467](https://github.com/headroomlabs-ai/headroom/issues/2467)) ([e583e08](https://github.com/headroomlabs-ai/headroom/commit/e583e082d8dee942229ac6211c742f9c9448a905))
|
||||
* **ccr:** verify a scanned marker's hash before advertising it ([#2908](https://github.com/headroomlabs-ai/headroom/issues/2908)) ([41dab2d](https://github.com/headroomlabs-ai/headroom/commit/41dab2d09925658b96fed492d534346ce1930f4c))
|
||||
* **ci:** align Ruff tooling versions ([#2406](https://github.com/headroomlabs-ai/headroom/issues/2406)) ([2bb14d1](https://github.com/headroomlabs-ai/headroom/commit/2bb14d1ab24617971a657b71ead567479021119d))
|
||||
* **ci:** prevent native detector from hanging test shards ([#2996](https://github.com/headroomlabs-ai/headroom/issues/2996)) ([a708c05](https://github.com/headroomlabs-ai/headroom/commit/a708c0571eecfb53eaab6b787b7a6ace9b21c162))
|
||||
* **ci:** publish latest from the root Docker manifest ([#2252](https://github.com/headroomlabs-ai/headroom/issues/2252)) ([5568d73](https://github.com/headroomlabs-ai/headroom/commit/5568d738afb5e080d8df56e64500026996cbf025))
|
||||
* **ci:** restrict Codecov shard uploads ([#2745](https://github.com/headroomlabs-ai/headroom/issues/2745)) ([3f2ca99](https://github.com/headroomlabs-ai/headroom/commit/3f2ca99fe16668e3d50b8e1706182ec7b226c352))
|
||||
* **ci:** scope the release credential and stop persisting it to disk ([#3062](https://github.com/headroomlabs-ai/headroom/issues/3062)) ([ac8646a](https://github.com/headroomlabs-ai/headroom/commit/ac8646aa3c6323c3c0b7051e09831f779859af6f))
|
||||
* **ci:** unjam release and Docker publishing ([#2958](https://github.com/headroomlabs-ai/headroom/issues/2958)) ([e269afb](https://github.com/headroomlabs-ai/headroom/commit/e269afb935f298a833a189acfb8573e908b3b60b))
|
||||
* **claude:** reject conflicting auth before proxy startup ([#2993](https://github.com/headroomlabs-ai/headroom/issues/2993)) ([2d88e31](https://github.com/headroomlabs-ai/headroom/commit/2d88e31a404e2be6c1c428deb2a387599eb820ba))
|
||||
* **claude:** stop forcing tool search on Foundry ([#2477](https://github.com/headroomlabs-ai/headroom/issues/2477)) ([7981396](https://github.com/headroomlabs-ai/headroom/commit/798139608c0fb5118eb3a7a183b8b2abe92341f1))
|
||||
* **claude:** treat non-zero claude --version exit as version-unknown & ([#2233](https://github.com/headroomlabs-ai/headroom/issues/2233)) ([f71fef1](https://github.com/headroomlabs-ai/headroom/commit/f71fef1ca6a1540a3c13c3508c5c1468bf14ea88))
|
||||
* **cli/init:** fail clearly on a target settings file with invalid JSON ([#2227](https://github.com/headroomlabs-ai/headroom/issues/2227)) ([daca1dd](https://github.com/headroomlabs-ai/headroom/commit/daca1dd7561948f460889cd69d68344d2a53b5b5))
|
||||
* **cli/install:** resolve the deployment profile instead of dead-ending on default ([#2832](https://github.com/headroomlabs-ai/headroom/issues/2832)) ([8252619](https://github.com/headroomlabs-ai/headroom/commit/82526191a103a8d0e079d170e47631b3c2bcb0d9))
|
||||
* **cli/update:** let install ownership win over bare /.dockerenv so venv installs self-update ([#2830](https://github.com/headroomlabs-ai/headroom/issues/2830)) ([7092b53](https://github.com/headroomlabs-ai/headroom/commit/7092b53c466bf5dbda8a1cda88403d1a4b16deb1))
|
||||
* **cli:** stop the macOS malloc re-exec replacing an embedder's process ([#3064](https://github.com/headroomlabs-ai/headroom/issues/3064)) ([96c25f5](https://github.com/headroomlabs-ai/headroom/commit/96c25f518154536cf15f4e0b2d3fed80de6e67f6))
|
||||
* **cli:** warn when Headroom proxy URL leaks into the shell after unwrap claude ([#2238](https://github.com/headroomlabs-ai/headroom/issues/2238)) ([#2571](https://github.com/headroomlabs-ai/headroom/issues/2571)) ([904bc67](https://github.com/headroomlabs-ai/headroom/commit/904bc675b35072dc61191963cbe485fa692927d1))
|
||||
* **code-compressor:** recover valid Python rewrites after local syntax rejection ([#2202](https://github.com/headroomlabs-ai/headroom/issues/2202)) ([dbbef4b](https://github.com/headroomlabs-ai/headroom/commit/dbbef4bd41f10ec748e462717fb976256a6a8916))
|
||||
* **code:** pin tree-sitter-language-pack <1.0.0 in [code] extra ([#1219](https://github.com/headroomlabs-ai/headroom/issues/1219)) ([412db40](https://github.com/headroomlabs-ai/headroom/commit/412db40a0bcb35d2a631ea5e74eb910b1f89feb3))
|
||||
* **code:** quarantine Perl parser from code-aware compression ([#2204](https://github.com/headroomlabs-ai/headroom/issues/2204)) ([8522fcb](https://github.com/headroomlabs-ai/headroom/commit/8522fcbc40b716a5faf8978237e7b829a6468d09))
|
||||
* **codex:** detect keyring-backed ChatGPT auth ([#2478](https://github.com/headroomlabs-ai/headroom/issues/2478)) ([46293f4](https://github.com/headroomlabs-ai/headroom/commit/46293f4daf4d217ab6f8a83f7c571571b79bae0c))
|
||||
* **codex:** preserve wrapped sessions and recover state ([#2160](https://github.com/headroomlabs-ai/headroom/issues/2160)) ([dec60de](https://github.com/headroomlabs-ai/headroom/commit/dec60de976ee0a64b33bd4c4625c9e73688ddcd3))
|
||||
* **codex:** rewrite config.toml properly so Codex will route through & ([#2102](https://github.com/headroomlabs-ai/headroom/issues/2102)) ([5d9bbbe](https://github.com/headroomlabs-ai/headroom/commit/5d9bbbeea07c2e1ee1640cc455aaeb23d9f75768))
|
||||
* **codex:** route alpha search through the Codex backend ([#2538](https://github.com/headroomlabs-ai/headroom/issues/2538)) ([a540eb2](https://github.com/headroomlabs-ai/headroom/commit/a540eb2c61b1a47e5ab8b07ea4a80fee780b6514))
|
||||
* **compression:** honor qualified CCR names across integrations ([#2698](https://github.com/headroomlabs-ai/headroom/issues/2698)) ([dcb674b](https://github.com/headroomlabs-ai/headroom/commit/dcb674b5e4e0d29d52672118ba3cf5062b16d280))
|
||||
* **compression:** report source-line span in CCR compression marker ([#2597](https://github.com/headroomlabs-ai/headroom/issues/2597)) ([18e1c3c](https://github.com/headroomlabs-ai/headroom/commit/18e1c3c9badc5169466b7f76ae08e0639f4ba104))
|
||||
* **compress:** resolve the /v1/compress tokenizer per model, and document the real contract ([#2743](https://github.com/headroomlabs-ai/headroom/issues/2743)) ([6422a80](https://github.com/headroomlabs-ai/headroom/commit/6422a80a58010da805d4001e83265300aa716d8a))
|
||||
* **content_router:** pin FREEZE_BLOCK_DECISION verdict to stop cache-write churn ([#1620](https://github.com/headroomlabs-ai/headroom/issues/1620)) ([a069979](https://github.com/headroomlabs-ai/headroom/commit/a0699794660132313446e8c52c588d6ead05af21))
|
||||
* **content-router:** protect custom-tag blocks before mixed-content section split ([d7bc1e2](https://github.com/headroomlabs-ai/headroom/commit/d7bc1e275f411788abffa2d007db14aa17fd31c5))
|
||||
* **copilot:** derive GHE credential host from API URL ([#800](https://github.com/headroomlabs-ai/headroom/issues/800)) ([#2511](https://github.com/headroomlabs-ai/headroom/issues/2511)) ([4a8157f](https://github.com/headroomlabs-ai/headroom/commit/4a8157fa0a3f1d07699f1071ceb653f8902f10a4))
|
||||
* **copilot:** normalize subscription API routing ([#2441](https://github.com/headroomlabs-ai/headroom/issues/2441)) ([#2455](https://github.com/headroomlabs-ai/headroom/issues/2455)) ([2eca5ee](https://github.com/headroomlabs-ai/headroom/commit/2eca5ee1140c9ce0a5fee05e604d3198f7f86026))
|
||||
* **copilot:** preserve /v1 for the Anthropic /v1/messages endpoint ([#2409](https://github.com/headroomlabs-ai/headroom/issues/2409)) ([#2414](https://github.com/headroomlabs-ai/headroom/issues/2414)) ([c400f90](https://github.com/headroomlabs-ai/headroom/commit/c400f9081052f633e4e64ad70b95a0230dc6fb3d))
|
||||
* **copilot:** route VS Code inline completions to Copilot, not OpenAI ([#3077](https://github.com/headroomlabs-ai/headroom/issues/3077)) ([204e751](https://github.com/headroomlabs-ai/headroom/commit/204e751d2f01b0e987e9c05edec21664bb2df279))
|
||||
* **copilot:** send VS Code inline completions to the host that serves them ([#3112](https://github.com/headroomlabs-ai/headroom/issues/3112)) ([b77d612](https://github.com/headroomlabs-ai/headroom/commit/b77d61291399976985f12adcd6014aba2f0275cf))
|
||||
* **core:** avoid unidiff panic on bash xtrace ([#1506](https://github.com/headroomlabs-ai/headroom/issues/1506)) ([3757a7c](https://github.com/headroomlabs-ai/headroom/commit/3757a7cef3c3f672287244f5d5c768b9b5c6f854))
|
||||
* **cost:** send litellm the total prompt so --budget stops seeing $0 ([#2757](https://github.com/headroomlabs-ai/headroom/issues/2757)) ([a033ac4](https://github.com/headroomlabs-ai/headroom/commit/a033ac4176b09c716905aa0f45ae317e954f0eb9))
|
||||
* **deps:** bump aiohttp and cryptography to clear the CVEs blocking 0.34.0 ([#2753](https://github.com/headroomlabs-ai/headroom/issues/2753)) ([0221e7f](https://github.com/headroomlabs-ai/headroom/commit/0221e7f240cf470628650d749dc0ab5f3f0135f3))
|
||||
* **deps:** bump datasets past PYSEC-2026-3716 ([#3136](https://github.com/headroomlabs-ai/headroom/issues/3136)) ([df6ff6b](https://github.com/headroomlabs-ai/headroom/commit/df6ff6bd5b47837c1247cf4eb8ac151ebd799aa5))
|
||||
* **deps:** bump h2 to 4.4.1 for CVE-2026-71554 ([#2839](https://github.com/headroomlabs-ai/headroom/issues/2839)) ([564e0a8](https://github.com/headroomlabs-ai/headroom/commit/564e0a8d0fe440dff21a6c405c88e05698b3059f))
|
||||
* **deps:** bump mcp to 1.28.1 to clear 3 high-severity CVEs ([#2348](https://github.com/headroomlabs-ai/headroom/issues/2348)) ([a90be94](https://github.com/headroomlabs-ai/headroom/commit/a90be94e32c393332d37db4fb439e0c776b89f27))
|
||||
* **deps:** clear Dependabot lockfile alerts ([#2175](https://github.com/headroomlabs-ai/headroom/issues/2175)) ([ea3d5a8](https://github.com/headroomlabs-ai/headroom/commit/ea3d5a86b725d7b0a0a024980f6e1214da4c5fcc))
|
||||
* **deps:** clear the two Rust advisories and make cargo audit blocking ([#3121](https://github.com/headroomlabs-ai/headroom/issues/3121)) ([93c474e](https://github.com/headroomlabs-ai/headroom/commit/93c474e84b2eeee147c274f3d75f48e5ea42d0d5))
|
||||
* **deps:** enforce audited transitive dependency floors ([#2791](https://github.com/headroomlabs-ai/headroom/issues/2791)) ([64e2039](https://github.com/headroomlabs-ai/headroom/commit/64e203931b9810e5a010f063d26d154419016f86))
|
||||
* **deps:** enforce transformers security floor ([#2201](https://github.com/headroomlabs-ai/headroom/issues/2201)) ([cbfa267](https://github.com/headroomlabs-ai/headroom/commit/cbfa267c5f4f6c924c377115b5bcd1cef5230451))
|
||||
* **deps:** raise the GitPython floor to 3.1.58 to clear 9 open advisories ([#3120](https://github.com/headroomlabs-ai/headroom/issues/3120)) ([8156d4d](https://github.com/headroomlabs-ai/headroom/commit/8156d4dc3a376476513ef6f78104ff81d08967ac))
|
||||
* **diff-compressor:** CJK-aware relevance scoring for hunk selection ([#2220](https://github.com/headroomlabs-ai/headroom/issues/2220)) ([528517c](https://github.com/headroomlabs-ai/headroom/commit/528517cff86ae1a27e8e325d96d0124260fc9fe1))
|
||||
* **docker:** give :latest exactly one writer ([#3154](https://github.com/headroomlabs-ai/headroom/issues/3154)) ([bf651c3](https://github.com/headroomlabs-ai/headroom/commit/bf651c3dc1b8c43cca84d085b57528fa9c7de5cd))
|
||||
* **docker:** publish compose ports on loopback only ([#3061](https://github.com/headroomlabs-ai/headroom/issues/3061)) ([481e0b8](https://github.com/headroomlabs-ai/headroom/commit/481e0b83d5393419b27b17d95767104c7c1bda26))
|
||||
* **docker:** ship Bedrock auth and current registry ([#2982](https://github.com/headroomlabs-ai/headroom/issues/2982)) ([eafdf11](https://github.com/headroomlabs-ai/headroom/commit/eafdf11a2cea44aabc51ce59bbc031e0aaee9640))
|
||||
* **doctor:** flag `ollama launch claude` proxy bypass instead of misdirecting ([#2566](https://github.com/headroomlabs-ai/headroom/issues/2566)) ([7f24d69](https://github.com/headroomlabs-ai/headroom/commit/7f24d695eea00b9bb3265fbaa6629acf0c2ff181))
|
||||
* **doctor:** surface that Claude Desktop agent sessions bypass the proxy ([#2987](https://github.com/headroomlabs-ai/headroom/issues/2987)) ([be5b26d](https://github.com/headroomlabs-ai/headroom/commit/be5b26d807be81d83594c9144a8520f6f0f1b273))
|
||||
* emit SSE ping before message_start on Bedrock streaming path (issue [#902](https://github.com/headroomlabs-ai/headroom/issues/902)) ([#1080](https://github.com/headroomlabs-ai/headroom/issues/1080)) ([4dab254](https://github.com/headroomlabs-ai/headroom/commit/4dab254d52914c39ffe13071848604e1771b1bd1))
|
||||
* **gemini:** resolve native CCR retrieval calls ([#2253](https://github.com/headroomlabs-ai/headroom/issues/2253)) ([2483f57](https://github.com/headroomlabs-ai/headroom/commit/2483f570025763cd9183a93749ea8cf38f1aeb85))
|
||||
* **grok:** preserve business-seat auth while routing only inference ([#2514](https://github.com/headroomlabs-ai/headroom/issues/2514)) ([e4076bb](https://github.com/headroomlabs-ai/headroom/commit/e4076bbe99d500982b51444fe37f8f467cd6abe2))
|
||||
* harden fd lifecycle and SystemError handling in runtime and proxy kill ([#1556](https://github.com/headroomlabs-ai/headroom/issues/1556)) ([f42ce4a](https://github.com/headroomlabs-ai/headroom/commit/f42ce4a2399f3285548b5a67f2bf1cede0334816))
|
||||
* **health:** label kompress as degraded/optional when not yet loaded ([#2865](https://github.com/headroomlabs-ai/headroom/issues/2865)) ([8949371](https://github.com/headroomlabs-ai/headroom/commit/89493714d2cffdc1f81a8f417ea09891453d7009))
|
||||
* **image:** decouple routing types from trained_router so importing the compressor doesn't import torch ([#2513](https://github.com/headroomlabs-ai/headroom/issues/2513)) ([#2537](https://github.com/headroomlabs-ai/headroom/issues/2537)) ([d7cf981](https://github.com/headroomlabs-ai/headroom/commit/d7cf981093cf505192a3736dadd0254a120830a1))
|
||||
* **image:** reuse image models instead of rebuilding them per request ([#2513](https://github.com/headroomlabs-ai/headroom/issues/2513)) ([#2536](https://github.com/headroomlabs-ai/headroom/issues/2536)) ([2a63ec7](https://github.com/headroomlabs-ai/headroom/commit/2a63ec70b65605dfcff1b0afc292ab0298459f20))
|
||||
* **init/codex:** don't delete per-profile provider settings ([#2146](https://github.com/headroomlabs-ai/headroom/issues/2146)) ([8da4384](https://github.com/headroomlabs-ai/headroom/commit/8da4384bfcb21d81f9972a8523879336bdfd36d7))
|
||||
* **install/windows:** register persistent-task from S4U hidden XML ([#2453](https://github.com/headroomlabs-ai/headroom/issues/2453)) ([#2459](https://github.com/headroomlabs-ai/headroom/issues/2459)) ([1edaeb8](https://github.com/headroomlabs-ai/headroom/commit/1edaeb8b76f6b872a6c810d404c944caf1a594b2))
|
||||
* **install:** carry upstream-routing env overrides into supervised deployments ([#2429](https://github.com/headroomlabs-ai/headroom/issues/2429)) ([170b04a](https://github.com/headroomlabs-ai/headroom/commit/170b04a74d5361cdfac4a6e265f5ea0dfecbd841))
|
||||
* **install:** consolidate Windows fallback and cleanup safety ([#2980](https://github.com/headroomlabs-ai/headroom/issues/2980)) ([ddd2a25](https://github.com/headroomlabs-ai/headroom/commit/ddd2a259ecce4e57202a68a74a2c1adcb879679b))
|
||||
* **install:** default to cache mode, matching `headroom proxy` ([#1893](https://github.com/headroomlabs-ai/headroom/issues/1893) follow-up) ([#2563](https://github.com/headroomlabs-ai/headroom/issues/2563)) ([b121223](https://github.com/headroomlabs-ai/headroom/commit/b121223ec97e95c5a7a4c2c5e06a4655c7328e88))
|
||||
* **install:** don't crash the PowerShell installer when $PROFILE is unset ([#2469](https://github.com/headroomlabs-ai/headroom/issues/2469)) ([fc5c4e2](https://github.com/headroomlabs-ai/headroom/commit/fc5c4e239ce32f2b90a6777772a01bdf49c66cb6))
|
||||
* **install:** guard non-dict health config in 'install status' ([#2150](https://github.com/headroomlabs-ai/headroom/issues/2150)) ([8f867e4](https://github.com/headroomlabs-ai/headroom/commit/8f867e46222239a45136df8f5a05515897077bbf))
|
||||
* **install:** honor HEADROOM_PORT in install apply and deploy ([#3085](https://github.com/headroomlabs-ai/headroom/issues/3085)) ([58f28dc](https://github.com/headroomlabs-ai/headroom/commit/58f28dc7a6b6ce5bbf0f88524bd78cbe3f3ffa4b))
|
||||
* **install:** migrate deployments off the retired chopratejas image repo ([#2427](https://github.com/headroomlabs-ai/headroom/issues/2427)) ([17ff13c](https://github.com/headroomlabs-ai/headroom/commit/17ff13ccbe274e831d5d9327740cd6d506ea8c1c))
|
||||
* **install:** stop the PowerShell installer leaking temp dirs into the real user PATH ([#2985](https://github.com/headroomlabs-ai/headroom/issues/2985)) ([ddd9f76](https://github.com/headroomlabs-ai/headroom/commit/ddd9f76729d5662201b84bd0a51281cd3ac64ad3))
|
||||
* **install:** trust Docker bridge for dashboard metadata ([e044139](https://github.com/headroomlabs-ai/headroom/commit/e044139001680fd5198147bf373df6f00db32cc7))
|
||||
* **install:** use --userns=keep-id under Podman so bind-mount writes don't fail ([#2846](https://github.com/headroomlabs-ai/headroom/issues/2846)) ([3488f8d](https://github.com/headroomlabs-ai/headroom/commit/3488f8d4b5fae4eab157e0c4031ccf712bcbcc0d))
|
||||
* **install:** use CREATE_NO_WINDOW instead of DETACHED_PROCESS on Windows ([#2527](https://github.com/headroomlabs-ai/headroom/issues/2527)) ([045f3df](https://github.com/headroomlabs-ai/headroom/commit/045f3dfe6fd9f4e39e4cdd8c0c529a815d925c7e))
|
||||
* **kompress:** let orgs run Kompress on their own inference stack ([#2736](https://github.com/headroomlabs-ai/headroom/issues/2736)) ([3d23d76](https://github.com/headroomlabs-ai/headroom/commit/3d23d76248d2052b846a84b70be87c8c95bad9ac))
|
||||
* **kompress:** load merged.pt for the v2 checkpoint instead of the unmerged PEFT safetensors ([#2716](https://github.com/headroomlabs-ai/headroom/issues/2716)) ([46da91b](https://github.com/headroomlabs-ai/headroom/commit/46da91b2f1370b6b4910ae8a4ad0613929803887))
|
||||
* **kompress:** raise the default execution-slot wait ([#2456](https://github.com/headroomlabs-ai/headroom/issues/2456)) ([5bd2266](https://github.com/headroomlabs-ai/headroom/commit/5bd2266f16bb351a7a7334e1c29c598d28187b1d))
|
||||
* **kompress:** reject artifacts that fail at run, and prefetch model files at startup ([#2740](https://github.com/headroomlabs-ai/headroom/issues/2740)) ([224578e](https://github.com/headroomlabs-ai/headroom/commit/224578e80b4abbe1e16f1952efc24af5fdee106a))
|
||||
* **learn/claude:** don't abort the whole scan on a null message line ([#2299](https://github.com/headroomlabs-ai/headroom/issues/2299)) ([eed80dd](https://github.com/headroomlabs-ai/headroom/commit/eed80dd4baa6a9d8be0ed36a575d0169f6b5eb3c))
|
||||
* **learn/gemini:** stop double-counting session tokens ([#2230](https://github.com/headroomlabs-ai/headroom/issues/2230)) ([29d8a5e](https://github.com/headroomlabs-ai/headroom/commit/29d8a5e563cf16dbd3a53a1571f4f352e61e1b33))
|
||||
* **learn/grok:** detect a Windows absolute project path ([#2283](https://github.com/headroomlabs-ai/headroom/issues/2283)) ([e240df2](https://github.com/headroomlabs-ai/headroom/commit/e240df2b698e601324b85956bd93cb304f6030ab))
|
||||
* **learn:** detect the active OpenCode database ([#2587](https://github.com/headroomlabs-ai/headroom/issues/2587)) ([f74d874](https://github.com/headroomlabs-ai/headroom/commit/f74d87477701f1f95bd4709c4727f3d3890a4e22))
|
||||
* **learn:** don't desync verbosity pairing on empty assistant turns ([#2123](https://github.com/headroomlabs-ai/headroom/issues/2123)) ([def2f9a](https://github.com/headroomlabs-ai/headroom/commit/def2f9a7286a271a36402bc564867b53a3c11b70))
|
||||
* **learn:** filter ambient user-role scaffolding ([#2275](https://github.com/headroomlabs-ai/headroom/issues/2275)) ([3eb0122](https://github.com/headroomlabs-ai/headroom/commit/3eb01220683d65660544c07631b1efb4781e1d53))
|
||||
* **learn:** include stdout in CLI failure messages, not just stderr ([#3080](https://github.com/headroomlabs-ai/headroom/issues/3080)) ([c5563d3](https://github.com/headroomlabs-ai/headroom/commit/c5563d3a7dd8b7f88767cf503f1b1696917e36ee))
|
||||
* **learn:** keep traceback tail in tool-error digest preview ([#2596](https://github.com/headroomlabs-ai/headroom/issues/2596)) ([85e8699](https://github.com/headroomlabs-ai/headroom/commit/85e869945138f06471501046c5725eac119dea58))
|
||||
* **learn:** run project discovery off the event loop ([#2731](https://github.com/headroomlabs-ai/headroom/issues/2731)) ([a70e5ff](https://github.com/headroomlabs-ai/headroom/commit/a70e5ff78dc9486e63a6563f122d392469ceef38))
|
||||
* **learn:** stop classifying a successful exit code 0 as an error ([#2289](https://github.com/headroomlabs-ai/headroom/issues/2289)) ([a24fe7d](https://github.com/headroomlabs-ai/headroom/commit/a24fe7dcbfe5ab30d0cef631c936e2245c12d123))
|
||||
* **learn:** treat unreadable candidate paths as absent in project decode ([#2446](https://github.com/headroomlabs-ai/headroom/issues/2446)) ([a09ba6c](https://github.com/headroomlabs-ai/headroom/commit/a09ba6c08723618dba5f282a9beac78c9406edbf))
|
||||
* **litellm:** add async_post_call_success_hook to HeadroomCallback ([#1322](https://github.com/headroomlabs-ai/headroom/issues/1322)) ([3107994](https://github.com/headroomlabs-ai/headroom/commit/3107994aed5fd42e713d3c26f3f08121a62b980e))
|
||||
* **litellm:** don't forward a caller key the target cannot accept ([#2883](https://github.com/headroomlabs-ai/headroom/issues/2883)) ([2f2950a](https://github.com/headroomlabs-ai/headroom/commit/2f2950a626cebf851aac29255e7188fbb1639f5a))
|
||||
* **litellm:** forward chat_template_kwargs and other vendor top-level fields to OpenAI-compatible backends via extra_body ([#2128](https://github.com/headroomlabs-ai/headroom/issues/2128)) ([#2163](https://github.com/headroomlabs-ai/headroom/issues/2163)) ([fb683e1](https://github.com/headroomlabs-ai/headroom/commit/fb683e18d4cbb0228dcbf951762826bc0eb63a39))
|
||||
* **mcp/claude:** don't clobber an unparseable Claude config on register ([#1660](https://github.com/headroomlabs-ai/headroom/issues/1660)) ([bc24e25](https://github.com/headroomlabs-ai/headroom/commit/bc24e258b11f3a91c23562336a3d38d90d347fc1))
|
||||
* **mcp:** mcp status checks ~/.claude.json, not only ~/.claude/mcp.json ([#990](https://github.com/headroomlabs-ai/headroom/issues/990)) ([9e376af](https://github.com/headroomlabs-ai/headroom/commit/9e376afabe7dbed29fb9ff33ce2f8eee283faabd))
|
||||
* **mcp:** pin mcp dependency to <2.0.0 to prevent server startup crash ([#2642](https://github.com/headroomlabs-ai/headroom/issues/2642)) ([b3f016b](https://github.com/headroomlabs-ai/headroom/commit/b3f016b866375cfe2ff8518055ab93844e11ec27))
|
||||
* **mcp:** reap orphaned mcp serve on client death ([#2226](https://github.com/headroomlabs-ai/headroom/issues/2226)) ([7a5d8a7](https://github.com/headroomlabs-ai/headroom/commit/7a5d8a7ace2c86f7ab606b0746907443a3565344))
|
||||
* **mcp:** regenerate stale server.json (0.27.0 -> 0.32.0) ([#2218](https://github.com/headroomlabs-ai/headroom/issues/2218)) ([79d8056](https://github.com/headroomlabs-ai/headroom/commit/79d8056fd76a8f94cc17045236c15f52e3da73e0))
|
||||
* **mcp:** restore SDK v1 compatibility cap ([#2978](https://github.com/headroomlabs-ai/headroom/issues/2978)) ([6077e5a](https://github.com/headroomlabs-ai/headroom/commit/6077e5a149ee6548edaff033f2cdffffce6ea0cf))
|
||||
* **memory:** audit passive context injection ([#2212](https://github.com/headroomlabs-ai/headroom/issues/2212)) ([2de07db](https://github.com/headroomlabs-ai/headroom/commit/2de07db28199f2da5ef27d37a38c638addf367fc))
|
||||
* **memory:** bound the TrafficLearner pending-pattern accumulator (memory leak) ([#2579](https://github.com/headroomlabs-ai/headroom/issues/2579)) ([1f5feff](https://github.com/headroomlabs-ai/headroom/commit/1f5fefffd3e82c73bddd928cfd53334031e807bc))
|
||||
* **memory:** close DirectMem0 resources ([6596182](https://github.com/headroomlabs-ai/headroom/commit/65961827cf5e90d7b4e7026feb89aac000a73ea3))
|
||||
* **memory:** close MCP backend on shutdown ([4bd8ecd](https://github.com/headroomlabs-ai/headroom/commit/4bd8ecd1e31475365801791d35630f66f7393553))
|
||||
* **memory:** don't crash inline memory extraction on a non-object <memory> block ([#2470](https://github.com/headroomlabs-ai/headroom/issues/2470)) ([e00c6ff](https://github.com/headroomlabs-ai/headroom/commit/e00c6ff81ce2003e04042b8f2d1bd6aa3c6e885c))
|
||||
* **memory:** filter inactive graph-expanded results ([#2210](https://github.com/headroomlabs-ai/headroom/issues/2210)) ([aa4515c](https://github.com/headroomlabs-ai/headroom/commit/aa4515cf7aaf74e1780c170ec8fe24d5fb3a7e49))
|
||||
* **memory:** keep vector metadata in sync ([#2295](https://github.com/headroomlabs-ai/headroom/issues/2295)) ([c471800](https://github.com/headroomlabs-ai/headroom/commit/c471800e8ee22986c308464b02a85da5575f34cc))
|
||||
* **memory:** make explicit-project and user store keys collision-resistant ([#2231](https://github.com/headroomlabs-ai/headroom/issues/2231)) ([f840d5f](https://github.com/headroomlabs-ai/headroom/commit/f840d5f2fe938432e542c3f71f2218eeecd06b05))
|
||||
* **memory:** preserve semantically similar memories ([#2303](https://github.com/headroomlabs-ai/headroom/issues/2303)) ([5279c33](https://github.com/headroomlabs-ai/headroom/commit/5279c33b192402faa7c4cbb7b1f6bae36ccda9c7))
|
||||
* **memory:** require explicit updates for supersession ([#2188](https://github.com/headroomlabs-ai/headroom/issues/2188)) ([6d897e8](https://github.com/headroomlabs-ai/headroom/commit/6d897e8eaabaddee22a7763292ab3991ffe15af0))
|
||||
* **memory:** sanitize entity_refs to prevent dict-shaped entries crashing search ([#2951](https://github.com/headroomlabs-ai/headroom/issues/2951)) ([2d1e96b](https://github.com/headroomlabs-ai/headroom/commit/2d1e96b85c61cc7aab821750f549f24d54cbb6f5))
|
||||
* **memory:** serialize MCP backend initialization ([#2309](https://github.com/headroomlabs-ai/headroom/issues/2309)) ([0924755](https://github.com/headroomlabs-ai/headroom/commit/0924755591d0fb625439facb04905e4fc052b445))
|
||||
* **memory:** skip <system-reminder> blocks when building the retrieval query ([#2195](https://github.com/headroomlabs-ai/headroom/issues/2195)) ([#2541](https://github.com/headroomlabs-ai/headroom/issues/2541)) ([4e5a67a](https://github.com/headroomlabs-ai/headroom/commit/4e5a67a342be4be659b62c7863a9e72422605788))
|
||||
* **memory:** sync FTS5 and vector indexes on CLI delete/edit/prune/purge ([fd4628d](https://github.com/headroomlabs-ai/headroom/commit/fd4628d82156c65d4fa22df9513315790a6cd2fb))
|
||||
* **metrics:** attribute tool-schema savings per model, not just compression ([#3155](https://github.com/headroomlabs-ai/headroom/issues/3155)) ([81fe9d5](https://github.com/headroomlabs-ai/headroom/commit/81fe9d534579d4dcac197ba901f65d6f19986d32))
|
||||
* 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](https://github.com/headroomlabs-ai/headroom/commit/789a4f3060aa33a5bae82680968c3e367fa2db83))
|
||||
* **oauth2:** make repository lint checks pass ([c85abf7](https://github.com/headroomlabs-ai/headroom/commit/c85abf7a87920012e01f0a677f6fbd98c4b08de0))
|
||||
* **observability:** aggregate tool savings in OTEL ([#2936](https://github.com/headroomlabs-ai/headroom/issues/2936)) ([941c25d](https://github.com/headroomlabs-ai/headroom/commit/941c25d31e6c6e0b436c307cbe212771ff76b45f))
|
||||
* **onnx:** enforce Rust API-24 runtime compatibility ([#2979](https://github.com/headroomlabs-ai/headroom/issues/2979)) ([a3fe5cb](https://github.com/headroomlabs-ai/headroom/commit/a3fe5cb65bed625e2a6cb415821bd0798754ce08))
|
||||
* **onnx:** stop ONNX thread pools from spinning idle cores ([#2495](https://github.com/headroomlabs-ai/headroom/issues/2495)) ([#2540](https://github.com/headroomlabs-ai/headroom/issues/2540)) ([5c561bd](https://github.com/headroomlabs-ai/headroom/commit/5c561bd913ea60fad2c3c53f4b65e679e7d248d0))
|
||||
* **openai:** skip Responses tool-search deferral for clients that cannot execute it ([#2696](https://github.com/headroomlabs-ai/headroom/issues/2696)) ([54ea28d](https://github.com/headroomlabs-ai/headroom/commit/54ea28d9839a0dcfa4dd0cf4210a4421f03beeff))
|
||||
* **openclaw-plugin:** circuit breaker + per-request timeout for proxy resilience ([#639](https://github.com/headroomlabs-ai/headroom/issues/639)) ([6576ef6](https://github.com/headroomlabs-ai/headroom/commit/6576ef639cbb7be8bc5e6c25134956803d18f8d8))
|
||||
* **opencode:** send x-headroom-project header on all proxied requests ([#2868](https://github.com/headroomlabs-ai/headroom/issues/2868)) ([eeb038b](https://github.com/headroomlabs-ai/headroom/commit/eeb038bc0c28fc8078986db0849bfcff6743c158))
|
||||
* **opencode:** ship the transport hook-shim so wheel installs route Node child traffic ([702dbc5](https://github.com/headroomlabs-ai/headroom/commit/702dbc5902ff184a7c20178958a811beb9c78fa3))
|
||||
* **opencode:** Use opencode.jsonc when present ([#1590](https://github.com/headroomlabs-ai/headroom/issues/1590)) ([4e2bbfe](https://github.com/headroomlabs-ai/headroom/commit/4e2bbfee3f65e3287ab7693da70f0d7b20dada28))
|
||||
* **opencode:** use type=local + environment field for MCP config ([#1380](https://github.com/headroomlabs-ai/headroom/issues/1380)) ([#1388](https://github.com/headroomlabs-ai/headroom/issues/1388)) ([a51bbfb](https://github.com/headroomlabs-ai/headroom/commit/a51bbfb6a56fa06ef18109ee0194610c400a2f43))
|
||||
* **policy:** price net-cost mutations with the 1h cache-write tier ([#2780](https://github.com/headroomlabs-ai/headroom/issues/2780)) ([ef7e07e](https://github.com/headroomlabs-ai/headroom/commit/ef7e07e0f5d6510ab96b5abb1698b1b681b5f9bf))
|
||||
* **providers/anthropic:** don't crash token estimation on null tool_calls ([#2472](https://github.com/headroomlabs-ai/headroom/issues/2472)) ([08466f3](https://github.com/headroomlabs-ai/headroom/commit/08466f3cae4dbb2647dc6f249fe42c4e840600c5))
|
||||
* **providers/openai:** bound tiktoken vocab loads with the guarded loader ([#2554](https://github.com/headroomlabs-ai/headroom/issues/2554)) ([0805e8e](https://github.com/headroomlabs-ai/headroom/commit/0805e8e410543d75c7ddd3b83dde5eda3bc13144))
|
||||
* **providers:** don't crash on a non-object HEADROOM_MODEL_LIMITS / models.json ([#3089](https://github.com/headroomlabs-ai/headroom/issues/3089)) ([3ed8f76](https://github.com/headroomlabs-ai/headroom/commit/3ed8f7601935cb08eebfd34007e97675903180a5))
|
||||
* **providers:** give every model exactly one tokenizer ([#2761](https://github.com/headroomlabs-ai/headroom/issues/2761)) ([cd92ed5](https://github.com/headroomlabs-ai/headroom/commit/cd92ed52ff80ee7932600306349fd5d6601b5404))
|
||||
* **providers:** stop a shorter model family shadowing a longer one ([#2762](https://github.com/headroomlabs-ai/headroom/issues/2762)) ([0cb72f4](https://github.com/headroomlabs-ai/headroom/commit/0cb72f45b23bdf7129822b16dd1d4cb7d6e0b062))
|
||||
* **providers:** stop pricing modern content blocks at zero ([#2760](https://github.com/headroomlabs-ai/headroom/issues/2760)) ([06add9e](https://github.com/headroomlabs-ai/headroom/commit/06add9e9d833783c1144316c0cb3cb142377d897))
|
||||
* **proxy/anthropic:** don't buffer a CCR stream when passthrough discards the stream flip ([#2953](https://github.com/headroomlabs-ai/headroom/issues/2953)) ([f1c34d3](https://github.com/headroomlabs-ai/headroom/commit/f1c34d336cf35db341153c1c65e8c15219398340))
|
||||
* **proxy/anthropic:** don't replay recorded prefix over live history ([#3026](https://github.com/headroomlabs-ai/headroom/issues/3026)) ([#3052](https://github.com/headroomlabs-ai/headroom/issues/3052)) ([c16be9b](https://github.com/headroomlabs-ai/headroom/commit/c16be9bbbec4aec6d4b35e482c166daef8afa72c))
|
||||
* **proxy/anthropic:** inject headroom_retrieve whenever a CCR marker is present, not only for new markers ([#2848](https://github.com/headroomlabs-ai/headroom/issues/2848)) ([3808f60](https://github.com/headroomlabs-ai/headroom/commit/3808f60ca61e84faf3ea8f8e003a6e6c8e9af4da))
|
||||
* **proxy/anthropic:** None-guard usage token counts on the direct buffered path ([#2434](https://github.com/headroomlabs-ai/headroom/issues/2434)) ([2b5ee7c](https://github.com/headroomlabs-ai/headroom/commit/2b5ee7cde809ca37f6998d9679b1eb2133ab50ca))
|
||||
* **proxy/anthropic:** repair headroom_retrieve history references the tools array cannot support ([#2876](https://github.com/headroomlabs-ai/headroom/issues/2876)) ([7de3573](https://github.com/headroomlabs-ai/headroom/commit/7de35739c61bed385dd078aee1b36865938c486d))
|
||||
* **proxy/anthropic:** run tool-search history repair after turn hooks ([c6f9948](https://github.com/headroomlabs-ai/headroom/commit/c6f99482e1bea024db6014a70c8e6da419543957))
|
||||
* **proxy/anthropic:** stop answering a non-streaming turn with an event stream ([#3142](https://github.com/headroomlabs-ai/headroom/issues/3142)) ([0e26fb8](https://github.com/headroomlabs-ai/headroom/commit/0e26fb80de600795e96435473486c4a7c79c6eaa))
|
||||
* **proxy/batch:** don't crash an OpenAI batch on a valid-JSON non-object line ([#2316](https://github.com/headroomlabs-ai/headroom/issues/2316)) ([1f2c681](https://github.com/headroomlabs-ai/headroom/commit/1f2c681c0b48150a569277d3ebd5e95709dc7c39))
|
||||
* **proxy/batch:** preserve sibling tool configs on Google batch requests ([#2177](https://github.com/headroomlabs-ai/headroom/issues/2177)) ([a5d7e12](https://github.com/headroomlabs-ai/headroom/commit/a5d7e12c9078c008dbb8dc34a77018e5d13cb5da))
|
||||
* **proxy/bedrock:** report uncached input tokens from backend usage, not the live-zone count ([#2318](https://github.com/headroomlabs-ai/headroom/issues/2318)) ([c19e412](https://github.com/headroomlabs-ai/headroom/commit/c19e412b3356d80dece001887d4ff48b6fd5150b))
|
||||
* **proxy/bedrock:** wire PrefixCacheTracker updates into Bedrock backend paths ([#2196](https://github.com/headroomlabs-ai/headroom/issues/2196)) ([a352fa0](https://github.com/headroomlabs-ai/headroom/commit/a352fa0168180844dfac68dd053dfb1b041da822))
|
||||
* **proxy/cache:** strip cache_control from messages in the semantic cache key ([#3086](https://github.com/headroomlabs-ai/headroom/issues/3086)) ([2cae0f8](https://github.com/headroomlabs-ai/headroom/commit/2cae0f8eaf627f6b743deb215f7c19c499c26bcd))
|
||||
* **proxy/cost:** count Gemini thinking tokens in output usage ([#2639](https://github.com/headroomlabs-ai/headroom/issues/2639)) ([22b707f](https://github.com/headroomlabs-ai/headroom/commit/22b707fd31d75914e1677290d2a8011727eb74f5))
|
||||
* **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](https://github.com/headroomlabs-ai/headroom/commit/01df2452529a86c689cf226fecd5918cc5d19676))
|
||||
* **proxy/cost:** record each request's savings exactly once (drop 3 double-counts) ([#2545](https://github.com/headroomlabs-ai/headroom/issues/2545)) ([0845b26](https://github.com/headroomlabs-ai/headroom/commit/0845b26ee61c507487cd8476cfabe8284f59402b))
|
||||
* **proxy/cost:** warn once per model when pricing lookup fails ([#2504](https://github.com/headroomlabs-ai/headroom/issues/2504)) ([#2535](https://github.com/headroomlabs-ai/headroom/issues/2535)) ([fa47637](https://github.com/headroomlabs-ai/headroom/commit/fa4763761b5912cccde95903f4b9a681b555465b))
|
||||
* **proxy/debug:** reconcile Kompress warmup state in /debug/warmup ([#2711](https://github.com/headroomlabs-ai/headroom/issues/2711)) ([3a27c4d](https://github.com/headroomlabs-ai/headroom/commit/3a27c4dacb08a006ca5aa71e8e7728b230c7283f))
|
||||
* **proxy/gemini:** forward a non-JSON upstream body with its real status ([#2174](https://github.com/headroomlabs-ai/headroom/issues/2174)) ([f723925](https://github.com/headroomlabs-ai/headroom/commit/f723925be75ad93978b4bfeab81df4196a9dd401))
|
||||
* **proxy/gemini:** guard CCR continuation usage against present-null counts ([#3035](https://github.com/headroomlabs-ai/headroom/issues/3035)) ([a01897c](https://github.com/headroomlabs-ai/headroom/commit/a01897c791f4bb6471defafd560d29d491eb2df8))
|
||||
* **proxy/gemini:** keep streaming-parity baseline so eligible_pct can't exceed 100 ([#2824](https://github.com/headroomlabs-ai/headroom/issues/2824)) ([b97c7c6](https://github.com/headroomlabs-ai/headroom/commit/b97c7c6e99eac84df49c7a7e5f21dedb298716fe))
|
||||
* **proxy/gemini:** None-guard token counts from usageMetadata ([#2347](https://github.com/headroomlabs-ai/headroom/issues/2347)) ([f64aac9](https://github.com/headroomlabs-ai/headroom/commit/f64aac9733d5e314f381644eaea62e2c28b6dc65))
|
||||
* **proxy/gemini:** tolerate malformed parts on the compression path ([#2486](https://github.com/headroomlabs-ai/headroom/issues/2486)) ([07cf547](https://github.com/headroomlabs-ai/headroom/commit/07cf5476072a45bac7dd94386de126234a8049e7))
|
||||
* **proxy/memory:** don't crash memory tool-call detection on a null function ([#2272](https://github.com/headroomlabs-ai/headroom/issues/2272)) ([8b7e797](https://github.com/headroomlabs-ai/headroom/commit/8b7e797ed41ea9a37ef8711e102b355f9194c571))
|
||||
* **proxy/metrics:** cap client-supplied model label cardinality ([#2480](https://github.com/headroomlabs-ai/headroom/issues/2480)) ([e24a7e6](https://github.com/headroomlabs-ai/headroom/commit/e24a7e66b95fa908c4ea6fd079809ece7692e6b2))
|
||||
* **proxy/metrics:** escape label values in the Prometheus export ([#2463](https://github.com/headroomlabs-ai/headroom/issues/2463)) ([6a53861](https://github.com/headroomlabs-ai/headroom/commit/6a53861063c3839e698bbec7194517bdfd851c38))
|
||||
* **proxy/metrics:** move the savings-ledger append off the event loop ([#2439](https://github.com/headroomlabs-ai/headroom/issues/2439)) ([4aac068](https://github.com/headroomlabs-ai/headroom/commit/4aac068814246db3fa250c48f5c916aa2561d8c8))
|
||||
* **proxy/openai:** cache under looked-up messages ([#2420](https://github.com/headroomlabs-ai/headroom/issues/2420)) ([7052d52](https://github.com/headroomlabs-ai/headroom/commit/7052d52dcbb2fd97b756c9b60a096cdfeee32c94))
|
||||
* **proxy/openai:** don't crash the Responses memory tool loops on null arguments ([#2273](https://github.com/headroomlabs-ai/headroom/issues/2273)) ([a30db2c](https://github.com/headroomlabs-ai/headroom/commit/a30db2cae49b4ef03ebbd404ec1fc6c4f5f2404d))
|
||||
* **proxy/openai:** don't record Codex WS savings without input accounting ([#2493](https://github.com/headroomlabs-ai/headroom/issues/2493)) ([2195ba7](https://github.com/headroomlabs-ai/headroom/commit/2195ba7d917649ba2ac647fdefa661cf598e3028))
|
||||
* **proxy/openai:** feed chat/completions traffic into the traffic learner ([#2333](https://github.com/headroomlabs-ai/headroom/issues/2333)) ([6cdfd3f](https://github.com/headroomlabs-ai/headroom/commit/6cdfd3f64d2f64d50ed47644126df71872a21050))
|
||||
* **proxy/openai:** feed Codex WS traffic into the traffic learner ([#2334](https://github.com/headroomlabs-ai/headroom/issues/2334)) ([f669149](https://github.com/headroomlabs-ai/headroom/commit/f6691497692869b7067438597421ff12aace6bf4))
|
||||
* **proxy/openai:** None-guard usage token counts on the chat path ([#2431](https://github.com/headroomlabs-ai/headroom/issues/2431)) ([313c290](https://github.com/headroomlabs-ai/headroom/commit/313c290df96ca58a19ea0f79c67f5b71bb5f4d60))
|
||||
* **proxy/openai:** propagate provider usage on the Responses WS->HTTP fallback ([#2988](https://github.com/headroomlabs-ai/headroom/issues/2988)) ([536c949](https://github.com/headroomlabs-ai/headroom/commit/536c949a692f4855719d71d612abc4968040286b))
|
||||
* **proxy/openai:** replay incremental events in buffered Responses SSE ([#2410](https://github.com/headroomlabs-ai/headroom/issues/2410)) ([#2415](https://github.com/headroomlabs-ai/headroom/issues/2415)) ([0cbc0e8](https://github.com/headroomlabs-ai/headroom/commit/0cbc0e8e5435cd8d743ae537cdbaa70787bfc5b4))
|
||||
* **proxy/openai:** run response hooks on Responses, and bill their re-drives ([#2872](https://github.com/headroomlabs-ai/headroom/issues/2872)) ([675d13f](https://github.com/headroomlabs-ai/headroom/commit/675d13f08d42455c8fa17bda878c1a11b905cee4))
|
||||
* **proxy/openai:** run tool-description compaction on chat-completions ([#2741](https://github.com/headroomlabs-ai/headroom/issues/2741)) ([f9db5b5](https://github.com/headroomlabs-ai/headroom/commit/f9db5b506030a0e8557af8a350f3806464f8ff15))
|
||||
* **proxy/output-shaping:** tolerate a non-string system block text in steering ([#2435](https://github.com/headroomlabs-ai/headroom/issues/2435)) ([3e97671](https://github.com/headroomlabs-ai/headroom/commit/3e976712e717a53ab6aea73120ae6ffacea74250))
|
||||
* **proxy/perf:** count turn-hook message folds in token accounting ([#2520](https://github.com/headroomlabs-ai/headroom/issues/2520)) ([c371d5a](https://github.com/headroomlabs-ai/headroom/commit/c371d5ad602f5ab93645b2db4673ae2c5e9f0575))
|
||||
* **proxy/perf:** tokenizer-consistent token accounting + surface tool-schema savings ([#2542](https://github.com/headroomlabs-ai/headroom/issues/2542)) ([1cc53c9](https://github.com/headroomlabs-ai/headroom/commit/1cc53c9c92cd4dffaf048dc806cb8c570bdb86b6))
|
||||
* **proxy/savings:** append history point on cache-only savings too ([#2194](https://github.com/headroomlabs-ai/headroom/issues/2194)) ([d125805](https://github.com/headroomlabs-ai/headroom/commit/d1258055893a0af854c0ff7eaf37bbeb9d697706))
|
||||
* **proxy/streaming:** preserve non-standard content-block fields on SSE reconstruction ([#2271](https://github.com/headroomlabs-ai/headroom/issues/2271)) ([6decbd1](https://github.com/headroomlabs-ai/headroom/commit/6decbd1e6e6732dc94f7d501116282c41994ce74))
|
||||
* **proxy/streaming:** tolerate malformed content in _response_to_sse ([#2481](https://github.com/headroomlabs-ai/headroom/issues/2481)) ([77b26c0](https://github.com/headroomlabs-ai/headroom/commit/77b26c093cfb7b5c71a46d5156cb774a2ae889b1))
|
||||
* **proxy:** accept Codex websocket before upstream retries ([#2203](https://github.com/headroomlabs-ai/headroom/issues/2203)) ([551f473](https://github.com/headroomlabs-ai/headroom/commit/551f473e04123a11244429456ca3df28549c6adf))
|
||||
* **proxy:** adapt 200 SSE upstream replies on buffered /v1/responses instead of 502 ([#2622](https://github.com/headroomlabs-ai/headroom/issues/2622)) ([d76fce0](https://github.com/headroomlabs-ai/headroom/commit/d76fce04a39b3f206e38a02e012d50b2c728f7ca))
|
||||
* **proxy:** align signed-thinking wire accounting ([#3015](https://github.com/headroomlabs-ai/headroom/issues/3015)) ([b3f4436](https://github.com/headroomlabs-ai/headroom/commit/b3f443636d279d4bad845a8ef2bddb7ca50e9bc6))
|
||||
* **proxy:** allow settings routes for trusted gateway/dashboard clients ([#2491](https://github.com/headroomlabs-ai/headroom/issues/2491)) ([a5b0a8f](https://github.com/headroomlabs-ai/headroom/commit/a5b0a8f4cc54d68afcf371a422b3a4a9635b7e7f))
|
||||
* **proxy:** batch small Codex Responses tool outputs ([#2239](https://github.com/headroomlabs-ai/headroom/issues/2239)) ([09c66ac](https://github.com/headroomlabs-ai/headroom/commit/09c66ac2128469422ea25f8514776546659ea2f8))
|
||||
* **proxy:** cache litellm model resolution to stop repeated Provider List spam ([99f07e7](https://github.com/headroomlabs-ai/headroom/commit/99f07e7bbdded9dadc70e35ee6ab025279d1aa22))
|
||||
* **proxy:** cancel periodic TOIN task on shutdown ([739fdef](https://github.com/headroomlabs-ai/headroom/commit/739fdef423fa8cbc82537481c875d4570b0ecad4))
|
||||
* **proxy:** close the upstream stream when a streaming body is never consumed ([0951663](https://github.com/headroomlabs-ai/headroom/commit/09516635621caccf7e3db4f537eb49ea49b8a453))
|
||||
* **proxy:** complete stateless Responses and buffered CCR lifecycle ([#2997](https://github.com/headroomlabs-ai/headroom/issues/2997)) ([8a1d38b](https://github.com/headroomlabs-ai/headroom/commit/8a1d38bc5da87b49a530df22090c3a156d2d0cd6))
|
||||
* **proxy:** compress cache-mode cold starts and tag prefix-mismatch passthrough ([#2365](https://github.com/headroomlabs-ai/headroom/issues/2365)) ([aaeba0a](https://github.com/headroomlabs-ai/headroom/commit/aaeba0a319f12b98cad3bfcf1cf991b694b946bf))
|
||||
* **proxy:** compress OpenCode tool schemas and embedded JSON ([#1535](https://github.com/headroomlabs-ai/headroom/issues/1535)) ([05932d7](https://github.com/headroomlabs-ai/headroom/commit/05932d716567cc78087fc4080d45741be18e5cba))
|
||||
* **proxy:** dedupe Codex WS request logging for accurate mixed-provider dashboards ([#2189](https://github.com/headroomlabs-ai/headroom/issues/2189)) ([e5b3a63](https://github.com/headroomlabs-ai/headroom/commit/e5b3a634df81610bb4ae5a5b9d1859f6fb38b6d3))
|
||||
* **proxy:** emit request log timestamps in UTC ([620028f](https://github.com/headroomlabs-ai/headroom/commit/620028fa18843622d3e454bd40fb91a93e607dbf))
|
||||
* **proxy:** enable tool search by default and repair poisoned transcripts ([#2807](https://github.com/headroomlabs-ai/headroom/issues/2807)) ([0237cbf](https://github.com/headroomlabs-ai/headroom/commit/0237cbffbbc456ad8a7398005602d76881862d99))
|
||||
* **proxy:** gate mid-turn message coalescing to Claude Code clients ([#1643](https://github.com/headroomlabs-ai/headroom/issues/1643)) ([a4bd2e6](https://github.com/headroomlabs-ai/headroom/commit/a4bd2e62a5bb73f15b3b12e979c69e2b555bee10))
|
||||
* **proxy:** give each Codex /v1/responses WS turn a unique request_id ([#2164](https://github.com/headroomlabs-ai/headroom/issues/2164)) ([d02df10](https://github.com/headroomlabs-ai/headroom/commit/d02df1075894b414d60626aca2bbcadd7a3577a0))
|
||||
* **proxy:** graceful shutdown and reliable Ctrl+C exit ([#621](https://github.com/headroomlabs-ai/headroom/issues/621)) ([17cdb18](https://github.com/headroomlabs-ai/headroom/commit/17cdb185bc79d8cfec104e781a7e555af3ef11e1))
|
||||
* **proxy:** guard feedback endpoints and add CSRF checks to loopback writes ([#3060](https://github.com/headroomlabs-ai/headroom/issues/3060)) ([a6ab359](https://github.com/headroomlabs-ai/headroom/commit/a6ab359a5d8d67a85f734131b55dbcef768a821a))
|
||||
* **proxy:** guard telemetry and TOIN endpoints ([cde1513](https://github.com/headroomlabs-ai/headroom/commit/cde1513c91b6c6c240869bc5660f4b8966197bbc))
|
||||
* **proxy:** include tool_search_deferral savings in the savings ledger ([12149f7](https://github.com/headroomlabs-ai/headroom/commit/12149f74466c08b69be8d5fe751425be63c2fda4))
|
||||
* **proxy:** keep anthropic ccr compression active across deferred injection ([#2291](https://github.com/headroomlabs-ai/headroom/issues/2291)) ([#2297](https://github.com/headroomlabs-ai/headroom/issues/2297)) ([26b43f6](https://github.com/headroomlabs-ai/headroom/commit/26b43f64d6863fafebb0e2a48e059dcb59b9b397))
|
||||
* **proxy:** keep buffered CCR streams alive ([#2479](https://github.com/headroomlabs-ai/headroom/issues/2479)) ([a2e42fb](https://github.com/headroomlabs-ai/headroom/commit/a2e42fb877642e7eacfcc77655183244823d969e))
|
||||
* **proxy:** keep core tools and the client's ToolSearch resident for PascalCase clients ([#2647](https://github.com/headroomlabs-ai/headroom/issues/2647)) ([1d29738](https://github.com/headroomlabs-ai/headroom/commit/1d29738818bb40e00847dba46e2f9acce773d3eb))
|
||||
* **proxy:** keep prefixed core tools resident ([#3046](https://github.com/headroomlabs-ai/headroom/issues/3046)) ([2f4d001](https://github.com/headroomlabs-ai/headroom/commit/2f4d001c9ffd7f856c8dab3e31a8240a1c676f04))
|
||||
* **proxy:** key drift detector on conversations, not credentials; canonicalize drift hashes ([#2301](https://github.com/headroomlabs-ai/headroom/issues/2301)) ([6744833](https://github.com/headroomlabs-ai/headroom/commit/6744833afed9aba7bdadd2aa59ed3a6fa99afc15))
|
||||
* **proxy:** offload OpenAI and Gemini tokenizer counting off the event loop ([#2498](https://github.com/headroomlabs-ai/headroom/issues/2498)) ([806d2e4](https://github.com/headroomlabs-ai/headroom/commit/806d2e468ace012ebfa1a0907a679781b5004c72))
|
||||
* **proxy:** one bad extension no longer aborts proxy startup ([#2215](https://github.com/headroomlabs-ai/headroom/issues/2215)) ([cb6c828](https://github.com/headroomlabs-ai/headroom/commit/cb6c8284575b70d754f5fc83158d8ef38777526b))
|
||||
* **proxy:** pass through cross-region prefixed Bedrock model IDs directly ([#2330](https://github.com/headroomlabs-ai/headroom/issues/2330)) ([64cb46e](https://github.com/headroomlabs-ai/headroom/commit/64cb46e24bf7b223ea71b14b6f5e86e78fa7ac45))
|
||||
* **proxy:** port session-sticky beta headers to the Rust proxy ([#2381](https://github.com/headroomlabs-ai/headroom/issues/2381)) ([f6398a6](https://github.com/headroomlabs-ai/headroom/commit/f6398a64768a095b722a5fb0b2445c7953dee1c6))
|
||||
* **proxy:** preserve Codex WebSocket model attribution ([#3029](https://github.com/headroomlabs-ai/headroom/issues/3029)) ([a06a51e](https://github.com/headroomlabs-ai/headroom/commit/a06a51eca63f88271dfa77f2ee6bf3c8da6b24e4))
|
||||
* **proxy:** preserve content-part array structure in excluded-tool lossless fold write-back ([#2261](https://github.com/headroomlabs-ai/headroom/issues/2261)) ([8951a26](https://github.com/headroomlabs-ai/headroom/commit/8951a264a2dea417a733ce446463cc5ee4d74781))
|
||||
* **proxy:** preserve merged session and quarantine contracts ([#2943](https://github.com/headroomlabs-ai/headroom/issues/2943)) ([039cd24](https://github.com/headroomlabs-ai/headroom/commit/039cd2431aaec7d59fefaf7e97aeda1fd7ab3afa))
|
||||
* **proxy:** preserve signed Anthropic thinking blocks on outbound re-serialize ([#2254](https://github.com/headroomlabs-ai/headroom/issues/2254)) ([dc163bc](https://github.com/headroomlabs-ai/headroom/commit/dc163bcd1cba4cd8898f23286eb1365fcf6e0356))
|
||||
* **proxy:** promote Kompress health after runtime load ([#2402](https://github.com/headroomlabs-ai/headroom/issues/2402)) ([54526bc](https://github.com/headroomlabs-ai/headroom/commit/54526bc8586cdeb248d6257dc497136a21b971c0))
|
||||
* **proxy:** quarantine compression while timed-out workers run ([#2292](https://github.com/headroomlabs-ai/headroom/issues/2292)) ([517bf99](https://github.com/headroomlabs-ai/headroom/commit/517bf992cfb096c9f277d1f39aa24f9a979600dc))
|
||||
* **proxy:** reassemble server_tool_use.input from streamed partial_json ([#2449](https://github.com/headroomlabs-ai/headroom/issues/2449)) ([8c8fae0](https://github.com/headroomlabs-ai/headroom/commit/8c8fae0d0bca75f7f2561136910e40f716be57ab))
|
||||
* **proxy:** record Prometheus metrics for POST /v1/compress ([#2247](https://github.com/headroomlabs-ai/headroom/issues/2247)) ([81d40a6](https://github.com/headroomlabs-ai/headroom/commit/81d40a6437979d6b8ebc524ff8c5a9d9b7c2d10a))
|
||||
* **proxy:** reject rate_limit_requests_per_minute=0 when limiting is enabled ([#2142](https://github.com/headroomlabs-ai/headroom/issues/2142)) ([8a71947](https://github.com/headroomlabs-ai/headroom/commit/8a71947023f41efdc81887c531b134f135e8ef67))
|
||||
* **proxy:** relocate stray system-role messages to the top-level system param ([#765](https://github.com/headroomlabs-ai/headroom/issues/765)) ([#1357](https://github.com/headroomlabs-ai/headroom/issues/1357)) ([9fde127](https://github.com/headroomlabs-ai/headroom/commit/9fde12753416a6102535235b822e44afebf76e9e))
|
||||
* **proxy:** repair main lint (ruff-format drift + mypy host_header) ([#2268](https://github.com/headroomlabs-ai/headroom/issues/2268)) ([718c8dc](https://github.com/headroomlabs-ai/headroom/commit/718c8dc559c0432d234da28053cea602c2d9245a))
|
||||
* **proxy:** report deferred Kompress status and promote health from cache ([#2564](https://github.com/headroomlabs-ai/headroom/issues/2564)) ([d50cfab](https://github.com/headroomlabs-ai/headroom/commit/d50cfabedca2c4b7d83751adaa8aa7b317f13c7b))
|
||||
* **proxy:** restore the buffered-CCR heartbeat behind a grace window ([#3091](https://github.com/headroomlabs-ai/headroom/issues/3091)) ([a29d201](https://github.com/headroomlabs-ai/headroom/commit/a29d2015e5eaf72730a4155f0307cbfac1ea1c9b))
|
||||
* **proxy:** route Codex Live voice through a dedicated /v1/live transport ([#2709](https://github.com/headroomlabs-ai/headroom/issues/2709)) ([232fb49](https://github.com/headroomlabs-ai/headroom/commit/232fb49c733122652528edcf3c500f365df265c4))
|
||||
* **proxy:** satisfy rustfmt import ordering ([#2158](https://github.com/headroomlabs-ai/headroom/issues/2158)) ([f008336](https://github.com/headroomlabs-ai/headroom/commit/f00833654f187eade7c70a2e5be549b75399bbab))
|
||||
* **proxy:** scope the signed-thinking lock to blocks that actually changed ([#3124](https://github.com/headroomlabs-ai/headroom/issues/3124)) ([17522fb](https://github.com/headroomlabs-ai/headroom/commit/17522fb0a1013c012e8123b1e713dbb2f3e770d9))
|
||||
* **proxy:** skip max_tokens rename for backend-routed openai chat ([#2401](https://github.com/headroomlabs-ai/headroom/issues/2401)) ([d6a1af4](https://github.com/headroomlabs-ai/headroom/commit/d6a1af40d5a18f4440a45e342c2d05fee7a642e3))
|
||||
* **proxy:** skip OpenAI tool_search deferral for Codex client ([#2729](https://github.com/headroomlabs-ai/headroom/issues/2729)) ([56b3e4c](https://github.com/headroomlabs-ai/headroom/commit/56b3e4c1b1e3513c409242b30e7712514f2624d5))
|
||||
* **proxy:** skip Responses memory tools for ChatGPT auth ([#1579](https://github.com/headroomlabs-ai/headroom/issues/1579)) ([1c50eca](https://github.com/headroomlabs-ai/headroom/commit/1c50eca8b3f44ba06fee3d1cae22f3cf40eac5f8))
|
||||
* **proxy:** stop a lone surrogate turning a thinking body into a 500 ([#3134](https://github.com/headroomlabs-ai/headroom/issues/3134)) ([284ff31](https://github.com/headroomlabs-ai/headroom/commit/284ff31947ec9eac1de0e2dc1cf5de4933c29a50))
|
||||
* **proxy:** stop cached responses replaying the producing turn's wire framing ([#3024](https://github.com/headroomlabs-ai/headroom/issues/3024)) ([9d37059](https://github.com/headroomlabs-ai/headroom/commit/9d370592b022d01e6bc44a88649a611507794776))
|
||||
* **proxy:** stop discarding compressed Codex WS later-frame payloads ([#2823](https://github.com/headroomlabs-ai/headroom/issues/2823)) ([4ec416d](https://github.com/headroomlabs-ai/headroom/commit/4ec416df8899036544e679f561f1cf921f3da0dd))
|
||||
* **proxy:** stop operator secrets following a client-chosen upstream ([#3122](https://github.com/headroomlabs-ai/headroom/issues/3122)) ([05f5ef4](https://github.com/headroomlabs-ai/headroom/commit/05f5ef47cbc8b31a60458553d6bf240896a47e16))
|
||||
* **proxy:** stop toggling headroom_retrieve in the Anthropic tools array ([#2672](https://github.com/headroomlabs-ai/headroom/issues/2672)) ([08fce29](https://github.com/headroomlabs-ai/headroom/commit/08fce29b4750a79fb2fbc3969847bb38f35e29b3))
|
||||
* **proxy:** support Codex WS compatible gateways ([#1281](https://github.com/headroomlabs-ai/headroom/issues/1281)) ([ac7ee4e](https://github.com/headroomlabs-ai/headroom/commit/ac7ee4e0bf25a49f05df44a38d40ecb806cf3972))
|
||||
* **proxy:** time-cap the compression timeout-debt quarantine ([#2360](https://github.com/headroomlabs-ai/headroom/issues/2360)) ([#2412](https://github.com/headroomlabs-ai/headroom/issues/2412)) ([c5a08d2](https://github.com/headroomlabs-ai/headroom/commit/c5a08d22e05a7dd2b929f3cca76ee3fb42f122db))
|
||||
* **proxy:** tune macOS libmalloc and trim allocator pages so long-lived RSS stays bounded ([#2879](https://github.com/headroomlabs-ai/headroom/issues/2879)) ([6d87825](https://github.com/headroomlabs-ai/headroom/commit/6d87825f62e47bc65eeae05fbb8a131d545fe5a2))
|
||||
* **proxy:** unwrap Hermes tool_call bridge in tool name map ([#2717](https://github.com/headroomlabs-ai/headroom/issues/2717)) ([a97b824](https://github.com/headroomlabs-ai/headroom/commit/a97b82413bdc86655c064417ed4628ff4d9d7c9d))
|
||||
* publish headroom-opencode in release workflow ([#2372](https://github.com/headroomlabs-ai/headroom/issues/2372)) ([7859154](https://github.com/headroomlabs-ai/headroom/commit/78591545ceb8303fdf9b93cd5ff02b626df97d2b))
|
||||
* **release:** publish Windows wheel + sdist (disable PyPI attestations, [#112](https://github.com/headroomlabs-ai/headroom/issues/112)) ([#2405](https://github.com/headroomlabs-ai/headroom/issues/2405)) ([f9cbdd6](https://github.com/headroomlabs-ai/headroom/commit/f9cbdd6e390714e037832f78c59d00907a26b612))
|
||||
* **release:** sync generated version metadata on the release branch ([#2659](https://github.com/headroomlabs-ai/headroom/issues/2659)) ([5383c6b](https://github.com/headroomlabs-ai/headroom/commit/5383c6bf2f5209ddfe33cb9bf1c36c0b2e431bcd))
|
||||
* remove rtk and lean-ctx CLI context tools ([#2677](https://github.com/headroomlabs-ai/headroom/issues/2677)) ([e0ce4b1](https://github.com/headroomlabs-ai/headroom/commit/e0ce4b1d4817e1b352e68e8b316273d863260ba7))
|
||||
* replace computer_call_output with apply_patch_call_output in output_shaper ([#2250](https://github.com/headroomlabs-ai/headroom/issues/2250)) ([63f74aa](https://github.com/headroomlabs-ai/headroom/commit/63f74aa3e6477db9ac2049007a71ec5a3522649c))
|
||||
* **reporting:** show net vs gross savings, real skip thresholds, and the effective profile ([#3123](https://github.com/headroomlabs-ai/headroom/issues/3123)) ([250ede2](https://github.com/headroomlabs-ai/headroom/commit/250ede2f7f4752c0ab08831013fad3f753f4a578))
|
||||
* **router:** stop counting an image's base64 payload as suffix tokens ([#2778](https://github.com/headroomlabs-ai/headroom/issues/2778)) ([f03cc6d](https://github.com/headroomlabs-ai/headroom/commit/f03cc6d88b826c2752b20bdce944f9ad1e507e83))
|
||||
* **router:** stop protecting passing build/test output as error traces ([#1740](https://github.com/headroomlabs-ai/headroom/issues/1740)) ([7ab83c5](https://github.com/headroomlabs-ai/headroom/commit/7ab83c5107b5183a652f566adeffc7a6ef16a8bc))
|
||||
* **rust:** port CJK-aware relevance-query matching to CodeCompressor ([#2634](https://github.com/headroomlabs-ai/headroom/issues/2634)) ([e86c639](https://github.com/headroomlabs-ai/headroom/commit/e86c6390cec4fc0f932b006b36d5b924511a5b0b))
|
||||
* **savings:** don't bill free models at the $3/M fallback in the ledger ([#2147](https://github.com/headroomlabs-ai/headroom/issues/2147)) ([fb17156](https://github.com/headroomlabs-ai/headroom/commit/fb17156bfae156bd8f62668c19a4f560e11102e0))
|
||||
* **savings:** don't fabricate output savings for a free (zero-priced) model ([#2298](https://github.com/headroomlabs-ai/headroom/issues/2298)) ([ec12e18](https://github.com/headroomlabs-ai/headroom/commit/ec12e18186852118204ec9ac8fdd33e068c0dcad))
|
||||
* **savings:** record pre-compression original as ledger before, not forwarded count ([#2176](https://github.com/headroomlabs-ai/headroom/issues/2176)) ([195ed90](https://github.com/headroomlabs-ai/headroom/commit/195ed90ced746408f05d6abb7d60ac3ec1a55ccc))
|
||||
* **savings:** surface request growth the tok_saved clamp swallows ([#2708](https://github.com/headroomlabs-ai/headroom/issues/2708)) ([184146b](https://github.com/headroomlabs-ai/headroom/commit/184146b6884b7b0e4c589c5ee414f96bf56d867f))
|
||||
* **security:** address u9up assessment findings (WEB-0107) ([#2207](https://github.com/headroomlabs-ai/headroom/issues/2207)) ([1f96dab](https://github.com/headroomlabs-ai/headroom/commit/1f96dabc19130947770353cd6e814db4fd96e6a0))
|
||||
* **security:** exclude compromised ast-grep-cli 0.44.1 (supply-chain trojan) ([#2342](https://github.com/headroomlabs-ai/headroom/issues/2342)) ([494fb5a](https://github.com/headroomlabs-ai/headroom/commit/494fb5a60e15ae1ce425f79f1432827b42923c73))
|
||||
* **settings:** accept documented HEADROOM_* env names as settings keys ([#2833](https://github.com/headroomlabs-ai/headroom/issues/2833)) ([de9e052](https://github.com/headroomlabs-ai/headroom/commit/de9e0523dad47b700062464adecd60f82547f332))
|
||||
* **stats:** report one "Tokens Saved" headline across every harness ([#2737](https://github.com/headroomlabs-ai/headroom/issues/2737)) ([8262a4a](https://github.com/headroomlabs-ai/headroom/commit/8262a4a3217bf6125f293bacc1df9ae21f63264d))
|
||||
* **stats:** tag streamed output token source ([#2214](https://github.com/headroomlabs-ai/headroom/issues/2214)) ([1c9585d](https://github.com/headroomlabs-ai/headroom/commit/1c9585d42ee4167def21cf5e823cdb7ee329c33f))
|
||||
* **subscription:** dedup transcript usage by message id ([#2340](https://github.com/headroomlabs-ai/headroom/issues/2340) token inflation) ([#2408](https://github.com/headroomlabs-ai/headroom/issues/2408)) ([74275b7](https://github.com/headroomlabs-ai/headroom/commit/74275b7c3e2b39be5198f9efa35057a5e026e665))
|
||||
* **subscription:** keep efficiency_pct from exceeding 100% ([#2121](https://github.com/headroomlabs-ai/headroom/issues/2121)) ([5fb449e](https://github.com/headroomlabs-ai/headroom/commit/5fb449e90be354c5846b9ba96dedbbcd8201eff7))
|
||||
* **subscription:** read newest transcript tail ([#2310](https://github.com/headroomlabs-ai/headroom/issues/2310)) ([793d20f](https://github.com/headroomlabs-ai/headroom/commit/793d20fb2a1c0d3608abd23c4587db1b17dc238d))
|
||||
* **telemetry:** anonymous compression stats no prompts, no data ([#2728](https://github.com/headroomlabs-ai/headroom/issues/2728)) ([9cfb008](https://github.com/headroomlabs-ai/headroom/commit/9cfb00838a197159d94aa52bc042df1a754b7984))
|
||||
* **telemetry:** only advance usage-report baseline after a 200 ([#2149](https://github.com/headroomlabs-ai/headroom/issues/2149)) ([0cddac6](https://github.com/headroomlabs-ai/headroom/commit/0cddac632d8ab4e0bcd752b9c7519d5099aa085e))
|
||||
* **telemetry:** stop mixing tokenizer scales in RequestOutcome, and fix the overhead framing ([#2756](https://github.com/headroomlabs-ai/headroom/issues/2756)) ([04e1517](https://github.com/headroomlabs-ai/headroom/commit/04e1517ede0a17ffa950a9531f210e31d236c660))
|
||||
* **tests:** repair three main-branch test failures ([#2306](https://github.com/headroomlabs-ai/headroom/issues/2306)) ([1d79e70](https://github.com/headroomlabs-ai/headroom/commit/1d79e70f9598f866be6c11a64e81887625127a94))
|
||||
* **toin:** bound private query and pattern retention ([8cd1380](https://github.com/headroomlabs-ai/headroom/commit/8cd138039edbfc295080ec474325d527fb3aedf3))
|
||||
* **tokenizer:** coerce non-string tool_call fields before counting ([#2801](https://github.com/headroomlabs-ai/headroom/issues/2801)) ([b6f9877](https://github.com/headroomlabs-ai/headroom/commit/b6f9877c78b3fa3b1d705426bd27d74be77f4fa0))
|
||||
* **tokenizer:** price CJK in the Rust fixed-ratio estimator (Python parity) ([#2260](https://github.com/headroomlabs-ai/headroom/issues/2260)) ([6840153](https://github.com/headroomlabs-ai/headroom/commit/6840153473caa0d61e982215e16a8cf54b0b6cc7))
|
||||
* **tokenizers:** count HuggingFace chat templates, and resolve gpt-5 / gateway-wrapped names ([#2758](https://github.com/headroomlabs-ai/headroom/issues/2758)) ([0ed306b](https://github.com/headroomlabs-ai/headroom/commit/0ed306b22bf61bfaa421991aea0bd562fc97d910))
|
||||
* **tokenizers:** price Claude against a real BPE (tiktoken o200k) not a char estimate ([#2543](https://github.com/headroomlabs-ai/headroom/issues/2543)) ([285176b](https://github.com/headroomlabs-ai/headroom/commit/285176be54e1d179676dcf205de44d5893f8efa5))
|
||||
* **tokenizers:** resolve gpt-5 and mixed-case model names to the right encoding ([#2776](https://github.com/headroomlabs-ai/headroom/issues/2776)) ([fc4680b](https://github.com/headroomlabs-ai/headroom/commit/fc4680b37af1d522fdbeba8e5d3228769dc49ba4))
|
||||
* tool_search_tool_regex deferred and falsely resolved on direct-Anthropic path ([#2971](https://github.com/headroomlabs-ai/headroom/issues/2971)) ([8ea87e7](https://github.com/headroomlabs-ai/headroom/commit/8ea87e7804abfbb55beaf869e50dcb66deab975a))
|
||||
* **transforms/adaptive-sizer:** honor max_k on small-input fast path ([#2319](https://github.com/headroomlabs-ai/headroom/issues/2319)) ([8a90523](https://github.com/headroomlabs-ai/headroom/commit/8a905232091d993fac9e19a59bc449f201d4cdf3))
|
||||
* **transforms/cross-turn-dedup:** don't renumber-fold zero-padded line prefixes ([#2369](https://github.com/headroomlabs-ai/headroom/issues/2369)) ([f4070c4](https://github.com/headroomlabs-ai/headroom/commit/f4070c44cbd65ecf49f2ae81ad26a95296ef552b))
|
||||
* **transforms/kompress-remote:** keep compress fail-open on malformed 200 ([#2320](https://github.com/headroomlabs-ai/headroom/issues/2320)) ([b759990](https://github.com/headroomlabs-ai/headroom/commit/b75999017fc060a4617077ef86c21ce3249d0842))
|
||||
* **transforms/smart_crusher:** don't crash on a tool call with a null function ([#2232](https://github.com/headroomlabs-ai/headroom/issues/2232)) ([3bb02f8](https://github.com/headroomlabs-ai/headroom/commit/3bb02f8f75f12cf8258a5b1c2a7fbdc190f9d074))
|
||||
* **transforms:** guard Log fallback against invalid JSON + fix MIXED false-positive on source code ([#1347](https://github.com/headroomlabs-ai/headroom/issues/1347)) ([02c7764](https://github.com/headroomlabs-ai/headroom/commit/02c77640a95e04a33361803fbc25d63d0b86e976))
|
||||
* **transforms:** stop ContentRouter recompressing headroom_retrieve results ([#2654](https://github.com/headroomlabs-ai/headroom/issues/2654)) ([677e097](https://github.com/headroomlabs-ai/headroom/commit/677e09735a41f6c37dedc842ab3c214b5bddeafc))
|
||||
* Vertex model pricing shows $0.00 for versioned model names and vertex:anthropic provider ([#2517](https://github.com/headroomlabs-ai/headroom/issues/2517)) ([eb5b5e4](https://github.com/headroomlabs-ai/headroom/commit/eb5b5e41988f5c27d29ae8ae3e5fe74e56493b8c))
|
||||
* **vscode:** persist compatible Claude modes and route Copilot CAPI ([#2986](https://github.com/headroomlabs-ai/headroom/issues/2986)) ([1aa701a](https://github.com/headroomlabs-ai/headroom/commit/1aa701adaa1ff792dd0e701f498d8d0326655670))
|
||||
* **windows:** unwedge compression on degraded ONNX runtimes (every request timing out at 30s, 0% savings) ([#822](https://github.com/headroomlabs-ai/headroom/issues/822)) ([36202f4](https://github.com/headroomlabs-ai/headroom/commit/36202f4d0bd4dd919dba09f1b4a653754f7c2b2c))
|
||||
* **wrap/claude:** bind _wrap_settings_path before the try ([#2126](https://github.com/headroomlabs-ai/headroom/issues/2126)) ([faed4dc](https://github.com/headroomlabs-ai/headroom/commit/faed4dcfe72a329cc308057efd97fc99885173c4))
|
||||
* **wrap/claude:** keep --1m effective when an explicit --model is passed through ([c093bf1](https://github.com/headroomlabs-ai/headroom/commit/c093bf11eb5f356f71367ebb7b56ae3c2b434a12))
|
||||
* **wrap/codex:** export the detected custom upstream base URL ([#2125](https://github.com/headroomlabs-ai/headroom/issues/2125)) ([d236b27](https://github.com/headroomlabs-ai/headroom/commit/d236b27c607c980a224e24a4e7c0282aea487cc4))
|
||||
* **wrap/opencode:** verify the opencode binary before mutating config ([ae38486](https://github.com/headroomlabs-ai/headroom/commit/ae384862a4950cec057103e9daf75e74107640df))
|
||||
* **wrap/serena:** install Serena from the serena-agent PyPI wheel, not the git source ([d7b25ae](https://github.com/headroomlabs-ai/headroom/commit/d7b25ae3bb3364cde4931509ecb65e32085e5b09))
|
||||
* **wrap/serena:** stop creating serena_config.yml, unbricking Serena on fresh installs ([#2676](https://github.com/headroomlabs-ai/headroom/issues/2676)) ([759209c](https://github.com/headroomlabs-ai/headroom/commit/759209cff3daa72dd9d47e57568e731d10573d63))
|
||||
* **wrap:** drop -p short flag from wrap claude so claude's own -p/--print passes through ([#2048](https://github.com/headroomlabs-ai/headroom/issues/2048)) ([14011b4](https://github.com/headroomlabs-ai/headroom/commit/14011b42dd752fe9a29a988e343ae84255032ab2))
|
||||
* **wrap:** emit bare dotted keys for Codex --config overrides ([#2383](https://github.com/headroomlabs-ai/headroom/issues/2383)) ([f57e959](https://github.com/headroomlabs-ai/headroom/commit/f57e959a506f87f14143d595cae24a1fd6084f66))
|
||||
* **wrap:** honor Copilot OAuth wire-api override and model default ([#2387](https://github.com/headroomlabs-ai/headroom/issues/2387)) ([1db6d88](https://github.com/headroomlabs-ai/headroom/commit/1db6d88ab4ea25654b8277358902b7df700db6b4))
|
||||
* **wrap:** make RTK opt-in (off by default) across wrap subcommands ([#2344](https://github.com/headroomlabs-ai/headroom/issues/2344)) ([44136ed](https://github.com/headroomlabs-ai/headroom/commit/44136ed0427edff338c5d7979b589f8540c9b967))
|
||||
* **wrap:** read/write instruction files as UTF-8 on Windows ([#1245](https://github.com/headroomlabs-ai/headroom/issues/1245)) ([6413cc7](https://github.com/headroomlabs-ai/headroom/commit/6413cc75a243d441d8eb9bb420f24da7a26ef0a9))
|
||||
* **wrap:** self-heal a stale ANTHROPIC_BASE_URL left by a dead proxy ([#2223](https://github.com/headroomlabs-ai/headroom/issues/2223)) ([8537e2c](https://github.com/headroomlabs-ai/headroom/commit/8537e2cf605dd0e378dd83329640c3215699919f))
|
||||
* **wrap:** serialize shared proxy startup ([#2946](https://github.com/headroomlabs-ai/headroom/issues/2946)) ([e540d64](https://github.com/headroomlabs-ai/headroom/commit/e540d64febf27f2e7997d3a1a1d89478cc1ef658))
|
||||
* **wrap:** set xAI upstream for grok-build proxy ([#2772](https://github.com/headroomlabs-ai/headroom/issues/2772)) ([c831081](https://github.com/headroomlabs-ai/headroom/commit/c8310819a4221b0d120436786fc499a24c8e55f1))
|
||||
* **wrap:** skip Serena project setup outside real project roots ([#2574](https://github.com/headroomlabs-ai/headroom/issues/2574)) ([0994ea0](https://github.com/headroomlabs-ai/headroom/commit/0994ea04c869939946b91cbe52ceaf46740786be))
|
||||
* **wrap:** stop same-port persistent routing during claude unwrap ([#2340](https://github.com/headroomlabs-ai/headroom/issues/2340)) ([#2350](https://github.com/headroomlabs-ai/headroom/issues/2350)) ([cf5fa64](https://github.com/headroomlabs-ai/headroom/commit/cf5fa644b6e019a3ea31b4f48509a63921055253))
|
||||
* **wrap:** stop the launch cwd from shadowing the installed package in the proxy subprocess ([#2843](https://github.com/headroomlabs-ai/headroom/issues/2843)) ([c49be26](https://github.com/headroomlabs-ai/headroom/commit/c49be269a18446779cd8a048caaa7f0ba3a3b48b))
|
||||
* **wrap:** stop the Serena pre-index stalling the launch path for 300s ([#2945](https://github.com/headroomlabs-ai/headroom/issues/2945)) ([6147883](https://github.com/headroomlabs-ai/headroom/commit/6147883d5e3a92cc7b890e6c05dce4391090c7e4))
|
||||
* **wrap:** verify proxy deps before mutating Codex config ([#1628](https://github.com/headroomlabs-ai/headroom/issues/1628)) ([b7f342c](https://github.com/headroomlabs-ai/headroom/commit/b7f342c153a3e6e43a9d3df006bcd4dd69842d00))
|
||||
|
||||
|
||||
### Performance Improvements
|
||||
|
||||
* **content_router:** dedupe content detection ([#2419](https://github.com/headroomlabs-ai/headroom/issues/2419)) ([9b016f2](https://github.com/headroomlabs-ai/headroom/commit/9b016f2b64cb50cd50ab68711ab2abdf7d74c8ec))
|
||||
* cut hot-path latency 27% (token-count memo, startup preloads, JSON scan memo) ([#2838](https://github.com/headroomlabs-ai/headroom/issues/2838)) ([53af90d](https://github.com/headroomlabs-ai/headroom/commit/53af90d68c723f644a5a41dd273a606117109866))
|
||||
* **perf:** skip rotated logs outside the requested window ([#3081](https://github.com/headroomlabs-ai/headroom/issues/3081)) ([6c9f41e](https://github.com/headroomlabs-ai/headroom/commit/6c9f41e08c47f2bfc440c5a4c6ac8a357ad5ada0))
|
||||
* **proxy:** bound upstream calls and hot-path costs ([#2852](https://github.com/headroomlabs-ai/headroom/issues/2852)) ([f624d3a](https://github.com/headroomlabs-ai/headroom/commit/f624d3a00ac271db7947443ddeb0c8bc2e93d3eb))
|
||||
* **subscription:** skip transcripts older than the window in compute_window_tokens ([#2861](https://github.com/headroomlabs-ai/headroom/issues/2861)) ([91d6bf3](https://github.com/headroomlabs-ai/headroom/commit/91d6bf33cde777b541375fb182d4479fdd78f81b))
|
||||
* surface optimization overhead diagnostics ([#1212](https://github.com/headroomlabs-ai/headroom/issues/1212)) ([7ddcbcb](https://github.com/headroomlabs-ai/headroom/commit/7ddcbcb616729e09d8c556f2b8510f50aa0ae298))
|
||||
|
||||
|
||||
### Dependencies
|
||||
|
||||
* bump axum from 0.7.9 to 0.8.9 ([#2966](https://github.com/headroomlabs-ai/headroom/issues/2966)) ([5731be7](https://github.com/headroomlabs-ai/headroom/commit/5731be7e68f57292aed40d76e770657a88f78c13))
|
||||
* bump brace-expansion from 5.0.7 to 5.0.9 in /docs ([#2751](https://github.com/headroomlabs-ai/headroom/issues/2751)) ([56ee57b](https://github.com/headroomlabs-ai/headroom/commit/56ee57be98bf109f0a46de522724ef169a4bc51c))
|
||||
* bump bytesize from 1.3.3 to 2.4.2 ([#2286](https://github.com/headroomlabs-ai/headroom/issues/2286)) ([6448545](https://github.com/headroomlabs-ai/headroom/commit/6448545a7f5a1dee88bce6f0830bdbfd1c99c617))
|
||||
* bump criterion from 0.5.1 to 0.8.2 ([#2965](https://github.com/headroomlabs-ai/headroom/issues/2965)) ([b30f339](https://github.com/headroomlabs-ai/headroom/commit/b30f339d694abcd8dada76a34a1d69e30390bfc2))
|
||||
* bump hf-hub from 0.4.3 to 0.5.0 ([#2285](https://github.com/headroomlabs-ai/headroom/issues/2285)) ([4925bf6](https://github.com/headroomlabs-ai/headroom/commit/4925bf6a829735977bab5000b469c3edb19c75b1))
|
||||
* bump next from 16.2.10 to 16.3.0 in /docs ([#2750](https://github.com/headroomlabs-ai/headroom/issues/2750)) ([0fd0b99](https://github.com/headroomlabs-ai/headroom/commit/0fd0b996a4b58a166491b145f4d3885c21b27cc0))
|
||||
* bump postcss from 8.5.19 to 8.5.25 in /plugins/openclaw ([#2749](https://github.com/headroomlabs-ai/headroom/issues/2749)) ([cd60ee9](https://github.com/headroomlabs-ai/headroom/commit/cd60ee9ae886b32ba5da3203e35bb6b088031fd3))
|
||||
* bump postcss from 8.5.19 to 8.5.25 in /plugins/opencode ([#2748](https://github.com/headroomlabs-ai/headroom/issues/2748)) ([ff4e016](https://github.com/headroomlabs-ai/headroom/commit/ff4e0167bbccbd4ae51bf23ddec144e61c94cd68))
|
||||
* bump postcss from 8.5.19 to 8.5.25 in /sdk/typescript ([#2747](https://github.com/headroomlabs-ai/headroom/issues/2747)) ([267c2bd](https://github.com/headroomlabs-ai/headroom/commit/267c2bdcb56e132b2dd9c065dab3498dbf730ca3))
|
||||
* bump postcss from 8.5.19 to 8.5.26 in /docs ([#2881](https://github.com/headroomlabs-ai/headroom/issues/2881)) ([e6e5826](https://github.com/headroomlabs-ai/headroom/commit/e6e5826423a0a700a8c544ce2c8cbcdef694160e))
|
||||
* bump ruff from 0.15.17 to 0.15.22 in the pip-minor-patch group ([#2501](https://github.com/headroomlabs-ai/headroom/issues/2501)) ([ecf130d](https://github.com/headroomlabs-ai/headroom/commit/ecf130d3ac6fb864098cb93fafd2621ae3ac7e12))
|
||||
* bump ruff from 0.15.22 to 0.16.2 in the pip-minor-patch group across 1 directory ([#2962](https://github.com/headroomlabs-ai/headroom/issues/2962)) ([ff17961](https://github.com/headroomlabs-ai/headroom/commit/ff17961cd76a7cea1cff0a9dcfb7338929f37c5a))
|
||||
* bump rusqlite from 0.32.1 to 0.40.1 ([#2287](https://github.com/headroomlabs-ai/headroom/issues/2287)) ([522faa1](https://github.com/headroomlabs-ai/headroom/commit/522faa1a59aa94e4adfd4a4afe0202d1126e187d))
|
||||
* bump sha2 from 0.10.9 to 0.11.0 ([#2288](https://github.com/headroomlabs-ai/headroom/issues/2288)) ([322425c](https://github.com/headroomlabs-ai/headroom/commit/322425c43bffde1ed0b64fecf3cf5951565dd82b))
|
||||
* bump the cargo-minor-patch group across 1 directory with 22 updates ([#2916](https://github.com/headroomlabs-ai/headroom/issues/2916)) ([148d860](https://github.com/headroomlabs-ai/headroom/commit/148d8605e2087f3c8d6a3fa4b8d248ad2da5858f))
|
||||
* bump the cargo-minor-patch group across 1 directory with 4 updates ([#2964](https://github.com/headroomlabs-ai/headroom/issues/2964)) ([888a9f4](https://github.com/headroomlabs-ai/headroom/commit/888a9f4e147cf1f87244977fac81d5e9613352d7))
|
||||
* bump the cargo-minor-patch group with 10 updates ([#2284](https://github.com/headroomlabs-ai/headroom/issues/2284)) ([3266ed7](https://github.com/headroomlabs-ai/headroom/commit/3266ed7641cc92f5cae79b1befeb6bee7c96242e))
|
||||
* bump the npm-minor-patch group across 3 directories with 7 updates ([#2276](https://github.com/headroomlabs-ai/headroom/issues/2276)) ([961866b](https://github.com/headroomlabs-ai/headroom/commit/961866ba7c277b59ccdd51e784de9547a09198af))
|
||||
* bump tokio-tungstenite from 0.24.0 to 0.30.0 ([#2967](https://github.com/headroomlabs-ai/headroom/issues/2967)) ([bbe9013](https://github.com/headroomlabs-ai/headroom/commit/bbe901319d49a3d70caf7b37da2c29f7d7996e07))
|
||||
* update mcp requirement from <2.0.0,>=1.28.1 to >=1.28.1,<3.0.0 ([#2963](https://github.com/headroomlabs-ai/headroom/issues/2963)) ([d6fb536](https://github.com/headroomlabs-ai/headroom/commit/d6fb5365f67b9b7f90c7c55caead16ca6b41c586))
|
||||
|
||||
|
||||
### Code Refactoring
|
||||
|
||||
* **pricing:** make LiteLLM the source of truth, not the hardcoded table ([#2779](https://github.com/headroomlabs-ai/headroom/issues/2779)) ([0e1d6bf](https://github.com/headroomlabs-ai/headroom/commit/0e1d6bfa797d865834cc247989115a11949ce3f5))
|
||||
* **proxy:** extract tool definition serialization ([#1998](https://github.com/headroomlabs-ai/headroom/issues/1998)) ([ad6ab48](https://github.com/headroomlabs-ai/headroom/commit/ad6ab48cbb2a9cf12f1d7cefaf4699a9905a92bb))
|
||||
* remove the dead headroom/prediction module ([#2692](https://github.com/headroomlabs-ai/headroom/issues/2692)) ([b7a79ac](https://github.com/headroomlabs-ai/headroom/commit/b7a79ac31a99ec67dc5fbe7bd15e7b96f8c040ec))
|
||||
* **transforms:** dispatch simple built-in strategies via the compressor registry ([#2399](https://github.com/headroomlabs-ai/headroom/issues/2399)) ([fc9c63f](https://github.com/headroomlabs-ai/headroom/commit/fc9c63f18c1a8414b62ced8b2dd54ad1fe4d1c14))
|
||||
* **wrap:** retire tokensave; Serena is the code-memory MCP ([#2499](https://github.com/headroomlabs-ai/headroom/issues/2499)) ([5d23a0a](https://github.com/headroomlabs-ai/headroom/commit/5d23a0aec22dacdbd7bf221dafbb17bcf9f10c63))
|
||||
|
||||
---
|
||||
This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please).
|
||||
Loading…
Add table
Add a link
Reference in a new issue