headroomlabs-ai/headroom v0.43.1 on GitHub

0.43.1 (2026-11-05)

ccr: keep the in-memory order queue from evicting re-stored entries (#4545) (c6f5bf9)
memory: read the relation key the memory_save schema advertises (#4647) (7592e68)
memory: replace the HNSW vector when a memory is re-indexed (#4649) (ee638f9)
openclaw: accept 12-character hashes in headroom_retrieve (#4640) (8d3e9e5)
ort: avoid implicit runtime discovery from the workspace (#4570) (69fbd23)
proxy: bound the model-keyed tokenizer, beacon and litellm caches (#4497) (e51b806)
proxy: use HTTP/1.1 client for ChatGPT streaming and model metadata (#4006) (e1becdf)
release: normalize damaged release PR envelopes before detection (#4664) (917edc6)
router: keep tagged blocks out of the lossy size-gate fallback (#4543) (f333edf)
router: log the ONNX fallbacks at info instead of warning (#4535) (db30d82)

bump the npm-minor-patch group across 3 directories with 6 updates (#4662) (8f104f8)

Want more savings? Headroom Enterprise saves more for teams and enterprises. Talk to us at hello@headroomlabs.ai or headroomlabs.ai.