v0.52.16
tinyhumansai/openhumanv0.52.16Apr 16, 2026by github-actions[bot]
AI Summary
Locks down local AI model selection to specific tiers and improves overlay visibility and voice server reliability.
Key Highlights
- Local AI model selection locked to 2-4 GB tier
- Fullscreen visibility improvements
- Voice server reliability fixes
New Features
- Overlay fullscreen visibility
- Thread agent_id integration
- Chat processing persistence across tab switches
Full Release Notes
## What's Changed * feat(local_ai): MVP model lockdown — lock selection to 2-4 GB tier (#573) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/588 * fix(overlay): fullscreen visibility, voice server reliability, and resize (#528) by @oxoxDev in https://github.com/tinyhumansai/openhuman/pull/585 * fix(agent): thread agent_id into build_session_agent_inner by @sanil-23 in https://github.com/tinyhumansai/openhuman/pull/584 * test(coverage): batch 1–4 — Rust unit tests toward 80% for critical modules (#530) by @CodeGhost21 in https://github.com/tinyhumansai/openhuman/pull/581 * fix: keep chat processing alive across tab switches by @M3gA-Mind in https://github.com/tinyhumansai/openhuman/pull/587 **Full Changelog**: https://github.com/tinyhumansai/openhuman/compare/v0.52.15...v0.52.16