Lataa OpenHuman 0.57.40

The Parallel Power Upgrade
This release brings a faster, more transparent desktop experience—more concurrency in chat, smoother reliability in memory flows, and easier access to diagnostics. 🚀
Highlights
Faster chat, more parallelism ⚡
Agent inference now runs concurrently instead of one-at-a-time—both across threads (no more single global active-thread lock) and within a thread via parallel “forked” turns. Cancellation is also hardened to be more cooperative and resilient under load. (#3633) — Thank you @senamakel!
Memory source reliability improvements 🧠
Memory sources now re-fetch when a session becomes authenticated, improving consistency and reducing flakiness in memory-source UI flows after reloads. This also adds test coverage to lock in the behavior. (#3621) — Thank you @sanil-23!
Smoother CI + test stability 🧪
CI and tests got a cleanup pass to eliminate multiple flaky/failing categories: removing stale UI assertions, fixing async race conditions in autosave/memory, and adjusting Playwright timeouts to reduce infrastructure flakes. Also includes a small UX regression fix where a join success toast could fail to fire due to an unmounting effect. (#3618, #3623) — Thank you @senamakel-droid and @sanil-23!
Always-on Developer & Diagnostics access 🛠️
Developer & Diagnostics settings are now always visible—no more “Developer Mode” gate. This surfaces the Settings section, related settings search entries, and the Intelligence “council” tab by default, with tests updated accordingly. (#3639) — Thank you @senamakel!
Contributor Credits
Thanks to everyone who contributed to this release: @github-actions[bot], @sanil-23, @senamakel, and @senamakel-droid.
Full Compare
https://github.com/tinyhumansai/openhuman/compare/v0.57.39...v0.57.40