v0.5.13

janhq/janv0.5.13Jan 6, 2025by github-actions[bot]

AI Summary

Stability improvements addressing configuration resets, analytics opt-in preferences, and compatibility issues with MacOS Intel hardware.

Key Highlights

Fixed max tokens auto-reverting to 8192
Defaulted analytics to opt-in with UI controls
Restored Vulkan support option
Fixed model loading issues on MacOS Intel

Full Release Notes

## 🐛 Fixes

- fix: max\_tokens revert back to 8192 automatically when creating a new thread @louis-jan (#4397)
- fix: revert back product analytic with default opt-out @urmauur (#4394)
- fix: send event opt out @urmauur (#4390)
- fix: enable default opt in analytic @urmauur (#4387)
- fix: should not disable Vulkan support option @louis-jan (#4382)
- fix: bump llama.cpp engine hotfix version to address model load issue on some MacOS Intel machines @louis-jan (#4374)

## 🧰 Maintenance

- chore: bump latest cortex release 1.0.8 @louis-jan (#4405)
- chore: add cpu\_threads settings in cortex extension @louis-jan (#4386)

## Contributor

@louis-jan and @urmauur