DJL v0.5.8
Added
- Added a replayable first-run tutorial for Work, Projects, local AI, and Settings.
- Added one-click local AI setup by purpose—General, Documents, Reasoning, or Coding—with hardware-aware recommendations, readiness checks, and automatic fallback to a safer model in the same category.
- Added Get Started, Guide, and Changelog pages to the DJL website with release-aware desktop downloads.
Fixed
- Fixed local AI hardware detection on Windows and translated Apple Silicon builds so model recommendations use the host CPU, GPU memory, system memory, and disk capacity more reliably.
- Fixed local AI setup continuity when a recommended model cannot load, including reuse of the active setup while DJL downloads the fallback model.
- Fixed AI detector cache invalidation so updated calibration and model-output settings cannot reuse stale analysis results.
- Fixed the desktop updater’s recovery path when version context is missing or a previous update action failed.
Changed
- Kept the desktop update control available as a consistent place to check, download, and install new DJL versions.
- Expanded AI detector evaluation coverage, metrics, and model-license evidence across English and Chinese benchmark sources.
DJL desktop installers for macOS Apple Silicon, macOS Intel, and Windows x64. macOS
installers are Developer ID signed, notarized, and stapled. The Windows installer is
intentionally unsigned and may trigger Microsoft SmartScreen. Verify SHA256SUMS before
installing.
What's Changed
- feat(landing): guide, GitHub-driven changelog, and a single design system by @Anthonysu798 in #7
- feat: improve zero-config AI onboarding and evaluation by @Anthonysu798 in #6
- test: stabilize downgraded local model setup by @Anthonysu798 in #8
Full Changelog: v0.5.7...v0.5.8
Contributors
Anthonysu798