Files
dbx/apps
t8y2 2afcfff4e3 fix(ai): extend timeout and token budget for thinking models
Thinking models like DeepSeek V4 Flash can exceed the 120s stream
timeout during long reasoning, causing truncated output and missing
answers. Increase stream timeout to 600s when thinking is enabled,
raise max_tokens floor to 8192, and bump reasoning display max-height.

Closes #326
2026-05-19 18:08:08 +08:00
..
2026-05-18 02:50:50 +08:00

Apps

Runnable DBX applications live here.

Directories

  • desktop/ - the Vue frontend used by the Tauri desktop app and the Docker/web build.

The Tauri native shell remains in src-tauri/ because that is the conventional Tauri project location used by the existing build and release tooling.