Jon Saad-Falcon f5c0d412fc fix: pull all fitting Qwen3.5 models before app opens, fix download button ...

- Boot sequence: Phase 2 now pulls ALL Qwen3.5 models that fit in RAM
  before the server starts. SetupScreen blocks until every model is
  downloaded, showing per-model progress. No more background Phase 4.

- Default model: third-largest fitting model (qwen3.5:9b on 64GB).

- Download button: added pull_ollama_model and delete_ollama_model Tauri
  commands. Frontend uses Tauri invoke in desktop mode, fixing the
  "Load failed!" CORS/timeout issue with fetch().

2026-03-13 22:24:21 -07:00

..

public

init commit

2026-03-12 17:29:39 +00:00

src

fix: pull all fitting Qwen3.5 models before app opens, fix download button

2026-03-13 22:24:21 -07:00

src-tauri

init commit

2026-03-12 17:29:39 +00:00

index.html

init commit

2026-03-12 17:29:39 +00:00

package-lock.json

Revert "feat: auto-pull all Qwen3.5 models that fit on user's hardware"

2026-03-13 21:15:38 -07:00

package.json

fix: clean stale desktop release artifacts and fix frontend port mismatch (#52)

2026-03-13 19:11:39 -07:00

tsconfig.json

init commit

2026-03-12 17:29:39 +00:00

tsconfig.tsbuildinfo

init commit

2026-03-12 17:29:39 +00:00

vite.config.ts

fix: frontend now uses settings API URL for all backend requests (#49)

2026-03-13 13:51:56 -07:00