Commit Graph
2 Commits
Author SHA1 Message Date
bruno 43f5b4a078 chore(lint): fixe les 3 dernières erreurs ruff pré-existantes
CI / lint (push) Failing after 19s
CI / test (push) Skipped
CI / build (push) Skipped
CI / e2e (push) Skipped
CI / security (push) Successful in 27s
Desktop Build / build-windows (push) Canceled after 0s
Desktop Build / build-linux (push) Canceled after 0s
- bookslm.py: PERF402 — list(_cache) au lieu de la boucle d'append
- bookslm_routes.py: SIM102 — combine les conditions imbriquées (via --unsafe-fixes)
- export.py: DTZ005 — datetime.now(tz=timezone.utc) au lieu de naive now()
- watcher.py: SIM102 — combine les conditions imbriquées

Résultat : ruff check backend/ → All checks passed!
Vérifié : pytest full suite reste 492 passed, 5 skipped, 0 failed.
2026-09-07 09:06:11 -04:00
bruno 524e6da591 feat(bookslm): v2.2.0 - BooksLM chat AI contextuel par répertoire + 4 providers AI
CI / lint (push) Failing after 16s
CI / test (push) Skipped
CI / build (push) Skipped
CI / e2e (push) Skipped
CI / security (push) Successful in 21s
Desktop Build / build-windows (push) Canceled after 0s
Desktop Build / build-linux (push) Canceled after 0s
BooksLM (#76):
- Panneau chat slide-in 450px, clic-droit répertoire → 🧠 BooksLM
- Collecte récursive .md avec limites (200 fichiers, 200K chars)
- Cache SHA-256, redaction secrets, priorité README/index
- SSE streaming, badges sources cliquables, historique localStorage
- Commandes palette: BooksLM ouvrir/nouvelle conversation

Providers AI (4 nouveaux):
- NVIDIA (integrate.api.nvidia.com)
- QwenCloud (dashscope.aliyuncs.com)
- Xiaomi (api.xiaomi.com)
- Mistral (api.mistral.ai)
- Tous OpenAI-compatible, auto-listing modèles

Fix: dropdown config-select suit maintenant le thème (option bg/color)
27 tests BooksLM + 466 tests au total
2026-09-06 19:42:40 -04:00