Add selectable LLM profiles and treat LAN Ollama as local.
Deploy Development / deploy (push) Successful in 53s
Test Suite / pytest-backend (push) Failing after 2m40s
Test Suite / smoke-dev (push) Successful in 0s
Test Suite / frontend-build (push) Successful in 16s

Saved presets keep URL and model per stage so detect can switch to Ollama without re-entering settings or sending plaintext to OpenRouter.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
LarsandCursor committed 2026-09-08 12:48:25 +02:00
1 parent af6fe55577
commit bef422a429
20 files changed
+903 -114

No files matched your search

@@ -124,6 +124,7 @@ Ziel wie Mitai: **Einfachheit in der Nutzer-UX, Differenzierung in administrierb
- UI-Katalog: welche Karten/Nav-Beiträge sichtbar, Layout-Overrides
- System-Prompts vs. Instanz-Anpassungen (Reset auf Default)
- Provider-URL, Modell und ZDR/No-Train für Generate und Detect (`provider_settings`, Admin Schnittstellen)
- **Additiv 2026-09-08:** benannte LLM-Profile (`llm_profiles`); aktive Zuordnung je Stufe. Secrets bleiben Env.
- später: Privacy-Profile (Strict/Balanced), sobald fachlich konkret
### 4.2 Code / Env (nicht pro Klick im Admin)