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

+2 -2
View File
@@ -14,8 +14,8 @@ KANSHO_PROVIDER_KEY=
# KANSHO_PROVIDER_ZDR=1
# KANSHO_PROVIDER_NO_TRAIN=1
# Detect: Klartext lokal, in Development/Test, oder in Production mit KANSHO_ALLOW_REMOTE_DETECT.
# Leer = Generate-Key mitnutzen (nur wenn remote Detect erlaubt ist).
# Detect: lokal (Ollama LAN) oder in Development/Test remote. Production remote nur mit KANSHO_ALLOW_REMOTE_DETECT.
# URL/Modell liegen in LLM-Profilen (Admin → Schnittstellen), nicht in der .env.
KANSHO_DETECT_PROVIDER_KEY=
# KANSHO_DETECT_PROVIDER_URL=https://openrouter.ai/api/v1/chat/completions
# KANSHO_DETECT_PROVIDER_MODEL=openai/gpt-4.1-nano