Benjamin Admin 2f68646c2d fix(advisor): keep_alive 30m gegen Modell-Kaltstart ("Load failed") ...

Ollama entlädt das 35b-Modell nach 5 Min Leerlauf → jede Frage danach
startet es kalt (Modell-Load) und läuft in den Frontend-Timeout ("Load
failed"). keep_alive='30m' im Chat-Request hält es warm.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-06-12 13:20:13 +02:00

..

agents

…

compliance-advisor

fix(advisor): keep_alive 30m gegen Modell-Kaltstart ("Load failed")

2026-06-12 13:20:13 +02:00

drafting-engine

fix(admin): resolve all 266 TypeScript errors, enable strict build

2026-06-11 00:42:44 +02:00

v1

refactor+feat: Snapshot-Router-Split + generischer ChecklistAgent + AGB-Modul

2026-06-11 14:23:29 +02:00