Till JS fa16f1fe38 feat(apps): add GPU server fallback to all LLM-using apps ... Configure all apps with gpu-llm.mana.how as fallback when MANA_LLM_URL is not set. This ensures apps can use the GPU server's local LLM models (Ollama gemma3, qwen2.5-coder) instead of cloud providers. Apps updated: - Chat: LLM fallback to GPU server - Context: LLM fallback (replaces Azure OpenAI dependency) - NutriPhi: LLM + Vision fallback (replaces Google Gemini for food analysis) - Planta: LLM + Vision fallback (replaces Google Gemini for plant analysis) - ManaDeck: LLM + Vision fallback for card generation - Traces: LLM fallback for AI city guides Vision model default: ollama/gemma3:12b (multimodal, runs on RTX 3090) Added VISION_MODEL to .env.development Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>		2026-03-27 22:21:20 +01:00
..
src	feat(apps): add GPU server fallback to all LLM-using apps	2026-03-27 22:21:20 +01:00
docker-entrypoint.sh	fix(nutriphi): add shared-drizzle-config and make db:push non-fatal	2026-02-02 16:17:22 +01:00
Dockerfile	feat(infra): extend Dockerfile validator to backends and services	2026-03-25 08:57:10 +01:00
drizzle.config.ts	🔧 chore: create @manacore/shared-drizzle-config and migrate 16 configs	2026-01-29 16:54:44 +01:00
jest.config.js	✨ feat(nutriphi): prepare for production release with tests and improved UX	2026-01-28 15:23:35 +01:00
nest-cli.json	✨ feat(nutriphi): add AI-powered nutrition tracking app	2026-01-25 13:19:51 +01:00
package.json	fix(monitoring): add missing prom-client dependency to 4 backends	2026-03-25 10:22:25 +01:00
tsconfig.json	🐛 fix: resolve tsconfig issues across all NestJS backends	2026-02-01 03:47:17 +01:00