2 Commits

Author	SHA1	Message	Date
home	7a40ff629e	feat: LLM routing by tier (free→Ollama, pro→Timeweb) ... - Add tier-based provider routing in llm-svc - free tier → Ollama (local qwen3.5:9b) - pro/business → Timeweb Cloud AI - Add /api/v1/embed endpoint for embeddings via Ollama - Update Ollama client: qwen3.5:9b default, remove auth - Add GenerateEmbedding() function for qwen3-embedding:0.6b - Add Ollama K8s deployment with GPU support (RTX 4060 Ti) - Add monitoring stack (Prometheus, Grafana, Alertmanager) - Add Grafana dashboards for LLM and security metrics - Update deploy.sh with monitoring and Ollama deployment Made-with: Cursor	2026-03-03 02:25:22 +03:00
home	e6b9cfc60a	feat: spaces redesign, model selector, auth fixes ... Spaces: - Perplexity-like UI with collaboration features - Space detail page with threads/members tabs - Invite members via email, role management - New space creation with icon/color picker Model selector: - Added Ollama client for free Auto model - GooSeek 1.0 via Timeweb (tariff-based) - Frontend model dropdown in ChatInput Auth & Infrastructure: - Fixed auth-svc missing from Dockerfile.all - Removed duplicate ratelimit_tiered.go (conflict) - Added Redis to api-gateway for rate limiting - Fixed Next.js proxy for local development UI improvements: - Redesigned login button in sidebar (gradient) - Settings page with tabs (account/billing/prefs) - Auth pages visual refresh Made-with: Cursor	2026-02-28 02:30:05 +03:00