fix: auto-correct model class for decoder models + show Colab logs in dashboard

fix: strip markdown fences client-side + fix AI prompt for CausalLM models

fix: auto-push script to Colab when Start Training is clicked

feat: async job + polling architecture — fixes proxy timeout wall

fix: client-side template fallback + shorter timeouts — generation NEVER fails

fix: template fallback + 6 providers — script generation always works

fix: sync-first architecture — eliminates network errors

fix: restore max_tokens to 4096 + add retry back

fix: eliminate retry-append duplication + partial-success detection

fix: stream recovery when connection drops mid-generation

fix: auto-retry + sync fallback for network errors in Architect

fix: multi-provider fallback, SSE heartbeat, timeout — kills network error

Rebrand to TRAIN YOUR AI: add Guide page, lock credentials, remove Settings from nav

Fix: remove Anthropic from onboarding, require 3/3 credentials

🧠 Deploy NEXUS AI v1.0 — HF Inference powered