Aug 3

1. 15:06

   Speed: 2 models (drop slow DeepSeek), max_tokens=400, timeout=30s

   tomyimkc
   1db7af5
2. 15:00

   Redesign: multi-model parallel UI — one prompt, 3 LLMs, side-by-side comparison

   tomyimkc
   83a00a9
3. 14:36

   Fix: auto-fallback models (Qwen→Llama-3.3-70B→DeepSeek-V3)

   tomyimkc
   46e62f2
4. 13:19

   Initial deploy: polished demo with Qwen2.5-7B API + step verification + 7 challenges

   tomyimkc
   b6e520e