Commit History

  1. Fix backend inference logging and improvements

    adityaverma977
    3890926
  2. Improve agent chat tone and HF fallback behavior

    adityaverma977
    258a316
  3. Update HF router models and inference flow

    adityaverma977
    2a49cf3
  4. Replace unavailable models with HF Inference API-verified models (Mistral, Llama 2, Zephyr, etc.)

    adityaverma977
    7b69e72
  5. Add contextual chat message generation when HF models don't return messages

    adityaverma977
    221d021
  6. Add comprehensive logging for HF API token and inference failures

    adityaverma977
    967c2f6
  7. Remove Groq models; switch registry and clients to HF-only curated list

    adityaverma977
    593e9c0
  8. Add Groq->HF fallback mapping and accept HUGGINGFACE_API_TOKEN

    adityaverma977
    d4d710c
  9. Add fire status ETA event, probabilistic lethality by intensity, display ETA in UI

    adityaverma977
    30e238f
  10. Add 15+ free HF models, expand model selection, add debug logging

    adityaverma977
    8bcd5b0
  11. Trigger HF Space pod rebuild

    adityaverma977
    c0a08aa
  12. Keep both Groq + HF models, remove rate-limited Groq models, unify model selection UI without backend labels

    adityaverma977
    8e038ca
  13. Tune fire extinguishing: inverse scaling so 2 agents = fast game (90s), more agents = slower game (110s+)

    adityaverma977
    d1adb89
  14. Fix place-fire range errors and improve error detail

    adityaverma977
    263efa8
  15. Use model-authored dynamic chat with recent radio context

    adityaverma977
    e0206f3
  16. Make simulation chat lively and celebrate fire reduction

    adityaverma977
    a832193
  17. Prepare backend for HF Space and set Node 22 for Vercel

    adityaverma977
    a64703a
  18. inital build

    adityaverma977
    43d708a