Commit History

  1. Fix TypeScript type error in page.tsx - add type assertion after filter

    adityaverma977
    71640b5
  2. Fix backend inference logging and improvements

    adityaverma977
    3890926
  3. Update README files for HF router workflow

    adityaverma977
    b2c8834
  4. Improve agent chat tone and HF fallback behavior

    adityaverma977
    258a316
  5. Fix Space runtime HF router integration

    adityaverma977
    cb64216
  6. Update HF router models and inference flow

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

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

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

    adityaverma977
    967c2f6
  10. Add scroll to models panel (max-height 400px, overflow-y-auto)

    adityaverma977
    11ba25d
  11. Remove Groq models; switch registry and clients to HF-only curated list

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

    adityaverma977
    d4d710c
  13. Add HF fallback for Groq rate-limit errors; remove rate-limited Groq models

    adityaverma977
    97270d8
  14. Remove rate-limited Groq models (llama-3.1 variants, gemma) and use Mixtral as default

    adityaverma977
    5c81985
  15. Add fire status ETA event, probabilistic lethality by intensity, display ETA in UI

    adityaverma977
    30e238f
  16. Frontend: accept legacy available-models response (groq_models / hf_spaces_models) and merge into unified list

    adityaverma977
    25f6a95
  17. Add 15+ free HF models, expand model selection, add debug logging

    adityaverma977
    8bcd5b0
  18. Trigger HF Space pod rebuild

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

    adityaverma977
    8e038ca
  20. Add complete YAML front matter with sdk_version and python_version to READMEs

    adityaverma977
    117a348
  21. Merge hf/main: keep master version of .gitignore and README.md

    adityaverma977
    aef7859
  22. Tune fire extinguishing: inverse scaling so 2 agents = fast game (90s), more agents = slower game (110s+)

    adityaverma977
    d1adb89
  23. Fix report build using tickHistory updater to avoid stale closure; compute final report from authoritative history

    adityaverma977
    ac45880
  24. Compute report from tick events and store full tick messages

    adityaverma977
    98e2ee8
  25. Collect tick history, render tracks and show per-model report

    adityaverma977
    bc3902d
  26. Fix place-fire random range failures

    adityaverma977
    94158b3
  27. Fix place-fire range errors and improve error detail

    adityaverma977
    263efa8
  28. Switch to dynamic model-generated chat with context

    adityaverma977
    1bb7020
  29. Use model-authored dynamic chat with recent radio context

    adityaverma977
    e0206f3
  30. Update simulation chat personality and celebration messages

    adityaverma977
    da20490
  31. Make simulation chat lively and celebrate fire reduction

    adityaverma977
    a832193
  32. Fix websocket backend URL for HF Space deployments

    adityaverma977
    56215c3
  33. Load models via backend env API instead of localhost

    adityaverma977
    0e54f19
  34. Fix frontend backend URL handling and track frontend lib folder

    adityaverma977
    0d6660e
  35. Prepare backend for HF Space and set Node 22 for Vercel

    adityaverma977
    a64703a
  36. Fix HF Space metadata colors

    adityaverma977
    86358db
  37. Deploy backend from Rush-Agents-Rush

    adityaverma977
    9f7b0e1
  38. initial commit

    Verified signature
    f5cc0ba
  39. inital build

    adityaverma977
    43d708a