Spaces:
Sleeping
Sleeping
Commit History
-
Fix backend inference logging and improvements
adityaverma9773890926 -
Improve agent chat tone and HF fallback behavior
adityaverma977258a316 -
Fix Space runtime HF router integration
adityaverma977cb64216 -
Replace unavailable models with HF Inference API-verified models (Mistral, Llama 2, Zephyr, etc.)
adityaverma9777b69e72 -
Add contextual chat message generation when HF models don't return messages
adityaverma977221d021 -
Add comprehensive logging for HF API token and inference failures
adityaverma977967c2f6 -
Remove Groq models; switch registry and clients to HF-only curated list
adityaverma977593e9c0 -
Add HF fallback for Groq rate-limit errors; remove rate-limited Groq models
adityaverma97797270d8 -
Remove rate-limited Groq models (llama-3.1 variants, gemma) and use Mixtral as default
adityaverma9775c81985 -
Fix place-fire random range failures
adityaverma97794158b3 -
Switch to dynamic model-generated chat with context
adityaverma9771bb7020 -
Update simulation chat personality and celebration messages
adityaverma977da20490 -
Deploy backend from Rush-Agents-Rush
adityaverma9779f7b0e1