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

Fix backend inference logging and improvements

Update README files for HF router workflow

Improve agent chat tone and HF fallback behavior

Fix Space runtime HF router integration

Update HF router models and inference flow

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

Add contextual chat message generation when HF models don't return messages

Add comprehensive logging for HF API token and inference failures

Add scroll to models panel (max-height 400px, overflow-y-auto)

Remove Groq models; switch registry and clients to HF-only curated list

Add Groq->HF fallback mapping and accept HUGGINGFACE_API_TOKEN

Add HF fallback for Groq rate-limit errors; remove rate-limited Groq models

Remove rate-limited Groq models (llama-3.1 variants, gemma) and use Mixtral as default

Add fire status ETA event, probabilistic lethality by intensity, display ETA in UI

Frontend: accept legacy available-models response (groq_models / hf_spaces_models) and merge into unified list

Add 15+ free HF models, expand model selection, add debug logging

Trigger HF Space pod rebuild

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

Add complete YAML front matter with sdk_version and python_version to READMEs

Merge hf/main: keep master version of .gitignore and README.md

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

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

Compute report from tick events and store full tick messages

Collect tick history, render tracks and show per-model report

Fix place-fire random range failures

Fix place-fire range errors and improve error detail

Switch to dynamic model-generated chat with context

Use model-authored dynamic chat with recent radio context

Update simulation chat personality and celebration messages

Make simulation chat lively and celebrate fire reduction

Fix websocket backend URL for HF Space deployments

Load models via backend env API instead of localhost

Fix frontend backend URL handling and track frontend lib folder

Prepare backend for HF Space and set Node 22 for Vercel

Fix HF Space metadata colors

Deploy backend from Rush-Agents-Rush

initial commit

inital build