Add NN provider as default, remove HF inference (7B/0.5B)

Default LLM probability to 10% for cloud providers, ignore stale DB value

Fix Gemini conversations: bump LLM budget to 2 and remove double probability gate

Reset Gemini circuit breaker after failed startup probe

Add logging config so server output is visible in HF container logs

Set soci-agent-7b as default LLM for Ollama and HF providers

Set soci-agent-q4 as default LLM for all providers

Fix NameError: import PROVIDER_OLLAMA and PROVIDER_CLAUDE in server.py

Set default LLM call probability to 10% for all providers

Auto-fallback provider on startup if configured provider is quota-exhausted

Persist LLM probability across restarts; fix Gemini model fallback

Add LLM probability slider: controls AI usage per call site

Clean up token env vars; add Gemini to free provider menu

Remove paid providers from menu; circuit-break on 402 (no credits)

Fix HF LLM: use free SmolLM3 as default, strip thinking tokens

Fix HF Inference: migrate to router.huggingface.co/v1, use Qwen as default

Fix HF/Gemini LLM errors: token env var + rate limiting

Show all HF models individually in SWITCH LLM popup

Add Hugging Face Serverless Inference as free LLM provider

Split GITHUB_REPO into GITHUB_OWNER + GITHUB_REPO_NAME (no slash)

Click model pill to switch LLM provider at runtime

Add render.yaml, fix gemini provider routing, show LLM model in header

Fix infinite redeploy loop: push state to separate branch

Make startup crash-proof against corrupt/empty state

Fix startup crash on empty/missing GitHub state file

Add GitHub state persistence and reduce default agent count to 50

Fix real-time sync, speed, and persistence for deployed Render

Add bed/back views, road routing, evening fix, LLM cap

Add Groq rate limiter, global LLM budget, and provider chooser

Add Groq LLM provider and fix speed controls for real fast-forward

Add simulation speed controls: pause/resume and speed adjustment

Add gender, romance system, web UI, and API event log

Add Ollama support for free local LLM inference

Initial implementation of Soci city population simulator