Add life events, goals, pregnancy system; fix profile editor bugs

Fix Gemini circuit breaker: distinguish per-minute rate limit from daily quota

Fix Groq circuit breaker: don't treat per-minute 429 as daily quota exhaustion

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

Fix HF provider switch: don't raise at init if HF_TOKEN missing

Set soci-agent-7b as default across all providers and UI

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

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

Add Soci fine-tuned model and training data pipeline

Fix Gemini default: use gemini-2.0-flash-lite (confirmed free-tier working)

Add _last_error tracking to GeminiClient and GroqClient for diagnosis

Fix HF provider: require token, hide from menu if absent, fix stuck provider

Fix Gemini model: default to gemini-1.5-flash, robust fallback detection

Fix Gemini fallback: add 'serverless' to model-not-found keyword list

Persist LLM probability across restarts; fix Gemini model fallback

Fix Gemini circuit-breaker: expire at midnight Pacific, not fixed 8h

Fix Gemini RPM (4 not 14) and add daily quota warnings at 50/70/90/99%

Fix Gemini quota circuit-breaker: detect 'quota' in 429 body

Fix Gemini 429 log truncation: escape braces in response body

Log Gemini 429 body in complete_json too

Log Gemini 429 response body for diagnostics

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 router URL: model ID must be in the path

Fix HF endpoint: migrate to router.huggingface.co

Silence JSON parse warnings for empty LLM responses

Fix HF serverless URL: use per-model endpoint path

Read hf_soci_token env var for HF Inference API key

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

Fix HF 503 cold-start: circuit-break immediately instead of blocking

Show actual HTTP error in LLM test toast instead of 'empty response'

Switch HF default model to zephyr-7b-beta (ungated, no license needed)

Add LLM call counter, test button, and better HF error handling

Distinguish 'no token' from 'rate limited' in LLM status indicator

Fix HF provider switch: don't raise on missing HF_TOKEN

Add Hugging Face Serverless Inference as free LLM provider

Show live LLM status in header (active/limited/skipped/idle)

Add Gemini LLM support, fix back-view direction, scripted conversation fallbacks

Fix Groq daily quota: circuit breaker skips LLM instead of freezing

Auto-resume on startup; fix Groq sleep bug and env var model selection

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

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

Redesign city: individual houses, real streets, async Ollama client

Switch to llama3.1:8b with Ollama native JSON mode

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