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

Remove Render deploy hook step (native GitHub integration active)

Add GitHub Action to auto-sync master → HuggingFace Space on push

Persist LLM probability across restarts; fix Gemini model fallback

Update README: message flow charts, full deployment guide

Add LLM probability slider: controls AI usage per call site

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'

Show all HF models individually in SWITCH LLM popup

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

Show HF provider in switcher regardless of HF_TOKEN presence

Add Hugging Face Serverless Inference as free LLM provider

Dockerfile: use PYTHONPATH instead of pip install -e . (fixes setuptools.backends error)

Add HF Space metadata to README

render.yaml: GITHUB_OWNER and GITHUB_REPO_NAME as plain values

Split GITHUB_REPO into GITHUB_OWNER + GITHUB_REPO_NAME (no slash)

Add Dockerfile for Hugging Face Spaces deployment (port 7860)

Click model pill to switch LLM provider at runtime

Fix back view: show whenever movingUp, not just during walk anim

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

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

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

Fix apartment assignment, player sleep, gender profile, and NPC conversations

Fix WebSocket: use wss:// on HTTPS, ws:// on HTTP

Update README for v0.7.0

Add player login, agent creation, and NPC chat

chore: update simulation state [skip ci]