Fix model, improve error handling, add startup diagnostics for all modes

Major fix: Improved web search with Tavily AI answers, better content extraction, enhanced system prompt

Fix LLM model to openai/gpt-oss-20b

Deploy to Hugging Face Spaces - Remove Render, enable full features

Fix: Correct Groq model openai/gpt-oss-20b

Fix: Groq model, error handling for all modes, LITE_MODE fallbacks

Fix: Use openai/gpt-oss-20b model

Fix: Add LITE_MODE for Render free tier (512MB RAM)

Add Product MVP and Video Brain modes + Render deployment

Fix: LangChain 0.2.x compatibility - update imports and model config

Perplexity AI Clone - Full Production Version with 8 Modes