Switch model to openai/gpt-oss-120b on Groq

Configure Human-Grade Writing constraints and force enhanced mode

Improved few-shot examples and natural burstiness in Enhanced mode

Fix hyphenated compound words in Enhanced prompt

Apply Walters research anti-AI prompts with perplexity and burstiness rules

Remove hyphens and dashes from all output prompts

Add automatic double pass for Enhanced mode

Integrate few-shot writing examples for enhanced prompt

Upgrade humanizer model to Llama 3.3 70B

Add readability and purpose controls to humanizer

Switch to Groq API

Deploy humanizer backend