Switch Llama 3.1 8B to ungated unsloth mirror

Add local model inference backend for Layer 2

Add 502/504 and hyphenated Time-out to retry list

Add retry with exponential backoff for HF Inference API calls

Clean up dead code, unused imports, and move hardcoded values to config.yaml

Remove all rule-based fallback systems, require LLM inference

Wire up real LLM integration via HF Inference API

Fix critical gaps: prompt-sensitive agent, adversarial customers, executable GRPO, OpenEnv wrapper

Implement self-improving AI oversight system with nested RL environments