Fix: Resolved NameError for reward_img in app.py causing startup crash

Fix: Reverted to absolute HF resolve URLs and removed path replacement in app for better image reliability

Docs & UI Sync: Synchronized all photos and links across App UI, README, and Blog

Fix: Synced Llama model ID with README for consistent judge discovery

Final Polish: Realistic UI equity caps, storytelling UI insights, clean model naming, and Top/Bottom README narrative impacts

UI: Refactored run_simulation to use yield for real-time UI updates during model load and simulation

UI: Added missing reward_vs_episode and step-wise plots to the Gradio dashboard

Fix: Replaced all relative image paths with absolute Hugging Face URLs to guarantee visibility in Markdown and Gradio

Fix: Resolved name 'torch' is not defined and fixed Gradio image paths

Fix: Final attempt at image visibility - renamed directory to evidence and updated all links

Fix: Enhanced model loading with trust_remote_code and added UI error reporting

Final submission: Dual-model support (Llama-1B & Qwen-7B), consolidated asset_final, and README updates

🚀 FINAL SYNC: Integrated final plot assets from asset_final into main UI and README

🚀 FINAL POLISH: Fixed image visibility in UI and added captioned plots to README

🚀 FINAL INTEGRATION: Connected trained Llama-1B-GRPO model and added Analysis UI

🔧 FIX: Assets visibility in Gradio UI and YAML cleanup in README tab

🔧 FINAL FIX: Eliminated all remaining 'service_level' references in environment and reward logic

🏙️ FINAL: Critical bug fixes, reward tuning, and judge-ready README

🔧 FIX: Resolved Gradio 'missing input' error and improved UI layout

🚀 FEAT: Integrated Live HF LLM (Llama-3) & Training Data Logging

🔧 FIX: Fixed simulation progression loop, added phase-aware policies, and restored action history tracking

🚀 STRUCTURAL REBUILD: Fully aligned FairRecovery++ with OpenEnv reference patterns and stateful grading

🖼️ ASSETS: Replaced hero image with the new high-res screenshot

✨ UI IMPROVEMENT: Added dashboard preview image to the Interactive Simulation tab

✨ UI FEATURE: Added integrated Project README tab to the Gradio interface

🐛 BUGFIX: Resolved NameError (r_adapt) in _build_observation

🐛 BUGFIX: Resolved TypeError in compute_execute_step (removed obsolete adaptation_score)

🐛 BUGFIX: Resolved SyntaxError in server/app.py (unterminated triple quote)

💎 HONEST TRUTH: Synchronized Space simulation with train.ipynb metrics (0.4/0.4/0.2 & MAD Fairness)

Fix reward polarity and UI visibility: positive fairness index and all-zone status updates

Update UI wording to match README

Fix policy import error and add realtime LLM Inference API capability

Fix Pydantic typing error for Request

Fix Pydantic typing error for Optional[str]

fix(ui): Mount Gradio at /ui and redirect from / to prevent 404s and blank screens

fix(ui): Add fallback redirect from /web to / to prevent 404s from cached HF iframes

fix(ui): Mount Gradio app directly at root to resolve blank screen issue on HF Spaces

feat(ui): Redesign Gradio interface for human-impact narrative and judge demo

Fix AttributeError: readme_content by cleaning README.md on disk and using high-level create_app

Fix AttributeError: readme_content by patching metadata object in server/app.py

Fix README display in OpenEnv UI by manually loading and cleaning README.md

Fix HF YAML metadata length limit

Initial commit: FairRecovery++ complete multi-agent RL environment