Add YouTube video link

Force add all results images

Add all 7 results charts to README and BLOG

Add detailed results charts to README and BLOG

Clean notebook outputs and add Colab warning note

Add comprehensive LLM finetuning analysis with 7 visualization graphs

Add blog link to HF discussion post

Final hackathon submission: polished README + detailed blog writeup

Polish README for Hackathon judging criteria

Add Ollama fallback support to ai_fixer

Add Hugging Face Inference API fallback for AI fixer

Fix builtin syntax fixer for inline one-line headers and validate TGI fixes

Fix HF Spaces TGI launch entrypoint to avoid unexpected argument error

Fix TGI endpoint plumbing and use full TGI runtime image in Dockerfile

Add TGI integration for cloud LLM serving

Add AI coding system with local Hugging Face LLM integration

Update to Node 20 for better React 19 compatibility

Fix Dockerfile with multi-stage build for frontend

Update Dockerfile to build frontend for Spaces deployment

Resolve merge conflict and update HF Space URL

initial commit

Serve React frontend from FastAPI backend for one-click access

Fix emoji in README

Update README with HF Space metadata

Finalizing CodeArena RL Benchmark: frontend improvements, GRPO training scripts, and cleaned environment

fix: clamp reward to [0.01,0.99] so .2f never rounds to 0.00 or 1.00

fix: removed invalid openenv-py package from notebook install cell

feat: use m-a-p/Code-Feedback dataset for GRPO training

chore: update dependencies and include training results for README

docs: Rewrite README for hackathon submission

Complete all tasks: Adaptive curriculum, GRPO, React frontend, LLM-as-a-judge

Upload meta

fix: reset task_id parsing, grader tuple crash fallback, and inference score output

fix: exclusive score clamping (0.001, 0.999) for evaluator

fix: clamp scores to strict (0.001, 0.999) range

Rewrite inference.py for strict OpenEnv parsing + add httpx

fix: openenv.yaml tasks graders + strict score bounds

fix: add safe_reward() clamp at every reward return point

Minimal patch: standalone proxy ping + reward clamped to (0,1)

Add normalize_reward(); enforce strict (0,1) on all paths

Update grading logic to strict (0,1) ratio fallback

fix: use API_BASE_URL/API_KEY for LiteLLM proxy — always make API call (Phase 2)

fix: make inference.py crash-proof when OPENAI_API_KEY is missing (Phase 2)

fix: OpenEnv multi-mode compliance — add main() entrypoint and uv.lock

Add pyproject.toml for OpenEnv validation compliance

Production-ready: add server/app.py with fallback-safe /reset, fix Dockerfile, add HF metadata, add task JSON files

Initial commit