Commit History

  1. Add YouTube video link

    havinashpatil
    e448fed
  2. Force add all results images

    havinashpatil
    ecfc00b
  3. Add all 7 results charts to README and BLOG

    havinashpatil
    b098526
  4. Add detailed results charts to README and BLOG

    havinashpatil
    7f4c57d
  5. Clean notebook outputs and add Colab warning note

    havinashpatil
    5dffd52
  6. Add comprehensive LLM finetuning analysis with 7 visualization graphs

    havinashpatil
    9d429ce
  7. Add blog link to HF discussion post

    havinashpatil
    9143510
  8. Final hackathon submission: polished README + detailed blog writeup

    havinashpatil
    90be6c7
  9. Polish README for Hackathon judging criteria

    havinashpatil
    5e35378
  10. Add Ollama fallback support to ai_fixer

    havinashpatil
    05d943b
  11. Add Hugging Face Inference API fallback for AI fixer

    havinashpatil
    18261cc
  12. Fix builtin syntax fixer for inline one-line headers and validate TGI fixes

    havinashpatil
    0c0a8ff
  13. Fix HF Spaces TGI launch entrypoint to avoid unexpected argument error

    havinashpatil
    27a8fcf
  14. Fix TGI endpoint plumbing and use full TGI runtime image in Dockerfile

    havinashpatil
    a8bc575
  15. Add TGI integration for cloud LLM serving⁠

    havinashpatil
    434afdf
  16. Add AI coding system with local Hugging Face LLM integration

    havinashpatil
    271cc02
  17. Update to Node 20 for better React 19 compatibility

    havinashpatil
    402970c
  18. Fix Dockerfile with multi-stage build for frontend

    havinashpatil
    43ecf30
  19. Update Dockerfile to build frontend for Spaces deployment

    havinashpatil
    da3a03d
  20. Resolve merge conflict and update HF Space URL

    havinashpatil
    99213a1
  21. initial commit

    Verified signature
    52752ed
  22. Serve React frontend from FastAPI backend for one-click access

    havinashpatil
    62c7e95
  23. Fix emoji in README

    havinashpatil
    034343c
  24. Update README with HF Space metadata

    havinashpatil
    c40cb2b
  25. Finalizing CodeArena RL Benchmark: frontend improvements, GRPO training scripts, and cleaned environment

    havinashpatil
    03a7eb9

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

    havinashpatil
    59fd9d3
  2. fix: removed invalid openenv-py package from notebook install cell

    havinashpatil
    82e39c9
  3. feat: use m-a-p/Code-Feedback dataset for GRPO training

    havinashpatil
    9204c04
  4. chore: update dependencies and include training results for README

    havinashpatil
    8599a81
  5. docs: Rewrite README for hackathon submission

    havinashpatil
    3f9399a
  6. Complete all tasks: Adaptive curriculum, GRPO, React frontend, LLM-as-a-judge

    havinashpatil
    a448db8
  7. Upload meta

    havinashpatil
    03defc2

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

    646409d
  2. fix: exclusive score clamping (0.001, 0.999) for evaluator

    2d8d38c
  3. fix: clamp scores to strict (0.001, 0.999) range

    b3485c6
  4. Rewrite inference.py for strict OpenEnv parsing + add httpx

    eb60bd2
  5. fix: openenv.yaml tasks graders + strict score bounds

    9967cb5
  6. fix: add safe_reward() clamp at every reward return point

    f14f8d9
  7. Minimal patch: standalone proxy ping + reward clamped to (0,1)

    74bfde0
  8. Add normalize_reward(); enforce strict (0,1) on all paths

    b53855f
  9. Update grading logic to strict (0,1) ratio fallback

    78b7e6b
  10. fix: use API_BASE_URL/API_KEY for LiteLLM proxy — always make API call (Phase 2)

    51fdbe8
  11. fix: make inference.py crash-proof when OPENAI_API_KEY is missing (Phase 2)

    1fe26af
  12. fix: OpenEnv multi-mode compliance — add main() entrypoint and uv.lock

    e92bfc1
  13. Add pyproject.toml for OpenEnv validation compliance

    652f070
  14. Production-ready: add server/app.py with fallback-safe /reset, fix Dockerfile, add HF metadata, add task JSON files

    dcc8fa3
  15. Initial commit

    54a19c9