fix:added client timeout

fix:added client timeout

fix: Each task's score must be strictly between 0 and 1 (not 0.0 and not 1.0)

fix: restructured dockerfile

fix: restructured dockerfile

fix: structurized the grader

fix:One or more task scores are out of range(1.0 and 0.0)

fix: - server/app.py main() function not callable (missing if __name__ == '__main__')

updated dockerfile

- Restructured directory layout for clarity and

Merge branch 'main' of https://github.com/Addyk-24/-Debate-Coach-Environment

updated app.py - reset req condition fix

updated app.py - reset req condition fix

Update README.md

updated reward metrics

updated ui with different response style of json and auto fill hf space

updated ui with different response style of json and auto fill hf space

- Updated ui with different response style of json

updated ui with different response style of json and auto fill hf space

updated gradio ui

updated gradio ui

updated gradio ui

updated gradio ui

updated gradio ui

updated gradio ui

updated app.py final closing response

updated api key mismatch

updated dockerfile

updated gradio ui package fix

Merge branch 'main' of https://github.com/Addyk-24/-Debate-Coach-Environment

-Added validation script and updated grading logic

Update README.md

Update README.md

added model config

Fix reset signature to make topic optional

Fix reset signature to make topic optional

Fix reset signature to make topic optional

updated inheritance error of openenv

updated inheritance error of openenv

Add root redirect to docs and fix uvicorn port

updated error causing lines in code

changed chat inference

Merge branch 'main' of https://github.com/Addyk-24/-Debate-Coach-Environment

Updated tasks and inference , environment etc

updated main server error and env file of rl

Initial release: Strategic Argument Red-Teaming Environment

Initial release: Strategic Argument Red-Teaming Environment

initial commit

Merge pull request #1 from Addyk-24/AENV

added server, reward meterics,openenv.yaml,tasks.py, grpo_train.py script