Merge branch 'mainline' into hf_branch

changes upper and lower bounds for inference grading

Merge branch 'mainline' into hf_branch

removed final summary print table

:erge branch 'mainline' into hf_branch

fixed scoring and logging for final submission

Merge branch 'mainline' into hf_branch

changed grader to return 0 or 1

change logging of score to int

changed loggging of end reward to be int than float

Merge branch 'mainline' into hf_branch

fixed uv module activation issue in inference.py during test evaluation

Merge branch 'mainline' into hf_branch

fix dot env load issue in inference.py

added docker file of hf in mainline

added helpers in dockerfile for hf

Merge branch 'mainline' into hf_branch

black format and isort code

Merge branch 'mainline' into hf_branch

logging whole action response from llm in inference.py

updated readme and baseline.py

updated readme and baseline.py

Merge branch 'mainline' into hf_branch

grader changes for easy task

fixed issues in SQL schema not available to agent and code parsing issues

Merge branch 'mainline' into hf_branch

added 2 new hard tasks 1 medium and grader for each, SQL DB mock data for hard task

added start step and end logging in inference.py

fixed action parsing issues in inference.py and increased concurrent env in server/app.py

added dockerfile and updated readme for hf deployment

added start step and end logs in inference.py

made changes to use apis from terminal in inferece.py and pointing direct to hf space for env evaluation

added inference.py script

made changes to use the proper context manager for inference in baseline.py

added configurations for black and formatted code

first commit