Expose independent grader scores in the reward calculator component models

Merge remote changes and keep local fixes

Fix float rounding output limit to prevent out of bounds exactly 1.0 rewards in logged inference metrics

Update baseline scores

Fix Phase 2 requirements: Add / endpoint for HF health checks and tasks grader definitions

added

Merge pull request #1 from lishhh06/test

Delete MANUAL_TESTING.md

openAi int

openAi int

Add FastAPI server to fix 404

endpoint

done

Merge hf/main into main

Prepare HF deploy with OpenAI token

initial commit

Refine manual deployment guide

Make environment fully checklist-compliant

Final

Completed

test

Made some changes

Fix HF Space config and validator flow

AI completed

first commit

all checks

added