Fix API reward clamp to (0.001, 0.999) and update README

Enforce strict (0.001, 0.999) bounds on ALL rewards and scores

Set minimum shaped reward to 0.001 (strict >0)

Clamp shaped rewards to non-negative values

Fix terminal reward to be grader score only (strict 0-1 range)

Restore Groq API defaults in inference.py

Fix score bounds to (0.001, 0.999) and use HF Router defaults

Add HF Space YAML frontmatter to README.md

Tighten score bounds to (0.000001, 0.999999) for strict validation

Fix grader scores to be strictly within (0, 1) range

Fix inference action sanitization and improve mobile responsiveness

Update README

Fix README filename casing for HuggingFace Spaces

Version 3: add trained model checkpoints

Version 3

Merge pull request #2 from Vishwa-docs/adi

fix: monorepo

Merge pull request #1 from Vishwa-docs/adi

push

feat: Initial dev

Update OpenEnv

Version 1 - VK

Initial Commit