Clamp task scores to strictly (0, 1) — never exactly 0.0 or 1.0

Clamp task scores to strictly (0, 1) — never exactly 0.0 or 1.0

Fix inference.py: always exit 0, fix import path resolution

Fix inference.py: support in-process env, use ENV_BASE_URL convention

Fix inference.py: correct default port to 7860, add retry logic

Fix OpenEnv validation: add uv.lock, scripts entry, openenv-core dep, main()

Add pyproject.toml for OpenEnv validation

Fix /reset endpoint to accept empty POST body for OpenEnv checker

Comprehensive README rewrite with full documentation

Drop Docling, PyMuPDF-only: fast multi-page PDF extraction, RL handles refinement by SpandanM110

Fix Docker build: add system libs, PyMuPDF fallback for table extraction by SpandanM110

Add system libs for Docling PDF processing (libxcb, libGL, poppler) by SpandanM110

Switch to Docker SDK with FastAPI + mounted Gradio UI by SpandanM110

Fix inference.py to strictly match pre-submission checklist by SpandanM110

Integrate Docling for accurate table/KPI extraction from uploaded PDFs by SpandanM110

Add PDF/image upload tab with document preview and grading by SpandanM110

Switch to Gradio SDK, mount OpenEnv API on Gradio FastAPI app by SpandanM110

Add app_port: 7860 to Space metadata for Docker by SpandanM110

Fix: redirect root / to Gradio UI at /ui by SpandanM110

Add Gradio UI, switch to Qwen2.5-72B-Instruct on HF Inference API by SpandanM110

Initial submission: OCR Table RL Environment for OpenEnv RL Challenge by SpandanM110