fix: resolve 500 error on /schema and add extra validation tasks

feat: implement diverse autonomous grader for real-world code debugging tasks

fix: standardize grader structure to tasks/ directory for OpenEnv validation compliance

fix: add mandatory /metadata and /schema endpoints for OpenEnv validation and update task metadata

Fix OpenEnv task mapping schema: Add required 'id' fields

Fix OpenEnv validation: Use explicit python grader for tasks

revert(training): temporarily revert dataset bounds back to 10 for complete trial confirmation before scaling

feat(training): scale dataset to 500 prompts and add hub export cell for full hackathon training run

fix(trl): inject warnings_issued dict into unsloth model to prevent TRL GRPO init crash on PeftModels

fix(trl): force hardware-specific fp16/bf16 flags to prevent TRL from crashing on T4 GPU

fix(trl): mock weave.trace to complete package bypass

fix(trl): add weave to the magic mock bypass list for cell 5

fix(trl): inject magicmock bypass into cell 5 to squash TRL 0.24.0 import crash

feat: complete rewrite of grpo training script using Unsloth optimized pathway

chore: test trial run for colab script with 10 dataset size and fixed dependencies

fix: downgrade TRL to 0.15.0 and nuke ghost vLLM install to prevent import crashes

fix: correct trl version pin to 0.17.0

fix: vLLM/TRL version conflict in Colab Cell 1

fix: training reward bounds to (0.01, 0.99) — prevents loss=0 from zero variance

fix: task routing by name, remove out-of-range rewards, add grader field to tasks

fix: strictly bound task scores to satisfy OpenEnv Phase 2 testing bounds

fix: allow empty body for /reset endpoint to pass auto-grader

feat: switch default API to Groq (llama-3.3-70b-versatile) for faster inference

feat: Introduce environment models, a restricted code sandbox, and a test runner for secure LLM code evaluation.

docs: rewrite README, clean up repo structure

fix: use Qwen2.5-Coder-32B-Instruct (available on HF router) instead of Qwen3-1.7B

feat: add pre-submission compliance checker

feat: add pyproject.toml, server entry point, uv.lock for openenv validate compliance

fix: rewrite inference.py & client.py to match OpenEnv sample pattern

feat: add inference.py, openenv.yaml, bug dataset & openai dep for hackathon submission

fix: increase num_generations=6, temperature=0.9, lr=2e-5 to fix zero-loss GRPO

fix: remove fp16=True, use paged_adamw_8bit for QLoRA BFloat16 compatibility

fix: add 4-bit quantization + LoRA to fit GRPO training in T4 15GB VRAM

refactor: rewrite training script - remove rollout_func, use inline reward evaluation

fix: remove deprecated GRPOConfig params for latest TRL compatibility

fix: set live HF Space URL in training script and demo app

fix: add HF Spaces YAML frontmatter to README.md

chore: add .gitignore, remove __pycache__ from tracking

feat: CodeSensei - GRPO-trained LLM code debugger on OpenEnv