Spaces:
Running
Running
Commit History
-
refactor: unify data format and add stateful HTTP server
Data Format Changes: - Replace corpus.json/tasks.json with per-seed JSON files - Rename fields: gold_answer→truth, gold_chunk_ids→supporting_items, difficulty→level - Add SupportingItem and DistractorItem models with verification fields - Add sample/ directory with mock data matching generator output format Training Module Updates: - Change difficulty (easy/medium/hard) to level (0/1/2) throughout - Update CurriculumScheduler to use integer levels - Update metrics to use success_rate_by_level dict - Update evaluation to group by level instead of difficulty Server Changes: - Replace stateless openenv server with custom stateful FastAPI server - Environment state now persists across HTTP requests - Add /tasks endpoint to list available tasks Production Data Loading: - Add load_tasks_from_directory() for per-seed file loading - Add load_verified_tasks() and load_tasks_by_level() helpers - Add get_directory_statistics() for production data analysis All 76 tests pass. Co-Authored-By: C…79b7d56 -
docs: update data module docstring
4a9ba57 -
feat: add data generation pipeline
6b7aaad -
feat: add base explorer agent
707712d -
feat: add core utils for data generation
e1c44ac -
feat: add data generator module
6224aa1 -
feat: add data module for documents and tasks
Move task/corpus data to top-level data/ directory: - documents.py: document definitions with metadata - tasks.py: multi-hop tasks by difficulty (easy, medium, hard) - __init__.py: unified API for loading tasks and documentsb653e4d