v2.0 frontend: multi-step investigation UI with step tracker, progressive reveal, and reasoning bonus

v2.0: multi-step episodes, procedural bugs, semantic grading, sessions, 71 tests

Fix all things

feat: serve frontend at root / so it shows in HF Spaces App tab, JSON status moved to /health

feat: add interactive demo frontend at /web — no existing endpoints changed

fix: add name/difficulty to tasks, per-task [START]/[END] logs for validator

fix: stateful endpoints + score clamping for validator pass

fix: last remaining 0.0 in reset() total_score

fix: reward_range to (0.05, 0.95) in environment.py TASKS_META

fix: replace 0.0 fallback with 0.05 in graders to satisfy strict range

Fix all things

fix: no exact 0.0 or 1.0 anywhere in rewards

fix: reward_range 0.05-0.95 and proper descriptions

fix: correct grader import paths

Fix all things

fix: add pydantic dependency for grader import

fix: tasks returns plain array for validator

Fix all things

Fix all things

fix: add openai to requirements - was causing silent import failure

Fix all things

fix: add get_metadata with tasks and graders to Environment class

fix: override /reset to accept task_id for validator

fix: force override /metadata with tasks for validator

fix: override /metadata with tasks and graders for validator

final fix: validator-compatible graders

fix: add /grader and /baseline endpoints for validator

fix: make each task independent with task_id param in reset

fix: add task endpoints and per-task reset for validator

fix server/app.py

fix: remove groqiikik typo from requirements.txt

fix: typo in requirements.txt groqiikik -> groq

fix: add root health check route

fix: auto-init bug in __init__ for stateless HTTP server

fix: explicit TriageState args

upgrade environment.py: done guard, fix tasks_completed, sample_bug

upgrade task.py: milestone grading, team in medium, 5 bugs per task

fix pyproject.toml and generate uv.lock

fix import paths for Docker

complete bug triage openenv environment