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

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 all things

fix: add get_metadata with tasks and graders to Environment class

fix: make each task independent with task_id param in reset

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

fix: explicit TriageState args

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

fix import paths for Docker

complete bug triage openenv environment