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

docs: comprehensive README with spec compliance checklist, log format, API examples

fix: remove all 0.0/1.0 references, update reward ranges throughout

update README with final scores and structure

Revise task scores in README

Revise task descriptions and update script references

Update README.md

complete bug triage openenv environment

Initial commit