Fix phase tracking and WrappedResult per-call class definition

Fix task routing bug, update yaml, improve fallback and phase instructions

Expand to 30 tickets, fix Phase 1 grader, add benchmark table

Redesign environment as proper 3-phase RL MDP

Fix inference.py unhandled exception crash

Inject task-level instructions into agent prompt

Always run all 3 tasks in inference.py

Run all 3 tasks in inference.py for task validation check

Fix Phase 2 proxy bypass and openenv validation failures

v2

Initial commit with files from Support-Agent repository