docs: fix incorrect citation and mischaracterized claim in Design Background

improve: enrich graders, observations, and reward signals

improve: add budget overrun penalty, require agent diversity in expert conflict check

docs: fix misleading expert task description

docs: replace oracle with best known (hand-written)

docs: simplify README language throughout

docs: remove salesy claims, em dashes, tighten prose

docs: restructure README for natural voice and practical-first ordering

docs: rewrite README to be concise and human-readable

improve: tighten graders, enrich breakdowns, enhance inference prompting

feat: add Mission Control dashboard with DAG visualization

improve: strengthen graders, enrich observations, overhaul README

fix: prevent score=0.000 in stdout for Phase 2 validation

fix: clamp observation rewards to [0,1] for Phase 2 eval compliance

fix: increase grader score epsilon to survive .3f stdout formatting

fix: clamp grader scores to strict (0, 1) interval for Phase 2 compliance

fix: add activity gate to graders, expand README, improve inference

fix: improve env robustness, grader fairness, and inference compatibility

feat: complete Phase 3 — inference, expert task, deployment

feat: implement Phase 2 — environment, graders, server endpoints, Dockerfile

fix: close Phase 0/1 gaps — conftest.py, critical path computation

feat: implement Phase 1 core engine — models, DAG, agents, rewards, tasks

chore: scaffold workflow_orchestrator environment via openenv init