custom: in-process episode driver + CaptainRL rename (mirrors github c17c1ba)

ui: opponent + captain selectors with explicit presets (mirrors github 54e156d)

sync: pull latest from main (model_server.py, captain LLM toggle in ui.py, 0.6B configs, SUBMISSION + RUNTIME_DURABILITY docs)

fix: complete UI rewrite — per-tool groups, correct field dispatch, auto-play

feat: all-12-tool UI, auto-play, timestamped run folders, model fix

fix: match OpenEnv Gradio builder signature

feat: mount Gradio UI in OpenEnv app

chore: add OpenEnv submission files (Dockerfile, validate, uv.lock)

docs: comprehensive README update + fix ui.py dead code

feat: expand environment to full match simulator

Initial commit: CricketCaptain-LLM OpenEnv RL environment