sync: today's source updates (XML-only prompt, reward unclip, neg-reward on loss, pinned versions, configs reorg)

feat: CricsheetOpponentPolicy — real match data as opponent decisions

docs: update README, slides, illustrations with format mapper, tool budget, player rosters, 5/20-over baselines

fix: incremental log writes, openenv.yaml descriptions, openai dep

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

Ensure non-zero rewards for all valid tool calls

feat: add field-aware hybrid ball simulation and timing logs

fix: tighten cricket rules and reward visibility

fix: enforce bowler changes at over boundaries

test: add 5-over training rollout smoke

feat: align benchmark data and training roadmap

push

Initial commit: CricketCaptain-LLM OpenEnv RL environment