feat: introduce reward ablation configurations for enhanced training flexibility, implement YAML loading with extends support, and add reward variant tracking in training scripts

feat: enhance reward configuration management with new logging functions, add parallel Modal training guidelines to documentation, and improve reward config hashing for deterministic behavior

feat: enhance CyberSecurity_OWASP observation model with scenario prompt, improve GRPO batch configuration validation, and add scenario grouping for adaptive difficulty curriculum

feat: add episode trace fingerprinting for improved trace logging and update reward penalties in GRPO configuration

feat: enhance scenario authoring and caching mechanisms, update action submission terminology, and improve reward configuration for CyberSecurity_OWASP environment

feat: update training configuration and documentation for Modal execution, including new model integration and enhanced tracking utilities

feat: integrate Trackio for experiment tracking and add Modal training infrastructure with environment and test utilities.

feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts.