name: viral-script-debugging-engine version: "1.0.0" description: > A multi-agent RL environment where an LLM Arbitrator learns to improve short-form video scripts through adversarial debate. Trains with GRPO via HuggingFace TRL + Unsloth. Hits Theme 1 (Multi-Agent) and Theme 4 (Self-Improvement) simultaneously. themes: - multi_agent_interactions - self_improvement author: "Team Name" python_requires: ">=3.10" entry_point: viral_script_engine.environment.env:ViralScriptEnv reset_method: reset step_method: step state_method: state reward_method: reward tools: - name: env_reset description: "Start a new script improvement episode. Accepts: session_id (str), difficulty (str: easy|medium|hard), options (dict). Returns: observation dict, info dict." - name: env_step description: "Execute one debate round: Critic attacks, Defender responds, Arbitrator acts, Rewriter executes. Accepts: session_id (str), action (dict with action_type, target_section, instruction, critique_claim_id, reasoning). Returns: observation, reward, terminated, truncated, info." - name: env_state description: "Get the full current environment state. Accepts: session_id (str). Returns: current_script, original_script, debate_history, reward_components, step_num, difficulty_level, episode_id." - name: env_health description: "Health check endpoint. Returns: status, environment name, version." dependencies: - anthropic>=0.40.0 - sentence-transformers>=2.7.0 - unsloth - trl>=0.12.0 - numpy>=1.26.0 - pydantic>=2.0.0 - fastapi>=0.110.0 - uvicorn>=0.29.0