Execute an evaluation YAML produced by pmstack-eval against a real target system, running n_trials per task and reporting both pass@k and pass^k. Implements the running side of Anthropic's eval framework. HARD-STOPS with educative errors if no target is configured, no tasks are present, or required
Execute an evaluation YAML produced by pmstack-eval against a real target system, running n_trials per task and reporting both pass@k and pass^k. Implements the running side of Anthropic's eval framework. HARD-STOPS with educative errors if no target is configured, no tasks are present, or required env vars are missing — never simulates results. Use when the user asks to "run", "execute", or "scor