The Agent Harness Is Becoming Part of Model Training

When an agent fails, the model is not always the culprit. A tool may return an unexpected payload, useful state may be stored in the wrong place, or the system may ask the model to operate under conditions it never encountered during training.These failures begin outside the weights, inside the agent harness.
Macaron‑V1 makes that relationship explicit. Its harness was co-designed and trained with the model, while the same routing, memory, tool-call, and context conventions are carried fro