[Feature Request] Fragile Enforcement of JSON-only A2UI Output

I would suggest building in some prompt augmentation to the agent SDK to enforce proper A2UI messages. I don’t think you should be required to write something like `Your final output MUST be a a2ui UI JSON response`. Even with that, it doesn’t always work.

For example, my role description of `You are a helpful agent that helps find and book weekend activities. Your final output MUST be a a2ui UI JSON response` generated an A2UI validation failure.

However, something like this did work: `You are a powerful and intelligent agent that translates user requests into a stream of valid A2UI JSON messages. You must respond to the user's request using only the component and data schemas provided below. Do not add any conversational text or markdown outside of the designated component properties. Your entire response must be a valid JSON array of A2UI messages.`

Look at the agent SDK's prompt construction logic, likely in the core agent or message handling modules. Examine how validation failures occur and where output formatting is enforced. Test with the provided prompt examples to understand the failure modes. The goal is to modify the SDK to automatically augment prompts to ensure JSON-only A2UI output without requiring explicit user instructions.

索引モデルが issue の本文から書いたものです。