Response format

Every call to AgentPrompt::HandlePrompt() returns a JSON response with a consistent structure:

• bSuccess – global success flag.
• sMode – how the prompt was interpreted ("test", "file-test", "operations", "echo", …).
• sMessage – human-readable status.
• sQuestion – the original prompt text.
• aDebug – logbook with all debug lines for this run.

For JSON prompts with aOperations, the response also contains:

• aOperations – what you asked.
• aOpResults – what happened per operation.

This makes it easy for an external AI (or a human) to inspect the logbook, learn from it, and send better prompts next time.