How does Spring AI's structured output converter get an LLM (which only produces text) to return valid JSON matching a Java class?

It appends formatting instructions to the prompt describing the exact JSON schema derived from your target Java record/class, asking the model to respond only in that shape, then parses the response back into that class. It's still fundamentally the model choosing to comply with instructions in the prompt, not a hard guarantee — which is why validating/retrying on parse failure is still necessary in production.