Generated JSON schema fails strict mode checks of Azure

[bwaldvogel]

After upgrading Spring AI from 1.0.1 to 1.0.2, my chat client began throwing this exception:

400 Bad Request: {
  "error": {
    "message": "Invalid schema for response_format 'custom_schema': In context=('properties', [MASKED]), 'additionalProperties' must be supplied and set to false.",
    "type": "invalid_request_error",
    "param": "response_format",
    "code": null
  }
}

The problem seems to arise because the strict property is now mapped correctly (probably changed via #3928), which exposes previously “invalid” JSON schemas.

I’m looking for the correct way to generate a JSON schema that satisfies strict mode—that is, where additionalProperties is set to false in every nested object and every field is listed in required.

So far I’ve configured the response format like this:

AzureOpenAiResponseFormat.builder()
    .type(AzureOpenAiResponseFormat.Type.JSON_SCHEMA)
    .jsonSchema(JsonSchemaGenerator.generateForType(JSON_SCHEMA_CLASS))
    .build();

However, JsonSchemaGenerator.generateForType(JSON_SCHEMA_CLASS) sets additionalProperties=false only on the top-level object, not on nested ones.

I also tried BeanOutputConverter.getJsonSchema. That method correctly sets additionalProperties=false on nested objects, but it doesn’t mark every field as required, leading to a different exception:

400 Bad Request: {
  "error": {
    "message": "Invalid schema for response_format 'custom_schema': In context=('properties', [MASKED]), 'required' must be supplied and must include every key in properties. Missing '[MASKED]'.",
    "type": "invalid_request_error",
    "param": "response_format",
    "code": null
  }
}