Strict JSON output may need a place for reasoning
With the OpenAI , strict using json_schema and strict: true force the model to answer inside a fixed JSON shape. A can ask the model to choose a design direction and justify it before producing the final artifact, but the schema may only include fields such as phase, message, designTokens, html, and qaNote.
In that setup, the results looked more similar and generic than the same prompt with free-form text output. The main question is whether a standard GPT model can only make useful intermediate reasoning through tokens it actually outputs, so reasoning requested by the prompt may have little effect if there is no field to contain it.
The possible fix is to add explicit fields such as direction and rationale instead of relying on the prompt alone. There is also a question about whether the order of properties in the schema changes the result, because text generation moves from earlier tokens to later tokens, so a reasoning field placed before designTokens or html might influence what comes next.
Key points
- Strict make the model answer inside a fixed JSON shape.
- If the schema has no field for reasoning, a prompt asking for reasoning may not improve the final artifact much.
- Adding fields such as direction and rationale could make the model’s choice visible and usable.
- The order of properties may matter because later output can be shaped by earlier generated fields.
- For cost control, short reasoning fields can be better than repeated retries caused by generic output.