128k whitespace tokens, by accident: debugging the Responses API

Always set the max_output_tokens request parameter in the OpenAI Responses API ↗. This is my new rule.

While testing phrasebook-fr-to-en CLI, for some reason the API generated 128k tokens, the maximum. I expected a JSON like this:

{
  "translations": [
    {
      "french": "fr2",
      "english": "en2"
    },
    {
      "french": "fr3",
      "english": "en3"
    }
  ]
}

I used their structured output ↗ feature and defined the expected JSON schema with this Pydantic ↗ model:

# DON'T USE THIS CODE.  IT MAKES THE REPSONSES API BUG.
from openai import OpenAI
from pydantic import BaseModel, conlist

client = OpenAI()

class Translation(BaseModel):
    french: str
    english: str

class Translations(BaseModel):
    # BUG CAUSED BY THIS FOLLOWING LINE
    translations: conlist(Translation, min_length=2, max_length=2)

response = client.responses.parse(
    model="gpt-5.2",
    input="Il est beau. -> He is handsome.",
    text_format=Translations,
)

But what I got was an incomplete JSON with more than 63,000 whitespaces. In total, it hit exactly 128k tokens. If I had set the max_output_tokens request parameter to 256, it would have stopped at 256.

View Full Size

The bug seems to kick in because of the minItems and maxItems array fields in the JSON schema. I set both to 2 with conlist(Translation, min_length=2, max_length=2) in the Pydantic model. Per the docs ↗ this should have worked:

View Full Size

And it did, once I removed the length condition on the array, the API responded the right way:

class Translations(BaseModel):
    translations: list[Translation]

Lesson learned:

Always set the max_output_tokens request parameter in the OpenAI Responses API ↗.

That's all I have for today! Talk soon 👋

References