Function test_parse_max_tokens_reached

tests/lib/chat/test_completions.py:526–551

(client: OpenAI, respx_mock: MockRouter)

@pytest.mark.respx(base_url=base_url)
def test_parse_max_tokens_reached(client: OpenAI, respx_mock: MockRouter) -> None:
    class Location(BaseModel):
        city: str
        temperature: float
        units: Literal["c", "f"]

    with pytest.raises(openai.LengthFinishReasonError):
        make_snapshot_request(
            lambda c: c.chat.completions.parse(
                model="gpt-4o-2024-08-06",
                messages=[
                    {
                        "role": "user",
                        "content": "What's the weather like in SF?",
                    },
                ],
                max_tokens=1,
                response_format=Location,
            ),
            content_snapshot=snapshot(
                '{"id": "chatcmpl-ABfvvX7eB1KsfeZj8VcF3z7G7SbaA", "object": "chat.completion", "created": 1727346163, "model": "gpt-4o-2024-08-06", "choices": [{"index": 0, "message": {"role": "assistant", "content": "{\\"", "refusal": null}, "logprobs": null, "finish_reason": "length"}], "usage": {"prompt_tokens": 79, "completion_tokens": 1, "total_tokens": 80, "completion_tokens_details": {"reasoning_tokens": 0}}, "system_fingerprint": "fp_7568d46099"}'
            ),
            path="/chat/completions",
            mock_client=client,
            respx_mock=respx_mock,
        )


@pytest.mark.respx(base_url=base_url)