Since today I get broken replies where both parsed and refusal values are “None”, which breaks running code which worked fine yesterday.
API error: Structured Output response does not have a ‘parsed’ field nor a ‘refusal’ field. Received message:
content='{"action":"read_range","sheet":"Sheet1"}'
additional_kwargs={'parsed': None, 'refusal': None}
response_metadata = {
"token_usage": {
"completion_tokens": 11,
"prompt_tokens": 268,
"total_tokens": 279,
"completion_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0},
"prompt_tokens_details": {"audio_tokens": None, "cached_tokens": 0},
},
"model_name": "gpt-4o-2024-08-06",
"system_fingerprint": "fp_e5e4913e83",
"finish_reason": "stop",
"logprobs": None,
}
id='run-1e6d411f-c50b-4234-aef7-6155c7072727-0'
usage_metadata={'input_tokens': 268, 'output_tokens': 11, 'total_tokens': 279}