Error messages

{
  "error": {
    "message": "Only `tool_choice` 'auto' and 'none' are supported; forcing a tool call is not supported yet.",
    "type": "invalid_request_error",
    "param": "tool_choice",
    "code": "unsupported_tool_choice"
  }
}

import math
import os
import random
import time

from perceptron import Client, QuotaExceededError, SDKError, TimeoutError, TransportError


client = Client(
    api_key=os.environ["PERCEPTRON_API_KEY"],
    provider="perceptron",
    timeout=30.0,
)
RETRYABLE_STATUS = {408, 429, 500, 502, 503, 504}


def retry_delay(retry_after, attempt):
    try:
        delay = float(retry_after)
    except (TypeError, ValueError):
        delay = -1
    if math.isfinite(delay) and delay >= 0:
        return delay
    return 2 ** attempt + random.random()


def complete_with_retries(messages):
    for attempt in range(3):
        try:
            return client.chat.completions.create(
                model="perceptron-mk1.5",
                messages=messages,
                max_completion_tokens=256,
            )
        except QuotaExceededError:
            raise
        except (TimeoutError, TransportError):
            if attempt == 2:
                raise
            delay = retry_delay(None, attempt)
        except SDKError as error:
            if error.status_code not in RETRYABLE_STATUS or attempt == 2:
                raise
            delay = retry_delay(error.retry_after, attempt)
            if delay > 60:
                raise
        time.sleep(delay)


if __name__ == "__main__":
    response = complete_with_retries([
        {"role": "user", "content": "Give one tip for reviewing a video."},
    ])
    choice = response.choices[0]
    if choice.finish_reason != "stop" or choice.message.tool_calls:
        raise RuntimeError("The request did not return a complete text answer")
    print(choice.message.content or "")