The lack of built-in retries is a huge pain, but the bigger risk is a "successful" retry that just outputs another hallucination.
How are you defining a "success" signal for these tasks? Is it just a 200 OK, or are you planning a fidelity audit for each item in the queue to trigger those retries?
The lack of built-in retries is a huge pain, but the bigger risk is a "successful" retry that just outputs another hallucination.
How are you defining a "success" signal for these tasks? Is it just a 200 OK, or are you planning a fidelity audit for each item in the queue to trigger those retries?