# the library's LLM wrapper - retry-with-backoff, built into every parse call

def llm_parse(*, input, text_format, max_retries=6, cache=True, **opts):
    for attempt in range(max_retries):
        try:
            return client.responses.parse(input=input, text_format=text_format)
        except Exception as err:
            if not is_retriable(err):              # timeout/429/5xx retry ;
                raise                              # context-length never does
            if attempt == max_retries - 1:
                raise                              # hard cap -> propagate
            delay = _compute_delay(attempt, base=2, cap=60, jitter=0.3,
                                   retry_after=extract_retry_after(err))  # 2,4,..,60s
            time.sleep(delay)                      # honour Retry-After floor