并行问题

QUESTIONS = {
    "breach_72h": Noul(
        instructions="Must a personal data breach be reported to the supervisory authority within 72 hours?"
    ),
    "applies_non_eu": Noul(
        instructions="Does the regulation apply to organisations established outside the EU that offer goods or services to people in the EU?"
    ),
    "dpo_all_orgs": Noul(
        instructions="Must every organisation appoint a Data Protection Officer, regardless of what data it processes?"
    ),
    "pre_ticked_consent": Noul(
        instructions="Can valid consent be obtained through pre-ticked boxes or inactivity?"
    ),
    "right_erasure": Noul(
        instructions="Does the regulation grant individuals a right to erasure of their personal data?"
    ),
    "data_portability": Noul(
        instructions="Does the regulation include a right to data portability?"
    ),
    "us_federal_law": Noul(instructions="Is the GDPR a United States federal law?"),
    "criminal_penalties": Noul(
        instructions="Does the GDPR itself impose criminal penalties such as imprisonment?"
    ),
    "instrument_type": Choice(
        instructions="What kind of EU legal instrument is the GDPR?",
        criteria={
            "Regulation": "Directly binding law in all member states, no national implementation needed.",
            "Directive": "Sets goals that member states implement through national law.",
            "Treaty": "An international treaty between states.",
            "Recommendation": "Non-binding guidance.",
        },
    ),
    "max_fine": Choice(
        instructions="What is the maximum administrative fine for the most serious infringements?",
        criteria={
            "TwentyM_or_4pct": "Up to EUR 20 million or 4% of annual worldwide turnover, whichever is greater.",
            "TenM_or_2pct": "Up to EUR 10 million or 2% of annual worldwide turnover, whichever is greater.",
            "FixedCap": "A fixed amount not tied to turnover.",
            "NoFines": "The GDPR provides no administrative fines.",
        },
    ),
    "individual_rights": Score(
        instructions="How strong are the rights the GDPR grants to individuals over their data?",
        criteria=[
            "None: individuals get no rights over their data.",
            "Weak: a right to be informed, but little control.",
            "Moderate: access and correction rights, but limited means to act on them.",
            "Strong: access, erasure, portability, and objection rights, with enforcement behind them.",
        ],
    ),
    "penalty_severity": Score(
        instructions="How severe are the penalties the GDPR provides for non-compliance?",
        criteria=[
            "None: no penalties of any kind.",
            "Symbolic: small fixed fines unlikely to change behavior.",
            "Substantial: fines large enough to matter to most companies.",
            "Severe: fines scaled to global revenue, material even to the largest companies.",
        ],
    ),
    "compliance_burden": Score(
        instructions="How heavy is the compliance burden the GDPR places on organisations?",
        criteria=[
            "Negligible: no meaningful obligations.",
            "Light: a few notices and disclosures.",
            "Moderate: documented processes and some dedicated roles for larger processors.",
            "Heavy: records, impact assessments, officers, and breach procedures for many organisations.",
            "Extreme: obligations so demanding that ordinary organisations cannot fully comply.",
        ],
    ),
}
N = len(QUESTIONS)
METRIC = {  # question type -> the one number we track per answer
    Noul: "p(yes)",
    Choice: "max prob",
    Score: "normalized score",
}
 

@json_cache
def ask(keys: tuple[str, ...], run: int):
    """One TypeSafe call -> ({key: tracked metric}, input_tokens, output_tokens, latency_s);
    ``run`` only forces a distinct live call per repeat."""
    started = perf_counter()
    response = client.system_one(
        state={"article": DOCUMENT},
        questions={key: QUESTIONS[key] for key in keys},
        model=TYPESAFE_MODEL,
    )
    values = {}
    for key in keys:
        answer = response.answers[key]
        if isinstance(answer, NoulAnswer):
            values[key] = answer.noul
        elif isinstance(answer, ChoiceAnswer):
            values[key] = max(answer.probabilities.values())
        else:
            values[key] = answer.score / (len(QUESTIONS[key].criteria) - 1)
    return (
        values,
        response.usage.input_tokens,
        response.usage.output_tokens,
        perf_counter() - started,
    )
 
 
def priced(result):
    """({key: metric}, in_tokens, out_tokens, latency) -> ({key: metric}, cost_usd, latency)."""
    values, input_tokens, output_tokens, latency = result
    return values, input_tokens / 1e6 * PRICE[0] + output_tokens / 1e6 * PRICE[1], latency
 
 
# Price after cache retrieval, so a price change needs no new calls.
batched = [
    priced(ask(tuple(QUESTIONS), run)) for run in range(RUNS)
]  # all N in one call, x RUNS
singles = [
    {key: priced(ask((key,), run)) for key in QUESTIONS} for run in range(RUNS)
]  # N x 1, x RUNS