{"task": "ticket_routing", "state": "Checkout returns HTTP 500 for every customer since 09:10.",
 "question": {"type": "choice", "instructions": "Which team should handle this ticket?",
              "criteria": {"billing": "Charges, invoices and refunds",
                           "engineering": "Bugs, errors and outages",
                           "support": "How-to and account questions"}},
 "answer": "engineering"}
{"task": "refund_check", "state": {"subject": "Charged twice", "body": "Please refund the duplicate."},
 "question": {"type": "noul", "instructions": "Does the customer ask for a refund?",
              "criteria": {"true": "yes, a refund is requested", "false": "no refund is requested"}},
 "answer": true}
{"task": "urgency", "state": "Payroll export fails and payroll runs today.",
 "question": {"type": "score", "instructions": "How urgent is this request?",
              "criteria": ["not urgent", "soon", "today", "blocking right now"]},
 "answer": 2}
{"task": "intent_soft", "state": "I was billed twice and the app keeps crashing.",
 "question": {"type": "choice", "instructions": "What is the main topic?",
              "criteria": {"billing": "payments", "technical": "bugs"}},
 "target": {"billing": 0.6, "technical": 0.4}}

# prepare_data.py
"""Turn a few public datasets into decision records, remove duplicates and eval overlap, split by task."""
import hashlib
import json
import random
from pathlib import Path

from datasets import load_dataset

random.seed(13)
SST5_LEVELS = ["very negative", "negative", "neutral", "positive", "very positive"]
OCNLI = {"entailment": "前提为真时，假设一定为真",
         "neutral": "前提为真时，假设可能为真也可能为假",
         "contradiction": "前提为真时，假设一定为假"}


def banking77():
    ds = load_dataset("mteb/banking77", split="train")
    intents = sorted(set(ds["label_text"]))
    for row in ds:
        # 77 intents do not fit 26 letters: show the gold intent among 9 random distractors
        shown = random.sample([i for i in intents if i != row["label_text"]], 9) + [row["label_text"]]
        random.shuffle(shown)
        yield {"task": "banking77", "state": row["text"],
               "question": {"type": "choice",
                            "instructions": "Which banking intent does the customer's message express?",
                            "criteria": {i: i.replace("_", " ") for i in shown}},
               "answer": row["label_text"]}


def boolq():
    for row in load_dataset("google/boolq", split="train"):
        yield {"task": "boolq", "state": row["passage"],
               "question": {"type": "noul", "instructions": row["question"].capitalize() + "?",
                            "criteria": {"true": "yes, according to the passage",
                                         "false": "no, according to the passage"}},
               "answer": row["answer"]}


def sst5():
    for row in load_dataset("SetFit/sst5", split="train"):
        yield {"task": "sst5", "state": row["text"],
               "question": {"type": "score", "instructions": "How positive is this movie review?",
                            "criteria": SST5_LEVELS},
               "answer": row["label"]}


def ocnli():
    ds = load_dataset("clue/clue", "ocnli", split="train")
    names = ds.features["label"].names
    for row in ds:
        if row["label"] >= 0:  # -1 marks unlabeled rows
            yield {"task": "ocnli", "state": {"前提": row["sentence1"], "假设": row["sentence2"]},
                   "question": {"type": "choice", "instructions": "假设和前提是什么关系？", "criteria": OCNLI},
                   "answer": names[row["label"]]}


def key(record):
    text = json.dumps([record["state"], record["question"]["instructions"]], ensure_ascii=False)
    return hashlib.sha1(" ".join(text.lower().split()).encode()).hexdigest()


def write(path, rows):
    with open(path, "w", encoding="utf-8") as f:
        f.writelines(json.dumps(r, ensure_ascii=False) + "\n" for r in rows)


def main():
    held_out_tasks = {"banking77"}  # whole tasks never trained on (choice is still covered by ocnli)
    banned = {key(json.loads(line)) for p in Path("eval").glob("*.jsonl")
              for line in open(p, encoding="utf-8")}  # JevBench public files, your lockbox, ...
    seen, train, dev, held_out = set(), [], [], []
    for source in (banking77, boolq, sst5, ocnli):
        rows = list(source())
        random.shuffle(rows)
        for r in rows[:20000]:  # cap every task so no single dataset dominates the mix
            k = key(r)
            if k in seen or k in banned:
                continue
            seen.add(k)
            if r["task"] in held_out_tasks:
                held_out.append(r)
            elif random.random() < 0.05:
                dev.append(r)
            else:
                train.append(r)
    random.shuffle(train)
    Path("data").mkdir(exist_ok=True)
    write("data/train.jsonl", train)
    write("data/dev.jsonl", dev)
    write("data/heldout_tasks.jsonl", held_out)
    print(f"train {len(train)}  dev {len(dev)}  held-out tasks {len(held_out)}")


if __name__ == "__main__":
    main()

pip install torch transformers peft accelerate datasets fastapi uvicorn
# GPU 机器上再装 Qwen3.5 线性注意力层的加速算子
pip install flash-linear-attention causal-conv1d

# decision_format.py
"""Shared by training, evaluation and serving: render a decision as a prompt and read option probabilities."""
import json
import string

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

LETTERS = string.ascii_uppercase  # up to 26 options per question
SYSTEM = ("You are a decision model. Read the state and the question, "
          "then answer with the letter of exactly one option.")


def load(base, dtype=torch.bfloat16):
    tok = AutoTokenizer.from_pretrained(base)
    tok.padding_side = "left"  # every row then ends at its answer slot
    model = AutoModelForCausalLM.from_pretrained(base, dtype=dtype)  # Qwen3.5 loads text-only here
    ids = [tok.encode(c, add_special_tokens=False) for c in LETTERS]
    assert all(len(i) == 1 for i in ids), "every option letter must be a single token"
    return tok, model, torch.tensor([i[0] for i in ids])


def options(question):
    """[(key, description)] in the caller's order; noul is shown as yes / no."""
    kind, crit = question["type"], question.get("criteria")
    if kind == "noul":
        crit = crit or {}
        return [("yes", crit.get("true", "")), ("no", crit.get("false", ""))]
    if kind == "score":
        return [(str(i), desc) for i, desc in enumerate(crit)]
    return list(crit.items()) if isinstance(crit, dict) else [(c, "") for c in crit]


def target(record, opts):
    """Target distribution over opts: a soft label if the record has one, else one-hot."""
    keys = [k for k, _ in opts]
    if "target" in record:  # e.g. {"billing": 0.7, "technical": 0.3}
        dist = [float(record["target"].get(k, 0.0)) for k in keys]
    else:
        ans = record.get("answer", record.get("expected"))
        if record["question"]["type"] == "noul":
            ans = "yes" if ans in (True, "yes", "true") else "no"
        dist = [1.0 if k == str(ans) else 0.0 for k in keys]
    if sum(dist) <= 0:
        raise ValueError(f"answer is not one of the options: {record.get('id', record['question'])}")
    return [d / sum(dist) for d in dist]


def prompt(tok, record, order, max_state_tokens=6000):
    """Chat prompt whose next token is the answer letter; slot s shows option order[s]."""
    q, opts, state = record["question"], options(record["question"]), record["state"]
    if not isinstance(state, str):
        state = json.dumps(state, ensure_ascii=False, indent=1)
    ids = tok.encode(state, add_special_tokens=False)
    if len(ids) > max_state_tokens:  # cut the state, never the options or the answer slot
        state = tok.decode(ids[:max_state_tokens]) + "\n[truncated]"
    lines = [f"{LETTERS[s]}. {opts[i][0]}" + (f": {opts[i][1]}" if opts[i][1] else "")
             for s, i in enumerate(order)]
    user = (f"<state>\n{state}\n</state>\n\nQuestion ({q['type']}): {q['instructions']}\n"
            "Options:\n" + "\n".join(lines) + "\n\nAnswer with the letter of one option.")
    messages = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": user}]
    return tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True,
                                   enable_thinking=False)


def option_logits(model, tok, letter_ids, prompts, ks, device):
    """One forward pass for a batch: logits of the shown option letters at the answer slot."""
    enc = tok(prompts, return_tensors="pt", padding=True, add_special_tokens=False).to(device)
    out = model(input_ids=enc.input_ids, attention_mask=enc.attention_mask, logits_to_keep=1)
    z = out.logits[:, -1, letter_ids[: max(ks)].to(device)].float()
    mask = torch.arange(z.shape[1], device=device)[None, :] < torch.tensor(ks, device=device)[:, None]
    return z.masked_fill(~mask, -1e4), mask

# train.py
"""LoRA fine-tuning of a decision model with strictly proper scoring rules, or Laya-style RLCD."""
import argparse
import json
import math
import random

import torch
from accelerate import Accelerator
from peft import LoraConfig, get_peft_model
from torch.utils.data import DataLoader
from transformers import get_cosine_schedule_with_warmup

from decision_format import load, option_logits, options, prompt, target


def reward(z, mask, y, ordinal):
    """Laya's composite of strictly proper scores: log + 0.5 * spherical - RPS (RPS for score only)."""
    logq = z.log_softmax(-1)
    q = logq.exp()
    s_log = (y * logq).sum(-1)                      # log score = minus cross-entropy
    s_sph = (y * q).sum(-1) / q.norm(dim=-1)        # spherical score, bounded in [0, 1]
    k = mask.sum(-1).clamp(min=2)
    rps = ((q.cumsum(-1) - y.cumsum(-1)) ** 2).sum(-1) / (k - 1)  # ranked probability score
    return s_log + 0.5 * s_sph - ordinal * rps


def rlcd_loss(z, mask, y, ordinal, sigma, group=8):
    """Policy gradient over Gaussian-perturbed logits with a group-mean baseline, as Laya describes RLCD."""
    m = mask.float()
    eps = torch.randn(group, *z.shape, device=z.device) * m
    eps = (eps - eps.sum(-1, keepdim=True) / m.sum(-1, keepdim=True)) * m  # softmax ignores a common shift
    sample = z.detach() + eps
    with torch.no_grad():
        r = reward(sample, mask, y, ordinal)            # [group, batch]
        adv = (r - r.mean(0)) / (r.std(0) + 1e-6)
    logp = -(((sample - z) ** 2) * m).sum(-1) / (2 * sigma**2)  # Gaussian log-density up to a constant
    return -(adv * logp).mean()


class Collate:
    def __init__(self, tok, max_state_tokens):
        self.tok, self.max_state_tokens = tok, max_state_tokens

    def __call__(self, records):
        prompts, ks, ys, ordinal = [], [], [], []
        for r in records:
            opts = options(r["question"])
            order = list(range(len(opts)))
            if r["question"]["type"] != "score":  # score levels keep their order, RPS relies on it
                random.shuffle(order)
            y = target(r, opts)
            prompts.append(prompt(self.tok, r, order, self.max_state_tokens))
            ys.append([y[i] for i in order])
            ks.append(len(opts))
            ordinal.append(float(r["question"]["type"] == "score"))
        y = torch.zeros(len(records), max(ks))
        for row, t in enumerate(ys):
            y[row, : len(t)] = torch.tensor(t)
        return {"prompts": prompts, "ks": ks, "y": y, "ordinal": torch.tensor(ordinal)}


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--base", default="Qwen/Qwen3.5-4B")
    ap.add_argument("--train", default="data/train.jsonl")
    ap.add_argument("--out", default="out/my-jev")
    ap.add_argument("--objective", choices=["proper", "rlcd"], default="proper")
    ap.add_argument("--epochs", type=int, default=2)
    ap.add_argument("--lr", type=float, default=1e-4)
    ap.add_argument("--batch-size", type=int, default=4)
    ap.add_argument("--grad-accum", type=int, default=8)
    ap.add_argument("--lora-r", type=int, default=32)
    ap.add_argument("--max-state-tokens", type=int, default=3000)
    ap.add_argument("--mixed-precision", default="bf16")
    args = ap.parse_args()

    acc = Accelerator(mixed_precision=args.mixed_precision, gradient_accumulation_steps=args.grad_accum)
    tok, model, letter_ids = load(args.base)
    model.gradient_checkpointing_enable(gradient_checkpointing_kwargs={"use_reentrant": False})
    model = get_peft_model(model, LoraConfig(
        r=args.lora_r, lora_alpha=2 * args.lora_r, lora_dropout=0.05, target_modules="all-linear"))
    if acc.is_main_process:
        model.print_trainable_parameters()

    records = [json.loads(line) for line in open(args.train, encoding="utf-8")]
    loader = DataLoader(records, batch_size=args.batch_size, shuffle=True,
                        collate_fn=Collate(tok, args.max_state_tokens))
    opt = torch.optim.AdamW([p for p in model.parameters() if p.requires_grad], lr=args.lr, weight_decay=0.0)
    total = args.epochs * math.ceil(len(loader) / args.grad_accum)
    sched = get_cosine_schedule_with_warmup(opt, max(1, int(0.03 * total)), total)
    model, opt, loader, sched = acc.prepare(model, opt, loader, sched)

    step, n_batches = 0, args.epochs * len(loader)
    for epoch in range(args.epochs):
        model.train()
        for batch in loader:
            with acc.accumulate(model):
                z, mask = option_logits(model, tok, letter_ids, batch["prompts"], batch["ks"], acc.device)
                if args.objective == "rlcd":
                    sigma = 1.0 - 0.7 * step / n_batches  # exploration decays from 1.0 to 0.3
                    loss = rlcd_loss(z, mask, batch["y"], batch["ordinal"], sigma)
                else:
                    loss = -reward(z, mask, batch["y"], batch["ordinal"]).mean()
                acc.backward(loss)
                if acc.sync_gradients:
                    acc.clip_grad_norm_(model.parameters(), 1.0)
                opt.step()
                sched.step()
                opt.zero_grad()
            step += 1
            if step % 20 == 0:
                acc.print(f"epoch {epoch + 1} step {step}/{n_batches} loss {loss.item():.4f}")
        acc.wait_for_everyone()
        if acc.is_main_process:
            acc.unwrap_model(model).save_pretrained(f"{args.out}/epoch{epoch + 1}")
    acc.end_training()


if __name__ == "__main__":
    main()

# 单卡：有效 batch = 4 × 8 = 32 道题
python train.py --base Qwen/Qwen3.5-4B --train data/train.jsonl --out out/my-jev

# 8 卡数据并行：有效 batch = 4 × 2 × 8 = 64 道题
accelerate launch --num_processes 8 train.py --base Qwen/Qwen3.5-4B \
  --train data/train.jsonl --out out/my-jev --grad-accum 2

# 对比实验：换成 Laya 式的 RLCD
python train.py --base Qwen/Qwen3.5-4B --train data/train.jsonl --out out/my-jev-rlcd --objective rlcd

# evaluate.py
"""Evaluate a decision model: accuracy, chance-corrected accuracy, calibration, order robustness, latency."""
import argparse
import json
import statistics
import time

import torch
from peft import PeftModel

from decision_format import load, option_logits, options, prompt, target


@torch.no_grad()
def predict(model, tok, letter_ids, records, batch_size=8, reverse=False):
    """Logits over each record's options, in the caller's order."""
    result = []
    for i in range(0, len(records), batch_size):
        chunk, orders = records[i : i + batch_size], []
        for r in chunk:
            order = list(range(len(options(r["question"]))))
            if reverse and r["question"]["type"] != "score":
                order.reverse()
            orders.append(order)
        prompts = [prompt(tok, r, o) for r, o in zip(chunk, orders)]
        z, _ = option_logits(model, tok, letter_ids, prompts, [len(o) for o in orders], model.device)
        for row, order in enumerate(orders):
            logits = torch.empty(len(order))
            logits[order] = z[row, : len(order)].cpu()  # slot s showed option order[s]
            result.append(logits)
    return result


def ece(conf, correct, bins=10):
    groups = {}
    for c, ok in zip(conf, correct):
        groups.setdefault(min(int(c * bins), bins - 1), []).append((c, ok))
    return sum(len(g) / len(conf) * abs(statistics.mean(o for _, o in g) - statistics.mean(c for c, _ in g))
               for g in groups.values())


def summary(rows):
    conf = [p.max().item() for _, p, _ in rows]
    correct = [float(p.argmax() == y.argmax()) for _, p, y in rows]
    acc = statistics.mean(correct)
    chance = statistics.mean(1 / len(p) for _, p, _ in rows)
    out = {"n": len(rows), "accuracy": acc, "chance_corrected": (acc - chance) / (1 - chance),
           "log_loss": statistics.mean(-(y * p.clamp_min(1e-12).log()).sum().item() for _, p, y in rows),
           "brier": statistics.mean(((p - y) ** 2).sum().item() for _, p, y in rows),
           "ece": ece(conf, correct)}
    ordinal = [(p, y) for kind, p, y in rows if kind == "score"]
    if ordinal:
        out["rps"] = statistics.mean((((p.cumsum(0) - y.cumsum(0)) ** 2).sum() / (len(p) - 1)).item()
                                     for p, y in ordinal)
    return out


def metrics(records, logits, temps):
    rows = []
    for r, z in zip(records, logits):
        kind = r["question"]["type"]
        p = (z / temps.get(kind, 1.0)).softmax(-1)
        rows.append((kind, p, torch.tensor(target(r, options(r["question"])))))
    report = {"all": summary(rows)}
    for kind in ("choice", "noul", "score"):
        if any(row[0] == kind for row in rows):
            report[kind] = summary([row for row in rows if row[0] == kind])
    return report


def fit_temperatures(records, logits):
    """One temperature per question type, chosen to minimise log loss (fit on dev data only)."""
    grid, temps = [round(0.3 + 0.05 * i, 2) for i in range(55)], {}
    for kind in ("choice", "noul", "score"):
        pairs = [(z, torch.tensor(target(r, options(r["question"]))))
                 for r, z in zip(records, logits) if r["question"]["type"] == kind]
        if pairs:
            temps[kind] = min(grid, key=lambda t: sum(-(y * (z / t).log_softmax(-1)).sum().item()
                                                      for z, y in pairs))
    return temps


@torch.no_grad()
def latency_ms(model, tok, letter_ids, records, n=50):
    times = []
    for r in records[:n]:
        k = len(options(r["question"]))
        text = prompt(tok, r, list(range(k)))
        if torch.cuda.is_available():
            torch.cuda.synchronize()
        start = time.perf_counter()
        option_logits(model, tok, letter_ids, [text], [k], model.device)
        if torch.cuda.is_available():
            torch.cuda.synchronize()
        times.append((time.perf_counter() - start) * 1000)
    times.sort()
    return {"p50": times[len(times) // 2], "p95": times[min(len(times) - 1, int(0.95 * len(times)))]}


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--base", default="Qwen/Qwen3.5-4B")
    ap.add_argument("--adapter", help="LoRA directory; omit it to score the raw base model")
    ap.add_argument("--data", nargs="+", required=True)
    ap.add_argument("--fit-temperature", help="fit temperatures on --data (dev only) and save them here")
    ap.add_argument("--temperatures", help="temperatures fitted earlier")
    ap.add_argument("--batch-size", type=int, default=8)
    args = ap.parse_args()

    tok, model, letter_ids = load(args.base)
    if args.adapter:
        model = PeftModel.from_pretrained(model, args.adapter).merge_and_unload()
    model.to("cuda" if torch.cuda.is_available() else "cpu").eval()
    records = [json.loads(line) for path in args.data for line in open(path, encoding="utf-8")]

    logits = predict(model, tok, letter_ids, records, args.batch_size)
    temps = json.load(open(args.temperatures)) if args.temperatures else {}
    if args.fit_temperature:
        temps = fit_temperatures(records, logits)
        json.dump(temps, open(args.fit_temperature, "w"), indent=2)
    flipped = predict(model, tok, letter_ids, records, args.batch_size, reverse=True)
    flips = [bool(a.argmax() != b.argmax())
             for r, a, b in zip(records, logits, flipped) if r["question"]["type"] != "score"]

    report = metrics(records, logits, temps)
    report["flip_rate_reversed_options"] = sum(flips) / max(1, len(flips))
    report["temperatures"] = temps
    report["latency_ms"] = latency_ms(model, tok, letter_ids, records)
    print(json.dumps(report, indent=2))


if __name__ == "__main__":
    main()

# 1) 零样本基线：不加适配器，直接读底座模型的字母概率，先知道起点
python evaluate.py --base Qwen/Qwen3.5-4B --data data/dev.jsonl data/heldout_tasks.jsonl

# 2) 在开发集上评测训练好的模型，并按题型拟合温度
python evaluate.py --base Qwen/Qwen3.5-4B --adapter out/my-jev/epoch2 \
  --data data/dev.jsonl --fit-temperature out/my-jev/temperatures.json

# 3) 带上温度，在留出任务和 JevBench 公开题上打分（温度只能在开发集上拟合）
python evaluate.py --base Qwen/Qwen3.5-4B --adapter out/my-jev/epoch2 \
  --temperatures out/my-jev/temperatures.json --data data/heldout_tasks.jsonl
python evaluate.py --base Qwen/Qwen3.5-4B --adapter out/my-jev/epoch2 \
  --temperatures out/my-jev/temperatures.json --data eval/easy.jsonl eval/original.jsonl eval/hard.jsonl

{
  "all":    {"n": 120, "accuracy": 0.642, "chance_corrected": 0.488, "log_loss": 1.326, "brier": 0.523, "ece": 0.108},
  "choice": {"n": 72,  "accuracy": 0.694, "chance_corrected": 0.614, "ece": 0.117},
  "noul":   {"n": 36,  "accuracy": 0.583, "chance_corrected": 0.167, "ece": 0.220},
  "score":  {"n": 12,  "accuracy": 0.500, "chance_corrected": 0.333, "rps": 0.151},
  "flip_rate_reversed_options": 0.620
}

# serve.py
"""A minimal /v1/systemone server (Jev wire format) in front of the fine-tuned model."""
import json
import os

import torch
from fastapi import FastAPI, HTTPException
from peft import PeftModel

from decision_format import LETTERS, load, option_logits, options, prompt

BASE = os.environ.get("BASE_MODEL", "Qwen/Qwen3.5-4B")
ADAPTER = os.environ.get("ADAPTER", "out/my-jev/epoch2")
TEMPS = json.load(open(os.environ["TEMPERATURES"])) if os.environ.get("TEMPERATURES") else {}

tok, model, letter_ids = load(BASE)
model = PeftModel.from_pretrained(model, ADAPTER).merge_and_unload()
model.to("cuda" if torch.cuda.is_available() else "cpu").eval()
app = FastAPI()


@app.post("/v1/systemone")
@torch.no_grad()
def systemone(body: dict):
    questions = body.get("questions")
    if not isinstance(questions, dict) or not 0 < len(questions) <= 32:
        raise HTTPException(422, "questions must be an object with 1 to 32 entries")
    names, prompts, ks = list(questions), [], []
    for name in names:
        q = questions[name]
        try:
            k = len(options(q))
            ok = q["type"] in ("choice", "noul", "score") and isinstance(q["instructions"], str)
        except (KeyError, TypeError, AttributeError):
            ok = False
        if not ok or not 2 <= k <= len(LETTERS):
            raise HTTPException(422, f"{name}: malformed question or unsupported option count")
        prompts.append(prompt(tok, {"state": body.get("state", ""), "question": q}, list(range(k))))
        ks.append(k)

    z, _ = option_logits(model, tok, letter_ids, prompts, ks, model.device)
    answers = {}
    for row, name in enumerate(names):
        q, k = questions[name], ks[row]
        p = (z[row, :k] / TEMPS.get(q["type"], 1.0)).softmax(-1).tolist()
        if q["type"] == "noul":
            answers[name] = {"type": "noul", "noul": p[0]}  # P(yes)
        elif q["type"] == "score":
            answers[name] = {"type": "score", "score": sum(i * x for i, x in enumerate(p)),
                             "probabilities": {str(i): x for i, x in enumerate(p)}}
        else:
            probs = {key: x for (key, _), x in zip(options(q), p)}
            best = max(probs, key=probs.get)
            answers[name] = {"type": "choice", "choice": best, "probabilities": probs,
                             "confidence": (k * probs[best] - 1) / (k - 1)}
    used = sum(len(ids) for ids in tok(prompts, add_special_tokens=False).input_ids)
    return {"answers": answers, "usage": {"input_tokens": used, "output_tokens": 0}}

ADAPTER=out/my-jev/epoch2 TEMPERATURES=out/my-jev/temperatures.json \
  uvicorn serve:app --host 127.0.0.1 --port 8741

curl -s http://127.0.0.1:8741/v1/systemone -H 'Content-Type: application/json' -d '{
  "state": "Checkout returns HTTP 500 for every customer since 09:10.",
  "questions": {
    "team": {"type": "choice", "instructions": "Which team should handle this?",
             "criteria": {"billing": "charges and refunds", "engineering": "bugs and outages"}},
    "outage": {"type": "noul", "instructions": "Is a production system down?"}
  }
}'

git clone https://github.com/fstandhartinger/jevbench && cd jevbench
python -m jevbench.cli run \
  --tasks datasets/public/easy.jsonl,datasets/public/original.jsonl,datasets/public/hard.jsonl \
  --adapter typesafe --endpoint http://127.0.0.1:8741 --key-env '' --model my-jev \
  --cost-basis self_hosted_gpu --reserve-usd 0 --delay-s 0 \
  --results RUN/results.jsonl --raw-dir RUN/raw --ledger RUN/ledger.jsonl --manifest RUN/manifest.json

# 汇总成绩
python -m jevbench.cli summarize \
  --tasks datasets/public/easy.jsonl,datasets/public/original.jsonl,datasets/public/hard.jsonl \
  --results RUN/results.jsonl --public-export RUN/summary.json