hack/tools/scripts/llm-key-hunter/reverify_iflytek_smart.py

#!/usr/bin/env python3
"""Smart iFlytek MaaS verifier — queries /models per key, then tries each
granted model until one returns a real chat completion.

iFlytek MaaS keys are per-user and each has a different set of granted models
(the /models endpoint returns the key's own entitlements). A blanket model list
misses them — we must enumerate per key.
"""
import json, sys, time, urllib.request, urllib.error
from concurrent.futures import ThreadPoolExecutor, as_completed
from pathlib import Path

sys.path.insert(0, str(Path(__file__).resolve().parent))
from verify_cache import CachedVerifier

BASE = "https://maas-api.cn-huabei-1.xf-yun.com/v1"
OUT = Path("results/iflytek_maas_smart")
OUT.mkdir(parents=True, exist_ok=True)


def http(method, path, key, body=None, timeout=20):
    url = BASE + path
    headers = {"Authorization": f"Bearer {key}", "Accept": "application/json"}
    data = None
    if body is not None:
        data = json.dumps(body).encode()
        headers["Content-Type"] = "application/json"
    req = urllib.request.Request(url, data=data, headers=headers, method=method)
    try:
        with urllib.request.urlopen(req, timeout=timeout) as r:
            return r.getcode(), r.read().decode("utf-8", "replace")
    except urllib.error.HTTPError as e:
        try:
            return e.code, e.read().decode("utf-8", "replace")
        except Exception:
            return e.code, ""
    except Exception as e:
        return 0, f"net:{type(e).__name__}"


def verify(key):
    # 1. enumerate granted models
    code, body = http("GET", "/models", key)
    if code == 401:
        return "DEAD", f"401 {body[:140]}"
    models = []
    if code == 200:
        try:
            data = json.loads(body)
            models = [m.get("id") for m in data.get("data", []) if m.get("id")]
        except Exception:
            pass
    if not models:
        # fallback list
        models = ["xop3qwen1b7", "xopglm5", "xopkimik26", "xsparkx2flash",
                  "generalv3.5", "4.0Ultra", "xqwen257bchat", "xdeepseekv3"]
    # 2. try chat against each granted model
    last = "no model tried"
    for model in models[:12]:
        cc, cb = http("POST", "/chat/completions", key, {
            "model": model,
            "messages": [{"role": "user", "content": "reply ok"}],
            "max_tokens": 8, "temperature": 0.01,
        })
        bl = (cb or "").lower()
        if cc == 200 and '"choices"' in bl:
            # extract content snippet
            try:
                j = json.loads(cb)
                content = (j["choices"][0].get("message", {}).get("content")
                           or "")[:60]
            except Exception:
                content = ""
            return "USABLE", f"{model} 200 {content}"
        if cc == 401:
            return "DEAD", f"{model} 401 {cb[:140]}"
        if cc in (402, 429):
            return "NO_BALANCE", f"{model} {cc} {cb[:140]}"
        # 403/400 with "无权使用模型" = model not granted, try next
        if cc in (400, 403, 404) and ("无权" in cb or "not found" in bl
                                        or "model" in bl or "forbidden" in bl):
            last = f"{model} {cc}: {cb[:120]}"
            continue
        if cc == 0:
            last = f"{model} net: {cb[:120]}"
            continue
        last = f"{model} {cc}: {cb[:140]}"
    return "NO_ACCESS", last


def load_keys():
    """Load all iflytek_maas candidate keys from candidates.tsv + bucket files."""
    keys = {}
    root = Path("results/all_deep")
    # from dead/unknown buckets (prov<TAB>key format, possibly concatenated)
    for fn in ("dead.txt", "unknown.txt", "no_access.txt", "no_balance.txt",
               "usable.txt"):
        p = root / fn
        if not p.exists():
            continue
        for ln in p.read_text(errors="replace").splitlines():
            parts = ln.split("\t")
            if len(parts) < 3:
                continue
            prov, key, url = parts[0], parts[1], parts[2]
            if not key.startswith("sk-") and prov.startswith("iflytek_maas"):
                # prov might be "iflytek_maassk-..." (concatenation bug)
                m = __import__("re").match(r"^(iflytek_maas)(sk-.+)$", prov)
                if m:
                    prov, key = m.group(1), m.group(2)
            if prov == "iflytek_maas" and key.startswith("sk-"):
                keys.setdefault(key, url)
    return keys


def main():
    keys = load_keys()
    print(f"iflytek_maas candidate keys: {len(keys)}", flush=True)
    buckets = {"USABLE": [], "NO_BALANCE": [], "NO_ACCESS": [],
               "UNKNOWN": [], "DEAD": []}
    with CachedVerifier("iflytek_maas_smart", verify, force=True) as ver:
        with ThreadPoolExecutor(max_workers=24) as pool:
            futs = {pool.submit(ver, k): (k, s) for k, s in keys.items()}
            done = 0
            for fut in as_completed(futs):
                k, s = futs[fut]; done += 1
                try:
                    v, d = fut.result()
                except Exception as e:
                    v, d = "UNKNOWN", f"exc:{e}"
                buckets[v].append((k, s, d))
                if done % 25 == 0:
                    print(f"  {done}/{len(keys)} usable={len(buckets['USABLE'])} "
                          f"dead={len(buckets['DEAD'])}", flush=True)
    for label, rows in buckets.items():
        with (OUT / f"{label.lower()}.txt").open("w") as f:
            for k, s, d in rows:
                f.write(f"{k}\t{s}\t{d}\n")
    print("\n=== IFLYTEK MAAS SMART RESULTS ===")
    for label in buckets:
        print(f"  {label:11s}: {len(buckets[label])}")
    for k, s, d in buckets["USABLE"]:
        print(f"  ✅ {k}")
        print(f"     {s}")
        print(f"     {d[:140]}")


if __name__ == "__main__":
    main()