51 lines
1.7 KiB
Python
51 lines
1.7 KiB
Python
from __future__ import annotations
|
|
|
|
import argparse
|
|
import json
|
|
import ssl
|
|
import time
|
|
import urllib.request
|
|
|
|
|
|
def _json_request(url: str, method: str = "GET", payload: dict | None = None, timeout: int = 30) -> dict:
|
|
body = None if payload is None else json.dumps(payload, ensure_ascii=False).encode("utf-8")
|
|
req = urllib.request.Request(url=url, method=method, data=body)
|
|
if payload is not None:
|
|
req.add_header("Content-Type", "application/json")
|
|
ctx = ssl._create_unverified_context() if url.startswith("https://") else None
|
|
with urllib.request.urlopen(req, timeout=timeout, context=ctx) as resp:
|
|
return json.loads(resp.read().decode("utf-8"))
|
|
|
|
|
|
def main() -> None:
|
|
parser = argparse.ArgumentParser(description="Long-run stability test")
|
|
parser.add_argument("--base-url", default="https://127.0.0.1:8080")
|
|
parser.add_argument("--minutes", type=int, default=60)
|
|
parser.add_argument("--interval-sec", type=int, default=30)
|
|
args = parser.parse_args()
|
|
|
|
end_ts = time.time() + args.minutes * 60
|
|
rounds = 0
|
|
while time.time() < end_ts:
|
|
rounds += 1
|
|
data = _json_request(
|
|
f"{args.base_url}/chat/text",
|
|
method="POST",
|
|
payload={"text": f"长稳测试第{rounds}轮，请简短回复。"},
|
|
timeout=60,
|
|
)
|
|
health = _json_request(f"{args.base_url}/health")
|
|
print(
|
|
f"round={rounds} ok={data.get('ok')} "
|
|
f"last_latency={health.get('last_latency_ms')} "
|
|
f"llm={health.get('last_llm_latency_ms')} "
|
|
f"tts={health.get('last_tts_latency_ms')}"
|
|
)
|
|
time.sleep(args.interval_sec)
|
|
|
|
print("longrun done, rounds:", rounds)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|