Flash の返事の調子が変わった朝、最初に見るのは自分のプロンプトではありません

import json
import os
import time
import urllib.error
import urllib.request
 
BASE = "https://generativelanguage.googleapis.com/v1beta"
REQUESTED = os.environ.get("GEMINI_MODEL", "gemini-3.7-flash")  # 自分のコードに書いているモデル ID
LOG = "canary_log.jsonl"
 
# 普段の用途に近い短い入力を 3 本だけ。長さと形式が見えれば十分です。
PROMPTS = {
    "reply_draft": "星 2 のレビュー「広告が多い」に、丁寧な返信を 3 文で書いてください。",
    "json_shape": 'JSON だけで答えてください。キーは "tone" と "reason"。文面: 「ありがとう、助かりました」',
    "short_answer": "壁紙アプリの通知は何時に送ると開封されやすいですか。1 文で。",
}
 
 
def call(prompt, key):
    body = json.dumps({
        "contents": [{"parts": [{"text": prompt}]}],
        "generationConfig": {"maxOutputTokens": 256, "temperature": 0},
    }).encode()
    req = urllib.request.Request(
        f"{BASE}/models/{REQUESTED}:generateContent",
        data=body, method="POST",
        headers={"Content-Type": "application/json", "x-goog-api-key": key},
    )
    try:
        with urllib.request.urlopen(req, timeout=30) as r:
            return r.status, json.load(r)
    except urllib.error.HTTPError as e:
        return e.code, {"error": e.read().decode()[:300]}
 
 
def summarize(label, status, resp):
    """レスポンス 1 件を、後で突き合わせる 1 行に畳む。"""
    cand = (resp.get("candidates") or [{}])[0]
    parts = (cand.get("content") or {}).get("parts") or [{}]
    text = parts[0].get("text", "")
    served = resp.get("modelVersion", "(none)")  # 実際に応答したモデル
    try:
        json.loads(text.strip().removeprefix("```json").removesuffix("```").strip())
        json_ok = True
    except ValueError:
        json_ok = False
    return {
        "ts": time.strftime("%Y-%m-%dT%H:%M:%S"),
        "label": label, "status": status,
        "requested": REQUESTED, "served": served,
        "routed": served != REQUESTED and served != "(none)",
        "chars": len(text), "json_ok": json_ok,
        "finish": cand.get("finishReason", "(none)"),
    }
 
 
def last_two_runs(path=LOG):
    rows = [json.loads(l) for l in open(path, encoding="utf-8")]
    labels = sorted({r["label"] for r in rows})
    out = {}
    for lb in labels:
        mine = [r for r in rows if r["label"] == lb]
        if len(mine) >= 2:
            out[lb] = (mine[-2], mine[-1])
    return out
 
 
def report(path=LOG):
    for lb, (a, b) in last_two_runs(path).items():
        notes = []
        if a["served"] != b["served"]:
            notes.append(f"served {a['served']} -> {b['served']}")
        if a["json_ok"] != b["json_ok"]:
            notes.append(f"json_ok {a['json_ok']} -> {b['json_ok']}")
        if a["chars"] and abs(b["chars"] - a["chars"]) / a["chars"] > 0.5:
            notes.append(f"chars {a['chars']} -> {b['chars']}")
        print(f"{lb:<13}", "; ".join(notes) if notes else "変化なし")
 
 
if __name__ == "__main__":
    key = os.environ["GEMINI_API_KEY"]
    with open(LOG, "a", encoding="utf-8") as f:
        for label, prompt in PROMPTS.items():
            status, resp = call(prompt, key)
            row = summarize(label, status, resp)
            f.write(json.dumps(row, ensure_ascii=False) + "\n")
            print(row["label"], row["status"], row["requested"], "->", row["served"])
    report()

json_shape    served gemini-3.7-flash -> gemini-3.8-flash; chars 25 -> 87