番号が世代を表さなくなった — モデルIDを正規表現で分解する集計を作り直した記録

# latest_probe.py — 「最新を選ぶ」の3実装を突き合わせる
import re
 
CANDIDATES = ["gemini-3.5-pro", "gemini-3.6-flash",
              "gemini-3.10-flash", "gemini-3.5-flash-lite"]
 
print("[1] lexicographic max()      ->", max(CANDIDATES))
 
def numkey(m):
    x = re.search(r"(\d+)\.(\d+)", m)
    return (int(x.group(1)), int(x.group(2))) if x else (0, 0)
 
print("[2] numeric (major,minor) max ->", max(CANDIDATES, key=numkey))
print("[3] float(version) max        ->",
      max(CANDIDATES, key=lambda m: float(re.search(r"(\d+\.\d+)", m).group(1))))
 
print()
print("float('3.10') =", float("3.10"), " float('3.6') =", float("3.6"),
      "->", float("3.10") > float("3.6"))
print("'3.10' > '3.6' (str) =", "3.10" > "3.6")

[1] lexicographic max()      -> gemini-3.6-flash
[2] numeric (major,minor) max -> gemini-3.10-flash
[3] float(version) max        -> gemini-3.6-flash
 
float('3.10') = 3.1  float('3.6') = 3.6 -> False
'3.10' > '3.6' (str) = False

# attribution.py — 正規表現派生とレジストリ結合を突き合わせる
import re, sqlite3
 
con = sqlite3.connect(":memory:")
con.executescript("""
CREATE TABLE usage_fact (day TEXT, model_id TEXT, calls INT, in_tok INT, out_tok INT);
CREATE TABLE model_registry (
  model_id TEXT PRIMARY KEY, family TEXT, generation TEXT, tier TEXT, modality TEXT
);
""")
 
rows = [
    ("2026-07-01", "gemini-3.5-flash",            9800, 4_900_000, 980_000),
    ("2026-07-01", "gemini-3.5-flash-lite",      41000, 8_200_000, 410_000),
    ("2026-07-01", "gemini-3.1-flash-lite-image", 2600,   520_000,  26_000),
    ("2026-07-01", "gemini-3.5-pro",               420, 1_260_000, 336_000),
    ("2026-07-22", "gemini-3.6-flash",            9100, 4_550_000, 755_000),
    ("2026-07-22", "gemini-3.5-flash-lite",      40500, 8_100_000, 405_000),
    ("2026-07-22", "gemini-3.1-flash-lite-image", 2700,   540_000,  27_000),
    ("2026-07-22", "gemini-3.5-pro",               400, 1_200_000, 320_000),
    ("2026-07-22", "gemini-omni-flash",             90,    45_000,  18_000),
]
con.executemany("INSERT INTO usage_fact VALUES (?,?,?,?,?)", rows)
 
reg = [
    ("gemini-3.5-flash",            "flash",      "3.5", "flash",      "text"),
    ("gemini-3.6-flash",            "flash",      "3.6", "flash",      "text"),
    ("gemini-3.5-flash-lite",       "flash-lite", "3.5", "flash-lite", "text"),
    ("gemini-3.5-pro",              "pro",        "3.5", "pro",        "text"),
    ("gemini-3.1-flash-lite-image", "image",      "3.1", "flash-lite", "image"),
    ("gemini-omni-flash",           "omni",       "n/a", "omni",       "video"),
]
con.executemany("INSERT INTO model_registry VALUES (?,?,?,?,?)", reg)
 
PAT = re.compile(r"^gemini-(\d+)\.(\d+)-([a-z]+)")
 
def derive(mid):
    h = PAT.match(mid)
    return (f"{h.group(1)}.{h.group(2)}", h.group(3)) if h else ("unknown", "unknown")
 
print(f"{'tier(regex)':<14}{'out_tok':>12} | {'tier(registry)':<16}{'out_tok':>12}")
a = {}
for mid, out in con.execute("SELECT model_id, SUM(out_tok) FROM usage_fact GROUP BY model_id"):
    k = derive(mid)[1]
    a[k] = a.get(k, 0) + out
b = dict(con.execute("""SELECT r.tier, SUM(f.out_tok) FROM usage_fact f
                        JOIN model_registry r USING(model_id) GROUP BY r.tier"""))
for k in sorted(set(a) | set(b)):
    print(f"{k:<14}{a.get(k,0):>12,} | {k:<16}{b.get(k,0):>12,}")

tier(regex)        out_tok | tier(registry)       out_tok
flash            2,603,000 | flash              1,735,000
flash-lite               0 | flash-lite           868,000
omni                     0 | omni                  18,000
pro                656,000 | pro                  656,000
unknown             18,000 | unknown                    0

  gemini-3.1-flash-lite-image       53,000  (  2.0% of regex 'flash')
  gemini-3.5-flash                 980,000  ( 37.6% of regex 'flash')
  gemini-3.5-flash-lite            815,000  ( 31.3% of regex 'flash')
  gemini-3.6-flash                 755,000  ( 29.0% of regex 'flash')

# effect.py — 切替効果を2つの束ね方で測る
def per_call(day, pred):
    c = o = 0
    for mid, cl, ot in con.execute(
            "SELECT model_id, calls, out_tok FROM usage_fact WHERE day=?", (day,)):
        if pred(mid):
            c += cl
            o += ot
    return o / c if c else 0
 
regex_flash = lambda m: (PAT.match(m).group(3) if PAT.match(m) else None) == "flash"
reg_flash   = lambda m: m in ("gemini-3.5-flash", "gemini-3.6-flash")
 
for label, pred in (("regex tier='flash'", regex_flash),
                    ("registry tier='flash'", reg_flash)):
    b, a = per_call("2026-07-01", pred), per_call("2026-07-22", pred)
    print(f"{label:<24} out_tok/call {b:7.2f} -> {a:7.2f}   ({(a-b)/b*100:+5.1f}%)")

regex tier='flash'       out_tok/call   26.52 ->   22.70   (-14.4%)
registry tier='flash'    out_tok/call  100.00 ->   82.97   (-17.0%)

CREATE TABLE model_registry (
  model_id    TEXT NOT NULL,
  generation  TEXT NOT NULL,
  tier        TEXT NOT NULL,
  modality    TEXT NOT NULL,
  shutdown_on TEXT,
  valid_from  TEXT NOT NULL,
  valid_to    TEXT,
  PRIMARY KEY (model_id, valid_from)
);
 
SELECT r.tier, SUM(f.out_tok) AS out_tok
FROM usage_fact f
JOIN model_registry r
  ON r.model_id = f.model_id
 AND f.day >= r.valid_from
 AND (r.valid_to IS NULL OR f.day < r.valid_to)
GROUP BY r.tier;

from dataclasses import dataclass
 
@dataclass(frozen=True)
class ModelFacts:
    generation: str
    tier: str
    modality: str
    known: bool
 
UNKNOWN = ModelFacts("unknown", "unknown", "unknown", known=False)
 
def resolve(model_id: str, registry: dict[str, ModelFacts]) -> ModelFacts:
    facts = registry.get(model_id)
    if facts is None:
        # 近い名前に丸めない。丸めた瞬間に、誤りが正しい値の顔をする
        return UNKNOWN
    return facts