Claude API でApp Storeの多言語ストア掲載情報を文字数制限つきで生成する

import anthropic
import json
 
client = anthropic.Anthropic()  # ANTHROPIC_API_KEY は環境変数から読み込みます
 
SYSTEM_RULES = (
    "あなたはApp Storeのローカライズ担当です。各フィールドの文字数上限を厳守してください。"
    "上限はコードポイント単位で数えます（全角も1文字）。"
    "keywords はカンマ区切りでスペースを入れず、App名と重複する語は避け、複数形と単数形を両方入れないでください。"
)
 
def build_tool(limits):
    return {
        "name": "emit_listing",
        "description": "ローカライズ済みのApp Store掲載メタデータを返す",
        "input_schema": {
            "type": "object",
            "properties": {
                "name": {"type": "string", "maxLength": limits["name"]},
                "subtitle": {"type": "string", "maxLength": limits["subtitle"]},
                "keywords": {"type": "string", "maxLength": limits["keywords"]},
                "promotional_text": {"type": "string", "maxLength": limits["promotional_text"]},
            },
            "required": ["name", "subtitle", "keywords", "promotional_text"],
        },
    }
 
def generate_listing(locale, source, glossary, limits):
    tool = build_tool(limits)
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
        tools=[tool],
        tool_choice={"type": "tool", "name": "emit_listing"},
        system=[
            {"type": "text", "text": SYSTEM_RULES},
            {"type": "text", "text": glossary, "cache_control": {"type": "ephemeral"}},
        ],
        messages=[{
            "role": "user",
            "content": f"対象ロケール: {locale}\n元の英語掲載情報:\n{json.dumps(source, ensure_ascii=False)}",
        }],
    )
    for block in resp.content:
        if block.type == "tool_use":
            return block.input
    raise RuntimeError("構造化出力が返りませんでした")

def count_chars(s):
    # App Store は概ね Unicode コードポイント単位で数えます。
    # 日本語の全角も1文字として扱われます（バイト数ではありません）。
    return len(s)
 
def validate(listing, limits):
    problems = []
    for field, limit in limits.items():
        value = listing.get(field, "")
        n = count_chars(value)
        if n > limit:
            problems.append({"field": field, "count": n, "limit": limit, "over": n - limit})
    # キーワード固有のルール（スペース入りは文字数の無駄）
    kw = listing.get("keywords", "")
    if ", " in kw or " ," in kw:
        problems.append({"field": "keywords", "count": count_chars(kw), "limit": limits["keywords"], "over": 0})
    return problems

def compress_fields(locale, listing, problems, limits):
    hint = "; ".join(
        f'{p["field"]} は {p["count"]}文字。あと{p["over"]}文字削って上限{p["limit"]}に収めてください'
        for p in problems if p["over"] > 0
    )
    tool = build_tool(limits)
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=512,
        tools=[tool],
        tool_choice={"type": "tool", "name": "emit_listing"},
        system=[{"type": "text", "text": SYSTEM_RULES}],
        messages=[{
            "role": "user",
            "content": (
                f"対象ロケール: {locale}\n現在の案: {json.dumps(listing, ensure_ascii=False)}\n"
                f"次の超過を解消してください（意味は保つこと）: {hint}"
            ),
        }],
    )
    for block in resp.content:
        if block.type == "tool_use":
            return block.input
    return listing
 
def generate_with_repair(locale, source, glossary, limits, max_retries=2):
    listing = generate_listing(locale, source, glossary, limits)
    for _ in range(max_retries):
        problems = validate(listing, limits)
        if not problems:
            return listing
        listing = compress_fields(locale, listing, problems, limits)
    return hard_truncate(listing, limits)  # 最後の砦：機械的に詰める
 
def hard_truncate(listing, limits):
    out = dict(listing)
    for field, limit in limits.items():
        if count_chars(out.get(field, "")) > limit:
            out[field] = out[field][:limit].rstrip("、,・ ")
    return out

def normalize_keywords(raw, app_name, limit=100):
    seen, kept = set(), []
    banned = {w.lower() for w in app_name.replace(",", " ").split()}
    for term in raw.replace("、", ",").split(","):
        t = term.strip()
        key = t.lower()
        if not t or key in seen or key in banned:
            continue  # 空・重複・App名と被る語は捨てる
        candidate = ",".join(kept + [t])  # スペースなしで連結して長さを確認
        if count_chars(candidate) > limit:
            continue  # 入れると上限を超える語はスキップ
        seen.add(key)
        kept.append(t)
    return ",".join(kept)