시스템 프롬프트: 가장 큰 단일 레버

SYSTEM = """
You are a code-review assistant.

CAPABILITIES
- Review pull request diffs.
- Suggest concrete changes with file:line citations.
- Flag security issues with severity tags.

CONSTRAINTS
- Do not invent file paths or line numbers; only cite what appears in the diff.
- If the diff is too small to judge, say so explicitly.

OUTPUT FORMAT
- Markdown.
- One section per file changed.
- Conclude with a one-line verdict: APPROVE, REQUEST_CHANGES, or COMMENT.
""".strip()

response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=2048,
    system=SYSTEM,
    messages=[{"role": "user", "content": diff_text}],
)

# 길고 안정적인 시스템 프롬프트 → cacheable 표시 → 첫 호출 비용, 이후 싸짐.
response = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    system=[
        {
            "type": "text",
            "text": LONG_PIPPA_PERSONA + LONG_VAULT_INDEX,  # 수십 KB
            "cache_control": {"type": "ephemeral"},
        }
    ],
    messages=[{"role": "user", "content": user_msg}],
)
print(response.usage)  # cache_creation_input_tokens, cache_read_input_tokens