例を使った重要度基準

system = (
    "You are a code reviewer. "
    "Rate each issue as Critical, High, Medium, or Low. "
    "Be precise and only report important problems."
)

# Problem: 'important', 'precise', and the four levels are
# never defined. The bar is whatever the model infers today.

CRITICAL = """
Critical: causes data loss, a security breach, or a
production crash. Always report, even if low-confidence.

Example (SQL injection):
    query = f"SELECT * FROM users WHERE id = {user_input}"
    db.execute(query)
Why: user_input is interpolated unescaped -> injectable.
"""

HIGH = """
High: produces incorrect results or a test failure, but
does not breach security or crash production.

Example (off-by-one):
    for i in range(len(items) - 1):
        process(items[i])     # last item never processed
Why: range stops one element early; silent wrong output.
"""

MEDIUM = """
Medium: reliability or maintainability risk, not yet a bug.
Example:
    requests.get(url)        # no timeout -> can hang forever
"""

LOW = """
Low: style or naming only, no behavioral impact.
Example:
    def calc(x): return x*2  # name 'calc' is unclear
"""

import anthropic

client = anthropic.Anthropic()

system = [{
    "type": "text",
    "text": "You are a code reviewer.\n"
            + CRITICAL + HIGH + MEDIUM + LOW
            + "\nAssign exactly one level per finding using the\n"
              "rules and examples above. When unsure between two\n"
              "levels, pick the lower one.",
    "cache_control": {"type": "ephemeral"},
}]

finding_schema = {
    "type": "object",
    "properties": {
        "line": {"type": "integer"},
        "severity": {
            "type": "string",
            "enum": ["critical", "high", "medium", "low"],
        },
        "rule": {"type": "string"},
        "suggested_fix": {"type": "string"},
    },
    "required": ["line", "severity", "rule"],
    "additionalProperties": False,
}

resp = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=4096,
    thinking={"type": "adaptive"},
    system=system,                      # cached rubric prefix
    output_config={
        "format": {
            "type": "json_schema",
            "schema": {
                "type": "object",
                "properties": {"findings": {
                    "type": "array", "items": finding_schema}},
                "required": ["findings"],
                "additionalProperties": False,
            },
        }
    },
    messages=[{"role": "user", "content": diff_text}],
)

import json

findings = json.loads(resp.content[0].text)["findings"]

BLOCKING = {"critical", "high"}
blockers = [f for f in findings if f["severity"] in BLOCKING]

if blockers:
    print(f"BLOCK MERGE: {len(blockers)} issue(s)")
    raise SystemExit(1)
print("OK to merge (medium/low only)")