合同审查辅助

import difflib
import json
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.tutujin.com/v1", api_key=os.environ["TUTUJIN_API_KEY"])

# The company playbook, written by your legal team: one entry per rule.
PLAYBOOK = [
    {"id": "LIAB-1", "topic": "limitation of liability", "standard": "Our total liability is capped at the contract value.", "red_line": "Unlimited liability for us."},
    {"id": "PAY-1", "topic": "payment terms", "standard": "We pay within 30 days of a valid invoice.", "red_line": "Payment due in under 15 days or prepayment over 30%."},
    {"id": "TERM-1", "topic": "termination", "standard": "Either party may terminate with 30 days of written notice.", "red_line": "Only the other party may terminate for convenience."},
]
RULES = "Playbook:\n" + json.dumps(PLAYBOOK, ensure_ascii=False)


def ask(system, user):
    resp = client.chat.completions.create(
        model="claude-sonnet-5-5",
        messages=[{"role": "system", "content": system + "\n\n" + RULES}, {"role": "user", "content": user}],
        temperature=0,
    )
    return resp.choices[0].message.content


def review(contract):
    raw = ask(
        "You help a company lawyer review contracts against the playbook. For every clause that departs from a rule "
        "or crosses a red line, and for every playbook topic the contract does not cover, return one finding. "
        'Reply with JSON only: {"findings": [{"rule_id": "", "clause": "clause number", "quote": "exact words copied '
        'from the contract, empty if missing", "risk": "high|medium|low", "reason": "", "suggestion": ""}]}. '
        "Do not give legal advice; the lawyer decides.",
        contract,
    )
    findings = json.loads(raw[raw.find("{"): raw.rfind("}") + 1])["findings"]
    for f in findings:
        # a quote that cannot be found in the contract must be checked by the lawyer, never trusted
        f["quote_found"] = f["quote"] == "" or f["quote"] in contract
    return findings


def explain_changes(old, new):
    """Diff in code first, so the model only reads the paragraphs that changed."""
    a, b = old.splitlines(), new.splitlines()
    changes = [
        "BEFORE:\n" + "\n".join(a[i1:i2]) + "\nAFTER:\n" + "\n".join(b[j1:j2])
        for op, i1, i2, j1, j2 in difflib.SequenceMatcher(None, a, b).get_opcodes()
        if op != "equal"
    ]
    return ask(
        "For each change, say in one or two sentences what changed, which party it favours "
        "and which playbook rule it touches, if any.",
        "\n\n".join(changes),
    )


with open("contract_v1.txt", encoding="utf-8") as f1, open("contract_v2.txt", encoding="utf-8") as f2:
    v1, v2 = f1.read(), f2.read()
for item in review(v2):
    print(item["risk"], item["rule_id"], item["clause"], "" if item["quote_found"] else "QUOTE NOT FOUND - check by hand")
print(explain_changes(v1, v2))