qiaoqichaoandClaude Code
b5feee6982
T07 是"预审执行"大卡，按纪律拆子卡。本批为第一块：纯确定性的结论校验， 不调用任何模型、不计算概率。覆盖 AC-05/06/07/09/12/45 与 BR-05/06/07/12。 新增 services/prescreen_policy.py： - decide()：四级优先（hard_block → critical_incomplete → open_findings → clean）， 优先级顺序即业务口径，改动等于改结论，已显式标注 - **硬性阻断不可覆盖**：命中 hard 规则即 stop，并指出规则版本、保留模型原始 结构化提案供审计；专项模型的正面单题判断不能翻盘（有专门反例） - **未知不等于风险也不等于通过**：关键核查不可完成给 insufficient_information 并列出未完成项，findings 的 result 原样保留、**不得被改写成 issue** - **没有 second path 给概率**：probability() 不接受任何入参，模型分数无法顺手传入； native_metrics 里名为 probability 的指标会被 assert_no_probability_leak 拦下， self_reported 置信度可入档但不得变概率 - stop 明确不触碰正式审批（AC-45），预算耗尽按 E-08 列未完成项而非伪造完成 实现中修正了两处自己的测试写法：断言"不含高风险三字"会被免责说明本身命中； 断言 open_findings 为空与"unknown 属待处理"的定义矛盾。两处都改成检验真正的 不变量（结论非风险判定 + findings 不被改写）。 测试：新增 test_prescreen_policy.py 19 项。全量 368 项 OK（349 → 368）； verify.py 10/10 PASS。 Co-Authored-By: Claude Code <noreply@anthropic.com>
157 lines
7.7 KiB
Python
157 lines
7.7 KiB
Python
"""T07-a 预审结果约束测试：AC-05/06/07/09/12/45。
|
|
|
|
每条规则都配反例——只测"正常给出 advance"证明不了约束存在。
|
|
本模块纯确定性，不调用模型、不算概率。
|
|
"""
|
|
|
|
import unittest
|
|
|
|
from services import prescreen_policy as policy
|
|
|
|
|
|
def finding(code, result, basis_version=None, **over):
|
|
item = {"code": code, "title": f"检查项 {code}", "result": result}
|
|
if basis_version:
|
|
item["basis_version"] = basis_version
|
|
item.update(over)
|
|
return item
|
|
|
|
|
|
class HardBlockTests(unittest.TestCase):
|
|
def test_hard_block_forces_stop(self):
|
|
result = policy.decide([finding("lease.coverage.below", "issue")],
|
|
hard_rule_codes=["lease.coverage.below"],
|
|
critical_check_ids=["lease.coverage.below"])
|
|
self.assertEqual(result["recommendation"], "stop")
|
|
self.assertEqual(result["stage"], "hard_block")
|
|
|
|
def test_hard_block_cites_the_rule_version(self):
|
|
result = policy.decide([finding("r.hard", "issue", basis_version="rule.credit@v3")],
|
|
hard_rule_codes=["r.hard"])
|
|
self.assertIn("rule.credit@v3", result["recommendation_reason"])
|
|
|
|
def test_positive_single_judgment_cannot_override_a_hard_block(self):
|
|
# AC-05 / BR-05：单题正面判断不能覆盖综合意见
|
|
judgments = [{"question_id": "q1", "status": "completed",
|
|
"answer": {"kind": "choice", "value": "supported"}}]
|
|
result = policy.decide([finding("r.hard", "issue")], hard_rule_codes=["r.hard"],
|
|
judgments=judgments)
|
|
self.assertEqual(result["recommendation"], "stop")
|
|
self.assertFalse(result["judgment_can_override"])
|
|
self.assertEqual(result["judgments"], judgments, "判断仍应入档供审计")
|
|
|
|
def test_hard_block_beats_insufficient_information(self):
|
|
result = policy.decide(
|
|
[finding("r.hard", "issue"), finding("k1", "unknown")],
|
|
hard_rule_codes=["r.hard"], critical_check_ids=["k1"])
|
|
self.assertEqual(result["recommendation"], "stop")
|
|
|
|
def test_block_does_not_touch_formal_approval(self):
|
|
# AC-45：stop 只表示暂不建议推进，系统不得自动关闭项目或审批
|
|
result = policy.decide([finding("r.hard", "issue")], hard_rule_codes=["r.hard"])
|
|
self.assertFalse(result["formal_approval_touched"])
|
|
self.assertIn("暂不建议推进", result["recommendation_reason"])
|
|
|
|
def test_advisory_code_is_not_a_hard_block(self):
|
|
result = policy.decide([finding("r.advisory", "issue")],
|
|
hard_rule_codes=["r.hard"])
|
|
self.assertNotEqual(result["recommendation"], "stop")
|
|
|
|
|
|
class InsufficientInformationTests(unittest.TestCase):
|
|
def test_incomplete_critical_check_never_becomes_high_risk(self):
|
|
# AC-07 / BR-07：全部关键资料缺失时给信息不足，**不判高风险**
|
|
result = policy.decide([finding("k1", "unknown"), finding("k2", "unknown")],
|
|
critical_check_ids=["k1", "k2"])
|
|
self.assertEqual(result["recommendation"], "insufficient_information")
|
|
# 要求不是"别出现高风险三个字"（免责说明本身就会写到它），而是：
|
|
# 结论不能变成风险判定，且不得凭空生成"高风险"这类 finding
|
|
self.assertIn("不得据此判定企业高风险", result["recommendation_reason"])
|
|
self.assertNotEqual(result["recommendation"], "stop")
|
|
# 缺证可以（也应该）出现在待处理列表里，但**不得被改写成风险问题**：
|
|
# findings 数量与 result 取值必须原样保留，不能凭空多出 issue
|
|
self.assertEqual(len(result["findings"]), 2)
|
|
self.assertTrue(all(item["result"] == "unknown" for item in result["findings"]))
|
|
self.assertFalse(any(item["result"] == "issue" for item in result["open_findings"]))
|
|
|
|
def test_missing_inputs_include_the_incomplete_critical_checks(self):
|
|
result = policy.decide([finding("k1", "unknown")], critical_check_ids=["k1"],
|
|
missing_inputs=["现金流材料"])
|
|
self.assertEqual(result["missing_inputs"], ["k1", "现金流材料"])
|
|
|
|
def test_execution_failure_counts_as_incomplete(self):
|
|
result = policy.decide([finding("k1", "error")], critical_check_ids=["k1"])
|
|
self.assertEqual(result["recommendation"], "insufficient_information")
|
|
|
|
def test_non_critical_unknown_does_not_force_insufficient(self):
|
|
# 非关键项的未知只要求补件，不阻断成信息不足
|
|
result = policy.decide([finding("other", "unknown")], critical_check_ids=["k1"])
|
|
self.assertEqual(result["recommendation"], "supplement")
|
|
|
|
|
|
class SupplementAndAdvanceTests(unittest.TestCase):
|
|
def test_open_issue_leads_to_supplement(self):
|
|
result = policy.decide([finding("c1", "issue")])
|
|
self.assertEqual(result["recommendation"], "supplement")
|
|
|
|
def test_clean_run_advances_but_does_not_approve(self):
|
|
result = policy.decide([finding("c1", "pass")])
|
|
self.assertEqual(result["recommendation"], "advance")
|
|
self.assertIn("正式审批仍由业务流程决定", result["recommendation_reason"])
|
|
|
|
def test_no_findings_at_all_is_treated_as_clean(self):
|
|
result = policy.decide([])
|
|
self.assertEqual(result["stage"], "clean")
|
|
self.assertEqual(result["open_findings"], [])
|
|
|
|
|
|
class DegradationTests(unittest.TestCase):
|
|
def test_degradations_are_preserved_not_swallowed(self):
|
|
result = policy.decide([finding("c1", "pass")],
|
|
degradations=[{"code": "JUDGMENT_UNAVAILABLE",
|
|
"message": "专项核查未完成"}])
|
|
self.assertEqual(len(result["degradations"]), 1)
|
|
|
|
def test_budget_exhaustion_reports_unfinished_not_success(self):
|
|
# E-08：耗尽即停止并列未完成，不伪造完成
|
|
item = policy.budget_exhausted()
|
|
self.assertEqual(item["code"], "RUN_BUDGET_EXCEEDED")
|
|
self.assertFalse(item["retryable"])
|
|
self.assertIn("未完成项", item["message"])
|
|
|
|
|
|
class ProbabilityGateTests(unittest.TestCase):
|
|
def test_probability_is_always_null_with_a_reason(self):
|
|
for findings in ([], [finding("c1", "pass")], [finding("c1", "issue")]):
|
|
with self.subTest(findings=len(findings)):
|
|
result = policy.decide(findings)
|
|
self.assertIsNone(result["probability"]["value"])
|
|
self.assertEqual(result["probability"]["reason"], "not_calibrated")
|
|
|
|
def test_probability_takes_no_input_so_a_model_score_cannot_leak_in(self):
|
|
with self.assertRaises(TypeError):
|
|
policy.probability(0.93)
|
|
|
|
def test_native_metric_named_probability_is_rejected(self):
|
|
# BR-12 / AC-18：厂商原生指标不得被当作审批概率
|
|
result = policy.decide(
|
|
[finding("c1", "pass")],
|
|
judgments=[{"question_id": "q1", "status": "completed",
|
|
"native_metrics": [{"name": "probability", "value": 0.91}]}])
|
|
with self.assertRaises(ValueError) as ctx:
|
|
policy.assert_no_probability_leak(result)
|
|
self.assertIn("不得被当作审批概率", str(ctx.exception))
|
|
|
|
def test_self_reported_confidence_does_not_become_probability(self):
|
|
result = policy.decide(
|
|
[finding("c1", "pass")],
|
|
judgments=[{"question_id": "q1", "status": "completed",
|
|
"native_metrics": [{"name": "confidence", "value": 0.99,
|
|
"source": "self_reported"}]}])
|
|
policy.assert_no_probability_leak(result) # 可以入档，但不得变概率
|
|
self.assertIsNone(result["probability"]["value"])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|