zizi c9f69d9d6d 治理: Skill 测试治理第一阶段——harness 控制平面 + 实现测试迁出运行时目录
范围(不含 design-story-foundation、docs/、humanization/README.md 等进行中改动):

1. 新增 harness/ 控制平面
   - skill_harness.py 静态审计:32 个运行时 Skill 的 frontmatter/manifest/文档污染,当前 0 问题
   - run_selected.py 选择性执行器:manifest 与磁盘一一对账、依赖阻断、
     空跑与 skip-only 失败关闭、AST 测试形状门
   - manifests/skills.json:32 个 Skill 的合同责任方与协作领域登记
   - manifests/test-inventory.json:81 个测试资产登记
   - specs/skill-testing.md 与 README.md:测试分层、证据边界与 harness 职责

2. 实现测试从 .claude/skills/*/scripts/ 迁至 tests/skills/<skill>/
   - 71 个测试文件迁移并修复项目根与临时目录运行导入
   - 数据库触发器测试宽泛异常收窄为 psycopg.errors.RaiseException
   - 抽取离线大测试拆出真实 PG smoke(默认阻断,不计入离线通过)
   - 抽取 presence 去重边界拆出独立测试:493 + 78 = 571 项检查不变

3. 运行时文档清理
   - 13 个 SKILL.md 移除自测/离线验证段落、测试命令与测试文件事实源表述,
     只保留运行时合同;业务运行合同、额度、授权与离线模式均保留

4. SoT 同步
   - AGENTS.md:新增 Skill 领域索引(7 个合同责任方分组,覆盖 32 个运行时 Skill)
   - 领域 07:测试入口改由 harness/manifests/ 登记,SKILL.md 不承载测试命令
   - humanization 覆盖矩阵:活动测试路径同步迁移

验证证据: harness 自测 15 项 + runner 自测 13 项通过;静态审计 32 Skill / 0 问题;
73 个非数据库测试通过;8 个集成条目中 6 个 PostgreSQL 项被依赖门明确阻断;
py_compile 与 git diff --check 通过。未连接 PostgreSQL、网络、真实模型或额度。

已知边界: 真正 skill_behavior_eval 仍为 0,尚未验证任何 Skill 自然语言行为;
evaluate-frozen-replay 的 raw 存储边界冲突留待单独治理。
2026-08-19 01:50:20 +08:00

139 lines
6.9 KiB
Python

#!/usr/bin/env python3
"""fact_delta reducer 的离线测试。
模型只能提类型化增量,证据引文必须真实出现在候选正文中(不得编造证据);
字段闭集、类型闭集、payload 合同、重复 ID 一律失败关闭。
跑法:.venv/bin/python tests/skills/decide-candidate/test_fact_delta.py
"""
from __future__ import annotations
import copy
import pathlib
import sys
import unittest
PROJECT_ROOT = pathlib.Path(__file__).resolve().parents[3]
SKILLS_DIR = PROJECT_ROOT / ".claude" / "skills"
SCRIPT_DIR = SKILLS_DIR / "decide-candidate" / "scripts"
for path in (SCRIPT_DIR, SKILLS_DIR / "assemble-context" / "scripts"):
if str(path) not in sys.path:
sys.path.insert(0, str(path))
from fact_delta import ( # noqa: E402
DELTA_TYPES, FactDeltaError, validate_delta_batch, validate_delta_proposal,
)
BODY = "林深把黑纹缠上手臂,异种核心在胸腔里低鸣。何岚站在舱门口没有说话。"
def _proposal(delta_type="character_location_changed", *, delta_id="delta-1",
payload=None, quote="异种核心在胸腔里低鸣"):
if payload is None:
payload = {"characterName": "林深", "toLocation": "舱室底层"}
return {"deltaId": delta_id, "deltaType": delta_type,
"payload": payload, "evidenceQuote": quote}
class ValidateDeltaProposalTest(unittest.TestCase):
def test_each_delta_type_has_working_contract(self) -> None:
cases = {
"character_location_changed":
({"characterName": "林深", "toLocation": "舱室底层"}, "异种核心在胸腔里低鸣"),
"character_knowledge_added":
({"characterName": "何岚", "knowledge": "林深体内有异种核心"}, "何岚站在舱门口没有说话"),
"relationship_changed":
({"fromName": "林深", "toName": "何岚", "relation": "互相提防"}, "何岚站在舱门口没有说话"),
"hook_advanced":
({"hookId": "hook-voice", "action": "advanced",
"dueWindow": {"fromChapter": 5, "toChapter": 8}}, "异种核心在胸腔里低鸣"),
"timeline_event_added":
({"event": "隔离舱首次审讯结束"}, "何岚站在舱门口没有说话"),
"setting_added":
({"factType": "污染规则", "text": "黑纹扩散不可逆"}, "林深把黑纹缠上手臂"),
}
self.assertEqual(set(cases), DELTA_TYPES)
for delta_type, (payload, quote) in cases.items():
with self.subTest(delta_type=delta_type):
got = validate_delta_proposal(
_proposal(delta_type, payload=payload, quote=quote),
candidate_body=BODY, target_chapter=2)
self.assertEqual(got["deltaType"], delta_type)
self.assertTrue(got["subjectKey"])
def test_subject_key_derivation(self) -> None:
got = validate_delta_proposal(
_proposal("relationship_changed",
payload={"fromName": "林深", "toName": "何岚", "relation": "同盟"},
quote="何岚站在舱门口没有说话"),
candidate_body=BODY, target_chapter=2)
self.assertEqual(got["subjectKey"], "林深→何岚")
hook = validate_delta_proposal(
_proposal("hook_advanced", payload={"hookId": "hook-voice", "action": "planted"},
quote="异种核心在胸腔里低鸣"),
candidate_body=BODY, target_chapter=2)
self.assertEqual(hook["subjectKey"], "hook-voice")
def test_quote_not_found_fails_closed(self) -> None:
with self.assertRaises(FactDeltaError) as caught:
validate_delta_proposal(_proposal(quote="正文里不存在的句子"),
candidate_body=BODY, target_chapter=2)
self.assertEqual(caught.exception.code, "FACT_DELTA_QUOTE_NOT_FOUND")
def test_closed_field_set_and_type_enum(self) -> None:
extra = _proposal()
extra["extraField"] = 1
with self.assertRaises(FactDeltaError) as caught:
validate_delta_proposal(extra, candidate_body=BODY, target_chapter=2)
self.assertEqual(caught.exception.code, "FACT_DELTA_INVALID")
bad_type = _proposal(delta_type="character_resurrected")
with self.assertRaises(FactDeltaError) as caught:
validate_delta_proposal(bad_type, candidate_body=BODY, target_chapter=2)
self.assertEqual(caught.exception.code, "FACT_DELTA_TYPE_INVALID")
def test_payload_contract_enforced_per_type(self) -> None:
missing_field = _proposal(payload={"characterName": "林深"}) # 缺 toLocation
with self.assertRaises(FactDeltaError):
validate_delta_proposal(missing_field, candidate_body=BODY, target_chapter=2)
bad_hook_action = _proposal(
"hook_advanced", payload={"hookId": "h1", "action": "detonated"},
quote="异种核心在胸腔里低鸣")
with self.assertRaises(FactDeltaError):
validate_delta_proposal(bad_hook_action, candidate_body=BODY, target_chapter=2)
bad_due_window = _proposal(
"hook_advanced",
payload={"hookId": "h1", "action": "planted",
"dueWindow": {"fromChapter": 9, "toChapter": 3}},
quote="异种核心在胸腔里低鸣")
with self.assertRaises(FactDeltaError):
validate_delta_proposal(bad_due_window, candidate_body=BODY, target_chapter=2)
def test_batch_rejects_duplicate_ids(self) -> None:
batch = [_proposal(delta_id="delta-1"),
_proposal(delta_id="delta-1", payload={"characterName": "何岚",
"toLocation": "指挥舱"})]
with self.assertRaises(FactDeltaError) as caught:
validate_delta_batch(batch, candidate_body=BODY, target_chapter=2)
self.assertEqual(caught.exception.code, "FACT_DELTA_DUPLICATE_ID")
ok = validate_delta_batch(
[_proposal(delta_id="delta-1"),
_proposal(delta_id="delta-2", payload={"characterName": "何岚",
"toLocation": "指挥舱"})],
candidate_body=BODY, target_chapter=2)
self.assertEqual([item["deltaId"] for item in ok], ["delta-1", "delta-2"])
def test_quote_is_normalized_before_matching(self) -> None:
# 正文里的字面转义换行(模型 JSON 双重转义)归一为真换行后再匹配,与正文合同一致
escaped_body = BODY + "\\n舱灯闪了一下"
got = validate_delta_proposal(
_proposal(payload={"characterName": "林深", "toLocation": "舱室底层"},
quote="\n舱灯闪了一下"),
candidate_body=escaped_body, target_chapter=2)
self.assertEqual(got["deltaType"], "character_location_changed")
self.assertIn("\n舱灯闪了一下", escaped_body.replace("\\n", "\n"))
if __name__ == "__main__":
unittest.main()