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。
75 lines
2.8 KiB
Python
75 lines
2.8 KiB
Python
#!/usr/bin/env python3
|
||
"""文风取数端回归:load_confirmed_style / derive_style_constraints(桩连接,不连真库)。
|
||
|
||
read-context 的文风取数端,与细纲/范式取数端并排成一等公民。优先独立 style 规划行,
|
||
回退设定行的 style 字段(书12 现状为一句话 blob)。结构化画像抽取仍待建。
|
||
"""
|
||
|
||
import pathlib
|
||
import sys
|
||
import unittest
|
||
|
||
PROJECT_ROOT = pathlib.Path(__file__).resolve().parents[3]
|
||
SCRIPT_DIR = PROJECT_ROOT / ".claude" / "skills" / "assemble-context" / "scripts"
|
||
sys.path.insert(0, str(SCRIPT_DIR))
|
||
|
||
from retrieve_writer_sources import derive_style_constraints, load_confirmed_style # noqa: E402
|
||
|
||
|
||
class FakeCursor:
|
||
def __init__(self, row):
|
||
self._row = row
|
||
|
||
def fetchone(self):
|
||
return self._row
|
||
|
||
|
||
class FakeConn:
|
||
"""按 SQL 区分两次查询:schema_type='style' 的独立文风行 / section_type='setting' 的设定行。"""
|
||
|
||
def __init__(self, style_row=None, setting_row=None):
|
||
self.style_row = style_row
|
||
self.setting_row = setting_row
|
||
|
||
def execute(self, sql, params=None):
|
||
if "schema_type='style'" in sql:
|
||
return FakeCursor(self.style_row)
|
||
if "section_type='setting'" in sql:
|
||
return FakeCursor(self.setting_row)
|
||
return FakeCursor(None)
|
||
|
||
|
||
class DeriveStyleTest(unittest.TestCase):
|
||
def test_blob_becomes_single_constraint(self):
|
||
self.assertEqual(derive_style_constraints("冷峻、克制、微恐。"), ["冷峻、克制、微恐。"])
|
||
|
||
def test_structured_dict_projects_per_aspect(self):
|
||
self.assertEqual(
|
||
derive_style_constraints({"叙事人称": "第三人称限制视角", "AI味黑名单": "禁 仿佛/似乎", "达标样张": ""}),
|
||
["叙事人称:第三人称限制视角", "AI味黑名单:禁 仿佛/似乎"],
|
||
)
|
||
|
||
def test_blank_and_illegal_return_empty(self):
|
||
self.assertEqual(derive_style_constraints(" "), [])
|
||
self.assertEqual(derive_style_constraints(None), [])
|
||
self.assertEqual(derive_style_constraints(42), [])
|
||
|
||
|
||
class LoadConfirmedStyleTest(unittest.TestCase):
|
||
def test_prefers_dedicated_style_section(self):
|
||
conn = FakeConn(style_row=('{"叙事人称": "第三人称"}',),
|
||
setting_row=('{"style": "不该用到我"}',))
|
||
self.assertEqual(load_confirmed_style(conn, work_id=12), ["叙事人称:第三人称"])
|
||
|
||
def test_falls_back_to_setting_style_field(self):
|
||
conn = FakeConn(style_row=None, setting_row=('{"title": "深渊机神", "style": "冷峻克制"}',))
|
||
self.assertEqual(load_confirmed_style(conn, work_id=12), ["冷峻克制"])
|
||
|
||
def test_no_confirmed_style_returns_empty(self):
|
||
conn = FakeConn(style_row=None, setting_row=None)
|
||
self.assertEqual(load_confirmed_style(conn, work_id=12), [])
|
||
|
||
|
||
if __name__ == "__main__":
|
||
unittest.main()
|