host
be41ad2c0a
- test_skill_appendix_sync: all 9 appendix chapters 00..08 in order, body role-matrix set == appendix role-title set, authority statement on both sides, GitHub guarantee in body + named appendix chapters 00/04/07, seeded copy byte-identical with full appendix. Previously only 00/08 existence was asserted. - test_skill_seed_pinning: only SKILL.md copied (pack extras never land, never resurrected), tenant extras left alone, tenant-modified SKILL.md never overwritten across repeats, identical = noop, deleted SKILL.md re-seeded (documented boundary, not deletion preservation). - skill_seed.py: evaluation note only (why whole-dir copy is not done); no code change.
219 lines
9.7 KiB
Python
219 lines
9.7 KiB
Python
"""Body<->appendix sync for the software-engineering skill (C-line).
|
||
|
||
Scope guard: this file READS cloud/skills/software-engineering/SKILL.md
|
||
and asserts structure; it never edits the skill text. If any assertion
|
||
here fails, the fix is a skill-content decision (edit SKILL.md through
|
||
its own track), not a silent edit by this test.
|
||
|
||
Audit finding on origin/main (2026-10-31): there was NO bidirectional
|
||
test at all. The only appendix coverage was test_skill_seed_worker.py
|
||
asserting two chapters (00-coordinator, 08-shared-core) exist in the
|
||
seeded file -- a dropped middle chapter (01..07) would pass CI silently.
|
||
The bidirectional assertion previously discussed on the #209 track is
|
||
unmerged, so main does not have it; this file supplies it on the main
|
||
base (skill text v0.2, 9 appendix chapters 00..08).
|
||
|
||
What "bidirectional" means here, concretely (all derived from SKILL.md
|
||
itself, no new semantics invented):
|
||
- body names the appendix as the authority AND the appendix intro
|
||
claims itself as the authority (either side missing -> fail naming
|
||
the missing side);
|
||
- body names exactly three appendix chapters for the GitHub guarantee
|
||
(coordinator, client, acceptance) AND each named chapter carries
|
||
the rule keywords (each chapter's keyword set is tailored to what
|
||
that chapter actually says -- e.g. 07-acceptance carries force-push /
|
||
merge-gate / PR-number rules but no literal "GitHub" word, so the
|
||
test must not demand that word there);
|
||
- body role-matrix role names == appendix role-title names as sets
|
||
(order differs: matrix order vs numeric 00..08 order, so set, not
|
||
list, comparison), and appendix ids are exactly 00..08 in order.
|
||
|
||
CI: .github/workflows/host-verify.yml and release.yml both run
|
||
`python3 -m unittest discover -s cloud/tests -v`, so this test_*.py
|
||
file runs in CI automatically with no workflow edit.
|
||
|
||
Only software-engineering has an appendix (grep: the other four
|
||
skills contain zero "附录"); appendix checks are therefore scoped to
|
||
this one skill and must NOT be generalised to the other skills.
|
||
"""
|
||
|
||
import re
|
||
import sys
|
||
import tempfile
|
||
import unittest
|
||
from pathlib import Path
|
||
|
||
try:
|
||
from cloud.skill_seed import ensure_codex_home_skills
|
||
except ImportError:
|
||
sys.path.insert(0, str(Path(__file__).resolve().parents[2]))
|
||
from cloud.skill_seed import ensure_codex_home_skills
|
||
|
||
REPO_ROOT = Path(__file__).resolve().parents[2]
|
||
SKILL_PATH = (REPO_ROOT / "cloud" / "skills" / "software-engineering"
|
||
/ "SKILL.md")
|
||
|
||
EXPECTED_IDS = ["00-coordinator", "01-product-manager", "02-architect",
|
||
"03-designer", "04-client-developer", "05-backend",
|
||
"06-qa", "07-acceptance", "08-shared-core"]
|
||
|
||
# Chapter -> keywords that chapter must carry for the GitHub guarantee
|
||
# the body claims is "同样写进了附录的协调员、客户端、验收章节".
|
||
# 07 has no literal "GitHub" word (its rules live under
|
||
# "按端发布与回滚（验收）"); demanding it would be a false failure.
|
||
GITHUB_CHAPTER_KEYWORDS = {
|
||
"00-coordinator": ["GitHub 保证", "force-push", "合并门"],
|
||
"04-client-developer": ["GitHub 交付", "force-push", "PR 号"],
|
||
"07-acceptance": ["force-push", "合并门", "PR 号"],
|
||
}
|
||
|
||
CHAPTER_RE = re.compile(
|
||
r"^## 附录角色：(\d{2}-[a-z0-9-]+)"
|
||
r"（来源 templates/roles/(\d{2}-[a-z0-9-]+\.md)）",
|
||
flags=re.M)
|
||
TITLE_RE = re.compile(r"^# 角色模板：(.+)$", flags=re.M)
|
||
|
||
|
||
def _read_skill():
|
||
assert SKILL_PATH.is_file(), (
|
||
"正文侧缺失：技能源文件不存在：%s" % SKILL_PATH)
|
||
return SKILL_PATH.read_text(encoding="utf-8")
|
||
|
||
|
||
def _split(text):
|
||
marker = "## 附录：角色模板"
|
||
assert marker in text, "正文侧缺失：找不到附录引言节 %r" % marker
|
||
body, appendix = text.split(marker, 1)
|
||
return body, appendix
|
||
|
||
|
||
def _chapters(appendix):
|
||
matches = list(CHAPTER_RE.finditer(appendix))
|
||
chapters = {}
|
||
for i, m in enumerate(matches):
|
||
end = matches[i + 1].start() if i + 1 < len(matches) else len(appendix)
|
||
chapters[m.group(1)] = appendix[m.start():end]
|
||
return chapters, matches
|
||
|
||
|
||
def _base_role_name(title):
|
||
# "后端 / API（可选，1 个线程）" -> "后端 / API";
|
||
# "后端 / API（如有）" (matrix cell) -> "后端 / API".
|
||
return re.sub(r"（[^）]*）\s*$", "", title.strip())
|
||
|
||
|
||
class AppendixSyncTestCase(unittest.TestCase):
|
||
def test_appendix_has_all_nine_chapters_in_order(self):
|
||
text = _read_skill()
|
||
_body, appendix = _split(text)
|
||
chapters, matches = _chapters(appendix)
|
||
found = [m.group(1) for m in matches]
|
||
self.assertEqual(
|
||
found, EXPECTED_IDS,
|
||
"附录侧缺失/错序：附录章节 id 应为 %s，实际为 %s"
|
||
% (EXPECTED_IDS, found))
|
||
for cid in EXPECTED_IDS:
|
||
sec = chapters[cid]
|
||
src = [m.group(2) for m in matches if m.group(1) == cid][0]
|
||
self.assertEqual(
|
||
src, cid + ".md",
|
||
"附录侧不一致：章节 %s 的来源注应为 %s，实际为 %s"
|
||
% (cid, cid + ".md", src))
|
||
title = TITLE_RE.search(sec)
|
||
self.assertIsNotNone(
|
||
title,
|
||
"附录侧缺失：章节 %s 内找不到“# 角色模板：”标题行" % cid)
|
||
# Smallest real chapter is ~600 chars; 300 catches a
|
||
# dropped/emptied chapter without being brittle.
|
||
self.assertGreater(
|
||
len(sec), 300,
|
||
"附录侧缺失/被掏空：章节 %s 仅 %d 字" % (cid, len(sec)))
|
||
|
||
def test_body_role_matrix_matches_appendix_titles(self):
|
||
text = _read_skill()
|
||
body, appendix = _split(text)
|
||
chapters, _m = _chapters(appendix)
|
||
appendix_roles = set()
|
||
for cid, sec in chapters.items():
|
||
title = TITLE_RE.search(sec)
|
||
self.assertIsNotNone(title, "附录侧缺失：%s 无标题" % cid)
|
||
appendix_roles.add(_base_role_name(title.group(1)))
|
||
matrix_roles = set()
|
||
# Only the role-matrix section: other body tables (gate table
|
||
# with G0..G6, etc.) must not leak into the role set.
|
||
matrix_section = body.split("## 角色线程矩阵", 1)[1]
|
||
matrix_section = matrix_section.split("\n## ", 1)[0]
|
||
for line in matrix_section.splitlines():
|
||
if not line.startswith("| "):
|
||
continue
|
||
cells = [c.strip() for c in line.strip().strip("|").split("|")]
|
||
if not cells or cells[0] in ("角色", "------"):
|
||
continue
|
||
matrix_roles.add(_base_role_name(cells[0]))
|
||
self.assertEqual(
|
||
matrix_roles, appendix_roles,
|
||
"双向不一致：正文角色矩阵缺 %s；附录缺角色 %s"
|
||
% (sorted(appendix_roles - matrix_roles),
|
||
sorted(matrix_roles - appendix_roles)))
|
||
|
||
def test_authority_statement_is_bidirectional(self):
|
||
text = _read_skill()
|
||
body, appendix = _split(text)
|
||
for phrase in ("角色模板的权威来源是本文件末尾的附录",
|
||
"不一致时以附录为准"):
|
||
self.assertIn(
|
||
phrase, body,
|
||
"正文侧缺失：正文未声明“%s”（附录单方面有权威也无法核对）"
|
||
% phrase)
|
||
intro = appendix.split("## 附录角色：", 1)[0]
|
||
for phrase in ("以本附录为准", "核对附录与 `templates/roles/` 一致"):
|
||
self.assertIn(
|
||
phrase, intro,
|
||
"附录侧缺失：附录引言未声明“%s”（正文单方面指认附录也无法核对）"
|
||
% phrase)
|
||
|
||
def test_github_guarantee_in_body_and_named_appendix_chapters(self):
|
||
text = _read_skill()
|
||
body, appendix = _split(text)
|
||
chapters, _m = _chapters(appendix)
|
||
for phrase in ("同样写进了附录的协调员、客户端、验收章节",
|
||
"正文与附录不一致就是不合格"):
|
||
self.assertIn(
|
||
phrase, body,
|
||
"正文侧缺失：正文 GitHub 保证节未声明“%s”" % phrase)
|
||
for cid, keywords in GITHUB_CHAPTER_KEYWORDS.items():
|
||
self.assertIn(
|
||
cid, chapters, "附录侧缺失：正文点名的章节 %s 不在附录中" % cid)
|
||
for kw in keywords:
|
||
self.assertIn(
|
||
kw, chapters[cid],
|
||
"附录侧缺失：章节 %s 缺少规则关键词 %r"
|
||
"（正文 GitHub 保证节声称该规则已写进本章）"
|
||
% (cid, kw))
|
||
|
||
def test_seeded_copy_carries_full_appendix_byte_identical(self):
|
||
# Delivery-channel check: the seeded tenant copy must carry
|
||
# the whole appendix, not just the two chapters the old test
|
||
# checked. Byte-identity is the strongest form: skill_seed
|
||
# copies SKILL.md verbatim, so any appendix edit in the pack
|
||
# reaches the tenant only through this exact file.
|
||
with tempfile.TemporaryDirectory() as tmp:
|
||
out = ensure_codex_home_skills(tmp)
|
||
self.assertIn("software-engineering", out["skills_copied"])
|
||
seeded = Path(tmp) / "skills" / "software-engineering" \
|
||
/ "SKILL.md"
|
||
self.assertTrue(seeded.is_file(), "播种侧缺失：未生成租户 SKILL.md")
|
||
seeded_text = seeded.read_text(encoding="utf-8")
|
||
self.assertEqual(
|
||
seeded_text, _read_skill(),
|
||
"播种侧不一致：租户 SKILL.md 与源包字节不一致（附录可能被截断）")
|
||
_body, appendix = _split(seeded_text)
|
||
chapters, _m = _chapters(appendix)
|
||
self.assertEqual(
|
||
sorted(chapters), sorted(EXPECTED_IDS),
|
||
"播种侧缺失：租户副本附录章节不全：%s" % sorted(chapters))
|
||
|
||
|
||
if __name__ == "__main__":
|
||
unittest.main()
|