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

305 lines
14 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/usr/bin/env python3
"""事实增量对 muse-example 真实库的集成测试。
覆盖:
- 提案登记幂等:同候选重复 deltaId 拒绝(不得覆盖);
- ChapterCommit 原子性:已批准增量与正文同一事务落账本;任一增量非法则整体回滚,
正文也不写入;
- 账本绑定:source_block_revision + command_id 与正文提交一致;
- 账本 append-only:UPDATE/DELETE 被触发器拒绝。
测试数据 unittest-delta- 前缀隔离;清理时短暂禁用账本防删触发器(try/finally 恢复)。
跑法(需 Tailscale 内网可达 muse-example):
.venv/bin/python tests/skills/decide-candidate/test_fact_delta_db.py
"""
from __future__ import annotations
import hashlib
import pathlib
import sys
import uuid
from psycopg.errors import RaiseException
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 / "access-database" / "scripts"):
if str(path) not in sys.path:
sys.path.insert(0, str(path))
from db import connect # noqa: E402
from fact_delta import FactDeltaError, propose_fact_deltas # noqa: E402
from write_canonical import ConflictError, accept # noqa: E402
SUFFIX = uuid.uuid4().hex[:10]
WORK_TITLE = f"unittest-delta-{SUFFIX}"
BODY = f"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。{SUFFIX}"
_command_ids: list[str] = []
_candidate_ids: list[int] = []
_delta_ids: list[int] = []
_work_id: int | None = None
def _sha(text: str) -> str:
return hashlib.sha256(text.encode("utf-8")).hexdigest()
def _cleanup() -> None:
if _work_id is None:
return
with connect() as conn:
try:
conn.execute(
"ALTER TABLE example_fact_ledger DISABLE TRIGGER trg_example_fact_ledger_append_only")
conn.execute(
"ALTER TABLE example_user_decision DISABLE TRIGGER trg_example_user_decision_append_only")
try:
if _candidate_ids:
conn.execute("DELETE FROM example_user_decision WHERE candidate_id = ANY(%s)",
(_candidate_ids,))
if _command_ids:
conn.execute("DELETE FROM muse_content_command_log WHERE command_id = ANY(%s)",
(_command_ids,))
conn.execute("DELETE FROM example_fact_ledger WHERE work_id=%s", (_work_id,))
conn.execute("DELETE FROM example_fact_delta WHERE work_id=%s", (_work_id,))
conn.execute("DELETE FROM muse_content_block_source_attribution WHERE work_id=%s",
(_work_id,))
conn.execute("DELETE FROM muse_content_block WHERE work_id=%s", (_work_id,))
conn.execute("DELETE FROM muse_content_chapter WHERE work_id=%s", (_work_id,))
if _candidate_ids:
conn.execute("DELETE FROM example_candidate WHERE id = ANY(%s)",
(_candidate_ids,))
conn.execute("DELETE FROM muse_content_work WHERE id=%s", (_work_id,))
conn.commit()
finally:
conn.execute(
"ALTER TABLE example_fact_ledger ENABLE TRIGGER trg_example_fact_ledger_append_only")
conn.execute(
"ALTER TABLE example_user_decision ENABLE TRIGGER trg_example_user_decision_append_only")
conn.commit()
except Exception:
conn.rollback()
raise
def _setup() -> int:
global _work_id
with connect() as conn:
work_id = conn.execute(
"INSERT INTO muse_content_work(owner_user_id, title, status, creator) "
"VALUES (1,%s,'writing','unittest') RETURNING id", (WORK_TITLE,)).fetchone()[0]
conn.execute(
"INSERT INTO muse_content_chapter(work_id, title, order_no, creator) "
"VALUES (%s,'测试章',1,'unittest')", (work_id,))
conn.commit()
_work_id = work_id
return work_id
def _insert_candidate(work_id: int, *, version: str) -> int:
with connect() as conn:
candidate_id = conn.execute(
"INSERT INTO example_candidate(work_id, target_chapter, run_id, attempt, run_type, "
"candidate_version, candidate_sha256, candidate_body, quality_policy_version, mode, "
"source_role, state, acceptance_eligible, semantic_status, semantic_report_sha256, creator) "
"VALUES (%s,1,%s,1,'production',%s,%s,%s,'writer-production-v1','continuation','writer',"
"'passed',TRUE,'passed',%s,'unittest') RETURNING id",
(work_id, f"unittest-delta-run-{SUFFIX}-{version}", version, _sha(BODY), BODY,
_sha("sem:" + BODY))).fetchone()[0]
conn.commit()
_candidate_ids.append(candidate_id)
return candidate_id
def _command_id(tag: str) -> str:
cid = f"unittest-delta-{tag}-{SUFFIX}"
_command_ids.append(cid)
return cid
def _good_delta(delta_id="delta-1"):
return {"deltaId": delta_id, "deltaType": "hook_advanced",
"payload": {"hookId": "hook-voice", "action": "advanced",
"dueWindow": {"fromChapter": 3, "toChapter": 6}},
"evidenceQuote": "异种核心在胸腔里低鸣"}
def test_propose_is_idempotent_reject(work_id: int) -> None:
candidate_sha = _sha(BODY)
out = propose_fact_deltas(
work_id=work_id, target_chapter=1, run_id=None,
candidate_sha256_bare=candidate_sha, candidate_body=BODY,
deltas=[_good_delta("delta-prop-1"), _good_delta("delta-prop-2")])
assert out["status"] == "proposed" and len(out["proposed_ids"]) == 2
_delta_ids.extend(out["proposed_ids"])
# 同候选重复 deltaId:失败关闭,不得覆盖
try:
propose_fact_deltas(
work_id=work_id, target_chapter=1, run_id=None,
candidate_sha256_bare=candidate_sha, candidate_body=BODY,
deltas=[_good_delta("delta-prop-1")])
raise AssertionError("重复 deltaId 必须被拒绝")
except AssertionError:
raise
except FactDeltaError as exc:
assert exc.code == "FACT_DELTA_DUPLICATE_ID"
with connect(readonly=True) as conn:
count = int(conn.execute(
"SELECT COUNT(*) FROM example_fact_delta WHERE candidate_sha256=%s AND delta_id='delta-prop-1'",
(candidate_sha,)).fetchone()[0])
assert count == 1
def test_commit_applies_approved_deltas_atomically(work_id: int) -> None:
candidate_id = _insert_candidate(work_id, version="1")
command_id = _command_id("commit-1")
result = accept(candidate_id, rationale="unittest", expected_revision=0,
command_id=command_id,
approved_deltas=[_good_delta("delta-acc-1"), _good_delta("delta-acc-2")])
assert result["status"] == "accepted" and len(result["delta_ids"]) == 2
_delta_ids.extend(result["delta_ids"])
with connect(readonly=True) as conn:
ledger_rows = conn.execute(
"SELECT delta_type, subject_key, source_block_revision, command_id, "
"source_candidate_sha256 FROM example_fact_ledger WHERE work_id=%s ORDER BY id",
(work_id,)).fetchall()
delta_rows = conn.execute(
"SELECT status, source_revision, decided_by FROM example_fact_delta WHERE id = ANY(%s)",
(result["delta_ids"],)).fetchall()
assert len(ledger_rows) == 2
for row in ledger_rows:
assert row[0] == "hook_advanced"
assert row[1] == "hook-voice"
assert row[2] == result["revision"], "账本必须绑同事务的正文 revision"
assert row[3] == command_id, "账本必须与正文提交同一幂等键"
assert row[4] == _sha(BODY)
for row in delta_rows:
assert row == ("accepted", result["revision"], "1")
def test_invalid_delta_rolls_back_entire_commit(work_id: int) -> None:
candidate_id = _insert_candidate(work_id, version="2")
command_id = _command_id("commit-bad")
forged = {"deltaId": "delta-forged", "deltaType": "setting_added",
"payload": {"factType": "污染规则", "text": "编造的设定"},
"evidenceQuote": "这句话根本不在正文里"}
try:
# expected_revision=1:上一测试已把正文块写到 rev1,给对的值才能真正走到增量校验
accept(candidate_id, rationale="unittest", expected_revision=1,
command_id=command_id, approved_deltas=[_good_delta("delta-ok"), forged])
raise AssertionError("非法增量必须中止整个提交")
except AssertionError:
raise
except FactDeltaError as exc:
assert exc.code == "FACT_DELTA_QUOTE_NOT_FOUND", exc
with connect(readonly=True) as conn:
blocks = int(conn.execute(
"SELECT COUNT(*) FROM muse_content_block WHERE work_id=%s AND deleted=false",
(work_id,)).fetchone()[0])
ledger = int(conn.execute(
"SELECT COUNT(*) FROM example_fact_ledger WHERE work_id=%s", (work_id,)).fetchone()[0])
delta_acc = int(conn.execute(
"SELECT COUNT(*) FROM example_fact_delta WHERE work_id=%s AND status='accepted'",
(work_id,)).fetchone()[0])
state = conn.execute(
"SELECT state FROM example_candidate WHERE id=%s", (candidate_id,)).fetchone()[0]
# 整体回滚:正文块、账本、accepted 提案全部不得出现(上一条测试已落的 2 行账本不变)
assert blocks == 1, "非法增量不得写入正文"
assert ledger == 2, "非法增量不得半合并进账本"
assert delta_acc == 2, "合法增量也不得单独生效(同事务)"
assert state == "passed"
def test_propose_then_approve_no_unique_collision(work_id: int) -> None:
"""抽取先登记提案、用户批准后随正文接受:翻态正道,不撞唯一键。"""
candidate_id = _insert_candidate(work_id, version="3")
candidate_sha = _sha(BODY)
out = propose_fact_deltas(
work_id=work_id, target_chapter=1, run_id=None,
candidate_sha256_bare=candidate_sha, candidate_body=BODY,
deltas=[_good_delta("delta-flow-1")])
assert out["status"] == "proposed"
_delta_ids.extend(out["proposed_ids"])
command_id = _command_id("commit-flow")
# 前面的测试把正文块写到 rev1(非法增量整体回滚不改变它),给 rev1 才走到增量合并
result = accept(candidate_id, rationale="unittest", expected_revision=1,
command_id=command_id, approved_deltas=[_good_delta("delta-flow-1")])
assert result["status"] == "accepted" and len(result["delta_ids"]) == 1
assert result["revision"] == 2
with connect(readonly=True) as conn:
row = conn.execute(
"SELECT status, decided_by, source_revision FROM example_fact_delta WHERE id=%s",
(result["delta_ids"][0],)).fetchone()
# 按 delta_ref 精确查(同 sha 的候选在本文件多个测试里复用过,按 sha 过滤会串)
ledger = conn.execute(
"SELECT delta_ref, source_block_revision, command_id FROM example_fact_ledger "
"WHERE delta_ref=%s", (result["delta_ids"][0],)).fetchall()
assert row == ("accepted", "1", result["revision"]), "提案行应翻 accepted 并绑正文 revision"
assert len(ledger) == 1, "该增量在账本中恰有一行"
assert ledger[0][0] == result["delta_ids"][0]
assert ledger[0][1] == result["revision"], "账本绑同事务正文 revision"
assert ledger[0][2] == command_id, "账本绑同一幂等键"
# 已裁决的提案不得再次接受(稳定错误码,不是裸 DB 异常);
# expected_revision 给当前 rev2,确保穿过 revision 校验真正走到增量阶段
candidate_id_2 = _insert_candidate(work_id, version="4")
try:
accept(candidate_id_2, rationale="unittest", expected_revision=2,
command_id=_command_id("commit-flow-2"),
approved_deltas=[_good_delta("delta-flow-1")])
raise AssertionError("已 accepted 的提案不得再次接受")
except AssertionError:
raise
except FactDeltaError as exc:
assert exc.code == "FACT_DELTA_ALREADY_DECIDED"
except Exception as exc:
raise AssertionError(f"必须是稳定错误码,得到 {type(exc).__name__}: {exc}")
def test_ledger_append_only(work_id: int) -> None:
try:
with connect() as conn:
conn.execute("UPDATE example_fact_ledger SET subject_key='hacked' WHERE work_id=%s",
(work_id,))
conn.commit()
raise AssertionError("账本必须 append-only")
except AssertionError:
raise
except RaiseException:
pass
try:
with connect() as conn:
conn.execute("DELETE FROM example_fact_ledger WHERE work_id=%s", (work_id,))
conn.commit()
raise AssertionError("账本必须 append-only")
except AssertionError:
raise
except RaiseException:
pass
def main() -> None:
work_id = _setup()
tests = (
("提案登记幂等拒绝", test_propose_is_idempotent_reject),
("ChapterCommit 原子合并增量", test_commit_applies_approved_deltas_atomically),
("非法增量整体回滚", test_invalid_delta_rolls_back_entire_commit),
("提案→批准翻态不撞唯一键", test_propose_then_approve_no_unique_collision),
("账本 append-only", test_ledger_append_only),
)
try:
for name, test in tests:
test(work_id)
print(f"PASS: {name}")
print("PASS:事实增量真实库集成测试全部通过")
finally:
_cleanup()
if __name__ == "__main__":
main()