c9f69d9d6d
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。
82 lines
3.7 KiB
Python
82 lines
3.7 KiB
Python
#!/usr/bin/env python3
|
||
"""build_semantic_input_v3 生产投影的离线测试。
|
||
|
||
验证：WriterContext + 候选能被投影成通过闭集校验的 semantic-detector-input-v3；
|
||
sourceRef 多余字段被清洗；身份字段严格绑定；哈希自洽。
|
||
|
||
跑法：.venv/bin/python tests/skills/check-content-consistency/test_build_semantic_input.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"
|
||
TEST_DIR = PROJECT_ROOT / "tests" / "skills" / "check-content-consistency"
|
||
SCRIPT_DIR = SKILLS_DIR / "check-content-consistency" / "scripts"
|
||
CONTINUATION_DIR = SKILLS_DIR / "write-next-chapter" / "scripts"
|
||
READ_CONTEXT_DIR = SKILLS_DIR / "assemble-context" / "scripts"
|
||
for path in (TEST_DIR, SCRIPT_DIR, CONTINUATION_DIR, READ_CONTEXT_DIR):
|
||
if str(path) not in sys.path:
|
||
sys.path.insert(0, str(path))
|
||
|
||
from run_writer_semantic_detector import ( # noqa: E402
|
||
build_semantic_input_v3, validate_semantic_detector_input,
|
||
)
|
||
from test_check_writer_candidate import _valid_pair # noqa: E402
|
||
|
||
|
||
class BuildSemanticInputV3Test(unittest.TestCase):
|
||
def test_projects_valid_input_that_passes_closed_validation(self) -> None:
|
||
context, candidate = _valid_pair()
|
||
payload = build_semantic_input_v3(
|
||
run_id=context["runId"], sample_id="writer-ch2", opaque_arm_id="production",
|
||
writer_context=context, candidate=candidate)
|
||
# 返回值本身必须能再过一遍闭集校验（幂等自洽）
|
||
validated = validate_semantic_detector_input(payload)
|
||
self.assertEqual(validated["runId"], context["runId"])
|
||
self.assertEqual(validated["candidateSha256"], candidate["candidateSha256"])
|
||
self.assertEqual(validated["candidateVersion"], candidate["candidateVersion"])
|
||
self.assertEqual(
|
||
validated["contextSnapshotSha256"], context["contextSnapshot"]["contextSha256"])
|
||
self.assertEqual(validated["asOf"], context["asOf"])
|
||
self.assertNotIn("_expectedAssertionIds", payload)
|
||
|
||
def test_cleans_source_ref_extra_fields(self) -> None:
|
||
context, candidate = _valid_pair()
|
||
# _bound_context 的 factEvidence.sourceRef 带 sourceType 多余字段，必须被清洗掉
|
||
payload = build_semantic_input_v3(
|
||
run_id=context["runId"], sample_id="writer-ch2", opaque_arm_id="production",
|
||
writer_context=context, candidate=candidate)
|
||
for item in payload["factEvidence"]:
|
||
self.assertNotIn("sourceType", item["sourceRef"])
|
||
# 原上下文不被改动
|
||
self.assertIn("sourceType", context["factEvidence"][0]["sourceRef"])
|
||
|
||
def test_outline_constraints_get_stable_ids(self) -> None:
|
||
context, candidate = _valid_pair()
|
||
payload = build_semantic_input_v3(
|
||
run_id=context["runId"], sample_id="writer-ch2", opaque_arm_id="production",
|
||
writer_context=context, candidate=candidate)
|
||
ids = [item["constraintId"] for item in payload["hardConstraints"]]
|
||
self.assertEqual(ids, [f"constraint-{i + 1}" for i in range(len(ids))])
|
||
self.assertEqual(
|
||
[item["constraintId"] for item in payload["fineOutline"]["hardConstraints"]], ids)
|
||
|
||
def test_candidate_body_hash_mismatch_fails_closed(self) -> None:
|
||
context, candidate = _valid_pair()
|
||
bad = copy.deepcopy(candidate)
|
||
bad["candidateSha256"] = "sha256:" + "f" * 64
|
||
with self.assertRaises(Exception):
|
||
build_semantic_input_v3(
|
||
run_id=context["runId"], sample_id="writer-ch2", opaque_arm_id="production",
|
||
writer_context=context, candidate=bad)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
unittest.main()
|