#!/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 .claude/skills/check-content-consistency/scripts/test_build_semantic_input.py """ from __future__ import annotations import copy import pathlib import sys import unittest SCRIPT_DIR = pathlib.Path(__file__).resolve().parent SKILLS_DIR = SCRIPT_DIR.parents[1] for path in (SCRIPT_DIR, SKILLS_DIR / "check-content-consistency" / "scripts", SKILLS_DIR / "write-next-chapter" / "scripts", SKILLS_DIR / "assemble-context" / "scripts"): 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()