lhl
d01e1b720f
- 步骤0: 新增中文镜像模板 scripts/make_zh_template.py 与 samples/概要设计书模板_中文.docx（7章锚点原样保留） - 步骤1: config.WriterConfig.output_language→Settings.writer；GenerationContext.output_language + to_vars.language_instruction（zh/ja/auto）；writer_agent【语言约束】改引变量；context_builder/orchestrator/run_trial 透传 --output-language - 步骤A: 新建 src/genesis/writer/language.py（detect_script/resolve_expected_language/find_language_violations）；WriterAgent.generate_chapter 按期望语言强制、违规重试、耗尽硬失败；max_retries 默认 1→2 - 步骤B: _format_impact 影响调查标签按 output_language 本地化（zh 新建/变更/删除/警告） - 步骤C: eval scorer 第 11 维度 language_consistency（不可验证=满分，不拉低总分）；ChapterArtifact.expected_language；QAValidator.validate_doc 透传；QALoop.run 透传 output_language - 测试: test_zh_template/test_language_plumbing/test_writer_language/test_scorer_language/test_language_coverage，并更新 test_phase5_e2e - 全量 pytest 424 passed / 99.15%（覆盖率门槛 99% 达标）
103 lines
4.6 KiB
Python
103 lines
4.6 KiB
Python
"""步骤 A/C 边界覆盖测试（恢复覆盖率至 ≥99%）。"""
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
|
|
from genesis.writer.language import find_language_violations
|
|
from genesis.writer.models import ChapterContent, ContentBlock, GenerationContext, ChapterSpec
|
|
from genesis.writer.writer_agent import WriterAgent
|
|
from genesis.writer.writer_state import WriterState
|
|
from genesis.writer.exceptions import WriterGenerationError
|
|
from genesis.qa.qa_loop import QALoop
|
|
from genesis.data_models import StructuredSource
|
|
from genesis.parsers.word_template_parser import WordTemplateParser
|
|
|
|
|
|
class _Reg:
|
|
@staticmethod
|
|
def get_or_create(name, template):
|
|
return SimpleNamespace(name=name, version="1", template=template)
|
|
|
|
|
|
def test_find_violations_unexpected_language_code_returns_empty():
|
|
blocks = [ContentBlock(block_id="0", type="paragraph", text="中文正文内容充分长度足够")]
|
|
# 非 zh/ja 的期望语言 → 不强制，返回空
|
|
assert find_language_violations(blocks, "xx") == []
|
|
|
|
|
|
def test_writer_agent_zh_expected_rejects_japanese():
|
|
class JpEngine:
|
|
def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
|
|
return SimpleNamespace(
|
|
data={"title": variables["title"],
|
|
"blocks": [{"type": "paragraph",
|
|
"text": "本機能は注文処理を行う画面であり、詳細は以下の通り。"}]},
|
|
status="ok",
|
|
)
|
|
agent = WriterAgent(session_id="s", engine=JpEngine(), prompt_registry=_Reg(),
|
|
state=WriterState(["db_design"]), max_retries=1)
|
|
ctx = GenerationContext(chapter_id="db_design", title="DB 設計",
|
|
template_marker=ChapterSpec(chapter_id="db_design", title="DB 設計"),
|
|
structured_source=None, write_rules=[], design_rules=[],
|
|
template_styles=set(), output_language="zh")
|
|
try:
|
|
agent.generate_chapter(ctx)
|
|
assert False, "应抛 WriterGenerationError"
|
|
except WriterGenerationError:
|
|
pass
|
|
|
|
|
|
def test_qa_loop_passes_with_explicit_zh_on_chinese_fake(tmp_path):
|
|
"""显式 zh + 中文 Fake → 语言维度通过（验证透传链路）。"""
|
|
template = Path("samples/phase5-slice/template.docx")
|
|
if not template.exists():
|
|
import pytest
|
|
pytest.skip("样本模板缺失")
|
|
parsed = WordTemplateParser().parse(str(template))
|
|
ss = StructuredSource(template=parsed, tables=[], rule_docs=[], image_analyses=[],
|
|
existing_system=None, comments=[])
|
|
out = tmp_path / "o.docx"
|
|
|
|
class ZhEngine:
|
|
def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
|
|
return SimpleNamespace(
|
|
data={"title": variables["title"],
|
|
"blocks": [{"type": "paragraph",
|
|
"text": "由 FakeLLM 生成的充分说明内容，满足写入规则要求。"}]},
|
|
status="ok",
|
|
)
|
|
loop = QALoop(max_rounds=1)
|
|
report = loop.run(ss, str(out), samples_dir="nonexistent_dir_xyz",
|
|
engine=ZhEngine(), template_path=str(template), output_language="zh")
|
|
assert report.passed is True
|
|
|
|
|
|
def test_qa_loop_fails_with_explicit_ja_on_chinese_fake(tmp_path):
|
|
"""显式 ja + 中文 Fake → 语言维度判失败。"""
|
|
template = Path("samples/phase5-slice/template.docx")
|
|
if not template.exists():
|
|
import pytest
|
|
pytest.skip("样本模板缺失")
|
|
parsed = WordTemplateParser().parse(str(template))
|
|
ss = StructuredSource(template=parsed, tables=[], rule_docs=[], image_analyses=[],
|
|
existing_system=None, comments=[])
|
|
out = tmp_path / "o.docx"
|
|
|
|
class ZhEngine:
|
|
def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
|
|
return SimpleNamespace(
|
|
data={"title": variables["title"],
|
|
"blocks": [{"type": "paragraph",
|
|
"text": "由 FakeLLM 生成的充分说明内容，满足写入规则要求。"}]},
|
|
status="ok",
|
|
)
|
|
loop = QALoop(max_rounds=1)
|
|
# 显式 ja + 中文 Fake：writer 生成阶段即因语言不一致硬失败（设计语义）
|
|
try:
|
|
loop.run(ss, str(out), samples_dir="nonexistent_dir_xyz",
|
|
engine=ZhEngine(), template_path=str(template), output_language="ja")
|
|
assert False, "应抛出 WriterGenerationError"
|
|
except WriterGenerationError:
|
|
pass
|