feat(writer): 输出语言一致性保障 + 用户可选输出语言

- 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）
2026-08-25 23:30:24 +08:00
parent 9d0d3409c2
commit d01e1b720f
20 changed files with 1049 additions and 31 deletions
@@ -0,0 +1,172 @@
+"""步骤 A：确定性语言检测 + 输出语言强制测试。
+
+- detect_script：含假名→ja，CJK 零假名→zh，否则 None
+- resolve_expected_language：显式 > 标题假名 > 规则文档主导脚本 > ""（不可验证）
+- find_language_violations：仅检正文块（heading/table 不检），长度≥12 防误杀
+- WriterAgent.generate_chapter：期望语言非空时违规即重试，耗尽→硬失败
+"""
+from __future__ import annotations
+
+from genesis.writer.language import (
+    detect_script,
+    find_language_violations,
+    resolve_expected_language,
+)
+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
+
+
+# ---------- detect_script ----------
+
+def test_detect_script_kana_is_ja():
+    assert detect_script("機能一覧の説明を記述します。") == "ja"
+
+
+def test_detect_script_cjk_no_kana_is_zh():
+    assert detect_script("功能一览的说明内容。") == "zh"
+
+
+def test_detect_script_ascii_is_none():
+    assert detect_script("Hello world 123") is None
+
+
+def test_detect_script_mixed_cjk_kana_is_ja():
+    # 含假名即判 ja，即使混有汉字（中文不可能含日文假名）
+    assert detect_script("DB設計の概要を説明する。") == "ja"
+
+
+# ---------- resolve_expected_language ----------
+
+def test_resolve_explicit_overrides():
+    assert resolve_expected_language("zh", "DB 設計", ["日本語の影響"]) == "zh"
+    assert resolve_expected_language("ja", "DB 设計", ["中文影响"]) == "ja"
+
+
+def test_resolve_falls_back_to_title_kana():
+    # 标题含假名→ja（注意：纯汉字日文标题如「DB設計」无假名，会落入 fallback）
+    assert resolve_expected_language("auto", "機能一覧の説明", []) == "ja"
+
+
+def test_resolve_falls_back_to_fallback_text():
+    # 标题纯汉字无假名（中文式）→ 看 fallback（日文影响书）→ ja
+    assert resolve_expected_language("auto", "DB 設計", ["影響調査の結果（日本語）"]) == "ja"
+
+
+def test_resolve_unverifiable_when_no_hint():
+    assert resolve_expected_language("auto", "DB 設計", ["123 abc"]) == ""
+
+
+# ---------- find_language_violations ----------
+
+def _blocks(*specs):
+    out = []
+    for i, (t, text) in enumerate(specs):
+        out.append(ContentBlock(block_id=str(i), type=t, text=text))
+    return out
+
+
+def test_violation_ja_expected_but_pure_chinese_paragraph():
+    blocks = _blocks(("paragraph", "这是一段纯中文的章节正文内容。"))
+    viol = find_language_violations(blocks, "ja")
+    assert viol  # 期望日文却为中文 → 违规
+
+
+def test_no_violation_ja_expected_japanese_paragraph():
+    blocks = _blocks(("paragraph", "本機能は注文処理を行う画面であり、詳細は以下の通り。"))
+    assert not find_language_violations(blocks, "ja")
+
+
+def test_heading_and_table_blocks_excluded():
+    # heading 与 table（照抄原文）即使含中文也不算违规
+    blocks = _blocks(
+        ("heading", "機能一覧表"),
+        ("table", "機能ID 機能名"),  # 表格不检
+        ("paragraph", "本機能は注文処理を行う。"),
+    )
+    assert not find_language_violations(blocks, "ja")
+
+
+def test_short_chinese_not_flagged_under_threshold():
+    # 长度<12 的短术语不误杀
+    blocks = _blocks(("paragraph", "中文术语"))
+    assert not find_language_violations(blocks, "ja")
+
+
+def test_violation_zh_expected_but_kana_present():
+    blocks = _blocks(("paragraph", "本機能は注文処理を行う画面である。"))
+    assert find_language_violations(blocks, "zh")
+
+
+# ---------- WriterAgent 强制 ----------
+
+class MixedLanguageEngine:
+    """返回中英混杂（期望日文时违规）的章节内容。"""
+    def __init__(self, texts):
+        self._texts = list(texts)
+        self._i = 0
+    def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
+        from types import SimpleNamespace
+        text = self._texts[min(self._i, len(self._texts) - 1)]
+        self._i += 1
+        return SimpleNamespace(
+            data={"title": variables["title"], "blocks": [{"type": "paragraph", "text": text}]},
+            status="ok",
+        )
+
+
+class FakePromptRegistry:
+    @staticmethod
+    def get_or_create(name, template):
+        from types import SimpleNamespace
+        return SimpleNamespace(name=name, version="1", template=template)
+
+
+def _ctx_with_lang(cid, title, lang):
+    return GenerationContext(
+        chapter_id=cid, title=title,
+        template_marker=ChapterSpec(chapter_id=cid, title=title),
+        structured_source=None, write_rules=[], design_rules=[],
+        template_styles=set(), output_language=lang,
+    )
+
+
+def test_generate_chapter_retries_on_language_violation_then_passes():
+    # 第一次返回中文（ja 期望→违规），第二次返回日文（通过）
+    engine = MixedLanguageEngine([
+        "这是一段纯中文的章节正文内容，应当被判定为语言违规。",
+        "本機能は注文処理を行う画面であり、詳細は以下の通り記述する。",
+    ])
+    agent = WriterAgent(session_id="s", engine=engine,
+                        prompt_registry=FakePromptRegistry(),
+                        state=WriterState(["db_design"]), max_retries=3)
+    content = agent.generate_chapter(_ctx_with_lang("db_design", "DB 設計", "ja"))
+    assert content is not None
+    assert "本機能" in content.blocks[0].text
+
+
+def test_generate_chapter_hard_fails_when_violation_persists():
+    # 始终返回中文（ja 期望），重试耗尽→硬失败
+    engine = MixedLanguageEngine([
+        "这是一段纯中文的章节正文内容，应当被判定为语言违规。",
+        "还是一段纯中文的章节正文内容，依旧违规。",
+    ])
+    agent = WriterAgent(session_id="s", engine=engine,
+                        prompt_registry=FakePromptRegistry(),
+                        state=WriterState(["db_design"]), max_retries=2)
+    try:
+        agent.generate_chapter(_ctx_with_lang("db_design", "DB 設計", "ja"))
+        assert False, "应抛出 WriterGenerationError"
+    except WriterGenerationError as e:
+        assert "语言" in str(e) or "language" in str(e).lower()
+
+
+def test_generate_chapter_auto_unverifiable_not_enforced():
+    # auto 且无法推导期望语言（标题纯汉字无假名、无日文 fallback）→ 不强制，直接通过
+    engine = MixedLanguageEngine(["这是中文正文但 auto 不可验证所以放行。"])
+    agent = WriterAgent(session_id="s", engine=engine,
+                        prompt_registry=FakePromptRegistry(),
+                        state=WriterState(["db_design"]), max_retries=1)
+    content = agent.generate_chapter(_ctx_with_lang("db_design", "DB 設計", "auto"))
+    assert content is not None