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）

src/genesis/qa/qa_loop.py

@@ -21,8 +21,8 @@ class QALoop:
     def __init__(self, max_rounds: int = DEFAULT_MAX_QA_ROUNDS) -> None:
         self.controller = QALoopController(max_rounds=max_rounds)
 
-    def _build(self, structured_source, samples_dir, engine, prompt_registry, template_path, output_path, session_id, only_ids=None, prev=None):
-        ctxs = build_contexts(structured_source, samples_dir)
+    def _build(self, structured_source, samples_dir, engine, prompt_registry, template_path, output_path, session_id, only_ids=None, prev=None, output_language: str = "auto"):
+        ctxs = build_contexts(structured_source, samples_dir, output_language=output_language)
         _warn_unanchored(ctxs)
         state = WriterState([c.chapter_id for c in ctxs])
         agent = WriterAgent(session_id=session_id, engine=engine, prompt_registry=prompt_registry, state=state)
@@ -47,12 +47,14 @@ class QALoop:
         doc.save(output_path)
         return [contents_map[cid] for cid in order]
 
-    def run(self, structured_source, output_path, session_id="writer", samples_dir="samples", engine=None, prompt_registry=None, template_path=None) -> QAReport:
+    def run(self, structured_source, output_path, session_id="writer", samples_dir="samples", engine=None, prompt_registry=None, template_path=None, output_language: str = "auto") -> QAReport:
         engine = engine or build_inference_engine()
         prompt_registry = prompt_registry or PromptRegistry()
         validator = QAValidator()
-        contents = self._build(structured_source, samples_dir, engine, prompt_registry, template_path, output_path, session_id)
-        report = validator.validate_doc(contents, structured_source)
+        # auto 不可推导期望语言 → 语言维度记满分（unverifiable）；zh/ja 显式强制
+        expected = output_language if output_language in ("zh", "ja") else ""
+        contents = self._build(structured_source, samples_dir, engine, prompt_registry, template_path, output_path, session_id, output_language=output_language)
+        report = validator.validate_doc(contents, structured_source, expected_language=expected)
         while self.controller.can_continue() and report.failed_chapters:
             self.controller.advance()
             contents = self._build(
@@ -65,6 +67,7 @@ class QALoop:
                 session_id,
                 only_ids=set(report.failed_chapters),
                 prev={c.chapter_id: c for c in contents},
+                output_language=output_language,
             )
-            report = validator.validate_doc(contents, structured_source)
+            report = validator.validate_doc(contents, structured_source, expected_language=expected)
         return report