fix(writer): 章节级数据注入 + 修复 prompt 从未渲染的关键缺陷

- models: CHAPTER_SHEET_TYPES/CHAPTER_IMPACT_ELEMENT 章节→数据映射（design §6.8 ①） - models: _format_chapter_data 按章定向渲染 ExcelTable 为 Markdown；GENERIC 自由記述作通用背景 - models: _format_impact 支持按 ElementType 过滤（章节级影响上下文） - writer_agent: {{source}}(全量repr) → {{data}}(章节数据)；新增【主题约束】 - writer_agent: 关键修复——真实 PromptRegistry.get 返回模板字符串，引擎对 str 不做变量渲染，LLM 实际收到的是 {{占位符}} 原文； _resolve_prompt 统一包装为 Prompt 对象保证渲染 - 真实试运行验证：13 章主题全部正确、引用影响调查数据、语言漂移消除
2026-08-24 11:50:59 +08:00
parent 6372bb17b9
commit 80ccc324fc
6 changed files with 410 additions and 27 deletions
@@ -66,6 +66,116 @@ def test_prompt_template_has_impact_context_var():
    assert "{{impact}}" in WRITER_PROMPT_TEMPLATE


+def test_prompt_template_enforces_topic_and_chapter_data():
+    # 主题约束：正文必须围绕本章标题主题，依据章节数据，禁止套用系统整体架构
+    assert "主题约束" in WRITER_PROMPT_TEMPLATE
+    assert "参考资料（本章对应数据）" in WRITER_PROMPT_TEMPLATE
+    assert "{{data}}" in WRITER_PROMPT_TEMPLATE
+    # 旧的全量 source 变量不再使用
+    assert "{{source}}" not in WRITER_PROMPT_TEMPLATE
+
+
+class RecordingEngine(FakeEngine):
+    """记录 variables 以断言 prompt 渲染输入。"""
+
+    def __init__(self):
+        super().__init__()
+        self.last_vars = None
+
+    def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
+        self.last_vars = dict(variables)
+        return super().chat_structured(
+            session_id=session_id, prompt=prompt,
+            variables=variables, schema=schema, retry_count=retry_count,
+        )
+
+
+class RealStylePromptRegistry:
+    """模拟真实 PromptRegistry：无 get_or_create，get() 返回模板字符串（非 Prompt）。"""
+
+    def __init__(self):
+        self._tpl = {}
+
+    def register(self, name, version, template):
+        self._tpl[(name, version)] = template
+
+    def get(self, name, version=None):
+        return self._tpl[(name, version)]
+
+
+class RenderingEngine:
+    """模拟真实引擎渲染行为：仅当收到 Prompt 对象时才用 jinja2 渲染（engine._render_prompt 契约）。"""
+
+    def __init__(self):
+        self.last_rendered = None
+
+    def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
+        from jinja2 import Template
+        from genesis.inference.types import Prompt as P
+        tpl = prompt.template if isinstance(prompt, P) else prompt  # str 原样返回 → 不渲染
+        self.last_rendered = Template(tpl).render(**variables) if isinstance(prompt, P) else tpl
+        return SimpleNamespace(
+            data={"title": variables["title"], "blocks": [{"type": "paragraph", "text": "ok"}]},
+            status="ok",
+        )
+
+
+def test_prompt_is_rendered_with_real_style_registry():
+    """回归：真实 PromptRegistry.get 返回模板字符串 → 引擎按 str 原样发送，
+    {{data}}/{{title}} 等占位符从未被替换（真实试运行暴露）。
+    WriterAgent 必须保证交给引擎的是可渲染的 Prompt 对象。"""
+    agent = WriterAgent(
+        session_id="s",
+        engine=RenderingEngine(),
+        prompt_registry=RealStylePromptRegistry(),
+        state=WriterState(["db_design"]),
+    )
+    ctx = _ctx("db_design", "DB 設計")
+    agent.generate_chapter(ctx)
+    assert "{{" not in agent.engine.last_rendered          # 无残留占位符
+    assert "DB 設計" in agent.engine.last_rendered         # title 已渲染
+    assert "W1" in agent.engine.last_rendered              # write_rules 已渲染
+
+
+def test_generate_chapter_passes_chapter_scoped_data_var():
+    from genesis.data_models import (
+        CellValue, ExcelTable, ParsedTemplate, ChapterMarker,
+        Provenance, SheetType, StructuredSource,
+    )
+
+    def cell(v):
+        return CellValue(value=v, provenance=Provenance("f.xlsx", "s", 1, "A", "列"))
+
+    src = StructuredSource(
+        tables=[
+            ExcelTable("DB定義", SheetType.DATABASE, "openpyxl",
+                       ["テーブルID", "テーブル名"],
+                       [{"テーブルID": cell("T001"), "テーブル名": cell("trade_order")}]),
+            ExcelTable("機能一覧", SheetType.FUNCTION, "openpyxl",
+                       ["機能ID", "機能名"],
+                       [{"機能ID": cell("F001"), "機能名": cell("止损风控")}]),
+        ],
+        template=ParsedTemplate("t.docx",
+                                [ChapterMarker(type="heading", name="x", level=1)],
+                                {}, {"used": []}),
+        rule_docs=[], image_analyses=[], existing_system=None, comments=[],
+    )
+    ctx = GenerationContext(
+        chapter_id="db_design", title="DB 設計",
+        template_marker=ChapterSpec(chapter_id="db_design", title="DB 設計", section_placeholder=None),
+        structured_source=src, write_rules=["W1"], design_rules=["D1"],
+        template_styles={"Heading1"},
+    )
+    engine = RecordingEngine()
+    agent = WriterAgent(session_id="s", engine=engine,
+                        prompt_registry=FakePromptRegistry(),
+                        state=WriterState(["db_design"]))
+    agent.generate_chapter(ctx)
+    data = engine.last_vars["data"]
+    assert "T001" in data and "trade_order" in data   # 本章对应数据
+    assert "止损风控" not in data                      # 其他章数据被排除
+
+
 def test_generate_chapter_retries():
    class Boom(FakeEngine):
        def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):