test(qa): add headless Phase5 e2e (FakeLLM pipeline)

2026-08-13 11:23:00 +08:00
parent 86c3abb5fa
commit 64c271a22c
1 changed files with 54 additions and 0 deletions
@@ -0,0 +1,54 @@
+import pytest
+from types import SimpleNamespace
+from pathlib import Path
+
+from docx import Document
+
+from genesis.data_models import StructuredSource
+from genesis.parsers.word_template_parser import WordTemplateParser
+from genesis.qa.qa_loop import QALoop
+
+
+class FakeEngine:
+    def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
+        cid = variables.get("title", "x")
+        return SimpleNamespace(
+            data={
+                "title": cid,
+                "blocks": [
+                    {"type": "heading", "level": 2, "text": f"{cid} 小节"},
+                    {"type": "paragraph", "text": "由 FakeLLM 生成的充分说明内容，满足写入规则要求。"},
+                    {"type": "table", "caption": "示例表", "rows": [["列1", "列2"], ["值1", "值2"]]},
+                ],
+            },
+            status="ok",
+        )
+
+
+def _all_text(doc: Document) -> str:
+    parts = [p.text for p in doc.paragraphs]
+    for tbl in doc.tables:
+        for row in tbl.rows:
+            for cell in row.cells:
+                parts.append(cell.text)
+    return "\n".join(parts)
+
+
+def test_phase5_e2e_fake_llm(tmp_path):
+    template = Path("samples/phase5-slice/template.docx")
+    if not template.exists():
+        pytest.skip("样本模板缺失，跳过 e2e")
+    parsed = WordTemplateParser().parse(str(template))
+    ss = StructuredSource(
+        template=parsed, tables=[], rule_docs=[], image_analyses=[], existing_system=None, comments=[]
+    )
+    out = tmp_path / "e2e_out.docx"
+    loop = QALoop(max_rounds=2)
+    report = loop.run(
+        ss, str(out), samples_dir="nonexistent_dir_xyz", engine=FakeEngine(), template_path=str(template)
+    )
+    assert report.passed is True
+    loaded = Document(str(out))
+    text = _all_text(loaded)
+    assert "由 FakeLLM 生成的充分说明内容" in text
+    assert "示例表" in text