feat(qa): add QALoop (closed loop, regenerate only failed chapters)

2026-08-13 11:12:22 +08:00
parent b318c9fd41
commit 24d3aa3b85
2 changed files with 126 additions and 0 deletions
@@ -0,0 +1,70 @@
+"""QA 闭环：生成 → 校验 → 仅重生成失败章 → 复校验（Phase 5）。"""
+from __future__ import annotations
+
+from pathlib import Path
+from types import SimpleNamespace
+
+from genesis.inference.engine import InferenceEngine
+from genesis.inference.prompt_registry import PromptRegistry
+from genesis.qa.guardrails import DEFAULT_MAX_QA_ROUNDS, QALoopController
+from genesis.qa.report import QAReport
+from genesis.qa.validator import QAValidator
+from genesis.writer.context_builder import build_contexts
+from genesis.writer.docx_injector import Block, DocxInjector
+from genesis.writer.models import ChapterContent
+from genesis.writer.orchestrator import _section_id_of
+from genesis.writer.renderer import render_chapter_blocks
+from genesis.writer.writer_agent import WriterAgent
+from genesis.writer.writer_state import WriterState
+
+
+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)
+        state = WriterState([c.chapter_id for c in ctxs])
+        agent = WriterAgent(session_id=session_id, engine=engine, prompt_registry=prompt_registry, state=state)
+        contents_map = dict(prev) if prev else {}
+        order = [c.chapter_id for c in ctxs]
+        sections: dict[str, list[Block]] = {}
+        for ctx in ctxs:
+            if only_ids is not None and ctx.chapter_id not in only_ids and ctx.chapter_id in contents_map:
+                content = contents_map[ctx.chapter_id]
+            else:
+                content = agent.generate_chapter(ctx)
+                contents_map[ctx.chapter_id] = content
+            blocks = render_chapter_blocks(content)
+            sec_id = _section_id_of(ctx.template_marker.section_placeholder)
+            if sec_id:
+                sections[sec_id] = blocks
+        tpl = template_path or getattr(structured_source.template, "file_name", None)
+        if not tpl:
+            raise ValueError("template_path 必须提供")
+        Path(output_path).parent.mkdir(parents=True, exist_ok=True)
+        doc = DocxInjector(tpl).inject(sections, meta={})
+        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:
+        engine = engine or InferenceEngine()
+        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)
+        while self.controller.can_continue() and report.failed_chapters:
+            self.controller.advance()
+            contents = self._build(
+                structured_source,
+                samples_dir,
+                engine,
+                prompt_registry,
+                template_path,
+                output_path,
+                session_id,
+                only_ids=set(report.failed_chapters),
+                prev={c.chapter_id: c for c in contents},
+            )
+            report = validator.validate_doc(contents, structured_source)
+        return report
@@ -0,0 +1,56 @@
+import pytest
+from types import SimpleNamespace
+from docx import Document
+
+from genesis.data_models import ParsedTemplate, ChapterMarker
+from genesis.qa.qa_loop import QALoop
+from genesis.writer.models import ChapterContent
+
+
+class ImprovingEngine:
+    def __init__(self):
+        self.calls: dict[str, int] = {}
+
+    def chat_structured(self, *, session_id, prompt, variables, schema, retry_count=2):
+        cid = variables["title"]
+        self.calls[cid] = self.calls.get(cid, 0) + 1
+        n = self.calls[cid]
+        # "a" 首次即通过；"b" 首次太短失败，第二次（n>=2）充分
+        text = "充分且规范的说明内容，满足写入规则要求。" if (cid == "A" or n >= 2) else "x"
+        return SimpleNamespace(data={"title": cid, "blocks": [{"type": "paragraph", "text": text}]}, status="ok")
+
+
+def _make_template(path):
+    doc = Document()
+    doc.add_paragraph("A", style="Heading 1")
+    doc.add_paragraph("{{section:a}}")
+    doc.add_paragraph("B", style="Heading 1")
+    doc.add_paragraph("{{section:b}}")
+    doc.save(path)
+
+
+def _ss(template_path):
+    parsed = ParsedTemplate(
+        file_name=template_path,
+        sections=[
+            ChapterMarker(type="heading", name="A", level=1),
+            ChapterMarker(type="placeholder", name="section:a", level=0),
+            ChapterMarker(type="heading", name="B", level=1),
+            ChapterMarker(type="placeholder", name="section:b", level=0),
+        ],
+        placeholders={},
+        styles={"defined": ["Heading 1"], "used": ["Heading 1"]},
+    )
+    return SimpleNamespace(template=parsed)
+
+
+def test_qa_loop_regenerates_only_failed(tmp_path):
+    tpl = tmp_path / "tpl.docx"
+    out = tmp_path / "out.docx"
+    _make_template(str(tpl))
+    engine = ImprovingEngine()
+    loop = QALoop(max_rounds=3)
+    report = loop.run(_ss(str(tpl)), str(out), samples_dir="nonexistent_dir_xyz", engine=engine)
+    assert report.passed is True
+    assert engine.calls["A"] == 1   # A 首次即通过，未被重生成
+    assert engine.calls["B"] == 2   # B 失败后被重生成一次