Coverage for src\genesis\qa\qa_loop.py: 95%

1"""QA 闭环：生成 → 校验 → 仅重生成失败章 → 复校验（Phase 5）。""" 

2from __future__ import annotations 

3 

4from pathlib import Path 

5 

6from genesis.inference.factory import build_inference_engine 

7from genesis.inference.prompt_registry import PromptRegistry 

8from genesis.qa.guardrails import DEFAULT_MAX_QA_ROUNDS, QALoopController 

9from genesis.qa.report import QAReport 

10from genesis.qa.validator import QAValidator 

11from genesis.writer.context_builder import build_contexts 

12from genesis.writer.docx_injector import Block, DocxInjector 

13from genesis.writer.models import ChapterContent 

14from genesis.writer.orchestrator import _section_id_of, _warn_unanchored 

15from genesis.writer.renderer import render_chapter_blocks 

16from genesis.writer.writer_agent import WriterAgent 

17from genesis.writer.writer_state import WriterState 

18 

19 

20class QALoop: 

21 def __init__(self, max_rounds: int = DEFAULT_MAX_QA_ROUNDS) -> None: 

22 self.controller = QALoopController(max_rounds=max_rounds) 

23 

24 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"): 

25 ctxs = build_contexts(structured_source, samples_dir, output_language=output_language) 

26 _warn_unanchored(ctxs) 

27 state = WriterState([c.chapter_id for c in ctxs]) 

28 agent = WriterAgent(session_id=session_id, engine=engine, prompt_registry=prompt_registry, state=state) 

29 contents_map = dict(prev) if prev else {} 

30 order = [c.chapter_id for c in ctxs] 

31 sections: dict[str, list[Block]] = {} 

32 for ctx in ctxs: 

33 if only_ids is not None and ctx.chapter_id not in only_ids and ctx.chapter_id in contents_map: 

34 content = contents_map[ctx.chapter_id] 

35 else: 

36 content = agent.generate_chapter(ctx) 

37 contents_map[ctx.chapter_id] = content 

38 blocks = render_chapter_blocks(content) 

39 sec_id = _section_id_of(ctx.template_marker.section_placeholder) 

40 if sec_id: 40 ↛ 32line 40 didn't jump to line 32 because the condition on line 40 was always true

41 sections[sec_id] = blocks 

42 tpl = template_path or getattr(structured_source.template, "file_name", None) 

43 if not tpl: 43 ↛ 44line 43 didn't jump to line 44 because the condition on line 43 was never true

44 raise ValueError("template_path 必须提供") 

45 Path(output_path).parent.mkdir(parents=True, exist_ok=True) 

46 doc = DocxInjector(tpl).inject(sections, meta={}) 

47 doc.save(output_path) 

48 return [contents_map[cid] for cid in order] 

49 

50 def run(self, structured_source, output_path, session_id="writer", samples_dir="sample", engine=None, prompt_registry=None, template_path=None, output_language: str = "auto") -> QAReport: 

51 engine = engine or build_inference_engine() 

52 prompt_registry = prompt_registry or PromptRegistry() 

53 validator = QAValidator() 

54 # auto 不可推导期望语言 → 语言维度记满分（unverifiable）；zh/ja 显式强制 

55 expected = output_language if output_language in ("zh", "ja") else "" 

56 contents = self._build(structured_source, samples_dir, engine, prompt_registry, template_path, output_path, session_id, output_language=output_language) 

57 report = validator.validate_doc(contents, structured_source, expected_language=expected) 

58 while self.controller.can_continue() and report.failed_chapters: 

59 self.controller.advance() 

60 contents = self._build( 

61 structured_source, 

62 samples_dir, 

63 engine, 

64 prompt_registry, 

65 template_path, 

66 output_path, 

67 session_id, 

68 only_ids=set(report.failed_chapters), 

69 prev={c.chapter_id: c for c in contents}, 

70 output_language=output_language, 

71 ) 

72 report = validator.validate_doc(contents, structured_source, expected_language=expected) 

73 return report