lhl
becd3e1f57
按《参赛成果物提交规范·赛道一》§6 红线： - samples/ 目录改名 sample/（git mv，保留历史） - 10 个中日文样本文件 + docs 参赛手册 PDF 重命名为 ASCII （requirements_*/template_*/rules_*/contestant-handbook.pdf） - tests/test_zh_template.py 硬编码绝对路径 D:\00_project\Genesis 改为相对路径 - 全局更新 21 个活动文件引用；历史日志/审查文档不改（追加说明记录） 全量 pytest 431 passed / 99.15%
74 lines
3.8 KiB
Python
74 lines
3.8 KiB
Python
"""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 genesis.inference.factory import build_inference_engine
|
|
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, _warn_unanchored
|
|
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, 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)
|
|
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="sample", 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()
|
|
# 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(
|
|
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},
|
|
output_language=output_language,
|
|
)
|
|
report = validator.validate_doc(contents, structured_source, expected_language=expected)
|
|
return report
|