Files
life-echo/api/app/features/memoir/narrative_to_markdown.py
Kevin 07c6478742 feat(api): 访谈路径轻量门控、Memoir Phase1 批处理与叙事/记忆管线加固
- 新增 utterance_substance:短时/应答/元话语可跳过记忆检索、阶段 LLM 与资料抽取 LLM;可配置
- 输入归一化:LLM 模式默认仅语音/ASR;配置项写入 .env.example
- Memoir Phase1:可选 batch LLM 一次性抽取+分类(失败回退逐段);Extraction 空槽位时阶段与 current_stage 对齐,prompt 约束收紧
- 叙事与忠实度:narrative_safety、证据重叠/场合锚点、标题 slots 与履历短语 grounded;fidelity 解析失败 fail-open 可配置
- 章节管线:锁 TTL 上调、锁竞争 Celery 重试、Phase2 immediate singleflight 等;story_pipeline_sync / chapter_compose / memoir_tasks 联动
- Memory:compaction / repo / summarizer / evidence 小修;事实 FTS 未命中是否回退最近事实可配置
- 新增 memoir_pipeline_trace;补充 memoir_reliability 文档与多项回归/门控测试
2026-04-03 10:12:59 +08:00

35 lines
1.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
"""将 NarrativeAgent / LLM 返回的 JSON 或纯文本规范为 markdown 正文。"""
from __future__ import annotations
import json
def narrative_to_markdown(narrative: str) -> str:
"""
将 narrativeJSON paragraphs 或纯文本)转为 markdown。
与已删除的 ChapterComposerOrchestrator._to_markdown 行为一致。
"""
if not narrative or not str(narrative).strip():
return ""
stripped = narrative.strip()
if stripped.startswith("{") and "paragraphs" in stripped:
try:
data = json.loads(stripped)
paras = data.get("paragraphs", [])
if isinstance(paras, list):
parts = []
for p in paras:
if isinstance(p, dict):
text = p.get("content", p.get("text", ""))
else:
text = str(p)
if text.strip():
parts.append(text.strip())
return "\n\n".join(parts)
return stripped
except json.JSONDecodeError:
# 不得以伪 JSON 字符串落库;上层 _coalesce_story_markdown 会回退口述/旧文
return ""
return stripped