786ebf8ae6
- 对齐「多智能体收敛」与「回忆录 stories-first / markdown-first」方向：收紧运行时契约、 删除过渡兼容路径与双轨逻辑，并同步更新客户端与文档。 - Chat：以 ChatOrchestrator 为实时编排入口；删除独立 conversation_agent，精简 prompts。 - Memoir：删除 memory_agent；MemoirOrchestrator、classification / story_route 与 prompts 收敛到 prepare_batches + run_story_pipeline_for_category_batch 主链路。 - 将 agents 侧 processor 迁入 feature 层为 background_runner，并移除 features 下重复/过时 processor 封装。 - 新增 history_store，强化「conversation_messages 为 DB 真源、Redis 为缓存」模型。 - 调整 models、repo、service、session_history；精简 WS message_types，重构 pipeline 与 router。 - 移除章节占位、整章再生等旧路径；章节列表与封面逻辑要求 story 关联；收紧 cover 资格与 enqueue。 - helpers、repo、service、router、reading_segment_materialize、story_pipeline_sync、pdf_service 等按 canonical markdown / cover_asset_id 收缩；删除 memoir_images/provider 等冗余。 - tasks：memoir_tasks、chapter_cover_tasks 等大幅瘦身；story_image_tasks 等与当前图片任务对齐。 - core：config、logging、redis、task_tracker 小幅调整。 - auth / user / payment / quota：路由或服务侧删减过时接口或逻辑（如 payment router 行数减少）。 - pyproject.toml、development.sh、.env.example / .env.production、README 等同步说明或变量。 - Alembic 0001_initial_schema 微调（与当前 schema 叙事一致的小改动）。 - 回忆录：types / mappers / api、章节页与 memoir 页与后端契约对齐；markdown-renderer 调整。 - 语音：删除 voice/player，voice-segment-store 相应精简。 - api/tests：删除 conftest 及绝大部分既有测试文件（websocket_baseline、conversation、memoir 图片、PDF、SMS 等），属有意收缩/待按 backend-test-system 重建的信号。 - docs：新增多智能体收敛与移除兼容层计划摘要；更新 story-first 设计、backend-test-system、 multi-agent-refactor-plan、实施总结等。 BREAKING CHANGE: 后端对外契约、回忆录章节字段与若干路由/任务行为已变更；大量 API 测试被移除， CI 若依赖这些用例需按新策略补测或调整流水线。
110 lines
3.4 KiB
Python
110 lines
3.4 KiB
Python
import json
|
||
import re
|
||
from typing import Any
|
||
|
||
from app.features.memoir.asset_resolver import strip_image_placeholders
|
||
|
||
from .json_payload import extract_json_payload
|
||
from .schema import IMAGE_STATUS_PENDING
|
||
|
||
PLACEHOLDER_RE = re.compile(
|
||
r"\{\{\{\{IMAGE:(.*?)\}\}\}\}|\{\{IMAGE:(.*?)\}\}",
|
||
re.DOTALL,
|
||
)
|
||
|
||
|
||
def parse_image_placeholders(content: str, max_images: int) -> list[dict[str, Any]]:
|
||
"""离线迁移/调试用：解析正文中的 IMAGE 占位符。"""
|
||
items: list[dict[str, Any]] = []
|
||
for match in PLACEHOLDER_RE.finditer(content or ""):
|
||
description = (match.group(1) or match.group(2) or "").strip()
|
||
if not description:
|
||
continue
|
||
items.append(
|
||
{
|
||
"index": len(items),
|
||
"description": description,
|
||
"placeholder": match.group(0),
|
||
"start_offset": match.start(),
|
||
}
|
||
)
|
||
if max_images is not None and len(items) >= max_images:
|
||
break
|
||
return items
|
||
|
||
|
||
def build_initial_image_assets(
|
||
placeholders: list[dict[str, Any]],
|
||
provider: str,
|
||
style: str,
|
||
size: str,
|
||
now_iso: str,
|
||
) -> list[dict[str, Any]]:
|
||
return [
|
||
{
|
||
"index": item["index"],
|
||
"placeholder": item["placeholder"],
|
||
"description": item["description"],
|
||
"prompt": None,
|
||
"url": None,
|
||
"status": IMAGE_STATUS_PENDING,
|
||
"provider": provider,
|
||
"style": style,
|
||
"size": size,
|
||
"error": None,
|
||
"created_at": now_iso,
|
||
"updated_at": now_iso,
|
||
}
|
||
for item in placeholders
|
||
]
|
||
|
||
|
||
def parse_narrative_json(raw: str) -> list[dict[str, Any]]:
|
||
"""
|
||
解析 LLM 输出的 JSON 叙事（paragraphs）。
|
||
不根据 image_description 生成配图占位；插图由 story/chapter 结构化流程单独处理。
|
||
"""
|
||
if not raw or not str(raw).strip():
|
||
return []
|
||
try:
|
||
payload = extract_json_payload(raw)
|
||
data = json.loads(payload)
|
||
paragraphs = data.get("paragraphs") or []
|
||
if not isinstance(paragraphs, list):
|
||
return []
|
||
except (json.JSONDecodeError, TypeError, AttributeError):
|
||
return []
|
||
|
||
result: list[dict[str, Any]] = []
|
||
for p in paragraphs:
|
||
if not isinstance(p, dict):
|
||
continue
|
||
content = (p.get("content") or "").strip()
|
||
if content:
|
||
result.append({"content": content, "placeholder_info": None})
|
||
return result
|
||
|
||
|
||
def split_plain_narrative_into_sections(narrative: str) -> list[dict[str, Any]]:
|
||
"""非 JSON 叙事：去掉遗留占位符后按空行拆段，不产生段落配图。"""
|
||
text = strip_image_placeholders(narrative or "")
|
||
if not text.strip():
|
||
return []
|
||
parts = [p.strip() for p in text.split("\n\n") if p.strip()]
|
||
return [{"content": p, "placeholder_info": None} for p in parts]
|
||
|
||
|
||
def parse_narrative_to_sections(narrative: str) -> list[dict[str, Any]]:
|
||
"""
|
||
将 narrative 解析为 sections。
|
||
JSON（paragraphs）走 parse_narrative_json；否则剥离占位符后按段拆分。
|
||
"""
|
||
if not narrative or not str(narrative).strip():
|
||
return []
|
||
stripped = narrative.strip()
|
||
if stripped.startswith("{") and "paragraphs" in stripped:
|
||
segments = parse_narrative_json(narrative)
|
||
if segments:
|
||
return segments
|
||
return split_plain_narrative_into_sections(narrative)
|