refactor(api,expo): 多智能体与会话收敛、回忆录兼容层移除、后端测试集大幅删减
- 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。
This commit is contained in:
Kevin
@@ -2,110 +2,48 @@
|
||||
PDF 生成服务（从 services 迁入 memoir feature）
|
||||
"""
|
||||
|
||||
from app.core.logging import get_logger
|
||||
from io import BytesIO
|
||||
from typing import List, Optional
|
||||
|
||||
import httpx
|
||||
from PIL import Image
|
||||
from reportlab.lib.pagesizes import A4
|
||||
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
|
||||
from reportlab.lib.styles import ParagraphStyle, getSampleStyleSheet
|
||||
from reportlab.lib.units import inch
|
||||
from reportlab.pdfbase import pdfmetrics
|
||||
from reportlab.pdfbase.cidfonts import UnicodeCIDFont
|
||||
from reportlab.platypus import (
|
||||
Image as ReportLabImage,
|
||||
)
|
||||
from reportlab.platypus import (
|
||||
PageBreak,
|
||||
Paragraph,
|
||||
SimpleDocTemplate,
|
||||
Spacer,
|
||||
)
|
||||
from reportlab.pdfbase import pdfmetrics
|
||||
from reportlab.pdfbase.cidfonts import UnicodeCIDFont
|
||||
|
||||
from app.core.logging import get_logger
|
||||
from app.features.memoir.asset_resolver import (
|
||||
collect_asset_ids_from_markdown,
|
||||
split_markdown_by_asset_refs,
|
||||
strip_legacy_image_placeholders,
|
||||
strip_image_placeholders,
|
||||
)
|
||||
from app.features.memoir.chapter_markdown_compose import (
|
||||
materialize_chapter_pdf_markdown_from_loaded_chapter,
|
||||
)
|
||||
from app.features.memoir.helpers import (
|
||||
_chapter_markdown,
|
||||
sections_to_content_and_images,
|
||||
)
|
||||
from app.features.memoir.helpers import _chapter_markdown
|
||||
|
||||
logger = get_logger(__name__)
|
||||
|
||||
|
||||
def _chapter_markdown_for_pdf(chapter) -> str:
|
||||
"""有 story 编排时 PDF 使用「## 故事名 + 正文」物化；否则沿用章节 canonical。"""
|
||||
links = getattr(chapter, "story_links", None) or []
|
||||
if links and any(getattr(l, "story", None) for l in links):
|
||||
if links and any(getattr(link, "story", None) for link in links):
|
||||
return materialize_chapter_pdf_markdown_from_loaded_chapter(chapter)
|
||||
return _chapter_markdown(chapter)
|
||||
|
||||
|
||||
from app.features.memoir.memoir_images.parser import PLACEHOLDER_RE
|
||||
from app.features.memoir.memoir_images.schema import (
|
||||
IMAGE_STATUS_COMPLETED,
|
||||
normalize_image_assets,
|
||||
)
|
||||
from app.features.memoir.memoir_images.storage import (
|
||||
CosDownloadUrlError,
|
||||
TencentCosStorageService,
|
||||
mark_image_delivery_unavailable,
|
||||
resolve_image_storage_key,
|
||||
)
|
||||
|
||||
logger = get_logger(__name__)
|
||||
|
||||
|
||||
def strip_image_placeholders(text: str) -> str:
|
||||
return PLACEHOLDER_RE.sub("", text or "").strip()
|
||||
|
||||
|
||||
def split_content_blocks(content: str, images: list[dict]) -> list[dict]:
|
||||
blocks: list[dict] = []
|
||||
remaining = content
|
||||
for image in sorted(images or [], key=lambda item: item.get("index", 0)):
|
||||
placeholder = image.get("placeholder")
|
||||
if not placeholder or placeholder not in remaining:
|
||||
continue
|
||||
before, remaining = remaining.split(placeholder, 1)
|
||||
cleaned_before = strip_image_placeholders(before)
|
||||
if cleaned_before:
|
||||
blocks.append({"type": "text", "value": cleaned_before})
|
||||
if image.get("status") == IMAGE_STATUS_COMPLETED and image.get("url"):
|
||||
blocks.append({"type": "image", "url": image["url"]})
|
||||
cleaned_remaining = strip_image_placeholders(remaining)
|
||||
if cleaned_remaining:
|
||||
blocks.append({"type": "text", "value": cleaned_remaining})
|
||||
return blocks
|
||||
|
||||
|
||||
def _prepare_pdf_image_assets(images: list[dict]) -> list[dict]:
|
||||
storage = TencentCosStorageService.from_env()
|
||||
prepared_assets: list[dict] = []
|
||||
for item in normalize_image_assets(images):
|
||||
asset = dict(item)
|
||||
storage_key = resolve_image_storage_key(asset)
|
||||
if asset.get("status") == IMAGE_STATUS_COMPLETED and storage_key:
|
||||
try:
|
||||
asset["url"] = storage.get_download_url(storage_key)
|
||||
except CosDownloadUrlError as exc:
|
||||
logger.warning(
|
||||
"PDF 图片签名失败: key=%s, retryable=%s, request_id=%s, error=%s",
|
||||
storage_key,
|
||||
exc.retryable,
|
||||
exc.request_id,
|
||||
exc,
|
||||
)
|
||||
asset = mark_image_delivery_unavailable(asset)
|
||||
except Exception as exc:
|
||||
logger.warning("PDF 图片签名失败: key=%s, error=%s", storage_key, exc)
|
||||
asset = mark_image_delivery_unavailable(asset)
|
||||
prepared_assets.append(asset)
|
||||
return prepared_assets
|
||||
|
||||
|
||||
def _fit_image_size(
|
||||
image_bytes: bytes, max_width: float, max_height: float
|
||||
) -> tuple[float, float]:
|
||||
@@ -180,12 +118,6 @@ class PDFService:
|
||||
story.append(Spacer(1, 0.2 * inch))
|
||||
# 有 story_links 时按章节内故事注入 ## 标题（与物化章节正文不含故事标题区分）
|
||||
markdown = _chapter_markdown_for_pdf(chapter)
|
||||
_, images_list = sections_to_content_and_images(chapter)
|
||||
if not markdown:
|
||||
markdown = getattr(chapter, "content", "") or ""
|
||||
if not images_list:
|
||||
images_list = list(getattr(chapter, "images", None) or [])
|
||||
prepared_images = _prepare_pdf_image_assets(images_list)
|
||||
blocks: list[dict]
|
||||
if asset_url_map and collect_asset_ids_from_markdown(markdown):
|
||||
blocks = split_markdown_by_asset_refs(
|
||||
@@ -194,11 +126,14 @@ class PDFService:
|
||||
)
|
||||
for b in blocks:
|
||||
if b.get("type") == "text":
|
||||
b["value"] = strip_legacy_image_placeholders(
|
||||
b.get("value") or ""
|
||||
)
|
||||
b["value"] = strip_image_placeholders(b.get("value") or "")
|
||||
else:
|
||||
blocks = split_content_blocks(markdown, prepared_images)
|
||||
cleaned_markdown = strip_image_placeholders(markdown or "")
|
||||
blocks = (
|
||||
[{"type": "text", "value": cleaned_markdown}]
|
||||
if cleaned_markdown
|
||||
else []
|
||||
)
|
||||
for block in blocks:
|
||||
if block["type"] == "text":
|
||||
paragraphs = block["value"].split("\n\n")
|
||||
|
||||
Reference in New Issue
Block a user