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
2026-03-22 16:45:57 +08:00
parent 70070216c4
commit 786ebf8ae6
122 changed files with 2802 additions and 7941 deletions

View File

@@ -12,7 +12,11 @@ from sqlalchemy.orm import Session, joinedload
from app.agents.memoir.narrative_agent import NarrativeAgent
from app.agents.memoir.prompts import STAGE_TO_ORDER, format_evidence_chunks_for_prompt
from app.agents.memoir.story_route_agent import StoryRouteAgent
from app.agents.memoir.story_route_agent import (
PLAN_BATCH_MAX_SEGMENTS,
StoryBatchPlan,
StoryRouteAgent,
)
from app.agents.state_schema import MemoirStateSchema
from app.core.logging import get_logger
from app.features.memoir.cover_eligibility import chapter_needs_cover_enqueue
@@ -21,6 +25,7 @@ from app.features.memoir.memoir_images.settings import MemoirImageSettings
from app.features.memoir.models import Chapter
from app.features.memoir.narrative_to_markdown import narrative_to_markdown
from app.features.memoir.repo import compose_chapter_from_story_links_sync
from app.features.memory.repo import retrieve_evidence_sync
from app.features.story.models import Story
from app.features.story.sync_write import (
append_story_version_sync,
@@ -28,7 +33,6 @@ from app.features.story.sync_write import (
ensure_chapter_story_link_sync,
list_active_stories_for_user_sync,
)
from app.features.memory.repo import retrieve_evidence_sync
logger = get_logger(__name__)
@@ -40,6 +44,172 @@ def _is_json_narrative(text: str) -> bool:
return s.startswith("{") and "paragraphs" in s
def _ordered_text_for_segment_ids(
category_segments: list, segment_ids: list[str]
) -> str:
id_to_text = {seg.id: (seg.transcript_text or "") for seg in category_segments}
return "\n\n".join(id_to_text.get(sid, "") for sid in segment_ids)
def _apply_narrative_fallbacks(
narrative_raw: str,
combined_unit_text: str,
existing_for_narrative: str,
existing_chapter_md: str,
*,
chapter_category: str,
) -> str:
if (
existing_for_narrative
and not _is_json_narrative(narrative_raw)
and len(narrative_raw) < len(existing_for_narrative) * 0.8
):
logger.warning("叙事长度异常: 回退为原文追加")
return f"{existing_for_narrative}\n\n{combined_unit_text}"
if (
not existing_for_narrative
and existing_chapter_md
and not _is_json_narrative(narrative_raw)
and len(narrative_raw) < len(existing_chapter_md) * 0.8
):
logger.warning(
"章节级长度异常: 回退为 transcript 追加, category=%s",
chapter_category,
)
return f"{existing_chapter_md}\n\n{combined_unit_text}"
return narrative_raw
def _ensure_chapter_record(
session: Session,
*,
user_id: str,
chapter_category: str,
title: str,
source_ids: list[str],
calculated_order_index: int,
) -> Chapter:
stmt_chapter = (
select(Chapter)
.where(
Chapter.user_id == user_id,
Chapter.category == chapter_category,
Chapter.is_active == True, # noqa: E712
)
.options(
joinedload(Chapter.images),
joinedload(Chapter.story_links),
)
)
chapter = session.execute(stmt_chapter).unique().scalar_one_or_none()
if not chapter:
chapter = Chapter(
id=str(uuid.uuid4()),
user_id=user_id,
title=title,
order_index=calculated_order_index,
status="completed",
category=chapter_category,
is_new=True,
source_segments=source_ids,
)
session.add(chapter)
session.flush()
else:
chapter.source_segments = list(
set((chapter.source_segments or []) + source_ids)
)
chapter.is_new = True
session.flush()
return chapter
def _run_batch_plan_writes(
session: Session,
*,
plan: StoryBatchPlan,
category_segments: list,
chapter: Chapter,
chapter_category: str,
evidence_text: str,
existing_chapter_md: str,
slot_snippets: dict[str, str],
user_id: str,
user_profile: str,
user_birth_year: int | None,
llm: Any,
narrative_agent: NarrativeAgent,
) -> set[str]:
dispatch_ids: set[str] = set()
for unit in plan.units:
unit_text = _ordered_text_for_segment_ids(category_segments, unit.segment_ids)
new_content_input = (
f"{unit_text}\n\n【相关记忆摘录】\n{evidence_text}"
if evidence_text.strip()
else unit_text
)
target_story_id: str | None = None
existing_for_narrative = ""
if unit.decision == "append_story" and unit.target_story_id:
st = session.get(Story, unit.target_story_id)
if st and st.user_id == user_id:
target_story_id = st.id
existing_for_narrative = (st.canonical_markdown or "").strip()
narrative_raw = narrative_agent.generate_narrative(
stage=chapter_category,
slots=slot_snippets,
new_content=new_content_input,
existing_content=existing_for_narrative,
user_profile=user_profile,
birth_year=user_birth_year,
llm=llm,
)
narrative_raw = _apply_narrative_fallbacks(
narrative_raw,
unit_text,
existing_for_narrative,
existing_chapter_md,
chapter_category=chapter_category,
)
md = narrative_to_markdown(narrative_raw)
if not md.strip():
md = unit_text.strip()
if target_story_id:
append_story_version_sync(session, target_story_id, md)
dispatch_ids.add(target_story_id)
ensure_chapter_story_link_sync(
session, chapter_id=chapter.id, story_id=target_story_id
)
else:
story_title = (unit.new_story_title or "").strip()
if not story_title:
story_title = narrative_agent.generate_title(
stage=chapter_category,
emotion="neutral",
slots=slot_snippets,
user_profile=user_profile,
birth_year=user_birth_year,
llm=llm,
)
st = create_story_with_version_sync(
session,
user_id=user_id,
title=story_title,
canonical_markdown=md,
stage=chapter_category,
)
dispatch_ids.add(st.id)
ensure_chapter_story_link_sync(
session, chapter_id=chapter.id, story_id=st.id
)
return dispatch_ids
def run_story_pipeline_for_category_batch(
session: Session,
*,
@@ -125,107 +295,121 @@ def run_story_pipeline_for_category_batch(
if evidence_text.strip()
else combined_text
)
route = route_agent.decide(
chapter_category=chapter_category,
chapter_title=title,
batch_transcript=batch_for_route,
candidate_stories=candidates,
llm=llm,
valid_story_ids=valid_ids,
)
target_story_id: str | None = None
existing_for_narrative = ""
if route.decision == "append_story" and route.target_story_id:
st = session.get(Story, route.target_story_id)
if st and st.user_id == user_id:
target_story_id = st.id
existing_for_narrative = (st.canonical_markdown or "").strip()
narrative_raw = narrative_agent.generate_narrative(
stage=chapter_category,
slots=slot_snippets,
new_content=new_content_input,
existing_content=existing_for_narrative,
user_profile=user_profile,
birth_year=user_birth_year,
llm=llm,
)
if (
existing_for_narrative
and not _is_json_narrative(narrative_raw)
and len(narrative_raw) < len(existing_for_narrative) * 0.8
):
logger.warning("叙事长度异常: 回退为原文追加")
narrative_raw = f"{existing_for_narrative}\n\n{combined_text}"
if (
not existing_for_narrative
and existing_chapter_md
and not _is_json_narrative(narrative_raw)
and len(narrative_raw) < len(existing_chapter_md) * 0.8
):
logger.warning(
"章节级长度异常: 回退为 transcript 追加, category=%s",
chapter_category,
)
narrative_raw = f"{existing_chapter_md}\n\n{combined_text}"
md = narrative_to_markdown(narrative_raw)
if not md.strip():
md = combined_text.strip()
calculated_order_index = STAGE_TO_ORDER.get(chapter_category, 999)
if not chapter:
chapter = Chapter(
id=str(uuid.uuid4()),
user_id=user_id,
title=title,
order_index=calculated_order_index,
status="completed",
category=chapter_category,
cover_image=None,
is_new=True,
source_segments=source_ids,
use_batch_plan = (
llm
and len(category_segments) >= 2
and len(category_segments) <= PLAN_BATCH_MAX_SEGMENTS
)
plan: StoryBatchPlan | None = None
if use_batch_plan:
segs = [(seg.id, seg.transcript_text or "") for seg in category_segments]
plan = route_agent.plan_batch(
chapter_category=chapter_category,
chapter_title=title,
segments=segs,
candidate_stories=candidates,
llm=llm,
valid_story_ids=valid_ids,
)
session.add(chapter)
session.flush()
else:
chapter.source_segments = list(
set((chapter.source_segments or []) + source_ids)
)
chapter.is_new = True
do_append = target_story_id is not None
chapter = _ensure_chapter_record(
session,
user_id=user_id,
chapter_category=chapter_category,
title=title,
source_ids=source_ids,
calculated_order_index=calculated_order_index,
)
if do_append:
append_story_version_sync(session, target_story_id, md)
dispatch_ids.add(target_story_id)
ensure_chapter_story_link_sync(
session, chapter_id=chapter.id, story_id=target_story_id
)
else:
story_title = (route.new_story_title or "").strip()
if not story_title:
story_title = narrative_agent.generate_title(
stage=chapter_category,
emotion="neutral",
slots=slot_snippets,
user_profile=user_profile,
birth_year=user_birth_year,
llm=llm,
)
st = create_story_with_version_sync(
if plan is not None:
dispatch_ids = _run_batch_plan_writes(
session,
plan=plan,
category_segments=category_segments,
chapter=chapter,
chapter_category=chapter_category,
evidence_text=evidence_text,
existing_chapter_md=existing_chapter_md,
slot_snippets=slot_snippets,
user_id=user_id,
title=story_title,
canonical_markdown=md,
stage=chapter_category,
user_profile=user_profile,
user_birth_year=user_birth_year,
llm=llm,
narrative_agent=narrative_agent,
)
dispatch_ids.add(st.id)
ensure_chapter_story_link_sync(session, chapter_id=chapter.id, story_id=st.id)
else:
route = route_agent.decide(
chapter_category=chapter_category,
chapter_title=title,
batch_transcript=batch_for_route,
candidate_stories=candidates,
llm=llm,
valid_story_ids=valid_ids,
)
target_story_id: str | None = None
existing_for_narrative = ""
if route.decision == "append_story" and route.target_story_id:
st = session.get(Story, route.target_story_id)
if st and st.user_id == user_id:
target_story_id = st.id
existing_for_narrative = (st.canonical_markdown or "").strip()
narrative_raw = narrative_agent.generate_narrative(
stage=chapter_category,
slots=slot_snippets,
new_content=new_content_input,
existing_content=existing_for_narrative,
user_profile=user_profile,
birth_year=user_birth_year,
llm=llm,
)
narrative_raw = _apply_narrative_fallbacks(
narrative_raw,
combined_text,
existing_for_narrative,
existing_chapter_md,
chapter_category=chapter_category,
)
md = narrative_to_markdown(narrative_raw)
if not md.strip():
md = combined_text.strip()
do_append = target_story_id is not None
if do_append:
append_story_version_sync(session, target_story_id, md)
dispatch_ids.add(target_story_id)
ensure_chapter_story_link_sync(
session, chapter_id=chapter.id, story_id=target_story_id
)
else:
story_title = (route.new_story_title or "").strip()
if not story_title:
story_title = narrative_agent.generate_title(
stage=chapter_category,
emotion="neutral",
slots=slot_snippets,
user_profile=user_profile,
birth_year=user_birth_year,
llm=llm,
)
st = create_story_with_version_sync(
session,
user_id=user_id,
title=story_title,
canonical_markdown=md,
stage=chapter_category,
)
dispatch_ids.add(st.id)
ensure_chapter_story_link_sync(
session, chapter_id=chapter.id, story_id=st.id
)
compose_chapter_from_story_links_sync(session, chapter.id)
session.flush()