237 lines
7.6 KiB
Python
237 lines
7.6 KiB
Python
"""
|
||
Celery 用：按批次将 transcript 写入 Story，并物化 Chapter canonical_markdown。
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import uuid
|
||
from typing import Any
|
||
|
||
from sqlalchemy import select
|
||
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.state_schema import MemoirStateSchema
|
||
from app.core.logging import get_logger
|
||
from app.features.memoir.cover_eligibility import chapter_needs_cover_enqueue
|
||
from app.features.memoir.helpers import _chapter_markdown
|
||
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.story.models import Story
|
||
from app.features.story.sync_write import (
|
||
append_story_version_sync,
|
||
create_story_with_version_sync,
|
||
ensure_chapter_story_link_sync,
|
||
list_active_stories_for_user_sync,
|
||
)
|
||
from app.features.memory.repo import retrieve_evidence_sync
|
||
|
||
logger = get_logger(__name__)
|
||
|
||
|
||
def _is_json_narrative(text: str) -> bool:
|
||
if not text or not text.strip():
|
||
return False
|
||
s = text.strip()
|
||
return s.startswith("{") and "paragraphs" in s
|
||
|
||
|
||
def run_story_pipeline_for_category_batch(
|
||
session: Session,
|
||
*,
|
||
user_id: str,
|
||
chapter_category: str,
|
||
category_segments: list,
|
||
state: MemoirStateSchema,
|
||
user_profile: str,
|
||
user_birth_year: int | None,
|
||
llm: Any,
|
||
) -> tuple[Chapter | None, bool, set[str]]:
|
||
"""
|
||
返回 (chapter, needs_cover_enqueue, story_ids_to_dispatch_after_commit)。
|
||
"""
|
||
narrative_agent = NarrativeAgent()
|
||
route_agent = StoryRouteAgent()
|
||
dispatch_ids: set[str] = set()
|
||
|
||
segment_texts = [seg.transcript_text or "" for seg in category_segments]
|
||
combined_text = "\n\n".join(segment_texts)
|
||
source_ids = [seg.id for seg in category_segments]
|
||
|
||
try:
|
||
evidence = retrieve_evidence_sync(session, user_id, combined_text, top_k=10)
|
||
except Exception as e:
|
||
logger.warning("Evidence 检索跳过: %s", e)
|
||
evidence = {
|
||
"relevant_chunks": [],
|
||
"relevant_summaries": [],
|
||
"relevant_facts": [],
|
||
"timeline_hints": [],
|
||
"relevant_stories": [],
|
||
}
|
||
|
||
evidence_text = format_evidence_chunks_for_prompt(evidence)
|
||
new_content_input = (
|
||
f"{combined_text}\n\n【相关记忆摘录】\n{evidence_text}"
|
||
if evidence_text.strip()
|
||
else combined_text
|
||
)
|
||
|
||
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()
|
||
|
||
slot_snippets: dict[str, str] = {}
|
||
stage_slots = state.slots.get(chapter_category, {}) or {}
|
||
for key, value in stage_slots.items():
|
||
snip = getattr(value, "snippet", None) or (
|
||
value.get("snippet") if isinstance(value, dict) else None
|
||
)
|
||
if snip:
|
||
slot_snippets[key] = snip
|
||
|
||
title = chapter.title if chapter else f"{chapter_category} 回忆"
|
||
existing_chapter_md = _chapter_markdown(chapter) if chapter else ""
|
||
|
||
if not chapter:
|
||
title = narrative_agent.generate_title(
|
||
stage=chapter_category,
|
||
emotion="neutral",
|
||
slots=slot_snippets,
|
||
user_profile=user_profile,
|
||
birth_year=user_birth_year,
|
||
llm=llm,
|
||
)
|
||
|
||
candidates = list_active_stories_for_user_sync(session, user_id)
|
||
valid_ids = {s.id for s in candidates}
|
||
|
||
batch_for_route = (
|
||
f"{combined_text}\n\n{evidence_text}"
|
||
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,
|
||
)
|
||
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
|
||
|
||
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()
|
||
|
||
image_settings = MemoirImageSettings.from_env()
|
||
needs_cover = image_settings.enabled and chapter_needs_cover_enqueue(chapter)
|
||
|
||
return chapter, needs_cover, dispatch_ids
|