Create-knowledge-find-decode/creation_knowledge/stages/assemble.py

"""组装：把帖子+知识片段+解构，组装成 ingest 请求体（对齐 创作知识-重构设计.md §6）。

纯函数，无 LLM、无 IO。同一帖子拆出的多条知识复用同一 source.id。
"""
from __future__ import annotations

import json

from creation_knowledge.models import (
    Deconstruction,
    IngestPayload,
    KnowledgeItem,
    Post,
)


def build_ingest_payload(
    post: Post, item: KnowledgeItem, deco: Deconstruction
) -> IngestPayload:
    content = json.dumps(
        {"what": item.what, "why": item.why, "how": item.how},
        ensure_ascii=False,
    )
    custom_ext: list[dict] = []
    if item.source_cards:
        custom_ext.append(
            {"key": "来源卡片", "type": "str",
             "value": "、".join(f"卡片{n}" for n in item.source_cards)}
        )
    if item.evidence:
        ev = " / ".join(
            f"{e.text}（卡片{e.card}）" if e.card else e.text for e in item.evidence
        )
        custom_ext.append({"key": "原文证据", "type": "str", "value": ev})
    if deco.stage_reason:
        custom_ext.append(
            {"key": "阶段判断理由", "type": "str", "value": deco.stage_reason}
        )
    if deco.scope_reason:
        custom_ext.append(
            {"key": "作用域判断理由", "type": "str", "value": deco.scope_reason}
        )
    return IngestPayload(
        source={
            "id": post.id,
            "source_type": "post",
            "title": post.title,
            "author": post.author_name,
            "source_metadata": {"platform": post.platform, "url": post.url},
        },
        title=item.title,
        content=content,
        dim_attributes=list(item.knowledge_types),
        dim_creations=list(deco.stages),
        scopes=[{"scope_type": s.scope_type, "value": s.value} for s in deco.scopes],
        custom_ext=custom_ext,
    )