PlantAI-rag-new/paper_writer_service/app/services/paper/outline.py

"""outline.py —— propose_paper_outline：建 papers 行 → search_refs 注入线索 → LLM 出大纲 → 预填 sections。"""
from __future__ import annotations

import uuid
from typing import Any

from ...db import db, dumps_json, now_iso
from . import llm, search

_OUTLINE_SYSTEM = (
    "你是植物学论文撰写助手。根据用户给出的论文主题与写作要求，生成论文大纲。"
    "只输出一个合法 JSON 对象，结构为："
    '{"title": 论文标题, "abstract_expect": 摘要预期内容(一句话), '
    '"sections": [{"section_id": "s1", "title": "节标题", "key_points": ["要点1", "要点2"], "target_words": 1200}, ...]}。'
    "章节 5-6 节，覆盖 引言/材料与方法/结果/讨论/结论 等综述常见结构；target_words 每节 1200-2500。"
)

_DEFAULT_SECTIONS = [
    ("s1", "引言"),
    ("s2", "材料与方法"),
    ("s3", "结果"),
    ("s4", "讨论"),
    ("s5", "结论与展望"),
]


async def propose_paper_outline(
    topic: str,
    requirements: str = "",
    paper_type: str = "",
    language: str = "",
    length: str = "",
    format_req: str = "",
    style: str = "",
    kb_hints: list[dict[str, Any]] | None = None,
) -> dict[str, Any]:
    # 1. 知识库线索：优先用调用方传入的 kb_hints，否则现场 search_refs（失败静默降级）
    hints = list(kb_hints or [])
    if not hints:
        try:
            r = await search.search_refs(query=topic, top_k=8)
            hints = list(r.get("items") or [])
        except Exception:
            hints = []

    # 2. LLM 出大纲
    user = f"论文主题：{topic}\n"
    if paper_type:
        user += f"论文类型：{paper_type}\n"
    if requirements:
        user += f"写作要求：{requirements}\n"
    if language:
        user += f"语言：{language}\n"
    if length:
        user += f"篇幅：{length}\n"
    if format_req:
        user += f"格式：{format_req}\n"
    if style:
        user += f"风格：{style}\n"
    if hints:
        user += "可参考知识库文献线索（仅选题依据，非硬性引用）：\n" + "\n".join(
            f"- {h.get('title', '')}: {str(h.get('snippet', ''))[:120]}" for h in hints[:5]
        )
    try:
        outline = await llm.complete_json(_OUTLINE_SYSTEM, user)
    except llm.LLMError as exc:
        return {"ok": False, "code": "LLM_ERROR", "message": f"大纲生成失败：{exc}"}

    title = str(outline.get("title") or topic).strip() or topic
    sections = outline.get("sections") or []
    if not sections:
        sections = [
            {"section_id": sid, "title": t, "key_points": [], "target_words": 1500}
            for sid, t in _DEFAULT_SECTIONS
        ]

    # 3. 落库 papers + paper_sections
    paper_id = uuid.uuid4().hex[:16]
    await db.execute(
        "INSERT INTO papers (id, title, paper_type, language, format_req, style, status, brief_json, outline_json, created_at, updated_at) "
        "VALUES (?, ?, ?, ?, ?, ?, 'outline', ?, ?, ?, ?)",
        (
            paper_id, title, paper_type, language, format_req, style,
            dumps_json({
                "topic": topic, "requirements": requirements, "length": length,
                "kb_hints": hints,
            }),
            dumps_json({
                "title": title,
                "abstract_expect": outline.get("abstract_expect", ""),
                "sections": sections,
            }),
            now_iso(), now_iso(),
        ),
    )
    for s in sections:
        await db.execute(
            "INSERT INTO paper_sections (id, paper_id, section_id, title, key_points, status, updated_at) "
            "VALUES (?, ?, ?, ?, ?, 'pending', ?)",
            (
                uuid.uuid4().hex[:16], paper_id,
                s.get("section_id") or "s1", s.get("title", ""),
                dumps_json(s.get("key_points") or []), now_iso(),
            ),
        )
    return {
        "ok": True,
        "paper_id": paper_id,
        "title": title,
        "abstract_expect": outline.get("abstract_expect", ""),
        "sections": sections,
    }