paper-doc/backend/app/mcp/specs.py

"""The shapes a model may send when it writes.

These are tool-argument models, not domain models: they exist so the JSON
Schema a client receives is precise enough that the model gets the shape right
the first time. Each one is converted into the project's own payload
(:class:`~app.schemas.paper.SentenceInput`,
:class:`~app.schemas.template.TemplateFieldInput`) before it reaches the CRUD
layer, so the validation rules stay in one place — a citation with a blank
quote is refused here for the same reason the REST API refuses it.

The union types are deliberate. A model writing sentences naturally produces
either plain strings or objects, and refusing one of the two shapes would
produce a retry that costs a whole round trip:

    "sentences": ["First sentence.", "Second sentence."]
    "sentences": [{"content": "Cited sentence.", "citations": [{"quote": "…"}]}]
    "sentences": [{"text": "One long block to be cut.", "split": "sentence"}]
"""

from __future__ import annotations

from typing import Annotated, Literal

from pydantic import BaseModel, Field

#: How a block of text becomes sentences when the caller sent ``text`` instead
#: of an explicit list. See :func:`app.mcp.support.split_text`.
SplitMode = Literal["line", "sentence", "paragraph"]


class CitationSpec(BaseModel):
    """One citation of one sentence."""

    quote: Annotated[
        str,
        Field(description="引用内容，必填；空引用会被拒绝"),
    ]
    reference_id: Annotated[
        int | None,
        Field(description="参考文献库的编号，暂无库时可省略"),
    ] = None


class SentenceSpec(BaseModel):
    """One sentence, optionally carrying citations."""

    content: Annotated[str, Field(description="句子正文；空白会被折叠成一行")]
    citations: Annotated[
        list[CitationSpec],
        Field(description="这一段引用了哪些文献"),
    ] = []


class TextSpec(BaseModel):
    """A block of text to be cut into sentences by the server."""

    text: Annotated[str, Field(description="要写入的整段文本")]
    split: Annotated[
        SplitMode,
        Field(description="切句方式：line 一行一句（默认）/ sentence 按句号切 / paragraph 整段一句"),
    ] = "line"
    citations: Annotated[
        list[CitationSpec],
        Field(description="整段共用的引用"),
    ] = []


#: One entry of a paragraph's sentence list — a string, a sentence object, or a
#: block to be cut.
SentenceItem = str | SentenceSpec | TextSpec


class ParagraphSpec(BaseModel):
    """One paragraph to write, addressed by position or by heading."""

    position: Annotated[
        int | None,
        Field(description="段落位置（模板字段的 sort）；与 heading 二选一"),
    ] = None
    heading: Annotated[
        str | None,
        Field(description="段落标题，如 “1. Introduction”；会按模板解析成位置"),
    ] = None
    sentences: Annotated[
        list[SentenceItem] | None,
        Field(description="句子列表；字符串或对象都可以"),
    ] = None
    text: Annotated[
        str | None,
        Field(description="整段文本，等价于 sentences 里放一个 {text, split} 对象"),
    ] = None
    split: Annotated[
        SplitMode,
        Field(description="text 的切句方式；默认 line 一行一句"),
    ] = "line"
    citations: Annotated[
        list[CitationSpec],
        Field(description="整段共用的引用"),
    ] = []


class FieldSpec(BaseModel):
    """One placement of a library field inside a template."""

    field_id: Annotated[int, Field(description="字段库里的字段 id")]
    sort: Annotated[
        int,
        Field(description="渲染顺序，升序整数；唯一决定段落顺序的就是它"),
    ]


__all__ = [
    "CitationSpec",
    "FieldSpec",
    "ParagraphSpec",
    "SentenceItem",
    "SentenceSpec",
    "SplitMode",
    "TextSpec",
]