backend: let a model put a figure in the paper, and set a formula's alignment

Two things the editor gained and MCP could not do, both because the tool layer
had been told about the domain's columns by hand.

**A figure.** Bytes go to MinIO and the sentence keeps a Markdown address, so a
picture is ordinary text — which means the writing tools already carry it, and
the only half a model cannot do is the upload: it has bytes and no way to send
multipart. `image_upload` takes base64 and answers with the URL, the Markdown
and the *sentence object* the editor produces when a picture is dropped in, so a
figure is written by putting that object into `sentences` unchanged. It does not
fetch a URL the caller names: a service inside the cluster that will GET any
address it is handed is an SSRF primitive aimed at everything beside it.

The width argument is the reader's rule or it is refused. `{width=70%}` is
parsed by `frontend/src/utils/rich.ts`, and a value it cannot read is not an
error there — the picture just prints at its natural size. A size that silently
does not apply is worse than a refusal, so the syntax and the range (pixels
1–4000, per cent 1–100) are mirrored in `app/mcp/tools/images.py`, with the
usual comment naming the other side.

`paragraph_text` also had to learn what a figure is: a sentence holding nothing
but an image is a 插图 — the view prints it on its own line with the brackets'
text as its caption — and the text a tool hands back broke lines around a
display formula but not around a picture. Same rule as `figureOf`, same pair of
implementations, same warning about changing both.

**A formula's alignment.** `paper_sentence.formula_align` reached the editor and
the REST API and stopped there: `SentenceSpec` had no such field, so a model that
sent one got a successful call and a centred formula. The column is now declared,
carried through every write path and reported by every read path.

That is the second column lost the same way, so the fix is structural rather
than another two edits. `SENTENCE_FIELDS` is read from
`app.schemas.paper.SentenceInput` instead of written out, the payload is built
by one `sentence_payload()`, and the three append paths spread
`SentenceCreate(**item.model_dump())` rather than copying fields. One edit
remains — declaring the field in `specs.py` — and smoke_mcp.py's first step
compares the two field sets, so forgetting it now fails the suite instead of
losing the field. `sort` is declared too, which it never was: a model that sent
one had it dropped in silence.

smoke_mcp.py: 99 checks to 119. The figure step uploads a real 1x1 GIF (the same
bytes twice, and the key is the same object), writes the returned sentence as it
came back, checks the paragraph prints it alone on its line and that an image
inside a sentence does not break the line, and takes the four refusals — not a
picture, an unparseable size, an out-of-range one, not base64. The alignment step
writes a right-aligned formula, moves the sentence to left on its own, and takes
the paragraph to another position to prove the setting travels with it.

Deployed as v6, and the pod now carries MINIO_ENDPOINT (the in-cluster Service)
plus the two credential keys from the Secret; without them the image tool answers
with the missing variable names and every writing tool still works.
This commit is contained in:
2026-09-24 10:54:27 +08:00
parent eb0f12b8cf
commit ebaf9e558b
13 changed files with 816 additions and 79 deletions
+13 -2
View File
@@ -20,7 +20,7 @@ from pydantic import Field
from app.crud import paper as paper_crud
from app.mcp import support as s
from app.mcp.specs import CitationSpec
from app.mcp.specs import CitationSpec, FormulaAlign
from app.mcp.tools.registry import mcp_tool
from app.models import Paper
from app.schemas.paper import CitationInput, SentenceCreate, SentenceUpdate
@@ -94,6 +94,10 @@ def register(server: MCPServer) -> None:
)
),
] = False,
formula_align: Annotated[
FormulaAlign,
Field(description="display 公式怎么排:center(默认)/ left / right"),
] = "center",
sort: Annotated[
int | None, Field(description="段内位置;不传则排在段尾")
] = None,
@@ -109,6 +113,7 @@ def register(server: MCPServer) -> None:
paper_template_filed_sort=field_sort,
content=content,
line_break_before=line_break_before,
formula_align=formula_align,
citations=_citations(citations or []),
sort=sort,
),
@@ -137,17 +142,22 @@ def register(server: MCPServer) -> None:
bool | None,
Field(description="这一句是否另起一行;不传则不动,false 表示取消换行"),
] = None,
formula_align: Annotated[
FormulaAlign | None,
Field(description="display 公式怎么排;不传则不动"),
] = None,
citations: Annotated[
list[CitationSpec] | None,
Field(description="引用整组替换;传 [] 表示清空引用"),
] = None,
) -> str:
"""修改一句话的正文、所属段落、排序、换行或引用(引用是整体替换)。"""
"""修改一句话的正文、所属段落、排序、换行、公式对齐或引用(引用是整体替换)。"""
if (
content is None
and position is None
and sort is None
and line_break_before is None
and formula_align is None
and citations is None
):
s.fail("没有给出任何要修改的内容")
@@ -164,6 +174,7 @@ def register(server: MCPServer) -> None:
paper_template_filed_sort=position,
sort=sort,
line_break_before=line_break_before,
formula_align=formula_align,
citations=None if citations is None else _citations(citations),
),
)