fix(gitmost-bridge): neutralize col-0 block triggers in transcript lines + lock text-not-HTML (#378 review round 1)

Round-1 review found two issues:
- [regressions] Inserting a transcript line VERBATIM as a paragraph is unsafe on the
  git-sync doc->markdown->doc round-trip: the paragraph serializer emits text with no
  block-escape, so a line starting at col 0 with `- `/`> `/`# `/`1. `/```` ``` ````/`|`/
  `> [!info]` silently re-parses into a list/quote/heading/code/table/callout (the last
  hits the #359 callout machinery). Safe under the host contract (every line prefixed
  `You:`/`Speaker N:`, which starts with a letter) but the helper didn't enforce it, and
  leading-whitespace / stray lines exist. Fix: trim each kept line (drops the indent leak),
  and if it STILL begins with a col-0 markdown block trigger, prepend an invisible
  zero-width space (U+200B) so the trigger isn't at col 0 — the round-trip keeps it a
  paragraph. (Backslash-escape was rejected: `marked` consumes the `\` on re-import, so it
  would render visibly then vanish. ZWSP is invisible and never markdown-escaped.) The
  serializer's missing block-escape is the pre-existing root cause; this is the boundary
  defense. Prefixed transcript lines never match the trigger regex → left byte-exact.
- [test-coverage] The "inserted as TEXT, not HTML/markdown" contract wasn't locked (all
  test strings were plain alphabet). Added a test that inserts `<b>bold</b>
  <script>alert(1)</script> and *stars* and [link](x)` (with Bold/Italic/Link marks
  registered so an insertContent(html) regression would parse them) and asserts one
  verbatim text node, no marks, and getHTML() has no live tags.

Verified: apps/client tsc --noEmit 0 errors; gitmost bridge tests 4 passed; a NEW
prosemirror-markdown round-trip test (real convertProseMirrorToMarkdown ->
markdownToProseMirror) proves bare triggers corrupt while the ZWSP-neutralized form stays
a single byte-preserved paragraph and normal You:/Speaker N: lines round-trip byte-exact —
3 passed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-07-05 23:41:44 +03:00
parent 02308012a6
commit 751d55e9db
3 changed files with 230 additions and 13 deletions
@@ -4,19 +4,31 @@ import { Document } from "@tiptap/extension-document";
import { Paragraph } from "@tiptap/extension-paragraph";
import { Text } from "@tiptap/extension-text";
import { Heading } from "@tiptap/extension-heading";
import { Bold } from "@tiptap/extension-bold";
import { Italic } from "@tiptap/extension-italic";
import { Link } from "@tiptap/extension-link";
import { gitmostInsertTranscriptIntoEditor } from "./gitmost-recording.ts";
const ZWSP = "​"; // U+200B, the helper's block-trigger neutralizer
/**
* #377 — the web-side bridge must append the native host's transcript below the
* recording. These exercise the pure insert helper through a REAL Tiptap editor
* (Document/Paragraph/Text/Heading), asserting the resulting document rather
* than mocking the editor: transcript present -> "Transcript" heading + one
* paragraph per non-empty line (verbatim); absent/empty/non-string -> no-op.
* (Document/Paragraph/Text/Heading + Bold/Italic/Link marks so an HTML-parsing
* regression would be caught), asserting the resulting document rather than
* mocking the editor: transcript present -> "Transcript" heading + one paragraph
* per non-empty line; content is inserted as LITERAL TEXT (no HTML/markdown
* parsing); col-0 markdown block triggers are neutralized so git-sync keeps them
* paragraphs; absent/empty/non-string -> no-op.
*/
describe("gitmostInsertTranscriptIntoEditor", () => {
const makeEditor = () =>
new Editor({
extensions: [Document, Paragraph, Text, Heading],
// Bold/Italic/Link are registered specifically so that IF the helper ever
// regressed to inserting an HTML/markdown string (instead of a text node),
// TipTap would parse `<b>`/`*..*`/`[..](..)` into marks and the literal-
// text assertions below would fail.
extensions: [Document, Paragraph, Text, Heading, Bold, Italic, Link],
// Start from a single empty paragraph (a fresh page's baseline). The
// helper appends at the end of the doc, i.e. below existing content.
content: { type: "doc", content: [{ type: "paragraph" }] },
@@ -49,6 +61,73 @@ describe("gitmostInsertTranscriptIntoEditor", () => {
editor.destroy();
});
it("inserts HTML + markdown metacharacters as LITERAL text (no injection / no mark parsing)", () => {
const editor = makeEditor();
const line =
"You: <b>bold</b> <script>alert(1)</script> and *stars* and [link](x)";
const inserted = gitmostInsertTranscriptIntoEditor(editor, line);
expect(inserted).toBe(true);
const paras = (editor.getJSON().content ?? []).filter(
(n: any) => n.type === "paragraph",
) as any[];
// The transcript line is exactly ONE paragraph holding a SINGLE text node
// whose text is the verbatim string — not split into bold/link/other nodes,
// not carrying any marks, not raw HTML. This FAILS if the helper switched to
// insertContent(htmlString): TipTap would then parse <b>/[link](x)/*stars*.
const content = paras[paras.length - 1].content;
expect(content).toHaveLength(1);
expect(content[0].type).toBe("text");
expect(content[0].marks ?? []).toEqual([]);
expect(content[0].text).toBe(line);
// And no bold/italic/link mark exists anywhere in the document.
const html = editor.getHTML();
expect(html).not.toMatch(/<(strong|b|em|i|a)\b/);
// The angle brackets survived as escaped entities (literal text), not a live
// <script>/<b> element.
expect(html).not.toMatch(/<script/i);
editor.destroy();
});
it("neutralizes col-0 markdown block triggers with a leading ZWSP (git-sync safety)", () => {
const editor = makeEditor();
// Trigger lines (some with a leaked indent) + a normal prefixed line.
const inserted = gitmostInsertTranscriptIntoEditor(
editor,
[
"- dash",
" > quote", // leading indent must be trimmed then neutralized
"# hash",
"1. one",
"> [!info] note",
"```js",
"You: normal line",
].join("\n"),
);
expect(inserted).toBe(true);
const texts = (editor.getJSON().content ?? [])
.filter((n: any) => n.type === "paragraph")
.map((n: any) => n.content?.[0]?.text)
.filter((t: any) => typeof t === "string") as string[];
// Every block-trigger line is prefixed with the invisible ZWSP (indent
// trimmed first); the normal `You:` line is left byte-exact.
expect(texts).toEqual([
ZWSP + "- dash",
ZWSP + "> quote",
ZWSP + "# hash",
ZWSP + "1. one",
ZWSP + "> [!info] note",
ZWSP + "```js",
"You: normal line",
]);
editor.destroy();
});
it("is a no-op for undefined / empty / whitespace-only / non-string transcripts", () => {
for (const value of [undefined, "", " \n \n", 42, {}, null]) {
const editor = makeEditor();
@@ -240,23 +240,57 @@ export async function gitmostUploadFileToEditor(
}
}
// Zero-width space (U+200B). Prepended to a transcript line that begins with a
// markdown BLOCK trigger: it is invisible in the rendered doc but shifts the
// trigger off column 0, so the git-sync doc->markdown->doc round-trip keeps the
// line a plain paragraph (see GITMOST_MD_BLOCK_TRIGGER_RE).
const GITMOST_ZWSP = "​";
// A markdown BLOCK-level construct that, sitting at column 0 of a paragraph
// line, the git-sync markdown serializer (packages/prosemirror-markdown
// markdown-converter.ts, `case "paragraph"`) would re-parse into a NON-paragraph
// block on the doc->markdown->doc cycle. That serializer emits paragraph text
// verbatim with NO block-escape (the pre-existing root cause), so a leading
// `#`/`-`/`*`/`+`/`>`, an ordered-list `N.`/`N)`, a code fence ```/~~~, a table
// `|`, or a `> [!info]` callout opener would silently become a heading / list /
// quote / code block / table / callout. This matches a TRIMMED line's start;
// the transcript's own `You:` / `Speaker N:` prefix begins with a letter and
// never matches, so prefixed lines are left byte-exact.
const GITMOST_MD_BLOCK_TRIGGER_RE =
/^(#{1,6}(\s|$)|[-*+](\s|$)|>|\d+[.)](\s|$)|```|~~~|\|)/;
// Append a transcript block BELOW the recording's audio node in a live editor:
// a "Transcript" heading followed by one paragraph per non-empty transcript
// line. The transcript is plain text, `\n`-separated, each line already
// formatted as `You: ...` / `Speaker N: ...` by the native host — lines are
// inserted VERBATIM as text nodes (never HTML), so there is no injection
// surface. This is best-effort and meant to run AFTER the audio has already
// been inserted; the caller must guard against a throw so a transcript failure
// never fails the (already successful) recording. Returns true when a block was
// inserted, false when there was nothing to insert (transcript undefined/empty/
// not-a-string). A non-string value is a no-op, not an error.
// formatted as `You: ...` / `Speaker N: ...` by the native host — line text is
// inserted as a TEXT node (never HTML/markdown), so there is no injection or
// mark-parsing surface. Each kept line is trimmed (drops an indent that would
// both leak into the display and, at col 0, form a markdown block trigger) and,
// if it still begins with a col-0 markdown block trigger, gets an invisible
// zero-width space prepended so the git-sync round-trip cannot turn it into a
// list/quote/heading/callout/code/table (defensive boundary against the
// serializer's missing block-escape). This is best-effort and meant to run
// AFTER the audio has already been inserted; the caller must guard against a
// throw so a transcript failure never fails the (already successful) recording.
// Returns true when a block was inserted, false when there was nothing to
// insert (transcript undefined/empty/not-a-string). A non-string value is a
// no-op, not an error.
export function gitmostInsertTranscriptIntoEditor(
editor: Editor,
transcript: unknown,
): boolean {
if (typeof transcript !== "string") return false;
// Keep each line's text verbatim; only drop blank (whitespace-only) lines.
const lines = transcript.split("\n").filter((line) => line.trim().length > 0);
const lines = transcript
.split("\n")
// Trim each line and drop blank (whitespace-only) ones.
.map((line) => line.trim())
.filter((line) => line.length > 0)
// Neutralize a col-0 markdown block trigger with an invisible ZWSP so the
// git-sync round-trip keeps the line a paragraph. Host lines (`You:` /
// `Speaker N:`) never match and stay byte-exact.
.map((line) =>
GITMOST_MD_BLOCK_TRIGGER_RE.test(line) ? GITMOST_ZWSP + line : line,
);
if (lines.length === 0) return false;
const content = [