LaTeX-escape restoration at the display seam (owner ruling 2026-09-26): JSON-escape debris (FF ate \forall's f, VT \varphi's v, TAB \to's t) restored inside balanced math spans — one seam (tool-parts parse) heals new turns and poisoned records; outside spans untouched

This commit is contained in:
amosblomqvist
2026-09-27 02:19:27 +03:00
parent d6d7c09e2e
commit 8faf97edc7
3 changed files with 137 additions and 3 deletions
+53
View File
@@ -214,3 +214,56 @@ export function transformMathDelimiters(markdown: string): string {
return out.join("");
}
/**
* LaTeX-escape restoration (owner ruling 2026-09-26) — the JSON-debris fix.
*
* When a model emits LaTeX with SINGLE backslashes inside JSON tool-call
* arguments (`\forall`, not the properly escaped `\\forall`), JSON escape
* resolution eats the command's first letter: `\f` → form feed + "orall",
* `\v` → vertical tab + "arphi", `\t` → tab + "o". The debris survives into
* the persisted RAW args and renders as garbage. Inside a MATH SPAN these
* control chars can never be legitimate content, so restoring the two-char
* escape reconstructs the model's intent byte-perfectly. Outside spans the
* same chars might be real prose (pasted tables, formatted text), so only
* balanced `\(…\)` / `\[…\]` spans are touched — the same scanner rules as
* transformMathDelimiters (escaped delimiters are literal, unbalanced
* delimiters pass through untouched).
*/
const ESCAPE_DEBRIS: Record<string, string> = {
"\b": "\\b",
"\t": "\\t",
"\n": "\\n",
"\v": "\\v",
"\f": "\\f",
"\r": "\\r",
};
const DEBRIS_RE = /[\b\t\n\v\f\r]/;
export function restoreMathEscapes(text: string): string {
if (!DEBRIS_RE.test(text)) return text;
const out: string[] = [];
let i = 0;
while (i < text.length) {
const ch = text[i]!;
if (ch === "\\" && !isEscaped(text, i)) {
const next = text[i + 1];
if (next === "(" || next === "[") {
const isDisplay = next === "[";
const open = isDisplay ? DISPLAY_OPEN : INLINE_OPEN;
const close = isDisplay ? DISPLAY_CLOSE : INLINE_CLOSE;
const closeAt = findClose(text, i + open.length, close);
if (closeAt !== -1) {
const inner = text.slice(i + open.length, closeAt);
out.push(open + inner.replace(DEBRIS_RE, (c) => ESCAPE_DEBRIS[c]!) + close);
i = closeAt + close.length;
continue;
}
}
}
out.push(ch);
i += 1;
}
return out.join("");
}