Function truncateToByteBudget

packages/cli/src/lib/issue-body.ts:191–202

* Truncate a string to at most `maxBytes` UTF-8 bytes WITHOUT splitting a * multi-byte code point. Naive `Buffer.subarray(...).toString("utf8")` * replaces any partial codepoint at the cut with U+FFFD (3 bytes), which * paradoxically pushes the output OVER the requested budget when the cut * hap

(input: string, maxBytes: number)

 * the output past `maxBytes`.
 */
function truncateToByteBudget(input: string, maxBytes: number): string {
    if (maxBytes <= 0) return "";
    const buf = Buffer.from(input, "utf8");
    if (buf.length <= maxBytes) return input;
    let end = maxBytes;
    // Walk back to the nearest UTF-8 codepoint boundary. UTF-8 continuation
    // bytes are 10xxxxxx; start bytes are 0xxxxxxx or 11xxxxxx.
    while (end > 0 && (buf[end] & 0b1100_0000) === 0b1000_0000) {
        end -= 1;
    }
    return buf.subarray(0, end).toString("utf8");
}