/**
 * Sanitize text that may appear on the public thinking channel.
 *
 * English-only process narration, tool ids and UUIDs stay off the client.
 * Chinese thinking fragments are allowed through a dedicated event type,
 * never through the spoken answer.
 */
const CJK_RE = /[\u4e00-\u9fff]/;
const PUBLIC_THINKING_UUID_RE = /[0-9a-f]{8}-[0-9a-f]{4}-[1-5][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}/gi;
const PUBLIC_THINKING_TOOL_RE = /(?:rectification|run-jyotish)-[a-z0-9-]+/gi;

export function sanitizePublicThinkingText(text: string): string | null {
  const cleaned = text
    .replace(PUBLIC_THINKING_UUID_RE, "")
    .replace(PUBLIC_THINKING_TOOL_RE, "");
  if (!cleaned) return null;
  if (/[A-Za-z]{4,}/.test(cleaned) && !CJK_RE.test(cleaned)) return null;
  return cleaned.slice(0, 4_000);
}