fix: prevent reasoning text leak through handleMessageEnd fallback

When enforceFinalTag is active (Google providers), stripBlockTags
correctly returns empty for text without <final> tags. However, the
handleMessageEnd fallback recovered raw text, bypassing this protection
and leaking internal reasoning (e.g. "**Applying single-bot mention
rule**NO_REPLY") to Discord.

Guard the fallback with enforceFinalTag check: if the provider is
supposed to use <final> tags and none were seen, the text is treated
as leaked reasoning and suppressed.

Also harden stripSilentToken regex to allow bold markdown (**) as
separator before NO_REPLY, matching the pattern Gemini Flash Lite
produces.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/agents/pi-embedded-subscribe.handlers.messages.ts

@@ -288,7 +288,7 @@ export function handleMessageEnd(
   let mediaUrls = parsedText?.mediaUrls;
   let hasMedia = Boolean(mediaUrls && mediaUrls.length > 0);
 
-  if (!cleanedText && !hasMedia) {
+  if (!cleanedText && !hasMedia && !ctx.params.enforceFinalTag) {
     const rawTrimmed = rawText.trim();
     const rawStrippedFinal = rawTrimmed.replace(/<\s*\/?\s*final\s*>/gi, "").trim();
     const rawCandidate = rawStrippedFinal || rawTrimmed;