fix(automod): flow real LLM analysis + descriptive fallback

Root cause: ai-analysis-worker read llmResult.explanation and
llmResult.toxicityScore — fields the LLM pipeline never produces
(canonical AnalysisResult uses analysis/score). Every message fell back
to the bare template "Tidak ada indikasi pelanggaran." and the stored
score was always 0.

- Map analysis/score correctly; fallback now quotes the message content
- Prompt: ban generic analysis phrasing, require reply context
- LLM context: include replied-to message content (metadata.reference)
  so the model can explain what the user is replying to
- Frontend: show thread/channel names from metadata instead of raw IDs
  (message card, detail views, search overlay); detail panel now
  displays the ai_analysis text
- Auto-delete log/DM include the descriptive analysis as the reason

services/discord-gateway/src/modules/ai-moderation/autoDeleteLogger.ts

@@ -33,6 +33,7 @@ export async function logDeletionToChannel(
       const severity = message.ai_severity ?? "none";
       const categories =
         message.ai_categories ?? message.ai_moderation_flags ?? "—";
+      const reason = message.ai_analysis ?? "—";
       const snippet = (message.edited_content ?? message.content).substring(
         0,
         200,
@@ -42,6 +43,7 @@ export async function logDeletionToChannel(
           `**Status:** ${message.ai_status}\n` +
           `**Severitas:** ${severity}\n` +
           `**Kategori:** ${categories}\n` +
+          `**Alasan:** ${reason}\n` +
           `**Isi:** ${snippet}\n` +
           `**Waktu:** <t:${Math.floor(Date.now() / 1000)}:R>`,
       );