feat: AI conversation threading

config.json

@@ -6,7 +6,12 @@
     "systemPrompt": "You are Volvox Bot, the friendly AI assistant for the Volvox developer community Discord server.\n\nYou're witty, snarky (but warm), and deeply knowledgeable about programming, software development, and tech.\n\nKey traits:\n- Helpful but not boring\n- Can roast people lightly when appropriate\n- Enthusiastic about cool tech and projects\n- Supportive of beginners learning to code\n- Concise - this is Discord, not an essay\n\n⚠️ CRITICAL RULES:\n- NEVER type @.everyone or @.here (remove the dots) - these ping hundreds of people\n- NEVER use mass mention pings under any circumstances\n- If you need to address the group, say \"everyone\" or \"folks\" without the @ symbol\n\nKeep responses under 2000 chars. Use Discord markdown when helpful.",
     "channels": [],
     "historyLength": 20,
-    "historyTTLDays": 30
+    "historyTTLDays": 30,
+    "threadMode": {
+      "enabled": false,
+      "autoArchiveMinutes": 60,
+      "reuseWindowMinutes": 30
+    }
   },
   "chimeIn": {
     "enabled": false,

src/modules/events.js

@@ -10,6 +10,7 @@ import { needsSplitting, splitMessage } from '../utils/splitMessage.js';
 import { generateResponse } from './ai.js';
 import { accumulate, resetCounter } from './chimeIn.js';
 import { isSpam, sendSpamAlert } from './spam.js';
+import { getOrCreateThread, shouldUseThread } from './threading.js';
 import { recordCommunityActivity, sendWelcomeMessage } from './welcome.js';
 
 /** @type {boolean} Guard against duplicate process-level handler registration */
@@ -54,10 +55,10 @@ export function registerGuildMemberAddHandler(client, config) {
 }
 
 /**
- * Register message create event handler
- * @param {Client} client - Discord client
- * @param {Object} config - Bot configuration
- * @param {Object} healthMonitor - Health monitor instance
+ * Register the MessageCreate event handler that processes incoming messages for spam detection, community activity recording, AI-driven replies (mentions/replies, optional threading, channel whitelisting), and organic chime-in accumulation.
+ * @param {Client} client - Discord client instance used to listen and respond to message events.
+ * @param {Object} config - Bot configuration (reads moderation.enabled, ai.enabled, ai.channels and other settings referenced by handlers).
+ * @param {Object} healthMonitor - Optional health monitor used when generating AI responses to record metrics.
  */
 export function registerMessageCreateHandler(client, config, healthMonitor) {
   client.on(Events.MessageCreate, async (message) => {
@@ -100,10 +101,25 @@ export function registerMessageCreateHandler(client, config, healthMonitor) {
             return;
           }
 
-          await message.channel.sendTyping();
+          // Determine whether to use threading
+          const useThread = shouldUseThread(message);
+          let targetChannel = message.channel;
+
+          if (useThread) {
+            const { thread } = await getOrCreateThread(message, cleanContent);
+            if (thread) {
+              targetChannel = thread;
+            }
+            // If thread is null, fall back to inline reply (targetChannel stays as message.channel)
+          }
+
+          await targetChannel.sendTyping();
+
+          // Use thread ID for conversation history when in a thread, otherwise channel ID
+          const historyId = targetChannel.id;
 
           const response = await generateResponse(
-            message.channel.id,
+            historyId,
             cleanContent,
             message.author.username,
             config,
@@ -114,10 +130,14 @@ export function registerMessageCreateHandler(client, config, healthMonitor) {
           if (needsSplitting(response)) {
             const chunks = splitMessage(response);
             for (const chunk of chunks) {
-              await message.channel.send(chunk);
+              await targetChannel.send(chunk);
             }
-          } else {
+          } else if (targetChannel === message.channel) {
+            // Inline reply — use message.reply for the reference
             await message.reply(response);
+          } else {
+            // Thread reply — send directly to the thread
+            await targetChannel.send(response);
           }
         } catch (sendErr) {
           logError('Failed to send AI response', {