fix: reply in the Slack DM thread the user wrote in

- chat-sdk-bridge: forward thread.id to the router for DMs so sub-thread
  context survives into delivery. Previously hardcoded to null, which
  collapsed every reply to the DM top level.
- router: when a DM (is_group=0) is wired as `shared`, don't auto-escalate
  to per-thread — keep one session for the whole DM and let thread_id
  flow through to the adapter.
- agent-runner poll-loop: defer follow-up messages whose thread_id
  differs from the active turn's routing. Mixing threads into one
  streaming turn sent every reply to the first thread because routing
  is captured at turn start.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

container/agent-runner/src/poll-loop.ts

@@ -249,13 +249,18 @@ async function processQuery(query: AgentQuery, routing: RoutingContext, config:
   const pollHandle = setInterval(() => {
     if (done) return;
 
-    // Skip system messages (MCP tool responses) and admin commands (need fresh query)
+    // Skip system messages (MCP tool responses) and admin commands (need fresh query).
+    // Also defer messages whose thread_id differs from the active turn's routing
+    // — mixing threads into one streaming turn would send the reply to the wrong
+    // thread because `routing` is captured at turn start. The next turn will pick
+    // them up with fresh routing.
     const newMessages = getPendingMessages().filter((m) => {
       if (m.kind === 'system') return false;
       if (m.kind === 'chat' || m.kind === 'chat-sdk') {
         const cmd = categorizeMessage(m);
         if (cmd.category === 'admin') return false;
       }
+      if ((m.thread_id ?? null) !== (routing.threadId ?? null)) return false;
       return true;
     });
     if (newMessages.length > 0) {

src/channels/chat-sdk-bridge.ts

@@ -175,11 +175,14 @@ export function createChatSdkBridge(config: ChatSdkBridgeConfig): ChannelAdapter
         await thread.subscribe();
       });
 
-      // DMs — always forward + subscribe
+      // DMs — always forward + subscribe. Pass thread.id so sub-thread
+      // context carries through to delivery (Slack users can open threads
+      // inside a DM). The router collapses DM sub-threads to one session
+      // (is_group=0 short-circuits the per-thread escalation).
       chat.onDirectMessage(async (thread, message) => {
         const channelId = adapter.channelIdFromThreadId(thread.id);
         log.info('Inbound DM received', { adapter: adapter.name, channelId, sender: (message.author as any)?.fullName ?? (message.author as any)?.userId ?? 'unknown', threadId: thread.id });
-        await setupConfig.onInbound(channelId, null, await messageToInbound(message));
+        await setupConfig.onInbound(channelId, thread.id, await messageToInbound(message));
         await thread.subscribe();
       });
 

src/router.ts

@@ -144,8 +144,12 @@ export async function routeInbound(event: InboundEvent): Promise<void> {
   // wiring says, because "thread = session" is the first-class model for
   // threaded platforms. Agent-shared is preserved because it expresses a
   // cross-channel intent the adapter can't know about.
+  //
+  // Exception: DMs (is_group=0). Sub-threads within a DM are a UX affordance,
+  // not a conversation boundary — treat the whole DM as one session and let
+  // threadId flow through to delivery so replies land in the right sub-thread.
   let effectiveSessionMode = match.session_mode;
-  if (adapter && adapter.supportsThreads && effectiveSessionMode !== 'agent-shared') {
+  if (adapter && adapter.supportsThreads && effectiveSessionMode !== 'agent-shared' && mg.is_group !== 0) {
     effectiveSessionMode = 'per-thread';
   }
   const { session, created } = resolveSession(match.agent_group_id, mg.id, event.threadId, effectiveSessionMode);