fix(poll-loop): apply pre-task scripts to follow-up injections too

Tasks arriving during an active query were pushed into the stream as
follow-ups without running their `script` gate — so a wakeAgent=false
pre-script that was supposed to suppress the tick silently leaked
through and woke the agent every time. Evidence: monitoring cron
firing every 10 min with [task-script] log lines never showing.

Run applyPreTaskScripts on the follow-up batch too: wakeAgent=false
tasks get marked completed and dropped; wakeAgent=true tasks have
scriptOutput enriched exactly like the initial-batch path. Added a
pollInFlight guard to serialize async runs and avoid overlapping
script executions when the interval fires while one is still going.

Wrapped in a MODULE-HOOK:scheduling-pre-task-followup marker block
to match the existing initial-batch hook convention.

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

@@ -260,9 +260,13 @@ async function processQuery(
   // Stream liveness is decided host-side via the heartbeat file + processing
   // claim age (see src/host-sweep.ts); if something is truly stuck, the host
   // will kill the container and messages get reset to pending.
+  let pollInFlight = false;
   const pollHandle = setInterval(() => {
-    if (done) return;
+    if (done || pollInFlight) return;
+    pollInFlight = true;
 
+    void (async () => {
+      try {
         // Skip system messages (MCP tool responses) and /clear (needs fresh query).
         // Thread routing is the router's concern — if a message landed in this
         // session, the agent should see it. Per-thread sessions already isolate
@@ -275,16 +279,39 @@ async function processQuery(
           if ((m.kind === 'chat' || m.kind === 'chat-sdk') && isClearCommand(m)) return false;
           return true;
         });
-    if (newMessages.length > 0) {
+        if (newMessages.length === 0) return;
+
         const newIds = newMessages.map((m) => m.id);
         markProcessing(newIds);
 
-      const prompt = formatMessages(newMessages);
+        // Run pre-task scripts on follow-ups too — without this, a task that
-      log(`Pushing ${newMessages.length} follow-up message(s) into active query`);
+        // arrives during an active query (e.g. a */10 monitoring cron) bypasses
-      query.push(prompt);
+        // its script gate and always wakes the agent, defeating the gate.
-
+        // Mirrors the initial-batch hook above.
-      markCompleted(newIds);
+        let keep = newMessages;
+        let skipped: string[] = [];
+        // MODULE-HOOK:scheduling-pre-task-followup:start
+        const { applyPreTaskScripts } = await import('./scheduling/task-script.js');
+        const preTask = await applyPreTaskScripts(newMessages);
+        keep = preTask.keep;
+        skipped = preTask.skipped;
+        if (skipped.length > 0) {
+          markCompleted(skipped);
+          log(`Pre-task script skipped ${skipped.length} follow-up task(s): ${skipped.join(', ')}`);
         }
+        // MODULE-HOOK:scheduling-pre-task-followup:end
+
+        if (keep.length === 0) return;
+
+        const keptIds = keep.map((m) => m.id);
+        const prompt = formatMessages(keep);
+        log(`Pushing ${keep.length} follow-up message(s) into active query`);
+        query.push(prompt);
+        markCompleted(keptIds);
+      } finally {
+        pollInFlight = false;
+      }
+    })();
   }, ACTIVE_POLL_INTERVAL_MS);
 
   try {