feat: race-free on-wake messages and explicit restart CLI

Decouple container restart from config updates — config CLI ops now only
write to the DB; restart is a separate `ncl groups restart` command with
--rebuild and --message flags. Add on_wake column to messages_in so wake
messages are only picked up by a fresh container's first poll, preventing
dying containers from stealing them during the SIGTERM grace window.
killContainer accepts an onExit callback for race-free respawn. Agent-
called restart auto-scopes to the calling session.

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

container/agent-runner/src/db/connection.ts

@@ -196,7 +196,8 @@ export function initTestSessionDb(): { inbound: Database; outbound: Database } {
       platform_id    TEXT,
       channel_type   TEXT,
       thread_id      TEXT,
-      content        TEXT NOT NULL
+      content        TEXT NOT NULL,
+      on_wake        INTEGER NOT NULL DEFAULT 0
     );
     CREATE TABLE delivered (
       message_out_id      TEXT PRIMARY KEY,

container/agent-runner/src/db/messages-in.ts

@@ -49,7 +49,7 @@ function getMaxMessagesPerPrompt(): number {
  * sees the prior context it missed. Host's countDueMessages gates waking on
  * trigger=1 separately (see src/db/session-db.ts).
  */
-export function getPendingMessages(): MessageInRow[] {
+export function getPendingMessages(isFirstPoll = false): MessageInRow[] {
   const inbound = openInboundDb();
   const outbound = getOutboundDb();
 
@@ -59,10 +59,11 @@ export function getPendingMessages(): MessageInRow[] {
         `SELECT * FROM messages_in
          WHERE status = 'pending'
            AND (process_after IS NULL OR datetime(process_after) <= datetime('now'))
+           AND (on_wake = 0 OR ?1 = 1)
          ORDER BY seq DESC
-         LIMIT ?`,
+         LIMIT ?2`,
       )
-      .all(getMaxMessagesPerPrompt()) as MessageInRow[];
+      .all(isFirstPoll ? 1 : 0, getMaxMessagesPerPrompt()) as MessageInRow[];
 
     if (pending.length === 0) return [];
 

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

@@ -14,13 +14,18 @@ afterEach(() => {
   closeSessionDb();
 });
 
-function insertMessage(id: string, kind: string, content: object, opts?: { processAfter?: string; trigger?: 0 | 1 }) {
+function insertMessage(
+  id: string,
+  kind: string,
+  content: object,
+  opts?: { processAfter?: string; trigger?: 0 | 1; onWake?: 0 | 1 },
+) {
   getInboundDb()
     .prepare(
-      `INSERT INTO messages_in (id, kind, timestamp, status, process_after, trigger, content)
-     VALUES (?, ?, datetime('now'), 'pending', ?, ?, ?)`,
+      `INSERT INTO messages_in (id, kind, timestamp, status, process_after, trigger, on_wake, content)
+     VALUES (?, ?, datetime('now'), 'pending', ?, ?, ?, ?)`,
     )
-    .run(id, kind, opts?.processAfter ?? null, opts?.trigger ?? 1, JSON.stringify(content));
+    .run(id, kind, opts?.processAfter ?? null, opts?.trigger ?? 1, opts?.onWake ?? 0, JSON.stringify(content));
 }
 
 describe('formatter', () => {
@@ -131,6 +136,58 @@ describe('accumulate gate (trigger column)', () => {
   });
 });
 
+describe('on_wake filtering', () => {
+  it('first poll returns on_wake=1 messages', () => {
+    insertMessage('m1', 'chat', { sender: 'system', text: 'Resuming.' }, { onWake: 1 });
+    const messages = getPendingMessages(true);
+    expect(messages).toHaveLength(1);
+    expect(messages[0].id).toBe('m1');
+  });
+
+  it('subsequent polls skip on_wake=1 messages', () => {
+    insertMessage('m1', 'chat', { sender: 'system', text: 'Resuming.' }, { onWake: 1 });
+    const messages = getPendingMessages(false);
+    expect(messages).toHaveLength(0);
+  });
+
+  it('normal messages returned regardless of isFirstPoll', () => {
+    insertMessage('m1', 'chat', { sender: 'A', text: 'hello' });
+    expect(getPendingMessages(true)).toHaveLength(1);
+
+    // Reset: mark completed so we can re-test with a fresh message
+    markCompleted(['m1']);
+    insertMessage('m2', 'chat', { sender: 'A', text: 'hello again' });
+    expect(getPendingMessages(false)).toHaveLength(1);
+  });
+
+  it('mixed batch: first poll returns both normal and on_wake messages', () => {
+    insertMessage('m1', 'chat', { sender: 'A', text: 'user msg' });
+    insertMessage('m2', 'chat', { sender: 'system', text: 'Resuming.' }, { onWake: 1 });
+    const messages = getPendingMessages(true);
+    expect(messages).toHaveLength(2);
+    expect(messages.map((m) => m.id).sort()).toEqual(['m1', 'm2']);
+  });
+
+  it('mixed batch: subsequent poll returns only normal messages', () => {
+    insertMessage('m1', 'chat', { sender: 'A', text: 'user msg' });
+    insertMessage('m2', 'chat', { sender: 'system', text: 'Resuming.' }, { onWake: 1 });
+    const messages = getPendingMessages(false);
+    expect(messages).toHaveLength(1);
+    expect(messages[0].id).toBe('m1');
+  });
+
+  it('on_wake defaults to 0 for inserts without explicit value', () => {
+    getInboundDb()
+      .prepare(
+        `INSERT INTO messages_in (id, kind, timestamp, status, content)
+         VALUES ('m1', 'chat', datetime('now'), 'pending', '{"text":"hi"}')`,
+      )
+      .run();
+    // Should be returned even on non-first poll (on_wake=0)
+    expect(getPendingMessages(false)).toHaveLength(1);
+  });
+});
+
 describe('routing', () => {
   it('should extract routing from messages', () => {
     getInboundDb()

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

@@ -67,9 +67,11 @@ export async function runPollLoop(config: PollLoopConfig): Promise<void> {
   clearStaleProcessingAcks();
 
   let pollCount = 0;
+  let isFirstPoll = true;
   while (true) {
     // Skip system messages — they're responses for MCP tools (e.g., ask_user_question)
-    const messages = getPendingMessages().filter((m) => m.kind !== 'system');
+    const messages = getPendingMessages(isFirstPoll).filter((m) => m.kind !== 'system');
+    isFirstPoll = false;
     pollCount++;
 
     // Periodic heartbeat so we know the loop is alive