v2: fix agent-runner lifecycle and session DB reliability

- Use DELETE journal mode for session DBs instead of WAL. WAL doesn't
  sync reliably across Docker volume mounts (VirtioFS), causing dropped
  writes and duplicate deliveries.
- Add 20s idle detection to end the query stream. The concurrent poll
  tracks SDK activity via a new 'activity' provider event. When no SDK
  events arrive for 20s and no messages are pending, the stream ends
  and the poll loop continues.
- Add touchProcessing heartbeat so the host can distinguish active
  agents from idle ones by checking status_changed recency.
- Catch query errors in the poll loop and write error responses to
  messages_out instead of crashing the process.

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

src/session-manager.ts

@@ -80,7 +80,7 @@ export function initSessionFolder(agentGroupId: string, sessionId: string): void
   const dbPath = sessionDbPath(agentGroupId, sessionId);
   if (!fs.existsSync(dbPath)) {
     const db = new Database(dbPath);
-    db.pragma('journal_mode = WAL');
+    db.pragma('journal_mode = DELETE');
     db.exec(SESSION_SCHEMA);
     db.close();
     log.debug('Session DB created', { dbPath });
@@ -105,7 +105,7 @@ export function writeSessionMessage(
 ): void {
   const dbPath = sessionDbPath(agentGroupId, sessionId);
   const db = new Database(dbPath);
-  db.pragma('journal_mode = WAL');
+  db.pragma('journal_mode = DELETE');
 
   try {
     db.prepare(
@@ -134,7 +134,7 @@ export function writeSessionMessage(
 export function openSessionDb(agentGroupId: string, sessionId: string): Database.Database {
   const dbPath = sessionDbPath(agentGroupId, sessionId);
   const db = new Database(dbPath);
-  db.pragma('journal_mode = WAL');
+  db.pragma('journal_mode = DELETE');
   return db;
 }