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>

container/agent-runner/src/providers/mock.ts

@@ -20,9 +20,11 @@ export class MockProvider implements AgentProvider {
 
     const events: AsyncIterable<ProviderEvent> = {
       async *[Symbol.asyncIterator]() {
+        yield { type: 'activity' };
         yield { type: 'init', sessionId: `mock-session-${Date.now()}` };
 
         // Process initial prompt
+        yield { type: 'activity' };
         yield { type: 'result', text: responseFactory(input.prompt) };
 
         // Process any pushed follow-ups