feat(runtime): wire personal memory observation and skill runtime config

Hook shadow pipeline observation into session finish and agent runs, and
expose skill runtime settings through auth and runtime status endpoints.

Co-authored-by: Cursor <cursoragent@cursor.com>

chat-agent-run-gate.test.mjs

@@ -25,6 +25,17 @@ test('resolvePostAgentRunChatState prefers portal direct chat completion', () =>
   );
 });
 
+test('resolvePostAgentRunChatState idles after worker-side agent run success', () => {
+  assert.equal(
+    resolvePostAgentRunChatState({ chatState: 'waiting', agentRunSucceeded: true }),
+    'idle',
+  );
+  assert.equal(
+    resolvePostAgentRunChatState({ chatState: 'streaming', agentRunSucceeded: true }),
+    'idle',
+  );
+});
+
 test('shouldPromoteSessionIdToStreaming skips re-streaming after Finish', () => {
   assert.equal(shouldPromoteSessionIdToStreaming('idle'), false);
   assert.equal(shouldPromoteSessionIdToStreaming('waiting'), true);