fix: status falls back to the live agent before the first host frame; recent route ties break deterministically

Under turn isolation `session.status` passed agent=None and only the metadata
mirror's model/provider, so until the compute host sent its first frame the
mirror was empty and the TUI rendered "Model: (unknown) (unknown)" where main
showed the in-process agent's route. Fall back to the live agent's model and
provider like `server._session_info` already does.

`get_recent_session_model_route` ordered by `last_seen DESC` alone; two rows
stamped in the same flush tie and SQLite's temp-sort order is unspecified, so
the retired route could be reported as current. Order by `rowid DESC` as the
secondary key so the route that appeared later wins.

hermes_state_sessions.py

@@ -748,7 +748,9 @@ class SessionSessionsMixin:
         """Most recently used main-loop model route as one coherent per-call tuple
         (``session_model_usage`` keeps model+provider together; ``sessions`` mixes route changes).
         Recency, not lifetime call count: on a long session a route retired weeks ago can hold the
-        highest ``api_call_count`` forever, and /status and /usage would keep calling it current."""
+        highest ``api_call_count`` forever, and /status and /usage would keep calling it current.
+        ``rowid DESC`` breaks same-timestamp ties toward the route that first appeared later; without
+        it SQLite's temp-sort order is unspecified and the retired route can win."""
         self.flush_token_counts()
         row = self._read_one(
             """SELECT model, billing_provider, billing_base_url, billing_mode,
@@ -758,7 +760,7 @@ class SessionSessionsMixin:
                   AND task = ''
                   AND model <> 'unknown'
                   AND billing_provider <> ''
-                ORDER BY last_seen DESC
+                ORDER BY last_seen DESC, rowid DESC
                 LIMIT 1""",
             (session_id,),
         )