fix(broker): restore main wiring and add production retry cadence + status surface

Co-authored-by: genichin <4282227+genichin@users.noreply.github.com>

tests/application/test_balance_health.py

@@ -0,0 +1,38 @@
+from __future__ import annotations
+
+from datetime import UTC, datetime, timedelta
+
+from trex_core.application.balance_health import BalanceHealthTracker
+
+
+def test_long_outage_backoff_is_capped_and_status_stays_valid():
+    now = {"t": datetime(2026, 9, 12, tzinfo=UTC)}
+    tracker = BalanceHealthTracker(clock=lambda: now["t"], base_backoff_sec=15, max_backoff_sec=300)
+
+    backoffs: list[float] = []
+    for _ in range(20):
+        lifecycle, backoff = tracker.record_failure("execution", code="http_5xx")
+        backoffs.append(backoff)
+        assert lifecycle in {None, "detected", "ongoing"}
+        now["t"] += timedelta(seconds=301)
+
+    assert max(backoffs) == 300.0
+    state = tracker.status("execution", stale_after_sec=600)
+    assert state["state"] == "unavailable"
+    assert state["consecutive_failures"] == 20
+    assert state["failure_code"] == "http_5xx"
+
+
+def test_restart_resets_process_local_health_and_re_emits_detected():
+    now = {"t": datetime(2026, 9, 12, tzinfo=UTC)}
+    before_restart = BalanceHealthTracker(clock=lambda: now["t"])
+    before_restart.record_success("execution")
+    lifecycle, _ = before_restart.record_failure("execution", code="timeout")
+    assert lifecycle == "detected"
+
+    after_restart = BalanceHealthTracker(clock=lambda: now["t"])
+    lifecycle, _ = after_restart.record_failure("execution", code="timeout")
+    assert lifecycle == "detected"
+    state = after_restart.status("execution", stale_after_sec=600)
+    assert state["last_success_at"] is None
+    assert state["consecutive_failures"] == 1