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

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

trex_core/application/messaging_handlers.py

@@ -192,6 +192,63 @@ class SlotsBrokerQuantityReader(Protocol):
     def holdings_for_slots_rpc(self) -> tuple[list[BalanceItem], datetime]: ...
 
 
+class SlotsBrokerBalanceHealthReader(Protocol):
+    def balance_health_for_slots_rpc(self) -> dict[str, dict[str, object]]: ...
+
+
+_BALANCE_HEALTH_STATES = frozenset({"ok", "unavailable", "stale"})
+_BALANCE_HEALTH_FAILURE_CODES = frozenset({
+    "token_issuance_failed",
+    "authentication_failed",
+    "authorization_failed",
+    "transport_failed",
+    "timeout",
+    "http_5xx",
+    "malformed_response",
+    "broker_rejected",
+    "ownership_mismatch",
+    "stale_snapshot",
+    "account_mismatch",
+    "not_ready",
+    "expired",
+    "live_read_failed",
+    "read_failed",
+})
+
+
+def _sanitize_balance_worker_status(
+    *,
+    instance_key: str,
+    worker: str,
+    raw: dict[str, object],
+) -> dict[str, object]:
+    state = str(raw.get("state") or "unavailable")
+    if state not in _BALANCE_HEALTH_STATES:
+        state = "unavailable"
+    try:
+        consecutive_failures = max(0, int(raw.get("consecutive_failures", 0)))
+    except (TypeError, ValueError):
+        consecutive_failures = 0
+    failure_code_raw = raw.get("failure_code")
+    failure_code = (
+        str(failure_code_raw)
+        if isinstance(failure_code_raw, str)
+        and failure_code_raw in _BALANCE_HEALTH_FAILURE_CODES
+        else None
+    )
+    last_success_at = raw.get("last_success_at")
+    next_retry_at = raw.get("next_retry_at")
+    return {
+        "instance_key": instance_key,
+        "worker": worker,
+        "state": state,
+        "last_success_at": last_success_at if isinstance(last_success_at, str) else None,
+        "consecutive_failures": consecutive_failures,
+        "failure_code": failure_code,
+        "next_retry_at": next_retry_at if isinstance(next_retry_at, str) else None,
+    }
+
+
 def make_slots_rpc_handler(
     slot_repo: SlotRepository,
     *,
@@ -205,6 +262,7 @@ def make_slots_rpc_handler(
     max_active_slots: Optional[int] = None,
     strategy_state_store=None,
     broker_quantity_reader: Optional[SlotsBrokerQuantityReader] = None,
+    broker_balance_health_reader: Optional[SlotsBrokerBalanceHealthReader] = None,
 ):
     """Build the RPC handler for `trex.slots.req` (REQ-073/074/116).
 
@@ -437,6 +495,23 @@ def make_slots_rpc_handler(
             "reason": reason,
             "message": message,
         }
+        if broker_balance_health_reader is not None:
+            try:
+                raw_health = broker_balance_health_reader.balance_health_for_slots_rpc()
+            except Exception:  # noqa: BLE001 - status surface must stay available
+                raw_health = {}
+            health_payload: dict[str, dict[str, object]] = {}
+            if isinstance(raw_health, dict):
+                for worker, raw in raw_health.items():
+                    if not isinstance(worker, str) or not worker or not isinstance(raw, dict):
+                        continue
+                    health_payload[worker] = _sanitize_balance_worker_status(
+                        instance_key=instance_key,
+                        worker=worker,
+                        raw=raw,
+                    )
+            if health_payload:
+                base_payload["broker_balance_health"] = health_payload
         if warn_store is not None:
             base_payload["excluded_slots"] = {
                 "reconcile_quantity_mismatch": excluded_count,