feat: stabilize multi-region runtime sync and worker orchestration

domain-api/app/core/redis_client.py

@@ -1,17 +1,64 @@
 from __future__ import annotations
 
+import os
+import threading
+
 import redis
 
 from app.core.config import settings
 
 
+_REDIS_CLIENT: redis.Redis | None = None
+_LOCK = threading.Lock()
+
+
+def _safe_int(raw_value: object, default: int, minimum: int) -> int:
+    try:
+        parsed = int(raw_value)
+    except Exception:
+        parsed = default
+    return max(minimum, parsed)
+
+
+def _safe_float(raw_value: object, default: float, minimum: float) -> float:
+    try:
+        parsed = float(raw_value)
+    except Exception:
+        parsed = default
+    return max(minimum, parsed)
+
+
 def get_redis() -> redis.Redis:
-    return redis.Redis(
-        host=settings.redis_host,
-        port=settings.redis_port,
-        password=settings.redis_password or None,
-        db=settings.redis_db,
-        decode_responses=True,
-        socket_connect_timeout=5,
-        socket_timeout=5,
-    )
+    global _REDIS_CLIENT
+    with _LOCK:
+        if _REDIS_CLIENT is not None:
+            return _REDIS_CLIENT
+
+        pool = redis.BlockingConnectionPool(
+            host=settings.redis_host,
+            port=settings.redis_port,
+            password=settings.redis_password or None,
+            db=settings.redis_db,
+            decode_responses=True,
+            socket_connect_timeout=5,
+            socket_timeout=5,
+            health_check_interval=_safe_int(os.getenv("DOMAIN_API_REDIS_HEALTH_CHECK_INTERVAL", "30"), 30, 0),
+            retry_on_timeout=True,
+            max_connections=_safe_int(os.getenv("DOMAIN_API_REDIS_MAX_CONNECTIONS", "32"), 32, 1),
+            timeout=_safe_float(os.getenv("DOMAIN_API_REDIS_POOL_TIMEOUT", "1.5"), 1.5, 0.1),
+            client_name=f"domain-api:{settings.node_code}:{os.getpid()}",
+        )
+        _REDIS_CLIENT = redis.Redis(connection_pool=pool)
+        return _REDIS_CLIENT
+
+
+def reset_redis_client_for_tests() -> None:
+    global _REDIS_CLIENT
+    with _LOCK:
+        client = _REDIS_CLIENT
+        _REDIS_CLIENT = None
+    if client is not None:
+        try:
+            client.close()
+        except Exception:
+            pass