From 62ba69a29d4e78635b4eb0c086e569c17bbbe800 Mon Sep 17 00:00:00 2001
From: teknium1 <teknium1@gmail.com>
Date: Tue, 10 Feb 2026 16:01:00 -0800
Subject: [PATCH] Fix gateway exit code to enable systemd auto-restart on
 connection failure

- Updated the start_gateway function to return a boolean indicating success or failure, allowing for better control over exit codes.
- Modified the main function to handle gateway startup failures, ensuring systemd can automatically restart on transient errors.
- Enhanced error handling in the hermes_cli gateway to exit with code 1 if the gateway fails to connect to any platform.
---
 gateway/run.py        | 14 ++++++++++----
 hermes_cli/gateway.py |  6 +++++-
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/gateway/run.py b/gateway/run.py
index 2e126d59f..81c5dcf09 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -612,11 +612,13 @@ class GatewayRunner:
         return response
 
 
-async def start_gateway(config: Optional[GatewayConfig] = None) -> None:
+async def start_gateway(config: Optional[GatewayConfig] = None) -> bool:
     """
     Start the gateway and run until interrupted.
     
     This is the main entry point for running the gateway.
+    Returns True if the gateway ran successfully, False if it failed to start.
+    A False return causes a non-zero exit code so systemd can auto-restart.
     """
     runner = GatewayRunner(config)
     
@@ -635,10 +637,11 @@ async def start_gateway(config: Optional[GatewayConfig] = None) -> None:
     # Start the gateway
     success = await runner.start()
     if not success:
-        return
+        return False
     
     # Wait for shutdown
     await runner.wait_for_shutdown()
+    return True
 
 
 def main():
@@ -658,8 +661,11 @@ def main():
             data = json.load(f)
             config = GatewayConfig.from_dict(data)
     
-    # Run the gateway
-    asyncio.run(start_gateway(config))
+    # Run the gateway - exit with code 1 if no platforms connected,
+    # so systemd Restart=on-failure will retry on transient errors (e.g. DNS)
+    success = asyncio.run(start_gateway(config))
+    if not success:
+        sys.exit(1)
 
 
 if __name__ == "__main__":
diff --git a/hermes_cli/gateway.py b/hermes_cli/gateway.py
index 579ea5f1e..f36c21b86 100644
--- a/hermes_cli/gateway.py
+++ b/hermes_cli/gateway.py
@@ -360,7 +360,11 @@ def run_gateway(verbose: bool = False):
     print("└─────────────────────────────────────────────────────────┘")
     print()
     
-    asyncio.run(start_gateway())
+    # Exit with code 1 if gateway fails to connect any platform,
+    # so systemd Restart=on-failure will retry on transient errors
+    success = asyncio.run(start_gateway())
+    if not success:
+        sys.exit(1)
 
 
 # =============================================================================