fixed issue where remote agents could create duplicates in hub

butane/monitor.yaml

@@ -4,8 +4,8 @@ version: 1.0.0
 # Dozzle log viewer hub.
 #
 # Aggregates container logs from the dozzle agents running on the other Flatcar
-# VMs (see butane/oswl_connector.yaml.tftpl) and, via the local socket, from
+# VMs (see the dozzle-agent units in the other butane configs) and, via the
-# this host's own containers. Reachable at http://192.168.7.63:8080.
+# local socket, from this host's own containers. Reachable on :8080.
 #
 # No state is kept on disk: /data is a tmpfs, so the container is fully
 # disposable and there is nothing to back up. That is also why simple auth
@@ -13,8 +13,9 @@ version: 1.0.0
 #
 # Hub <-> agent traffic is TLS, using the certificate pair baked into the
 # dozzle image. Every hub and agent on the same image version shares it, so
-# nothing needs mounting here. To move to a custom pair later, generate one
+# nothing needs mounting here -- which is also why the agents must stay pinned
-# with (do not run as root, writes into $PWD):
+# to the same tag as the hub. To move to a custom pair later, generate one
+# with (writes into $PWD):
 #
 #   docker run --rm -v "$PWD":/out amir20/dozzle:v11.1.1 generate-certs \
 #     --cert-out /out/dozzle_cert.pem --key-out /out/dozzle_key.pem
@@ -34,20 +35,69 @@ systemd:
         Requires=docker.service
         [Service]
         TimeoutStartSec=0
+        # Kept as unit environment rather than inline -e values so that
+        # wait-for-agents.sh can read the agent list from the same place the
+        # container does. docker run forwards them by bare name below.
+        Environment="DOZZLE_HOSTNAME=Oswald Logs"
+        Environment="DOZZLE_ENABLE_MCP=true"
+        Environment="DOZZLE_REMOTE_AGENT=192.168.7.60:7007|oswald-runner|Goose,192.168.7.61:7007|ai|Goose,192.168.7.62:7007|oswl-connector|Goose"
         # Pulled up front so a slow first pull is not mistaken for a hung unit.
         ExecStartPre=/usr/bin/docker pull amir20/dozzle:v11.1.1
         # Leading "-" so a missing container is not a failure.
         ExecStartPre=-/usr/bin/docker rm --force dozzle
+        # If the hub starts before the agents are listening, the failed initial
+        # handshake leaves a permanently-offline placeholder host in the UI
+        # alongside the real one once it connects. Bounded and "-" prefixed, so
+        # an agent that is genuinely gone delays the hub but never blocks it.
+        ExecStartPre=-/usr/bin/timeout 180 /opt/dozzle/wait-for-agents.sh
         # Foreground (no -d) so systemd supervises the container process.
         ExecStart=/usr/bin/docker run --rm --name dozzle \
           -v /var/run/docker.sock:/var/run/docker.sock:ro \
           --tmpfs /data \
           -p 8080:8080 \
-          -e "DOZZLE_HOSTNAME=Oswald Logs" \
+          -e DOZZLE_HOSTNAME \
-          -e "DOZZLE_REMOTE_AGENT=192.168.7.60:7007|oswald-runner|Infra,192.168.7.61:7007|ai|Infra,192.168.7.62:7007|oswl-connector|Infra" \
+          -e DOZZLE_ENABLE_MCP \
+          -e DOZZLE_REMOTE_AGENT \
           amir20/dozzle:v11.1.1
         ExecStop=/usr/bin/docker stop dozzle
         Restart=always
         RestartSec=5s
         [Install]
         WantedBy=multi-user.target
+
+storage:
+  files:
+    # Blocks until every agent named in DOZZLE_REMOTE_AGENT accepts a TCP
+    # connection. The list is read from the environment, so adding or removing
+    # an agent above needs no change here.
+    - path: /opt/dozzle/wait-for-agents.sh
+      mode: 0755
+      contents:
+        inline: |
+          #!/usr/bin/bash
+          # Note: /dev/tcp is unavailable -- Flatcar's bash is built without
+          # net redirections -- so reachability is probed with curl. The agent
+          # speaks gRPC over TLS, so any completed connection answers with a
+          # protocol error; only exit 7 (refused) and 28 (timeout) mean the
+          # agent is not up yet.
+          if [ -z "$DOZZLE_REMOTE_AGENT" ]; then
+            exit 0
+          fi
+
+          for entry in $(echo "$DOZZLE_REMOTE_AGENT" | tr ',' ' '); do
+            # Strip the |name|group suffix; what is left is host:port.
+            hostport=$(echo "$entry" | cut -d'|' -f1)
+            while true; do
+              curl -sk -o /dev/null --max-time 3 "https://$hostport"
+              rc=$?
+              case "$rc" in
+                7|28)
+                  echo "waiting for dozzle agent $hostport"
+                  sleep 2
+                  ;;
+                *)
+                  break
+                  ;;
+              esac
+            done
+          done