fix(telemetry): restore worker agent delivery and truthful system status

deploy/telemetry-plane/telegraf/mission-core-windows.conf.tmpl

@@ -1,5 +1,8 @@
 [agent]
   interval = "${MISSIONCORE_TELEMETRY_INTERVAL}"
+  flush_interval = "${MISSIONCORE_TELEMETRY_INTERVAL}"
+  metric_batch_size = 200
+  metric_buffer_limit = 2000
   round_interval = true
   omit_hostname = false
 
@@ -30,6 +33,7 @@
 [[inputs.docker]]
   endpoint = "npipe:////./pipe/docker_engine"
   container_name_include = []
+  container_state_include = ["running", "exited", "restarting", "paused"]
 
 [[inputs.http_response]]
   urls = ["http://127.0.0.1:8000/v2/health/ready"]
@@ -59,6 +63,9 @@
     "current_stage",
     "active_request_id",
     "collector_state",
+    "profile_name",
+    "input_state",
+    "wait_reason",
   ]
 
 [[inputs.tail]]
@@ -73,6 +80,7 @@
   data_type = "string"
 
 [[outputs.mqtt]]
+  startup_error_behavior = "retry"
   servers = ["tcp://${MISSIONCORE_MQTT_HOST}:${MISSIONCORE_MQTT_PORT}"]
   topic = "mission-core/v1/contours/${MISSIONCORE_CONTOUR_ID}/agents/${MISSIONCORE_AGENT_ID}/host"
   username = "${MISSIONCORE_MQTT_USERNAME}"
@@ -83,6 +91,7 @@
   namedrop = ["missioncore_pipeline", "missioncore_pipeline_event"]
 
 [[outputs.mqtt]]
+  startup_error_behavior = "retry"
   servers = ["tcp://${MISSIONCORE_MQTT_HOST}:${MISSIONCORE_MQTT_PORT}"]
   topic = "mission-core/v1/contours/${MISSIONCORE_CONTOUR_ID}/agents/${MISSIONCORE_AGENT_ID}/pipeline"
   username = "${MISSIONCORE_MQTT_USERNAME}"