Merge pull request #15113 from Security-Onion-Solutions/reyesj2/es-8188

generate new elastic agents in post soup

.github/DISCUSSION_TEMPLATE/2-4.yml

@@ -31,6 +31,7 @@ body:
         - 2.4.160
         - 2.4.170
         - 2.4.180
+        - 2.4.190
         - Other (please provide detail below)
     validations:
       required: true

VERSION

@@ -1 +1 @@
-2.4.180
+2.4.0-foxtrot

salt/common/tools/sbin/so-common

@@ -323,8 +323,8 @@ get_elastic_agent_vars() {
 
 	if [ -f "$defaultsfile" ]; then
 		ELASTIC_AGENT_TARBALL_VERSION=$(egrep " +version: " $defaultsfile | awk -F: '{print $2}' | tr -d '[:space:]')
-		ELASTIC_AGENT_URL="https://repo.securityonion.net/file/so-repo/prod/2.4/elasticagent/elastic-agent_SO-$ELASTIC_AGENT_TARBALL_VERSION.tar.gz"
-		ELASTIC_AGENT_MD5_URL="https://repo.securityonion.net/file/so-repo/prod/2.4/elasticagent/elastic-agent_SO-$ELASTIC_AGENT_TARBALL_VERSION.md5"
+		ELASTIC_AGENT_URL="https://demo.jorgereyes.dev/elastic-agent_SO-$ELASTIC_AGENT_TARBALL_VERSION.tar.gz"
+		ELASTIC_AGENT_MD5_URL="https://demo.jorgereyes.dev/elastic-agent_SO-$ELASTIC_AGENT_TARBALL_VERSION.md5"
 		ELASTIC_AGENT_FILE="/nsm/elastic-fleet/artifacts/elastic-agent_SO-$ELASTIC_AGENT_TARBALL_VERSION.tar.gz"
 		ELASTIC_AGENT_MD5="/nsm/elastic-fleet/artifacts/elastic-agent_SO-$ELASTIC_AGENT_TARBALL_VERSION.md5"
 		ELASTIC_AGENT_EXPANSION_DIR=/nsm/elastic-fleet/artifacts/beats/elastic-agent
@@ -441,8 +441,7 @@ lookup_grain() {
 
 lookup_role() {
 	id=$(lookup_grain id)
-	pieces=($(echo $id | tr '_' ' '))
-	echo ${pieces[1]}
+	echo "${id##*_}"
 }
 
 is_feature_enabled() {

salt/common/tools/sbin/so-log-check

@@ -268,6 +268,13 @@ for log_file in $(cat /tmp/log_check_files); do
     tail -n $RECENT_LOG_LINES $log_file > /tmp/log_check
     check_for_errors
 done
+# Look for OOM specific errors in /var/log/messages which can lead to odd behavior / test failures
+if [[ -f /var/log/messages ]]; then
+    status "Checking log file /var/log/messages"
+    if journalctl --since "24 hours ago" | grep -iE 'out of memory|oom-kill'; then
+        RESULT=1
+    fi
+fi
 
 # Cleanup temp files
 rm -f /tmp/log_check_files

salt/common/tools/sbin_jinja/so-import-pcap

@@ -173,7 +173,7 @@ for PCAP in $INPUT_FILES; do
   status "- assigning unique identifier to import: $HASH"
 
   pcap_data=$(pcapinfo "${PCAP}")
-  if ! echo "$pcap_data" | grep -q "First packet time:" || echo "$pcap_data" |egrep -q "Last packet time:    1970-01-01|Last packet time:    n/a"; then
+  if ! echo "$pcap_data" | grep -q "Earliest packet time:" || echo "$pcap_data" |egrep -q "Latest packet time:   1970-01-01|Latest packet time:   n/a"; then
     status "- this PCAP file is invalid; skipping"
     INVALID_PCAPS_COUNT=$((INVALID_PCAPS_COUNT + 1))
   else
@@ -205,8 +205,8 @@ for PCAP in $INPUT_FILES; do
       HASHES="${HASHES} ${HASH}"
     fi
 
-    START=$(pcapinfo "${PCAP}" -a |grep "First packet time:" | awk '{print $4}')
-    END=$(pcapinfo "${PCAP}" -e |grep "Last packet time:" | awk '{print $4}')
+    START=$(pcapinfo "${PCAP}" -a |grep "Earliest packet time:" | awk '{print $4}')
+    END=$(pcapinfo "${PCAP}" -e |grep "Latest packet time:" | awk '{print $4}')
     status "- found PCAP data spanning dates $START through $END"
 
     # compare $START to $START_OLDEST

salt/elasticfleet/enabled.sls

@@ -135,12 +135,18 @@ so-elastic-fleet-package-statefile:
 so-elastic-fleet-package-upgrade:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-package-upgrade
+    - retry:
+        attempts: 3
+        interval: 10
     - onchanges:
       - file: /opt/so/state/elastic_fleet_packages.txt
 
 so-elastic-fleet-integrations:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-integration-policy-load
+    - retry:
+        attempts: 3
+        interval: 10
 
 so-elastic-agent-grid-upgrade:
   cmd.run:
@@ -152,7 +158,11 @@ so-elastic-agent-grid-upgrade:
 so-elastic-fleet-integration-upgrade:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-integration-upgrade
+    - retry:
+        attempts: 3
+        interval: 10
 
+{# Optional integrations script doesn't need the retries like so-elastic-fleet-integration-upgrade which loads the default integrations #}
 so-elastic-fleet-addon-integrations:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-optional-integrations-load

salt/elasticfleet/files/integrations/grid-nodes_general/import-evtx-logs.json

@@ -20,7 +20,7 @@
             ],
             "data_stream.dataset": "import",
             "custom": "",
-            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- drop_fields:\n    fields: [\"host\"]\n    ignore_missing: true\n- add_fields:\n    target: data_stream\n    fields:\n      type: logs\n      dataset: system.security\n- add_fields:\n    target: event\n    fields:\n      dataset: system.security\n      module: system\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: logs-system.security-2.5.4\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.sysmon_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.sysmon_operational-3.1.2\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.application-2.5.4\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.system-2.5.4\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.powershell_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.powershell_operational-3.1.2\n- add_fields:\n    target: data_stream\n    fields:\n        dataset: import",
+            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- drop_fields:\n    fields: [\"host\"]\n    ignore_missing: true\n- add_fields:\n    target: data_stream\n    fields:\n      type: logs\n      dataset: system.security\n- add_fields:\n    target: event\n    fields:\n      dataset: system.security\n      module: system\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: logs-system.security-2.6.1\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.sysmon_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.sysmon_operational-3.1.2\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.application-2.6.1\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.system-2.6.1\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.powershell_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.powershell_operational-3.1.2\n- add_fields:\n    target: data_stream\n    fields:\n        dataset: import",
             "tags": [
               "import"
             ]

salt/elasticfleet/tools/sbin/so-elastic-fleet-common

@@ -23,6 +23,13 @@ fi
 # Define a banner to separate sections
 banner="========================================================================="
 
+fleet_api() {
+    local QUERYPATH=$1
+    shift
+
+    curl -sK /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/${QUERYPATH}" "$@" --retry 3 --retry-delay 10 --fail 2>/dev/null
+}
+
 elastic_fleet_integration_check() {
 
     AGENT_POLICY=$1
@@ -39,7 +46,9 @@ elastic_fleet_integration_create() {
 
     JSON_STRING=$1
 
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/package_policies" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+    if ! fleet_api "package_policies" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPOST -d "$JSON_STRING"; then
+        return 1
+    fi
 }
 
 
@@ -56,7 +65,10 @@ elastic_fleet_integration_remove() {
                     '{"packagePolicyIds":[$INTEGRATIONID]}'
                     )
 
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/package_policies/delete" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+    if ! fleet_api "package_policies/delete" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+        echo "Error: Unable to delete '$NAME' from '$AGENT_POLICY'"
+        return 1
+    fi
 }
 
 elastic_fleet_integration_update() {
@@ -65,7 +77,9 @@ elastic_fleet_integration_update() {
 
     JSON_STRING=$2
 
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/package_policies/$UPDATE_ID" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+    if ! fleet_api "package_policies/$UPDATE_ID" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPUT -d "$JSON_STRING"; then
+        return 1
+    fi
 }
 
 elastic_fleet_integration_policy_upgrade() {
@@ -77,78 +91,83 @@ elastic_fleet_integration_policy_upgrade() {
                     '{"packagePolicyIds":[$INTEGRATIONID]}'
                     )
 
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/package_policies/upgrade" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+    if ! fleet_api "package_policies/upgrade" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+        return 1
+    fi
 }
 
 
 elastic_fleet_package_version_check() {
     PACKAGE=$1
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/epm/packages/$PACKAGE" | jq -r '.item.version'
+
+    if output=$(fleet_api "epm/packages/$PACKAGE"); then
+        echo "$output" | jq -r '.item.version'
+    else
+        echo "Error: Failed to get current package version for '$PACKAGE'"
+        return 1
+    fi
 }
 
 elastic_fleet_package_latest_version_check() {
     PACKAGE=$1
-    if output=$(curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/epm/packages/$PACKAGE" --fail); then
+    if output=$(fleet_api "epm/packages/$PACKAGE"); then
         if version=$(jq -e -r '.item.latestVersion' <<< $output); then
             echo "$version"
         fi
     else
-        echo "Error: Failed to get latest version for $PACKAGE"
+        echo "Error: Failed to get latest version for '$PACKAGE'"
+        return 1
     fi
 }
 
 elastic_fleet_package_install() {
     PKG=$1
     VERSION=$2
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X POST -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  -d '{"force":true}' "localhost:5601/api/fleet/epm/packages/$PKG/$VERSION"
+    if ! fleet_api "epm/packages/$PKG/$VERSION" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d '{"force":true}'; then
+        return 1
+    fi
 }
 
 elastic_fleet_bulk_package_install() {
     BULK_PKG_LIST=$1
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X POST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d@$1 "localhost:5601/api/fleet/epm/packages/_bulk"
-}
-
-elastic_fleet_package_is_installed() {
-    PACKAGE=$1
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET -H 'kbn-xsrf: true' "localhost:5601/api/fleet/epm/packages/$PACKAGE" | jq -r '.item.status'
-}
-
-elastic_fleet_installed_packages() {
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET -H 'kbn-xsrf: true' -H 'Content-Type: application/json' "localhost:5601/api/fleet/epm/packages/installed?perPage=500"
-}
-
-elastic_fleet_agent_policy_ids() {
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/agent_policies" | jq -r .items[].id
-    if [ $? -ne 0 ]; then
-        echo "Error: Failed to retrieve agent policies."
-        exit 1
+    if ! fleet_api "epm/packages/_bulk" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d@$BULK_PKG_LIST; then
+        return 1
     fi
 }
 
-elastic_fleet_agent_policy_names() {
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/agent_policies" | jq -r .items[].name
-    if [ $? -ne 0 ]; then
+elastic_fleet_installed_packages() {
+    if ! fleet_api "epm/packages/installed?perPage=500"; then
+        return 1
+    fi
+}
+
+elastic_fleet_agent_policy_ids() {
+    if output=$(fleet_api "agent_policies"); then
+        echo "$output" | jq -r .items[].id
+    else
         echo "Error: Failed to retrieve agent policies."
-        exit 1
+        return 1
     fi
 }
 
 elastic_fleet_integration_policy_names() {
     AGENT_POLICY=$1
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/agent_policies/$AGENT_POLICY" | jq -r .item.package_policies[].name
-    if [ $? -ne 0 ]; then
+    if output=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+        echo "$output" | jq -r .item.package_policies[].name
+    else
         echo "Error: Failed to retrieve integrations for '$AGENT_POLICY'."
-        exit 1
+        return 1
     fi
 }
 
 elastic_fleet_integration_policy_package_name() {
     AGENT_POLICY=$1
     INTEGRATION=$2
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/agent_policies/$AGENT_POLICY" | jq -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .package.name'
-    if [ $? -ne 0 ]; then
+    if output=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+        echo "$output" | jq -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .package.name'
+    else
         echo "Error: Failed to retrieve package name for '$INTEGRATION' in '$AGENT_POLICY'."
-        exit 1
+        return 1
     fi
 }
 
@@ -156,32 +175,32 @@ elastic_fleet_integration_policy_package_version() {
     AGENT_POLICY=$1
     INTEGRATION=$2
 
-    if output=$(curl -s -K /opt/so/conf/elasticsearch/curl.config -L -X GET "localhost:5601/api/fleet/agent_policies/$AGENT_POLICY" --fail); then
-        if version=$(jq -e -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .package.version' <<< $output); then
+    if output=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+        if version=$(jq -e -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .package.version' <<< "$output"); then
             echo "$version"
         fi
     else
-        echo "Error: Failed to retrieve agent policy $AGENT_POLICY"
-        exit 1
+        echo "Error: Failed to retrieve integration version for '$INTEGRATION' in policy '$AGENT_POLICY'"
+        return 1
     fi
 }
 
 elastic_fleet_integration_id() {
     AGENT_POLICY=$1
     INTEGRATION=$2
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/agent_policies/$AGENT_POLICY" | jq -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .id'
-    if [ $? -ne 0 ]; then
+    if output=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+        echo "$output" | jq -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .id'
+    else
         echo "Error: Failed to retrieve integration ID for '$INTEGRATION' in '$AGENT_POLICY'."
-        exit 1
+        return 1
     fi
 }
 
 elastic_fleet_integration_policy_dryrun_upgrade() {
     INTEGRATION_ID=$1
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -H "Content-Type: application/json" -H 'kbn-xsrf: true' -L -X POST "localhost:5601/api/fleet/package_policies/upgrade/dryrun" -d "{\"packagePolicyIds\":[\"$INTEGRATION_ID\"]}"
-    if [ $? -ne 0 ]; then
+    if ! fleet_api "package_policies/upgrade/dryrun" -H "Content-Type: application/json" -H 'kbn-xsrf: true' -XPOST -d "{\"packagePolicyIds\":[\"$INTEGRATION_ID\"]}"; then
         echo "Error: Failed to complete dry run for '$INTEGRATION_ID'."
-        exit 1
+        return 1
     fi
 }
 
@@ -190,25 +209,18 @@ elastic_fleet_policy_create() {
     NAME=$1
     DESC=$2
     FLEETSERVER=$3
-        TIMEOUT=$4
+    TIMEOUT=$4
 
     JSON_STRING=$( jq -n \
-                    --arg NAME "$NAME" \
-                    --arg DESC "$DESC" \
-                    --arg TIMEOUT $TIMEOUT \
-                    --arg FLEETSERVER "$FLEETSERVER" \
-                    '{"name": $NAME,"id":$NAME,"description":$DESC,"namespace":"default","monitoring_enabled":["logs"],"inactivity_timeout":$TIMEOUT,"has_fleet_server":$FLEETSERVER}'
-                    )
+        --arg NAME "$NAME" \
+        --arg DESC "$DESC" \
+        --arg TIMEOUT $TIMEOUT \
+        --arg FLEETSERVER "$FLEETSERVER" \
+            '{"name": $NAME,"id":$NAME,"description":$DESC,"namespace":"default","monitoring_enabled":["logs"],"inactivity_timeout":$TIMEOUT,"has_fleet_server":$FLEETSERVER}'
+        )
     # Create Fleet Policy
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/agent_policies" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+    if ! fleet_api "agent_policies" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+        return 1
+    fi
 
 }
-
-elastic_fleet_policy_update() {
-
-    POLICYID=$1
-    JSON_STRING=$2
-
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/agent_policies/$POLICYID" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
-}
-

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-elastic-defend

@@ -8,6 +8,7 @@
 
 . /usr/sbin/so-elastic-fleet-common
 
+ERROR=false
 # Manage Elastic Defend Integration for Initial Endpoints Policy
 for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/elastic-defend/*.json
 do
@@ -15,9 +16,20 @@ do
   elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
   if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Upgrading integration policy\n"
-      elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"
+      if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then
+        echo -e "\nFailed to upgrade integration policy for ${INTEGRATION##*/}"
+        ERROR=true
+        continue
+      fi
   else
     printf "\n\nIntegration does not exist - Creating integration\n"
-    elastic_fleet_integration_create "@$INTEGRATION"
+    if ! elastic_fleet_integration_create "@$INTEGRATION"; then
+        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
+        ERROR=true
+        continue
+    fi
   fi
 done
+if [[ "$ERROR" == "true" ]]; then
+    exit 1
+fi

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-elastic-fleet-server

@@ -25,5 +25,9 @@ for POLICYNAME in $POLICY; do
     .name = $name' /opt/so/conf/elastic-fleet/integrations/fleet-server/fleet-server.json)
 
     # Now update the integration policy using the modified JSON
-    elastic_fleet_integration_update "$INTEGRATION_ID" "$UPDATED_INTEGRATION_POLICY"
+    if ! elastic_fleet_integration_update "$INTEGRATION_ID" "$UPDATED_INTEGRATION_POLICY"; then
+        # exit 1 on failure to update fleet integration policies, let salt handle retries
+        echo "Failed to update $POLICYNAME.."
+        exit 1
+    fi
 done

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-load

@@ -13,11 +13,10 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
   /usr/sbin/so-elastic-fleet-package-upgrade
 
   # Second, update Fleet Server policies
-  /sbin/so-elastic-fleet-integration-policy-elastic-fleet-server
+  /usr/sbin/so-elastic-fleet-integration-policy-elastic-fleet-server
 
   # Third, configure Elastic Defend Integration seperately
   /usr/sbin/so-elastic-fleet-integration-policy-elastic-defend
-
   # Initial Endpoints
   for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/endpoints-initial/*.json
   do
@@ -25,10 +24,18 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
     elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
     if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Updating integration\n"
-      elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"
+      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
+        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
+        RETURN_CODE=1
+        continue
+      fi
     else
       printf "\n\nIntegration does not exist - Creating integration\n"
-      elastic_fleet_integration_create "@$INTEGRATION"
+      if ! elastic_fleet_integration_create "@$INTEGRATION"; then
+        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
+        RETURN_CODE=1
+        continue
+      fi
     fi
   done
 
@@ -39,10 +46,18 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
     elastic_fleet_integration_check "so-grid-nodes_general" "$INTEGRATION"
     if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Updating integration\n"
-      elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"
+      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
+        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
+        RETURN_CODE=1
+        continue
+      fi
     else
       printf "\n\nIntegration does not exist - Creating integration\n"
-      elastic_fleet_integration_create "@$INTEGRATION"
+      if ! elastic_fleet_integration_create "@$INTEGRATION"; then
+        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
+        RETURN_CODE=1
+        continue
+      fi
     fi
   done
   if [[ "$RETURN_CODE" != "1" ]]; then
@@ -56,11 +71,19 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
     elastic_fleet_integration_check "so-grid-nodes_heavy" "$INTEGRATION"
     if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Updating integration\n"
-      elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"
+      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
+        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
+        RETURN_CODE=1
+        continue
+      fi
     else
       printf "\n\nIntegration does not exist - Creating integration\n"
       if [ "$NAME" != "elasticsearch-logs" ]; then
-        elastic_fleet_integration_create "@$INTEGRATION"
+        if ! elastic_fleet_integration_create "@$INTEGRATION"; then
+          echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
+          RETURN_CODE=1
+          continue
+        fi
       fi
     fi
   done
@@ -77,11 +100,19 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
       elastic_fleet_integration_check "$FLEET_POLICY" "$INTEGRATION"
       if [ -n "$INTEGRATION_ID" ]; then
         printf "\n\nIntegration $NAME exists - Updating integration\n"
-        elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"
+        if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
+          echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
+          RETURN_CODE=1
+          continue
+        fi
       else
         printf "\n\nIntegration does not exist - Creating integration\n"
         if [ "$NAME" != "elasticsearch-logs" ]; then
-          elastic_fleet_integration_create "@$INTEGRATION"
+          if ! elastic_fleet_integration_create "@$INTEGRATION"; then
+            echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
+            RETURN_CODE=1
+            continue
+          fi
         fi
       fi
     fi

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-integration-upgrade

@@ -24,12 +24,18 @@ fi
 
 default_packages=({% for pkg in SUPPORTED_PACKAGES %}"{{ pkg }}"{% if not loop.last %} {% endif %}{% endfor %})
 
+ERROR=false
 for AGENT_POLICY in $agent_policies; do
-    integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY")
+    if ! integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY"); then
+        # this script upgrades default integration packages, exit 1 and let salt handle retrying
+        exit 1
+    fi
     for INTEGRATION in $integrations; do
         if ! [[ "$INTEGRATION" == "elastic-defend-endpoints" ]] && ! [[ "$INTEGRATION" == "fleet_server-"* ]]; then
             # Get package name so we know what package to look for when checking the current and latest available version
-            PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION")
+            if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
+                exit 1
+            fi
             {%- if not AUTO_UPGRADE_INTEGRATIONS %}
             if [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
             {%- endif %}
@@ -48,7 +54,9 @@ for AGENT_POLICY in $agent_policies; do
                 fi
 
                 # Get integration ID
-                INTEGRATION_ID=$(elastic_fleet_integration_id "$AGENT_POLICY" "$INTEGRATION")
+                if ! INTEGRATION_ID=$(elastic_fleet_integration_id "$AGENT_POLICY" "$INTEGRATION"); then
+                    exit 1
+                fi
 
                 if [[ "$PACKAGE_VERSION" != "$AVAILABLE_VERSION" ]]; then
                     # Dry run of the upgrade
@@ -56,20 +64,23 @@ for AGENT_POLICY in $agent_policies; do
                     echo "Current $PACKAGE_NAME package version ($PACKAGE_VERSION) is not the same as the latest available package ($AVAILABLE_VERSION)..."
                     echo "Upgrading $INTEGRATION..."
                     echo "Starting dry run..."
-                    DRYRUN_OUTPUT=$(elastic_fleet_integration_policy_dryrun_upgrade "$INTEGRATION_ID")
+                    if ! DRYRUN_OUTPUT=$(elastic_fleet_integration_policy_dryrun_upgrade "$INTEGRATION_ID"); then
+                        exit 1
+                    fi
                     DRYRUN_ERRORS=$(echo "$DRYRUN_OUTPUT" | jq .[].hasErrors)
 
                     # If no errors with dry run, proceed with actual upgrade
                     if [[ "$DRYRUN_ERRORS" == "false" ]]; then
                         echo "No errors detected. Proceeding with upgrade..."
-                        elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"
-                        if [ $? -ne 0 ]; then
+                        if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then
                             echo "Error: Upgrade failed for $PACKAGE_NAME with integration ID '$INTEGRATION_ID'."
-                            exit 1
+                            ERROR=true
+                            continue
                         fi
                     else
                         echo "Errors detected during dry run for $PACKAGE_NAME policy upgrade..."
-                        exit 1
+                        ERROR=true
+                        continue
                     fi
                 fi
             {%- if not AUTO_UPGRADE_INTEGRATIONS %}
@@ -78,4 +89,7 @@ for AGENT_POLICY in $agent_policies; do
         fi
     done
 done
+if [[ "$ERROR" == "true" ]]; then
+    exit 1
+fi
 echo

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-optional-integrations-load

@@ -62,9 +62,17 @@ default_packages=({% for pkg in SUPPORTED_PACKAGES %}"{{ pkg }}"{% if not loop.l
 in_use_integrations=()
 
 for AGENT_POLICY in $agent_policies; do
-    integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY")
+
+    if ! integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY"); then
+        # skip the agent policy if we can't get required info, let salt retry. Integrations loaded by this script are non-default integrations.
+        echo "Skipping $AGENT_POLICY.. "
+        continue
+    fi
     for INTEGRATION in $integrations; do
-        PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION")
+        if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
+            echo  "Not adding $INTEGRATION, couldn't get package name"
+            continue
+        fi
         # non-default integrations that are in-use in any policy
         if ! [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
             in_use_integrations+=("$PACKAGE_NAME")
@@ -160,7 +168,11 @@ if [[ -f $STATE_FILE_SUCCESS  ]]; then
 
             for file in "${pkg_filename}_"*.json; do
                 [ -e "$file" ] || continue
-                elastic_fleet_bulk_package_install $file >> $BULK_INSTALL_OUTPUT
+                if ! elastic_fleet_bulk_package_install $file >> $BULK_INSTALL_OUTPUT; then
+                    # integrations loaded my this script are non-essential and shouldn't cause exit, skip them for now next highstate run can retry
+                    echo "Failed to complete a chunk of bulk package installs -- $file "
+                    continue
+                fi
             done
             # cleanup any temp files for chunked package install
             rm -f ${pkg_filename}_*.json $BULK_INSTALL_PACKAGE_LIST
@@ -168,8 +180,9 @@ if [[ -f $STATE_FILE_SUCCESS  ]]; then
             echo "Elastic integrations don't appear to need installation/updating..."
         fi
         # Write out file for generating index/component/ilm templates
-        latest_installed_package_list=$(elastic_fleet_installed_packages)
-        echo $latest_installed_package_list | jq '[.items[] | {name: .name, es_index_patterns: .dataStreams}]' > $PACKAGE_COMPONENTS
+        if latest_installed_package_list=$(elastic_fleet_installed_packages); then
+            echo $latest_installed_package_list | jq '[.items[] | {name: .name, es_index_patterns: .dataStreams}]' > $PACKAGE_COMPONENTS
+        fi
         if retry 3 1 "so-elasticsearch-query / --fail --output /dev/null"; then
             # Refresh installed component template list
             latest_component_templates_list=$(so-elasticsearch-query _component_template | jq '.component_templates[] | .name' | jq -s '.')

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-outputs-update

@@ -15,8 +15,21 @@ if ! is_manager_node; then
 fi
 
 function update_logstash_outputs() {
-	# Generate updated JSON payload
-    JSON_STRING=$(jq -n --arg UPDATEDLIST $NEW_LIST_JSON '{"name":"grid-logstash","type":"logstash","hosts": $UPDATEDLIST,"is_default":true,"is_default_monitoring":true,"config_yaml":""}')
+    if logstash_policy=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/outputs/so-manager_logstash" --retry 3 --retry-delay 10 --fail 2>/dev/null); then
+        SSL_CONFIG=$(echo "$logstash_policy" | jq -r '.item.ssl')
+        if SECRETS=$(echo "$logstash_policy" | jq -er '.item.secrets' 2>/dev/null); then
+            JSON_STRING=$(jq -n \
+                --arg UPDATEDLIST "$NEW_LIST_JSON" \
+                --argjson SECRETS "$SECRETS" \
+                --argjson SSL_CONFIG "$SSL_CONFIG" \
+                '{"name":"grid-logstash","type":"logstash","hosts": $UPDATEDLIST,"is_default":true,"is_default_monitoring":true,"config_yaml":"","ssl": $SSL_CONFIG,"secrets": $SECRETS}')
+        else
+            JSON_STRING=$(jq -n \
+                --arg UPDATEDLIST "$NEW_LIST_JSON" \
+                --argjson SSL_CONFIG "$SSL_CONFIG" \
+                '{"name":"grid-logstash","type":"logstash","hosts": $UPDATEDLIST,"is_default":true,"is_default_monitoring":true,"config_yaml":"","ssl": $SSL_CONFIG}')
+        fi
+    fi
 
     # Update Logstash Outputs
     curl -K /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/outputs/so-manager_logstash" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING" | jq

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-package-load

@@ -10,8 +10,16 @@
 
 {%- for PACKAGE in SUPPORTED_PACKAGES %}
 echo "Setting up {{ PACKAGE }} package..."
-VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}")
-elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"
+if VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}"); then
+    if ! elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"; then
+        # packages loaded by this script should never fail to install and REQUIRED before an installation of SO can be considered successful
+        echo -e "\nERROR: Failed to install default integration package -- $PACKAGE $VERSION"
+        exit 1
+    fi
+else
+    echo -e "\nERROR: Failed to get version information for integration $PACKAGE"
+    exit 1
+fi
 echo
 {%- endfor %}
 echo

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-package-upgrade

@@ -10,8 +10,15 @@
 
 {%- for PACKAGE in SUPPORTED_PACKAGES %}
 echo "Upgrading {{ PACKAGE }} package..."
-VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}")
-elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"
+if VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
+    if ! elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"; then
+        # exit 1 on failure to upgrade a default package, allow salt to handle retries
+        echo -e "\nERROR: Failed to upgrade $PACKAGE to version: $VERSION"
+        exit 1
+    fi
+else
+    echo -e "\nERROR: Failed to get version information for integration $PACKAGE"
+fi
 echo
 {%- endfor %}
 echo

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-setup

@@ -23,18 +23,17 @@ if [[ "$RETURN_CODE" != "0" ]]; then
     exit 1
 fi
 
-ALIASES=".fleet-servers .fleet-policies-leader .fleet-policies .fleet-agents .fleet-artifacts .fleet-enrollment-api-keys .kibana_ingest"
-for ALIAS in ${ALIASES}
-do
+ALIASES=(.fleet-servers .fleet-policies-leader .fleet-policies .fleet-agents .fleet-artifacts .fleet-enrollment-api-keys .kibana_ingest)
+for ALIAS in "${ALIASES[@]}"; do
     # Get all concrete indices from alias
-    INDXS=$(curl -K /opt/so/conf/kibana/curl.config -s -k -L -H "Content-Type: application/json" "https://localhost:9200/_resolve/index/${ALIAS}"  | jq -r '.aliases[].indices[]')
-
-    # Delete all resolved indices
-    for INDX in ${INDXS}
-    do
+    if INDXS_RAW=$(curl -sK /opt/so/conf/kibana/curl.config -s -k -L -H "Content-Type: application/json" "https://localhost:9200/_resolve/index/${ALIAS}" --fail 2>/dev/null); then
+        INDXS=$(echo "$INDXS_RAW" | jq -r '.aliases[].indices[]')
+        # Delete all resolved indices
+        for INDX in ${INDXS}; do
             status "Deleting $INDX"
             curl -K /opt/so/conf/kibana/curl.config -s -k -L -H "Content-Type: application/json" "https://localhost:9200/${INDX}" -XDELETE
-    done
+        done
+    fi
 done
 
 # Restarting Kibana...
@@ -51,22 +50,61 @@ if [[ "$RETURN_CODE" != "0" ]]; then
 fi
 
 printf "\n### Create ES Token ###\n"
-ESTOKEN=$(curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/service_tokens" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' |  jq -r .value)
+if ESTOKEN_RAW=$(fleet_api "service_tokens" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    ESTOKEN=$(echo "$ESTOKEN_RAW" | jq -r .value)
+else
+    echo -e "\nFailed to create ES token..."
+    exit 1
+fi
 
 ### Create Outputs, Fleet Policy and Fleet URLs ###
 # Create the Manager Elasticsearch Output first and set it as the default output
 printf "\nAdd Manager Elasticsearch Output...\n"
-ESCACRT=$(openssl x509 -in  $INTCA)
-JSON_STRING=$( jq -n \
-                  --arg ESCACRT "$ESCACRT" \
-                  '{"name":"so-manager_elasticsearch","id":"so-manager_elasticsearch","type":"elasticsearch","hosts":["https://{{ GLOBALS.manager_ip }}:9200","https://{{ GLOBALS.manager }}:9200"],"is_default":true,"is_default_monitoring":true,"config_yaml":"","ssl":{"certificate_authorities": [$ESCACRT]}}' )
-curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/outputs" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+ESCACRT=$(openssl x509 -in "$INTCA" -outform DER | sha256sum | cut -d' ' -f1 | tr '[:lower:]' '[:upper:]')
+JSON_STRING=$(jq -n \
+    --arg ESCACRT "$ESCACRT" \
+        '{"name":"so-manager_elasticsearch","id":"so-manager_elasticsearch","type":"elasticsearch","hosts":["https://{{ GLOBALS.manager_ip }}:9200","https://{{ GLOBALS.manager }}:9200"],"is_default":false,"is_default_monitoring":false,"config_yaml":"","ca_trusted_fingerprint": $ESCACRT}')
+
+if ! fleet_api "outputs" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+    echo -e "\nFailed to create so-elasticsearch_manager policy..."
+    exit 1
+fi
 printf "\n\n"
 
+# so-manager_elasticsearch should exist and be disabled. Now update it before checking its the only default policy
+MANAGER_OUTPUT_ENABLED=$(echo "$JSON_STRING" | jq 'del(.id) | .is_default = true | .is_default_monitoring = true')
+if ! curl -sK /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/outputs/so-manager_elasticsearch" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$MANAGER_OUTPUT_ENABLED"; then
+    echo -e "\n failed to update so-manager_elasticsearch"
+    exit 1
+fi
+
+# At this point there should only be two policies. fleet-default-output & so-manager_elasticsearch
+status "Verifying so-manager_elasticsearch policy is configured as the current default"
+
+# Grab the fleet-default-output policy instead of so-manager_elasticsearch, because a weird state can exist where both fleet-default-output & so-elasticsearch_manager can be set as the active default output for logs / metrics. Resulting in logs not ingesting on import/eval nodes
+if DEFAULTPOLICY=$(fleet_api "outputs/fleet-default-output"); then
+    fleet_default=$(echo "$DEFAULTPOLICY" | jq -er '.item.is_default')
+    fleet_default_monitoring=$(echo "$DEFAULTPOLICY" | jq -er '.item.is_default_monitoring')
+#   Check that fleet-default-output isn't configured as a default for anything ( both variables return false )
+    if [[ $fleet_default == "false" ]] && [[ $fleet_default_monitoring == "false" ]]; then
+        echo -e "\nso-manager_elasticsearch is configured as the current default policy..."
+    else
+        echo -e "\nVerification of so-manager_elasticsearch policy failed... The default 'fleet-default-output' output is still active..."
+        exit 1
+    fi
+else
+    # fleet-output-policy is created automatically by fleet when started. Should always exist on any installation type
+    echo -e "\nDefault fleet-default-output policy doesn't exist...\n"
+    exit 1
+fi
+
 # Create the Manager Fleet Server Host Agent Policy
 # This has to be done while the Elasticsearch Output is set to the default Output
 printf "Create Manager Fleet Server Policy...\n"
-elastic_fleet_policy_create "FleetServer_{{ GLOBALS.hostname }}" "Fleet Server - {{ GLOBALS.hostname }}" "false" "120"
+if ! elastic_fleet_policy_create "FleetServer_{{ GLOBALS.hostname }}" "Fleet Server - {{ GLOBALS.hostname }}" "false" "120"; then
+    echo -e "\n Failed to create Manager fleet server policy..."
+    exit 1
+fi
 
 # Modify the default integration policy to update the policy_id with the correct naming
 UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "FleetServer_{{ GLOBALS.hostname }}" --arg name "fleet_server-{{ GLOBALS.hostname }}" '
@@ -74,7 +112,10 @@ UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "FleetServer_{{ GLOBALS.hostname
 .name = $name' /opt/so/conf/elastic-fleet/integrations/fleet-server/fleet-server.json)
 
 # Add the Fleet Server Integration to the new Fleet Policy
-elastic_fleet_integration_create "$UPDATED_INTEGRATION_POLICY"
+if ! elastic_fleet_integration_create "$UPDATED_INTEGRATION_POLICY"; then
+    echo -e "\nFailed to create Fleet server integration for Manager.."
+    exit 1
+fi
 
 # Now we can create the Logstash Output and set it to to be the default Output
 printf "\n\nCreate Logstash Output Config if node is not an Import or Eval install\n"
@@ -86,9 +127,12 @@ JSON_STRING=$( jq -n \
                   --arg LOGSTASHCRT "$LOGSTASHCRT" \
                   --arg LOGSTASHKEY "$LOGSTASHKEY" \
                   --arg LOGSTASHCA "$LOGSTASHCA" \
-                  '{"name":"grid-logstash","is_default":true,"is_default_monitoring":true,"id":"so-manager_logstash","type":"logstash","hosts":["{{ GLOBALS.manager_ip }}:5055", "{{ GLOBALS.manager }}:5055"],"config_yaml":"","ssl":{"certificate": $LOGSTASHCRT,"key": $LOGSTASHKEY,"certificate_authorities":[ $LOGSTASHCA ]},"proxy_id":null}'
+                  '{"name":"grid-logstash","is_default":true,"is_default_monitoring":true,"id":"so-manager_logstash","type":"logstash","hosts":["{{ GLOBALS.manager_ip }}:5055", "{{ GLOBALS.manager }}:5055"],"config_yaml":"","ssl":{"certificate": $LOGSTASHCRT,"certificate_authorities":[ $LOGSTASHCA ]},"secrets":{"ssl":{"key": $LOGSTASHKEY }},"proxy_id":null}'
                   )
-curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/outputs" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+if ! fleet_api "outputs" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+    echo -e "\nFailed to create logstash fleet output"
+    exit 1
+fi
 printf "\n\n"
 {%- endif %}
 
@@ -106,7 +150,10 @@ else
 fi
 
 ## This array replaces whatever URLs are currently configured
-curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/fleet_server_hosts" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d  "$JSON_STRING"
+if ! fleet_api "fleet_server_hosts" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d  "$JSON_STRING"; then
+    echo -e "\nFailed to add manager fleet URL"
+    exit 1
+fi
 printf "\n\n"
 
 ### Create Policies & Associated Integration Configuration ###
@@ -117,13 +164,22 @@ printf "\n\n"
 /usr/sbin/so-elasticsearch-templates-load
 
 # Initial Endpoints Policy
-elastic_fleet_policy_create "endpoints-initial" "Initial Endpoint Policy" "false" "1209600"
+if ! elastic_fleet_policy_create "endpoints-initial" "Initial Endpoint Policy" "false" "1209600"; then
+    echo -e "\nFailed to create endpoints-initial policy..."
+    exit 1
+fi
 
 # Grid Nodes - General Policy
-elastic_fleet_policy_create "so-grid-nodes_general" "SO Grid Nodes - General Purpose" "false" "1209600"
+if ! elastic_fleet_policy_create "so-grid-nodes_general" "SO Grid Nodes - General Purpose" "false" "1209600"; then
+    echo -e "\nFailed to create so-grid-nodes_general policy..."
+    exit 1
+fi
 
 # Grid Nodes - Heavy Node Policy
-elastic_fleet_policy_create "so-grid-nodes_heavy" "SO Grid Nodes - Heavy Node" "false" "1209600"
+if ! elastic_fleet_policy_create "so-grid-nodes_heavy" "SO Grid Nodes - Heavy Node" "false" "1209600"; then
+    echo -e "\nFailed to create so-grid-nodes_heavy policy..."
+    exit 1
+fi
 
 # Load Integrations for default policies
 so-elastic-fleet-integration-policy-load
@@ -135,14 +191,34 @@ JSON_STRING=$( jq -n \
                 '{"name":$NAME,"host":$URL,"is_default":true}'
                 )
 
-curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/agent_download_sources" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+if ! fleet_api "agent_download_sources" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+    echo -e "\nFailed to update Elastic Agent artifact URL"
+    exit 1
+fi
 
 ### Finalization ###
 
 # Query for Enrollment Tokens for default policies
-ENDPOINTSENROLLMENTOKEN=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
-GRIDNODESENROLLMENTOKENGENERAL=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_general")) | .api_key')
-GRIDNODESENROLLMENTOKENHEAVY=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_heavy")) | .api_key')
+if ENDPOINTSENROLLMENTOKEN_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    ENDPOINTSENROLLMENTOKEN=$(echo "$ENDPOINTSENROLLMENTOKEN_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
+else
+    echo -e "\nFailed to query for Endpoints enrollment token"
+    exit 1
+fi
+
+if GRIDNODESENROLLMENTOKENGENERAL_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    GRIDNODESENROLLMENTOKENGENERAL=$(echo "$GRIDNODESENROLLMENTOKENGENERAL_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_general")) | .api_key')
+else
+    echo -e "\nFailed to query for Grid nodes - General enrollment token"
+    exit 1
+fi
+
+if GRIDNODESENROLLMENTOKENHEAVY_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    GRIDNODESENROLLMENTOKENHEAVY=$(echo "$GRIDNODESENROLLMENTOKENHEAVY_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_heavy")) | .api_key')
+else
+    echo -e "\nFailed to query for Grid nodes - Heavy enrollment token"
+    exit 1
+fi
 
 # Store needed data in minion pillar
 pillar_file=/opt/so/saltstack/local/pillar/minions/{{ GLOBALS.minion_id }}.sls

salt/elasticsearch/defaults.yaml

@@ -1,6 +1,6 @@
 elasticsearch:
   enabled: false
-  version: 8.18.6
+  version: 8.18.8
   index_clean: true
   config:
     action:

salt/hypervisor/map.jinja

@@ -13,6 +13,7 @@
 
 {# Import defaults.yaml for model hardware capabilities #}
 {% import_yaml 'hypervisor/defaults.yaml' as DEFAULTS %}
+{% set HYPERVISORMERGED = salt['pillar.get']('hypervisor', default=DEFAULTS.hypervisor, merge=True) %}
 
 {# Get hypervisor nodes from pillar #}
 {% set NODES = salt['pillar.get']('hypervisor:nodes', {}) %}
@@ -30,9 +31,10 @@
     {% set model = '' %}
     {% if grains %}
       {% set minion_id = grains.keys() | first %}
-      {% set model = grains[minion_id].get('sosmodel', '') %}
+      {% set model = grains[minion_id].get('sosmodel', grains[minion_id].get('byodmodel', '')) %}
     {% endif %}
-    {% set model_config = DEFAULTS.hypervisor.model.get(model, {}) %}
+
+    {% set model_config = HYPERVISORMERGED.model.get(model, {}) %}
     
     {# Get VM list from VMs file #}
     {% set vms = {} %}

salt/hypervisor/tools/sbin/so-nvme-raid1.sh

@@ -30,7 +30,9 @@
 #
 # WARNING: This script will DESTROY all data on the target drives!
 #
-# USAGE: sudo ./so-nvme-raid1.sh
+# USAGE: 
+#   sudo ./so-nvme-raid1.sh              # Normal operation
+#   sudo ./so-nvme-raid1.sh --force-cleanup  # Force cleanup of existing RAID
 #
 #################################################################
 
@@ -41,6 +43,19 @@ set -e
 RAID_ARRAY_NAME="md0"
 RAID_DEVICE="/dev/${RAID_ARRAY_NAME}"
 MOUNT_POINT="/nsm"
+FORCE_CLEANUP=false
+
+# Parse command line arguments
+for arg in "$@"; do
+    case $arg in
+        --force-cleanup)
+            FORCE_CLEANUP=true
+            shift
+            ;;
+        *)
+            ;;
+    esac
+done
 
 # Function to log messages
 log() {
@@ -55,6 +70,91 @@ check_root() {
     fi
 }
 
+# Function to force cleanup all RAID components
+force_cleanup_raid() {
+    log "=== FORCE CLEANUP MODE ==="
+    log "This will destroy all RAID configurations and data on target drives!"
+    
+    # Stop all MD arrays
+    log "Stopping all MD arrays"
+    mdadm --stop --scan 2>/dev/null || true
+    
+    # Wait for arrays to stop
+    sleep 2
+    
+    # Remove any running md devices
+    for md in /dev/md*; do
+        if [ -b "$md" ]; then
+            log "Stopping $md"
+            mdadm --stop "$md" 2>/dev/null || true
+        fi
+    done
+    
+    # Force cleanup both NVMe drives
+    for device in "/dev/nvme0n1" "/dev/nvme1n1"; do
+        log "Force cleaning $device"
+        
+        # Kill any processes using the device
+        fuser -k "${device}"* 2>/dev/null || true
+        
+        # Unmount any mounted partitions
+        for part in "${device}"*; do
+            if [ -b "$part" ]; then
+                umount -f "$part" 2>/dev/null || true
+            fi
+        done
+        
+        # Force zero RAID superblocks on partitions
+        for part in "${device}"p*; do
+            if [ -b "$part" ]; then
+                log "Zeroing RAID superblock on $part"
+                mdadm --zero-superblock --force "$part" 2>/dev/null || true
+            fi
+        done
+        
+        # Zero superblock on the device itself
+        log "Zeroing RAID superblock on $device"
+        mdadm --zero-superblock --force "$device" 2>/dev/null || true
+        
+        # Remove LVM physical volumes
+        pvremove -ff -y "$device" 2>/dev/null || true
+        
+        # Wipe all filesystem and partition signatures
+        log "Wiping all signatures from $device"
+        wipefs -af "$device" 2>/dev/null || true
+        
+        # Overwrite the beginning of the drive (partition table area)
+        log "Clearing partition table on $device"
+        dd if=/dev/zero of="$device" bs=1M count=10 2>/dev/null || true
+        
+        # Clear the end of the drive (backup partition table area)
+        local device_size=$(blockdev --getsz "$device" 2>/dev/null || echo "0")
+        if [ "$device_size" -gt 0 ]; then
+            dd if=/dev/zero of="$device" bs=512 seek=$(( device_size - 2048 )) count=2048 2>/dev/null || true
+        fi
+        
+        # Force kernel to re-read partition table
+        blockdev --rereadpt "$device" 2>/dev/null || true
+        partprobe -s "$device" 2>/dev/null || true
+    done
+    
+    # Clear mdadm configuration
+    log "Clearing mdadm configuration"
+    echo "DEVICE partitions" > /etc/mdadm.conf
+    
+    # Remove any fstab entries for the RAID device or mount point
+    log "Cleaning fstab entries"
+    sed -i "\|${RAID_DEVICE}|d" /etc/fstab
+    sed -i "\|${MOUNT_POINT}|d" /etc/fstab
+    
+    # Wait for system to settle
+    udevadm settle
+    sleep 5
+    
+    log "Force cleanup complete!"
+    log "Proceeding with RAID setup..."
+}
+
 # Function to find MD arrays using specific devices
 find_md_arrays_using_devices() {
     local target_devices=("$@")
@@ -205,10 +305,15 @@ check_existing_raid() {
             fi
             
             log "Error: $device appears to be part of an existing RAID array"
-            log "To reuse this device, you must first:"
-            log "1. Unmount any filesystems"
-            log "2. Stop the RAID array: mdadm --stop $array_name"
-            log "3. Zero the superblock: mdadm --zero-superblock ${device}p1"
+            log "Old RAID metadata detected but array is not running."
+            log ""
+            log "To fix this, run the script with --force-cleanup:"
+            log "  sudo $0 --force-cleanup"
+            log ""
+            log "Or manually clean up with:"
+            log "1. Stop any arrays: mdadm --stop --scan"
+            log "2. Zero superblocks: mdadm --zero-superblock --force ${device}p1"
+            log "3. Wipe signatures: wipefs -af $device"
             exit 1
         fi
     done
@@ -238,7 +343,7 @@ ensure_devices_free() {
     done
     
     # Clear MD superblock
-    mdadm --zero-superblock "${device}"* 2>/dev/null || true
+    mdadm --zero-superblock --force "${device}"* 2>/dev/null || true
     
     # Remove LVM PV if exists
     pvremove -ff -y "$device" 2>/dev/null || true
@@ -263,6 +368,11 @@ main() {
     # Check if running as root
     check_root
     
+    # If force cleanup flag is set, do aggressive cleanup first
+    if [ "$FORCE_CLEANUP" = true ]; then
+        force_cleanup_raid
+    fi
+    
     # Check for existing RAID setup
     check_existing_raid
     

salt/kibana/defaults.yaml

@@ -22,7 +22,7 @@ kibana:
           - default
           - file
     migrations:
-      discardCorruptObjects: "8.18.6"
+      discardCorruptObjects: "8.18.8"
     telemetry:
       enabled: False
     security:

salt/kratos/enabled.sls

@@ -54,6 +54,9 @@ so-kratos:
       - file: kratosconfig
       - file: kratoslogdir
       - file: kratosdir
+    - retry:
+        attempts: 10
+        interval: 10
 
 delete_so-kratos_so-status.disabled:
   file.uncomment:

salt/libvirt/bridge.sls

@@ -4,6 +4,9 @@
 # Elastic License 2.0.
 
 # We do not import GLOBALS in this state because it is called during setup
+include:
+  - salt.minion.service_file
+  - salt.mine_functions
 
 down_original_mgmt_interface:
   cmd.run:
@@ -28,29 +31,14 @@ wait_for_br0_ip:
     - timeout: 95
     - onchanges:
       - cmd: down_original_mgmt_interface
-
-{% if grains.role == 'so-hypervisor' %}
-
-update_mine_functions:
-  file.managed:
-    - name: /etc/salt/minion.d/mine_functions.conf
-    - contents: |
-        mine_interval: 25
-        mine_functions:
-          network.ip_addrs:
-            - interface: br0
-        {%- if role in ['so-eval','so-import','so-manager','so-managerhype','so-managersearch','so-standalone'] %}
-          x509.get_pem_entries:
-            - glob_path: '/etc/pki/ca.crt'
-        {% endif %}
-    - onchanges:
-      - cmd: wait_for_br0_ip
+    - onchanges_in:
+      - file: salt_minion_service_unit_file
+      - file: mine_functions
 
 restart_salt_minion_service:
   service.running:
     - name: salt-minion
     - enable: True
     - listen:
-      - file: update_mine_functions
-
-{% endif %}
+      - file: salt_minion_service_unit_file
+      - file: mine_functions

salt/manager/tools/sbin/so-user

@@ -387,7 +387,7 @@ function syncElastic() {
     if [[ -z "$SKIP_STATE_APPLY" ]]; then
       echo "Elastic state will be re-applied to affected minions. This will run in the background and may take several minutes to complete."
       echo "Applying elastic state to elastic minions at $(date)" >> /opt/so/log/soc/sync.log 2>&1
-      salt --async -C 'G@role:so-standalone or G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managersearch or G@role:so-searchnode or G@role:so-heavynode' state.apply elasticsearch queue=True >> /opt/so/log/soc/sync.log 2>&1
+      salt --async -C 'I@elasticsearch:enabled:true' state.apply elasticsearch queue=True >> /opt/so/log/soc/sync.log 2>&1
     fi
   else
     echo "Newly generated users/roles files are incomplete; aborting."

salt/manager/tools/sbin/soup

@@ -169,6 +169,8 @@ airgap_update_dockers() {
       tar xf "$AGDOCKER/registry.tar" -C /nsm/docker-registry/docker
       echo "Add Registry back"
       docker load -i "$AGDOCKER/registry_image.tar"
+      echo "Restart registry container"
+      salt-call state.apply registry queue=True
     fi
   fi
 }
@@ -420,6 +422,7 @@ preupgrade_changes() {
     [[ "$INSTALLEDVERSION" == 2.4.150 ]] && up_to_2.4.160
     [[ "$INSTALLEDVERSION" == 2.4.160 ]] && up_to_2.4.170
     [[ "$INSTALLEDVERSION" == 2.4.170 ]] && up_to_2.4.180
+    [[ "$INSTALLEDVERSION" == 2.4.180 ]] && up_to_2.4.190
     true
 }
 
@@ -450,6 +453,7 @@ postupgrade_changes() {
     [[ "$POSTVERSION"  == 2.4.150 ]] && post_to_2.4.160
     [[ "$POSTVERSION"  == 2.4.160 ]] && post_to_2.4.170
     [[ "$POSTVERSION"  == 2.4.170 ]] && post_to_2.4.180
+    [[ "$POSTVERSION"  == 2.4.180 ]] && post_to_2.4.190
     true
 }
 
@@ -599,15 +603,34 @@ post_to_2.4.170() {
 }
 
 post_to_2.4.180() {
-  echo "Regenerating Elastic Agent Installers"
-  /sbin/so-elastic-agent-gen-installers
-
   # Force update to Kafka output policy
   /usr/sbin/so-kafka-fleet-output-policy --force
 
   POSTVERSION=2.4.180
 }
 
+post_to_2.4.190() {
+    echo "Regenerating Elastic Agent Installers"
+    /sbin/so-elastic-agent-gen-installers
+
+    # Only need to update import / eval nodes
+    if [[ "$MINION_ROLE" == "import" ]] || [[ "$MINION_ROLE" == "eval" ]]; then
+        update_import_fleet_output
+    fi
+
+    # Check if expected default policy is logstash (global.pipeline is REDIS or "")
+    pipeline=$(lookup_pillar "pipeline" "global")
+    if [[ -z "$pipeline" ]] || [[ "$pipeline" == "REDIS" ]]; then
+        # Check if this grid is currently affected by corrupt fleet output policy
+        if elastic-agent status | grep "config: key file not configured" > /dev/null 2>&1; then
+            echo "Elastic Agent shows an ssl error connecting to logstash output. Updating output policy..."
+            update_default_logstash_output
+        fi
+    fi
+
+  POSTVERSION=2.4.190
+}
+
 repo_sync() {
   echo "Sync the local repo."
   su socore -c '/usr/sbin/so-repo-sync' || fail "Unable to complete so-repo-sync."
@@ -864,10 +887,15 @@ up_to_2.4.170() {
 }
 
 up_to_2.4.180() {
+  echo "Nothing to do for 2.4.180"
+  INSTALLEDVERSION=2.4.180
+}
+
+up_to_2.4.190() {
   # Elastic Update for this release, so download Elastic Agent files
   determine_elastic_agent_upgrade
 
-  INSTALLEDVERSION=2.4.180
+  INSTALLEDVERSION=2.4.190
 }
 
 add_hydra_pillars() {
@@ -1143,6 +1171,44 @@ update_elasticsearch_index_settings() {
   done
 }
 
+update_import_fleet_output() {
+    if output=$(curl -sK /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/outputs/so-manager_elasticsearch" --retry 3 --fail 2>/dev/null); then
+        # Update the current config of so-manager_elasticsearch output policy in place (leaving any customizations like having changed the preset value from 'balanced' to 'performance')
+        CAFINGERPRINT=$(openssl x509 -in /etc/pki/tls/certs/intca.crt -outform DER | sha256sum | cut -d' ' -f1 | tr '[:lower:]' '[:upper:]')
+        updated_policy=$(jq --arg CAFINGERPRINT "$CAFINGERPRINT" '.item | (del(.id) | .ca_trusted_fingerprint = $CAFINGERPRINT)' <<< "$output")
+        if curl -sK /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/outputs/so-manager_elasticsearch" -XPUT -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$updated_policy" --retry 3 --fail 2>/dev/null; then
+            echo "Successfully updated so-manager_elasticsearch fleet output policy"
+        else
+            fail "Failed to update so-manager_elasticsearch fleet output policy"
+        fi
+    fi
+}
+
+update_default_logstash_output() {
+    echo "Updating fleet logstash output policy grid-logstash"
+    if logstash_policy=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/outputs/so-manager_logstash" --retry 3 --retry-delay 10 --fail 2>/dev/null); then
+        # Keep already configured hosts for this update, subsequent host updates come from so-elastic-fleet-outputs-update
+        HOSTS=$(echo "$logstash_policy" | jq -r '.item.hosts')
+        DEFAULT_ENABLED=$(echo "$logstash_policy" | jq -r '.item.is_default')
+        DEFAULT_MONITORING_ENABLED=$(echo "$logstash_policy" | jq -r '.item.is_default_monitoring')
+        LOGSTASHKEY=$(openssl rsa -in  /etc/pki/elasticfleet-logstash.key)
+        LOGSTASHCRT=$(openssl x509 -in /etc/pki/elasticfleet-logstash.crt)
+        LOGSTASHCA=$(openssl x509 -in  /etc/pki/tls/certs/intca.crt)
+        JSON_STRING=$(jq -n \
+            --argjson HOSTS "$HOSTS" \
+            --arg DEFAULT_ENABLED "$DEFAULT_ENABLED" \
+            --arg DEFAULT_MONITORING_ENABLED "$DEFAULT_MONITORING_ENABLED" \
+            --arg LOGSTASHKEY "$LOGSTASHKEY" \
+            --arg LOGSTASHCRT "$LOGSTASHCRT" \
+            --arg LOGSTASHCA "$LOGSTASHCA" \
+            '{"name":"grid-logstash","type":"logstash","hosts": $HOSTS,"is_default": $DEFAULT_ENABLED,"is_default_monitoring": $DEFAULT_MONITORING_ENABLED,"config_yaml":"","ssl":{"certificate": $LOGSTASHCRT,"certificate_authorities":[ $LOGSTASHCA ]},"secrets":{"ssl":{"key": $LOGSTASHKEY }}}')
+    fi
+
+    if curl -K /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/outputs/so-manager_logstash" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING" --retry 3 --retry-delay 10 --fail; then
+        echo "Successfully updated grid-logstash fleet output policy"
+    fi
+}
+
 update_salt_mine() {
     echo "Populating the mine with mine_functions for each host."
     set +e
@@ -1359,6 +1425,7 @@ main() {
   fi
 
   set_minionid
+  MINION_ROLE=$(lookup_role)
   echo "Found that Security Onion $INSTALLEDVERSION is currently installed."
   echo ""
   if [[ $is_airgap -eq 0 ]]; then
@@ -1401,7 +1468,7 @@ main() {
   if [ "$is_hotfix" == "true" ]; then
     echo "Applying $HOTFIXVERSION hotfix"
     # since we don't run the backup.config_backup state on import we wont snapshot previous version states and pillars
-    if [[ ! "$MINIONID" =~ "_import" ]]; then
+    if [[ ! "$MINION_ROLE" == "import" ]]; then
       backup_old_states_pillars
     fi
     copy_new_files
@@ -1464,7 +1531,7 @@ main() {
     fi
 
     # since we don't run the backup.config_backup state on import we wont snapshot previous version states and pillars
-    if [[ ! "$MINIONID" =~ "_import" ]]; then
+    if [[ ! "$MINION_ROLE" == "import" ]]; then
       echo ""
       echo "Creating snapshots of default and local Salt states and pillars and saving to /nsm/backup/"
       backup_old_states_pillars

salt/salt/engines/master/virtual_node_manager.py

@@ -161,6 +161,7 @@ DEFAULT_BASE_PATH = '/opt/so/saltstack/local/salt/hypervisor/hosts'
 VALID_ROLES = ['sensor', 'searchnode', 'idh', 'receiver', 'heavynode', 'fleet']
 LICENSE_PATH = '/opt/so/saltstack/local/pillar/soc/license.sls'
 DEFAULTS_PATH = '/opt/so/saltstack/default/salt/hypervisor/defaults.yaml'
+HYPERVISOR_PILLAR_PATH = '/opt/so/saltstack/local/pillar/hypervisor/soc_hypervisor.sls'
 # Define the retention period for destroyed VMs (in hours)
 DESTROYED_VM_RETENTION_HOURS = 48
 
@@ -271,7 +272,7 @@ def parse_hardware_indices(hw_value: Any) -> List[int]:
     return indices
 
 def get_hypervisor_model(hypervisor: str) -> str:
-    """Get sosmodel from hypervisor grains."""
+    """Get sosmodel or byodmodel from hypervisor grains."""
     try:
         # Get cached grains using Salt runner
         grains = runner.cmd(
@@ -283,9 +284,9 @@ def get_hypervisor_model(hypervisor: str) -> str:
             
         # Get the first minion ID that matches our hypervisor
         minion_id = next(iter(grains.keys()))
-        model = grains[minion_id].get('sosmodel')
+        model = grains[minion_id].get('sosmodel', grains[minion_id].get('byodmodel', ''))
         if not model:
-            raise ValueError(f"No sosmodel grain found for hypervisor {hypervisor}")
+            raise ValueError(f"No sosmodel or byodmodel grain found for hypervisor {hypervisor}")
             
         log.debug("Found model %s for hypervisor %s", model, hypervisor)
         return model
@@ -295,16 +296,48 @@ def get_hypervisor_model(hypervisor: str) -> str:
         raise
 
 def load_hardware_defaults(model: str) -> dict:
-    """Load hardware configuration from defaults.yaml."""
+    """Load hardware configuration from defaults.yaml and optionally override with pillar configuration."""
+    config = None
+    config_source = None
+    
     try:
+        # First, try to load from defaults.yaml
+        log.debug("Checking for model %s in %s", model, DEFAULTS_PATH)
         defaults = read_yaml_file(DEFAULTS_PATH)
         if not defaults or 'hypervisor' not in defaults:
             raise ValueError("Invalid defaults.yaml structure")
         if 'model' not in defaults['hypervisor']:
             raise ValueError("No model configurations found in defaults.yaml")
-        if model not in defaults['hypervisor']['model']:
-            raise ValueError(f"Model {model} not found in defaults.yaml")
-        return defaults['hypervisor']['model'][model]
+        
+        # Check if model exists in defaults
+        if model in defaults['hypervisor']['model']:
+            config = defaults['hypervisor']['model'][model]
+            config_source = DEFAULTS_PATH
+            log.debug("Found model %s in %s", model, DEFAULTS_PATH)
+        
+        # Then, try to load from pillar file (if it exists)
+        try:
+            log.debug("Checking for model %s in %s", model, HYPERVISOR_PILLAR_PATH)
+            pillar_config = read_yaml_file(HYPERVISOR_PILLAR_PATH)
+            if pillar_config and 'hypervisor' in pillar_config:
+                if 'model' in pillar_config['hypervisor']:
+                    if model in pillar_config['hypervisor']['model']:
+                        # Override with pillar configuration
+                        config = pillar_config['hypervisor']['model'][model]
+                        config_source = HYPERVISOR_PILLAR_PATH
+                        log.debug("Found model %s in %s (overriding defaults)", model, HYPERVISOR_PILLAR_PATH)
+        except FileNotFoundError:
+            log.debug("Pillar file %s not found, using defaults only", HYPERVISOR_PILLAR_PATH)
+        except Exception as e:
+            log.warning("Failed to read pillar file %s: %s (using defaults)", HYPERVISOR_PILLAR_PATH, str(e))
+        
+        # If model was not found in either file, raise an error
+        if config is None:
+            raise ValueError(f"Model {model} not found in {DEFAULTS_PATH} or {HYPERVISOR_PILLAR_PATH}")
+        
+        log.debug("Using hardware configuration for model %s from %s", model, config_source)
+        return config
+        
     except Exception as e:
         log.error("Failed to load hardware defaults: %s", str(e))
         raise

salt/salt/map.jinja

@@ -4,7 +4,10 @@
    Elastic License 2.0. #}
 
 {% set role = salt['grains.get']('role', '') %}
-{% if role in ['so-hypervisor','so-managerhype'] and salt['network.ip_addrs']('br0')|length > 0 %}
+{# We are using usebr0 mostly for setup of the so-managerhype node and controlling when we use br0 vs the physical interface #}
+{% set usebr0 = salt['pillar.get']('usebr0', True) %}
+
+{% if role in ['so-hypervisor','so-managerhype'] and usebr0 %}
 {%   set interface = 'br0' %}
 {% else %}
 {%   set interface = pillar.host.mainint %}

salt/salt/mine_functions.sls

@@ -3,7 +3,7 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-# this state was seperated from salt.minion state since it is called during setup
+# this state was separated from salt.minion state since it is called during setup
 # GLOBALS are imported in the salt.minion state and that is not available at that point in setup
 # this state is included in the salt.minion state
 

salt/salt/minion/init.sls

@@ -1,18 +1,22 @@
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
 {% from 'vars/globals.map.jinja' import GLOBALS %}
 {% from 'salt/map.jinja' import UPGRADECOMMAND with context %}
 {% from 'salt/map.jinja' import SALTVERSION %}
 {% from 'salt/map.jinja' import INSTALLEDSALTVERSION %}
 {% from 'salt/map.jinja' import SALTPACKAGES %}
-{% from 'salt/map.jinja' import SYSTEMD_UNIT_FILE %}
 {% import_yaml 'salt/minion.defaults.yaml' as SALTMINION %}
 
 include:
   - salt.python_modules
   - salt.patch.x509_v2
   - salt
-  - systemd.reload
   - repo.client
   - salt.mine_functions
+  - salt.minion.service_file
 {% if GLOBALS.role in GLOBALS.manager_roles %}
   - ca
 {% endif %}
@@ -94,17 +98,6 @@ enable_startup_states:
     - regex: '^startup_states: highstate$'
     - unless: pgrep so-setup
 
-# prior to 2.4.30 this managed file would restart the salt-minion service when updated
-# since this file is currently only adding a delay service start
-# it is not required to restart the service
-salt_minion_service_unit_file:
-  file.managed:
-    - name: {{ SYSTEMD_UNIT_FILE }}
-    - source: salt://salt/service/salt-minion.service.jinja
-    - template: jinja
-    - onchanges_in:
-      - module: systemd_reload
-
 {% endif %}
 
 # this has to be outside the if statement above since there are <requisite>_in calls to this state

salt/salt/minion/service_file.sls

@@ -0,0 +1,26 @@
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+{% from 'salt/map.jinja' import SALTVERSION %}
+{% from 'salt/map.jinja' import INSTALLEDSALTVERSION %}
+{% from 'salt/map.jinja' import SYSTEMD_UNIT_FILE %}
+
+include:
+  - systemd.reload
+
+{% if INSTALLEDSALTVERSION|string == SALTVERSION|string %}
+
+# prior to 2.4.30 this managed file would restart the salt-minion service when updated
+# since this file is currently only adding a delay service start
+# it is not required to restart the service
+salt_minion_service_unit_file:
+  file.managed:
+    - name: {{ SYSTEMD_UNIT_FILE }}
+    - source: salt://salt/service/salt-minion.service.jinja
+    - template: jinja
+    - onchanges_in:
+      - module: systemd_reload
+
+{% endif %}

salt/soc/defaults.yaml

@@ -1493,6 +1493,7 @@ soc:
                 folder: securityonion-normalized
         assistant:
           apiUrl: https://onionai.securityonion.net
+          healthTimeoutSeconds: 3
         salt:
           queueDir: /opt/sensoroni/queue
           timeoutMs: 45000
@@ -2545,7 +2546,7 @@ soc:
               level: 'high'  # info | low | medium | high | critical
         assistant:
           enabled: false
-          investigationPrompt: Investigate Alert ID {socid}
+          investigationPrompt: Investigate Alert ID {socId}
           contextLimitSmall: 200000
           contextLimitLarge: 1000000
           thresholdColorRatioLow: 0.5

salt/soc/soc_soc.yaml

@@ -585,6 +585,10 @@ soc:
             description: The URL of the AI gateway.
             advanced: True
             global: True
+          healthTimeoutSeconds:
+            description: Timeout in seconds for the Onion AI health check.
+            global: True
+            advanced: True
       client:
         assistant:
           enabled:
@@ -615,6 +619,7 @@ soc:
             advanced: True 
           lowBalanceColorAlert:
             description: Onion AI credit amount at which balance turns red.
+            global: True
             advanced: True
         apiTimeoutMs:
           description: Duration (in milliseconds) to wait for a response from the SOC server API before giving up and showing an error on the SOC UI.

setup/so-functions

@@ -541,8 +541,15 @@ configure_minion() {
 		"log_file: /opt/so/log/salt/minion"\
 		"#startup_states: highstate" >> "$minion_config"
 
-	info "Running: salt-call state.apply salt.mine_functions --local --file-root=../salt/ -l info pillar='{"host": {"mainint": "$MNIC"}}'"
-	salt-call state.apply salt.mine_functions --local --file-root=../salt/ -l info pillar="{'host': {'mainint': $MNIC}}"
+	# At the time the so-managerhype node does not yet have the bridge configured.
+	# The so-hypervisor node doesn't either, but it doesn't cause issues here.
+	local usebr0=false
+	if [ "$minion_type" == 'hypervisor' ]; then
+    	usebr0=true
+	fi
+	local pillar_json="{\"host\": {\"mainint\": \"$MNIC\"}, \"usebr0\": $usebr0}"
+	info "Running: salt-call state.apply salt.mine_functions --local --file-root=../salt/ -l info pillar='$pillar_json'"
+	salt-call state.apply salt.mine_functions --local --file-root=../salt/ -l info pillar="$pillar_json"
 
 	{
 		logCmd "systemctl enable salt-minion";
@@ -1194,10 +1201,7 @@ hypervisor_local_states() {
         info "Running libvirt states for hypervisor"
         logCmd "salt-call state.apply libvirt.64962 --local --file-root=../salt/ -l info queue=True"
         info "Setting up bridge for $MNIC"
-		    salt-call state.apply libvirt.bridge --local --file-root=../salt/ -l info pillar='{"host": {"mainint": "'$MNIC'"}}' queue=True
-		    if [ $is_managerhype ]; then
-			    logCmd "salt-call state.apply salt.minion queue=True"
-		    fi
+		salt-call state.apply libvirt.bridge --local --file-root=../salt/ -l info pillar='{"host": {"mainint": "'$MNIC'"}}' queue=True
     fi
 }
 

setup/so-setup

@@ -762,6 +762,7 @@ if ! [[ -f $install_opt_file ]]; then
 		fi
 		logCmd "salt-call state.apply common.packages"
 		logCmd "salt-call state.apply common"
+		hypervisor_local_states
 		# this will apply the salt.minion state first since salt.master includes salt.minion
 		logCmd "salt-call state.apply salt.master"
 		# wait here until we get a response from the salt-master since it may have just restarted
@@ -826,7 +827,6 @@ if ! [[ -f $install_opt_file ]]; then
 		checkin_at_boot
 		set_initial_firewall_access
 		logCmd "salt-call schedule.enable -linfo --local"
-		hypervisor_local_states
 		verify_setup
 	else
 		touch /root/accept_changes