Merge pull request #16274 from Security-Onion-Solutions/fix/auto-apply-state-queue

Fix/auto apply state queue

salt/_beacons/postgres_pillar_beacon.py

@@ -131,6 +131,8 @@ def beacon(config):  # noqa: C901
             'setting_id': setting_id,
             'node_id': node_id,
         })
+        log.info('postgres_pillar_beacon: audit_settings id=%d setting_id=%s node_id=%s',
+                 row_id, setting_id, node_id)
         if row_id > max_id:
             max_id = row_id
 

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

@@ -177,6 +177,7 @@ if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Unexpected authorization header" # expected WARN log lines indicating invalid auth header
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Missing ory_kratos_session cookie" # expected WARN log lines indicating invalid auth header
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Static assets preprocessor only supports GET and HEAD requests" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|respondError"                 # respondError is a function name, output via http middleware as standard request logging
 fi
 
 if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
@@ -240,7 +241,7 @@ if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|marked for removal"           # docker container getting recycled
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|tcp 127.0.0.1:6791: bind: address already in use" # so-elastic-fleet agent restarting. Seen starting w/ 8.18.8 https://github.com/elastic/kibana/issues/201459
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|TransformTask\] \[logs-.*user so_kibana lacks the required permissions" # Known issue with integrations starting transform jobs that are explicitly not allowed to start as a system user
-    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|manifest unknown"             # appears in so-dockerregistry log for so-tcpreplay following docker upgrade to 29.2.1-1
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|manifest unknown"             # so-dockerregistry logs a tag lookup miss during image copy; not tied to one docker version
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Could not index event to Elasticsearch.*\"version\" => \"9.0.8\"" # Expected during Elastic upgrade temporarily, as policies referencing older pipelines are updated
 fi
 

salt/docker/init.sls

@@ -18,10 +18,10 @@ dockergroup:
 dockerheldpackages:
   pkg.installed:
     - pkgs:
-      - containerd.io: 2.2.1-1.el9
+      - containerd.io: 2.3.6-1.el9
-      - docker-ce: 3:29.2.1-1.el9
+      - docker-ce: 3:29.8.1-1.el9
-      - docker-ce-cli: 1:29.2.1-1.el9
+      - docker-ce-cli: 1:29.8.1-1.el9
-      - docker-ce-rootless-extras: 29.2.1-1.el9
+      - docker-ce-rootless-extras: 29.8.1-1.el9
     - hold: True
     - update_holds: True
 

salt/elastalert/config.sls

@@ -21,6 +21,7 @@ elastalert:
     - gid: 933
     - home: /opt/so/conf/elastalert
     - createhome: False
+    - shell: /sbin/nologin
 
 elastalogdir:
   file.directory:

salt/elastic-fleet-package-registry/config.sls

@@ -19,6 +19,7 @@ elastic-agent-pr:
     - gid: 948
     - home: /opt/so/conf/elastic-fleet-pr
     - createhome: False
+    - shell: /sbin/nologin
 
 {% else %}
 

salt/elasticagent/config.sls

@@ -20,6 +20,7 @@ elastic-agent:
     - gid: 949
     - home: /opt/so/conf/elastic-agent
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticagentconfdir:
   file.directory:

salt/elasticfleet/config.sls

@@ -26,6 +26,7 @@ elastic-fleet:
     - gid: 947
     - home: /opt/so/conf/elastic-fleet
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticfleet_sbin:
   file.recurse:

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

@@ -29,7 +29,7 @@
               "\\.gz$"
             ],
             "include_files": [],
-            "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-2.22.3\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-3.9.0\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-2.22.3\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-2.22.3\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-3.9.0\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- add_fields:\n    target: event\n    fields:\n      dataset: windows.forwarded\n      module: windows\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: import.evtx\n- if:\n    equals:\n      winlog.channel: 'Security'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.security\n          module: system\n- if:\n    equals:\n      winlog.channel: 'Windows PowerShell'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell\n          module: windows\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n          module: system\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n          module: system\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n- add_fields:\n    target: data_stream\n    fields:\n        type: logs\n        dataset: import",
             "tags": [
               "import"
             ],

salt/elasticfleet/integration-defaults.map.jinja

@@ -30,17 +30,14 @@
     'azure_metrics.monitor': 'azure.monitor',
     'azure_metrics.storage_account': 'azure.storage_account',
     'azure_openai.metrics': 'azure.open_ai',
-    'beat.state': 'beats.stack_monitoring.state',
-    'beat.stats': 'beats.stack_monitoring.stats',
-    'enterprisesearch.health': 'enterprisesearch.stack_monitoring.health',
-    'enterprisesearch.stats': 'enterprisesearch.stack_monitoring.stats',
     'kibana.cluster_actions': 'kibana.stack_monitoring.cluster_actions',
     'kibana.cluster_rules': 'kibana.stack_monitoring.cluster_rules',
     'kibana.node_actions': 'kibana.stack_monitoring.node_actions',
     'kibana.node_rules': 'kibana.stack_monitoring.node_rules',
     'kibana.stats': 'kibana.stack_monitoring.stats',
     'kibana.status': 'kibana.stack_monitoring.status',
-    'logstash.node_cel': 'logstash.stack_monitoring.node',
+    'logstash.node': 'logstash.stack_monitoring.node',
+    'logstash.node_cel': 'logstash.node',
     'logstash.node_stats': 'logstash.stack_monitoring.node_stats',
     'synthetics.browser': 'synthetics-browser',
     'synthetics.browser_network': 'synthetics-browser.network',

salt/elasticsearch/config.sls

@@ -32,6 +32,7 @@ elasticsearch:
     - gid: 930
     - home: /opt/so/conf/elasticsearch
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticsearch_sbin:
   file.recurse:

salt/elasticsearch/defaults.yaml

@@ -3309,6 +3309,7 @@ elasticsearch:
         composed_of:
         - event-mappings
         - logs-system.security@package
+        - so-fleet_system.security_caseless-1
         - logs-system.security@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4175,6 +4176,7 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.forwarded@package
+        - so-fleet_process_caseless-1
         - logs-windows.forwarded@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4224,6 +4226,7 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.powershell@package
+        - so-fleet_process_caseless-1
         - logs-windows.powershell@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4273,6 +4276,7 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.powershell_operational@package
+        - so-fleet_process_caseless-1
         - logs-windows.powershell_operational@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -4322,6 +4326,7 @@ elasticsearch:
       index_template:
         composed_of:
         - logs-windows.sysmon_operational@package
+        - so-fleet_process_caseless-1
         - logs-windows.sysmon_operational@custom
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1

salt/elasticsearch/files/ingest/global@custom

@@ -99,7 +99,7 @@
         },
         {
             "set": {
-                "if": "ctx.tags != null && ctx.tags.contains('import')",
+                "if": "ctx.tags != null && ctx.tags.contains('import') && ctx._index != null && ctx._index.startsWith('logs-import-')",
                 "override": true,
                 "field": "data_stream.dataset",
                 "value": "import"
@@ -107,7 +107,7 @@
         },
         {
             "set": {
-                "if": "ctx.tags != null && ctx.tags.contains('import')",
+                "if": "ctx.tags != null && ctx.tags.contains('import') && ctx._index != null && ctx._index.startsWith('logs-import-')",
                 "override": true,
                 "field": "data_stream.namespace",
                 "value": "so"

salt/elasticsearch/files/ingest/import.evtx

@@ -0,0 +1,31 @@
+{
+  "description" : "import.evtx: normalize imported EVTX and reroute to logs-<dataset>-import",
+  "processors" : [
+    { "script":  {
+        "description": "Host from the event, not the importing node",
+        "lang": "painless",
+        "source": "Map host = ['os': ['type': 'windows', 'family': 'windows', 'platform': 'windows']]; def cn = ctx.winlog?.computer_name; if (cn != null && cn.toString().length() > 0) { String name = cn.toString(); int dot = name.indexOf('.'); if (dot > 0) { name = name.substring(0, dot); } host.put('hostname', name); host.put('name', name.toLowerCase()); } ctx.host = host;"
+    } },
+    { "script":  {
+        "description": "String event IDs, as Winlogbeat sends",
+        "lang": "painless",
+        "source": "if (ctx.winlog?.event_id != null) { ctx.winlog.event_id = ctx.winlog.event_id.toString(); } if (ctx.event?.code != null) { ctx.event.code = ctx.event.code.toString(); }"
+    } },
+    { "script":  {
+        "description": "Unnamed <Data> to param1..N, as Winlogbeat",
+        "lang": "painless",
+        "if": "ctx.winlog?.event_data?.Data instanceof Map && ctx.winlog.event_data.Data['#text'] != null",
+        "source": "def t = ctx.winlog.event_data.Data['#text']; List vals = t instanceof List ? t : [t]; for (int i = 0; i < vals.size(); i++) { ctx.winlog.event_data['param' + (i + 1)] = vals.get(i); } ctx.winlog.event_data.remove('Data');"
+    } },
+    { "script":  {
+        "description": "String values and LF line endings, as Winlogbeat",
+        "lang": "painless",
+        "if": "ctx.winlog?.event_data instanceof Map || ctx.winlog?.user_data instanceof Map",
+        "source": "String lf = String.valueOf((char) 10); String crlf = String.valueOf((char) 13) + lf; for (def key : ['event_data', 'user_data']) { def m = ctx.winlog[key]; if (!(m instanceof Map)) { continue; } for (def e : m.entrySet()) { def v = e.getValue(); if (v instanceof String) { e.setValue(v.replace(crlf, lf)); } else if (v instanceof Number || v instanceof Boolean) { e.setValue(v.toString()); } } }"
+    } },
+    { "set":     { "description": "event.kind, as Winlogbeat", "field": "event.kind", "value": "event", "override": false } },
+    { "set":     { "field": "data_stream.dataset", "copy_from": "event.dataset", "override": true, "ignore_empty_value": true } },
+    { "set":     { "field": "data_stream.namespace", "value": "import", "override": true } },
+    { "reroute": { "dataset": "{{data_stream.dataset}}", "namespace": "{{data_stream.namespace}}" } }
+  ]
+}

salt/elasticsearch/templates/component/elastic-agent/so-fleet_process_caseless-1.json

@@ -0,0 +1,123 @@
+{
+  "_meta": {
+    "managed_by": "security_onion",
+    "managed": true,
+    "description": "Adds .caseless for Lucene queries. Restates each field's package type and .text."
+  },
+  "template": {
+    "mappings": {
+      "properties": {
+        "process": {
+          "properties": {
+            "executable": {
+              "type": "keyword",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                },
+                "text": {
+                  "type": "match_only_text"
+                }
+              }
+            },
+            "name": {
+              "type": "keyword",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                },
+                "text": {
+                  "type": "match_only_text"
+                }
+              }
+            },
+            "command_line": {
+              "type": "wildcard",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                },
+                "text": {
+                  "type": "match_only_text"
+                }
+              }
+            },
+            "parent": {
+              "properties": {
+                "executable": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    },
+                    "text": {
+                      "type": "match_only_text"
+                    }
+                  }
+                },
+                "name": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    },
+                    "text": {
+                      "type": "match_only_text"
+                    }
+                  }
+                },
+                "command_line": {
+                  "type": "wildcard",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    },
+                    "text": {
+                      "type": "match_only_text"
+                    }
+                  }
+                }
+              }
+            }
+          }
+        },
+        "file": {
+          "properties": {
+            "path": {
+              "type": "keyword",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                },
+                "text": {
+                  "type": "match_only_text"
+                }
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}

salt/elasticsearch/templates/component/elastic-agent/so-fleet_system.security_caseless-1.json

@@ -0,0 +1,80 @@
+{
+  "_meta": {
+    "managed_by": "security_onion",
+    "managed": true,
+    "description": "Adds .caseless for Lucene queries. Keeps each field's existing keyword type."
+  },
+  "template": {
+    "mappings": {
+      "properties": {
+        "process": {
+          "properties": {
+            "command_line": {
+              "type": "keyword",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                }
+              }
+            },
+            "parent": {
+              "properties": {
+                "executable": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    }
+                  }
+                },
+                "name": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    }
+                  }
+                },
+                "command_line": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "fields": {
+                    "caseless": {
+                      "type": "keyword",
+                      "ignore_above": 1024,
+                      "normalizer": "lowercase"
+                    }
+                  }
+                }
+              }
+            }
+          }
+        },
+        "file": {
+          "properties": {
+            "path": {
+              "type": "keyword",
+              "ignore_above": 1024,
+              "fields": {
+                "caseless": {
+                  "type": "keyword",
+                  "ignore_above": 1024,
+                  "normalizer": "lowercase"
+                }
+              }
+            }
+          }
+        }
+      }
+    }
+  }
+}

salt/kafka/config.sls

@@ -21,6 +21,7 @@ kafka_user:
     - gid: 960
     - home: /opt/so/conf/kafka
     - createhome: False
+    - shell: /sbin/nologin
 
 kafka_home_dir:
   file.absent:

salt/kibana/config.sls

@@ -22,6 +22,7 @@ kibana:
     - gid: 932
     - home: /opt/so/conf/kibana
     - createhome: False
+    - shell: /sbin/nologin
 
 # Drop the correct nginx config based on role
 

salt/kratos/config.sls

@@ -27,6 +27,7 @@ kratos:
     - uid: 928
     - gid: 928
     - home: /opt/so/conf/kratos
+    - shell: /sbin/nologin
 
 kratosdir:
   file.directory:

salt/logstash/config.sls

@@ -35,6 +35,7 @@ logstash:
     - uid: 931
     - gid: 931
     - home: /opt/so/conf/logstash
+    - shell: /sbin/nologin
 
 logstash_sbin:
   file.recurse:

salt/manager/tools/sbin/so-push-drainer

@@ -19,6 +19,8 @@ is older than debounce_seconds, this script:
   * dispatches a single `salt-run state.orchestrate orch.push_batch --async`
     with the deduped actions list passed as pillar kwargs
   * deletes the contributed intent files on successful dispatch
+  * records the orchestration jid under /opt/so/state/push_dispatched and, on
+    later passes, looks up its result and logs success or per-minion failures
 
 Reactor sls files (push_files, push_pillar) write intents
 but never dispatch directly
@@ -30,6 +32,7 @@ import json
 import logging
 import logging.handlers
 import os
+import re
 import subprocess
 import sys
 import time
@@ -40,8 +43,19 @@ PENDING_DIR = '/opt/so/state/push_pending'
 LOCK_FILE = os.path.join(PENDING_DIR, '.lock')
 LOG_FILE = '/opt/so/log/salt/so-push-drainer.log'
 
+DISPATCHED_DIR = '/opt/so/state/push_dispatched'
+
 HIGHSTATE_SENTINEL = '__highstate__'
 
+RESULT_CHECK_DELAY = 30
+RESULT_RECHECK_MAX = 300
+RESULT_MAX_AGE = 7200
+RESULT_CHECKS_PER_PASS = 5
+TEXT_LIMIT = 500
+
+# salt-run --async reports the jid only in a log line (stderr by default).
+JID_RE = re.compile(r'salt/run/(\d{20})')
+
 
 def _make_logger():
     logger = logging.getLogger('so-push-drainer')
@@ -113,14 +127,167 @@ def _dispatch(actions, log):
     except subprocess.CalledProcessError as exc:
         log.error('dispatch failed (rc=%s): stdout=%s stderr=%s',
                   exc.returncode, exc.stdout, exc.stderr)
-        return False
+        return None
     except subprocess.TimeoutExpired:
         log.error('dispatch timed out after 60s')
-        return False
+        return None
     except Exception:
         log.exception('dispatch raised')
+        return None
+    output = '{}\n{}'.format(result.stderr or '', result.stdout or '')
+    match = JID_RE.search(output)
+    if not match:
+        log.warning('dispatch accepted but no jid found, result will not be tracked: output=%s',
+                    _trim(output))
+        return ''
+    log.info('dispatch accepted: jid=%s', match.group(1))
+    return match.group(1)
+
+
+def _trim(value):
+    text = value if isinstance(value, str) else json.dumps(value, default=str)
+    lines = [line.strip() for line in text.splitlines() if line.strip()]
+    if 'Traceback (most recent call last):' in text:
+        # Keep the lead-in and the raised exception; the frames are noise in a log line.
+        lines = [text.split('Traceback (most recent call last):', 1)[0].strip(), lines[-1]]
+    text = ' '.join(line for line in lines if line)
+    return text if len(text) <= TEXT_LIMIT else text[:TEXT_LIMIT] + '...'
+
+
+def _unlink(path, log):
+    try:
+        os.unlink(path)
+    except FileNotFoundError:
+        pass
+    except OSError:
+        log.exception('failed to remove %s', path)
+
+
+def _write_record(path, record, log):
+    try:
+        os.makedirs(DISPATCHED_DIR, exist_ok=True)
+        tmp_path = path + '.tmp'
+        with open(tmp_path, 'w') as f:
+            json.dump(record, f)
+        os.rename(tmp_path, path)
+    except Exception:
+        log.exception('failed to record dispatch %s', record.get('jid'))
+
+
+def _record_dispatch(jid, actions, paths, log):
+    record = {'jid': jid, 'dispatched_at': time.time(), 'actions': actions, 'paths': paths}
+    _write_record(os.path.join(DISPATCHED_DIR, '{}.json'.format(jid)), record, log)
+
+
+def _lookup_jid(jid, log):
+    """Returns the job cache entry for jid, {} while it is still running, or None on error."""
+    cmd = ['salt-run', 'jobs.lookup_jid', jid, '--out=json']
+    try:
+        result = subprocess.run(cmd, check=True, capture_output=True, text=True, timeout=60)
+        return json.loads(result.stdout or '{}')
+    except (subprocess.CalledProcessError, subprocess.TimeoutExpired, ValueError) as exc:
+        log.warning('lookup of jid %s failed: %s', jid, exc)
+        return None
+
+
+def _minion_failure(minion_ret):
+    if isinstance(minion_ret, dict):
+        return '; '.join(
+            '{}: {}'.format(state.get('__id__', state_key), _trim(state.get('comment', '')))
+            for state_key, state in minion_ret.items()
+            if isinstance(state, dict) and state.get('result') is False
+        )
+    # A state run rejected before it starts (e.g. another state run is in
+    # progress) returns a list of error strings instead of state results.
+    if isinstance(minion_ret, (list, str)):
+        return _trim(minion_ret)
+    return ''
+
+
+def _step_failures(step):
+    if not isinstance(step, dict) or step.get('result') is not False:
+        return []
+    failures = ['{}: {}'.format(step.get('__id__', step.get('name')), _trim(step.get('comment', '')))]
+    changes = step.get('changes')
+    minion_rets = changes.get('ret') if isinstance(changes, dict) else None
+    if isinstance(minion_rets, dict):
+        for minion, minion_ret in minion_rets.items():
+            text = _minion_failure(minion_ret)
+            if text:
+                failures.append('{}: {}'.format(minion, text))
+    return failures
+
+
+def _orch_failures(ret):
+    if not isinstance(ret, dict):
+        return [_trim(ret)]
+    failures = []
+    for job in ret.values():
+        if not isinstance(job, dict):
+            continue
+        job_ret = job.get('return')
+        data = job_ret.get('data') if isinstance(job_ret, dict) else {}
+        if not isinstance(data, dict):
+            if data:
+                failures.append(_trim(data))
+            data = {}
+        for steps in data.values():
+            if not isinstance(steps, dict):
+                failures.append(_trim(steps))
+                continue
+            for step in steps.values():
+                failures.extend(_step_failures(step))
+        if job.get('success') is False and not failures:
+            failures.append('orchestration reported failure: {}'.format(_trim(job.get('return'))))
+    return failures
+
+
+def _recheck_delay(age):
+    return min(RESULT_RECHECK_MAX, max(RESULT_CHECK_DELAY, age / 4))
+
+
+def _check_dispatched(log, now):
+    due = []
+    for path in glob.glob(os.path.join(DISPATCHED_DIR, '*.json')):
+        record = _read_intent(path, log)
+        if not isinstance(record, dict) or not record.get('jid'):
+            _unlink(path, log)
+            continue
+        age = now - record.get('dispatched_at', 0)
+        last_check = record.get('checked_at', record.get('dispatched_at', 0))
+        if now - last_check >= _recheck_delay(age):
+            due.append((last_check, path, record, age))
+    # Least recently checked first, so pushes that are still running can't starve finished ones.
+    for _, path, record, age in sorted(due, key=lambda item: item[:2])[:RESULT_CHECKS_PER_PASS]:
+        jid = record['jid']
+        try:
+            if _report_result(record, age, log):
+                _unlink(path, log)
+            else:
+                record['checked_at'] = now
+                _write_record(path, record, log)
+        except Exception:
+            # Drop the record so one unreadable result can't fail every pass ahead of the drain.
+            log.exception('cannot evaluate result for jid=%s; no longer tracking', jid)
+            _unlink(path, log)
+
+
+def _report_result(record, age, log):
+    """Logs the outcome of a dispatched push. Returns True once the record is finished with."""
+    jid = record['jid']
+    paths = record.get('paths', [])
+    ret = _lookup_jid(jid, log)
+    if not ret:
+        if age > RESULT_MAX_AGE:
+            log.warning('no result for jid=%s after %ds, no longer tracking; paths=%s', jid, age, paths)
+            return True
         return False
-    log.info('dispatch accepted: %s', (result.stdout or '').strip())
+    failures = _orch_failures(ret)
+    if failures:
+        log.error('push failed jid=%s paths=%s; change will be applied at the next scheduled highstate: %s',
+                  jid, paths, ' | '.join(failures))
+    else:
+        log.info('push succeeded jid=%s paths=%s', jid, paths)
     return True
 
 
@@ -143,6 +310,9 @@ def main():
 
     debounce_seconds = int(push.get('debounce_seconds', 30))
 
+    # Outside the lock: lookups are slow and the reactors take the same lock.
+    _check_dispatched(log, time.time())
+
     os.makedirs(PENDING_DIR, exist_ok=True)
     lock_fd = os.open(LOCK_FILE, os.O_CREAT | os.O_RDWR, 0o644)
     try:
@@ -208,10 +378,16 @@ def main():
             len(ready), len(deduped), len(combined_actions),
             debounce_duration, all_paths[:20],
         )
+        for action in deduped:
+            log.info('action: %s tgt=%s', 'highstate' if action.get('highstate') else action.get('state'),
+                     action.get('tgt'))
 
-        if not _dispatch(deduped, log):
+        jid = _dispatch(deduped, log)
+        if jid is None:
             log.warning('dispatch failed; leaving intent files in place for retry')
             return 1
+        if jid:
+            _record_dispatch(jid, deduped, all_paths[:20], log)
 
         for path, _ in ready:
             try:

salt/manager/tools/sbin/so-push-drainer_test.py

@@ -0,0 +1,477 @@
+# 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.
+
+import importlib.util
+import json
+import logging
+import os
+import shutil
+import subprocess
+import sys
+import tempfile
+import time
+import unittest
+from importlib.machinery import SourceFileLoader
+from unittest.mock import MagicMock, patch
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+SCRIPT = os.path.join(HERE, 'so-push-drainer')
+_loader = SourceFileLoader('so_push_drainer', SCRIPT)
+_spec = importlib.util.spec_from_loader('so_push_drainer', _loader)
+drainer = importlib.util.module_from_spec(_spec)
+
+# salt is not installed where these tests run; the drainer only needs salt.client.Caller.
+# Mocked only while the drainer loads: run from the repo root, 'salt' is this repo's salt/ directory.
+_salt = MagicMock()
+with patch.dict(sys.modules, {'salt': _salt, 'salt.client': _salt.client}):
+    _loader.exec_module(drainer)
+
+MASTER = 'manager.localdomain_master'
+JID = '20260930171554259426'
+ASYNC_STDERR = ('[WARNING ] Running in asynchronous mode. Results of this execution may be collected '
+                'by attaching to the master event bus or by examining the master job cache, if '
+                'configured. This execution is running under tag salt/run/{}\n'.format(JID))
+CONFLICT = ('The function "state.sls" is running as PID 372218 and was started at '
+            '2026, Sep 30 17:15:40.466233 with jid 20260930171540466233')
+
+
+def _orch_ret(steps, success=True):
+    return {MASTER: {
+        'fun': 'runner.state.orchestrate',
+        'jid': JID,
+        'return': {'data': {MASTER: steps}, 'outputter': 'highstate', 'retcode': 0 if success else 1},
+        'success': success,
+    }}
+
+
+REFRESH_STEP = {
+    'salt_|-refresh_pillar_1_|-saltutil.refresh_pillar_|-function': {
+        '__id__': 'refresh_pillar_1', 'result': True,
+        'changes': {'ret': {'manager_standalone': True}},
+        'comment': 'Function ran successfully.',
+    },
+}
+
+CONFLICT_RET = _orch_ret(dict(REFRESH_STEP, **{
+    'salt_|-apply_soc_1_|-apply_soc_1_|-state': {
+        '__id__': 'apply_soc_1', 'result': False,
+        'changes': {'out': 'highstate', 'ret': {'manager_standalone': [CONFLICT]}},
+        'comment': 'Run failed on minions: manager_standalone',
+    },
+}), success=False)
+
+STATE_FAIL_RET = _orch_ret({
+    'salt_|-apply_hydra_1_|-apply_hydra_1_|-state': {
+        '__id__': 'apply_hydra_1', 'result': False,
+        'changes': {'out': 'highstate', 'ret': {'manager_standalone': {
+            'test_|-no_license_|-no_license_|-fail_without_changes': {
+                '__id__': 'hydra.enabled_no_license_detected', 'result': False,
+                'comment': 'This is a feature supported only for customers with a valid license.',
+            },
+            'file_|-hydra_conf_|-/opt/so/conf/hydra_|-managed': {'result': True, 'comment': 'ok'},
+        }}},
+        'comment': 'Run failed on minions: manager_standalone',
+    },
+}, success=False)
+
+SUCCESS_RET = _orch_ret(dict(REFRESH_STEP, **{
+    'salt_|-apply_telegraf_1_|-apply_telegraf_1_|-state': {
+        '__id__': 'apply_telegraf_1', 'result': True,
+        'changes': {'out': 'highstate', 'ret': {'manager_standalone': {
+            'file_|-tgrafconf_|-/opt/so/conf/telegraf/etc/telegraf.conf_|-managed': {'result': True},
+        }}},
+        'comment': 'States ran successfully.',
+    },
+}))
+
+
+class DrainerTestCase(unittest.TestCase):
+
+    def setUp(self):
+        self.tmpdir = tempfile.mkdtemp()
+        self.pending = os.path.join(self.tmpdir, 'push_pending')
+        self.dispatched = os.path.join(self.tmpdir, 'push_dispatched')
+        os.makedirs(self.pending)
+        for name, value in (
+            ('PENDING_DIR', self.pending),
+            ('LOCK_FILE', os.path.join(self.pending, '.lock')),
+            ('DISPATCHED_DIR', self.dispatched),
+            ('LOG_FILE', os.path.join(self.tmpdir, 'log', 'so-push-drainer.log')),
+        ):
+            patcher = patch.object(drainer, name, value)
+            patcher.start()
+            self.addCleanup(patcher.stop)
+        self.log = MagicMock()
+
+    def tearDown(self):
+        shutil.rmtree(self.tmpdir, ignore_errors=True)
+
+    def write_json(self, directory, name, data):
+        os.makedirs(directory, exist_ok=True)
+        path = os.path.join(directory, name)
+        with open(path, 'w') as f:
+            if isinstance(data, str):
+                f.write(data)
+            else:
+                json.dump(data, f)
+        return path
+
+    def logged(self, level):
+        return ' '.join(c.args[0] % c.args[1:] for c in getattr(self.log, level).call_args_list)
+
+
+class TestHelpers(DrainerTestCase):
+
+    def test_make_logger_adds_handler_once(self):
+        logger = logging.getLogger('so-push-drainer')
+
+        def close_handlers():
+            for handler in logger.handlers:
+                handler.close()
+            logger.handlers.clear()
+
+        self.addCleanup(close_handlers)
+        logger.handlers.clear()
+        self.assertIs(drainer._make_logger(), logger)
+        drainer._make_logger()
+        self.assertEqual(len(logger.handlers), 1)
+        self.assertTrue(os.path.isdir(os.path.dirname(drainer.LOG_FILE)))
+
+    def test_load_push_cfg(self):
+        with patch.object(drainer.salt.client, 'Caller') as caller:
+            caller.return_value.cmd.return_value = {'enabled': False}
+            self.assertEqual(drainer._load_push_cfg(), {'enabled': False})
+            caller.return_value.cmd.return_value = 'garbage'
+            self.assertEqual(drainer._load_push_cfg(), {})
+
+    def test_read_intent(self):
+        good = self.write_json(self.pending, 'good.json', {'a': 1})
+        bad = self.write_json(self.pending, 'bad.json', '{nope')
+        self.assertEqual(drainer._read_intent(good, self.log), {'a': 1})
+        self.assertIsNone(drainer._read_intent(bad, self.log))
+        with patch('builtins.open', side_effect=RuntimeError('boom')):
+            self.assertIsNone(drainer._read_intent(good, self.log))
+        self.log.exception.assert_called_once()
+
+    def test_dedupe_actions(self):
+        actions = [
+            'not a dict',
+            {'state': 'soc'},
+            {'state': 'soc', 'tgt': '*'},
+            {'state': 'soc', 'tgt': '*', 'tgt_type': 'compound'},
+            {'highstate': True, 'tgt': '*'},
+            {'state': 'soc', 'tgt': 'node1', 'tgt_type': 'glob'},
+        ]
+        self.assertEqual(drainer._dedupe_actions(actions), [actions[2], actions[4], actions[5]])
+
+    def test_trim(self):
+        self.assertEqual(drainer._trim('  text \n'), 'text')
+        self.assertEqual(drainer._trim(['a']), '["a"]')
+        self.assertEqual(drainer._trim(None), 'null')
+        self.assertEqual(drainer._trim('x' * 600), 'x' * drainer.TEXT_LIMIT + '...')
+
+    def test_trim_traceback(self):
+        comment = ('An exception occurred in this state: Traceback (most recent call last):\n'
+                   '  File "salt/client/__init__.py", line 1934, in pub\n'
+                   '    raise AuthenticationError(err_msg)\n'
+                   'salt.exceptions.AuthenticationError: Authentication error occurred.\n')
+        self.assertEqual(drainer._trim(comment), 'An exception occurred in this state: '
+                         'salt.exceptions.AuthenticationError: Authentication error occurred.')
+        self.assertEqual(drainer._trim('line one\n  line two\n'), 'line one line two')
+
+    def test_unlink(self):
+        drainer._unlink(os.path.join(self.tmpdir, 'missing'), self.log)
+        self.log.exception.assert_not_called()
+        drainer._unlink(self.tmpdir, self.log)
+        self.log.exception.assert_called_once()
+
+
+class TestDispatch(DrainerTestCase):
+
+    def run_dispatch(self, **kwargs):
+        with patch.object(drainer.subprocess, 'run', **kwargs) as run:
+            jid = drainer._dispatch([{'state': 'soc', 'tgt': '*'}], self.log)
+        return jid, run
+
+    def test_jid_parsed_from_stderr(self):
+        jid, run = self.run_dispatch(return_value=MagicMock(stdout='', stderr=ASYNC_STDERR))
+        self.assertEqual(jid, JID)
+        cmd = run.call_args[0][0]
+        self.assertEqual(cmd[:3], ['salt-run', 'state.orchestrate', 'orch.push_batch'])
+        self.assertIn('--async', cmd)
+
+    def test_jid_parsed_from_stdout(self):
+        jid, _ = self.run_dispatch(return_value=MagicMock(stdout=ASYNC_STDERR, stderr=None))
+        self.assertEqual(jid, JID)
+
+    def test_no_jid(self):
+        jid, _ = self.run_dispatch(return_value=MagicMock(stdout='unexpected output', stderr=None))
+        self.assertEqual(jid, '')
+        self.assertIn('output=unexpected output', self.logged('warning'))
+
+    def test_failures_return_none(self):
+        for exc in (subprocess.CalledProcessError(1, 'salt-run', 'out', 'err'),
+                    subprocess.TimeoutExpired('salt-run', 60),
+                    RuntimeError('boom')):
+            jid, _ = self.run_dispatch(side_effect=exc)
+            self.assertIsNone(jid)
+
+    def test_record_dispatch(self):
+        drainer._record_dispatch(JID, [{'state': 'soc'}], ['audit:soc.config.licenseKey'], self.log)
+        with open(os.path.join(self.dispatched, JID + '.json')) as f:
+            record = json.load(f)
+        self.assertEqual(record['jid'], JID)
+        self.assertEqual(record['paths'], ['audit:soc.config.licenseKey'])
+        self.assertIn('dispatched_at', record)
+
+    def test_record_dispatch_errors(self):
+        with patch.object(drainer.os, 'makedirs', side_effect=OSError('ro')):
+            drainer._record_dispatch(JID, [], [], self.log)
+        drainer._record_dispatch(JID, [object()], [], self.log)
+        self.assertEqual(self.log.exception.call_count, 2)
+        self.assertFalse(os.path.exists(os.path.join(self.dispatched, JID + '.json')))
+
+
+class TestResults(DrainerTestCase):
+
+    def test_lookup_jid(self):
+        with patch.object(drainer.subprocess, 'run') as run:
+            run.return_value = MagicMock(stdout=json.dumps(SUCCESS_RET))
+            self.assertEqual(drainer._lookup_jid(JID, self.log), SUCCESS_RET)
+            self.assertEqual(run.call_args[0][0], ['salt-run', 'jobs.lookup_jid', JID, '--out=json'])
+            run.return_value = MagicMock(stdout='')
+            self.assertEqual(drainer._lookup_jid(JID, self.log), {})
+            run.return_value = MagicMock(stdout='not json')
+            self.assertIsNone(drainer._lookup_jid(JID, self.log))
+            run.side_effect = subprocess.TimeoutExpired('salt-run', 60)
+            self.assertIsNone(drainer._lookup_jid(JID, self.log))
+
+    def test_minion_failure_shapes(self):
+        self.assertEqual(drainer._minion_failure([CONFLICT]), json.dumps([CONFLICT]))
+        self.assertEqual(drainer._minion_failure('Rendering SLS failed'), 'Rendering SLS failed')
+        self.assertEqual(drainer._minion_failure(True), '')
+        self.assertEqual(drainer._minion_failure({'a': {'result': True}}), '')
+
+    def test_orch_failures_conflict(self):
+        failures = drainer._orch_failures(CONFLICT_RET)
+        self.assertEqual(failures[0], 'apply_soc_1: Run failed on minions: manager_standalone')
+        self.assertIn('manager_standalone', failures[1])
+        self.assertIn('is running as PID 372218', failures[1])
+        self.assertEqual(len(failures), 2)
+
+    def test_orch_failures_failed_state(self):
+        failures = drainer._orch_failures(STATE_FAIL_RET)
+        self.assertEqual(len(failures), 2)
+        self.assertIn('hydra.enabled_no_license_detected: This is a feature', failures[1])
+        self.assertNotIn('hydra_conf', failures[1])
+
+    def test_orch_failures_success(self):
+        self.assertEqual(drainer._orch_failures(SUCCESS_RET), [])
+
+    def test_orch_failures_render_error(self):
+        ret = {MASTER: {'return': {'data': {MASTER: ['Rendering SLS failed']}}, 'success': False}}
+        self.assertEqual(drainer._orch_failures(ret), ['["Rendering SLS failed"]'])
+
+    def test_orch_failures_not_a_dict(self):
+        self.assertEqual(drainer._orch_failures(['No minions matched']), ['["No minions matched"]'])
+        self.assertEqual(drainer._orch_failures('Runner error'), ['Runner error'])
+
+    def test_orch_failures_data_not_a_dict(self):
+        ret = {MASTER: {'return': {'data': ["Rendering SLS 'orch.push_batch' failed"]}, 'success': False}}
+        self.assertEqual(drainer._orch_failures(ret), ['["Rendering SLS \'orch.push_batch\' failed"]'])
+
+    def test_orch_failures_odd_changes(self):
+        for changes in ('Run failed', {'ret': ['manager_standalone']}):
+            ret = _orch_ret({'salt_|-apply_soc_1_|-apply_soc_1_|-state': {
+                '__id__': 'apply_soc_1', 'result': False, 'changes': changes, 'comment': 'Run failed on minions',
+            }}, success=False)
+            self.assertEqual(drainer._orch_failures(ret), ['apply_soc_1: Run failed on minions'])
+
+    def test_orch_failures_unparsed(self):
+        self.assertEqual(drainer._orch_failures({MASTER: 'odd'}), [])
+        ret = {MASTER: {'return': 'Exception occurred', 'success': False}}
+        self.assertEqual(drainer._orch_failures(ret), ['orchestration reported failure: Exception occurred'])
+
+    def record(self, jid, age, now):
+        return self.write_json(self.dispatched, jid + '.json', {
+            'jid': jid, 'dispatched_at': now - age, 'actions': [], 'paths': ['audit:' + jid],
+        })
+
+    def test_check_dispatched(self):
+        now = time.time()
+        results = {
+            '1_failed': CONFLICT_RET,
+            '2_ok': SUCCESS_RET,
+            '3_pending': {},
+            '4_expired': None,
+        }
+        young = self.record('0_young', 5, now)
+        paths = {jid: self.record(jid, 60, now) for jid in results}
+        paths['4_expired'] = self.record('4_expired', drainer.RESULT_MAX_AGE + 1, now)
+        bad = self.write_json(self.dispatched, '5_bad.json', '{nope')
+        with patch.object(drainer, '_lookup_jid', side_effect=lambda jid, log: results[jid]):
+            drainer._check_dispatched(self.log, now)
+
+        self.assertTrue(os.path.exists(young))
+        with open(paths['3_pending']) as f:
+            self.assertEqual(json.load(f)['checked_at'], now)
+        for jid in ('1_failed', '2_ok', '4_expired'):
+            self.assertFalse(os.path.exists(paths[jid]), jid)
+        self.assertFalse(os.path.exists(bad))
+        self.assertIn('push failed jid=1_failed', self.logged('error'))
+        self.assertIn('is running as PID 372218', self.logged('error'))
+        self.assertIn('push succeeded jid=2_ok', self.logged('info'))
+        self.assertIn('no result for jid=4_expired', self.logged('warning'))
+
+    def test_check_dispatched_survives_bad_result(self):
+        now = time.time()
+        bad = self.record('1_bad', 60, now)
+        good = self.record('2_ok', 60, now)
+
+        def orch_failures(ret):
+            if ret == 'boom':
+                raise ValueError('unexpected shape')
+            return []
+
+        with patch.object(drainer, '_lookup_jid', side_effect=lambda jid, log: 'boom' if jid == '1_bad' else SUCCESS_RET), \
+                patch.object(drainer, '_orch_failures', side_effect=orch_failures):
+            drainer._check_dispatched(self.log, now)
+        self.assertFalse(os.path.exists(bad))
+        self.assertFalse(os.path.exists(good))
+        self.log.exception.assert_called_once()
+        self.assertIn('jid=1_bad', self.log.exception.call_args[0][0] % self.log.exception.call_args[0][1:])
+        self.assertIn('push succeeded jid=2_ok', self.logged('info'))
+
+    def test_recheck_delay(self):
+        self.assertEqual(drainer._recheck_delay(10), drainer.RESULT_CHECK_DELAY)
+        self.assertEqual(drainer._recheck_delay(400), 100)
+        self.assertEqual(drainer._recheck_delay(drainer.RESULT_MAX_AGE), drainer.RESULT_RECHECK_MAX)
+
+    def test_check_dispatched_limit_rotates(self):
+        now = time.time()
+        limit = drainer.RESULT_CHECKS_PER_PASS
+        jids = ['{:02d}'.format(i) for i in range(limit + 2)]
+        for jid in jids:
+            self.record(jid, 60, now)
+        with patch.object(drainer, '_lookup_jid', return_value={}) as lookup:
+            drainer._check_dispatched(self.log, now)
+            self.assertEqual([c.args[0] for c in lookup.call_args_list], jids[:limit])
+            lookup.reset_mock()
+            drainer._check_dispatched(self.log, now + 40)
+        self.assertEqual([c.args[0] for c in lookup.call_args_list], jids[limit:] + jids[:limit - 2])
+
+    def test_check_dispatched_not_blocked_by_running(self):
+        now = time.time()
+        for i in range(drainer.RESULT_CHECKS_PER_PASS):
+            self.record('1_running{}'.format(i), 600, now)
+        done = self.record('2_done', 60, now)
+
+        def lookup(jid, log):
+            return SUCCESS_RET if jid == '2_done' else {}
+
+        with patch.object(drainer, '_lookup_jid', side_effect=lookup) as lookup_jid:
+            drainer._check_dispatched(self.log, now)
+            self.assertTrue(os.path.exists(done))
+            lookup_jid.reset_mock()
+            drainer._check_dispatched(self.log, now + 15)
+        self.assertEqual([c.args[0] for c in lookup_jid.call_args_list], ['2_done'])
+        self.assertFalse(os.path.exists(done))
+        self.assertIn('push succeeded jid=2_done', self.logged('info'))
+
+
+class TestMain(DrainerTestCase):
+
+    def setUp(self):
+        super().setUp()
+        self.cfg = {'enabled': True, 'debounce_seconds': 30}
+        for name, kwargs in (
+            ('_make_logger', {'return_value': self.log}),
+            ('_load_push_cfg', {'side_effect': lambda: self.cfg}),
+            ('_check_dispatched', {}),
+        ):
+            patcher = patch.object(drainer, name, **kwargs)
+            setattr(self, name, patcher.start())
+            self.addCleanup(patcher.stop)
+
+    def intent(self, name, age=60, actions=None, paths=None):
+        now = time.time()
+        return self.write_json(self.pending, name, {
+            'first_touch': now - age - 5, 'last_touch': now - age,
+            'actions': [{'state': 'soc', 'tgt': '*'}] if actions is None else actions,
+            'paths': paths or ['audit:soc.config.licenseKey'],
+        })
+
+    def test_no_pending_dir(self):
+        shutil.rmtree(self.pending)
+        self.assertEqual(drainer.main(), 0)
+        self._load_push_cfg.assert_not_called()
+
+    def test_cfg_error(self):
+        self._load_push_cfg.side_effect = RuntimeError('no salt')
+        self.assertEqual(drainer.main(), 1)
+
+    def test_disabled(self):
+        self.cfg['enabled'] = False
+        self.assertEqual(drainer.main(), 0)
+        self._check_dispatched.assert_not_called()
+
+    def test_no_intents_still_checks_results(self):
+        self.assertEqual(drainer.main(), 0)
+        self._check_dispatched.assert_called_once()
+
+    def test_debounce_and_broken(self):
+        young = self.intent('young.json', age=1)
+        broken = self.write_json(self.pending, 'broken.json', '{nope')
+        with patch.object(drainer, '_dispatch') as dispatch:
+            self.assertEqual(drainer.main(), 0)
+        dispatch.assert_not_called()
+        self.assertTrue(os.path.exists(young))
+        self.assertFalse(os.path.exists(broken))
+
+    def test_broken_unlink_error_ignored(self):
+        self.write_json(self.pending, 'broken.json', '{nope')
+        with patch.object(drainer.os, 'unlink', side_effect=OSError('busy')):
+            self.assertEqual(drainer.main(), 0)
+
+    def test_no_usable_actions(self):
+        path = self.intent('empty.json', actions=[{'state': 'soc'}])
+        self.assertEqual(drainer.main(), 0)
+        self.assertFalse(os.path.exists(path))
+        self.intent('empty.json', actions=[{'state': 'soc'}])
+        with patch.object(drainer.os, 'unlink', side_effect=OSError('busy')):
+            self.assertEqual(drainer.main(), 0)
+
+    def test_dispatch_failure_keeps_intents(self):
+        path = self.intent('pillar_soc.json')
+        with patch.object(drainer, '_dispatch', return_value=None):
+            self.assertEqual(drainer.main(), 1)
+        self.assertTrue(os.path.exists(path))
+
+    def test_dispatch_records_jid(self):
+        soc = self.intent('pillar_soc.json')
+        hs = self.intent('pillar_global.json', actions=[{'highstate': True, 'tgt': '*'}], paths=['audit:global.x'])
+        with patch.object(drainer, '_dispatch', return_value=JID) as dispatch, \
+                patch.object(drainer, '_record_dispatch') as record:
+            self.assertEqual(drainer.main(), 0)
+        self.assertEqual(len(dispatch.call_args[0][0]), 2)
+        record.assert_called_once()
+        self.assertEqual(record.call_args[0][0], JID)
+        self.assertEqual(sorted(record.call_args[0][2]), ['audit:global.x', 'audit:soc.config.licenseKey'])
+        self.assertFalse(os.path.exists(soc))
+        self.assertFalse(os.path.exists(hs))
+        self.assertIn('action: highstate tgt=*', self.logged('info'))
+
+    def test_dispatch_without_jid_not_recorded(self):
+        self.intent('pillar_soc.json')
+        with patch.object(drainer, '_dispatch', return_value=''), \
+                patch.object(drainer, '_record_dispatch') as record, \
+                patch.object(drainer.os, 'unlink', side_effect=OSError('busy')):
+            self.assertEqual(drainer.main(), 0)
+        record.assert_not_called()
+        self.log.exception.assert_called_once()
+
+
+if __name__ == '__main__':
+    unittest.main()

salt/manager/tools/sbin/so-yaml.py

@@ -42,7 +42,8 @@ def loadYaml(filename):
     try:
         with open(filename, "r") as file:
             content = file.read()
-            return yaml.safe_load(content)
+            loaded = yaml.safe_load(content)
+            return loaded if loaded is not None else {}
     except FileNotFoundError:
         print(f"File not found: {filename}", file=sys.stderr)
         sys.exit(1)

salt/manager/tools/sbin/so-yaml_test.py

@@ -95,6 +95,20 @@ class TestRemove(unittest.TestCase):
         expected = "key1:\n  child1: 123\n  child2:\n    deep2: ab\nkey2: false\n"
         self.assertEqual(actual, expected)
 
+    def test_remove_empty_file(self):
+        filename = "/tmp/so-yaml_test-remove-empty.yaml"
+        file = open(filename, "w")
+        file.close()
+
+        code = soyaml.remove([filename, "key1"])
+        self.assertEqual(code, 0)
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        self.assertEqual(actual, "{}\n")
+
     def test_remove_missing_args(self):
         with patch('sys.exit', new=MagicMock()) as sysmock:
             with patch('sys.stderr', new=StringIO()) as mock_stderr:
@@ -294,6 +308,36 @@ class TestRemove(unittest.TestCase):
         expected = "key1:\n  child1: 123\n  child2:\n    deep1: 45\n    deep2: d\nkey2: false\nkey3:\n- e\n- f\n- g\n"
         self.assertEqual(actual, expected)
 
+    def test_add_empty_file(self):
+        filename = "/tmp/so-yaml_test-add-empty.yaml"
+        file = open(filename, "w")
+        file.close()
+
+        code = soyaml.add([filename, "telegraf.output", "BOTH"])
+        self.assertEqual(code, 0)
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        expected = "telegraf:\n  output: BOTH\n"
+        self.assertEqual(actual, expected)
+
+    def test_add_empty_file_simple(self):
+        filename = "/tmp/so-yaml_test-add-empty-simple.yaml"
+        file = open(filename, "w")
+        file.close()
+
+        code = soyaml.add([filename, "telegraf", "BOTH"])
+        self.assertEqual(code, 0)
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        expected = "telegraf: BOTH\n"
+        self.assertEqual(actual, expected)
+
     def test_replace_missing_arg(self):
         with patch('sys.exit', new=MagicMock()) as sysmock:
             with patch('sys.stderr', new=StringIO()) as mock_stderr:
@@ -346,6 +390,21 @@ class TestRemove(unittest.TestCase):
         expected = "key1:\n  child1: 123\n  child2:\n    deep1: 46\nkey2: false\nkey3:\n- e\n- f\n- g\n"
         self.assertEqual(actual, expected)
 
+    def test_replace_empty_file(self):
+        filename = "/tmp/so-yaml_test-replace-empty.yaml"
+        file = open(filename, "w")
+        file.close()
+
+        code = soyaml.replace([filename, "telegraf.output", "BOTH"])
+        self.assertEqual(code, 0)
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        expected = "telegraf:\n  output: BOTH\n"
+        self.assertEqual(actual, expected)
+
     def test_convert(self):
         self.assertEqual(soyaml.convertType("foo"), "foo")
         self.assertEqual(soyaml.convertType("foo.bar"), "foo.bar")
@@ -506,6 +565,18 @@ class TestRemove(unittest.TestCase):
             self.assertEqual(result, 2)
             self.assertEqual("", mock_stdout.getvalue())
 
+    def test_get_empty_file(self):
+        with patch('sys.stdout', new=StringIO()) as mock_stdout:
+            with patch('sys.stderr', new=StringIO()) as mock_stderr:
+                filename = "/tmp/so-yaml_test-get-empty.yaml"
+                file = open(filename, "w")
+                file.close()
+
+                result = soyaml.get([filename, "telegraf.output"])
+                self.assertEqual(result, 2)
+                self.assertEqual("", mock_stdout.getvalue())
+                self.assertIn("Key 'telegraf.output' not found by so-yaml.py", mock_stderr.getvalue())
+
     def test_get_usage(self):
         with patch('sys.exit', new=MagicMock()) as sysmock:
             with patch('sys.stderr', new=StringIO()) as mock_stderr:
@@ -991,3 +1062,29 @@ class TestLoadYaml(unittest.TestCase):
                     soyaml.loadYaml("/tmp/so-yaml_test-unreadable.yaml")
                     sysmock.assert_called_with(1)
                     self.assertIn("Error reading file", mock_stderr.getvalue())
+
+    def test_load_yaml_empty_file(self):
+        filename = "/tmp/so-yaml_test-load-empty.yaml"
+        file = open(filename, "w")
+        file.close()
+
+        result = soyaml.loadYaml(filename)
+        self.assertEqual(result, {})
+
+    def test_load_yaml_whitespace_only(self):
+        filename = "/tmp/so-yaml_test-load-whitespace.yaml"
+        file = open(filename, "w")
+        file.write("   \n\n  \n")
+        file.close()
+
+        result = soyaml.loadYaml(filename)
+        self.assertEqual(result, {})
+
+    def test_load_yaml_comments_only(self):
+        filename = "/tmp/so-yaml_test-load-comments.yaml"
+        file = open(filename, "w")
+        file.write("# Just a comment\n# Another comment\n")
+        file.close()
+
+        result = soyaml.loadYaml(filename)
+        self.assertEqual(result, {})

salt/manager/tools/sbin/soup

@@ -1183,6 +1183,13 @@ up_to_3.4.0() {
   echo "Removing so-kratos, so-hydra and so-soc so they are recreated on the soauth network."
   docker rm -f so-kratos so-hydra so-soc >> $SOUP_LOG 2>&1
 
+  for template in so-metrics-logstash.node so-metrics-logstash.stack_monitoring.node; do
+    if ! remove_elasticsearch_index_template "$template" "logstash node and node_cel index patterns reversed"; then
+      FINAL_MESSAGE_QUEUE+=("WARNING: Unable to automatically remove the $template index template. Addon integration templates may fail to load until it is removed:")
+      FINAL_MESSAGE_QUEUE+=("    - sudo so-elasticsearch-query _index_template/$template -XDELETE && so-checkin")
+    fi
+  done
+
   INSTALLEDVERSION=3.4.0
 }
 
@@ -1248,6 +1255,10 @@ valid_soauth_range() {
 }
 
 post_to_3.4.0() {
+  for idx in "metrics-logstash.node-default" "metrics-logstash.stack_monitoring.node-default"; do
+    rollover_index "$idx"
+  done
+
   set_postversion 3.4.0
 }
 ### 3.4.0 End ###

salt/orch/push_batch.sls

@@ -3,6 +3,8 @@
 {% set BATCH = AUTOAPPLY.batch %}
 {% set BATCH_WAIT = AUTOAPPLY.batch_wait %}
 
+{# queue must be a top-level salt.state arg (kwarg is ignored); an int is max_queue and still fails on conflict #}
+
 {% for action in actions %}
 {%   if action.get('highstate') %}
 apply_highstate_{{ loop.index }}:
@@ -12,8 +14,7 @@ apply_highstate_{{ loop.index }}:
     - highstate: True
     - batch: {{ action.get('batch', BATCH) }}
     - batch_wait: {{ action.get('batch_wait', BATCH_WAIT) }}
-    - kwarg:
+    - queue: True
-        queue: 2
 {%   else %}
 refresh_pillar_{{ loop.index }}:
   salt.function:
@@ -29,8 +30,7 @@ apply_{{ action.state | replace('.', '_') }}_{{ loop.index }}:
       - {{ action.state }}
     - batch: {{ action.get('batch', BATCH) }}
     - batch_wait: {{ action.get('batch_wait', BATCH_WAIT) }}
-    - kwarg:
+    - queue: True
-        queue: 2
     - require:
       - salt: refresh_pillar_{{ loop.index }}
 {%   endif %}

salt/reactor/push_pillar.sls

@@ -138,6 +138,7 @@ def run():
     # top level so the reactor is robust to either shape.
     event = data.get('data', data)  # noqa: F821 -- data provided by reactor
     setting_id = event.get('setting_id', '')
+    audit_id = event.get('id')
     node_id = (event.get('node_id') or '').strip()
 
     app = _app_from_setting(setting_id)
@@ -150,8 +151,8 @@ def run():
     if not entry:
         LOG.warning(
             'push_pillar: app "%s" is not in pillar_push_map.yaml; change will be '
-            'picked up at the next scheduled highstate (setting_id=%s)',
+            'picked up at the next scheduled highstate (setting_id=%s audit_id=%s)',
-            app, setting_id,
+            app, setting_id, audit_id,
         )
         return {}
 
@@ -165,12 +166,12 @@ def run():
             'node_{}_{}'.format(node_id, app), actions,
             'audit:{}@{}'.format(setting_id, node_id),
         )
-        LOG.info('push_pillar: per-node intent updated for %s on %s (setting_id=%s)',
+        LOG.info('push_pillar: per-node intent updated for %s on %s (setting_id=%s audit_id=%s)',
-                 app, node_id, setting_id)
+                 app, node_id, setting_id, audit_id)
         return {}
 
     # Branch B: grid-wide app change -> use the map entry's actions as-is.
     actions = list(entry)  # copy to avoid mutating the cache
     _write_intent('pillar_{}'.format(app), actions, 'audit:{}'.format(setting_id))
-    LOG.info('push_pillar: app intent updated for %s (setting_id=%s)', app, setting_id)
+    LOG.info('push_pillar: app intent updated for %s (setting_id=%s audit_id=%s)', app, setting_id, audit_id)
     return {}

salt/repo/client/map.jinja

@@ -9,7 +9,7 @@
        'epel-testing.repo',
        'saltstack.repo',
        'salt-latest.repo',
-       'wazuh.repo'
+       'wazuh.repo',
        'Rocky-Base.repo',
        'Rocky-CR.repo',
        'Rocky-Debuginfo.repo',

salt/soc/config.sls

@@ -118,21 +118,33 @@ crondetectionsbackup:
     - month: '*'
     - dayweek: '*'
 
+# sigma-cli only loads *.yml from the pipelines dir
 socsigmafinalpipeline:
   file.managed:
-    - name: /opt/so/conf/soc/sigma_final_pipeline.yaml
+    - name: /opt/so/conf/soc/sigma_pipelines/sigma_final_pipeline.yml
     - source: salt://soc/files/soc/sigma_final_pipeline.yaml
     - user: 939
     - group: 939
     - mode: 600
+    - makedirs: True
 
-socsigmasopipeline:
+# sigma-cli loads every *.yml here; clean removes anything else
-  file.managed:
+socsigmapipelines:
-    - name: /opt/so/conf/soc/sigma_so_pipeline.yaml
+  file.recurse:
-    - source: salt://soc/files/soc/sigma_so_pipeline.yaml
+    - name: /opt/so/conf/soc/sigma_pipelines
+    - source: salt://soc/files/soc/sigma_pipelines
     - user: 939
     - group: 939
-    - mode: 600
+    - file_mode: 600
+    - clean: True
+    - require:
+      - file: socsigmafinalpipeline
+
+socsigmapipelinesold:
+  file.absent:
+    - names:
+      - /opt/so/conf/soc/sigma_final_pipeline.yaml
+      - /opt/so/conf/soc/sigma_so_pipeline.yaml
 
 socsigmaplaybookpipeline:
   file.managed:

salt/soc/defaults.yaml

@@ -1496,7 +1496,7 @@ soc:
           verifyCert: false
         notification:
           dismissedPruneDays: 30
-          enabled: false
+          enabled: true
         playbook:
           autoUpdateEnabled: true
           playbookImportFrequencySeconds: 86400
@@ -1561,6 +1561,14 @@ soc:
           reconcilePersona: ""
           toolUseTurnAttempts: 12
           toolUseTurnDelayMs: 175
+          agentSessionMaxTurns: 20
+          agentStreamFlushIntervalMs: 1000
+          agentStreamIdleTimeoutSeconds: 300
+          automationSettings:
+            tickIntervalSeconds: 60
+            maxConcurrentItems: 4
+            maxQueuedItems: 0
+            alertTriageEpoch: "2026-09-24T00:00:00Z"
           tools:
             filterEventFields:
               - "@timestamp"
@@ -2799,7 +2807,7 @@ soc:
             - id: sonnet
               displayName: Claude Sonnet
               origin: USA
-              contextLimitSmall: 200000
+              contextLimitSmall: 1000000
               contextLimitLarge: 1000000
               lowBalanceColorAlert: 500000
               enabled: true

salt/soc/enabled.sls

@@ -47,9 +47,8 @@ so-soc:
 {% endif %}
       - /opt/so/conf/soc/motd.md:/opt/sensoroni/html/motd.md:ro
       - /opt/so/conf/soc/banner.md:/opt/sensoroni/html/login/banner.md:ro
-      - /opt/so/conf/soc/sigma_so_pipeline.yaml:/opt/sensoroni/sigma_so_pipeline.yaml:ro
+      - /opt/so/conf/soc/sigma_pipelines:/opt/sensoroni/sigma_pipelines:ro
       - /opt/so/conf/soc/sigma_playbook_pipeline.yaml:/opt/sensoroni/sigma_playbook_pipeline.yaml:ro
-      - /opt/so/conf/soc/sigma_final_pipeline.yaml:/opt/sensoroni/sigma_final_pipeline.yaml:ro
       - /opt/so/conf/soc/playbook_placeholder_map.yaml:/opt/sensoroni/playbook_placeholder_map.yaml:ro
       - /opt/so/conf/soc/playbook_placeholder_map_custom.yaml:/opt/sensoroni/playbook_placeholder_map_custom.yaml:ro
       - /opt/so/conf/soc/custom.js:/opt/sensoroni/html/js/custom.js:ro
@@ -107,6 +106,7 @@ so-soc:
       - file: socclientsroles
       - file: socplaybookplaceholdermap
       - file: socplaybookplaceholdermapcustom
+      - file: socsigmapipelines
 
 delete_so-soc_so-status.disabled:
   file.uncomment:

salt/soc/files/soc/sigma_pipelines/sigma_esql_pipeline.yml

@@ -0,0 +1,477 @@
+name: Security Onion ES|QL Pipeline
+# ES|QL query settings
+priority: 92
+transformations:
+    - id: esql_default_index
+      type: set_state
+      key: index
+      val: .ds-logs-*
+    - id: esql_source_metadata
+      type: set_state
+      key: metadata
+      val: "_id, _index, _source"
+    - id: esql_source_keep
+      type: set_state
+      key: keep
+      val: "_id, _index, _source"
+    # unmapped fields read as null instead of failing the query
+    - id: esql_unmapped_fields
+      type: set_state
+      key: unmapped_fields
+      val: nullify
+    # FROM targets per logsource, any namespace; later entries win, correlations get the union
+    - id: esql_index_process_creation
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.process-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-system.security-*
+        - .ds-logs-windows.powershell-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-auditd_manager.auditd-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        category: process_creation
+    - id: esql_index_process_creation_windows
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.process-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-system.security-*
+        - .ds-logs-windows.powershell-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: windows
+        category: process_creation
+    - id: esql_index_process_creation_linux
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.process-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-auditd_manager.auditd-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: linux
+        category: process_creation
+    - id: esql_index_process_creation_macos
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.process-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: macos
+        category: process_creation
+    - id: esql_index_file
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.file-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: file_event
+      - type: logsource
+        category: file_delete
+      - type: logsource
+        category: file_rename
+      - type: logsource
+        category: file_change
+      - type: logsource
+        category: file_access
+    - id: esql_index_file_windows
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.file-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: windows
+        category: file_event
+      - type: logsource
+        product: windows
+        category: file_delete
+      - type: logsource
+        product: windows
+        category: file_rename
+      - type: logsource
+        product: windows
+        category: file_change
+      - type: logsource
+        product: windows
+        category: file_access
+    - id: esql_index_file_linux
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.file-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: linux
+        category: file_event
+      - type: logsource
+        product: linux
+        category: file_delete
+      - type: logsource
+        product: linux
+        category: file_rename
+      - type: logsource
+        product: linux
+        category: file_change
+      - type: logsource
+        product: linux
+        category: file_access
+    - id: esql_index_file_macos
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.file-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: macos
+        category: file_event
+      - type: logsource
+        product: macos
+        category: file_delete
+      - type: logsource
+        product: macos
+        category: file_rename
+      - type: logsource
+        product: macos
+        category: file_change
+      - type: logsource
+        product: macos
+        category: file_access
+    - id: esql_index_registry
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.registry-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: registry_set
+      - type: logsource
+        category: registry_add
+      - type: logsource
+        category: registry_delete
+      - type: logsource
+        category: registry_event
+    - id: esql_index_library
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.library-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: image_load
+      - type: logsource
+        category: driver_load
+    - id: esql_index_endpoint_network
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.network-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: network_connection
+      - type: logsource
+        category: dns_query
+    - id: esql_index_endpoint_network_windows
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.network-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: windows
+        category: network_connection
+      - type: logsource
+        product: windows
+        category: dns_query
+    - id: esql_index_endpoint_network_linux
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.network-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: linux
+        category: network_connection
+      - type: logsource
+        product: linux
+        category: dns_query
+    - id: esql_index_endpoint_network_macos
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-endpoint.events.network-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: macos
+        category: network_connection
+      - type: logsource
+        product: macos
+        category: dns_query
+    - id: esql_index_sysmon_only
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: process_access
+      - type: logsource
+        category: create_remote_thread
+      - type: logsource
+        category: pipe_created
+      - type: logsource
+        category: create_stream_hash
+      - type: logsource
+        category: wmi_event
+      - type: logsource
+        category: raw_access_thread
+      - type: logsource
+        category: process_tampering
+      - type: logsource
+        category: sysmon_status
+      - type: logsource
+        category: sysmon_error
+      - type: logsource
+        category: file_executable_detected
+      - type: logsource
+        category: file_block_executable
+      - type: logsource
+        category: file_block_shredding
+      - type: logsource
+        category: clipboard_capture
+      - type: logsource
+        product: windows
+        service: sysmon
+    - id: esql_index_ps_operational
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-windows.powershell_operational-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: ps_script
+      - type: logsource
+        category: ps_module
+      - type: logsource
+        product: windows
+        service: powershell
+    - id: esql_index_ps_classic
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-windows.powershell-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: ps_classic_start
+      - type: logsource
+        category: ps_classic_provider_start
+      - type: logsource
+        category: ps_classic_script
+      - type: logsource
+        product: windows
+        service: powershell-classic
+    - id: esql_index_win_security
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-system.security-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: windows
+        service: security
+    - id: esql_index_win_system
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-system.system-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: windows
+        service: system
+    - id: esql_index_win_application
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-system.application-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: windows
+        service: application
+    - id: esql_index_linux_auth
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-system.auth-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        product: linux
+        service: auth
+      - type: logsource
+        product: linux
+        service: sshd
+      - type: logsource
+        product: linux
+        service: sudo
+    - id: esql_index_linux_syslog
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-system.syslog-*
+        - .ds-logs-syslog-so-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: linux
+        service: syslog
+    - id: esql_index_linux_auditd
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-auditd_manager.auditd-*
+        - .ds-logs-auditd.log-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: linux
+        service: auditd
+    - id: esql_index_network
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-zeek-so-*
+        - .ds-logs-suricata-so-*
+        - .ds-logs-suricata.alerts-so-*
+        - .ds-logs-endpoint.events.network-*
+        - .ds-logs-windows.sysmon_operational-*
+        - .ds-logs-sysmon_linux.log-*
+        - .ds-logs-windows.forwarded-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        category: network
+    - id: esql_index_so_network
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-zeek-so-*
+        - .ds-logs-suricata-so-*
+        - .ds-logs-import-so-*
+      rule_cond_op: or
+      rule_conditions:
+      - type: logsource
+        category: network
+        service: connection
+      - type: logsource
+        category: network
+        service: dns
+      - type: logsource
+        category: network
+        service: http
+      - type: logsource
+        category: network
+        service: file
+      - type: logsource
+        category: network
+        service: x509
+      - type: logsource
+        category: network
+        service: ssl
+      - type: logsource
+        category: network
+        service: ssh
+      - type: logsource
+        category: dns
+    - id: esql_index_zeek
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-zeek-so-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: zeek
+    - id: esql_index_opencanary
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-idh-so-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: opencanary
+    - id: esql_index_kratos
+      type: set_state
+      key: index
+      val:
+        - .ds-logs-kratos-so-*
+        - .ds-logs-import-so-*
+      rule_conditions:
+      - type: logsource
+        product: kratos
+

salt/soc/files/soc/sigma_pipelines/sigma_so_pipeline.yml

@@ -14,18 +14,16 @@ transformations:
         - process.args
         - related.ip
         - dns.resolved_ip
-    - id: esql_default_index
+    # Not every source maps .caseless; EQL/ES|QL already match case-insensitively.
-      type: set_state
+    - id: caseless_to_parent_fields
-      key: index
+      type: field_name_mapping
-      val: .ds-logs-*
+      mapping:
-    - id: esql_source_metadata
+        process.executable.caseless: process.executable
-      type: set_state
+        process.name.caseless: process.name
-      key: metadata
+        process.parent.executable.caseless: process.parent.executable
-      val: "_id, _index, _source"
+        process.parent.name.caseless: process.parent.name
-    - id: esql_source_keep
+        target.process.executable.caseless: target.process.executable
-      type: set_state
+        target.process.name.caseless: target.process.name
-      key: keep
-      val: "_id, _index, _source"
     - id: baseline_field_name_mapping
       type: field_name_mapping
       mapping:

salt/soc/files/soc/sigma_playbook_pipeline.yaml

@@ -2,13 +2,13 @@ name: Security Onion - Playbook Pipeline
 priority: 97
 transformations:
     # Route to lowercase-normalized .caseless subfields for case-insensitive matching.
-    # file.path.caseless exists on Defend only (Sysmon file events lack it);
     # registry.path / dll.path / file.name have no .caseless on any source.
     - id: case_insensitive_string_fields
       type: field_name_mapping
       mapping:
         process.executable: process.executable.caseless
         process.parent.executable: process.parent.executable.caseless
+        process.parent.name: process.parent.name.caseless
         process.command_line: process.command_line.caseless
         process.parent.command_line: process.parent.command_line.caseless
         file.path: file.path.caseless

salt/soc/soc_soc.yaml

@@ -160,6 +160,7 @@ soc:
         description: Schedules that are shared across the Security Onion product. Modify via one of the SOC Schedules view.
         readonlyUi: True
         global: True
+        advanced: True
         forcedType: string
         syntax: json
         storage: db
@@ -495,6 +496,7 @@ soc:
             description: JSON list of notifications. Modify via the SOC Notifications view.
             readonlyUi: True
             global: True
+            advanced: True
             forcedType: string
             syntax: json
             storage: db
@@ -503,6 +505,10 @@ soc:
             description: The number of days to retain dismissed notifications. When a notification is dismissed, it will be pruned after this many days. Only one user need dismiss a notification for it to be pruned.
             forcedType: int
             global: True
+          maxListLimit:
+            description: Maximum number of notifications to display.
+            forcedType: int
+            global: True
           enabled:
             description: Enables or disables the SOC notification module.
             forcedType: bool
@@ -533,6 +539,48 @@ soc:
             global: True
             sensitive: True
             advanced: True
+        postgresmetrics:
+          host:
+            description: Hostname or IP address of the PostgreSQL server used by Telegraf. Defaults to the manager hostname.
+            global: True
+            advanced: True
+          port:
+            description: Port of the PostgreSQL server used by Telegraf.
+            global: True
+            advanced: True
+          sslMode:
+            description: "Use encrypted connections to the PostgreSQL server used by Telegraf. Must be one of the following values: disable, allow, prefer, require, verify-ca, verify-full."
+            global: True
+            advanced: True
+          database:
+            description: Database to authenticate to on the PostgreSQL server.
+            global: True
+            advanced: True
+          user:
+            description: Username to authenticate to the PostgreSQL server used by Telegraf.
+            global: True
+            advanced: True
+          password:
+            description: Password used to authenticate to the PostgreSQL server used by Telegraf.
+            global: True
+            sensitive: True
+            advanced: True
+          cacheExpirationMs:
+            description: The interval (in milliseconds) to wait before querying the DB for updated metrics.
+            global: True
+            advanced: True
+          maxMetricAgeSeconds:
+            description: The maximum age (in seconds) of metrics to display in the SOC Grid Metrics view. Metrics older than this value will not be displayed.
+            global: True
+            advanced: True
+          alarms:
+            description: JSON list of metric alarms. Modify via the SOC Grid Alarms view.
+            readonlyUi: True
+            advanced: True
+            global: True
+            forcedType: string
+            syntax: json
+            storage: db
         salt:
           longRelayTimeoutMs:
             description: Duration (in milliseconds) to wait for a response from the Salt API when executing tasks known for being long running before giving up and showing an error on the SOC UI.
@@ -791,6 +839,7 @@ soc:
                 - gemini
                 - openai_responses
                 - openai_chat
+                - openai_embeddings
             - field: apiUrl
               label: API URL
               required: False
@@ -812,6 +861,15 @@ soc:
             description: Indicates if the Assistant Module should operate in agentic mode or not. If true, agents can work together to solve tasks.
             global: True
             forcedType: bool
+          automations:
+            description: Scheduled automations for the Onion AI assistant, managed from the Agent Studio.
+            global: True
+            advanced: True
+            readonlyUi: True
+            storage: db
+            forcedType: string
+            syntax: json
+            helpLink: onion-ai
           agents:
             description: Agent definitions for the Onion AI assistant, managed from the Agent Studio. An entry naming a system agent overrides only the fields an admin may change; everything else comes from the built-in definition.
             global: True
@@ -844,6 +902,9 @@ soc:
             - field: persona
               label: Persona
               multiline: True
+            - field: maxConcurrentInstances
+              label: Max Concurrent Instances
+              forcedType: int
           skills:
             description: Skill definitions for the Onion AI assistant, managed from the Agent Studio. An entry naming a system skill overrides only its enabled state and persona addendum; its tool set comes from the built-in definition.
             global: True
@@ -947,6 +1008,43 @@ soc:
             description: The number of times to retry extracting memories from a session if errors occur.
             global: True
             advanced: True
+          agentSessionMaxTurns:
+            description: Maximum number of model turns a headless agent session, such as one started by an automation, may take before it is stopped. Turns taken by delegated sub-agents count toward this limit. A session that reaches the limit is recorded as failed.
+            global: True
+            advanced: True
+            forcedType: int
+          agentStreamFlushIntervalMs:
+            description: Milliseconds between writes of a streaming headless agent turn to the database. Lower values show progress sooner in the Agent Studio at the cost of more frequent Elasticsearch updates.
+            global: True
+            advanced: True
+            forcedType: int
+          agentStreamIdleTimeoutSeconds:
+            description: Seconds a streaming headless agent turn may go without receiving any output before it is abandoned and the session is recorded as failed. Set to 0 to disable the timeout.
+            global: True
+            advanced: True
+            forcedType: int
+          automationSettings:
+            tickIntervalSeconds:
+              description: How often, in seconds, the automation scheduler checks for automations that are due to run. Must be greater than 0.
+              global: True
+              advanced: True
+              forcedType: int
+            maxConcurrentItems:
+              description: Maximum number of automation work items that may run at the same time. Additional work items wait in the queue until a running item finishes. User chat sessions count toward this limit but are never held back by it. Set to 0 to disable the limit.
+              global: True
+              advanced: True
+              forcedType: int
+            maxQueuedItems:
+              description: Maximum number of automation work items that may wait to start. Once the queue is full, no new work items are created until the backlog drains. Set to 0 to disable the limit.
+              global: True
+              advanced: True
+              forcedType: int
+            alertTriageEpoch:
+              description: The earliest alert time the Alert Triage automation will consider. Alerts before this time are never triaged, which keeps a first run on an existing deployment from working through old history. Must be in UTC format (2026-09-24T00:00:00Z).
+              regex: '^(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?Z)?$'
+              regexFailureMessage: Expecting date in RFC3339 format (2026-09-24T00:00:00Z)
+              global: True
+              advanced: True
           tools:
             filterEventFields:
               description: A whitelist of fields to return when OnionAI uses the query_events tool. All other fields are removed. One field per line.

salt/suricata/config.sls

@@ -64,6 +64,7 @@ suricata:
     - gid: 940
     - home: /nsm/suricata
     - createhome: False
+    - shell: /sbin/nologin
 
 socoregroupwithsuricata:
   group.present:

salt/zeek/config.sls

@@ -23,6 +23,7 @@ zeek:
     - gid: 937
     - home: /opt/so/conf/zeek
     - createhome: False
+    - shell: /sbin/nologin
 
 # Create some directories
 zeekpolicydir: