Merge pull request #16266 from Security-Onion-Solutions/mreeves/soai-context-1m

Raise SOAI Sonnet default small context limit to 1M

.github/DISCUSSION_TEMPLATE/3-0.yml

@@ -13,6 +13,7 @@ body:
         - 3.1.0
         - 3.2.0
         - 3.3.0
+        - 3.4.0
         - Other (please provide detail below)
     validations:
       required: true

.github/workflows/pythontest.yml

@@ -6,6 +6,9 @@ on:
       - "salt/sensoroni/files/analyzers/**"
       - "salt/manager/tools/sbin/**"
       - "salt/_beacons/**"
+      - "salt/telegraf/tools/sbin_jinja/**"
+      - "salt/telegraf/defaults.yaml"
+      - "salt/telegraf/soc_telegraf.yaml"
 
 jobs:
   build:
@@ -34,3 +37,25 @@ jobs:
     - name: Test with pytest
       run: |
         PYTHONPATH=${{ matrix.python-code-path }} pytest ${{ matrix.python-code-path }} --cov=${{ matrix.python-code-path }} --doctest-modules --cov-report=term --cov-fail-under=100 --cov-config=pytest.ini
+
+  telegraf-collector:
+    # so-container-stats is a jinja template rather than an importable module, so it gets its
+    # own job: the test renders it the way salt does, then drives it with a faked docker engine
+    # and cgroup tree. No container runtime is needed.
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.14"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install flake8 pytest jinja2 pyyaml
+    - name: Lint with flake8
+      run: |
+        flake8 salt/telegraf/tools/sbin_jinja/so-container-stats_test.py --config=pytest.ini
+    - name: Test with pytest
+      run: |
+        pytest salt/telegraf/tools/sbin_jinja/so-container-stats_test.py -v

DOWNLOAD_AND_VERIFY_ISO.md

@@ -1,17 +1,17 @@
-### 3.2.0-20260729 ISO image released on 2026/07/29
+### 3.3.0-20260911 ISO image released on 2026/09/11
 
 
 ### Download and Verify
 
-3.2.0-20260729 ISO image:  
-https://download.securityonion.net/file/securityonion/securityonion-3.2.0-20260729.iso
+3.3.0-20260911 ISO image:  
+https://download.securityonion.net/file/securityonion/securityonion-3.3.0-20260911.iso
  
-MD5: B1E10F46DF872B655C29325DF965A4DB  
-SHA1: 0F3C7ED80F6D326B7A993C2F899B986320C01BF9  
-SHA256: 7465163C1D1ADFCDC3935530EAFB312E987C016941ADC11841B214553314D1FF  
+MD5: 12B18433D3A2198A185892FF79CF638F  
+SHA1: 2B3C2E1FA7A78ED1F956E7EDCC12E32593C14EEE  
+SHA256: 0938C73B76CE30EC9E4394D312C79EA7CAC721B6818541697279A6221F7D870D  
 
 Signature for ISO image:  
-https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.2.0-20260729.iso.sig
+https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.3.0-20260911.iso.sig
 
 Signing key:  
 https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/3/main/KEYS  
@@ -25,22 +25,22 @@ wget https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/3/
 
 Download the signature file for the ISO:  
 ```
-wget https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.2.0-20260729.iso.sig
+wget https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.3.0-20260911.iso.sig
 ```
 
 Download the ISO image:  
 ```
-wget https://download.securityonion.net/file/securityonion/securityonion-3.2.0-20260729.iso
+wget https://download.securityonion.net/file/securityonion/securityonion-3.3.0-20260911.iso
 ```
 
 Verify the downloaded ISO image using the signature file:  
 ```
-gpg --verify securityonion-3.2.0-20260729.iso.sig securityonion-3.2.0-20260729.iso
+gpg --verify securityonion-3.3.0-20260911.iso.sig securityonion-3.3.0-20260911.iso
 ```
 
 The output should show "Good signature" and the Primary key fingerprint should match what's shown below:
 ```
-gpg: Signature made Tue 28 Jul 2026 06:17:34 PM EDT using RSA key ID FE507013
+gpg: Signature made Fri 11 Sep 2026 11:23:56 AM EDT using RSA key ID FE507013
 gpg: Good signature from "Security Onion Solutions, LLC <info@securityonionsolutions.com>"
 gpg: WARNING: This key is not certified with a trusted signature!
 gpg:          There is no indication that the signature belongs to the owner.

VERSION

@@ -1 +1 @@
-3.3.0
+3.4.0

salt/_beacons/local_files_beacon.py

@@ -3,13 +3,14 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-# Custom salt beacon that watches the suricata/strelka rule directories for changes
-# and emits a beacon event per changed directory. This replaces the stock salt
-# `inotify` beacon, which leaks a kernel inotify instance every time the minion
-# rebuilds the beacon loader's __context__ (orphaning the old pyinotify.Notifier
-# without closing it) until fs.inotify.max_user_instances is exhausted and the
-# beacon dies with EMFILE. Polling holds zero inotify instances, so the leak is
-# impossible, and it keeps firing during state runs (no blackout).
+# Custom salt beacon that watches hand-edited directories under
+# /opt/so/saltstack/local/salt/ for changes and emits a beacon event per changed
+# directory. This replaces the stock salt `inotify` beacon, which leaks a kernel
+# inotify instance every time the minion rebuilds the beacon loader's __context__
+# (orphaning the old pyinotify.Notifier without closing it) until
+# fs.inotify.max_user_instances is exhausted and the beacon dies with EMFILE.
+# Polling holds zero inotify instances, so the leak is impossible, and it keeps
+# firing during state runs (no blackout).
 #
 # Detection is poll-based with a per-directory fingerprint persisted to
 # WATERMARK_DIR: each pass walks the directory and hashes every file's
@@ -19,9 +20,10 @@
 # up on the next one).
 #
 # Each emitted event carries the watched directory path under the configured tag
-# (e.g. salt/beacon/<minion>/rules_beacon/suricata); the push_suricata / push_strelka
-# reactors write a push intent, after which the existing so-push-drainer /
-# orch.push_batch pipeline takes over unchanged.
+# (e.g. salt/beacon/<minion>/local_files_beacon/zeek); the push_files reactor
+# looks the tag up in salt/reactor/pillar_push_map.yaml and writes a push intent,
+# after which the existing so-push-drainer / orch.push_batch pipeline takes over
+# unchanged.
 
 import hashlib
 import logging
@@ -77,7 +79,9 @@ def _fingerprint(directory):
     h = hashlib.sha1()
     if os.path.isdir(directory):
         entries = []
-        for root, _dirs, files in os.walk(directory):
+        for root, dirs, files in os.walk(directory):
+            # zkg packages are git clones; .git churn would fire a state apply on its own.
+            dirs[:] = [d for d in dirs if d != '.git']
             for name in files:
                 full = os.path.join(root, name)
                 if _excluded(full):
@@ -94,20 +98,22 @@ def _fingerprint(directory):
     return h.hexdigest()
 
 
-def _watermark_file(tag):
-    return os.path.join(WATERMARK_DIR, 'rules_beacon_%s.hash' % tag)
+def _watermark_file(tag, directory):
+    # Keyed by directory: zeek/policy and zeek/zkg share the tag `zeek`.
+    scope = hashlib.sha1(directory.encode('utf-8', 'surrogateescape')).hexdigest()[:12]
+    return os.path.join(WATERMARK_DIR, 'local_files_beacon_%s_%s.hash' % (tag, scope))
 
 
-def _read_watermark(tag):
+def _read_watermark(tag, directory):
     try:
-        with open(_watermark_file(tag), 'r') as f:
+        with open(_watermark_file(tag, directory), 'r') as f:
             return (f.read() or '').strip() or None
     except IOError:
         return None
 
 
-def _write_watermark(tag, digest):
-    path = _watermark_file(tag)
+def _write_watermark(tag, directory, digest):
+    path = _watermark_file(tag, directory)
     try:
         os.makedirs(WATERMARK_DIR, exist_ok=True)
         tmp = path + '.tmp'
@@ -115,7 +121,7 @@ def _write_watermark(tag, digest):
             f.write(digest)
         os.rename(tmp, path)
     except OSError:
-        log.exception('rules_beacon: failed to persist watermark to %s', path)
+        log.exception('local_files_beacon: failed to persist watermark to %s', path)
 
 
 def beacon(config):
@@ -123,17 +129,17 @@ def beacon(config):
 
     for directory, tag in _paths_from_config(config).items():
         digest = _fingerprint(directory)
-        previous = _read_watermark(tag)
+        previous = _read_watermark(tag, directory)
 
         # First run / missing watermark: seed the digest and emit nothing so a
         # fresh host does not fire a spurious fleetwide push.
         if previous is None:
-            _write_watermark(tag, digest)
+            _write_watermark(tag, directory, digest)
             continue
 
         if digest != previous:
-            _write_watermark(tag, digest)
+            _write_watermark(tag, directory, digest)
             retval.append({'tag': tag, 'path': directory})
-            log.info('rules_beacon: change detected in %s, emitting %s', directory, tag)
+            log.info('local_files_beacon: change detected in %s, emitting %s', directory, tag)
 
     return retval

salt/_beacons/local_files_beacon_test.py

@@ -0,0 +1,221 @@
+# 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 hashlib
+import os
+import shutil
+import tempfile
+import unittest
+from unittest.mock import patch
+
+import local_files_beacon
+
+
+class TestRulesBeacon(unittest.TestCase):
+
+    def setUp(self):
+        # Isolate all on-disk state (watermarks and the dirs we fingerprint) in a
+        # throwaway tree, and point WATERMARK_DIR at it so the real read/write
+        # helpers run against actual files.
+        self.tmpdir = tempfile.mkdtemp()
+        self.state = os.path.join(self.tmpdir, 'state')
+        patcher = patch.object(local_files_beacon, 'WATERMARK_DIR', self.state)
+        patcher.start()
+        self.addCleanup(patcher.stop)
+
+    def tearDown(self):
+        shutil.rmtree(self.tmpdir, ignore_errors=True)
+
+    def _make_dir(self, name, files=None):
+        path = os.path.join(self.tmpdir, name)
+        os.makedirs(path, exist_ok=True)
+        for fname, content in (files or {}).items():
+            with open(os.path.join(path, fname), 'w') as f:
+                f.write(content)
+        return path
+
+    # -- trivial contract -------------------------------------------------
+
+    def test_virtual_returns_true(self):
+        self.assertTrue(local_files_beacon.__virtual__())
+
+    def test_validate_returns_valid(self):
+        self.assertEqual(local_files_beacon.validate({}), (True, 'valid'))
+
+    # -- _paths_from_config -----------------------------------------------
+
+    def test_paths_from_config_list_of_dicts(self):
+        config = [{'interval': 10}, {'paths': {'/a': 'suricata', '/b': 'strelka'}}]
+        self.assertEqual(
+            local_files_beacon._paths_from_config(config),
+            {'/a': 'suricata', '/b': 'strelka'},
+        )
+
+    def test_paths_from_config_plain_dict(self):
+        self.assertEqual(
+            local_files_beacon._paths_from_config({'paths': {'/a': 'suricata'}}),
+            {'/a': 'suricata'},
+        )
+
+    def test_paths_from_config_skips_non_dict_items(self):
+        self.assertEqual(local_files_beacon._paths_from_config(['bogus', 42]), {})
+
+    def test_paths_from_config_paths_not_a_dict(self):
+        self.assertEqual(local_files_beacon._paths_from_config({'paths': 'nope'}), {})
+
+    def test_paths_from_config_unexpected_type(self):
+        self.assertEqual(local_files_beacon._paths_from_config('nonsense'), {})
+
+    # -- _excluded --------------------------------------------------------
+
+    def test_excluded_matches_temp_and_editor_files(self):
+        for pathname in ('/rules/foo.swp', '/rules/foo~', '/rules/4913', '/rules/.#foo'):
+            self.assertTrue(local_files_beacon._excluded(pathname), pathname)
+
+    def test_excluded_allows_real_rule_files(self):
+        self.assertFalse(local_files_beacon._excluded('/rules/suricata.rules'))
+
+    # -- _fingerprint -----------------------------------------------------
+
+    def test_fingerprint_missing_dir_is_empty_tree_digest(self):
+        missing = os.path.join(self.tmpdir, 'does-not-exist')
+        self.assertEqual(local_files_beacon._fingerprint(missing), hashlib.sha1().hexdigest())
+
+    def test_fingerprint_changes_when_content_changes(self):
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        before = local_files_beacon._fingerprint(d)
+        with open(os.path.join(d, 'a.rules'), 'w') as f:
+            f.write('alert tcp any any -> any any')  # different size
+        self.assertNotEqual(local_files_beacon._fingerprint(d), before)
+
+    def test_fingerprint_ignores_excluded_files(self):
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        before = local_files_beacon._fingerprint(d)
+        with open(os.path.join(d, 'a.rules.swp'), 'w') as f:
+            f.write('editor swap')
+        self.assertEqual(local_files_beacon._fingerprint(d), before)
+
+    def test_fingerprint_skips_unstatable_entries(self):
+        # A dangling symlink appears in os.walk's file list but os.stat raises
+        # OSError, exercising the except-continue path.
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        good = local_files_beacon._fingerprint(d)
+        os.symlink(os.path.join(d, 'missing-target'), os.path.join(d, 'broken.link'))
+        self.assertEqual(local_files_beacon._fingerprint(d), good)
+
+    def test_fingerprint_prunes_git_metadata(self):
+        # zkg packages are git clones, so the watched tree carries .git.
+        d = self._make_dir('zkg', {'pkg.zeek': 'print 1;'})
+        before = local_files_beacon._fingerprint(d)
+        git_dir = os.path.join(d, 'pkg', '.git', 'refs', 'heads')
+        os.makedirs(git_dir)
+        with open(os.path.join(git_dir, 'main'), 'w') as f:
+            f.write('0' * 40)
+        self.assertEqual(local_files_beacon._fingerprint(d), before)
+
+    def test_fingerprint_still_sees_worktree_next_to_git(self):
+        d = self._make_dir('zkg', {'pkg.zeek': 'print 1;'})
+        os.makedirs(os.path.join(d, 'pkg', '.git'))
+        before = local_files_beacon._fingerprint(d)
+        with open(os.path.join(d, 'pkg', 'scripts.zeek'), 'w') as f:
+            f.write('print 2;')
+        self.assertNotEqual(local_files_beacon._fingerprint(d), before)
+
+    # -- _read_watermark / _write_watermark -------------------------------
+
+    def test_watermark_round_trip(self):
+        local_files_beacon._write_watermark('suricata', '/rules/suricata', 'deadbeef')
+        self.assertEqual(
+            local_files_beacon._read_watermark('suricata', '/rules/suricata'), 'deadbeef')
+
+    def test_read_watermark_missing_returns_none(self):
+        self.assertIsNone(local_files_beacon._read_watermark('suricata', '/rules/suricata'))
+
+    def test_read_watermark_empty_file_returns_none(self):
+        os.makedirs(self.state, exist_ok=True)
+        with open(local_files_beacon._watermark_file('suricata', '/rules/suricata'), 'w') as f:
+            f.write('')
+        self.assertIsNone(local_files_beacon._read_watermark('suricata', '/rules/suricata'))
+
+    def test_write_watermark_swallows_oserror(self):
+        with patch.object(local_files_beacon.os, 'makedirs', side_effect=OSError):
+            local_files_beacon._write_watermark('suricata', '/rules/suricata', 'deadbeef')
+        self.assertIsNone(local_files_beacon._read_watermark('suricata', '/rules/suricata'))
+
+    def test_watermark_file_differs_per_directory_within_one_tag(self):
+        # zeek/policy and zeek/zkg share the tag 'zeek'.
+        self.assertNotEqual(
+            local_files_beacon._watermark_file('zeek', '/local/zeek/policy'),
+            local_files_beacon._watermark_file('zeek', '/local/zeek/zkg'),
+        )
+
+    def test_watermarks_are_independent_within_one_tag(self):
+        local_files_beacon._write_watermark('zeek', '/local/zeek/policy', 'policyhash')
+        local_files_beacon._write_watermark('zeek', '/local/zeek/zkg', 'zkghash')
+        self.assertEqual(
+            local_files_beacon._read_watermark('zeek', '/local/zeek/policy'), 'policyhash')
+        self.assertEqual(
+            local_files_beacon._read_watermark('zeek', '/local/zeek/zkg'), 'zkghash')
+
+    # -- beacon -----------------------------------------------------------
+
+    def _config(self, mapping):
+        return [{'paths': mapping}]
+
+    def test_beacon_seeds_first_run_and_emits_nothing(self):
+        with patch.object(local_files_beacon, '_fingerprint', return_value='hash1'), \
+             patch.object(local_files_beacon, '_read_watermark', return_value=None), \
+             patch.object(local_files_beacon, '_write_watermark') as mock_write:
+            result = local_files_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
+        self.assertEqual(result, [])
+        mock_write.assert_called_once_with('suricata', '/rules/suricata', 'hash1')
+
+    def test_beacon_emits_on_change(self):
+        with patch.object(local_files_beacon, '_fingerprint', return_value='newhash'), \
+             patch.object(local_files_beacon, '_read_watermark', return_value='oldhash'), \
+             patch.object(local_files_beacon, '_write_watermark') as mock_write:
+            result = local_files_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
+        self.assertEqual(result, [{'tag': 'suricata', 'path': '/rules/suricata'}])
+        mock_write.assert_called_once_with('suricata', '/rules/suricata', 'newhash')
+
+    def test_beacon_no_change_emits_nothing(self):
+        with patch.object(local_files_beacon, '_fingerprint', return_value='samehash'), \
+             patch.object(local_files_beacon, '_read_watermark', return_value='samehash'), \
+             patch.object(local_files_beacon, '_write_watermark') as mock_write:
+            result = local_files_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
+        self.assertEqual(result, [])
+        mock_write.assert_not_called()
+
+    def test_beacon_end_to_end_with_real_files(self):
+        # Exercise the full stack (real fingerprint + real watermark files) across
+        # two poll passes: first seeds silently, second fires after a write.
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        config = self._config({d: 'suricata'})
+
+        self.assertEqual(local_files_beacon.beacon(config), [])  # seed pass
+        self.assertEqual(local_files_beacon.beacon(config), [])  # unchanged pass
+
+        with open(os.path.join(d, 'b.rules'), 'w') as f:
+            f.write('alert tcp any any -> any any')
+        self.assertEqual(local_files_beacon.beacon(config), [{'tag': 'suricata', 'path': d}])
+
+    def test_beacon_two_dirs_one_tag_do_not_flap(self):
+        # Tag-keyed watermarks would clobber each other and emit on every pass.
+        policy = self._make_dir('zeek/policy', {'intel.dat': '#fields\tindicator'})
+        zkg = self._make_dir('zeek/zkg', {'README': 'place packages here'})
+        config = self._config({policy: 'zeek', zkg: 'zeek'})
+
+        self.assertEqual(local_files_beacon.beacon(config), [])  # seed pass
+        self.assertEqual(local_files_beacon.beacon(config), [])  # idle
+        self.assertEqual(local_files_beacon.beacon(config), [])  # still idle
+
+        with open(os.path.join(policy, 'intel.dat'), 'a') as f:
+            f.write('\nevil.com\tIntel::DOMAIN\tsource\n')
+        self.assertEqual(local_files_beacon.beacon(config), [{'tag': 'zeek', 'path': policy}])
+        self.assertEqual(local_files_beacon.beacon(config), [])  # quiet again
+
+
+if __name__ == '__main__':
+    unittest.main()

salt/_beacons/rules_beacon_test.py

@@ -1,172 +0,0 @@
-# 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 hashlib
-import os
-import shutil
-import tempfile
-import unittest
-from unittest.mock import patch
-
-import rules_beacon
-
-
-class TestRulesBeacon(unittest.TestCase):
-
-    def setUp(self):
-        # Isolate all on-disk state (watermarks and the dirs we fingerprint) in a
-        # throwaway tree, and point WATERMARK_DIR at it so the real read/write
-        # helpers run against actual files.
-        self.tmpdir = tempfile.mkdtemp()
-        self.state = os.path.join(self.tmpdir, 'state')
-        patcher = patch.object(rules_beacon, 'WATERMARK_DIR', self.state)
-        patcher.start()
-        self.addCleanup(patcher.stop)
-
-    def tearDown(self):
-        shutil.rmtree(self.tmpdir, ignore_errors=True)
-
-    def _make_dir(self, name, files=None):
-        path = os.path.join(self.tmpdir, name)
-        os.makedirs(path, exist_ok=True)
-        for fname, content in (files or {}).items():
-            with open(os.path.join(path, fname), 'w') as f:
-                f.write(content)
-        return path
-
-    # -- trivial contract -------------------------------------------------
-
-    def test_virtual_returns_true(self):
-        self.assertTrue(rules_beacon.__virtual__())
-
-    def test_validate_returns_valid(self):
-        self.assertEqual(rules_beacon.validate({}), (True, 'valid'))
-
-    # -- _paths_from_config -----------------------------------------------
-
-    def test_paths_from_config_list_of_dicts(self):
-        config = [{'interval': 10}, {'paths': {'/a': 'suricata', '/b': 'strelka'}}]
-        self.assertEqual(
-            rules_beacon._paths_from_config(config),
-            {'/a': 'suricata', '/b': 'strelka'},
-        )
-
-    def test_paths_from_config_plain_dict(self):
-        self.assertEqual(
-            rules_beacon._paths_from_config({'paths': {'/a': 'suricata'}}),
-            {'/a': 'suricata'},
-        )
-
-    def test_paths_from_config_skips_non_dict_items(self):
-        self.assertEqual(rules_beacon._paths_from_config(['bogus', 42]), {})
-
-    def test_paths_from_config_paths_not_a_dict(self):
-        self.assertEqual(rules_beacon._paths_from_config({'paths': 'nope'}), {})
-
-    def test_paths_from_config_unexpected_type(self):
-        self.assertEqual(rules_beacon._paths_from_config('nonsense'), {})
-
-    # -- _excluded --------------------------------------------------------
-
-    def test_excluded_matches_temp_and_editor_files(self):
-        for pathname in ('/rules/foo.swp', '/rules/foo~', '/rules/4913', '/rules/.#foo'):
-            self.assertTrue(rules_beacon._excluded(pathname), pathname)
-
-    def test_excluded_allows_real_rule_files(self):
-        self.assertFalse(rules_beacon._excluded('/rules/suricata.rules'))
-
-    # -- _fingerprint -----------------------------------------------------
-
-    def test_fingerprint_missing_dir_is_empty_tree_digest(self):
-        missing = os.path.join(self.tmpdir, 'does-not-exist')
-        self.assertEqual(rules_beacon._fingerprint(missing), hashlib.sha1().hexdigest())
-
-    def test_fingerprint_changes_when_content_changes(self):
-        d = self._make_dir('rules', {'a.rules': 'alert'})
-        before = rules_beacon._fingerprint(d)
-        with open(os.path.join(d, 'a.rules'), 'w') as f:
-            f.write('alert tcp any any -> any any')  # different size
-        self.assertNotEqual(rules_beacon._fingerprint(d), before)
-
-    def test_fingerprint_ignores_excluded_files(self):
-        d = self._make_dir('rules', {'a.rules': 'alert'})
-        before = rules_beacon._fingerprint(d)
-        with open(os.path.join(d, 'a.rules.swp'), 'w') as f:
-            f.write('editor swap')
-        self.assertEqual(rules_beacon._fingerprint(d), before)
-
-    def test_fingerprint_skips_unstatable_entries(self):
-        # A dangling symlink appears in os.walk's file list but os.stat raises
-        # OSError, exercising the except-continue path.
-        d = self._make_dir('rules', {'a.rules': 'alert'})
-        good = rules_beacon._fingerprint(d)
-        os.symlink(os.path.join(d, 'missing-target'), os.path.join(d, 'broken.link'))
-        self.assertEqual(rules_beacon._fingerprint(d), good)
-
-    # -- _read_watermark / _write_watermark -------------------------------
-
-    def test_watermark_round_trip(self):
-        rules_beacon._write_watermark('suricata', 'deadbeef')
-        self.assertEqual(rules_beacon._read_watermark('suricata'), 'deadbeef')
-
-    def test_read_watermark_missing_returns_none(self):
-        self.assertIsNone(rules_beacon._read_watermark('suricata'))
-
-    def test_read_watermark_empty_file_returns_none(self):
-        os.makedirs(self.state, exist_ok=True)
-        with open(rules_beacon._watermark_file('suricata'), 'w') as f:
-            f.write('')
-        self.assertIsNone(rules_beacon._read_watermark('suricata'))
-
-    def test_write_watermark_swallows_oserror(self):
-        with patch.object(rules_beacon.os, 'makedirs', side_effect=OSError):
-            rules_beacon._write_watermark('suricata', 'deadbeef')
-        self.assertIsNone(rules_beacon._read_watermark('suricata'))
-
-    # -- beacon -----------------------------------------------------------
-
-    def _config(self, mapping):
-        return [{'paths': mapping}]
-
-    def test_beacon_seeds_first_run_and_emits_nothing(self):
-        with patch.object(rules_beacon, '_fingerprint', return_value='hash1'), \
-             patch.object(rules_beacon, '_read_watermark', return_value=None), \
-             patch.object(rules_beacon, '_write_watermark') as mock_write:
-            result = rules_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
-        self.assertEqual(result, [])
-        mock_write.assert_called_once_with('suricata', 'hash1')
-
-    def test_beacon_emits_on_change(self):
-        with patch.object(rules_beacon, '_fingerprint', return_value='newhash'), \
-             patch.object(rules_beacon, '_read_watermark', return_value='oldhash'), \
-             patch.object(rules_beacon, '_write_watermark') as mock_write:
-            result = rules_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
-        self.assertEqual(result, [{'tag': 'suricata', 'path': '/rules/suricata'}])
-        mock_write.assert_called_once_with('suricata', 'newhash')
-
-    def test_beacon_no_change_emits_nothing(self):
-        with patch.object(rules_beacon, '_fingerprint', return_value='samehash'), \
-             patch.object(rules_beacon, '_read_watermark', return_value='samehash'), \
-             patch.object(rules_beacon, '_write_watermark') as mock_write:
-            result = rules_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
-        self.assertEqual(result, [])
-        mock_write.assert_not_called()
-
-    def test_beacon_end_to_end_with_real_files(self):
-        # Exercise the full stack (real fingerprint + real watermark files) across
-        # two poll passes: first seeds silently, second fires after a write.
-        d = self._make_dir('rules', {'a.rules': 'alert'})
-        config = self._config({d: 'suricata'})
-
-        self.assertEqual(rules_beacon.beacon(config), [])  # seed pass
-        self.assertEqual(rules_beacon.beacon(config), [])  # unchanged pass
-
-        with open(os.path.join(d, 'b.rules'), 'w') as f:
-            f.write('alert tcp any any -> any any')
-        self.assertEqual(rules_beacon.beacon(config), [{'tag': 'suricata', 'path': d}])
-
-
-if __name__ == '__main__':
-    unittest.main()

salt/common/init.sls

@@ -117,14 +117,25 @@ elastic_curl_config:
 {% endif %}
 
 
+# A non-root owner here can chmod the directory and replace any script in it, including
+# the root-owned ones. 555 is the mode the filesystem RPM ships; root ignores it anyway.
+usr_sbin_perms:
+  file.directory:
+    - name: /usr/sbin
+    - user: root
+    - group: root
+    - mode: 555
+
 common_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://common/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - show_changes: False
+    - require:
+      - file: usr_sbin_perms
 {% if GLOBALS.role == 'so-heavynode' %}
     - exclude_pat:
       - so-pcap-import
@@ -159,8 +170,8 @@ common_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://common/tools/sbin_jinja
-    - user: 939
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - show_changes: False
@@ -173,6 +184,8 @@ so-status_script:
   file.managed:
     - name: /usr/sbin/so-status
     - source: salt://common/tools/sbin/so-status
+    - user: root
+    - group: root
     - mode: 755
 
 {% if GLOBALS.is_sensor %}
@@ -204,9 +217,11 @@ sostatus_log:
     - replace: False
 
 # Install sostatus check cron. This is used to populate Grid.
+# telegraf reads status.log on the same minute boundary this runs, so write aside and rename
+# rather than truncating the file it is reading
 so-status_check_cron:
   cron.present:
-    - name: '/usr/sbin/so-status -j > /opt/so/log/sostatus/status.log 2>&1'
+    - name: '/usr/sbin/so-status -j > /opt/so/log/sostatus/status.log.tmp 2>&1; mv -f /opt/so/log/sostatus/status.log.tmp /opt/so/log/sostatus/status.log'
     - identifier: so-status_check_cron
     - user: root
     - minute: '*/1'

salt/common/soup_scripts.sls

@@ -18,47 +18,61 @@ copy_so-common_common_tools_sbin:
     - name: /opt/so/saltstack/default/salt/common/tools/sbin/so-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-image-common_common_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/common/tools/sbin/so-image-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-image-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_soup_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/soup
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/soup
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-firewall_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-firewall
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-firewall
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-yaml_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-yaml.py
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-yaml.py
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-repo-sync_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-repo-sync
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-repo-sync
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_bootstrap-salt_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/salt/scripts/bootstrap-salt.sh
     - source: {{UPDATE_DIR}}/salt/salt/scripts/bootstrap-salt.sh
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 644
 
 # This section is used to put the new script in place so that it can be called during soup.
 # It is faster than calling the states that normally manage them to put them in place.
@@ -67,46 +81,60 @@ copy_so-common_sbin:
     - name: /usr/sbin/so-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-image-common_sbin:
   file.copy:
     - name: /usr/sbin/so-image-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-image-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_soup_sbin:
   file.copy:
     - name: /usr/sbin/soup
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/soup
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-firewall_sbin:
   file.copy:
     - name: /usr/sbin/so-firewall
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-firewall
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-yaml_sbin:
   file.copy:
     - name: /usr/sbin/so-yaml.py
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-yaml.py
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-repo-sync_sbin:
   file.copy:
     - name: /usr/sbin/so-repo-sync
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-repo-sync
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_bootstrap-salt_sbin:
   file.copy:
     - name: /usr/sbin/bootstrap-salt.sh
     - source: {{UPDATE_DIR}}/salt/salt/scripts/bootstrap-salt.sh
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755

salt/common/tools/sbin/so-common

@@ -240,7 +240,8 @@ copy_new_files() {
   cd $UPDATE_DIR
   rsync -a salt $DEFAULT_SALT_DIR/ --delete "${EXCLUDE_ARGS[@]}"
   rsync -a pillar $DEFAULT_SALT_DIR/ --delete "${EXCLUDE_ARGS[@]}"
-  chown -R socore:socore $DEFAULT_SALT_DIR/
+  # Root-executed code; SOC only needs to read it. Local dirs stay socore-owned.
+  chown -R root:root $DEFAULT_SALT_DIR/
   cd /tmp
 }
 
@@ -418,6 +419,19 @@ is_single_node_grid() {
 	grep "role: so-" /etc/salt/grains | grep -E "eval|standalone|import" &> /dev/null
 }
 
+remove_elasticsearch_index_template() {
+  local template_name=$1
+  local reason=${2:-"Removing index template for upgrade"}
+
+  # check if template exists
+  if so-elasticsearch-query "_index_template/$template_name" --fail --retry 3 --retry-delay 5 >/dev/null 2>&1; then
+    echo "Removing Elasticsearch index template: $template_name ($reason)"
+    if ! so-elasticsearch-query "_index_template/$template_name" -XDELETE --fail --retry 3 --retry-delay 5; then
+      return 1
+    fi
+  fi
+}
+
 initialize_elasticsearch_indices() {
     local index_names=$1
     local default_entry=${2:-'{"@timestamp":"0"}'}

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

@@ -9,6 +9,7 @@ import sys
 import subprocess
 import os
 import json
+import tempfile
 
 sys.path.append('/opt/saltstack/salt/lib/python3.10/site-packages/')
 import salt.config
@@ -17,6 +18,21 @@ import salt.loader
 __opts__ = salt.config.minion_config('/etc/salt/minion')
 __grains__ = salt.loader.grains(__opts__)
 
+def write_atomic(path, value):
+  # telegraf reads these files on its own schedule; replacing them by rename means it never
+  # reads a truncated file and reports an empty value as if it were real
+  directory = os.path.dirname(path)
+  handle, temp = tempfile.mkstemp(dir=directory)
+  try:
+    with os.fdopen(handle, 'w') as f:
+      f.write(str(value))
+    os.chmod(temp, 0o644)
+    os.replace(temp, path)
+  except Exception:
+    os.path.exists(temp) and os.unlink(temp)
+    raise
+
+
 def check_needs_restarted():
   osfam = __grains__['os_family']
   val = '0'
@@ -34,8 +50,7 @@ def check_needs_restarted():
   else:
     fail("Unsupported OS")
 
-  with open(outfile, 'w') as f:
-    f.write(val)
+  write_atomic(outfile, val)
 
 def check_for_fps():
     feat = 'fps'
@@ -56,8 +71,7 @@ def check_for_fps():
           # Unknown, so assume 0
           fps = 0
 
-    with open('/opt/so/log/sostatus/fps_enabled', 'w') as f:
-       f.write(str(fps))
+    write_atomic('/opt/so/log/sostatus/fps_enabled', fps)
 
 def check_for_lks():
     feat = 'Lks'
@@ -80,8 +94,7 @@ def check_for_lks():
                                 lks = 1
         if lks:
             break
-    with open('/opt/so/log/sostatus/lks_enabled', 'w') as f:
-       f.write(str(lks))
+    write_atomic('/opt/so/log/sostatus/lks_enabled', lks)
 
 def fail(msg):
   print(msg, file=sys.stderr)

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

@@ -134,6 +134,7 @@ if [[ $EXCLUDE_STARTUP_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Redis may have been restarted" # Redis likely restarted by salt
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|file already closed"          # Go logging race condition during container restart
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|relation \"audit_settings\" does not exist" # salt checking for changes before SOC starts
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Error in plugin: elasticsearch: Unable to retrieve master node information" # expected error while ES is upgrading/electing a master 
 fi
 
 if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
@@ -176,6 +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
@@ -240,6 +242,7 @@ if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$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|Could not index event to Elasticsearch.*\"version\" => \"9.0.8\"" # Expected during Elastic upgrade temporarily, as policies referencing older pipelines are updated
 fi
 
 RESULT=0
@@ -304,4 +307,4 @@ else
     echo -e "\nResult: One or more errors found"
 fi
 
-exit $RESULT
+exit $RESULT

salt/common/tools/sbin/so-sensor-clean

@@ -8,21 +8,37 @@
 # Elastic License 2.0.
 
 
-SENSOR_DIR='/nsm'
+SENSOR_DIR="${SENSOR_DIR:-/nsm}"
 CRIT_DISK_USAGE=90
-CUR_USAGE=$(df -P $SENSOR_DIR | tail -1 | awk '{print $5}' | tr -d %)
-LOG="/opt/so/log/sensor_clean.log"
-TODAY=$(date -u "+%Y-%m-%d")
+LOG="${LOG:-/opt/so/log/sensor_clean.log}"
+LOCK="${LOCK:-/var/tmp/so-sensor-clean.lock}"
+MAX_PASSES=100
 
+ZEEK_LOGS="$SENSOR_DIR/zeek/logs"
+STRELKA_FILES="$SENSOR_DIR/strelka/processed"
+SURICATA_LOGS="$SENSOR_DIR/suricata"
+PCAPS="$SENSOR_DIR/pcapout"
+
+log() {
+	echo "$(date) - $*" >>"$LOG"
+}
+
+disk_usage() {
+	df -P "$SENSOR_DIR" | tail -1 | awk '{print $5}' | tr -d %
+}
+
+disk_avail() {
+	df -P "$SENSOR_DIR" | tail -1 | awk '{print $4}'
+}
+
+# sets REMOVED=1 if anything was actually deleted
 clean() {
 	## find the oldest Zeek logs directory
-	OLDEST_DIR=$(ls /nsm/zeek/logs/ | grep -v "current" | grep -v "stats" | grep -v "packetloss" | grep -v "zeek_clean" | sort | head -n 1)
-	if [ -z "$OLDEST_DIR" -o "$OLDEST_DIR" == ".." -o "$OLDEST_DIR" == "." ]; then
-		echo "$(date) - No old Zeek logs available to clean up in /nsm/zeek/logs/" >>$LOG
-		#exit 0
-	else
-		echo "$(date) - Removing directory: /nsm/zeek/logs/$OLDEST_DIR" >>$LOG
-		rm -rf /nsm/zeek/logs/"$OLDEST_DIR"
+	OLDEST_DIR=$(ls "$ZEEK_LOGS" 2>/dev/null | grep -v "current" | grep -v "stats" | grep -v "packetloss" | grep -v "zeek_clean" | sort | head -n 1)
+	if [ -n "$OLDEST_DIR" ]; then
+		log "Removing directory: $ZEEK_LOGS/$OLDEST_DIR"
+		rm -rf "$ZEEK_LOGS/$OLDEST_DIR"
+		REMOVED=1
 	fi
 
 	## Remarking for now, as we are moving extracted files to /nsm/strelka/processed
@@ -43,58 +59,73 @@ clean() {
 	#fi
 
 	## Clean up Zeek extracted files processed by Strelka
-	STRELKA_FILES='/nsm/strelka/processed'
-	OLDEST_STRELKA=$(find $STRELKA_FILES -type f -printf '%T+ %p\n' | sort -n | head -n 1)
-	if [ -z "$OLDEST_STRELKA" -o "$OLDEST_STRELKA" == ".." -o "$OLDEST_STRELKA" == "." ]; then
-		echo "$(date) - No old files available to clean up in $STRELKA_FILES" >>$LOG
-	else
+	OLDEST_STRELKA=$(find "$STRELKA_FILES" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
+	if [ -n "$OLDEST_STRELKA" ]; then
 		OLDEST_STRELKA_DATE=$(echo $OLDEST_STRELKA | awk '{print $1}' | cut -d+ -f1)
-		OLDEST_STRELKA_FILE=$(echo $OLDEST_STRELKA | awk '{print $2}')
-		echo "$(date) - Removing extracted files for $OLDEST_STRELKA_DATE" >>$LOG
-		find $STRELKA_FILES -type f -printf '%T+ %p\n' | grep $OLDEST_STRELKA_DATE | awk '{print $2}' | while read FILE; do
-			echo "$(date) - Removing file: $FILE" >>$LOG
+		log "Removing extracted files for $OLDEST_STRELKA_DATE"
+		REMOVED=1
+		find "$STRELKA_FILES" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_STRELKA_DATE | awk '{print $2}' | while read FILE; do
+			log "Removing file: $FILE"
 			rm -f "$FILE"
 		done
 	fi
 
 	## Clean up Suricata log files
-	SURICATA_LOGS='/nsm/suricata'
-	OLDEST_SURICATA=$(find $SURICATA_LOGS -type f -printf '%T+ %p\n' | sort -n | head -n 1)
-	if [[ -z "$OLDEST_SURICATA" ]] || [[ "$OLDEST_SURICATA" == ".." ]] || [[ "$OLDEST_SURICATA" == "." ]]; then
-		echo "$(date) - No old files available to clean up in $SURICATA_LOGS" >>$LOG
-	else
+	OLDEST_SURICATA=$(find "$SURICATA_LOGS" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
+	if [ -n "$OLDEST_SURICATA" ]; then
 		OLDEST_SURICATA_DATE=$(echo $OLDEST_SURICATA | awk '{print $1}' | cut -d+ -f1)
-		OLDEST_SURICATA_FILE=$(echo $OLDEST_SURICATA | awk '{print $2}')
-		echo "$(date) - Removing logs for $OLDEST_SURICATA_DATE" >>$LOG
-		find $SURICATA_LOGS -type f -printf '%T+ %p\n' | grep $OLDEST_SURICATA_DATE | awk '{print $2}' | while read FILE; do
-			echo "$(date) - Removing file: $FILE" >>$LOG
+		log "Removing logs for $OLDEST_SURICATA_DATE"
+		REMOVED=1
+		find "$SURICATA_LOGS" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_SURICATA_DATE | awk '{print $2}' | while read FILE; do
+			log "Removing file: $FILE"
 			rm -f "$FILE"
 		done
 	fi
 
 	## Clean up extracted pcaps
-	PCAPS='/nsm/pcapout'
-	OLDEST_PCAP=$(find $PCAPS -type f -printf '%T+ %p\n' | sort -n | head -n 1)
-	if [ -z "$OLDEST_PCAP" -o "$OLDEST_PCAP" == ".." -o "$OLDEST_PCAP" == "." ]; then
-		echo "$(date) - No old files available to clean up in $PCAPS" >>$LOG
-	else
+	OLDEST_PCAP=$(find "$PCAPS" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
+	if [ -n "$OLDEST_PCAP" ]; then
 		OLDEST_PCAP_DATE=$(echo $OLDEST_PCAP | awk '{print $1}' | cut -d+ -f1)
-		OLDEST_PCAP_FILE=$(echo $OLDEST_PCAP | awk '{print $2}')
-		echo "$(date) - Removing extracted files for $OLDEST_PCAP_DATE" >>$LOG
-		find $PCAPS -type f -printf '%T+ %p\n' | grep $OLDEST_PCAP_DATE | awk '{print $2}' | while read FILE; do
-			echo "$(date) - Removing file: $FILE" >>$LOG
+		log "Removing extracted files for $OLDEST_PCAP_DATE"
+		REMOVED=1
+		find "$PCAPS" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_PCAP_DATE | awk '{print $2}' | while read FILE; do
+			log "Removing file: $FILE"
 			rm -f "$FILE"
 		done
 	fi
 }
 
-# Check to see if we are already running
-NUM_RUNNING=$(pgrep -cf "/bin/bash /usr/sbin/so-sensor-clean")
-[ "$NUM_RUNNING" -gt 1 ] && echo "$(date) - $NUM_RUNNING sensor clean script processes running...exiting." >>$LOG && exit 0
-
-if [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; then
-	while [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; do
-		clean
-		CUR_USAGE=$(df -P $SENSOR_DIR | tail -1 | awk '{print $5}' | tr -d %)
-	done
+# Only one instance at a time; the lock is the fd, so it releases on any exit
+exec 9>"$LOCK" || exit 1
+if ! flock -n 9; then
+	log "another so-sensor-clean is already running (lock $LOCK held); exiting"
+	exit 0
 fi
+
+CUR_USAGE=$(disk_usage)
+[ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ] || exit 0
+
+log "$SENSOR_DIR at ${CUR_USAGE}% (threshold ${CRIT_DISK_USAGE}%); starting cleanup"
+
+PASS=0
+while [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; do
+	PASS=$((PASS + 1))
+	if [ "$PASS" -gt "$MAX_PASSES" ]; then
+		log "stopping after $MAX_PASSES passes; $SENSOR_DIR still at ${CUR_USAGE}%"
+		break
+	fi
+
+	REMOVED=0
+	BEFORE=$(disk_avail)
+	clean
+	CUR_USAGE=$(disk_usage)
+
+	if [ "$REMOVED" -eq 0 ]; then
+		log "nothing left to remove in $ZEEK_LOGS, $STRELKA_FILES, $SURICATA_LOGS, $PCAPS; $SENSOR_DIR still at ${CUR_USAGE}% - space is consumed outside of NSM cleanup scope"
+		break
+	fi
+	if [ "$(disk_avail)" -le "$BEFORE" ]; then
+		log "pass $PASS freed no space; $SENSOR_DIR still at ${CUR_USAGE}% - stopping until next run"
+		break
+	fi
+done

salt/common/tools/sbin_jinja/so-raid-status

@@ -125,4 +125,6 @@ else
   RAIDSTATUS=1
 fi
 
-echo "nsmraid=$RAIDSTATUS" > /opt/so/log/raid/status.log
+# telegraf reads this file; write aside and rename so it never sees a half-written file
+echo "nsmraid=$RAIDSTATUS" > /opt/so/log/raid/status.log.tmp
+mv -f /opt/so/log/raid/status.log.tmp /opt/so/log/raid/status.log

salt/docker/defaults.yaml

@@ -1,6 +1,12 @@
 docker:
   range: '172.17.1.0/24'
   gateway: '172.17.1.1'
+  networks:
+    sobridge: {}
+    soauth:
+      range: '172.17.2.0/24'
+      gateway: '172.17.2.1'
+      manager_only: True
   ulimits:
     - name: nofile
       soft: 1048576
@@ -58,18 +64,18 @@ docker:
       ulimits: []
     'so-kratos':
       final_octet: 28
+      networks: ['soauth']
       port_bindings:
         - 0.0.0.0:4433:4433
-        - 0.0.0.0:4434:4434
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
       ulimits: []
     'so-hydra':
       final_octet: 30
+      networks: ['soauth']
       port_bindings:
         - 0.0.0.0:4444:4444
-        - 0.0.0.0:4445:4445
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
@@ -128,6 +134,7 @@ docker:
       ulimits: []
     'so-soc':
       final_octet: 34
+      networks: ['sobridge', 'soauth']
       port_bindings:
         - 0.0.0.0:9822:9822
       custom_bind_mounts: []

salt/docker/docker.map.jinja

@@ -1,8 +1,26 @@
 {% import_yaml 'docker/defaults.yaml' as DOCKERDEFAULTS %}
 {% set DOCKERMERGED = salt['pillar.get']('docker', DOCKERDEFAULTS.docker, merge=True) %}
-{% set RANGESPLIT = DOCKERMERGED.range.split('.') %}
-{% set FIRSTTHREE = RANGESPLIT[0] ~ '.' ~ RANGESPLIT[1] ~ '.' ~ RANGESPLIT[2] ~ '.' %}
+
+{% if DOCKERMERGED.networks.sobridge is not mapping %}
+{%   do DOCKERMERGED.networks.update({'sobridge': {}}) %}
+{% endif %}
+{% do DOCKERMERGED.networks['sobridge'].update({'range': DOCKERMERGED.range, 'gateway': DOCKERMERGED.gateway}) %}
+
+{% for netname, net in DOCKERMERGED.networks.items() %}
+{%   set RANGESPLIT = net.range.split('.') %}
+{%   do net.update({'prefix': RANGESPLIT[0] ~ '.' ~ RANGESPLIT[1] ~ '.' ~ RANGESPLIT[2] ~ '.'}) %}
+{% endfor %}
 
 {% for container, vals in DOCKERMERGED.containers.items() %}
-{%   do DOCKERMERGED.containers[container].update({'ip': FIRSTTHREE ~ DOCKERMERGED.containers[container].final_octet}) %}
+{%   set CONTAINER_NETS = vals.get('networks', ['sobridge']) %}
+{%   set IPS = {} %}
+{%   for netname in CONTAINER_NETS %}
+{%     do IPS.update({netname: DOCKERMERGED.networks[netname].prefix ~ vals.final_octet}) %}
+{%   endfor %}
+{%   do DOCKERMERGED.containers[container].update({
+         'networks': CONTAINER_NETS,
+         'ips': IPS,
+         'network': CONTAINER_NETS[0],
+         'ip': IPS[CONTAINER_NETS[0]]
+       }) %}
 {% endfor %}

salt/docker/init.sls

@@ -71,15 +71,19 @@ dockerreserveports:
     - source: salt://common/files/99-reserved-ports.conf
     - name: /etc/sysctl.d/99-reserved-ports.conf
 
-sos_docker_net:
+{% for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
+{% if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
+sos_docker_net_{{ NETNAME }}:
   docker_network.present:
-    - name: sobridge
-    - subnet: {{ DOCKERMERGED.range }}
-    - gateway: {{ DOCKERMERGED.gateway }}
+    - name: {{ NETNAME }}
+    - subnet: {{ NETWORK.range }}
+    - gateway: {{ NETWORK.gateway }}
     - options:
-        com.docker.network.bridge.name: 'sobridge'
+        com.docker.network.bridge.name: '{{ NETNAME }}'
         com.docker.network.driver.mtu: '1500'
         com.docker.network.bridge.enable_ip_masquerade: 'true'
         com.docker.network.bridge.enable_icc: 'true'
         com.docker.network.bridge.host_binding_ipv4: '0.0.0.0'
-    - unless: ip l | grep sobridge
+    - unless: ip l | grep {{ NETNAME }}
+{% endif %}
+{% endfor %}

salt/docker/soc_docker.yaml

@@ -7,6 +7,40 @@ docker:
     description: Default docker IP range for containers.
     helpLink: docker
     advanced: True
+  networks:
+    sobridge:
+      description: |
+        The default docker network, carrying most containers. Its range and gateway are taken
+        from the docker.range and docker.gateway settings above rather than set here.
+      helpLink: docker
+      readonly: True
+      advanced: True
+      global: True
+    soauth:
+      range:
+        description: |
+          IP range for the soauth docker network, an isolated network for the authentication
+          services, so that the Kratos and Hydra admin APIs are only reachable from the
+          containers placed on it.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+      gateway:
+        description: Gateway for the soauth docker network.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+      manager_only:
+        description: |
+          Limits the soauth network to grid members running the authentication containers,
+          instead of creating it on every node.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+        forcedType: bool
   ulimits:
     description: |
       Default ulimit settings applied to all containers via the Docker daemon. Each entry specifies a resource name (e.g. nofile, memlock, core, nproc) with soft and hard limits. Individual container ulimits override these defaults. Valid resource names include: cpu, fsize, data, stack, core, rss, nproc, nofile, memlock, as, locks, sigpending, msgqueue, nice, rtprio, rttime.
@@ -34,6 +68,16 @@ docker:
         readonly: True
         advanced: True
         global: True
+      networks:
+        description: |
+          Docker networks this container is attached to. The first entry is the container's
+          primary network and determines the address its published ports are forwarded to.
+          Defaults to sobridge when unset.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+        forcedType: "[]string"
       port_bindings:
         description: List of port bindings for the container.
         helpLink: docker

salt/elastalert/config.sls

@@ -21,6 +21,7 @@ elastalert:
     - gid: 933
     - home: /opt/so/conf/elastalert
     - createhome: False
+    - shell: /sbin/nologin
 
 elastalogdir:
   file.directory:
@@ -33,8 +34,8 @@ elastalert_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elastalert/tools/sbin
-    - user: 933
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #elastalert_sbin_jinja:

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:
@@ -39,8 +40,8 @@ elasticagent_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticagent/tools/sbin_jinja
-    - user: 949
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
 

salt/elasticfleet/config.sls

@@ -26,13 +26,14 @@ elastic-fleet:
     - gid: 947
     - home: /opt/so/conf/elastic-fleet
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticfleet_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticfleet/tools/sbin
-    - user: 947
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - show_changes: False
 
@@ -40,8 +41,8 @@ elasticfleet_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticfleet/tools/sbin_jinja
-    - user: 947
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - exclude_pat:
@@ -81,8 +82,8 @@ eapackageupgrade:
   file.managed:
     - name: /usr/sbin/so-elastic-fleet-package-upgrade
     - source: salt://elasticfleet/tools/sbin_jinja/so-elastic-fleet-package-upgrade
-    - user: 947
-    - group: 939
+    - user: root
+    - group: root
     - mode: 755
     - template: jinja
 

salt/elasticfleet/files/integrations/elastic-defend/elastic-defend-endpoints.json

@@ -5,7 +5,7 @@
   "package": {
     "name": "endpoint",
     "title": "Elastic Defend",
-    "version": "9.3.1",
+    "version": "9.4.1",
     "requires_root": true
   },
   "enabled": true,

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-2.20.0\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-3.8.3\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-2.20.0\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-2.20.0\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-3.8.3\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-2.22.3\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",
             "tags": [
               "import"
             ],

salt/elasticfleet/install_agent_grid.sls

@@ -14,8 +14,8 @@ so-elastic-agent-install:
   file.managed:
     - name: /usr/sbin/so-elastic-agent-install
     - source: salt://elasticfleet/tools/sbin/so-elastic-agent-install
-    - user: 947
-    - group: 939
+    - user: root
+    - group: root
     - mode: 755
     - show_changes: False
 

salt/elasticfleet/integration-defaults.map.jinja

@@ -16,7 +16,6 @@
     'awsfirehose.metrics': 'aws.cloudwatch',
     'cribl.logs': 'cribl',
     'cribl.metrics': 'cribl',
-    'sentinel_one_cloud_funnel.logins': 'sentinel_one_cloud_funnel.login',
     'azure_application_insights.app_insights': 'azure.app_insights',
     'azure_application_insights.app_state': 'azure.app_state',
     'azure_billing.billing': 'azure.billing',

salt/elasticfleet/manager.sls

@@ -68,6 +68,24 @@ so-elastic-fleet-package-upgrade:
     - require:
       - http: wait_for_so-kibana
 
+# initial so-elasticsearch-templates run is earlier, but it can skip over templates that have component templates not yet installed to avoid elasticsearch rejecting the template.
+so-elasticsearch-templates-after-fleet-packages:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-templates-load
+    - cwd: /opt/so
+    - unless: test -f /opt/so/state/estemplates.txt
+    - require:
+      - cmd: so-elastic-fleet-package-upgrade
+
+so-elastic-fleet-integration-upgrade:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-fleet-integration-upgrade
+    - retry:
+        attempts: 3
+        interval: 10
+    - require:
+      - cmd: so-elastic-fleet-package-upgrade
+
 so-elastic-fleet-integrations:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-integration-policy-load
@@ -86,21 +104,13 @@ so-elastic-agent-grid-upgrade:
     - require:
       - http: wait_for_so-kibana
 
-so-elastic-fleet-integration-upgrade:
-  cmd.run:
-    - name: /usr/sbin/so-elastic-fleet-integration-upgrade
-    - retry:
-        attempts: 3
-        interval: 10
-    - require:
-      - http: wait_for_so-kibana
-
 {# 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
     - require:
       - http: wait_for_so-kibana
+      - cmd: so-elasticsearch-templates-after-fleet-packages
 
 {% if ELASTICFLEETMERGED.config.defend_filters.enable_auto_configuration %}
 so-elastic-defend-manage-filters-file-watch:

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

@@ -30,6 +30,56 @@ fleet_api() {
     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_require_agent_policy() {
+    local AGENT_POLICY=$1
+    local POLICY_JSON
+
+    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY") || [ -z "$POLICY_JSON" ]; then
+        echo "Error: Agent policy '$AGENT_POLICY' was not found or is not visible in the current Kibana space." >&2
+        return 1
+    fi
+
+    if ! jq -e '.item.package_policies | type == "array"' <<<"$POLICY_JSON" >/dev/null 2>&1; then
+        echo "Error: Agent policy '$AGENT_POLICY' was not found or is not visible in the current Kibana space." >&2
+        return 1
+    fi
+
+    echo "$POLICY_JSON"
+}
+
+# Print the single active enrollment token for POLICY_ID.
+# Exit 1: retryable (API failure, invalid response, no active token)
+# Exit 2: multiple active tokens - Shouldn't get into this state without manual intervention
+elastic_fleet_active_enrollment_token() {
+    local POLICY_ID=$1
+    local RESP TOKEN_COUNT API_KEY
+
+    if ! RESP=$(fleet_api "enrollment_api_keys?perPage=100" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+        echo "Error: Failed to retrieve enrollment tokens for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    if ! jq -e '.list' <<<"$RESP" >/dev/null 2>&1; then
+        echo "Error: Invalid enrollment token response for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    TOKEN_COUNT=$(jq --arg pid "$POLICY_ID" '[.list[] | select(.policy_id == $pid and .active == true)] | length' <<<"$RESP")
+
+    if [ "${TOKEN_COUNT:-0}" -eq 0 ]; then
+        echo "Error: No active enrollment token found for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    if [ "$TOKEN_COUNT" -gt 1 ]; then
+        echo "Error: Found $TOKEN_COUNT active enrollment tokens for agent policy '$POLICY_ID'; expected exactly one." >&2
+        return 2
+    fi
+
+    API_KEY=$(jq -r --arg pid "$POLICY_ID" '.list[] | select(.policy_id == $pid and .active == true) | .api_key' <<<"$RESP")
+    echo "$API_KEY"
+}
+
 # Max number of concurrent Fleet write jobs (create/update). Override via env if needed.
 MAX_FLEET_JOBS=${MAX_FLEET_JOBS:-10}
 
@@ -62,15 +112,7 @@ elastic_fleet_load_integrations_dir() {
     i=0
 
     # Fetch the agent policy a single time; we look up integration ids locally below.
-    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY"); then
-        echo "Error: Failed to retrieve agent policy '$AGENT_POLICY'."
-        rm -f "$FAIL_FILE"
-        rm -rf "$OUT_DIR"
-        return 1
-    fi
-
-    if ! jq -e '.item.package_policies' <<<"$POLICY_JSON" >/dev/null 2>&1; then
-        echo "Error: Invalid agent policy response for '$AGENT_POLICY'."
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
         rm -f "$FAIL_FILE"
         rm -rf "$OUT_DIR"
         return 1
@@ -124,9 +166,15 @@ elastic_fleet_integration_check() {
 
     JSON_STRING=$2
 
-    NAME=$(jq -r .name $JSON_STRING)
+    NAME=$(jq -r .name "$JSON_STRING")
+    INTEGRATION_ID=""
 
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$AGENT_POLICY" | jq -r '.item.package_policies[] | select(.name=="'"$NAME"'") | .id')
+    local POLICY_JSON
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
+        return 1
+    fi
+
+    INTEGRATION_ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
 
 }
 
@@ -148,7 +196,16 @@ elastic_fleet_integration_remove() {
 
     NAME=$2
 
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$AGENT_POLICY" | jq -r '.item.package_policies[] | select(.name=="'"$NAME"'") | .id')
+    local POLICY_JSON
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
+        return 1
+    fi
+
+    INTEGRATION_ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
+    if [ -z "$INTEGRATION_ID" ]; then
+        echo "Error: Integration '$NAME' was not found in agent policy '$AGENT_POLICY'." >&2
+        return 1
+    fi
 
     JSON_STRING=$( jq -n \
                     --arg INTEGRATIONID "$INTEGRATION_ID" \

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

@@ -13,7 +13,10 @@ ERROR=false
 for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/elastic-defend/*.json
 do
   printf "\n\nInitial Endpoints Policy - Loading $INTEGRATION\n"
-  elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
+  if ! elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"; then
+    ERROR=true
+    continue
+  fi
   if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Upgrading integration policy\n"
       if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then

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

@@ -7,20 +7,35 @@
 . /usr/sbin/so-elastic-fleet-common
 
 # Get all the fleet policies
-json_output=$(curl -s -K /opt/so/conf/elasticsearch/curl.config -L -X GET "localhost:5601/api/fleet/agent_policies" -H 'kbn-xsrf: true')
+if ! json_output=$(fleet_api "agent_policies" -H 'kbn-xsrf: true'); then
+    echo "Error: Failed to retrieve Fleet agent policies." >&2
+    exit 1
+fi
+
+if ! jq -e '.items' <<<"$json_output" >/dev/null 2>&1; then
+    echo "Error: Invalid Fleet agent policies response." >&2
+    exit 1
+fi
 
 # Extract the IDs that start with "FleetServer_"
-POLICY=$(echo "$json_output" | jq -r '.items[] | select(.id | startswith("FleetServer_")) | .id')
+POLICY=$(jq -r '.items[] | select(.id | startswith("FleetServer_")) | .id' <<<"$json_output")
 
 # Iterate over each ID in the POLICY variable
 for POLICYNAME in $POLICY; do
     printf "\nUpdating Policy: $POLICYNAME\n"
 
-    # First get the Integration ID
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$POLICYNAME" | jq -r '.item.package_policies[] | select(.package.name == "fleet_server") | .id')  
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$POLICYNAME"); then
+        exit 1
+    fi
+
+    INTEGRATION_ID=$(jq -r '.item.package_policies[]? | select(.package.name == "fleet_server") | .id' <<<"$POLICY_JSON")
+    if [ -z "$INTEGRATION_ID" ]; then
+        echo "Error: fleet_server integration was not found in agent policy '$POLICYNAME'." >&2
+        exit 1
+    fi
 
     # Modify the default integration policy to update the policy_id and an with the correct naming
-	UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "$POLICYNAME" --arg name "fleet_server-$POLICYNAME" '
+    UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "$POLICYNAME" --arg name "fleet_server-$POLICYNAME" '
     .policy_id = $policy_id |
     .name = $name' /opt/so/conf/elastic-fleet/integrations/fleet-server/fleet-server.json)
 

salt/elasticfleet/tools/sbin_jinja/so-elastic-agent-gen-installers

@@ -22,12 +22,19 @@ NUM_RUNNING=$(pgrep -cf "/bin/bash /sbin/so-elastic-agent-gen-installers")
 
 for i in {1..30}
 do
-   ENROLLMENTOKEN=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys?perPage=100" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
+   ENROLLMENTOKEN=$(elastic_fleet_active_enrollment_token "endpoints-initial")
+   TOKEN_RC=$?
+   if [ "$TOKEN_RC" -eq 2 ]; then
+     exit 1
+   fi
    FLEETHOST=$(curl -K /opt/so/conf/elasticsearch/curl.config 'http://localhost:5601/api/fleet/fleet_server_hosts/grid-default' | jq -r  '.item.host_urls[]' | paste -sd ',')
-if [[ $FLEETHOST ]] && [[  $ENROLLMENTOKEN ]]; then break; else sleep 10; fi
+   if [[ -n "$FLEETHOST" ]] && [[ -n "$ENROLLMENTOKEN" ]]; then
+     break
+   fi
+   sleep 10
 done
 
-if [[ -z $FLEETHOST ]] || [[ -z $ENROLLMENTOKEN ]]; then 
+if [[ -z "$FLEETHOST" ]] || [[ -z "$ENROLLMENTOKEN" ]]; then
   printf "\nFleet Host URL, Enrollment Token or Elastic Version empty - exiting..."
   printf "\nFleet Host: $FLEETHOST, Enrollment Token: $ENROLLMENTOKEN\n"
   exit 1
@@ -67,19 +74,25 @@ for GOOS in "${GOTARGETOS[@]}"; do
     GOARCH="amd64"
     if [[ $GOOS == 'darwin/arm64' ]]; then GOOS="darwin" && GOARCH="arm64"; fi
     printf "\n\n### Generating $GOOS/$GOARCH Installer...\n"
-    docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
+    if ! docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
     --mount type=bind,source=/etc/pki/tls/certs/,target=/workspace/files/cert/ \
     --mount type=bind,source=/nsm/elastic-agent-workspace/,target=/workspace/files/elastic-agent/ \
     --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ \
-    {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}
+    {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}; then
+        printf "\n### ERROR: Failed to generate $GOOS/$GOARCH installer. Exiting...\n"
+        exit 1
+    fi
     printf "\n### $GOOS/$GOARCH Installer Generated...\n"
 done
 
 printf "\n\n### Generating MSI...\n"
 cp /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64 /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64.exe
-docker run \
+if ! docker run \
 --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ -w /output \
-{{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs
+{{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs; then
+    printf "\n### ERROR: Failed to generate MSI. Exiting...\n"
+    exit 1
+fi
 printf "\n### MSI Generated...\n"
 
 # Verify installers were created

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

@@ -10,6 +10,25 @@
 
 PKG_LOAD_FAILURES=0
 PKG_LOAD_FAILURES_NAMES=()
+PKG_UPGRADED=0
+
+cleanup_elasticsearch_fleet_transforms() {
+    local transforms transform_id attempt
+    
+    if ! transforms=$(so-elasticsearch-query "_transform/logs-elasticsearch.index_pivot-default-*" --retry 1 --retry-delay 5); then
+        return 0
+    fi
+
+    while IFS= read -r transform_id; do
+        [ -n "$transform_id" ] || continue
+        for attempt in {1..3}; do
+            if so-elasticsearch-query "_transform/$transform_id?force=true" -XDELETE --fail --retry 1 --retry-delay 5; then
+                break
+            fi
+            sleep 5
+        done
+    done < <(jq -r '.transforms[]?.id' <<< "$transforms")
+}
 
 {%- for PACKAGE in SUPPORTED_PACKAGES %}
 if INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && LATEST_VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
@@ -17,10 +36,25 @@ if INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && L
     if [ "$INSTALLED_VERSION" == "$LATEST_VERSION" ]; then
         echo "{{ PACKAGE }} integration version $INSTALLED_VERSION is already at the reported latest version $LATEST_VERSION, skipping upgrade."
     else
+{%- if PACKAGE == 'elasticsearch' %}
+        cleanup_elasticsearch_fleet_transforms
+{%- endif %}
         echo "Upgrading {{ PACKAGE }} package from $INSTALLED_VERSION to version $LATEST_VERSION..."
         if ! elastic_fleet_package_install "{{ PACKAGE }}" "$LATEST_VERSION"; then
             PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
             PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
+        # check that package has upgraded to the expected version after install command
+        elif ! LATEST_VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
+            echo "ERROR: Failed to get latest version information for integration {{ PACKAGE }} after upgrade attempt"
+            PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
+            PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
+        elif INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && [ "$INSTALLED_VERSION" == "$LATEST_VERSION" ]; then
+            echo "{{ PACKAGE }} integration upgraded to version $LATEST_VERSION."
+            PKG_UPGRADED=$((PKG_UPGRADED + 1))
+        else
+            echo "ERROR: {{ PACKAGE }} integration still at ${INSTALLED_VERSION:-unknown}; expected $LATEST_VERSION"
+            PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
+            PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
         fi
     fi
 else
@@ -30,6 +64,11 @@ else
 fi
 {%- endfor %}
 
+if [ $PKG_UPGRADED -gt 0 ]; then
+    echo "Elasticsearch template statefiles cleared after $PKG_UPGRADED package upgrade(s), so templates can reload."
+    rm -f /opt/so/state/estemplates.txt /opt/so/state/addon_estemplates.txt
+fi
+
 if [ $PKG_LOAD_FAILURES -gt 0 ]; then
     echo "ERROR: Failed to upgrade $PKG_LOAD_FAILURES package(s):"
     for PKG in "${PKG_LOAD_FAILURES_NAMES[@]}"; do

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

@@ -202,26 +202,9 @@ fi
 ### Finalization ###
 
 # Query for Enrollment Tokens for default policies
-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 "$GRIDNODESENROLLMENTOKENHEAVY_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_heavy")) | .api_key')
-else
-    echo -e "\nFailed to query for Grid nodes - Heavy enrollment token"
-    exit 1
-fi
+ENDPOINTSENROLLMENTOKEN=$(elastic_fleet_active_enrollment_token "endpoints-initial") || exit 1
+GRIDNODESENROLLMENTOKENGENERAL=$(elastic_fleet_active_enrollment_token "so-grid-nodes_general") || exit 1
+GRIDNODESENROLLMENTOKENHEAVY=$(elastic_fleet_active_enrollment_token "so-grid-nodes_heavy") || exit 1
 
 # Store needed data in minion pillar
 pillar_file=/opt/so/saltstack/local/pillar/minions/{{ GLOBALS.minion_id }}.sls

salt/elasticsearch/cluster.sls

@@ -98,6 +98,13 @@ so-es-cluster-settings:
       - docker_container: so-elasticsearch
       - file: elasticsearch_sbin_jinja
       - http: wait_for_so-elasticsearch
+
+so-elasticsearch-system-indices-patch:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-system-indices-patch
+    - require:
+      - http: wait_for_so-elasticsearch
+      - file: so-elasticsearch-system-indices-patch-script
 {%  endif %}
 
 # heavynodes will only load ILM policies for SO managed indices. (Indicies defined in elasticsearch/defaults.yaml)

salt/elasticsearch/config.sls

@@ -32,24 +32,35 @@ elasticsearch:
     - gid: 930
     - home: /opt/so/conf/elasticsearch
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticsearch_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticsearch/tools/sbin
-    - user: 930
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - exclude_pat:
       - so-elasticsearch-pipelines # exclude this because we need to watch it for changes, we sync it in another state
+      - so-elasticsearch-system-indices-patch
+    - show_changes: False
+
+so-elasticsearch-system-indices-patch-script:
+  file.managed:
+    - name: /usr/sbin/so-elasticsearch-system-indices-patch
+    - source: salt://elasticsearch/tools/sbin/so-elasticsearch-system-indices-patch
+    - user: root
+    - group: root
+    - mode: 755
     - show_changes: False
 
 elasticsearch_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticsearch/tools/sbin_jinja
-    - user: 939
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - exclude_pat:
@@ -62,8 +73,8 @@ so-elasticsearch-ilm-policy-load-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-ilm-policy-load
     - source: salt://elasticsearch/tools/sbin_jinja/so-elasticsearch-ilm-policy-load
-    - user: 930
-    - group: 939
+    - user: root
+    - group: root
     - mode: 754
     - template: jinja
     - defaults:
@@ -74,8 +85,8 @@ so-elasticsearch-pipelines-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-pipelines
     - source: salt://elasticsearch/tools/sbin/so-elasticsearch-pipelines
-    - user: 930
-    - group: 939
+    - user: root
+    - group: root
     - mode: 754
     - show_changes: False
 

salt/elasticsearch/defaults.yaml

@@ -1,7 +1,7 @@
 elasticsearch:
   enabled: false
   esheap: '600m'
-  version: 9.3.7
+  version: 9.4.5
   index_clean: true
   data_retention_method: DLM
   vm:

salt/elasticsearch/files/ingest/suricata.fileinfo

@@ -5,7 +5,8 @@
     { "rename": 	{ "field": "message2.proto", 			"target_field": "network.transport",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.app_proto", 		"target_field": "network.protocol",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.filename", 	"target_field": "file.name",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.fileinfo.gaps", 		"target_field": "file.bytes.missing",	"ignore_missing": true 	} },
+    { "rename": 	{ "field": "message2.fileinfo.gaps", 		"target_field": "suricata.fileinfo.gaps",	"ignore_missing": true 	} },
+    { "set":		{ "if": "ctx.suricata?.fileinfo?.gaps == false", 	"field": "file.bytes.missing",	"value": 0 		} },
     { "rename": 	{ "field": "message2.fileinfo.magic", 		"target_field": "file.mime_type",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.md5", 		"target_field": "hash.md5",		"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.sha1", 		"target_field": "hash.sha1",		"ignore_missing": true 	} },

salt/elasticsearch/tools/sbin/so-elasticsearch-system-indices-patch

@@ -0,0 +1,203 @@
+#!/bin/bash
+# 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.
+
+set -eo pipefail
+
+SETTINGS='{"index":{"auto_expand_replicas":"0-1"}}'
+KIBANA_PASSWORD=
+INDEX_PATTERNS=(
+  '.entity_analytics.risk_score.lookup-*'
+  '.entity_analytics.watchlists.*'
+  '.entity_analytics.monitoring.users-*'
+  '.entity_analytics.entity-leads-*'
+  '.asset-criticality.asset-criticality-*'
+  '.workflows-executions'
+  '.workflows-step-executions'
+  '.entities.v2.latest.security_*'
+  '.entities.v2.history.security_*'
+  'risk-score.risk-score-latest-*'
+  '.metrics-endpoint.metadata_united_*'
+  '.metrics-endpoint.metadata_current_*'
+)
+DATA_STREAM_PATTERNS=(
+  '.entities.v2.updates.security_*'
+  'risk-score.risk-score-*'
+  '.rule-events'
+  '.alert-actions'
+)
+TEMPLATE_PATTERNS=(
+  'entities_v2_latest_security_default_index_template'
+  'entities_v2_history_security_default_index_template'
+  '.entities_v2_updates_security_default_index_template'
+  '.risk-score.risk-score-default-index-template'
+  '.rule-events'
+  '.alert-actions'
+  '.metrics-endpoint.metadata_united_default-template'
+  '.metrics-endpoint.metadata_current_default-template'
+)
+
+query_es() {
+  if so-elasticsearch-query "$@" --fail --retry 3 --retry-delay 5; then
+    return 0
+  fi
+
+  # retry failed attempts with so_kibana user (system managed indices reject so_elastic user)
+  local query_path="$1"
+  shift
+
+  if [[ -z "$KIBANA_PASSWORD" ]]; then
+    KIBANA_PASSWORD=$(salt-call pillar.get elasticsearch:auth:users:so_kibana_user:pass --out=newline_values_only)
+  fi
+  [[ -n "$KIBANA_PASSWORD" ]] || return 1
+
+  echo "Retrying ${query_path} as so_kibana." >&2
+  curl -K /opt/so/conf/elasticsearch/curl.config --user "so_kibana:${KIBANA_PASSWORD}" \
+    -s -k -L --fail --retry 3 --retry-delay 5 -H 'Content-Type: application/json' "https://localhost:9200/${query_path}" "$@"
+}
+
+# add auto_expand_replicas=0-1 to given index
+set_auto_expand_replicas() {
+  local index="$1"
+
+  echo "Setting auto_expand_replicas to 0-1 on ${index}."
+  query_es "${index}/_settings" -XPUT -d "$SETTINGS" >/dev/null
+}
+
+# resolve index patterns and find each index with an unassigned replica
+unassigned_replicas() {
+  local pattern="$1"
+  local resolved_indices response index
+
+  if ! resolved_indices=$(query_es "_resolve/index/${pattern}?expand_wildcards=all" 2>/dev/null); then
+    return 0
+  fi
+
+  while read -r index; do
+    if ! response=$(query_es "_cat/shards/${index}?format=json&h=index,prirep,state" 2>/dev/null); then
+      continue
+    fi
+    jq -r '.[]? | objects | select(.prirep == "r" and .state == "UNASSIGNED") | .index' <<<"$response"
+  done < <(jq -r '.indices[]?.name' <<<"$resolved_indices")
+}
+
+data_stream_indices() {
+  local pattern="$1"
+  local response
+
+  if ! response=$(query_es "_data_stream/${pattern}?expand_wildcards=all" 2>/dev/null); then
+    return 0
+  fi
+  jq -r '.data_streams[]?.indices[]?.index_name' <<<"$response"
+}
+
+update_system_indices() {
+  local pattern="$1"
+  local index
+
+  while read -r index; do
+    [[ -n "$index" ]] && set_auto_expand_replicas "$index"
+  done < <(unassigned_replicas "$pattern")
+}
+
+# update data stream backing indices with unassigned replicas
+update_system_ds() {
+  local pattern="$1"
+  local index
+
+  while read -r index; do
+    while read -r unassigned_index; do
+      [[ -n "$unassigned_index" ]] && set_auto_expand_replicas "$unassigned_index"
+    done < <(unassigned_replicas "$index")
+  done < <(data_stream_indices "$pattern")
+}
+
+has_unassigned_replicas() {
+  local pattern="$1"
+  local index
+
+  index=$(unassigned_replicas "$pattern" | sed -n '1p')
+  [[ -n "$index" ]]
+}
+
+data_stream_has_unassigned_replicas() {
+  local pattern="$1"
+  local index
+  while read -r index; do
+    has_unassigned_replicas "$index" && return 0
+  done < <(data_stream_indices "$pattern")
+
+  return 1
+}
+
+needs_patch() {
+  local pattern
+  for pattern in "${INDEX_PATTERNS[@]}"; do
+    has_unassigned_replicas "$pattern" && return 0
+  done
+  for pattern in "${DATA_STREAM_PATTERNS[@]}"; do
+    data_stream_has_unassigned_replicas "$pattern" && return 0
+  done
+
+  return 1
+}
+
+# get index templates, update with auto_expand_replicas=0-1, and PUT back. Keeping mappings/settings/aliases in-place
+update_system_templates() {
+  local pattern="$1"
+  local templates name response template auto_expand_replicas
+
+  if ! templates=$(query_es "_index_template/${pattern}" 2>/dev/null); then
+    return 0
+  fi
+  while read -r name; do
+    response=$(query_es "_index_template/${name}")
+    template=$(jq -c '.index_templates[0].index_template' <<<"$response")
+    auto_expand_replicas=$(jq -r '.template.settings["index.auto_expand_replicas"] // .template.settings.index.auto_expand_replicas // empty' <<<"$template")
+    [[ "$auto_expand_replicas" == "0-1" ]] && continue
+
+    template=$(jq '
+            if (.template.settings.index | type) == "object" then
+                .template.settings.index.auto_expand_replicas = "0-1"
+            else
+                .template.settings["index.auto_expand_replicas"] = "0-1"
+            end
+            | del(.created_date_millis, .modified_date_millis)
+        ' <<<"$template")
+    echo "Setting auto_expand_replicas to 0-1 on index template ${name}."
+    query_es "_index_template/${name}" -XPUT -d "$template" >/dev/null
+  done < <(jq -r '.index_templates[]?.name' <<<"$templates")
+}
+
+if [[ "${1:-}" == "--check" ]]; then
+  needs_patch
+  exit $?
+fi
+
+if [[ $# -ne 0 ]]; then
+  echo "Usage: $0 [--check]" >&2
+  exit 1
+fi
+
+patched=false
+for pattern in "${INDEX_PATTERNS[@]}"; do
+  if has_unassigned_replicas "$pattern"; then
+    update_system_indices "$pattern"
+    patched=true
+  fi
+done
+
+for pattern in "${DATA_STREAM_PATTERNS[@]}"; do
+  if data_stream_has_unassigned_replicas "$pattern"; then
+    update_system_ds "$pattern"
+    patched=true
+  fi
+done
+
+if [[ "$patched" == true ]]; then
+  for pattern in "${TEMPLATE_PATTERNS[@]}"; do
+    update_system_templates "$pattern"
+  done
+fi

salt/firewall/iptables.jinja

@@ -4,11 +4,19 @@
 {%- set role = GLOBALS.role.split('-')[1] %}
 {%- from 'firewall/containers.map.jinja' import NODE_CONTAINERS %}
 
+{%- set NODE_NETWORKS = [] %}
+{%- for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
+{%-   if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
+{%-     do NODE_NETWORKS.append(NETNAME) %}
+{%-   endif %}
+{%- endfor %}
+
 {%- set PR = [] %}
 {%- set D1 = [] %}
 {%- set D2 = [] %}
 {%- for container in NODE_CONTAINERS %}
 {%-   set IP = DOCKERMERGED.containers[container].ip %}
+{%-   set BRIDGE = DOCKERMERGED.containers[container].network %}
 {%-   if DOCKERMERGED.containers[container].port_bindings is defined %}
 {%-     for binding in DOCKERMERGED.containers[container].port_bindings %}
 {#-       cant split int so we convert to string #}
@@ -35,11 +43,11 @@
 {%-         endif %}
 {%-         do PR.append("-A POSTROUTING -s " ~ DOCKERMERGED.containers[container].ip ~ "/32 -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 -p " ~  proto ~ " -m " ~ proto  ~ " --dport " ~ containerPort ~ " -j MASQUERADE") %}
 {%-         if bindip | length and bindip != '0.0.0.0' %}
-{%-           do D1.append("-A DOCKER -d " ~ bindip ~ "/32 ! -i sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
+{%-           do D1.append("-A DOCKER -d " ~ bindip ~ "/32 ! -i " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
 {%-         else %}
-{%-           do D1.append("-A DOCKER ! -i sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
+{%-           do D1.append("-A DOCKER ! -i " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ hostPort ~ " -j DNAT --to-destination " ~ DOCKERMERGED.containers[container].ip ~ ":" ~ containerPort) %}
 {%-         endif %}
-{%-         do D2.append("-A DOCKER -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 ! -i sobridge -o sobridge -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ containerPort ~ " -j ACCEPT") %}
+{%-         do D2.append("-A DOCKER -d " ~ DOCKERMERGED.containers[container].ip ~ "/32 ! -i " ~ BRIDGE ~ " -o " ~ BRIDGE ~ " -p " ~ proto ~ " -m " ~ proto ~ " --dport " ~ containerPort ~ " -j ACCEPT") %}
 {%-     endfor %}
 {%-   endif %}
 {%- endfor %}
@@ -52,11 +60,15 @@
 :DOCKER - [0:0]
 -A PREROUTING -m addrtype --dst-type LOCAL -j DOCKER
 -A OUTPUT ! -d 127.0.0.0/8 -m addrtype --dst-type LOCAL -j DOCKER
--A POSTROUTING -s {{DOCKERMERGED.range}} ! -o sobridge -j MASQUERADE
+{%- for NETNAME in NODE_NETWORKS %}
+-A POSTROUTING -s {{ DOCKERMERGED.networks[NETNAME].range }} ! -o {{ NETNAME }} -j MASQUERADE
+{%- endfor %}
 {%- for rule in PR %}
 {{ rule }}
 {%- endfor %}
--A DOCKER -i sobridge -j RETURN
+{%- for NETNAME in NODE_NETWORKS %}
+-A DOCKER -i {{ NETNAME }} -j RETURN
+{%- endfor %}
 {%- for rule in D1 %}
 {{ rule }}
 {%- endfor %}
@@ -97,10 +109,12 @@ COMMIT
 {%- endif %}
 -A FORWARD -j DOCKER-USER
 -A FORWARD -j DOCKER-ISOLATION-STAGE-1
--A FORWARD -o sobridge -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A FORWARD -o sobridge -j DOCKER
--A FORWARD -i sobridge ! -o sobridge -j ACCEPT
--A FORWARD -i sobridge -o sobridge -j ACCEPT
+{%- for NETNAME in NODE_NETWORKS %}
+-A FORWARD -o {{ NETNAME }} -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
+-A FORWARD -o {{ NETNAME }} -j DOCKER
+-A FORWARD -i {{ NETNAME }} ! -o {{ NETNAME }} -j ACCEPT
+-A FORWARD -i {{ NETNAME }} -o {{ NETNAME }} -j ACCEPT
+{%- endfor %}
 -A FORWARD -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
 -A FORWARD -i lo -j ACCEPT
 -A FORWARD -m conntrack --ctstate INVALID -j DROP
@@ -112,13 +126,18 @@ COMMIT
 {%- for rule in D2 %}
 {{ rule }}
 {%- endfor %}
-
--A DOCKER-ISOLATION-STAGE-1 -i sobridge ! -o sobridge -j DOCKER-ISOLATION-STAGE-2
+{% for NETNAME in NODE_NETWORKS %}
+-A DOCKER-ISOLATION-STAGE-1 -i {{ NETNAME }} ! -o {{ NETNAME }} -j DOCKER-ISOLATION-STAGE-2
+{%- endfor %}
 -A DOCKER-ISOLATION-STAGE-1 -j RETURN
--A DOCKER-ISOLATION-STAGE-2 -o sobridge -j DROP
+{%- for NETNAME in NODE_NETWORKS %}
+-A DOCKER-ISOLATION-STAGE-2 -o {{ NETNAME }} -j DROP
+{%- endfor %}
 -A DOCKER-ISOLATION-STAGE-2 -j RETURN
--A DOCKER-USER ! -i sobridge -o sobridge -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
--A DOCKER-USER ! -i sobridge -o sobridge -j LOGGING
+{%- for NETNAME in NODE_NETWORKS %}
+-A DOCKER-USER ! -i {{ NETNAME }} -o {{ NETNAME }} -m conntrack --ctstate RELATED,ESTABLISHED -j ACCEPT
+-A DOCKER-USER ! -i {{ NETNAME }} -o {{ NETNAME }} -j LOGGING
+{%- endfor %}
 -A DOCKER-USER -j RETURN
 -A LOGGING -m limit --limit 2/min -j LOG --log-prefix "IPTables-dropped: "
 -A LOGGING -j DROP

salt/firewall/map.jinja

@@ -4,8 +4,12 @@
 
 {# add our ip to self #}
 {% do FIREWALL_DEFAULT.firewall.hostgroups.self.append(GLOBALS.node_ip) %}
-{# add dockernet range #}
-{% do FIREWALL_DEFAULT.firewall.hostgroups.dockernet.append(DOCKERMERGED.range) %}
+{# add dockernet ranges #}
+{% for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
+{%   if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
+{%     do FIREWALL_DEFAULT.firewall.hostgroups.dockernet.append(NETWORK.range) %}
+{%   endif %}
+{% endfor %}
 
 {% if GLOBALS.role == 'so-idh' %}
 {%   from 'idh/opencanary_config.map.jinja' import IDH_PORTGROUPS %}

salt/hydra/enabled.sls

@@ -26,8 +26,8 @@ so-hydra:
     - hostname: hydra
     - name: so-hydra
     - networks:
-      - sobridge:
-        - ipv4_address: {{ DOCKERMERGED.containers['so-hydra'].ip }}
+      - soauth:
+        - ipv4_address: {{ DOCKERMERGED.containers['so-hydra'].ips['soauth'] }}
     - binds:
       - /opt/so/conf/hydra/:/hydra-conf:ro
       - /opt/so/log/hydra/:/hydra-log:rw
@@ -73,7 +73,7 @@ delete_so-hydra_so-status.disabled:
 
 wait_for_hydra:
   http.wait_for_successful_query:
-    - name: 'http://{{ GLOBALS.manager }}:4444/health/alive'
+    - name: 'http://{{ DOCKERMERGED.containers['so-hydra'].ips['soauth'] }}:4444/health/alive'
     - ssl: True
     - verify_ssl: False
     - status:

salt/hypervisor/init.sls

@@ -21,12 +21,16 @@ hypervisor_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://hypervisor/tools/sbin
+    - user: root
+    - group: root
     - file_mode: 744
 
 hypervisor_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://hypervisor/tools/sbin_jinja
+    - user: root
+    - group: root
     - template: jinja
     - file_mode: 744
 

salt/idh/config.sls

@@ -86,8 +86,8 @@ idh_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://idh/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #idh_sbin_jinja:

salt/influxdb/config.sls

@@ -41,8 +41,8 @@ influxdb_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://influxdb/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #influxdb_sbin_jinja:

salt/influxdb/enabled.sls

@@ -94,9 +94,11 @@ metrics_link_file:
       - docker_container: so-influxdb
 
 # Install cron job to determine size of influxdb for telegraf
+# telegraf reads this while the cron rewrites it, so write aside and rename rather than
+# truncating in place. tgraflogdir recurses ownership, so the temp file is chowned to match
 get_influxdb_size:
   cron.present:
-    - name: 'du -s -k /nsm/influxdb | cut -f1 > /opt/so/log/telegraf/influxdb_size.log 2>&1'
+    - name: 'du -s -k /nsm/influxdb | cut -f1 > /opt/so/log/telegraf/influxdb_size.log.tmp 2>&1; chown 939:939 /opt/so/log/telegraf/influxdb_size.log.tmp; mv -f /opt/so/log/telegraf/influxdb_size.log.tmp /opt/so/log/telegraf/influxdb_size.log'
     - identifier: get_influxdb_size
     - user: root
     - minute: '*/1'

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:
@@ -30,16 +31,16 @@ kafka_sbin_tools:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kafka/tools/sbin
-    - user: 960
-    - group: 960
+    - user: root
+    - group: root
     - file_mode: 755
 
 kafka_sbin_jinja_tools:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kafka/tools/sbin_jinja
-    - user: 960
-    - group: 960
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - defaults:

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
 
@@ -36,16 +37,16 @@ kibana_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kibana/tools/sbin
-    - user: 932
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 kibana_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://kibana/tools/sbin_jinja
-    - user: 932
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - defaults:

salt/kibana/defaults.yaml

@@ -22,7 +22,7 @@ kibana:
           - default
           - file
     migrations:
-      discardCorruptObjects: "9.3.7"
+      discardCorruptObjects: "9.4.5"
     telemetry:
       enabled: False
     xpack:

salt/kibana/tools/sbin_jinja/so-kibana-space-defaults

@@ -9,5 +9,5 @@ SESSIONCOOKIE=$(curl -K /opt/so/conf/elasticsearch/curl.config -c - -X GET http:
 # Disable certain Features from showing up in the Kibana UI
 echo
 echo "Setting up default Kibana Space:"
-curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X PUT "localhost:5601/api/spaces/space/default" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d' {"id":"default","name":"Default","disabledFeatures":["ml","enterpriseSearch","logs","infrastructure","apm","uptime","monitoring","stackAlerts","actions","securitySolutionCasesV3","inventory","dataQuality","searchSynonyms","searchQueryRules","enterpriseSearchApplications","enterpriseSearchAnalytics","securitySolutionTimeline","securitySolutionNotes","securitySolutionRulesV1","entityManager","streams","cloudConnect","slo"]} ' >> /opt/so/log/kibana/misc.log
+curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X PUT "localhost:5601/api/spaces/space/default" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d' {"id":"default","name":"Default","disabledFeatures":["ml","enterpriseSearch","logs","infrastructure","apm","uptime","securitySolutionCasesV3","inventory","searchSynonyms","searchQueryRules","enterpriseSearchApplications","enterpriseSearchAnalytics","securitySolutionTimeline","securitySolutionNotes","securitySolutionRulesV4","securitySolutionAlertsV1","entityManager","slo","streams","anonymization","searchInferenceEndpoints","cloudConnect","queryActivity","automatic_import","stackAlerts","monitoring","dataQuality","actions"]} ' >> /opt/so/log/kibana/misc.log
 echo

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/kratos/enabled.sls

@@ -19,8 +19,8 @@ so-kratos:
     - hostname: kratos
     - name: so-kratos
     - networks:
-      - sobridge:
-        - ipv4_address: {{ DOCKERMERGED.containers['so-kratos'].ip }}
+      - soauth:
+        - ipv4_address: {{ DOCKERMERGED.containers['so-kratos'].ips['soauth'] }}
     - binds:
       - /opt/so/conf/kratos/:/kratos-conf:ro
       - /opt/so/log/kratos/:/kratos-log:rw
@@ -71,7 +71,7 @@ delete_so-kratos_so-status.disabled:
 
 wait_for_kratos:
   http.wait_for_successful_query:
-    - name: 'http://{{ GLOBALS.manager }}:4434/'
+    - name: 'http://{{ DOCKERMERGED.containers['so-kratos'].ips['soauth'] }}:4434/'
     - ssl: True
     - verify_ssl: False
     - status:

salt/libvirt/64962/init.sls

@@ -6,6 +6,8 @@ so-fix-salt-ldap_script:
   file.managed:
     - name: /usr/sbin/so-fix-salt-ldap.py
     - source: salt://libvirt/64962/scripts/so-fix-salt-ldap.py
+    - user: root
+    - group: root
     - mode: 744
 
 fix-salt-ldap:

salt/logrotate/defaults.yaml

@@ -220,6 +220,26 @@ logrotate:
       - extension .log
       - dateext
       - dateyesterday
+    /opt/so/log/salt/virtual_node_manager:
+      - daily
+      - rotate 14
+      - missingok
+      - copytruncate
+      - compress
+      - create
+      - extension .log
+      - dateext
+      - dateyesterday
+    /opt/so/log/salt/so-salt-cloud:
+      - daily
+      - rotate 14
+      - missingok
+      - copytruncate
+      - compress
+      - create
+      - extension .log
+      - dateext
+      - dateyesterday
     /opt/so/log/salt/so-soup-grid-highstate:
       - daily
       - rotate 14

salt/logrotate/soc_logrotate.yaml

@@ -140,6 +140,20 @@ logrotate:
       multiline: True
       global: True
       forcedType: "[]string"
+    "/opt/so/log/salt/virtual_node_manager":
+      description: List of logrotate options for this file.
+      title: /opt/so/log/salt/virtual_node_manager
+      advanced: True
+      multiline: True
+      global: True
+      forcedType: "[]string"
+    "/opt/so/log/salt/so-salt-cloud":
+      description: List of logrotate options for this file.
+      title: /opt/so/log/salt/so-salt-cloud
+      advanced: True
+      multiline: True
+      global: True
+      forcedType: "[]string"
     "/opt/so/log/salt/so-soup-grid-highstate":
       description: List of logrotate options for this file.
       title: /opt/so/log/salt/so-soup-grid-highstate

salt/logstash/config.sls

@@ -35,13 +35,14 @@ logstash:
     - uid: 931
     - gid: 931
     - home: /opt/so/conf/logstash
+    - shell: /sbin/nologin
 
 logstash_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://logstash/tools/sbin
-    - user: 931
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #logstash_sbin_jinja:

salt/manager/files/beacons_pushstate.conf.jinja

@@ -3,9 +3,16 @@ beacons:
   postgres_pillar_beacon:
     - interval: {{ AUTOAPPLY.drain_interval }}
     - disable_during_state_run: False
-  rules_beacon:
+  local_files_beacon:
     - interval: {{ AUTOAPPLY.drain_interval }}
     - disable_during_state_run: False
+    # Tags are app names in salt/reactor/pillar_push_map.yaml.
+    # Allowlist on purpose: salt writes elsewhere under local/salt/ and would self-retrigger.
     - paths:
         /opt/so/saltstack/local/salt/suricata/rules: suricata
         /opt/so/saltstack/local/salt/strelka/rules/compiled: strelka
+        /opt/so/saltstack/local/salt/zeek/policy: zeek
+        /opt/so/saltstack/local/salt/zeek/zkg: zeek
+        /opt/so/saltstack/local/salt/elasticsearch/files/ingest: elasticsearch
+        /opt/so/saltstack/local/salt/elasticsearch/roles: elasticsearch
+        /opt/so/saltstack/local/salt/logstash/pipelines/config/custom: logstash

salt/manager/init.sls

@@ -113,8 +113,8 @@ manager_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://manager/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
     - exclude_pat:
       - "*_test.py"
@@ -124,8 +124,8 @@ manager_sbin_jinja:
   file.recurse:
     - name: /usr/sbin/
     - source: salt://manager/tools/sbin_jinja/
-    - user: socore
-    - group: socore
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
     - show_changes: False
@@ -166,7 +166,7 @@ so-repo-sync:
 
 so_fleetagent_status:
   cron.present:
-    - name: /usr/sbin/so-elasticagent-status > /opt/so/log/agents/agentstatus.log 2>&1
+    - name: '/usr/sbin/so-elasticagent-status > /opt/so/log/agents/agentstatus.log.tmp 2>&1; mv -f /opt/so/log/agents/agentstatus.log.tmp /opt/so/log/agents/agentstatus.log'
     - identifier: so_fleetagent_status
     - user: root
     - minute: '*/5'
@@ -190,11 +190,15 @@ so_fleetagent_monitor:
   - month: '*'
   - dayweek: '*'
 
-socore_own_saltstack_default:
+# This tree is the source of every root-executed script (/usr/sbin, reactors, _runners,
+# engines, salt-relay.sh). SOC mounts /opt/so/saltstack rw as uid 939 but only writes
+# under local/. Do not add dir_mode/file_mode here -- SOC reads default/ and 750/640
+# would break its config load.
+root_own_saltstack_default:
   file.directory:
     - name: /opt/so/saltstack/default
-    - user: socore
-    - group: socore
+    - user: root
+    - group: root
     - recurse:
       - user
       - group

salt/manager/tools/sbin/so-client

@@ -106,7 +106,8 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
-hydraUrl=${HYDRA_URL:-http://127.0.0.1:4445}
+hydraContainer=${HYDRA_CONTAINER:-so-hydra}
+hydraUrl=${HYDRA_URL:-http://localhost:4445}
 socRolesFile=${SOC_ROLES_FILE:-/opt/so/conf/soc/soc_clients_roles}
 soUID=${SOCORE_UID:-939}
 soGID=${SOCORE_GID:-939}
@@ -124,6 +125,10 @@ function fail() {
   exit 1
 }
 
+function hydraCurl() {
+  docker exec "$hydraContainer" curl "$@"
+}
+
 function require() {
   cmd=$1
   which "$1" 2>&1 > /dev/null
@@ -133,8 +138,8 @@ function require() {
 # Verify this environment is capable of running this script
 function verifyEnvironment() {
   require "jq"
-  require "curl"
-  response=$(curl -Ss -L ${hydraUrl}/health/alive)
+  require "docker"
+  response=$(hydraCurl -Ss -L ${hydraUrl}/health/alive)
   [[ "$response" != '{"status":"ok"}' ]] && fail "Unable to communicate with Hydra; specify URL via HYDRA_URL environment variable"
 }
 
@@ -164,7 +169,7 @@ function ensureRoleFileExists() {
 }
 
 function listClients() {
-  response=$(curl -Ss -L -f ${hydraUrl}/admin/clients)
+  response=$(hydraCurl -Ss -L -f ${hydraUrl}/admin/clients)
   [[ $? != 0 ]] && fail "Unable to communicate with Hydra"
 
   clientIds=$(echo "${response}" | jq -r ".[] | .client_id" | sort)
@@ -251,7 +256,7 @@ function createClient() {
 EOF
   )
   
-  response=$(curl -Ss -L --fail-with-body -X POST ${hydraUrl}/admin/clients -d "$body")
+  response=$(hydraCurl -Ss -L --fail-with-body -X POST ${hydraUrl}/admin/clients -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -283,7 +288,7 @@ function update() {
 EOF
   )
   
-  response=$(curl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
+  response=$(hydraCurl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -305,7 +310,7 @@ function generateSecret() {
 EOF
   )
   
-  response=$(curl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
+  response=$(hydraCurl -Ss -L --fail-with-body -X PATCH ${hydraUrl}/admin/clients/$id -d "$body")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"
@@ -317,7 +322,7 @@ function deleteClient() {
 
   [[ ${identityId} == "" ]] && fail "Client not found"
 
-  response=$(curl -Ss -XDELETE -L --fail-with-body "${hydraUrl}/admin/clients/$identityId")
+  response=$(hydraCurl -Ss -XDELETE -L --fail-with-body "${hydraUrl}/admin/clients/$identityId")
   if [[ $? != 0 ]]; then
     error=$(echo $response | jq .error)
     fail "Failed to submit request to Hydra: $error"

salt/manager/tools/sbin/so-minion

@@ -121,8 +121,14 @@ for i in "$@"; do
 	esac
 done
 
-PILLARFILE=/opt/so/saltstack/local/pillar/minions/$MINION_ID.sls
-ADVPILLARFILE=/opt/so/saltstack/local/pillar/minions/adv_$MINION_ID.sls
+if [[ -n "$MINION_ID" && ! "$MINION_ID" =~ ^[A-Za-z0-9._-]{1,253}$ ]]; then
+	echo "Invalid minion id: $MINION_ID"
+	log "ERROR" "Invalid minion id: $MINION_ID"
+	exit 1
+fi
+
+readonly PILLARFILE=/opt/so/saltstack/local/pillar/minions/$MINION_ID.sls
+readonly ADVPILLARFILE=/opt/so/saltstack/local/pillar/minions/adv_$MINION_ID.sls
 
 function getinstallinfo() {
 	log "INFO" "Getting install info for minion $MINION_ID"
@@ -133,10 +139,23 @@ function getinstallinfo() {
 		return 1
 	fi
 
-	while read -r var; do export "$var"; done <<< "$INSTALLVARS"
-	if [ $? -ne 0 ]; then
-		log "ERROR" "Failed to source install variables"
-		return 1
+	# install.txt is controlled by the minion; only accept known keys and never eval or export them
+	local line key
+	while IFS= read -r line; do
+		[[ "$line" == *=* ]] || continue
+		key=${line%%=*}
+		case "$key" in
+			MAINIP|MNIC|NODE_DESCRIPTION|ES_HEAP_SIZE|PATCHSCHEDULENAME|INTERFACE|NODETYPE|CORECOUNT|LSHOSTNAME|LSHEAP|CPUCORES|IDH_MGTRESTRICT|IDH_SERVICES)
+				printf -v "$key" '%s' "${line#*=}"
+				;;
+			*)
+				log "WARN" "Ignoring unexpected install var from $MINION_ID: ${key:0:64}"
+				;;
+		esac
+	done <<< "$INSTALLVARS"
+
+	if [[ "$NODE_DESCRIPTION" == \'*\' ]]; then
+		NODE_DESCRIPTION=${NODE_DESCRIPTION:1:-1}
 	fi
 
 	log "INFO" "Fetched install info for $MINION_ID (node type: ${NODETYPE:-unset})"
@@ -176,6 +195,12 @@ function pcapspace() {
 		fi
 	fi
 
+	# Must be checked before arithmetic expansion, which evaluates array subscripts
+	if [[ ! "$SPACESIZE" =~ ^[0-9]+$ ]]; then
+		log "ERROR" "Invalid disk size for $MINION_ID: ${SPACESIZE:0:64}"
+		return 1
+	fi
+
 	local s=$(( $SPACESIZE / 1000000 ))
 	local s1=$(( $s / 4 * $PCAP_PERCENTAGE ))
 
@@ -1050,6 +1075,57 @@ function updateMineAndApplyStates() {
 	fi
 }
 
+# Values end up in a Jinja-rendered pillar and in bash, and may come from the minion
+function validate_minion_vars() {
+	local error_msg=""
+	# Inline rather than valid_ip4: so-common is not installed yet when setup runs -o=setup
+	local octet='(25[0-5]|2[0-4][0-9]|1?[0-9]?[0-9])'
+	local ip4_re="^($octet\.){3}$octet$"
+
+	case "$NODETYPE" in
+		EVAL|STANDALONE|MANAGER|MANAGERSEARCH|MANAGERHYPE|IMPORT)
+			# Manager pillars also rewrite the CA pillar, so never accept them from a remote node
+			[[ "$OPERATION" == "setup" ]] || error_msg="Node type $NODETYPE can only be configured during setup"
+			;;
+		FLEET|IDH|HEAVYNODE|SENSOR|SEARCHNODE|RECEIVER|HYPERVISOR|DESKTOP)
+			;;
+		*)
+			error_msg="Invalid node type: ${NODETYPE:0:64}"
+			;;
+	esac
+
+	if [[ -z "$error_msg" ]]; then
+		if [[ ! "$MAINIP" =~ $ip4_re ]]; then
+			error_msg="Invalid MAINIP: ${MAINIP:0:64}"
+		elif [[ ! "$MNIC" =~ ^[A-Za-z0-9._-]*$ ]]; then
+			error_msg="Invalid MNIC: ${MNIC:0:64}"
+		elif [[ ! "$INTERFACE" =~ ^[A-Za-z0-9._-]*$ ]]; then
+			error_msg="Invalid INTERFACE: ${INTERFACE:0:64}"
+		elif [[ ! "$LSHOSTNAME" =~ ^[A-Za-z0-9._-]*$ ]]; then
+			error_msg="Invalid LSHOSTNAME: ${LSHOSTNAME:0:64}"
+		elif [[ ! "$ES_HEAP_SIZE" =~ ^([0-9]+[kKmMgG]?)?$ ]]; then
+			error_msg="Invalid ES_HEAP_SIZE: ${ES_HEAP_SIZE:0:64}"
+		elif [[ ! "$LSHEAP" =~ ^([0-9]+[kKmMgG]?)?$ ]]; then
+			error_msg="Invalid LSHEAP: ${LSHEAP:0:64}"
+		elif [[ ! "$CORECOUNT" =~ ^[0-9]*$ ]]; then
+			error_msg="Invalid CORECOUNT: ${CORECOUNT:0:64}"
+		elif [[ ! "$CPUCORES" =~ ^[0-9]*$ ]]; then
+			error_msg="Invalid CPUCORES: ${CPUCORES:0:64}"
+		elif [[ ! "$IDH_MGTRESTRICT" =~ ^(True|False)?$ ]]; then
+			error_msg="Invalid IDH_MGTRESTRICT: ${IDH_MGTRESTRICT:0:64}"
+		fi
+	fi
+
+	if [[ -n "$error_msg" ]]; then
+		log "ERROR" "$error_msg"
+		echo "$error_msg"
+		return 1
+	fi
+
+	# Free text; removing braces is enough to prevent any Jinja delimiter
+	NODE_DESCRIPTION=${NODE_DESCRIPTION//[\{\}[:cntrl:]]/}
+}
+
 function setupMinionFiles() {
 	log "INFO" "Setting up minion files for $MINION_ID (pillar: $PILLARFILE)"
 	
@@ -1061,6 +1137,8 @@ function setupMinionFiles() {
 		return 1
 	fi
 
+	validate_minion_vars || return 1
+
 	# Create the base minion files
 	create_minion_files || return 1
 

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

@@ -20,7 +20,7 @@ is older than debounce_seconds, this script:
     with the deduped actions list passed as pillar kwargs
   * deletes the contributed intent files on successful dispatch
 
-Reactor sls files (push_suricata, push_strelka, push_pillar) write intents
+Reactor sls files (push_files, push_pillar) write intents
 but never dispatch directly
 """
 

salt/manager/tools/sbin/so-saltstack-update

@@ -124,8 +124,8 @@ copy_new_files() {
   
   rsync -a salt $default_salt_dir/
   rsync -a pillar $default_salt_dir/
-  chown -R socore:socore $default_salt_dir/salt
-  chown -R socore:socore $default_salt_dir/pillar
+  chown -R root:root $default_salt_dir/salt
+  chown -R root:root $default_salt_dir/pillar
   chmod 755 $default_salt_dir/pillar/firewall/addfirewall.sh
 
   rm -rf /tmp/sogh

salt/manager/tools/sbin/so-user

@@ -129,7 +129,8 @@ while [[ $# -gt 0 ]]; do
   esac
 done
 
-kratosUrl=${KRATOS_URL:-http://127.0.0.1:4434/admin}
+kratosContainer=${KRATOS_CONTAINER:-so-kratos}
+kratosUrl=${KRATOS_URL:-http://localhost:4434/admin}
 databasePath=${KRATOS_DB_PATH:-/nsm/kratos/db/db.sqlite}
 databaseTimeout=${KRATOS_DB_TIMEOUT:-5000}
 bcryptRounds=${BCRYPT_ROUNDS:-12}
@@ -154,6 +155,10 @@ function fail() {
   exit 1
 }
 
+function kratosCurl() {
+  docker exec "$kratosContainer" curl "$@"
+}
+
 function require() {
   cmd=$1
   which "$1" 2>&1 > /dev/null
@@ -164,18 +169,18 @@ function require() {
 function verifyEnvironment() {
   require "htpasswd"
   require "jq"
-  require "curl"
+  require "docker"
   require "openssl"
   require "sqlite3"
   [[ ! -f $databasePath ]] && fail "Unable to find database file; specify path via KRATOS_DB_PATH environment variable"
-  response=$(curl -Ss -L ${kratosUrl}/)
+  response=$(kratosCurl -Ss -L ${kratosUrl}/)
   [[ "$response" != "404 page not found" ]] && fail "Unable to communicate with Kratos; specify URL via KRATOS_URL environment variable"
 }
 
 function findIdByEmail() {
   email=${1,,}
 
-  response=$(curl -Ss -L ${kratosUrl}/identities)
+  response=$(kratosCurl -Ss -L ${kratosUrl}/identities)
   identityId=$(echo "${response}" | jq -r ".[] | select(.verifiable_addresses[0].value == \"$email\") | .id")
   echo $identityId
 }
@@ -416,7 +421,7 @@ function syncAll() {
 }
 
 function listUsers() {
-  response=$(curl -Ss -L ${kratosUrl}/identities)
+  response=$(kratosCurl -Ss -L ${kratosUrl}/identities)
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   users=$(echo "${response}" | jq -r ".[] | .verifiable_addresses[0].value" | sort)
@@ -495,7 +500,7 @@ function createUser() {
 EOF
   )
   
-  response=$(curl -Ss -L ${kratosUrl}/identities -d "$addUserJson")
+  response=$(kratosCurl -Ss -L ${kratosUrl}/identities -d "$addUserJson")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   identityId=$(echo "${response}" | jq -r ".id")
@@ -518,7 +523,7 @@ function updateStatus() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(curl -Ss -L "${kratosUrl}/identities/$identityId")
+  response=$(kratosCurl -Ss -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   schemaId=$(echo "$response" | jq -r .schema_id)
@@ -531,7 +536,7 @@ function updateStatus() {
     state="inactive"
   fi
   body="{ \"schema_id\": \"$schemaId\", \"state\": \"$state\", \"traits\": $traitBlock }"
-  response=$(curl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
+  response=$(kratosCurl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
   [[ $? != 0 ]] && fail "Unable to update user"
 }
 
@@ -550,7 +555,7 @@ function updateUserProfile() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(curl -Ss -L "${kratosUrl}/identities/$identityId")
+  response=$(kratosCurl -Ss -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   schemaId=$(echo "$response" | jq -r .schema_id)
@@ -559,7 +564,7 @@ function updateUserProfile() {
   traitBlock="{\"email\":\"$email\",\"firstName\":\"$firstName\",\"lastName\":\"$lastName\",\"note\":\"$note\"}"
 
   body="{ \"schema_id\": \"$schemaId\", \"state\": \"$state\", \"traits\": $traitBlock }"
-  response=$(curl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
+  response=$(kratosCurl -fSsL -XPUT -H "Content-Type: application/json" "${kratosUrl}/identities/$identityId" -d "$body")
   [[ $? != 0 ]] && fail "Unable to update user"
 }
 
@@ -569,7 +574,7 @@ function deleteUser() {
   identityId=$(findIdByEmail "$email")
   [[ ${identityId} == "" ]] && fail "User not found"
 
-  response=$(curl -Ss -XDELETE -L "${kratosUrl}/identities/$identityId")
+  response=$(kratosCurl -Ss -XDELETE -L "${kratosUrl}/identities/$identityId")
   [[ $? != 0 ]] && fail "Unable to communicate with Kratos"
 
   rolesTmpFile="${socRolesFile}.tmp"

salt/manager/tools/sbin/soup

@@ -28,6 +28,7 @@ INSTALLEDSALTVERSION=$(salt --versions-report | grep Salt: | awk '{print $2}')
 # percentage like "25%"). Empty means so-soup-grid-highstate uses the salt:auto_apply:batch
 # pillar default.
 BATCHSIZE=
+DEFAULT_DOCKER_RANGE='172.17.1.0/24'
 SOUP_LOG=/root/soup.log
 SOUP_DEBUG_LOG=/root/soup-debug.log
 WHATWOULDYOUSAYYAHDOHERE=soup
@@ -120,6 +121,9 @@ check_err() {
       161)
         echo 'Required intermediate Elasticsearch upgrade not complete'
       ;;
+      162)
+        echo 'One or more Elastic Agent nodes do not support the x86-64-v3 CPU instruction set'
+      ;;
       170)
         echo "Intermediate upgrade completed successfully to $next_step_so_version, but next soup to Security Onion $originally_requested_so_version could not be started automatically."
         echo "Start soup again manually to continue the upgrade to Security Onion $originally_requested_so_version."
@@ -331,29 +335,101 @@ check_pillar_items() {
 }
 
 check_cluster_health() {
+  # Require a 'green' cluster before upgrading
   echo "Checking Elasticsearch cluster health."
-  # Require a 'green' cluster before upgrading; anything less (yellow, red, or
-  # unreachable) blocks. Modeled on the wait used in so-elasticsearch-roles-load.
   if so-elasticsearch-query "_cluster/health?wait_for_status=green&timeout=120s" --fail > /dev/null 2>&1; then
     printf "\nThe Elasticsearch cluster is healthy (green). We can proceed with SOUP.\n\n"
+    return
+  fi
+
+  if command -v so-elasticsearch-troubleshoot > /dev/null 2>&1; then
+    printf "\nRunning so-elasticsearch-troubleshoot for additional detail.\n"
+    so-elasticsearch-troubleshoot || true
+  fi
+
+  printf "\nThe Elasticsearch cluster is not green. Resolve the cluster health issue so the cluster is green before running SOUP again.\n\n"
+  exit 0
+}
+
+no_soup_for_you() {
+  echo ""
+  echo "No soup for you!"
+  exit 162
+}
+
+check_cpu_compatibility() {
+  # Roles running a container built from the so-elastic-agent image; mirrors the
+  # elasticagent and elasticfleet entries in salt/reactor/pillar_push_map.yaml.
+  local cpu_target='G@role:so-heavynode or G@role:so-eval or G@role:so-fleet or G@role:so-import or G@role:so-manager or G@role:so-managerhype or G@role:so-managersearch or G@role:so-standalone'
+  local expected_nodes cpu_results node result confirm
+  local -a unsupported=() offline=()
+
+  echo "Checking that Elastic Agent nodes support the x86-64-v3 CPU instruction set now required by Elastic."
+
+  if [[ "$SKIP_CPU_CHECK" == "true" ]]; then
+    printf "\nSkipping the x86-64-v3 CPU check because --skip-cpu-check was specified.\n\n"
+    return
+  fi
+
+  # Nodes that never answer are absent from the results, so diff against who should have.
+  expected_nodes=$(salt -C "$cpu_target" --preview-target --out=json 2>/dev/null | jq -r '.[]?') || true
+  if [[ -z "$expected_nodes" ]]; then
+    printf "\nCould not determine which nodes run the Elastic Agent, so the x86-64-v3 CPU check cannot run.\n"
+    no_soup_for_you
+  fi
+
+  cpu_results=$(salt -t 30 -C "$cpu_target" cmd.run "/lib64/ld-linux-x86-64.so.2 --help | grep x86-64-v3" --out=json 2>/dev/null) || true
+
+  while IFS= read -r node; do
+    [[ -z "$node" ]] && continue
+    result=$(jq -r --arg node "$node" '.[$node] // empty' <<< "$cpu_results" 2>/dev/null)
+    if [[ -z "$result" || "$result" == *"did not return"* ]]; then
+      offline+=("$node")
+    elif [[ "$result" != *"x86-64-v3 (supported"* ]]; then
+      # glibc appends "(supported, searched)" only when supported; the open paren keeps
+      # this from matching a future "(unsupported".
+      unsupported+=("$node")
+    fi
+  done <<< "$expected_nodes"
+
+  if [[ ${#unsupported[@]} -eq 0 && ${#offline[@]} -eq 0 ]]; then
+    printf "\nAll Elastic Agent nodes support x86-64-v3. We can proceed with SOUP.\n\n"
+    return
+  fi
+
+  echo ""
+  if [[ ${#unsupported[@]} -gt 0 ]]; then
+    echo "The following node(s) do NOT support the x86-64-v3 CPU instruction set:"
+    printf '  %s\n' "${unsupported[@]}"
+    echo ""
+    echo "Upstream Elastic now builds its binaries for x86-64-v3, so these nodes can no"
+    echo "longer run Elastic. Upgrading them WILL BREAK them."
+    echo ""
+  fi
+  if [[ ${#offline[@]} -gt 0 ]]; then
+    echo "The following node(s) did not respond and could not be checked:"
+    printf '  %s\n' "${offline[@]}"
+    echo ""
+    echo "These nodes are offline, so we cannot confirm they support x86-64-v3, which"
+    echo "upstream Elastic now requires."
+    echo ""
+  fi
+
+  if [[ -n $UNATTENDED ]]; then
+    echo "Unattended mode cannot prompt for an override. Re-run soup interactively, or pass --skip-cpu-check to bypass this check."
+    no_soup_for_you
+  fi
+
+  read -rp "Type 'override' to continue anyway, or press Enter to exit: " confirm
+  if [[ "${confirm,,}" == "override" ]]; then
+    printf "\nOverride accepted. Continuing at your own risk.\n\n"
   else
-    printf "\nThe Elasticsearch cluster is not green. Please resolve the cluster health issue so the cluster is green before running SOUP again.\n\n"
-    exit 0
+    no_soup_for_you
   fi
 }
 
 check_fleet_server() {
   echo "Checking that Elastic Fleet Server is responding."
-  # Before checking fleet health, check for and fix known issue with elastic-agent container and fs.protected_symlinks
-  local protected_symlinks=$(sysctl -b fs.protected_symlinks)
-  if [[ "$protected_symlinks" == "1" ]]; then
-    # disable fs.protected_symlinks and restart elasticfleet
-    sysctl -w fs.protected_symlinks=0
-    docker stop so-elastic-fleet; docker rm -f so-elastic-fleet
-    printf "\nUpdated sysctl fs.protected_symlinks. Restarting fleet before running health check and continuing with soup.\n"
-    salt-call state.apply elasticfleet queue=True
-  fi
-  
   # Modeled on the wait_for_so-elastic-fleet state check in elasticfleet/enabled.sls,
   # which waits for HTTP 200 from the Fleet Server status API.
   if curl -sk --fail --retry 3 --retry-delay 10 --max-time 30 "https://localhost:8220/api/status" > /dev/null 2>&1; then
@@ -465,6 +541,19 @@ highstate() {
   salt-call state.highstate -l info queue=True
 }
 
+upgrade_searchnode_elasticsearch() {
+  # Run the elasticsearch state across the true elastic cluster (non-heavy) with a retry attempt
+  #   Excludes the manager, so that kibana & elasticfleet are not upgraded until searchnodes are upgraded.
+  echo "Getting ready to upgrade Elasticsearch across the grid. This may take a while..."
+  if salt -b 10% -C "I@elasticsearch:enabled and not G@role:so-heavynode and not G@id:${MINIONID}" state.apply elasticsearch queue=True; then
+    return 0
+  fi
+  
+  echo "Initial elasticsearch state attempt had a problem; retrying in 30 seconds."
+  sleep 30
+  salt -b 10% -C "I@elasticsearch:enabled and not G@role:so-heavynode and not G@id:${MINIONID}" state.apply elasticsearch queue=True
+}
+
 push_grid_highstate() {
   # Drive a batched, role-tiered highstate across the rest of the grid so remote minions
   # pick up this upgrade now instead of waiting up to ~2.5 hours for their own scheduled
@@ -493,11 +582,10 @@ push_grid_highstate() {
 masterlock() {
   echo "Locking Salt Master"
   mv -v $TOPFILE $BACKUPTOPFILE
-  # Render the real top file only for the host running soup; every other
-  # minion gets an empty top (no states) while the master is upgrading.
-  echo "{% if grains['id'] == '$MINIONID' %}" > $TOPFILE
-  cat $BACKUPTOPFILE >> $TOPFILE
-  echo "{% endif %}" >> $TOPFILE
+  echo "base:" > $TOPFILE
+  echo "  $MINIONID:" >> $TOPFILE
+  echo "    - ca" >> $TOPFILE
+  echo "    - elasticsearch" >> $TOPFILE
 }
 
 masterunlock() {
@@ -518,6 +606,7 @@ preupgrade_changes() {
     [[ "$INSTALLEDVERSION" == "3.0.0" ]] && up_to_3.1.0
     [[ "$INSTALLEDVERSION" == "3.1.0" ]] && up_to_3.2.0
     [[ "$INSTALLEDVERSION" == "3.2.0" ]] && up_to_3.3.0
+    [[ "$INSTALLEDVERSION" == "3.3.0" ]] && up_to_3.4.0
     true
 }
 
@@ -536,6 +625,7 @@ postupgrade_changes() {
     [[ "$POSTVERSION" == "3.0.0" ]] && post_to_3.1.0
     [[ "$POSTVERSION" == "3.1.0" ]] && post_to_3.2.0
     [[ "$POSTVERSION" == "3.2.0" ]] && post_to_3.3.0
+    [[ "$POSTVERSION" == "3.3.0" ]] && post_to_3.4.0
     # All applicable post-upgrade steps completed; clear the resume marker.
     rm -f "$POSTVERSION_FILE"
     true
@@ -1013,9 +1103,6 @@ update_kafka_metadata() {
 up_to_3.2.0() {
   ensure_salt_local_pillar
 
-  # download 9.3.7 elastic agent packages
-  determine_elastic_agent_upgrade
-
   fix_logstash_0013_lumberjack_pipeline_name
 
   pin_elasticsearch_data_retention_method
@@ -1034,10 +1121,6 @@ post_to_3.2.0() {
   # SOC database bootstrap is handled by the postgres.enabled highstate.
   scrub_postgres_log_passwords
 
-  # Generate 9.3.7 elastic agent installers
-  echo "Regenerating Elastic Agent Installers"
-  /sbin/so-elastic-agent-gen-installers
-
   kibana_backport_streams_index_template
 
   update_kafka_metadata "4.3"
@@ -1047,19 +1130,16 @@ post_to_3.2.0() {
 ### 3.2.0 End ###
 
 ### 3.3.0 Scripts ###
-
- # Sets fs.protected_symlinks=0
- #
- # Elastic Agent docker image chowns its directory to the running UID 
- # but does not chown the elastic-agent launcher symlink. 
- # Preventing non-root users from following that launcher symlink.
-disable_sysctl_fs_protected_symlink() {
-  salt -C 'I@stig:enabled' state.single sysctl.present name=fs.protected_symlinks value=0 config=/etc/sysctl.conf || true
-}
-    
 up_to_3.3.0() {
-  disable_sysctl_fs_protected_symlink
+  # download 9.4.5 elastic agent packages
+  determine_elastic_agent_upgrade
   
+  # remove existing (patched) elasticsearch index template to match integration naming change
+  if ! remove_elasticsearch_index_template "so-logs-sentinel_one_cloud_funnel.login" "sentinel_one_cloud_funnel.login changed to sentinel_one_cloud_funnel.logins"; then
+    FINAL_MESSAGE_QUEUE+=("WARNING: Unable to automatically remove the so-logs-sentinel_one_cloud_funnel.login index template. This step can be performed manually using the following command:")
+    FINAL_MESSAGE_QUEUE+=("    - sudo so-elasticsearch-query _index_template/so-logs-sentinel_one_cloud_funnel.login -XDELETE && so-checkin")
+  fi
+
   INSTALLEDVERSION=3.3.0
 }
 
@@ -1086,10 +1166,92 @@ post_to_3.3.0() {
   # Recollate again since some internal DBs were excluded during 3.2.0 soup
   recollate_postgres
 
+  # Generate 9.4.5 elastic agent installers
+  echo "Regenerating Elastic Agent Installers"
+  /sbin/so-elastic-agent-gen-installers
+
   telegraf_repair
+
+  set_postversion 3.3.0
 }
 ### 3.3.0 End ###
 
+### 3.4.0 Scripts ###
+up_to_3.4.0() {
+  set_soauth_range
+
+  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 >> $SOUP_LOG 2>&1
+
+  INSTALLEDVERSION=3.4.0
+}
+
+set_soauth_range() {
+  local pillar_file=/opt/so/saltstack/local/pillar/docker/soc_docker.sls
+  local current_range suggested authnet authgw input
+
+  [[ -f "$pillar_file" ]] || return 0
+
+  current_range=$(so-yaml.py get -r "$pillar_file" docker.range 2>/dev/null) || return 0
+
+  # A default range gets the 172.17.2.0/24 from docker/defaults.yaml, same as a fresh
+  # install, so there is nothing to ask about.
+  [[ -n "$current_range" && "$current_range" != "$DEFAULT_DOCKER_RANGE" ]] || return 0
+
+  if so-yaml.py get -r "$pillar_file" docker.networks.soauth.range >/dev/null 2>&1; then
+    return 0
+  fi
+
+  suggested=$(echo "${current_range%%/*}" | awk -F'.' '{ printf "%s.%s.%s.%s", $1, $2, ($3 + 1) % 256, $4 }')
+
+  if [[ -z $UNATTENDED ]]; then
+    echo ""
+    echo "This grid uses a custom Docker range ($current_range). The authentication"
+    echo "services are moving to their own isolated network, which needs a second /24"
+    echo "that does not overlap it."
+    echo ""
+    while :; do
+      read -rp "Enter the network without the /24 suffix, or press Enter for ${suggested}: " input
+      [[ -z "$input" ]] && input="$suggested"
+      if valid_soauth_range "$input" "$current_range"; then
+        authnet="$input"
+        break
+      fi
+      echo "That range must be a valid IPv4 network, must not be within 172.17.0.0/24, and must not overlap ${current_range}."
+    done
+  else
+    if ! valid_soauth_range "$suggested" "$current_range"; then
+      FINAL_MESSAGE_QUEUE+=("WARNING: Unable to pick a range for the authentication network alongside $current_range. Set it manually before the next highstate:")
+      FINAL_MESSAGE_QUEUE+=("    - so-yaml.py add $pillar_file docker.networks.soauth.range <network>/24")
+      FINAL_MESSAGE_QUEUE+=("    - so-yaml.py add $pillar_file docker.networks.soauth.gateway <gateway>")
+      return 0
+    fi
+    authnet="$suggested"
+    FINAL_MESSAGE_QUEUE+=("NOTE: The authentication services moved to an isolated Docker network and were assigned ${authnet}/24.")
+    FINAL_MESSAGE_QUEUE+=("    - If that conflicts with your environment, update docker.networks.soauth in $pillar_file and run so-checkin.")
+  fi
+
+  authgw=$(echo "$authnet" | awk -F'.' '{print $1,$2,$3,1}' OFS='.')
+
+  echo "Assigning the authentication network the range ${authnet}/24."
+  so-yaml.py add "$pillar_file" docker.networks.soauth.range "${authnet}/24" >> $SOUP_LOG 2>&1
+  so-yaml.py add "$pillar_file" docker.networks.soauth.gateway "$authgw" >> $SOUP_LOG 2>&1
+}
+
+valid_soauth_range() {
+  local candidate=$1 docker_range=$2
+
+  valid_ip4 "$candidate" || return 1
+  [[ $candidate =~ ^172\.17\.0\. ]] && return 1
+  [[ "${candidate}/24" == "$docker_range" ]] && return 1
+  return 0
+}
+
+post_to_3.4.0() {
+  set_postversion 3.4.0
+}
+### 3.4.0 End ###
+
 
 repo_sync() {
   echo "Sync the local repo."
@@ -1359,11 +1521,12 @@ verify_es_version_compatibility() {
     local is_active_intermediate_upgrade=1
     # supported upgrade paths for SO-ES versions
     declare -A es_upgrade_map=(
-        ["8.18.4"]="8.18.6 8.18.8 9.0.8"
+      ["8.18.4"]="8.18.6 8.18.8 9.0.8"
 	    ["8.18.6"]="8.18.8 9.0.8"
 	    ["8.18.8"]="9.0.8"
-        ["9.0.8"]="9.3.3 9.3.7"
-        ["9.3.3"]="9.3.7"
+      ["9.0.8"]="9.3.3 9.3.7 9.4.5"
+      ["9.3.3"]="9.3.7 9.4.5"
+      ["9.3.7"]="9.4.5"
     )
 
     # Elasticsearch MUST upgrade through these versions
@@ -1973,6 +2136,9 @@ main() {
 
   echo "Let's see if we need to update Security Onion."
   upgrade_check
+
+  check_cpu_compatibility
+
   upgrade_space
 
   echo "Verifying Elasticsearch version compatibility across the grid before upgrading."
@@ -2139,12 +2305,28 @@ main() {
 
     # ensure the mine is updated and populated before highstates run, following the salt-master restart
     update_salt_mine
-
+    
+    # kick off a searchnode elasticsearch upgrade
+    set +e
+    if [[ "$es_version" != "$target_es_version" ]]; then
+      if salt-key -L accepted | grep -q "_searchnode$" 2>/dev/null; then
+        # only run if there is atleast 1 searchnode
+        upgrade_searchnode_elasticsearch
+      fi
+    fi
+    set -e
+    
     highstate
     check_saltmaster_status
     postupgrade_changes
     [[ $is_airgap -eq 0 ]] && unmount_update
-
+    
+    if [[ "$es_version" != "$target_es_version" ]]; then
+      # Run final elasticsearch / fleet state on manager to ensure addon index templates are created/regenerated and loaded
+      echo "Running final Elastic states at $(date +"%T.%6N"), after upgrade to $NEWVERSION"
+      salt-call state.apply elasticsearch,elasticfleet queue=True
+    fi
+    
     echo ""
     echo "Upgrade to $NEWVERSION complete."
 
@@ -2235,6 +2417,17 @@ fi
   echo "### soup has been served at $(date) ###"
 }
 
+SKIP_CPU_CHECK=false
+declare -a SOUP_ARGS=()
+for arg in "$@"; do
+  if [[ "$arg" == "--skip-cpu-check" ]]; then
+    SKIP_CPU_CHECK=true
+  else
+    SOUP_ARGS+=("$arg")
+  fi
+done
+set -- "${SOUP_ARGS[@]}"
+
 while getopts ":b:f:y" opt; do
   case ${opt} in
     b )
@@ -2258,7 +2451,7 @@ while getopts ":b:f:y" opt; do
       ISOLOC="$OPTARG"
     ;;
     \? )
-      echo "Usage: soup [-b] [-y] [-f <iso location>]"
+      echo "Usage: soup [-b] [-y] [-f <iso location>] [--skip-cpu-check]"
       exit 1
     ;;
     : )

salt/nginx/config.sls

@@ -57,8 +57,8 @@ nginx_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://nginx/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #nginx_sbin_jinja:

salt/nginx/etc/nginx.conf

@@ -183,7 +183,7 @@ http {
 		ssl_prefer_server_ciphers on;
 		ssl_protocols TLSv1.2 TLSv1.3;
 
-		location ~* (^/login/.*|^/js/.*|^/css/.*|^/images/.*|^/pages/.*|^/docs/.*) {
+		location ~* (^/login|^/login/.*|^/js/.*|^/css/.*|^/images/.*|^/pages/.*|^/docs/.*) {
 			proxy_pass            http://{{ GLOBALS.manager }}:9822;
 			proxy_read_timeout    90;
 			proxy_connect_timeout 90;
@@ -260,7 +260,7 @@ http {
 		}
 
 {%  if 'api' in salt['pillar.get']('features', []) %}
-		location ~* (^/oauth2/token.*|^.well-known/jwks.json|^.well-known/openid-configuration) {
+		location ~* (^/oauth2/token.*|^/\.well-known/jwks.json|^/\.well-known/openid-configuration) {
 			limit_req             zone=auth_throttle burst={{ NGINXMERGED.config.throttle_login_burst }} nodelay;
 			limit_req_status      429;
 			proxy_pass            http://{{ GLOBALS.manager }}:4444;

salt/reactor/pillar_push_map.yaml

@@ -1,3 +1,6 @@
+# Read by push_pillar.sls (SOC config saves) and push_files.sls (local/salt file edits);
+# both key on the app name. An app missing here waits for the next scheduled highstate.
+#
 # One pillar directory can map to multiple (state, tgt) actions.
 # tgt is a raw salt compound expression. tgt_type is always "compound".
 # Per-action `batch` / `batch_wait` override the orch defaults (25% / 15s).

salt/reactor/push_files.sls

@@ -0,0 +1,131 @@
+#!py
+
+# Reactor invoked by local_files_beacon when a watched directory under
+# /opt/so/saltstack/local/salt/ changes. The beacon tag is an app name in
+# pillar_push_map.yaml, so file changes and pillar changes route through the same
+# table -- see salt/reactor/push_pillar.sls.
+#
+# The app comes from the event tag, not the payload: salt's beacon loop pops the
+# beacon's 'tag' key off the data and appends it to the event tag instead (see
+# salt/beacons/__init__.py). The reactor renderer sets both `tag` and `data` as
+# module globals.
+#
+# Reactors never dispatch directly. The so-push-drainer schedule picks up ready
+# intents, dedupes across pending files, and dispatches orch.push_batch.
+
+import fcntl
+import json
+import logging
+import os
+import time
+
+from salt.client import Caller
+import yaml
+
+LOG = logging.getLogger(__name__)
+
+PENDING_DIR = '/opt/so/state/push_pending'
+LOCK_FILE = os.path.join(PENDING_DIR, '.lock')
+MAX_PATHS = 20
+
+# The pillar_push_map.yaml is shipped via salt:// but the reactor runs on the
+# master, which mounts the default saltstack tree at this path.
+PUSH_MAP_PATH = '/opt/so/saltstack/default/salt/reactor/pillar_push_map.yaml'
+
+_PUSH_MAP_CACHE = {'mtime': 0, 'data': None}
+
+
+def _load_push_map():
+    try:
+        st = os.stat(PUSH_MAP_PATH)
+    except OSError:
+        LOG.warning('push_files: %s not found', PUSH_MAP_PATH)
+        return {}
+    if _PUSH_MAP_CACHE['mtime'] != st.st_mtime:
+        try:
+            with open(PUSH_MAP_PATH, 'r') as f:
+                _PUSH_MAP_CACHE['data'] = yaml.safe_load(f) or {}
+        except Exception:
+            LOG.exception('push_files: failed to load %s', PUSH_MAP_PATH)
+            _PUSH_MAP_CACHE['data'] = {}
+        _PUSH_MAP_CACHE['mtime'] = st.st_mtime
+    return _PUSH_MAP_CACHE['data'] or {}
+
+
+def _push_enabled():
+    try:
+        caller = Caller()
+        return bool(caller.cmd('pillar.get', 'salt:auto_apply:enabled', True))
+    except Exception:
+        LOG.exception('push_files: pillar.get salt:auto_apply:enabled failed, assuming enabled')
+        return True
+
+
+def _write_intent(key, actions, path):
+    now = time.time()
+    try:
+        os.makedirs(PENDING_DIR, exist_ok=True)
+    except OSError:
+        LOG.exception('push_files: cannot create %s', PENDING_DIR)
+        return
+
+    intent_path = os.path.join(PENDING_DIR, '{}.json'.format(key))
+    lock_fd = os.open(LOCK_FILE, os.O_CREAT | os.O_RDWR, 0o644)
+    try:
+        fcntl.flock(lock_fd, fcntl.LOCK_EX)
+
+        intent = {}
+        if os.path.exists(intent_path):
+            try:
+                with open(intent_path, 'r') as f:
+                    intent = json.load(f)
+            except (IOError, ValueError):
+                intent = {}
+
+        intent.setdefault('first_touch', now)
+        intent['last_touch'] = now
+        intent['actions'] = actions
+        paths = intent.get('paths', [])
+        if path and path not in paths:
+            paths.append(path)
+            paths = paths[-MAX_PATHS:]
+        intent['paths'] = paths
+
+        tmp_path = intent_path + '.tmp'
+        with open(tmp_path, 'w') as f:
+            json.dump(intent, f)
+        os.rename(tmp_path, intent_path)
+    except Exception:
+        LOG.exception('push_files: failed to write intent %s', intent_path)
+    finally:
+        try:
+            fcntl.flock(lock_fd, fcntl.LOCK_UN)
+        finally:
+            os.close(lock_fd)
+
+
+def run():
+    if not _push_enabled():
+        LOG.info('push_files: push disabled, skipping')
+        return {}
+
+    event = data.get('data', data)  # noqa: F821 -- data provided by reactor
+    path = event.get('path', '')
+    app = tag.rsplit('/', 1)[-1].strip()  # noqa: F821 -- tag provided by reactor
+
+    if not app:
+        LOG.debug('push_files: ignoring event with no app segment: tag=%s', tag)  # noqa: F821
+        return {}
+
+    entry = _load_push_map().get(app)
+    if not entry:
+        LOG.warning(
+            'push_files: app "%s" is not in pillar_push_map.yaml; change will be '
+            'picked up at the next scheduled highstate (path=%s)',
+            app, path,
+        )
+        return {}
+
+    _write_intent('files_{}'.format(app), list(entry), path)
+    LOG.info('push_files: intent updated for %s (path=%s)', app, path)
+    return {}

salt/reactor/push_strelka.sls

@@ -1,96 +0,0 @@
-#!py
-
-# Reactor invoked by the rules_beacon poll beacon (salt/_beacons/rules_beacon.py) on rule
-# file changes under /opt/so/saltstack/local/salt/strelka/rules/compiled/.
-#
-# Writes (or updates) a push intent at /opt/so/state/push_pending/rules_strelka.json
-# and returns {}. The so-push-drainer schedule picks up ready intents, dedupes
-# across pending files, and dispatches orch.push_batch. Reactors never dispatch
-# directly
-
-import fcntl
-import json
-import logging
-import os
-import time
-
-from salt.client import Caller
-
-LOG = logging.getLogger(__name__)
-
-PENDING_DIR = '/opt/so/state/push_pending'
-LOCK_FILE = os.path.join(PENDING_DIR, '.lock')
-MAX_PATHS = 20
-
-# Mirrors GLOBALS.sensor_roles in salt/vars/globals.map.jinja. Sensor-side
-# strelka runs on exactly these four roles; so-import gets strelka.manager
-# instead, which is not fired on pillar changes.
-SENSOR_ROLES = ['so-eval', 'so-heavynode', 'so-sensor', 'so-standalone']
-
-
-def _sensor_compound():
-    return ' or '.join('G@role:{}'.format(r) for r in SENSOR_ROLES)
-
-
-def _push_enabled():
-    try:
-        caller = Caller()
-        return bool(caller.cmd('pillar.get', 'salt:auto_apply:enabled', True))
-    except Exception:
-        LOG.exception('push_strelka: pillar.get salt:auto_apply:enabled failed, assuming enabled')
-        return True
-
-
-def _write_intent(key, actions, path):
-    now = time.time()
-    try:
-        os.makedirs(PENDING_DIR, exist_ok=True)
-    except OSError:
-        LOG.exception('push_strelka: cannot create %s', PENDING_DIR)
-        return
-
-    intent_path = os.path.join(PENDING_DIR, '{}.json'.format(key))
-    lock_fd = os.open(LOCK_FILE, os.O_CREAT | os.O_RDWR, 0o644)
-    try:
-        fcntl.flock(lock_fd, fcntl.LOCK_EX)
-
-        intent = {}
-        if os.path.exists(intent_path):
-            try:
-                with open(intent_path, 'r') as f:
-                    intent = json.load(f)
-            except (IOError, ValueError):
-                intent = {}
-
-        intent.setdefault('first_touch', now)
-        intent['last_touch'] = now
-        intent['actions'] = actions
-        paths = intent.get('paths', [])
-        if path and path not in paths:
-            paths.append(path)
-            paths = paths[-MAX_PATHS:]
-        intent['paths'] = paths
-
-        tmp_path = intent_path + '.tmp'
-        with open(tmp_path, 'w') as f:
-            json.dump(intent, f)
-        os.rename(tmp_path, intent_path)
-    except Exception:
-        LOG.exception('push_strelka: failed to write intent %s', intent_path)
-    finally:
-        try:
-            fcntl.flock(lock_fd, fcntl.LOCK_UN)
-        finally:
-            os.close(lock_fd)
-
-
-def run():
-    if not _push_enabled():
-        LOG.info('push_strelka: push disabled, skipping')
-        return {}
-
-    path = data.get('path', '')  # noqa: F821 -- data provided by reactor
-    actions = [{'state': 'strelka', 'tgt': _sensor_compound()}]
-    _write_intent('rules_strelka', actions, path)
-    LOG.info('push_strelka: intent updated for path=%s', path)
-    return {}

salt/reactor/push_suricata.sls

@@ -1,95 +0,0 @@
-#!py
-
-# Reactor invoked by the rules_beacon poll beacon (salt/_beacons/rules_beacon.py) on rule
-# file changes under /opt/so/saltstack/local/salt/suricata/rules/.
-#
-# Writes (or updates) a push intent at /opt/so/state/push_pending/rules_suricata.json
-# and returns {}. The so-push-drainer schedule picks up ready intents, dedupes
-# across pending files, and dispatches orch.push_batch. Reactors never dispatch
-# directly
-
-import fcntl
-import json
-import logging
-import os
-import time
-
-from salt.client import Caller
-
-LOG = logging.getLogger(__name__)
-
-PENDING_DIR = '/opt/so/state/push_pending'
-LOCK_FILE = os.path.join(PENDING_DIR, '.lock')
-MAX_PATHS = 20
-
-# Mirrors GLOBALS.sensor_roles in salt/vars/globals.map.jinja. Suricata also
-# runs on so-import per salt/top.sls, so that role is appended below.
-SENSOR_ROLES = ['so-eval', 'so-heavynode', 'so-sensor', 'so-standalone']
-
-
-def _sensor_compound_plus_import():
-    return ' or '.join('G@role:{}'.format(r) for r in SENSOR_ROLES) + ' or G@role:so-import'
-
-
-def _push_enabled():
-    try:
-        caller = Caller()
-        return bool(caller.cmd('pillar.get', 'salt:auto_apply:enabled', True))
-    except Exception:
-        LOG.exception('push_suricata: pillar.get salt:auto_apply:enabled failed, assuming enabled')
-        return True
-
-
-def _write_intent(key, actions, path):
-    now = time.time()
-    try:
-        os.makedirs(PENDING_DIR, exist_ok=True)
-    except OSError:
-        LOG.exception('push_suricata: cannot create %s', PENDING_DIR)
-        return
-
-    intent_path = os.path.join(PENDING_DIR, '{}.json'.format(key))
-    lock_fd = os.open(LOCK_FILE, os.O_CREAT | os.O_RDWR, 0o644)
-    try:
-        fcntl.flock(lock_fd, fcntl.LOCK_EX)
-
-        intent = {}
-        if os.path.exists(intent_path):
-            try:
-                with open(intent_path, 'r') as f:
-                    intent = json.load(f)
-            except (IOError, ValueError):
-                intent = {}
-
-        intent.setdefault('first_touch', now)
-        intent['last_touch'] = now
-        intent['actions'] = actions
-        paths = intent.get('paths', [])
-        if path and path not in paths:
-            paths.append(path)
-            paths = paths[-MAX_PATHS:]
-        intent['paths'] = paths
-
-        tmp_path = intent_path + '.tmp'
-        with open(tmp_path, 'w') as f:
-            json.dump(intent, f)
-        os.rename(tmp_path, intent_path)
-    except Exception:
-        LOG.exception('push_suricata: failed to write intent %s', intent_path)
-    finally:
-        try:
-            fcntl.flock(lock_fd, fcntl.LOCK_UN)
-        finally:
-            os.close(lock_fd)
-
-
-def run():
-    if not _push_enabled():
-        LOG.info('push_suricata: push disabled, skipping')
-        return {}
-
-    path = data.get('path', '')  # noqa: F821 -- data provided by reactor
-    actions = [{'state': 'suricata', 'tgt': _sensor_compound_plus_import()}]
-    _write_intent('rules_suricata', actions, path)
-    LOG.info('push_suricata: intent updated for path=%s', path)
-    return {}

salt/redis/config.sls

@@ -50,16 +50,16 @@ redis_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://redis/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 redis_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://redis/tools/sbin_jinja
-    - user: 939
-    - group: 939 
+    - user: root
+    - group: root
     - file_mode: 755
     - template: jinja
 

salt/salt/files/reactor_pushstate.conf

@@ -1,7 +1,5 @@
 reactor:
-  - 'salt/beacon/*/rules_beacon/suricata':
-    - salt://reactor/push_suricata.sls
-  - 'salt/beacon/*/rules_beacon/strelka':
-    - salt://reactor/push_strelka.sls
+  - 'salt/beacon/*/local_files_beacon/*':
+    - salt://reactor/push_files.sls
   - 'salt/beacon/*/postgres_pillar_beacon/audit_settings':
     - salt://reactor/push_pillar.sls

salt/salt/init.sls

@@ -3,6 +3,8 @@ salt_bootstrap:
   file.managed:
     - name: /usr/sbin/bootstrap-salt.sh
     - source: salt://salt/scripts/bootstrap-salt.sh
+    - user: root
+    - group: root
     - mode: 755
     - show_changes: False
 
@@ -10,6 +12,6 @@ salt_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://salt/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755

salt/sensor/init.sls

@@ -35,6 +35,8 @@ combine_bond_script:
   file.managed:
     - name: /usr/sbin/so-combine-bond
     - source: salt://sensor/tools/sbin_jinja/so-combine-bond
+    - user: root
+    - group: root
     - mode: 755
     - template: jinja
     - defaults:

salt/sensoroni/config.sls

@@ -64,8 +64,8 @@ sensoroni_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://sensoroni/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #sensoroni_sbin_jinja:

salt/sensoroni/files/analyzers/whoislookup/requirements.txt

@@ -1,2 +1,3 @@
-requests>=2.31.0
-whoisit>=2.7.0
+requests>=2.34.0
+whoisit>=4.0.5
+anyio>=4.15.1

salt/soc/config.sls

@@ -171,8 +171,8 @@ soc_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://soc/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 #soc_sbin_jinja:

salt/soc/defaults.map.jinja

@@ -14,6 +14,8 @@
 {%   do SOCDEFAULTS.soc.config.server.modules[module].update({'hostUrl': application_url}) %}
 {% endfor %}
 
+{% do SOCDEFAULTS.soc.config.server.modules.kratos.update({'publicHostUrl': 'http://' ~ DOCKERMERGED.containers['so-kratos'].ips['soauth'] ~ ':4433/'}) %}
+
 {# add all grid heavy nodes to soc.server.modules.elastic.remoteHostUrls #}
 {% for node_type, minions in salt['pillar.get']('elasticsearch:nodes', {}).items() %}
 {%   if node_type in ['heavynode'] %}

salt/soc/defaults.yaml

@@ -1380,6 +1380,7 @@ soc:
           retryFailureMaxAttempts: 5
         kratos:
           hostUrl:
+          publicHostUrl:
         hydra:
           hostUrl:
         elastalertengine:
@@ -1493,6 +1494,9 @@ soc:
           org: Security Onion
           bucket: telegraf/so_short_term
           verifyCert: false
+        notification:
+          dismissedPruneDays: 30
+          enabled: true
         playbook:
           autoUpdateEnabled: true
           playbookImportFrequencySeconds: 86400
@@ -1538,8 +1542,9 @@ soc:
             Orchestrator: sonnet@SOAI
             Investigator: gemma@SOAI
             DetectionEngineer: gemma@SOAI
-          useMemory: true
+          useMemory: false
           useMemoryScanner: false
+          dontScanBefore: ""
           memoryScanIntervalSeconds: 300
           memoryProximityThreshold: 0.8
           messageProximityThreshold: 0.5
@@ -1547,9 +1552,78 @@ soc:
           maxGlobalMemoriesToInclude: 5
           maxUserMemoriesToReconcile: 20
           maxGlobalMemoriesToReconcile: 20
+          memoryExtractBatchSize: 5
+          maxMemoryRetries: 2
           memoryModel: gemma@SOAI
           embedModel: amazon.titan-embed-text-v2@SOAI
           reconcileModel: gemma@SOAI
+          memoryPersona: ""
+          reconcilePersona: ""
+          toolUseTurnAttempts: 12
+          toolUseTurnDelayMs: 175
+          tools:
+            filterEventFields:
+              - "@timestamp"
+              - "client.name"
+              - "destination.ip"
+              - "destination.port"
+              - "destination.geo.country_name"
+              - "dns.query.name"
+              - "dns.query_name"
+              - "event.action"
+              - "event.category"
+              - "event.module"
+              - "event.dataset"
+              - "event.outcome"
+              - "event.severity"
+              - "event.severity_label"
+              - "event.type"
+              - "event_data.agent.name"
+              - "event_data.host.os.name"
+              - "file.mime_type"
+              - "file.name"
+              - "hash.md5"
+              - "hash.sha1"
+              - "host.mac"
+              - "host.name"
+              - "host.os.name"
+              - "http.method"
+              - "http.useragent"
+              - "http.virtual_host"
+              - "log.id.uid"
+              - "network.community_id"
+              - "network.protocol"
+              - "network.transport"
+              - "notice.message"
+              - "observer.name"
+              - "process.name"
+              - "process.executable"
+              - "process.entity_id"
+              - "process.command_line"
+              - "process.Ext.ancestry"
+              - "process.parent.entity_id"
+              - "process.parent.command_line"
+              - "rule.category"
+              - "rule.name"
+              - "rule.uuid"
+              - "software.name"
+              - "software.type"
+              - "software.version.unparsed"
+              - "source.ip"
+              - "source.port"
+              - "source.geo.country_name"
+              - "ssh.cypher_algorithm"
+              - "ssh.client"
+              - "ssh.server"
+              - "ssl.cipher"
+              - "ssl.server_name"
+              - "ssl.version"
+              - "system.auth.sudo.command"
+              - "user.name"
+              - "user.domain"
+              - "user.effective.name"
+              - "weird.name"
+              - "tags"
         onionconfig:
           saltstackDir: /opt/so/saltstack
           bypassEnabled: false
@@ -2725,7 +2799,7 @@ soc:
             - id: sonnet
               displayName: Claude Sonnet
               origin: USA
-              contextLimitSmall: 200000
+              contextLimitSmall: 1000000
               contextLimitLarge: 1000000
               lowBalanceColorAlert: 500000
               enabled: true

salt/soc/dyanno/hypervisor/init.sls

@@ -18,8 +18,8 @@ hypervisor_annotation:
     - name: /opt/so/saltstack/default/salt/hypervisor/soc_hypervisor.yaml
     - source: salt://soc/dyanno/hypervisor/soc_hypervisor.yaml.jinja
     - template: jinja
-    - user: socore
-    - group: socore
+    - user: root
+    - group: root
     - defaults:
         HYPERVISORS: {{ HYPERVISORS }}
         baseDomainStatus: {{ salt['pillar.get']('baseDomain:status', 'Initialized') }}

salt/soc/enabled.sls

@@ -23,7 +23,9 @@ so-soc:
     - name: so-soc
     - networks:
       - sobridge:
-        - ipv4_address: {{ DOCKERMERGED.containers['so-soc'].ip }}
+        - ipv4_address: {{ DOCKERMERGED.containers['so-soc'].ips['sobridge'] }}
+      - soauth:
+        - ipv4_address: {{ DOCKERMERGED.containers['so-soc'].ips['soauth'] }}
     - binds:
       - /nsm/rules:/nsm/rules:rw
       - /opt/so/conf/strelka:/opt/sensoroni/yara:rw

salt/soc/soc_soc.yaml

@@ -155,6 +155,15 @@ soc:
         description: Path to custom markdown templates for PDF report generation. All markdown files in this directory will be available as custom reports in the SOC Reports interface.
         global: True
         advanced: True
+      schedules:
+        title: Schedules
+        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
       subgrids:
         title: Subordinate Grids
         description: |
@@ -481,6 +490,29 @@ soc:
             global: True
             advanced: True
             forcedType: bool
+        notification:
+          destinations:
+            title: Notification Destinations
+            description: JSON list of notifications. Modify via the SOC Notifications view.
+            readonlyUi: True
+            global: True
+            advanced: True
+            forcedType: string
+            syntax: json
+            storage: db
+          dismissedPruneDays:
+            title: Dismissed Retention Days
+            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
+            global: True
         postgres:
           host:
             description: Hostname or IP address of the PostgreSQL server used by SOC. Defaults to the manager hostname.
@@ -507,6 +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.
@@ -765,6 +839,7 @@ soc:
                 - gemini
                 - openai_responses
                 - openai_chat
+                - openai_embeddings
             - field: apiUrl
               label: API URL
               required: False
@@ -858,6 +933,12 @@ soc:
             description: Enables the memory scanner for automatic memory extraction from historical sessions.
             global: True
             forcedType: bool
+          dontScanBefore:
+            description: A date specifying how far back to scan for memories. Must be in UTC format (2026-08-31T22:05:48Z).
+            regex: '^(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(\.\d+)?Z)?$'
+            regexFailureMessage: Expecting date in RFC3339 format (2026-08-31T22:05:48Z)
+            global: True
+            advanced: True
           memoryScanIntervalSeconds:
             description: How long to wait in seconds between attempts to scan sessions for new memories.
             global: True
@@ -889,6 +970,37 @@ soc:
           reconcileModel:
             description: The model to use when reconciling memories that contain nearly the same content.
             global: True
+          memoryPersona:
+            description: Text appended to the built-in prompt of the memory extraction agent, managed from the Agent Studio. Use it to steer what is worth remembering.
+            global: True
+            readonlyUi: True
+            multiline: True
+          reconcilePersona:
+            description: Text appended to the built-in prompt of the memory reconciliation agent, managed from the Agent Studio. Use it to steer how new memories are merged with existing ones.
+            global: True
+            readonlyUi: True
+            multiline: True
+          toolUseTurnAttempts:
+            description: Number of times the API will retry looking up a tool request that has finished streaming but has not yet been saved to the database. Each retry waits toolUseTurnDelayMs before checking again. If tool auto-approval fails intermittently, increasing this value gives the message more time to be saved.
+            global: True
+            advanced: True
+          toolUseTurnDelayMs:
+            description: Milliseconds to wait between attempts to look up a tool request that has finished streaming but has not yet been saved to the database. The API retries up to toolUseTurnAttempts times, so this value times the attempt count is the maximum wait before auto-approval fails. Increase it if tool auto-approval fails intermittently.
+            global: True
+            advanced: True
+          memoryExtractBatchSize:
+            description: Max number of a session's messages that will be processed for memory extractions at a time. Larger values are more efficient but risk exceeding the memory extraction LLM's size limits, due to the variable and unpredictable size of each message.
+            global: True
+            advanced: True
+          maxMemoryRetries:
+            description: The number of times to retry extracting memories from a session if errors occur.
+            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.
+              global: True
+              multiline: True
       client:
         assistant:
           enabled:

salt/stig/enabled.sls

@@ -65,15 +65,6 @@ run_remediate:
     - success_retcodes:
       - 2
 
-# Elastic Agent docker image chowns its directory to the running UID but does not
-#  chown the elastic-agent launcher symlink. fs.protected_symlinks=1 then prevents
-#  non-root users from following that launcher symlink.
-{# OSCAP rule id: xccdf_org.ssgproject.content_rule_sysctl_fs_protected_symlinks #}
-fs.protected_symlinks:
-  sysctl.present:
-    - value: 0
-    - config: /etc/sysctl.conf
-
 {# OSCAP rule id: xccdf_org.ssgproject.content_rule_disable_ctrlaltdel_burstaction #}
 disable_ctrl_alt_del_action:
   file.replace:

salt/stig/files/sos-oscap.xml

@@ -1601,7 +1601,7 @@ DISA STIG for Oracle Linux 9 V1R3.</xccdf-1.2:description>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sudoers_validate_passwd" selected="true"/>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_crypto_fips_enabled" selected="true"/>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_fs_protected_hardlinks" selected="true"/>
-        <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_fs_protected_symlinks" selected="false"/>
+        <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_fs_protected_symlinks" selected="true"/>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_kernel_core_pattern" selected="true"/>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_kernel_dmesg_restrict" selected="true"/>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_kernel_exec_shield" selected="true"/>
@@ -2202,7 +2202,7 @@ standard DISA STIG for Oracle Linux 9 profile.</xccdf-1.2:description>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sudoers_validate_passwd" selected="true"/>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_crypto_fips_enabled" selected="true"/>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_fs_protected_hardlinks" selected="true"/>
-        <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_fs_protected_symlinks" selected="false"/>
+        <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_fs_protected_symlinks" selected="true"/>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_kernel_core_pattern" selected="true"/>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_kernel_dmesg_restrict" selected="true"/>
         <xccdf-1.2:select idref="xccdf_org.ssgproject.content_rule_sysctl_kernel_exec_shield" selected="true"/>

salt/strelka/config.sls

@@ -51,8 +51,8 @@ strelka_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://strelka/tools/sbin
-    - user: 939
-    - group: 939
+    - user: root
+    - group: root
     - file_mode: 755
 
 {% else %}