fix: экспорт всех текущих проблем в Zabbix + совместимость шаблона с Zabbix 5.0

collect_and_alert теперь экспортирует ВСЕ текущие проблемные DAG-и,
а не только новые — Zabbix видит проблему пока DAG не починен.

Zabbix XML шаблон: version 5.0, убраны tags, preprocessing params,
triggers/graphs вынесены на верхний уровень, history 7d / trends 365d.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

airflow_monitor/actions.py

@@ -211,14 +211,15 @@ class ActionHandler:
         return "needs_alert"
 
     def collect_and_alert(self, issues: list[DagIssue]):
-        """Export alerts for issues that need alerting.
+        """Export all current issues and mark new ones as alerted.
 
-        Filters to only unalerted issues, builds JSON payload,
+        Always exports the full list of current problems so Zabbix sees them
-        writes to file for Zabbix agent, and marks as alerted in state.
+        until they are resolved. Only logs warnings for newly discovered issues.
         """
-        to_alert = []
+        # Build export payload for ALL current issues
+        all_problems = []
+        new_issues = []
         for issue in issues:
-            if not self._state.is_alerted(issue.dag_id, issue.dag_run_id):
             entry = self._state.ensure_entry(issue.dag_id, issue.dag_run_id)
             alert_data = {
                 "dag_id": issue.dag_id,
@@ -229,36 +230,35 @@ class ActionHandler:
                 "error_info": issue.error_info,
                 "retry_count": entry["retry_count"],
             }
-                to_alert.append(alert_data)
+            all_problems.append(alert_data)
-                logger.debug(
+            if not self._state.is_alerted(issue.dag_id, issue.dag_run_id):
-                    "Issue queued for alert: %s/%s type=%s retries=%d",
+                new_issues.append(issue)
-                    issue.dag_id, issue.dag_run_id,
-                    issue.issue_type, entry["retry_count"],
-                )
 
-        if not to_alert:
+        if not all_problems:
-            # Write empty list to clear Zabbix trigger
             self._exporter.export_problems([])
-            logger.info("No issues to alert, exported empty problem list")
+            logger.info("No issues, exported empty problem list")
             return
 
+        # Log new issues at warning level
+        if new_issues:
             logger.warning(
-            "Exporting %d problematic DAG runs for Zabbix: %s",
+                "New problematic DAG runs: %s",
-            len(to_alert),
                 ", ".join(
-                f"{p['dag_id']}/{p['dag_run_id']}({p['issue_type']})"
+                    f"{i.dag_id}/{i.dag_run_id}({i.issue_type})"
-                for p in to_alert
+                    for i in new_issues
                 ),
             )
 
-        # Log full alert payload at debug level
+        logger.debug("Alert payload:\n%s", json.dumps(all_problems, indent=2, ensure_ascii=False))
-        logger.debug("Alert payload:\n%s", json.dumps(to_alert, indent=2, ensure_ascii=False))
 
-        self._exporter.export_problems(to_alert)
+        self._exporter.export_problems(all_problems)
 
-        for issue in issues:
+        # Mark new issues as alerted
-            if not self._state.is_alerted(issue.dag_id, issue.dag_run_id):
+        for issue in new_issues:
             self._state.mark_alerted(issue.dag_id, issue.dag_run_id)
             logger.debug("Marked as alerted: %s/%s", issue.dag_id, issue.dag_run_id)
 
-        logger.info("Exported %d issues to problems file for Zabbix agent", len(to_alert))
+        logger.info(
+            "Exported %d issues to problems file (%d new)",
+            len(all_problems), len(new_issues),
+        )

zabbix/zbx_template_airflow_monitor_5x.xml

@@ -1,6 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <zabbix_export>
-    <version>5.4</version>
+    <version>5.0</version>
     <groups>
         <group>
             <name>Templates/Applications</name>
@@ -17,7 +17,7 @@
 - Установлен airflow-monitor (/opt/airflow-monitor)&#13;
 - Установлен конфиг /etc/zabbix/zabbix_agentd.conf.d/airflow-monitor.conf&#13;
 &#13;
-Версия шаблона: 1.0.0 (Zabbix 5.x)</description>
+Версия шаблона: 1.0.1 (Zabbix 5.0)</description>
             <groups>
                 <group>
                     <name>Templates/Applications</name>
@@ -32,12 +32,6 @@
                     <history>7d</history>
                     <value_type>TEXT</value_type>
                     <description>JSON-массив проблемных DAG-запусков. [] = нет проблем.</description>
-                    <tags>
-                        <tag>
-                            <tag>component</tag>
-                            <value>airflow</value>
-                        </tag>
-                    </tags>
                 </item>
 
                 <!-- Problematic DAGs count -->
@@ -45,16 +39,10 @@
                     <name>Airflow: Problematic DAGs count</name>
                     <key>airflow.dag.problems.count</key>
                     <delay>1m</delay>
-                    <history>90d</history>
+                    <history>7d</history>
                     <trends>365d</trends>
                     <value_type>UNSIGNED</value_type>
                     <description>Количество DAG-запусков с проблемами.</description>
-                    <tags>
-                        <tag>
-                            <tag>component</tag>
-                            <value>airflow</value>
-                        </tag>
-                    </tags>
                 </item>
 
                 <!-- Heartbeat -->
@@ -63,14 +51,9 @@
                     <key>airflow.monitor.heartbeat</key>
                     <delay>1m</delay>
                     <history>7d</history>
+                    <trends>365d</trends>
                     <value_type>UNSIGNED</value_type>
                     <description>Epoch timestamp последнего успешного цикла мониторинга.</description>
-                    <tags>
-                        <tag>
-                            <tag>component</tag>
-                            <value>dag-monitor</value>
-                        </tag>
-                    </tags>
                 </item>
 
                 <!-- Status JSON -->
@@ -81,12 +64,6 @@
                     <history>7d</history>
                     <value_type>TEXT</value_type>
                     <description>JSON со статусом монитора.</description>
-                    <tags>
-                        <tag>
-                            <tag>component</tag>
-                            <value>dag-monitor</value>
-                        </tag>
-                    </tags>
                 </item>
 
                 <!-- Service alive -->
@@ -94,19 +71,13 @@
                     <name>Airflow Monitor: Service alive</name>
                     <key>airflow.monitor.alive</key>
                     <delay>1m</delay>
-                    <history>90d</history>
+                    <history>7d</history>
                     <trends>365d</trends>
                     <value_type>UNSIGNED</value_type>
                     <description>1 = сервис запущен, 0 = остановлен.</description>
                     <valuemap>
                         <name>Service state</name>
                     </valuemap>
-                    <tags>
-                        <tag>
-                            <tag>component</tag>
-                            <value>dag-monitor</value>
-                        </tag>
-                    </tags>
                 </item>
 
                 <!-- DAG count (dependent from status) -->
@@ -114,7 +85,7 @@
                     <name>Airflow Monitor: DAG count</name>
                     <type>DEPENDENT</type>
                     <key>airflow.monitor.dag_count</key>
-                    <history>90d</history>
+                    <history>7d</history>
                     <trends>365d</trends>
                     <value_type>UNSIGNED</value_type>
                     <description>Количество отслеживаемых DAG-ов.</description>
@@ -124,23 +95,13 @@
                     <preprocessing>
                         <step>
                             <type>JSONPATH</type>
-                            <parameters>
+                            <params>$.dag_count</params>
-                                <parameter>$.dag_count</parameter>
-                            </parameters>
                         </step>
                         <step>
                             <type>DISCARD_UNCHANGED_HEARTBEAT</type>
-                            <parameters>
+                            <params>1h</params>
-                                <parameter>1h</parameter>
-                            </parameters>
                         </step>
                     </preprocessing>
-                    <tags>
-                        <tag>
-                            <tag>component</tag>
-                            <value>airflow</value>
-                        </tag>
-                    </tags>
                 </item>
 
                 <!-- Cycle time (dependent from status) -->
@@ -148,7 +109,7 @@
                     <name>Airflow Monitor: Cycle time (seconds)</name>
                     <type>DEPENDENT</type>
                     <key>airflow.monitor.cycle_time</key>
-                    <history>90d</history>
+                    <history>7d</history>
                     <trends>365d</trends>
                     <value_type>FLOAT</value_type>
                     <units>s</units>
@@ -159,17 +120,9 @@
                     <preprocessing>
                         <step>
                             <type>JSONPATH</type>
-                            <parameters>
+                            <params>$.cycle_time_seconds</params>
-                                <parameter>$.cycle_time_seconds</parameter>
-                            </parameters>
                         </step>
                     </preprocessing>
-                    <tags>
-                        <tag>
-                            <tag>component</tag>
-                            <value>dag-monitor</value>
-                        </tag>
-                    </tags>
                 </item>
 
                 <!-- Cycle count (dependent from status) -->
@@ -177,7 +130,7 @@
                     <name>Airflow Monitor: Cycle count</name>
                     <type>DEPENDENT</type>
                     <key>airflow.monitor.cycle_count</key>
-                    <history>90d</history>
+                    <history>7d</history>
                     <trends>365d</trends>
                     <value_type>UNSIGNED</value_type>
                     <description>Номер текущего цикла мониторинга.</description>
@@ -187,42 +140,41 @@
                     <preprocessing>
                         <step>
                             <type>JSONPATH</type>
-                            <parameters>
+                            <params>$.cycle_count</params>
-                                <parameter>$.cycle_count</parameter>
-                            </parameters>
                         </step>
                         <step>
                             <type>DISCARD_UNCHANGED_HEARTBEAT</type>
-                            <parameters>
+                            <params>1h</params>
-                                <parameter>1h</parameter>
-                            </parameters>
                         </step>
                     </preprocessing>
-                    <tags>
-                        <tag>
-                            <tag>component</tag>
-                            <value>dag-monitor</value>
-                        </tag>
-                    </tags>
                 </item>
             </items>
 
+            <macros>
+                <macro>
+                    <macro>{$AIRFLOW.STALE_THRESHOLD}</macro>
+                    <value>600</value>
+                    <description>Порог устаревания данных (секунды).</description>
+                </macro>
+                <macro>
+                    <macro>{$AIRFLOW.CYCLE_TIME_WARN}</macro>
+                    <value>60</value>
+                    <description>Порог предупреждения о долгом цикле (секунды).</description>
+                </macro>
+            </macros>
+        </template>
+    </templates>
+
     <triggers>
         <!-- Problematic DAGs detected -->
         <trigger>
             <expression>{Airflow DAG Monitor:airflow.dag.problems.count.last()}&gt;0</expression>
-                    <recovery_expression>{Airflow DAG Monitor:airflow.dag.problems.count.last()}=0</recovery_expression>
+            <recovery_expression></recovery_expression>
             <name>Airflow: {ITEM.LASTVALUE1} problematic DAG run(s) detected</name>
             <priority>HIGH</priority>
             <description>Обнаружены проблемные DAG-запуски (failed или long_running).&#13;
 Подробности в item "Airflow: Problematic DAGs (JSON)".&#13;
 Триггер снимается автоматически при разрешении всех проблем.</description>
-                    <tags>
-                        <tag>
-                            <tag>scope</tag>
-                            <value>availability</value>
-                        </tag>
-                    </tags>
         </trigger>
 
         <!-- Heartbeat stale -->
@@ -238,12 +190,6 @@
                     <expression>{Airflow DAG Monitor:airflow.monitor.alive.last()}=0</expression>
                 </dependency>
             </dependencies>
-                    <tags>
-                        <tag>
-                            <tag>scope</tag>
-                            <value>availability</value>
-                        </tag>
-                    </tags>
         </trigger>
 
         <!-- Service down -->
@@ -253,12 +199,6 @@
             <priority>HIGH</priority>
             <description>Сервис airflow-monitor не запущен.&#13;
 Запустить: sudo systemctl start airflow-monitor</description>
-                    <tags>
-                        <tag>
-                            <tag>scope</tag>
-                            <value>availability</value>
-                        </tag>
-                    </tags>
         </trigger>
 
         <!-- Slow cycle -->
@@ -267,12 +207,6 @@
             <name>Airflow Monitor: Cycle time is high ({ITEM.LASTVALUE1}s)</name>
             <priority>WARNING</priority>
             <description>Цикл мониторинга выполняется дольше 60 секунд.</description>
-                    <tags>
-                        <tag>
-                            <tag>scope</tag>
-                            <value>performance</value>
-                        </tag>
-                    </tags>
         </trigger>
     </triggers>
 
@@ -314,21 +248,6 @@
         </graph>
     </graphs>
 
-            <macros>
-                <macro>
-                    <macro>{$AIRFLOW.STALE_THRESHOLD}</macro>
-                    <value>600</value>
-                    <description>Порог устаревания данных (секунды).</description>
-                </macro>
-                <macro>
-                    <macro>{$AIRFLOW.CYCLE_TIME_WARN}</macro>
-                    <value>60</value>
-                    <description>Порог предупреждения о долгом цикле (секунды).</description>
-                </macro>
-            </macros>
-        </template>
-    </templates>
-
     <value_maps>
         <value_map>
             <name>Service state</name>