From e8dc6fde538ed16a3387038f091e5a58c0cc2d27 Mon Sep 17 00:00:00 2001
From: Junyan Qin <rockchinq@gmail.com>
Date: Fri, 27 Mar 2026 11:57:24 +0800
Subject: [PATCH] feat: autoclean monitoring events

---
 .../pkg/api/http/service/monitoring.py        | 51 +++++++++++++++++++
 src/langbot/pkg/core/app.py                   | 28 ++++++++++
 src/langbot/templates/config.yaml             |  8 +++
 3 files changed, 87 insertions(+)

diff --git a/src/langbot/pkg/api/http/service/monitoring.py b/src/langbot/pkg/api/http/service/monitoring.py
index 33504aec..d2267a14 100644
--- a/src/langbot/pkg/api/http/service/monitoring.py
+++ b/src/langbot/pkg/api/http/service/monitoring.py
@@ -16,6 +16,57 @@ class MonitoringService:
     def __init__(self, ap: app.Application) -> None:
         self.ap = ap
 
+    # ========== Cleanup Methods ==========
+
+    async def cleanup_expired_records(self, retention_days: int) -> dict[str, int]:
+        """Delete monitoring records older than the specified retention period.
+
+        Args:
+            retention_days: Number of days to retain records.
+
+        Returns:
+            A dict mapping table name to the number of deleted rows.
+        """
+        cutoff = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None) - datetime.timedelta(
+            days=retention_days
+        )
+
+        tables_and_columns: list[tuple[str, type, sqlalchemy.Column]] = [
+            (
+                'monitoring_messages',
+                persistence_monitoring.MonitoringMessage,
+                persistence_monitoring.MonitoringMessage.timestamp,
+            ),
+            (
+                'monitoring_llm_calls',
+                persistence_monitoring.MonitoringLLMCall,
+                persistence_monitoring.MonitoringLLMCall.timestamp,
+            ),
+            (
+                'monitoring_embedding_calls',
+                persistence_monitoring.MonitoringEmbeddingCall,
+                persistence_monitoring.MonitoringEmbeddingCall.timestamp,
+            ),
+            (
+                'monitoring_errors',
+                persistence_monitoring.MonitoringError,
+                persistence_monitoring.MonitoringError.timestamp,
+            ),
+            (
+                'monitoring_sessions',
+                persistence_monitoring.MonitoringSession,
+                persistence_monitoring.MonitoringSession.last_activity,
+            ),
+        ]
+
+        deleted_counts: dict[str, int] = {}
+
+        for table_name, model_cls, ts_column in tables_and_columns:
+            result = await self.ap.persistence_mgr.execute_async(sqlalchemy.delete(model_cls).where(ts_column < cutoff))
+            deleted_counts[table_name] = result.rowcount
+
+        return deleted_counts
+
     # ========== Recording Methods ==========
 
     async def record_message(
diff --git a/src/langbot/pkg/core/app.py b/src/langbot/pkg/core/app.py
index 12849f2a..e515cfb9 100644
--- a/src/langbot/pkg/core/app.py
+++ b/src/langbot/pkg/core/app.py
@@ -188,6 +188,34 @@ class Application:
                 scopes=[core_entities.LifecycleControlScope.APPLICATION],
             )
 
+            # Start monitoring data cleanup task if enabled
+            monitoring_cfg = self.instance_config.data.get('monitoring', {})
+            auto_cleanup_cfg = monitoring_cfg.get('auto_cleanup', {})
+            if auto_cleanup_cfg.get('enabled', True):
+                retention_days = auto_cleanup_cfg.get('retention_days', 30)
+                check_interval_hours = auto_cleanup_cfg.get('check_interval_hours', 1)
+
+                async def monitoring_cleanup_loop():
+                    check_interval_seconds = check_interval_hours * 3600
+                    while True:
+                        try:
+                            deleted = await self.monitoring_service.cleanup_expired_records(retention_days)
+                            total_deleted = sum(deleted.values())
+                            if total_deleted > 0:
+                                self.logger.info(
+                                    f'Monitoring auto-cleanup: deleted {total_deleted} expired records '
+                                    f'(retention={retention_days}d): {deleted}'
+                                )
+                        except Exception as e:
+                            self.logger.warning(f'Monitoring auto-cleanup error: {e}')
+                        await asyncio.sleep(check_interval_seconds)
+
+                self.task_mgr.create_task(
+                    monitoring_cleanup_loop(),
+                    name='monitoring-cleanup',
+                    scopes=[core_entities.LifecycleControlScope.APPLICATION],
+                )
+
             self.task_mgr.create_task(
                 never_ending(),
                 name='never-ending-task',
diff --git a/src/langbot/templates/config.yaml b/src/langbot/templates/config.yaml
index a75a32fc..c622405d 100644
--- a/src/langbot/templates/config.yaml
+++ b/src/langbot/templates/config.yaml
@@ -78,6 +78,14 @@ plugin:
     runtime_ws_url: 'ws://langbot_plugin_runtime:5400/control/ws'
     enable_marketplace: true
     display_plugin_debug_url: 'ws://localhost:5401/plugin/debug/ws'
+monitoring:
+    auto_cleanup:
+        # Enable automatic cleanup of expired monitoring records
+        enabled: true
+        # Retention period in days, records older than this will be deleted
+        retention_days: 30
+        # Cleanup check interval in hours
+        check_interval_hours: 1
 space:
     # Space service URL for OAuth and API
     url: 'https://space.langbot.app'