From 3ffaf0cc4d94e3d93551ce5fc508654f1506cbca Mon Sep 17 00:00:00 2001
From: ryanv <ryan@alertwizard.cloud>
Date: Tue, 10 Mar 2026 14:30:10 +0000
Subject: [PATCH] check retention

---
 .env.example       |  4 ++++
 README.md          | 15 +++++++++++++++
 app/main.py        |  2 +-
 app/models.py      | 41 ++++++++++++++++++++++++++++++++++++++++-
 app/scheduler.py   |  5 ++++-
 docker-compose.yml |  1 +
 6 files changed, 65 insertions(+), 3 deletions(-)

diff --git a/.env.example b/.env.example
index c0347d7..4372fc9 100644
--- a/.env.example
+++ b/.env.example
@@ -3,3 +3,7 @@
 DOCKER_REGISTRY=docker.io
 DOCKER_IMAGE=myorg/myapp
 IMAGE_TAG=latest
+
+# Optional: check retention (limits DB growth)
+# CHECK_RETENTION_COUNT=5000   # keep last N checks per service (default 5000)
+# CHECK_RETENTION_DAYS=30      # also delete checks older than N days (0=disabled)
diff --git a/README.md b/README.md
index 88761fb..63a2c9a 100644
--- a/README.md
+++ b/README.md
@@ -42,6 +42,21 @@ docker run -p 8080:8080 -v $(pwd)/data:/app/data myapp:test
 
 Add services from the dashboard (e.g. `https://example.com`, `google.com:443` for TCP) and view reports.
 
+### Check Retention
+
+To limit database growth, the app prunes old checks every 15 minutes:
+
+| Env var | Default | Description |
+|---------|---------|-------------|
+| `CHECK_RETENTION_COUNT` | 5000 | Keep last N checks per service |
+| `CHECK_RETENTION_DAYS` | 0 (disabled) | Also delete checks older than N days |
+
+Example: keep 2000 checks per service and drop anything older than 30 days:
+
+```bash
+docker run -e CHECK_RETENTION_COUNT=2000 -e CHECK_RETENTION_DAYS=30 ...
+```
+
 ## Jenkins Pipeline
 
 The pipeline:
diff --git a/app/main.py b/app/main.py
index da48409..dbcd3bc 100644
--- a/app/main.py
+++ b/app/main.py
@@ -141,7 +141,7 @@ def report(service_id):
     status_filter = request.args.get("status")
     search = request.args.get("search", "").strip() or None
     page = max(1, int(request.args.get("page", 1)))
-    per_page = min(100, max(10, int(request.args.get("per_page", 25))))
+    per_page = min(100, max(10, int(request.args.get("per_page", 10))))
     stats = models.get_report_stats(service_id, from_ts=from_ts, to_ts=to_ts)
     checks_total = models.get_checks_count(service_id, from_ts=from_ts, to_ts=to_ts, status_filter=status_filter, search=search)
     checks = models.get_checks(
diff --git a/app/models.py b/app/models.py
index 9f9dfab..f7931be 100644
--- a/app/models.py
+++ b/app/models.py
@@ -2,12 +2,16 @@
 import os
 import sqlite3
 from contextlib import contextmanager
-from datetime import datetime
+from datetime import datetime, timedelta, timezone
 from pathlib import Path
 
 DATA_PATH = os.environ.get("DATA_PATH", "/app/data")
 DB_PATH = Path(DATA_PATH) / "monitor.db"
 
+# Retention: keep last N checks per service, and optionally drop checks older than N days
+CHECK_RETENTION_COUNT = int(os.environ.get("CHECK_RETENTION_COUNT", "5000"))
+CHECK_RETENTION_DAYS = int(os.environ.get("CHECK_RETENTION_DAYS", "0")) or None
+
 
 def _ensure_data_dir():
     Path(DATA_PATH).mkdir(parents=True, exist_ok=True)
@@ -232,3 +236,38 @@ def get_all_services_for_scheduler():
     with get_db() as conn:
         rows = conn.execute("SELECT id, target, protocol, interval_seconds FROM services").fetchall()
         return [dict(r) for r in rows]
+
+
+def prune_checks_retention() -> int:
+    """
+    Remove old checks to limit storage. Keeps last CHECK_RETENTION_COUNT per service.
+    If CHECK_RETENTION_DAYS is set, also deletes checks older than that.
+    Returns number of rows deleted.
+    """
+    with get_db() as conn:
+        deleted = 0
+        # Delete checks older than N days (if configured)
+        if CHECK_RETENTION_DAYS:
+            cutoff = (datetime.now(timezone.utc) - timedelta(days=CHECK_RETENTION_DAYS)).isoformat()
+            cur = conn.execute("DELETE FROM checks WHERE timestamp < ?", (cutoff,))
+            deleted += cur.rowcount
+
+        # Keep only last N checks per service
+        service_ids = [r[0] for r in conn.execute("SELECT id FROM services").fetchall()]
+        for sid in service_ids:
+            # Get ids of checks to keep (most recent N)
+            keep_ids = conn.execute(
+                "SELECT id FROM checks WHERE service_id = ? ORDER BY timestamp DESC LIMIT ?",
+                (sid, CHECK_RETENTION_COUNT),
+            ).fetchall()
+            keep_ids = [r[0] for r in keep_ids]
+            if not keep_ids:
+                continue
+            placeholders = ",".join("?" * len(keep_ids))
+            cur = conn.execute(
+                f"DELETE FROM checks WHERE service_id = ? AND id NOT IN ({placeholders})",
+                [sid] + keep_ids,
+            )
+            deleted += cur.rowcount
+
+        return deleted
diff --git a/app/scheduler.py b/app/scheduler.py
index d2314cf..f8a5f7e 100644
--- a/app/scheduler.py
+++ b/app/scheduler.py
@@ -2,7 +2,7 @@
 from apscheduler.schedulers.background import BackgroundScheduler
 
 from app.checker import run_check
-from app.models import get_all_services_for_scheduler
+from app.models import get_all_services_for_scheduler, prune_checks_retention
 
 
 def _run_all_checks():
@@ -54,4 +54,7 @@ def start_scheduler():
     # Sync job list every 60 seconds (only adds/removes when services change)
     scheduler.add_job(sync_jobs, "interval", seconds=60, id="sync_jobs")
 
+    # Prune old checks every 15 minutes (retention/compression)
+    scheduler.add_job(prune_checks_retention, "interval", minutes=15, id="prune_checks")
+
     scheduler.start()
diff --git a/docker-compose.yml b/docker-compose.yml
index 97d45f2..0c619ca 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -10,4 +10,5 @@ services:
       - ./data:/app/data
     environment:
       - VERSION=${IMAGE_TAG:-latest}
+      # Optional: CHECK_RETENTION_COUNT=5000, CHECK_RETENTION_DAYS=30
     restart: unless-stopped