Disable Minutely Recurrence for Automations (#781)

* Disable automation recurrence at minute level frequency

* Set a max lifetime for django's connections to the db

* Disable any automation that has a non-numeric first digit (i.e., recuring on the minute level)

* Re-enable automations

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>

src/khoj/interface/web/config_automation.html

@@ -2,16 +2,6 @@
 {% block content %}
 <div class="page">
     <div class="section">
-        <div id="maintenance-notice">
-            <div class="urgent-notice">
-                <p>
-                    Hold up! Our Automations are taking a well-deserved break for some maintenance magic. They'll be back in action soon, better than ever. Thanks for your patience!
-                </p>
-                <div>
-                    <a class="maintenance-action" href="/">Back to Chat</a>
-                </div>
-            </div>
-        </div>
         <h2 class="section-title">
             <img class="card-icon" src="/static/assets/icons/automation.svg?v={{ khoj_version }}" alt="Automate">
             <span class="card-title-text">Automate (Preview)</span>
@@ -218,32 +208,6 @@
         grid-gap: 8px;
     }
 
-    div#maintenance-notice {
-        display: flex;
-        justify-content: center;
-        align-items: center;
-        position: fixed;
-        top: 0;
-        right: 0;
-        bottom: 0;
-        left: 0;
-        z-index: 2;
-        background-image: linear-gradient(to bottom, rgba(250, 130, 130, 0.8), rgba(255, 165, 0, 0.8));
-    }
-
-    a.maintenance-action{
-        color: white;
-        text-decoration: none;
-    }
-
-    div.urgent-notice p,
-    div.urgent-notice a {
-        font-size: 24px;
-        font-weight: bold;
-        padding: 20px;
-        text-align: left;
-    }
-
     div.subject-wrapper p {
         margin: 0;
     }
@@ -273,7 +237,7 @@
     }
 
 </style>
-<!-- <script>
+<script>
     function deleteAutomation(automationId) {
         const AutomationList = document.getElementById("automations");
         fetch(`/api/automation?automation_id=${automationId}`, {
@@ -336,7 +300,7 @@
                     if (!response.ok) {
                         throw new Error('Network response was not ok');
                     }
-                    return response.json();
+                    return response;
                 })
             .then(automations => {
                 notificationEl.style.display = 'block';
@@ -875,9 +839,9 @@
             }, 2000);
         })
         .catch(error => {
-            notificationEl.textContent = `⚠️ Failed to ${actOn.toLowerCase()}e automations.`;
+            notificationEl.textContent = `⚠️ Failed to ${actOn.toLowerCase()}e automation.`;
             notificationEl.style.display = "block";
-            saveButtonEl.textContent = `⚠️ Failed to ${actOn.toLowerCase()}e automations`;
+            saveButtonEl.textContent = `⚠️ Failed to ${actOn.toLowerCase()}e automation`;
             setTimeout(function() {
                 saveButtonEl.textContent = `${actOn}e`;
             }, 2000);
@@ -915,5 +879,5 @@
         document.getElementById("automations").insertBefore(automationEl, document.getElementById("automations").firstChild);
         setupScheduleViewListener("* * * * *", placeholderId);
     })
-</script> -->
+</script>
 {% endblock %}

src/khoj/main.py

@@ -134,17 +134,17 @@ def run(should_start_server=True):
     poll_task_scheduler()
 
     # Setup Background Scheduler
-    # from django_apscheduler.jobstores import DjangoJobStore
+    from django_apscheduler.jobstores import DjangoJobStore
 
-    # state.scheduler = BackgroundScheduler(
+    state.scheduler = BackgroundScheduler(
-    #     {
+        {
-    #         "apscheduler.timezone": "UTC",
+            "apscheduler.timezone": "UTC",
-    #         "apscheduler.job_defaults.misfire_grace_time": "60",  # Useful to run scheduled jobs even when worker delayed because it was busy or down
+            "apscheduler.job_defaults.misfire_grace_time": "60",  # Useful to run scheduled jobs even when worker delayed because it was busy or down
-    #         "apscheduler.job_defaults.coalesce": "true",  # Combine multiple jobs into one if they are scheduled at the same time
+            "apscheduler.job_defaults.coalesce": "true",  # Combine multiple jobs into one if they are scheduled at the same time
-    #     }
+        }
-    # )
+    )
-    # state.scheduler.add_jobstore(DjangoJobStore(), "default")
+    state.scheduler.add_jobstore(DjangoJobStore(), "default")
-    # state.scheduler.start()
+    state.scheduler.start()
 
     # Start Server
     configure_routes(app)

src/khoj/routers/api.py

@@ -6,6 +6,7 @@ import os
 import threading
 import time
 import uuid
+from random import random
 from typing import Any, Callable, List, Optional, Union
 
 import cron_descriptor
@@ -467,8 +468,15 @@ async def post_automation(
         crontime = " ".join(crontime.split(" ")[:5])
     # Convert crontime to standard unix crontime
     crontime = crontime.replace("?", "*")
-    if crontime == "* * * * *":
+
-        return Response(content="Invalid crontime. Please create a more specific schedule.", status_code=400)
+    # Disallow minute level automation recurrence
+    minute_value = crontime.split(" ")[0]
+    if not minute_value.isdigit():
+        return Response(
+            content="Recurrence of every X minutes is unsupported. Please create a less frequent schedule.",
+            status_code=400,
+        )
+
     subject = await acreate_title_from_query(q)
 
     # Create new Conversation Session associated with this new task
@@ -560,6 +568,14 @@ def edit_job(
     # Convert crontime to standard unix crontime
     crontime = crontime.replace("?", "*")
 
+    # Disallow minute level automation recurrence
+    minute_value = crontime.split(" ")[0]
+    if not minute_value.isdigit():
+        return Response(
+            content="Recurrence of every X minutes is unsupported. Please create a less frequent schedule.",
+            status_code=400,
+        )
+
     # Construct updated automation metadata
     automation_metadata = json.loads(automation.name)
     automation_metadata["scheduling_request"] = q

src/khoj/routers/helpers.py

@@ -4,10 +4,12 @@ import hashlib
 import io
 import json
 import logging
+import math
 import re
 from concurrent.futures import ThreadPoolExecutor
 from datetime import datetime, timedelta, timezone
 from functools import partial
+from random import random
 from typing import (
     Annotated,
     Any,
@@ -1014,8 +1016,6 @@ def scheduled_chat(
 
 async def create_automation(q: str, timezone: str, user: KhojUser, calling_url: URL, meta_log: dict = {}):
     crontime, query_to_run, subject = await schedule_query(q, meta_log)
-    if crontime == "* * * * *":
-        raise HTTPException(status_code=400, detail="Cannot run jobs constantly. Please provide a valid crontime.")
     job = await schedule_automation(query_to_run, subject, crontime, timezone, q, user, calling_url)
     return job, crontime, query_to_run, subject
 
@@ -1029,9 +1029,13 @@ async def schedule_automation(
     user: KhojUser,
     calling_url: URL,
 ):
+    # Disable minute level automation recurrence
+    minute_value = crontime.split(" ")[0]
+    if not minute_value.isdigit():
+        # Run automation at some random minute (to distribute request load) instead of running every X minutes
+        crontime = " ".join([str(math.floor(random() * 60))] + crontime.split(" ")[1:])
+
     user_timezone = pytz.timezone(timezone)
-    if crontime == "* * * * *":
-        raise HTTPException(status_code=400, detail="Cannot run jobs constantly. Please provide a valid crontime.")
     trigger = CronTrigger.from_crontab(crontime, user_timezone)
     trigger.jitter = 60
     # Generate id and metadata used by task scheduler and process locks for the task runs