From b735a0841c385a1fb97f04e30c4039d33d6652ba Mon Sep 17 00:00:00 2001
From: shamoon <4887959+shamoon@users.noreply.github.com>
Date: Sun, 2 Feb 2025 23:56:14 -0800
Subject: [PATCH] Just use mtime and keep it fresh on every train

---
 src/documents/classifier.py |  5 +++++
 src/documents/views.py      | 23 +----------------------
 2 files changed, 6 insertions(+), 22 deletions(-)

diff --git a/src/documents/classifier.py b/src/documents/classifier.py
index 72bf1f16c..008a4ce10 100644
--- a/src/documents/classifier.py
+++ b/src/documents/classifier.py
@@ -1,6 +1,8 @@
 import logging
+import os
 import pickle
 import re
+import time
 import warnings
 from collections.abc import Iterator
 from hashlib import sha256
@@ -229,6 +231,9 @@ class DocumentClassifier:
             and self.last_doc_change_time >= latest_doc_change
         ) and self.last_auto_type_hash == hasher.digest():
             logger.info("No updates since last training")
+            # Update the modification time of the file to mark it as fresh
+            new_mtime = time.time()
+            os.utime(settings.MODEL_FILE, (new_mtime, new_mtime))
             # Set the classifier information into the cache
             # Caching for 50 minutes, so slightly less than the normal retrain time
             cache.set(
diff --git a/src/documents/views.py b/src/documents/views.py
index 92bb53a1b..410bb9e17 100644
--- a/src/documents/views.py
+++ b/src/documents/views.py
@@ -15,7 +15,6 @@ from urllib.parse import quote
 from urllib.parse import urlparse
 
 import pathvalidate
-from django.apps import apps
 from django.conf import settings
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import User
@@ -2174,33 +2173,13 @@ class SystemStatusView(PassUserMixin):
                     classifier_status = "WARNING"
                     raise FileNotFoundError(classifier_error)
             classifier_status = "OK"
-            task_result_model = apps.get_model("django_celery_results", "taskresult")
-            result = (
-                task_result_model.objects.filter(
-                    task_name="documents.tasks.train_classifier",
-                    status="SUCCESS",
-                )
-                .order_by(
-                    "-date_done",
-                )
-                .first()
-            )
-            classifier_last_auto_trained = result.date_done if result else None
-            classifier_last_modified = (
+            classifier_last_trained = (
                 make_aware(
                     datetime.fromtimestamp(settings.MODEL_FILE.stat().st_mtime),
                 )
                 if settings.MODEL_FILE.exists()
                 else None
             )
-            classifier_last_trained = (
-                max(
-                    classifier_last_auto_trained,
-                    classifier_last_modified,
-                )
-                if classifier_last_auto_trained and classifier_last_modified
-                else classifier_last_auto_trained or classifier_last_modified
-            )
         except Exception as e:
             if classifier_status is None:
                 classifier_status = "ERROR"