feat: auto cleanup orphan files

Dockerfile

@@ -39,7 +39,7 @@ RUN npm ci --force
 
 COPY . .
 ENV APP_BUILD_HASH=${BUILD_HASH}
-RUN npm run build
+RUN NODE_OPTIONS="--max_old_space_size=4096" npm run build
 
 ######## WebUI backend ########
 FROM python:3.11-slim-bookworm AS base
@@ -116,10 +116,9 @@ RUN echo -n 00000000-0000-0000-0000-000000000000 > $HOME/.cache/chroma/telemetry
 # Make sure the user has access to the app and root directory
 RUN chown -R $UID:$GID /app $HOME
 
-# Install common system dependencies
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-    git build-essential pandoc gcc netcat-openbsd curl jq \
+    git build-essential pandoc gcc netcat-openbsd curl jq cron \
     python3-dev \
     ffmpeg libsm6 libxext6 \
     && rm -rf /var/lib/apt/lists/*
@@ -167,6 +166,12 @@ COPY --chown=$UID:$GID --from=build /app/package.json /app/package.json
 # copy backend files
 COPY --chown=$UID:$GID ./backend .
 
+# Create directories for logs
+RUN mkdir -p /var/log && \
+    touch /var/log/clean-orphaned-files.log && \
+    chmod 644 /var/log/clean-orphaned-files.log && \
+    chown $UID:$GID /var/log/clean-orphaned-files.log
+
 EXPOSE 8080
 
 HEALTHCHECK CMD curl --silent --fail http://localhost:${PORT:-8080}/health | jq -ne 'input.status == true' || exit 1

backend/setup-cron.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+# Create the wrapper script
+cat > /app/backend/run-cleanup-script.sh << 'EOL'
+#!/bin/bash
+# This script runs the clean-orphaned-files.py script with the proper environment variables
+
+# Export all environment variables to the script
+export DATABASE_URL="${DATABASE_URL}"
+export ADMIN_TOKEN="${ADMIN_TOKEN:-your_admin_token}"
+export TEAMS_WEBHOOK_URL="${TEAMS_WEBHOOK_URL:-your_ms_teams_incoming_webhook_url}"
+
+# Check if the script exists (it should be in a mounted volume)
+if [ -f /app/backend/data/scripts/clean-orphaned-files.py ]; then
+    /usr/local/bin/python /app/backend/data/scripts/clean-orphaned-files.py --admin-token "${ADMIN_TOKEN}" --teams-webhook-url "${TEAMS_WEBHOOK_URL}" >> /var/log/clean-orphaned-files.log 2>&1
+else
+    echo "$(date): Warning - clean-orphaned-files.py not found in mounted volume" >> /var/log/clean-orphaned-files.log
+fi
+EOL
+
+# Make the wrapper script executable
+chmod +x /app/backend/run-cleanup-script.sh
+
+# Create the cron job entry
+CRONJOB="0 */6 * * * /app/backend/run-cleanup-script.sh"
+
+# Setup the crontab
+(crontab -l 2>/dev/null || echo "") | grep -v "run-cleanup-script.sh" | { cat; echo "$CRONJOB"; } | crontab -
+
+echo "Cron job has been set up successfully."

backend/start.sh

@@ -35,6 +35,27 @@ if test "$WEBUI_SECRET_KEY $WEBUI_JWT_SECRET_KEY" = " "; then
   WEBUI_SECRET_KEY=$(cat "$KEY_FILE")
 fi
 
+# Setup and start cron service
+echo "Setting up cron service..."
+if [ -x "$(command -v cron)" ]; then
+  # Create necessary directories for scripts if they don't exist
+  mkdir -p /app/backend/data/scripts
+
+  # Make the setup-cron.sh script executable
+  chmod +x "$SCRIPT_DIR/setup-cron.sh"
+  
+  # Run the cron setup script
+  "$SCRIPT_DIR/setup-cron.sh"
+  
+  # Start the cron service
+  echo "Starting cron service..."
+  service cron start || cron
+  
+  echo "Cron service started."
+else
+  echo "Warning: cron is not installed. Scheduled tasks will not run."
+fi
+
 if [[ "${USE_OLLAMA_DOCKER,,}" == "true" ]]; then
     echo "USE_OLLAMA is set to true, starting ollama serve."
     ollama serve &