Refactors versioning, improves Docker logging, and enables script sanitization.

Author: laurentftech

.github/workflows/release.yml

@@ -201,62 +201,39 @@ jobs:
   publish-docker:
     name: Publish Docker Image
     runs-on: ubuntu-latest
-    needs: [release] # Depend on 'release' job to ensure artifacts are uploaded and version is stable
+    needs: [release]
+
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
         with:
-          fetch-depth: 0 # Required for setuptools-scm to determine the version
-
-      - name: Setup Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.x' # Use a recent Python version
-
-      - name: Install setuptools-scm
-        run: pip install setuptools-scm
+          fetch-depth: 0
 
-      - name: Generate _version.py
-        run: |
-          python -c "import setuptools_scm; \
-                     import os; \
-                     # Get the version from setuptools_scm, using the current directory as root \
-                     # fallback_version is used if setuptools_scm cannot determine the version (e.g., no .git) \
-                     version = setuptools_scm.get_version(root='.', fallback_version='0.0.0+unknown'); \
-                     # Ensure the version string is clean for Python (remove leading 'v' if present) \
-                     if version.startswith('v'): version = version[1:]; \
-                     # Write the version to _version.py \
-                     with open('_version.py', 'w') as f: f.write(f\"__version__ = '{version}'\\n\"); \
-                     print(f\"Generated _version.py with __version__ = '{version}'\")"
-
-      - name: Get version from _version.py
-        id: get_version
+      - name: Extract version from tag
+        id: version
         run: |
-          # Read the __version__ variable from the generated _version.py
-          # Add current directory to PYTHONPATH to allow importing _version.py
-          VERSION=$(PYTHONPATH=. python -c "import _version; print(_version.__version__)")
-          # Remove leading 'v' if present (e.g., v1.0.0 -> 1.0.0)
-          VERSION="${VERSION#v}"
-          # Extract major version (e.g., 1.0.0 -> 1)
-          MAJOR_VERSION=$(echo "$VERSION" | cut -d. -f1)
+          RAW="${GITHUB_REF_NAME}"
+          VERSION="${RAW#v}"
+          MAJOR="${VERSION%%.*}"
           echo "VERSION=$VERSION" >> $GITHUB_ENV
-          echo "MAJOR_VERSION=$MAJOR_VERSION" >> $GITHUB_ENV
-          echo "Extracted VERSION: $VERSION"
-          echo "Extracted MAJOR_VERSION: $MAJOR_VERSION"
+          echo "MAJOR_VERSION=$MAJOR" >> $GITHUB_ENV
+          echo "Version = $VERSION"
+          echo "Major   = $MAJOR"
 
       - name: Log in to Docker Hub
         uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
 
-      # --- Build and push FULL image (with WhisperX) ---
       - name: Build and push FULL Docker image
         uses: docker/build-push-action@v5
         with:
           context: .
           push: true
-          target: with_whisperx # Assuming this is the target for the full version
+          target: with_whisperx
+          build-args: |
+            VERSION=${{ env.VERSION }}
           tags: |
             gandulf78/podcast_generator:${{ env.VERSION }}
             gandulf78/podcast_generator:${{ env.MAJOR_VERSION }}
@@ -265,13 +242,14 @@ jobs:
             org.opencontainers.image.source=${{ github.event.repository.html_url }}
             org.opencontainers.image.version=${{ env.VERSION }}
 
-      # --- Build and push LIGHT image (without WhisperX) ---
       - name: Build and push LIGHT Docker image
         uses: docker/build-push-action@v5
         with:
           context: .
           push: true
-          target: without_whisperx # Assuming this is the target for the light version
+          target: without_whisperx
+          build-args: |
+            VERSION=${{ env.VERSION }}
           tags: |
             gandulf78/podcast_generator:${{ env.VERSION }}-light
             gandulf78/podcast_generator:${{ env.MAJOR_VERSION }}-light

Dockerfile

@@ -1,53 +1,68 @@
-# --- Stage 1: Base dependencies ---
+# ================================
+# Stage 1: Base dependencies
+# ================================
 FROM python:3.11-slim-bookworm AS base
 
-# Set the working directory in the container
+# Workdir
 WORKDIR /app
 
-# Install FFmpeg (required for audio processing)
-# Also install git for whisperx dependencies
+# Avoid writing .pyc files and enable immediate flush
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+# Install system deps (ffmpeg required)
 RUN apt-get update && apt-get install -y --no-install-recommends \
     ffmpeg \
     git \
-    && rm -rf /var/lib/apt/lists/*
+    && rm -rf /var/lib/apt/lists/* \
+    && apt-get purge -y git
 
-# Copy the core requirements file
+# Copy requirements
 COPY requirements.txt .
 
-# Install core dependencies
+# Install Python dependencies (core only — no WhisperX)
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy the rest of the application code
+# Copy entire app
 COPY . .
 
-# --- Stage 2: Build with WhisperX support ---
+# Inject version (default "dev"; overwritten at build time)
+ARG VERSION="dev"
+RUN echo "{\"version\": \"${VERSION}\"}" > version.json
+
+
+# ================================
+# Stage 2: Image WITH WhisperX
+# ================================
 FROM base AS with_whisperx
 
-# Install PyTorch (CPU-only for broader compatibility in Docker) and torchaudio
-# Then install whisperx
+# Install CPU PyTorch + WhisperX
 RUN pip install --no-cache-dir \
     torch==2.2.2+cpu \
     torchaudio==2.2.2+cpu \
     -f https://download.pytorch.org/whl/torch_stable.html \
     && pip install --no-cache-dir whisperx==3.1.1
 
-# Set environment variable to enable demo features
+# Indicate WhisperX is available
 ENV DEMO_AVAILABLE=1
 
-# Expose the port that Gunicorn will listen on
+# Expose API port
 EXPOSE 8000
 
-# Run gunicorn to serve the Flask application
+# Start backend
 CMD ["gunicorn", "--bind", "0.0.0.0:8000", "app:app"]
 
-# --- Stage 3: Build without WhisperX support ---
+
+# ================================
+# Stage 3: Image WITHOUT WhisperX
+# ================================
 FROM base AS without_whisperx
 
-# Set environment variable to disable demo features
+# WhisperX disabled
 ENV DEMO_AVAILABLE=0
 
-# Expose the port that Gunicorn will listen on
+# Expose API port
 EXPOSE 8000
 
-# Run gunicorn to serve the Flask application
-CMD ["gunicorn", "--bind", "0.0.0.0:8000", "app:app"]
+# Start backend
+CMD ["gunicorn", "--bind", "0.0.0.0:8000", "app:app"]

app.py

@@ -13,6 +13,8 @@
 import re
 import uuid
 import threading
+import json
+from flask import jsonify
 
 # --- App Initialization ---
 app = Flask(__name__)
@@ -74,7 +76,15 @@ def get_asset(filename):
 
 @app.route('/api/about', methods=['GET'])
 def get_about_info():
-    return jsonify({'version': __version__, 'license': LICENSE_TEXT})
+    return jsonify({'version': version(), 'license': LICENSE_TEXT})
+
+def version():
+    try:
+        with open("version.json") as f:
+            data = json.load(f)
+            return data.get("version", "unknown")
+    except Exception:
+        return "unknown"
 
 @app.route('/api/status', methods=['GET'])
 def get_status():