feat: use multi stage docker image

Author: ohmayr

.generator/Dockerfile

@@ -12,6 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+# --- Builder Stage ---
+# This stage installs all build dependencies and compiles all Python versions.
 FROM marketplace.gcr.io/google/ubuntu2404 AS builder
 
 # TODO(https://github.com/googleapis/librarian/issues/901): Install the necssary dependencies and build tools.
@@ -38,54 +40,85 @@ RUN apt-get update && \
 # Set up environment variables for tool versions to make updates easier.
 ENV BAZELISK_VERSION=v1.26.0
 
+# Install multiple Python versions from source. `make altinstall` is used to
+# prevent replacing the system's default python binary.
 RUN for PYTHON_VERSION in 3.9.23 3.10.18 3.11.13 3.12.11 3.13.5; do \
-    # Install Python from source
     wget https://www.python.org/ftp/python/${PYTHON_VERSION}/Python-${PYTHON_VERSION}.tgz && \
     tar -xvf Python-${PYTHON_VERSION}.tgz && \
     cd Python-${PYTHON_VERSION} && \
-    ./configure --enable-optimizations && \
+    ./configure --enable-optimizations --prefix=/usr/local && \
+    make -j$(nproc) && \
     make altinstall && \
     cd / && \
     rm -rf Python-${PYTHON_VERSION}* \
     ; done
 
-# Get the pip installation script using the instructions below
-# https://pip.pypa.io/en/stable/installation/#get-pip-py
-# Attempts to use `ensurepip` instead of `get-pip.py` resulted in errors like `python3.13.5 not found`
-RUN wget --no-check-certificate -O /tmp/get-pip.py 'https://bootstrap.pypa.io/get-pip.py'
-
 # Install pip for each python version
-RUN for PYTHON_VERSION in 3.9 3.10 3.11 3.12 3.13; do \
-    python${PYTHON_VERSION} /tmp/get-pip.py \
-    ; done
-    
-# Remove the pip installation script
-RUN rm /tmp/get-pip.py
-
-# Test Pip
-RUN for PYTHON_VERSION in 3.9 3.10 3.11 3.12 3.13; do \
-    python${PYTHON_VERSION} -m pip \
-    ; done
-
-
-# TODO(https://github.com/googleapis/librarian/issues/904): Install protoc for gencode.
+RUN wget --no-check-certificate -O /tmp/get-pip.py 'https://bootstrap.pypa.io/get-pip.py' && \
+    for PYTHON_VERSION in 3.9 3.10 3.11 3.12 3.13; do \
+        python${PYTHON_VERSION} /tmp/get-pip.py; \
+    done && \
+    rm /tmp/get-pip.py
 
 # Install Bazelisk
 RUN wget https://github.com/bazelbuild/bazelisk/releases/download/${BAZELISK_VERSION}/bazelisk-linux-amd64 -O /usr/local/bin/bazelisk && \
     chmod +x /usr/local/bin/bazelisk
 
-# TODO(https://github.com/googleapis/librarian/issues/902): Create a dedicate non-root user and 
-# switch to the non-root user to run subsequent commands.
-
-# Set the working directory in the container.
+# Set the working directory for build-related tasks.
 WORKDIR /app
 
+# TODO(https://github.com/googleapis/librarian/issues/904): Install protoc for gencode.
 # TODO(https://github.com/googleapis/librarian/issues/907): Install Python dependencies from requirements.in.
 # TODO(https://github.com/googleapis/librarian/issues/905): Install Synthtool by cloning its repo.
 # TODO(https://github.com/googleapis/librarian/issues/906): Clone googleapis and run bazelisk build.
 
-# Copy the CLI script into the container and set ownership.
+# --- Final Stage ---
+# This stage creates the lightweight final image, copying only the
+# necessary artifacts from the builder stage.
+FROM marketplace.gcr.io/google/ubuntu2404
+
+# Install only the essential runtime libraries for Python.
+# These are the non "-dev" versions of the libraries used in the builder.
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+    ca-certificates \
+    libssl3 \
+    zlib1g \
+    libbz2-1.0 \
+    libffi8 \
+    libsqlite3-0 \
+    libreadline8 \
+    && apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# TODO(https://github.com/googleapis/librarian/issues/902): Create a dedicate non-root user and
+# switch to the non-root user to run subsequent commands.
+# Example:
+# RUN groupadd --system --gid 1000 appgroup && \
+#     useradd --system --uid 1000 --gid appgroup appuser
+# USER appuser
+
+# Copy all Python interpreters, their pip executables, and their standard libraries from the builder.
+COPY --from=builder /usr/local/bin/python3.9 /usr/local/bin/
+COPY --from=builder /usr/local/lib/python3.9 /usr/local/lib/python3.9
+
+COPY --from=builder /usr/local/bin/python3.10 /usr/local/bin/
+COPY --from=builder /usr/local/lib/python3.10 /usr/local/lib/python3.10
+
+COPY --from=builder /usr/local/bin/python3.11 /usr/local/bin/
+COPY --from=builder /usr/local/lib/python3.11 /usr/local/lib/python3.11
+
+COPY --from=builder /usr/local/bin/python3.12 /usr/local/bin/
+COPY --from=builder /usr/local/lib/python3.12 /usr/local/lib/python3.12
+
+COPY --from=builder /usr/local/bin/python3.13 /usr/local/bin/
+COPY --from=builder /usr/local/lib/python3.13 /usr/local/lib/python3.13
+
+# Set the working directory in the container.
+WORKDIR /app
+
+# Copy the CLI script into the container.
 COPY .generator/cli.py .
 
 # Set the entrypoint for the container to run the script.
-ENTRYPOINT ["python3.11", "./cli.py"]
+ENTRYPOINT ["python3.11", "./cli.py"]

cloudbuild.yaml

@@ -14,18 +14,30 @@
 
 # TODO(https://github.com/googleapis/google-cloud-python/issues/14142):
 # Reduce this timeout by moving the installation of Python runtimes to a separate base image
-timeout: 7200s  # 2 hours
+timeout: 7200s  # 2 hours for the first uncached run, can be lowered later.
 steps:
-  # This step builds the Docker image.
+  # STEP 1: Pull the latest version of the image to use as a cache.
+  # The '|| exit 0' part ensures the build doesn't fail if the image
+  # doesn't exist yet (e.g., on the very first run).
+  - name: 'gcr.io/cloud-builders/docker'
+    entrypoint: 'bash'
+    args: ['-c', 'docker pull gcr.io/$PROJECT_ID/python-librarian-generator:latest || exit 0']
+
+  # STEP 2: Build the new image, using the pulled image as a cache source.
   - name: 'gcr.io/cloud-builders/docker'
     args:
       - 'build'
-      - '-t'
-      - 'gcr.io/$PROJECT_ID/python-librarian-generator:latest'
-      - '-f'
-      - '.generator/Dockerfile'
+      - '--tag=gcr.io/$PROJECT_ID/python-librarian-generator:latest'
+      - '--cache-from=gcr.io/$PROJECT_ID/python-librarian-generator:latest'
+      - '--file=.generator/Dockerfile'
       - '.'
 
-# This section automatically create a storage bucket for storing docker build logs.
+# STEP 3: Push the newly built image to the registry so it can be used
+# as the cache for the next run. Cloud Build does this automatically if
+# the image is listed in the 'images' section.
+images:
+  - 'gcr.io/$PROJECT_ID/python-librarian-generator:latest'
+
+# This section automatically creates a storage bucket for storing docker build logs.
 options:
-  default_logs_bucket_behavior: REGIONAL_USER_OWNED_BUCKET
+  default_logs_bucket_behavior: REGIONAL_USER_OWNED_BUCKET