[Arch] Add runtime image build CI & clean up runtime build using jinja2 template (#3055)

* test_runtime_client.py to test _execute_bash()

* runtime_build and runtime tweaks

* fix in docker script

* revert bash changes

* use sandbox_config.update_source_code to control source code update

* add od_version to the sandbox tag

* add doc instruction for update source code

* do not remove whole poetry folder;
add mamba clean

* add missing newlines

* cleanup runtime dockerfile into jinja template

* make prep temp file a separate function;
make that function accessible through cli

* modify `runtime_build.py` so it can generate directory for building docker img

* add dockerfile and sdist of runtime to gitignore since it will be dynamically generated

* add runtime to build

* do not rebuild new image when an `od_runtime` is provided

* use default container_image for testing if possible

* move runtime tests to ghcr runtime workflow

* update docker base dir for runtime

* fix unittest

* fix image name

* fix image name for test case

* rename to make it consistent

---------

Co-authored-by: tobitege <tobitege@gmx.de>

.github/workflows/ghcr-runtime.yml

@@ -0,0 +1,242 @@
+name: Build Publish and Test Runtime Image
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
+
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - '*'
+  pull_request:
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: 'Reason for manual trigger'
+        required: true
+        default: ''
+
+jobs:
+  ghcr_build_runtime:
+    runs-on: ubuntu-latest
+
+    outputs:
+      tags: ${{ steps.capture-tags.outputs.tags }}
+
+    permissions:
+      contents: read
+      packages: write
+
+    strategy:
+      matrix:
+        image: ["od_runtime"]
+        base_image: ["ubuntu:22.04"]
+        platform: ["amd64", "arm64"]
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # if set to "true" but frees about 6 GB
+          tool-cache: true
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "poetry"
+
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+
+      - name: Create source distribution and Dockerfile
+        run: poetry run python3 opendevin/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image }} --build_folder containers/runtime
+
+      - name: Build and export image
+        id: build
+        run: ./containers/build.sh ${{ matrix.image }} ${{ github.repository_owner }} ${{ matrix.platform }}
+
+      - name: Capture tags
+        id: capture-tags
+        run: |
+          tags=$(cat tags.txt)
+          echo "tags=$tags"
+          echo "tags=$tags" >> $GITHUB_OUTPUT
+
+      - name: Upload Docker image as artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
+          path: /tmp/${{ matrix.image }}_image_${{ matrix.platform }}.tar
+
+  test-for-runtime:
+    name: Test for Runtime
+    runs-on: ubuntu-latest
+    needs: ghcr_build_runtime
+    env:
+      PERSIST_SANDBOX: "false"
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          # this might remove tools that are actually needed,
+          # when set to "true" but frees about 6 GB
+          tool-cache: true
+
+          # all of these default to true, but feel free to set to
+          # "false" if necessary for your workflow
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          swap-storage: true
+
+      - name: Install poetry via pipx
+        run: pipx install poetry
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: "poetry"
+
+      - name: Install Python dependencies using Poetry
+        run: make install-python-dependencies
+
+      - name: Download Runtime Docker image
+        uses: actions/download-artifact@v4
+        with:
+          name: od_runtime-docker-image-amd64
+          path: /tmp/
+
+      - name: Load Runtime image and run runtime tests
+        run: |
+          # Load the Docker image and capture the output
+          output=$(docker load -i /tmp/od_runtime_image_amd64.tar)
+
+          # Extract the first image name from the output
+          image_name=$(echo "$output" | grep -oP 'Loaded image: \K.*' | head -n 1)
+
+          # Print the full name of the image
+          echo "Loaded Docker image: $image_name"
+
+          SANDBOX_CONTAINER_IMAGE=$image_name TEST_IN_CI=true poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml -s ./tests/unit/test_runtime.py
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+
+  ghcr_push:
+    runs-on: ubuntu-latest
+    # don't push if runtime tests fail
+    needs: [ghcr_build_runtime, test-for-runtime]
+    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
+
+    env:
+      tags: ${{ needs.ghcr_build_runtime.outputs.tags }}
+
+    permissions:
+      contents: read
+      packages: write
+
+    strategy:
+      matrix:
+        image: ["od_runtime"]
+        platform: ["amd64", "arm64"]
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Login to GHCR
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Download Docker images
+        uses: actions/download-artifact@v4
+        with:
+          name: ${{ matrix.image }}-docker-image-${{ matrix.platform }}
+          path: /tmp/${{ matrix.platform }}
+
+      - name: Load images and push to registry
+        run: |
+          mv /tmp/${{ matrix.platform }}/${{ matrix.image }}_image_${{ matrix.platform }}.tar .
+          loaded_image=$(docker load -i ${{ matrix.image }}_image_${{ matrix.platform }}.tar | grep "Loaded image:" | head -n 1 | awk '{print $3}')
+          echo "loaded image = $loaded_image"
+          tags=$(echo ${tags} | tr ' ' '\n')
+          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
+          echo "image name = $image_name"
+          for tag in $tags; do
+            echo "tag = $tag"
+            docker tag $loaded_image $image_name:${tag}_${{ matrix.platform }}
+            docker push $image_name:${tag}_${{ matrix.platform }}
+          done
+
+  create_manifest:
+    runs-on: ubuntu-latest
+    needs: [ghcr_build_runtime, ghcr_push]
+    if: github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/')
+
+    env:
+      tags: ${{ needs.ghcr_build_runtime.outputs.tags }}
+
+    strategy:
+      matrix:
+        image: ["od_runtime"]
+
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Login to GHCR
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Create and push multi-platform manifest
+        run: |
+          image_name=$(echo "ghcr.io/${{ github.repository_owner }}/${{ matrix.image }}" | tr '[:upper:]' '[:lower:]')
+          echo "image name = $image_name"
+          tags=$(echo ${tags} | tr ' ' '\n')
+          for tag in $tags; do
+            echo 'tag = $tag'
+            docker buildx imagetools create --tag $image_name:$tag \
+              $image_name:${tag}_amd64 \
+              $image_name:${tag}_arm64
+          done

.github/workflows/run-runtime-tests.yml

@@ -1,64 +0,0 @@
-name: Run Runtime Tests
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
-
-on:
-  push:
-    branches:
-      - main
-    paths-ignore:
-      - '**/*.md'
-      - 'frontend/**'
-      - 'docs/**'
-      - 'evaluation/**'
-  pull_request:
-
-env:
-  PERSIST_SANDBOX : "false"
-
-jobs:
-  test-for-runtime:
-    name: Test for Runtime
-    runs-on: ubuntu-latest
-    env:
-      PERSIST_SANDBOX: "false"
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Free Disk Space (Ubuntu)
-        uses: jlumbroso/free-disk-space@main
-        with:
-          # this might remove tools that are actually needed,
-          # when set to "true" but frees about 6 GB
-          tool-cache: true
-
-          # all of these default to true, but feel free to set to
-          # "false" if necessary for your workflow
-          android: true
-          dotnet: true
-          haskell: true
-          large-packages: true
-          swap-storage: true
-
-      - name: Install poetry via pipx
-        run: pipx install poetry
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-          cache: "poetry"
-
-      - name: Install Python dependencies using Poetry
-        run: make install-python-dependencies
-
-      - name: Run runtime tests
-        run: |
-          TEST_IN_CI=true poetry run pytest --cov=agenthub --cov=opendevin --cov-report=xml -s ./tests/unit/test_runtime.py
-
-      - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v4
-        env:
-          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}