Add Docker, Java, Golang, and other programming languages to runtime image (#8026)

Co-authored-by: openhands <openhands@all-hands.dev>
2026-01-09 14:57:59 -05:00 · 2025-05-14 13:46:06 -04:00
parent b1dca48c8e
commit 6145552841
4 changed files with 113 additions and 12 deletions
--- a/.github/workflows/ghcr-build.yml
+++ b/.github/workflows/ghcr-build.yml
@@ -37,17 +37,18 @@ jobs:
        shell: bash
        id: define-base-images
        run: |
-          # Only build nikolaik on PRs, otherwise build both nikolaik and ubuntu.
+          # Only build nikolaik on PRs, otherwise build both nikolaik, nikolaik-full, ubuntu, and ubuntu-full.
          if [[ "$GITHUB_EVENT_NAME" == "pull_request" ]]; then
            json=$(jq -n -c '[
-                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik" },
-                { image: "ubuntu:24.04", tag: "ubuntu" }
-
+                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik", include_languages: false },
+                { image: "ubuntu:24.04", tag: "ubuntu", include_languages: false }
              ]')
          else
            json=$(jq -n -c '[
-                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik" },
-                { image: "ubuntu:24.04", tag: "ubuntu" }
+                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik", include_languages: false },
+                { image: "nikolaik/python-nodejs:python3.12-nodejs22", tag: "nikolaik-full", include_languages: true },
+                { image: "ubuntu:24.04", tag: "ubuntu", include_languages: false },
+                { image: "ubuntu:24.04", tag: "ubuntu-full", include_languages: true }
              ]')
          fi
          echo "base_image=$json" >> "$GITHUB_OUTPUT"
@@ -149,7 +150,7 @@ jobs:
      - name: Install Python dependencies using Poetry
        run: make install-python-dependencies POETRY_GROUP=main INSTALL_PLAYWRIGHT=0
      - name: Create source distribution and Dockerfile
-        run: poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image.image }} --build_folder containers/runtime --force_rebuild
+        run: poetry run python3 openhands/runtime/utils/runtime_build.py --base_image ${{ matrix.base_image.image }} --build_folder containers/runtime --force_rebuild ${{ matrix.base_image.include_languages && '--include_programming_languages' || '' }}
      - name: Lowercase Repository Owner
        run: |
          echo REPO_OWNER=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV
--- a/openhands/runtime/utils/runtime_build.py
+++ b/openhands/runtime/utils/runtime_build.py
@@ -32,13 +32,15 @@ def _generate_dockerfile(
    base_image: str,
    build_from: BuildFromImageType = BuildFromImageType.SCRATCH,
    extra_deps: str | None = None,
+    include_programming_languages: bool = False,
 ) -> str:
    """Generate the Dockerfile content for the runtime image based on the base image.

    Parameters:
    - base_image (str): The base image provided for the runtime image
    - build_from (BuildFromImageType): The build method for the runtime image.
-    - extra_deps (str):
+    - extra_deps (str): Extra dependencies to install
+    - include_programming_languages (bool): Whether to include programming language dependencies

    Returns:
    - str: The resulting Dockerfile content
@@ -55,6 +57,7 @@ def _generate_dockerfile(
        build_from_scratch=build_from == BuildFromImageType.SCRATCH,
        build_from_versioned=build_from == BuildFromImageType.VERSIONED,
        extra_deps=extra_deps if extra_deps is not None else '',
+        include_programming_languages=include_programming_languages,
    )
    return dockerfile_content

@@ -111,6 +114,7 @@ def build_runtime_image(
    dry_run: bool = False,
    force_rebuild: bool = False,
    extra_build_args: list[str] | None = None,
+    include_programming_languages: bool = False,
 ) -> str:
    """Prepares the final docker build folder.

@@ -120,11 +124,12 @@ def build_runtime_image(
    - base_image (str): The name of the base Docker image to use
    - runtime_builder (RuntimeBuilder): The runtime builder to use
    - platform (str): The target platform for the build (e.g. linux/amd64, linux/arm64)
-    - extra_deps (str):
+    - extra_deps (str): Extra dependencies to install
    - build_folder (str): The directory to use for the build. If not provided a temporary directory will be used
    - dry_run (bool): if True, it will only ready the build folder. It will not actually build the Docker image
    - force_rebuild (bool): if True, it will create the Dockerfile which uses the base_image
    - extra_build_args (List[str]): Additional build arguments to pass to the builder
+    - include_programming_languages (bool): Whether to include programming language dependencies

    Returns:
    - str: <image_repo>:<MD5 hash>. Where MD5 hash is the hash of the docker build folder
@@ -142,6 +147,7 @@ def build_runtime_image(
                force_rebuild=force_rebuild,
                platform=platform,
                extra_build_args=extra_build_args,
+                include_programming_languages=include_programming_languages,
            )
            return result

@@ -154,6 +160,7 @@ def build_runtime_image(
        force_rebuild=force_rebuild,
        platform=platform,
        extra_build_args=extra_build_args,
+        include_programming_languages=include_programming_languages,
    )
    return result

@@ -167,6 +174,7 @@ def build_runtime_image_in_folder(
    force_rebuild: bool,
    platform: str | None = None,
    extra_build_args: list[str] | None = None,
+    include_programming_languages: bool = False,
 ) -> str:
    runtime_image_repo, _ = get_runtime_image_repo_and_tag(base_image)
    lock_tag = f'oh_v{oh_version}_{get_hash_for_lock_files(base_image)}'
@@ -188,6 +196,7 @@ def build_runtime_image_in_folder(
            base_image,
            build_from=BuildFromImageType.SCRATCH,
            extra_deps=extra_deps,
+            include_programming_languages=include_programming_languages,
        )
        if not dry_run:
            _build_sandbox_image(
@@ -226,7 +235,13 @@ def build_runtime_image_in_folder(
    else:
        logger.debug(f'Build [{hash_image_name}] from scratch')

-    prep_build_folder(build_folder, base_image, build_from, extra_deps)
+    prep_build_folder(
+        build_folder,
+        base_image,
+        build_from,
+        extra_deps,
+        include_programming_languages=include_programming_languages,
+    )
    if not dry_run:
        _build_sandbox_image(
            build_folder,
@@ -251,6 +266,7 @@ def prep_build_folder(
    base_image: str,
    build_from: BuildFromImageType,
    extra_deps: str | None,
+    include_programming_languages: bool = False,
 ) -> None:
    # Copy the source code to directory. It will end up in build_folder/code
    # If package is not found, build from source code
@@ -282,6 +298,7 @@ def prep_build_folder(
        base_image,
        build_from=build_from,
        extra_deps=extra_deps,
+        include_programming_languages=include_programming_languages,
    )
    dockerfile_path = Path(build_folder, 'Dockerfile')
    with open(str(dockerfile_path), 'w') as f:
@@ -378,6 +395,12 @@ if __name__ == '__main__':
    parser.add_argument('--build_folder', type=str, default=None)
    parser.add_argument('--force_rebuild', action='store_true', default=False)
    parser.add_argument('--platform', type=str, default=None)
+    parser.add_argument(
+        '--include_programming_languages',
+        action='store_true',
+        default=False,
+        help='Include programming language dependencies (Java, Go, PHP, Ruby)',
+    )
    args = parser.parse_args()

    if args.build_folder is not None:
@@ -409,6 +432,7 @@ if __name__ == '__main__':
                dry_run=True,
                force_rebuild=args.force_rebuild,
                platform=args.platform,
+                include_programming_languages=args.include_programming_languages,
            )

            _runtime_image_repo, runtime_image_source_tag = (
--- a/openhands/runtime/utils/runtime_templates/Dockerfile.j2
+++ b/openhands/runtime/utils/runtime_templates/Dockerfile.j2
@@ -10,6 +10,13 @@ ENV POETRY_VIRTUALENVS_PATH=/openhands/poetry \
    GIT_EDITOR="code --wait" \
    OPENVSCODE_SERVER_ROOT=/openhands/.openvscode-server

+{% if include_programming_languages %}
+ENV GOPATH=/go \
+    GOROOT=/usr/local/go \
+    PATH="/usr/local/go/bin:/go/bin:/root/.cargo/bin:${PATH}" \
+    JAVA_HOME=/usr/lib/jvm/java-17-openjdk-amd64
+{% endif %}
+
 {% macro setup_base_system() %}

 # Install base system dependencies
@@ -27,10 +34,53 @@ RUN apt-get update && \
    TZ=Etc/UTC DEBIAN_FRONTEND=noninteractive \
        apt-get install -y --no-install-recommends nodejs python3.12 python-is-python3 python3-pip python3.12-venv && \
    corepack enable yarn && \
-    {% endif -%}
+    {% endif %}
    apt-get clean && \
    rm -rf /var/lib/apt/lists/*

+# Install Docker
+RUN apt-get update && \
+    apt-get install -y apt-transport-https ca-certificates gnupg lsb-release && \
+    if grep -q "Debian" /etc/os-release; then \
+        curl -fsSL https://download.docker.com/linux/debian/gpg | gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg && \
+        echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian $(lsb_release -cs) stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null; \
+    else \
+        curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg && \
+        echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null; \
+    fi && \
+    apt-get update && \
+    apt-get install -y docker-ce docker-ce-cli containerd.io && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+{% if include_programming_languages %}
+# Install Java
+RUN apt-get update && \
+    apt-get install -y openjdk-17-jdk maven gradle && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install Golang
+RUN curl -OL https://golang.org/dl/go1.21.0.linux-amd64.tar.gz && \
+    tar -C /usr/local -xzf go1.21.0.linux-amd64.tar.gz && \
+    rm go1.21.0.linux-amd64.tar.gz && \
+    echo "export PATH=$PATH:/usr/local/go/bin" >> /etc/profile && \
+    echo "export PATH=$PATH:/usr/local/go/bin" >> /etc/bash.bashrc
+
+# Install PHP
+RUN apt-get update && \
+    apt-get install -y php && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install Ruby
+RUN apt-get update && \
+    apt-get install -y ruby-full ruby-bundler && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+{% endif %}
+
+
 {% if 'ubuntu' in base_image %}
 RUN ln -s "$(dirname $(which node))/corepack" /usr/local/bin/corepack && \
    npm install -g corepack && corepack enable yarn && \
@@ -52,6 +102,11 @@ RUN mkdir -p /openhands && \
    mkdir -p /openhands/logs && \
    mkdir -p /openhands/poetry

+{% if include_programming_languages %}
+RUN mkdir -p /go && \
+    chmod -R 777 /go
+{% endif %}
+
 {% endmacro %}

 {% macro setup_vscode_server() %}
@@ -111,8 +166,19 @@ RUN /openhands/micromamba/bin/micromamba config set changeps1 False && \
    /openhands/micromamba/bin/micromamba run -n openhands poetry env use python3.12

 # Install project dependencies in smaller chunks
+# Ensure we have all necessary build dependencies for pydantic-core
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
+    gcc \
+    g++ \
+    python3-dev \
+    && apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Install main dependencies first
 RUN /openhands/micromamba/bin/micromamba run -n openhands poetry install --only main --no-interaction --no-root

+# Then install runtime dependencies
 RUN /openhands/micromamba/bin/micromamba run -n openhands poetry install --only runtime --no-interaction --no-root

 # Install playwright and its dependencies
--- a/tests/unit/test_runtime_build.py
+++ b/tests/unit/test_runtime_build.py
@@ -87,6 +87,7 @@ def test_prep_build_folder(temp_dir):
            base_image=DEFAULT_BASE_IMAGE,
            build_from=BuildFromImageType.SCRATCH,
            extra_deps=None,
+            include_programming_languages=False,
        )

    # make sure that the code was copied
@@ -133,6 +134,7 @@ def test_generate_dockerfile_build_from_scratch():
    dockerfile_content = _generate_dockerfile(
        base_image,
        build_from=BuildFromImageType.SCRATCH,
+        include_programming_languages=False,
    )
    assert base_image in dockerfile_content
    assert 'apt-get update' in dockerfile_content
@@ -153,6 +155,7 @@ def test_generate_dockerfile_build_from_lock():
    dockerfile_content = _generate_dockerfile(
        base_image,
        build_from=BuildFromImageType.LOCK,
+        include_programming_languages=False,
    )

    # These commands SHOULD NOT include in the dockerfile if build_from_scratch is False
@@ -171,6 +174,7 @@ def test_generate_dockerfile_build_from_versioned():
    dockerfile_content = _generate_dockerfile(
        base_image,
        build_from=BuildFromImageType.VERSIONED,
+        include_programming_languages=False,
    )

    # these commands should not exist when build from versioned
@@ -247,7 +251,11 @@ def test_build_runtime_image_from_scratch():
            == f'{get_runtime_image_repo()}:{OH_VERSION}_mock-lock-tag_mock-source-tag'
        )
        mock_prep_build_folder.assert_called_once_with(
-            ANY, base_image, BuildFromImageType.SCRATCH, None
+            ANY,
+            base_image,
+            BuildFromImageType.SCRATCH,
+            None,
+            include_programming_languages=False,
        )


@@ -342,6 +350,7 @@ def test_build_runtime_image_exact_hash_not_exist_and_lock_exist():
            f'{get_runtime_image_repo()}:{OH_VERSION}_mock-lock-tag',
            BuildFromImageType.LOCK,
            None,
+            include_programming_languages=False,
        )


@@ -401,6 +410,7 @@ def test_build_runtime_image_exact_hash_not_exist_and_lock_not_exist_and_version
            f'{get_runtime_image_repo()}:{OH_VERSION}_mock-versioned-tag',
            BuildFromImageType.VERSIONED,
            None,
+            include_programming_languages=False,
        )