feat: make ephemeral env use supersetbot + deprecate build_docker.py (a…

…pache#30870)

.github/workflows/ephemeral-env.yml

@@ -1,30 +1,25 @@
 name: Ephemeral env workflow
 
+# Example manual trigger:  gh workflow run ephemeral-env.yml --ref fix_ephemerals  --field comment_body="/testenv up" --field issue_number=666
+
 on:
   issue_comment:
     types: [created]
+  workflow_dispatch:
+    inputs:
+      comment_body:
+        description: 'Comment body to simulate /testenv command'
+        required: true
+        default: '/testenv up'
+      issue_number:
+        description: 'Issue or PR number'
+        required: true
 
 jobs:
-  config:
-    runs-on: "ubuntu-22.04"
-    if: github.event.issue.pull_request
-    outputs:
-      has-secrets: ${{ steps.check.outputs.has-secrets }}
-    steps:
-      - name: "Check for secrets"
-        id: check
-        shell: bash
-        run: |
-          if [ -n "${{ (secrets.AWS_ACCESS_KEY_ID != '' && secrets.AWS_SECRET_ACCESS_KEY != '') || '' }}" ]; then
-            echo "has-secrets=1" >> "$GITHUB_OUTPUT"
-          fi
-
   ephemeral-env-comment:
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.issue.number || github.run_id }}-comment
+      group: ${{ github.workflow }}-${{ github.event.inputs.issue_number || github.event.issue.number || github.run_id }}-comment
       cancel-in-progress: true
-    needs: config
-    if: needs.config.outputs.has-secrets
     name: Evaluate ephemeral env comment trigger (/testenv)
     runs-on: ubuntu-22.04
     permissions:
@@ -44,18 +39,18 @@ jobs:
       with:
         result-encoding: string
         script: |
-          const pattern = /^\/testenv (up|down)/
-          const result = pattern.exec(context.payload.comment.body)
-          return result === null ? 'noop' : result[1]
+          const pattern = /^\/testenv (up|down)/;
+          const result = pattern.exec('${{ github.event.inputs.comment_body || github.event.comment.body }}');
+          return result === null ? 'noop' : result[1];
 
-    - name: Eval comment body for feature flags
+    - name: Looking for feature flags
       uses: actions/github-script@v7
       id: eval-feature-flags
       with:
         script: |
           const pattern = /FEATURE_(\w+)=(\w+)/g;
           let results = [];
-          [...context.payload.comment.body.matchAll(pattern)].forEach(match => {
+          [...'${{ github.event.inputs.comment_body || github.event.comment.body }}'.matchAll(pattern)].forEach(match => {
             const config = {
               name: `SUPERSET_FEATURE_${match[1]}`,
               value: match[2],
@@ -67,24 +62,25 @@ jobs:
     - name: Limit to committers
       if: >
         steps.eval-body.outputs.result != 'noop' &&
+        github.event_name == 'issue_comment' &&
         github.event.comment.author_association != 'MEMBER' &&
         github.event.comment.author_association != 'OWNER'
       uses: actions/github-script@v7
       with:
-        github-token: ${{github.token}}
+        github-token: ${{ github.token }}
         script: |
-          const errMsg = '@${{ github.event.comment.user.login }} Ephemeral environment creation is currently limited to committers.'
+          const errMsg = '@${{ github.event.comment.user.login }} Ephemeral environment creation is currently limited to committers.';
           github.rest.issues.createComment({
             issue_number: ${{ github.event.issue.number }},
             owner: context.repo.owner,
             repo: context.repo.repo,
             body: errMsg
-          })
-          core.setFailed(errMsg)
+          });
+          core.setFailed(errMsg);
 
   ephemeral-docker-build:
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.issue.number || github.run_id }}-build
+      group: ${{ github.workflow }}-${{ github.event.inputs.issue_number || github.event.issue.number || github.run_id }}-build
       cancel-in-progress: true
     needs: ephemeral-env-comment
     name: ephemeral-docker-build
@@ -98,9 +94,9 @@ jobs:
             const request = {
                 owner: context.repo.owner,
                 repo: context.repo.repo,
-                pull_number: ${{ github.event.issue.number }},
-            }
-            core.info(`Getting PR #${request.pull_number} from ${request.owner}/${request.repo}`)
+                pull_number: ${{ github.event.inputs.issue_number || github.event.issue.number }},
+            };
+            core.info(`Getting PR #${request.pull_number} from ${request.owner}/${request.repo}`);
             const pr = await github.rest.pulls.get(request);
             return pr.data;
 
@@ -121,12 +117,17 @@ jobs:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
+      - name: Setup supersetbot
+        uses: ./.github/actions/setup-supersetbot/
+
       - name: Build ephemeral env image
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
-          ./scripts/build_docker.py \
-            "ci" \
-            "pull_request" \
-            --build_context_ref ${{ github.event.issue.number }}
+          supersetbot docker \
+            --preset ci \
+            --platform  linux/amd64 \
+            --context-ref "$RELEASE"
 
       - name: Configure AWS credentials
         uses: aws-actions/configure-aws-credentials@v4
@@ -146,7 +147,7 @@ jobs:
           ECR_REPOSITORY: superset-ci
           IMAGE_TAG: apache/superset:${{ steps.get-sha.outputs.sha }}-ci
         run: |
-          docker tag $IMAGE_TAG $ECR_REGISTRY/$ECR_REPOSITORY:pr-${{ github.event.issue.number }}-ci
+          docker tag $IMAGE_TAG $ECR_REGISTRY/$ECR_REPOSITORY:pr-${{ github.event.inputs.issue_number || github.event.issue.number }}-ci
           docker push -a $ECR_REGISTRY/$ECR_REPOSITORY
 
   ephemeral-env-up:
@@ -181,30 +182,30 @@ jobs:
         aws ecr describe-images \
         --registry-id $(echo "${{ steps.login-ecr.outputs.registry }}" | grep -Eo "^[0-9]+") \
         --repository-name superset-ci \
-        --image-ids imageTag=pr-${{ github.event.issue.number }}-ci
+        --image-ids imageTag=pr-${{ github.event.inputs.issue_number || github.event.issue.number }}-ci
 
     - name: Fail on missing container image
       if: steps.check-image.outcome == 'failure'
       uses: actions/github-script@v7
       with:
-        github-token: ${{github.token}}
+        github-token: ${{ github.token }}
         script: |
-          const errMsg = '@${{ github.event.comment.user.login }} Container image not yet published for this PR. Please try again when build is complete.'
+          const errMsg = '@${{ github.event.comment.user.login }} Container image not yet published for this PR. Please try again when build is complete.';
           github.rest.issues.createComment({
-            issue_number: ${{ github.event.issue.number }},
+            issue_number: ${{ github.event.inputs.issue_number || github.event.issue.number }},
             owner: context.repo.owner,
             repo: context.repo.repo,
             body: errMsg
-          })
-          core.setFailed(errMsg)
+          });
+          core.setFailed(errMsg);
 
     - name: Fill in the new image ID in the Amazon ECS task definition
       id: task-def
       uses: aws-actions/amazon-ecs-render-task-definition@v1
       with:
         task-definition: .github/workflows/ecs-task-definition.json
         container-name: superset-ci
-        image: ${{ steps.login-ecr.outputs.registry }}/superset-ci:pr-${{ github.event.issue.number }}-ci
+        image: ${{ steps.login-ecr.outputs.registry }}/superset-ci:pr-${{ github.event.inputs.issue_number || github.event.issue.number }}-ci
 
     - name: Update env vars in the Amazon ECS task definition
       run: |
@@ -213,13 +214,10 @@ jobs:
     - name: Describe ECS service
       id: describe-services
       run: |
-        echo "active=$(aws ecs describe-services --cluster superset-ci --services pr-${{ github.event.issue.number }}-service | jq '.services[] | select(.status == "ACTIVE") | any')" >> $GITHUB_OUTPUT
+        echo "active=$(aws ecs describe-services --cluster superset-ci --services pr-${{ github.event.inputs.issue_number || github.event.issue.number }}-service | jq '.services[] | select(.status == "ACTIVE") | any')" >> $GITHUB_OUTPUT
     - name: Create ECS service
-      if: steps.describe-services.outputs.active != 'true'
       id: create-service
-      env:
-        ECR_SUBNETS: subnet-0e15a5034b4121710,subnet-0e8efef4a72224974
-        ECR_SECURITY_GROUP: sg-092ff3a6ae0574d91
+      if: steps.describe-services.outputs.active != 'true'
       run: |
         aws ecs create-service \
         --cluster superset-ci \
@@ -230,7 +228,6 @@ jobs:
         --platform-version LATEST \
         --network-configuration "awsvpcConfiguration={subnets=[$ECR_SUBNETS],securityGroups=[$ECR_SECURITY_GROUP],assignPublicIp=ENABLED}" \
         --tags key=pr,value=${{ github.event.issue.number }} key=github_user,value=${{ github.actor }}
-
     - name: Deploy Amazon ECS task definition
       id: deploy-task
       uses: aws-actions/amazon-ecs-deploy-task-definition@v2
@@ -245,39 +242,35 @@ jobs:
       id: list-tasks
       run: |
         echo "task=$(aws ecs list-tasks --cluster superset-ci --service-name pr-${{ github.event.issue.number }}-service | jq '.taskArns | first')" >> $GITHUB_OUTPUT
-
     - name: Get network interface
       id: get-eni
       run: |
-        echo "eni=$(aws ecs describe-tasks --cluster superset-ci --tasks ${{ steps.list-tasks.outputs.task }} | jq '.tasks | .[0] | .attachments | .[0] | .details | map(select(.name=="networkInterfaceId")) | .[0] | .value')" >> $GITHUB_OUTPUT
-
+        echo "eni=$(aws ecs describe-tasks --cluster superset-ci --tasks ${{ steps.list-tasks.outputs.task }} | jq '.tasks | .[0] | .attachments | .[0] | .details | map(select(.name==\"networkInterfaceId\")) | .[0] | .value')" >> $GITHUB_OUTPUT
     - name: Get public IP
       id: get-ip
       run: |
         echo "ip=$(aws ec2 describe-network-interfaces --network-interface-ids ${{ steps.get-eni.outputs.eni }} | jq -r '.NetworkInterfaces | first | .Association.PublicIp')" >> $GITHUB_OUTPUT
-
     - name: Comment (success)
       if: ${{ success() }}
       uses: actions/github-script@v7
       with:
         github-token: ${{github.token}}
         script: |
           github.rest.issues.createComment({
-            issue_number: ${{ github.event.issue.number }},
+            issue_number: ${{ github.event.inputs.issue_number || github.event.issue.number }},
             owner: context.repo.owner,
             repo: context.repo.repo,
-            body: '@${{ github.event.comment.user.login }} Ephemeral environment spinning up at http://${{ steps.get-ip.outputs.ip }}:8080. Credentials are `admin`/`admin`. Please allow several minutes for bootstrapping and startup.'
+            body: '@${{ github.event.inputs.user_login || github.event.comment.user.login }} Ephemeral environment spinning up at http://${{ steps.get-ip.outputs.ip }}:8080. Credentials are `admin`/`admin`. Please allow several minutes for bootstrapping and startup.'
           })
-
     - name: Comment (failure)
       if: ${{ failure() }}
       uses: actions/github-script@v7
       with:
         github-token: ${{github.token}}
         script: |
           github.rest.issues.createComment({
-            issue_number: ${{ github.event.issue.number }},
+            issue_number: ${{ github.event.inputs.issue_number || github.event.issue.number }},
             owner: context.repo.owner,
             repo: context.repo.repo,
-            body: '@${{ github.event.comment.user.login }} Ephemeral environment creation failed. Please check the Actions logs for details.'
+            body: '@${{ github.event.inputs.user_login || github.event.comment.user.login }} Ephemeral environment creation failed. Please check the Actions logs for details.'
           })

Dockerfile

@@ -115,7 +115,7 @@ RUN mkdir -p ${PYTHONPATH} superset/static requirements superset-frontend apache
         libldap2-dev \
     && touch superset/static/version_info.json \
     && chown -R superset:superset ./* \
-    && rm -rf /var/lib/apt/lists/*
+    && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
 
 COPY --chown=superset:superset pyproject.toml setup.py MANIFEST.in README.md ./
 # setup.py uses the version information in package.json
@@ -128,7 +128,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     && pip install --no-cache-dir --upgrade setuptools pip \
     && pip install --no-cache-dir -r requirements/base.txt \
     && apt-get autoremove -yqq --purge build-essential \
-    && rm -rf /var/lib/apt/lists/*
+    && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
 
 # Copy the compiled frontend assets
 COPY --chown=superset:superset --from=superset-node /app/superset/static/assets superset/static/assets
@@ -177,7 +177,7 @@ RUN apt-get update -qq \
         libxtst6 \
         git \
         pkg-config \
-        && rm -rf /var/lib/apt/lists/*
+        && rm -rf /var/cache/apt/archives/* /var/lib/apt/lists/*
 
 RUN --mount=type=cache,target=/root/.cache/pip \
     pip install --no-cache-dir playwright
@@ -199,21 +199,21 @@ RUN if [ "$INCLUDE_FIREFOX" = "true" ]; then \
         && wget -q https://github.com/mozilla/geckodriver/releases/download/${GECKODRIVER_VERSION}/geckodriver-${GECKODRIVER_VERSION}-linux64.tar.gz -O - | tar xfz - -C /usr/local/bin \
         && wget -q https://download-installer.cdn.mozilla.net/pub/firefox/releases/${FIREFOX_VERSION}/linux-x86_64/en-US/firefox-${FIREFOX_VERSION}.tar.bz2 -O - | tar xfj - -C /opt \
         && ln -s /opt/firefox/firefox /usr/local/bin/firefox \
-        && apt-get autoremove -yqq --purge wget bzip2 && rm -rf /var/[log,tmp]/* /tmp/* /var/lib/apt/lists/*; \
+        && apt-get autoremove -yqq --purge wget bzip2 && rm -rf /var/[log,tmp]/* /tmp/* /var/lib/apt/lists/* /var/cache/apt/archives/*; \
     fi
 
 # Installing mysql client os-level dependencies in dev image only because GPL
 RUN apt-get install -yqq --no-install-recommends \
         default-libmysqlclient-dev \
-    && rm -rf /var/lib/apt/lists/*
+    && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
 
 COPY --chown=superset:superset requirements/development.txt requirements/
 RUN --mount=type=cache,target=/root/.cache/pip \
     apt-get update -qq && apt-get install -yqq --no-install-recommends \
       build-essential \
     && pip install --no-cache-dir -r requirements/development.txt \
     && apt-get autoremove -yqq --purge build-essential \
-    && rm -rf /var/lib/apt/lists/*
+    && rm -rf /var/lib/apt/lists/* /var/cache/apt/archives/*
 
 USER superset
 ######################################################################

docker-compose.yml

@@ -25,7 +25,6 @@ x-superset-user: &superset-user root
 x-superset-depends-on: &superset-depends-on
   - db
   - redis
-  - superset-checks
 x-superset-volumes: &superset-volumes
   # /app/pythonpath_docker will be appended to the PYTHONPATH in the final container
   - ./docker:/app/docker
@@ -131,23 +130,6 @@ services:
       - REDIS_PORT=6379
       - REDIS_SSL=false
 
-  superset-checks:
-    build:
-      context: .
-      target: python-base
-      cache_from:
-        - apache/superset-cache:3.10-slim-bookworm
-    container_name: superset_checks
-    command: ["/app/scripts/check-env.py"]
-    env_file:
-      - path: docker/.env # default
-        required: true
-      - path: docker/.env-local # optional override
-        required: false
-    user: *superset-user
-    healthcheck:
-      disable: true
-
   superset-init:
     build:
       <<: *common-build
@@ -179,6 +161,7 @@ services:
       # set this to false if you have perf issues running the npm i; npm run dev in-docker
       # if you do so, you have to run this manually on the host, which should perform better!
       BUILD_SUPERSET_FRONTEND_IN_DOCKER: true
+      NPM_RUN_PRUNE: false
       SCARF_ANALYTICS: "${SCARF_ANALYTICS:-}"
     container_name: superset_node
     command: ["/app/docker/docker-frontend.sh"]

docker/docker-frontend.sh

@@ -27,6 +27,11 @@ if [ "$BUILD_SUPERSET_FRONTEND_IN_DOCKER" = "true" ]; then
     echo "Building Superset frontend in dev mode inside docker container"
     cd /app/superset-frontend
 
+    if [ "$NPM_RUN_PRUNE" = "true" ]; then
+        echo "Running `npm run prune`"
+        npm run prune
+    fi
+
     echo "Running `npm install`"
     npm install
 

docs/docs/installation/docker-builds.mdx

@@ -29,7 +29,7 @@ We have a set of build "presets" that each represent a combination of
 parameters for the build, mostly pointing to either different target layer
 for the build, and/or base image.
 
-Here are the build presets that are exposed through the `build_docker.py` script:
+Here are the build presets that are exposed through the `supersetbot docker` utility:
 
 - `lean`: The default Docker image, including both frontend and backend. Tags
   without a build_preset are lean builds (ie: `latest`, `4.0.0`, `3.0.0`, ...). `lean`
@@ -62,8 +62,8 @@ Here are the build presets that are exposed through the `build_docker.py` script
 
 
 For insights or modifications to the build matrix and tagging conventions,
-check the [build_docker.py](https://github.com/apache/superset/blob/master/scripts/build_docker.py)
-script and the [docker.yml](https://github.com/apache/superset/blob/master/.github/workflows/docker.yml)
+check the [supersetbot docker](https://github.com/apache-superset/supersetbot)
+subcommand and the [docker.yml](https://github.com/apache/superset/blob/master/.github/workflows/docker.yml)
 GitHub action.
 
 ## Key ARGs in Dockerfile

docs/docs/installation/docker-compose.mdx

@@ -95,6 +95,14 @@ perform those operations. In this case, we recommend you set the env var
 Simply trigger `npm i && npm run dev`, this should be MUCH faster.
 :::
 
+:::tip
+Sometimes, your npm-related state can get out-of-wack, running `npm run prune` from
+the `superset-frontend/` folder will nuke the various' packages `node_module/` folders
+and help you start fresh. In the context of `docker compose` setting
+`export NPM_RUN_PRUNE=true` prior to running `docker compose up` will trigger that
+from within docker. This will slow down the startup, but will fix various npm-related issues.
+:::
+
 ### Option #2 - build a set of immutable images from the local branch
 
 ```bash