ci(frontend): Speed up E2E test job (#12090)

The frontend `e2e_test` doesn't have a working build cache setup,
causing really slow builds = slow test jobs. These changes reduce total
test runtime from ~12 minutes to ~5 minutes.

### Changes 🏗️

- Inject build cache config into docker compose config; let `buildx
bake` use GHA cache directly
  - Add `docker-ci-fix-compose-build-cache.py` script
- Optimize `backend/Dockerfile` + root `.dockerignore`
- Replace broken DIY pnpm store caching with `actions/setup-node`
built-in cache management
- Add caching for test seed data created in DB

### Checklist 📋

#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
  - CI

.github/workflows/platform-frontend-ci.yml

@@ -26,7 +26,6 @@ jobs:
   setup:
     runs-on: ubuntu-latest
     outputs:
-      cache-key: ${{ steps.cache-key.outputs.key }}
       components-changed: ${{ steps.filter.outputs.components }}
 
     steps:
@@ -41,28 +40,17 @@ jobs:
             components:
               - 'autogpt_platform/frontend/src/components/**'
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-
       - name: Enable corepack
         run: corepack enable
 
-      - name: Generate cache key
-        id: cache-key
-        run: echo "key=${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/package.json') }}" >> $GITHUB_OUTPUT
-
-      - name: Cache dependencies
-        uses: actions/cache@v5
+      - name: Set up Node
+        uses: actions/setup-node@v6
         with:
-          path: ~/.pnpm-store
-          key: ${{ steps.cache-key.outputs.key }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
-      - name: Install dependencies
+      - name: Install dependencies to populate cache
         run: pnpm install --frozen-lockfile
 
   lint:
@@ -73,22 +61,15 @@ jobs:
       - name: Checkout repository
         uses: actions/checkout@v6
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-
       - name: Enable corepack
         run: corepack enable
 
-      - name: Restore dependencies cache
-        uses: actions/cache@v5
+      - name: Set up Node
+        uses: actions/setup-node@v6
         with:
-          path: ~/.pnpm-store
-          key: ${{ needs.setup.outputs.cache-key }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
@@ -111,22 +92,15 @@ jobs:
         with:
           fetch-depth: 0
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-
       - name: Enable corepack
         run: corepack enable
 
-      - name: Restore dependencies cache
-        uses: actions/cache@v5
+      - name: Set up Node
+        uses: actions/setup-node@v6
         with:
-          path: ~/.pnpm-store
-          key: ${{ needs.setup.outputs.cache-key }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
@@ -141,10 +115,8 @@ jobs:
           exitOnceUploaded: true
 
   e2e_test:
+    name: end-to-end tests
     runs-on: big-boi
-    needs: setup
-    strategy:
-      fail-fast: false
 
     steps:
       - name: Checkout repository
@@ -152,19 +124,11 @@ jobs:
         with:
           submodules: recursive
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-
-      - name: Enable corepack
-        run: corepack enable
-
-      - name: Copy default supabase .env
+      - name: Set up Platform - Copy default supabase .env
         run: |
           cp ../.env.default ../.env
 
-      - name: Copy backend .env and set OpenAI API key
+      - name: Set up Platform - Copy backend .env and set OpenAI API key
         run: |
           cp ../backend/.env.default ../backend/.env
           echo "OPENAI_INTERNAL_API_KEY=${{ secrets.OPENAI_API_KEY }}" >> ../backend/.env
@@ -172,77 +136,125 @@ jobs:
           # Used by E2E test data script to generate embeddings for approved store agents
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
 
-      - name: Set up Docker Buildx
+      - name: Set up Platform - Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
+        with:
+          driver: docker-container
+          driver-opts: network=host
 
-      - name: Cache Docker layers
+      - name: Set up Platform - Expose GHA cache to docker buildx CLI
+        uses: crazy-max/ghaction-github-runtime@v3
+
+      - name: Set up Platform - Build Docker images (with cache)
+        working-directory: autogpt_platform
+        run: |
+          pip install pyyaml
+
+          # Resolve extends and generate a flat compose file that bake can understand
+          docker compose -f docker-compose.yml config > docker-compose.resolved.yml
+
+          # Add cache configuration to the resolved compose file
+          python ../.github/workflows/scripts/docker-ci-fix-compose-build-cache.py \
+            --source docker-compose.resolved.yml \
+            --cache-from "type=gha" \
+            --cache-to "type=gha,mode=max" \
+            --backend-hash "${{ hashFiles('autogpt_platform/backend/Dockerfile', 'autogpt_platform/backend/poetry.lock', 'autogpt_platform/backend/backend') }}" \
+            --frontend-hash "${{ hashFiles('autogpt_platform/frontend/Dockerfile', 'autogpt_platform/frontend/pnpm-lock.yaml', 'autogpt_platform/frontend/src') }}" \
+            --git-ref "${{ github.ref }}"
+
+          # Build with bake using the resolved compose file (now includes cache config)
+          docker buildx bake --allow=fs.read=.. -f docker-compose.resolved.yml --load
+        env:
+          NEXT_PUBLIC_PW_TEST: true
+
+      - name: Set up tests - Cache E2E test data
+        id: e2e-data-cache
         uses: actions/cache@v5
         with:
-          path: /tmp/.buildx-cache
-          key: ${{ runner.os }}-buildx-frontend-test-${{ hashFiles('autogpt_platform/docker-compose.yml', 'autogpt_platform/backend/Dockerfile', 'autogpt_platform/backend/pyproject.toml', 'autogpt_platform/backend/poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-buildx-frontend-test-
+          path: /tmp/e2e_test_data.sql
+          key: e2e-test-data-${{ hashFiles('autogpt_platform/backend/test/e2e_test_data.py', 'autogpt_platform/backend/migrations/**', '.github/workflows/platform-frontend-ci.yml') }}
 
-      - name: Run docker compose
+      - name: Set up Platform - Start Supabase DB + Auth
         run: |
-          NEXT_PUBLIC_PW_TEST=true docker compose -f ../docker-compose.yml up -d
+          docker compose -f ../docker-compose.resolved.yml up -d db auth --no-build
+          echo "Waiting for database to be ready..."
+          timeout 60 sh -c 'until docker compose -f ../docker-compose.resolved.yml exec -T db pg_isready -U postgres 2>/dev/null; do sleep 2; done'
+          echo "Waiting for auth service to be ready..."
+          timeout 60 sh -c 'until docker compose -f ../docker-compose.resolved.yml exec -T db psql -U postgres -d postgres -c "SELECT 1 FROM auth.users LIMIT 1" 2>/dev/null; do sleep 2; done' || echo "Auth schema check timeout, continuing..."
+
+      - name: Set up Platform - Run migrations
+        run: |
+          echo "Running migrations..."
+          docker compose -f ../docker-compose.resolved.yml run --rm migrate
+          echo "✅ Migrations completed"
         env:
-          DOCKER_BUILDKIT: 1
-          BUILDX_CACHE_FROM: type=local,src=/tmp/.buildx-cache
-          BUILDX_CACHE_TO: type=local,dest=/tmp/.buildx-cache-new,mode=max
+          NEXT_PUBLIC_PW_TEST: true
 
-      - name: Move cache
+      - name: Set up tests - Load cached E2E test data
+        if: steps.e2e-data-cache.outputs.cache-hit == 'true'
         run: |
-          rm -rf /tmp/.buildx-cache
-          if [ -d "/tmp/.buildx-cache-new" ]; then
-            mv /tmp/.buildx-cache-new /tmp/.buildx-cache
-          fi
+          echo "✅ Found cached E2E test data, restoring..."
+          {
+            echo "SET session_replication_role = 'replica';"
+            cat /tmp/e2e_test_data.sql
+            echo "SET session_replication_role = 'origin';"
+          } | docker compose -f ../docker-compose.resolved.yml exec -T db psql -U postgres -d postgres -b
+          # Refresh materialized views after restore
+          docker compose -f ../docker-compose.resolved.yml exec -T db \
+            psql -U postgres -d postgres -b -c "SET search_path TO platform; SELECT refresh_store_materialized_views();" || true
 
-      - name: Wait for services to be ready
+          echo "✅ E2E test data restored from cache"
+
+      - name: Set up Platform - Start (all other services)
         run: |
+          docker compose -f ../docker-compose.resolved.yml up -d --no-build
           echo "Waiting for rest_server to be ready..."
           timeout 60 sh -c 'until curl -f http://localhost:8006/health 2>/dev/null; do sleep 2; done' || echo "Rest server health check timeout, continuing..."
-          echo "Waiting for database to be ready..."
-          timeout 60 sh -c 'until docker compose -f ../docker-compose.yml exec -T db pg_isready -U postgres 2>/dev/null; do sleep 2; done' || echo "Database ready check timeout, continuing..."
+        env:
+          NEXT_PUBLIC_PW_TEST: true
 
-      - name: Create E2E test data
+      - name: Set up tests - Create E2E test data
+        if: steps.e2e-data-cache.outputs.cache-hit != 'true'
         run: |
           echo "Creating E2E test data..."
-          # First try to run the script from inside the container
-          if docker compose -f ../docker-compose.yml exec -T rest_server test -f /app/autogpt_platform/backend/test/e2e_test_data.py; then
-            echo "✅ Found e2e_test_data.py in container, running it..."
-            docker compose -f ../docker-compose.yml exec -T rest_server sh -c "cd /app/autogpt_platform && python backend/test/e2e_test_data.py" || {
-              echo "❌ E2E test data creation failed!"
-              docker compose -f ../docker-compose.yml logs --tail=50 rest_server
-              exit 1
-            }
-          else
-            echo "⚠️ e2e_test_data.py not found in container, copying and running..."
-            # Copy the script into the container and run it
-            docker cp ../backend/test/e2e_test_data.py $(docker compose -f ../docker-compose.yml ps -q rest_server):/tmp/e2e_test_data.py || {
-              echo "❌ Failed to copy script to container"
-              exit 1
-            }
-            docker compose -f ../docker-compose.yml exec -T rest_server sh -c "cd /app/autogpt_platform && python /tmp/e2e_test_data.py" || {
-              echo "❌ E2E test data creation failed!"
-              docker compose -f ../docker-compose.yml logs --tail=50 rest_server
-              exit 1
-            }
-          fi
+          docker cp ../backend/test/e2e_test_data.py $(docker compose -f ../docker-compose.resolved.yml ps -q rest_server):/tmp/e2e_test_data.py
+          docker compose -f ../docker-compose.resolved.yml exec -T rest_server sh -c "cd /app/autogpt_platform && python /tmp/e2e_test_data.py" || {
+            echo "❌ E2E test data creation failed!"
+            docker compose -f ../docker-compose.resolved.yml logs --tail=50 rest_server
+            exit 1
+          }
 
-      - name: Restore dependencies cache
-        uses: actions/cache@v5
+          # Dump auth.users + platform schema for cache (two separate dumps)
+          echo "Dumping database for cache..."
+          {
+            docker compose -f ../docker-compose.resolved.yml exec -T db \
+              pg_dump -U postgres --data-only --column-inserts \
+              --table='auth.users' postgres
+            docker compose -f ../docker-compose.resolved.yml exec -T db \
+              pg_dump -U postgres --data-only --column-inserts \
+              --schema=platform \
+              --exclude-table='platform._prisma_migrations' \
+              --exclude-table='platform.apscheduler_jobs' \
+              --exclude-table='platform.apscheduler_jobs_batched_notifications' \
+              postgres
+          } > /tmp/e2e_test_data.sql
+
+          echo "✅ Database dump created for caching ($(wc -l < /tmp/e2e_test_data.sql) lines)"
+
+      - name: Set up tests - Enable corepack
+        run: corepack enable
+
+      - name: Set up tests - Set up Node
+        uses: actions/setup-node@v6
         with:
-          path: ~/.pnpm-store
-          key: ${{ needs.setup.outputs.cache-key }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
-      - name: Install dependencies
+      - name: Set up tests - Install dependencies
         run: pnpm install --frozen-lockfile
 
-      - name: Install Browser 'chromium'
+      - name: Set up tests - Install browser 'chromium'
         run: pnpm playwright install --with-deps chromium
 
       - name: Run Playwright tests
@@ -269,7 +281,7 @@ jobs:
 
       - name: Print Final Docker Compose logs
         if: always()
-        run: docker compose -f ../docker-compose.yml logs
+        run: docker compose -f ../docker-compose.resolved.yml logs
 
   integration_test:
     runs-on: ubuntu-latest
@@ -281,22 +293,15 @@ jobs:
         with:
           submodules: recursive
 
-      - name: Set up Node.js
-        uses: actions/setup-node@v6
-        with:
-          node-version: "22.18.0"
-
       - name: Enable corepack
         run: corepack enable
 
-      - name: Restore dependencies cache
-        uses: actions/cache@v5
+      - name: Set up Node
+        uses: actions/setup-node@v6
         with:
-          path: ~/.pnpm-store
-          key: ${{ needs.setup.outputs.cache-key }}
-          restore-keys: |
-            ${{ runner.os }}-pnpm-${{ hashFiles('autogpt_platform/frontend/pnpm-lock.yaml') }}
-            ${{ runner.os }}-pnpm-
+          node-version: "22.18.0"
+          cache: "pnpm"
+          cache-dependency-path: autogpt_platform/frontend/pnpm-lock.yaml
 
       - name: Install dependencies
         run: pnpm install --frozen-lockfile

.github/workflows/scripts/docker-ci-fix-compose-build-cache.py

@@ -0,0 +1,195 @@
+#!/usr/bin/env python3
+"""
+Add cache configuration to a resolved docker-compose file for all services
+that have a build key, and ensure image names match what docker compose expects.
+"""
+
+import argparse
+
+import yaml
+
+
+DEFAULT_BRANCH = "dev"
+CACHE_BUILDS_FOR_COMPONENTS = ["backend", "frontend"]
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Add cache config to a resolved compose file"
+    )
+    parser.add_argument(
+        "--source",
+        required=True,
+        help="Source compose file to read (should be output of `docker compose config`)",
+    )
+    parser.add_argument(
+        "--cache-from",
+        default="type=gha",
+        help="Cache source configuration",
+    )
+    parser.add_argument(
+        "--cache-to",
+        default="type=gha,mode=max",
+        help="Cache destination configuration",
+    )
+    for component in CACHE_BUILDS_FOR_COMPONENTS:
+        parser.add_argument(
+            f"--{component}-hash",
+            default="",
+            help=f"Hash for {component} cache scope (e.g., from hashFiles())",
+        )
+    parser.add_argument(
+        "--git-ref",
+        default="",
+        help="Git ref for branch-based cache scope (e.g., refs/heads/master)",
+    )
+    args = parser.parse_args()
+
+    # Normalize git ref to a safe scope name (e.g., refs/heads/master -> master)
+    git_ref_scope = ""
+    if args.git_ref:
+        git_ref_scope = args.git_ref.replace("refs/heads/", "").replace("/", "-")
+
+    with open(args.source, "r") as f:
+        compose = yaml.safe_load(f)
+
+    # Get project name from compose file or default
+    project_name = compose.get("name", "autogpt_platform")
+
+    def get_image_name(dockerfile: str, target: str) -> str:
+        """Generate image name based on Dockerfile folder and build target."""
+        dockerfile_parts = dockerfile.replace("\\", "/").split("/")
+        if len(dockerfile_parts) >= 2:
+            folder_name = dockerfile_parts[-2]  # e.g., "backend" or "frontend"
+        else:
+            folder_name = "app"
+        return f"{project_name}-{folder_name}:{target}"
+
+    def get_build_key(dockerfile: str, target: str) -> str:
+        """Generate a unique key for a Dockerfile+target combination."""
+        return f"{dockerfile}:{target}"
+
+    def get_component(dockerfile: str) -> str | None:
+        """Get component name (frontend/backend) from dockerfile path."""
+        for component in CACHE_BUILDS_FOR_COMPONENTS:
+            if component in dockerfile:
+                return component
+        return None
+
+    # First pass: collect all services with build configs and identify duplicates
+    # Track which (dockerfile, target) combinations we've seen
+    build_key_to_first_service: dict[str, str] = {}
+    services_to_build: list[str] = []
+    services_to_dedupe: list[str] = []
+
+    for service_name, service_config in compose.get("services", {}).items():
+        if "build" not in service_config:
+            continue
+
+        build_config = service_config["build"]
+        dockerfile = build_config.get("dockerfile", "Dockerfile")
+        target = build_config.get("target", "default")
+        build_key = get_build_key(dockerfile, target)
+
+        if build_key not in build_key_to_first_service:
+            # First service with this build config - it will do the actual build
+            build_key_to_first_service[build_key] = service_name
+            services_to_build.append(service_name)
+        else:
+            # Duplicate - will just use the image from the first service
+            services_to_dedupe.append(service_name)
+
+    # Second pass: configure builds and deduplicate
+    modified_services = []
+    for service_name, service_config in compose.get("services", {}).items():
+        if "build" not in service_config:
+            continue
+
+        build_config = service_config["build"]
+        dockerfile = build_config.get("dockerfile", "Dockerfile")
+        target = build_config.get("target", "latest")
+        image_name = get_image_name(dockerfile, target)
+
+        # Set image name for all services (needed for both builders and deduped)
+        service_config["image"] = image_name
+
+        if service_name in services_to_dedupe:
+            # Remove build config - this service will use the pre-built image
+            del service_config["build"]
+            continue
+
+        # This service will do the actual build - add cache config
+        cache_from_list = []
+        cache_to_list = []
+
+        component = get_component(dockerfile)
+        if not component:
+            # Skip services that don't clearly match frontend/backend
+            continue
+
+        # Get the hash for this component
+        component_hash = getattr(args, f"{component}_hash")
+
+        # Scope format: platform-{component}-{target}-{hash|ref}
+        # Example: platform-backend-server-abc123
+
+        if "type=gha" in args.cache_from:
+            # 1. Primary: exact hash match (most specific)
+            if component_hash:
+                hash_scope = f"platform-{component}-{target}-{component_hash}"
+                cache_from_list.append(f"{args.cache_from},scope={hash_scope}")
+
+            # 2. Fallback: branch-based cache
+            if git_ref_scope:
+                ref_scope = f"platform-{component}-{target}-{git_ref_scope}"
+                cache_from_list.append(f"{args.cache_from},scope={ref_scope}")
+
+            # 3. Fallback: dev branch cache (for PRs/feature branches)
+            if git_ref_scope and git_ref_scope != DEFAULT_BRANCH:
+                master_scope = f"platform-{component}-{target}-{DEFAULT_BRANCH}"
+                cache_from_list.append(f"{args.cache_from},scope={master_scope}")
+
+        if "type=gha" in args.cache_to:
+            # Write to both hash-based and branch-based scopes
+            if component_hash:
+                hash_scope = f"platform-{component}-{target}-{component_hash}"
+                cache_to_list.append(f"{args.cache_to},scope={hash_scope}")
+
+            if git_ref_scope:
+                ref_scope = f"platform-{component}-{target}-{git_ref_scope}"
+                cache_to_list.append(f"{args.cache_to},scope={ref_scope}")
+
+        # Ensure we have at least one cache source/target
+        if not cache_from_list:
+            cache_from_list.append(args.cache_from)
+        if not cache_to_list:
+            cache_to_list.append(args.cache_to)
+
+        build_config["cache_from"] = cache_from_list
+        build_config["cache_to"] = cache_to_list
+        modified_services.append(service_name)
+
+    # Write back to the same file
+    with open(args.source, "w") as f:
+        yaml.dump(compose, f, default_flow_style=False, sort_keys=False)
+
+    print(f"Added cache config to {len(modified_services)} services in {args.source}:")
+    for svc in modified_services:
+        svc_config = compose["services"][svc]
+        build_cfg = svc_config.get("build", {})
+        cache_from_list = build_cfg.get("cache_from", ["none"])
+        cache_to_list = build_cfg.get("cache_to", ["none"])
+        print(f"  - {svc}")
+        print(f"      image: {svc_config.get('image', 'N/A')}")
+        print(f"      cache_from: {cache_from_list}")
+        print(f"      cache_to: {cache_to_list}")
+    if services_to_dedupe:
+        print(
+            f"Deduplicated {len(services_to_dedupe)} services (will use pre-built images):"
+        )
+        for svc in services_to_dedupe:
+            print(f"  - {svc} -> {compose['services'][svc].get('image', 'N/A')}")
+
+
+if __name__ == "__main__":
+    main()