PaperClipAI/.github/workflows/runner-full-stack-e2e.yml

name: Runner Full-Stack E2E

on:
  schedule:
    - cron: "47 8 * * 0"
  workflow_dispatch:
    inputs:
      target_branch:
        description: "Branch in paperclipai/paperclip to test; the trusted workflow still runs from master"
        type: string
        required: false
      all:
        description: "Run the complete paid matrix when no narrower selector is supplied"
        type: boolean
        default: true
      group:
        description: "Comma-separated groups (AND semantics: legacy,native,local,daytona,warm,core,breadth)"
        type: string
        required: false
      suite:
        description: "Comma-separated suite IDs"
        type: string
        required: false
      profile:
        description: "Comma-separated runner profile fixture IDs"
        type: string
        required: false
      environment:
        description: "Comma-separated environment fixture IDs"
        type: string
        required: false
      case:
        description: "Comma-separated task case fixture IDs"
        type: string
        required: false
      id:
        description: "Comma-separated full suite.profile.environment.case IDs; exclusive with other selectors"
        type: string
        required: false

permissions:
  contents: read

concurrency:
  group: runner-full-stack-e2e-${{ github.event_name == 'workflow_dispatch' && inputs.target_branch != '' && inputs.target_branch != github.event.repository.default_branch && format('development-{0}', inputs.target_branch) || format('protected-{0}', github.run_id) }}
  # Development branch campaigns supersede older runs for the same target.
  # Give protected/default-branch campaigns unique groups because GitHub also
  # replaces pending runs when cancel-in-progress is false.
  cancel-in-progress: ${{ github.event_name == 'workflow_dispatch' && inputs.target_branch != '' && inputs.target_branch != github.event.repository.default_branch }}

jobs:
  authorize:
    name: Authorize paid campaign
    if: github.event_name != 'schedule' || vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 5
    permissions:
      contents: read
    outputs:
      test_runner: ${{ steps.runner.outputs.runner }}
      max_parallel_default: ${{ steps.runner.outputs.max_parallel_default }}
      max_parallel_limit: ${{ steps.runner.outputs.max_parallel_limit }}
      playwright_channel: ${{ steps.runner.outputs.playwright_channel }}
      target_sha: ${{ steps.target.outputs.sha }}
      target_ref: ${{ steps.target.outputs.ref }}
    steps:
      - name: Require default branch and allowlisted numeric actor IDs
        env:
          GH_TOKEN: ${{ github.token }}
          REPOSITORY: ${{ github.repository }}
          REF: ${{ github.ref }}
          DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
          ACTOR: ${{ github.actor }}
          ACTOR_ID: ${{ github.actor_id }}
          TRIGGERING_ACTOR: ${{ github.triggering_actor }}
          ALLOWED_ACTOR_IDS: ${{ vars.RUNNER_E2E_ALLOWED_ACTOR_IDS }}
        run: |
          set -euo pipefail
          if [ "$REF" != "refs/heads/$DEFAULT_BRANCH" ]; then
            echo "Paid runner E2E campaigns may run only from the default branch." >&2
            exit 1
          fi
          if ! jq -e 'type == "array" and length > 0 and all(.[]; type == "number" and . > 0 and floor == .)' <<< "${ALLOWED_ACTOR_IDS:-}" >/dev/null; then
            echo "RUNNER_E2E_ALLOWED_ACTOR_IDS must be a non-empty JSON array of numeric GitHub user IDs." >&2
            exit 1
          fi
          # Retry transient transport/server failures, but never proceed without
          # a successfully resolved identity and the allowlist checks below.
          for attempt in 1 2 3; do
            if triggering_actor_id="$(timeout 30s gh api "users/$TRIGGERING_ACTOR" --jq .id)"; then
              break
            fi
            if [ "$attempt" = 3 ]; then exit 1; fi
            sleep "$((attempt * 2))"
          done
          if [ "$triggering_actor_id" != "$ACTOR_ID" ] && [ "$TRIGGERING_ACTOR" = "$ACTOR" ]; then
            echo "GitHub actor identity contexts disagree; refusing the paid run." >&2
            exit 1
          fi
          candidates=("$triggering_actor_id" "$ACTOR_ID")
          for candidate in "${candidates[@]}"; do
            if ! jq -e --argjson candidate "$candidate" 'index($candidate) != null' <<< "$ALLOWED_ACTOR_IDS" >/dev/null; then
              echo "The initiating GitHub account is not authorized to run paid runner E2E campaigns." >&2
              exit 1
            fi
          done

      - name: Resolve requested repository branch to an immutable commit
        id: target
        env:
          GH_TOKEN: ${{ github.token }}
          REPOSITORY: ${{ github.repository }}
          TARGET_BRANCH: ${{ inputs.target_branch || github.event.repository.default_branch }}
        run: |
          set -euo pipefail
          if [ -z "$TARGET_BRANCH" ] || [[ "$TARGET_BRANCH" == refs/* ]]; then
            echo "target_branch must name a branch in this repository without a refs/ prefix." >&2
            exit 1
          fi
          encoded_branch="$(jq -rn --arg branch "$TARGET_BRANCH" '$branch | @uri')"
          target_sha="$(gh api -X GET "repos/$REPOSITORY/branches/$encoded_branch" --jq .commit.sha)"
          if ! [[ "$target_sha" =~ ^[0-9a-f]{40}$ ]]; then
            echo "The requested repository branch did not resolve to a commit." >&2
            exit 1
          fi
          echo "sha=$target_sha" >> "$GITHUB_OUTPUT"
          echo "ref=refs/heads/$TARGET_BRANCH" >> "$GITHUB_OUTPUT"
          echo "Resolved the requested repository branch to $target_sha."

      - name: Select paid test runner
        id: runner
        env:
          AWS_PAID_RUNNER_ENABLED: ${{ vars.RUNNER_E2E_AWS_ENABLED }}
        run: |
          set -euo pipefail
          github_runner='ubuntu-latest'
          aws_runner='runs-on/fleet=paperclip-public-pr-x64/env=public-ci'

          if [ "$AWS_PAID_RUNNER_ENABLED" = true ]; then
            {
              echo "runner=$aws_runner"
              echo "max_parallel_default=100"
              echo "max_parallel_limit=100"
              echo "playwright_channel=chrome"
            } >> "$GITHUB_OUTPUT"
            echo '::notice title=Paid runner routing::Using an ephemeral RunsOn Fleet runner'
          else
            {
              echo "runner=$github_runner"
              echo "max_parallel_default=32"
              echo "max_parallel_limit=57"
              echo "playwright_channel="
            } >> "$GITHUB_OUTPUT"
            echo '::notice title=Paid runner routing::RUNNER_E2E_AWS_ENABLED is not true; using the proven GitHub-hosted runner'
          fi

  target_lock:
    name: Resolve target pnpm lockfile
    needs: authorize
    runs-on: ubuntu-latest
    timeout-minutes: 10
    permissions:
      contents: read
    outputs:
      artifact_id: ${{ steps.upload.outputs.artifact-id }}
      lock_sha256: ${{ steps.lock.outputs.sha256 }}
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          ref: ${{ needs.authorize.outputs.target_sha }}
          persist-credentials: false

      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24

      - uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
        env:
          NPM_CONFIG_AUDIT: "false"
          NPM_CONFIG_FUND: "false"
          NPM_CONFIG_UPDATE_NOTIFIER: "false"
        with:
          version: 9.15.4

      - name: Resolve target lockfile without lifecycle scripts
        id: lock
        run: |
          set -euo pipefail
          pnpm install --ignore-scripts --no-frozen-lockfile --lockfile-only
          test -s pnpm-lock.yaml
          unexpected="$(git status --short | awk '$2 != "pnpm-lock.yaml" { print }')"
          if [ -n "$unexpected" ]; then
            echo "Lockfile resolution changed files other than pnpm-lock.yaml:" >&2
            echo "$unexpected" >&2
            exit 1
          fi
          echo "sha256=$(sha256sum pnpm-lock.yaml | cut -d ' ' -f 1)" >> "$GITHUB_OUTPUT"

      - name: Upload resolved target lockfile
        id: upload
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: runner-e2e-target-pnpm-lock-${{ github.run_id }}-${{ github.run_attempt }}
          path: pnpm-lock.yaml
          retention-days: 30
          if-no-files-found: error

  catalog:
    name: Validate catalog and select cells
    needs: [authorize, target_lock]
    if: github.event_name != 'schedule' || vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 10
    permissions:
      contents: read
    outputs:
      matrix: ${{ steps.catalog.outputs.matrix }}
      needs_daytona: ${{ steps.catalog.outputs.needs_daytona }}
      needs_runner_typescript: ${{ steps.catalog.outputs.needs_runner_typescript }}
      needs_native_binaries: ${{ steps.catalog.outputs.needs_native_binaries }}
      needs_remote_provider_pack: ${{ steps.catalog.outputs.needs_remote_provider_pack }}
      execution_ids: ${{ steps.catalog.outputs.execution_ids }}
      max_parallel: ${{ steps.catalog.outputs.max_parallel }}
      daytona_image_content_id: ${{ steps.daytona_image_content.outputs.content_id }}
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          ref: ${{ needs.authorize.outputs.target_sha }}
          persist-credentials: false

      - name: Download resolved target lockfile
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          artifact-ids: ${{ needs.target_lock.outputs.artifact_id }}
          path: ${{ runner.temp }}/runner-e2e-target-lock

      - name: Restore resolved target lockfile
        env:
          TARGET_SHA: ${{ needs.authorize.outputs.target_sha }}
          EXPECTED_LOCK_SHA256: ${{ needs.target_lock.outputs.lock_sha256 }}
        run: |
          set -euo pipefail
          test "$(git rev-parse HEAD)" = "$TARGET_SHA"
          lock="$RUNNER_TEMP/runner-e2e-target-lock/pnpm-lock.yaml"
          test -f "$lock"
          test "$(find "$(dirname "$lock")" -type f | wc -l | tr -d ' ')" = 1
          test "$(sha256sum "$lock" | cut -d ' ' -f 1)" = "$EXPECTED_LOCK_SHA256"
          cp "$lock" pnpm-lock.yaml
          test "$(sha256sum pnpm-lock.yaml | cut -d ' ' -f 1)" = "$EXPECTED_LOCK_SHA256"

      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24

      - uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
        env:
          NPM_CONFIG_AUDIT: "false"
          NPM_CONFIG_FUND: "false"
          NPM_CONFIG_UPDATE_NOTIFIER: "false"
        with:
          version: 9.15.4

      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24
          cache: pnpm

      - run: pnpm install --frozen-lockfile

      # The v2 contract fails closed unless every Docker FROM is digest-pinned,
      # and hashes those exact base references into the immutable image tag.
      - name: Compute Daytona image content ID with pinned bases
        id: daytona_image_content
        run: echo "content_id=$(pnpm --silent test:e2e:runner:image-id)" >> "$GITHUB_OUTPUT"

      - name: Validate selectors and emit matrix
        id: catalog
        env:
          EVENT_NAME: ${{ github.event_name }}
          SELECT_ALL: ${{ inputs.all }}
          SELECT_SUITE: ${{ inputs.suite }}
          SELECT_GROUP: ${{ inputs.group }}
          SELECT_PROFILE: ${{ inputs.profile }}
          SELECT_ENVIRONMENT: ${{ inputs.environment }}
          SELECT_CASE: ${{ inputs.case }}
          SELECT_ID: ${{ inputs.id }}
          MAX_PARALLEL: ${{ vars.RUNNER_E2E_MAX_PARALLEL || needs.authorize.outputs.max_parallel_default }}
          MAX_PARALLEL_LIMIT: ${{ needs.authorize.outputs.max_parallel_limit }}
        run: |
          set -euo pipefail
          args=(--matrix-json)
          add_values() {
            local flag="$1"
            local values="$2"
            local value
            IFS=',' read -ra entries <<< "$values"
            for value in "${entries[@]}"; do
              value="${value#"${value%%[![:space:]]*}"}"
              value="${value%"${value##*[![:space:]]}"}"
              if [ -n "$value" ]; then
                args+=("$flag" "$value")
              fi
            done
          }
          explicit=false
          if [ -n "${SELECT_ID:-}" ]; then
            if [ -n "${SELECT_SUITE:-}${SELECT_GROUP:-}${SELECT_PROFILE:-}${SELECT_ENVIRONMENT:-}${SELECT_CASE:-}" ]; then
              echo "The id selector is exclusive with suite/group/profile/environment/case" >&2
              exit 1
            fi
            add_values --id "$SELECT_ID"
            explicit=true
          else
            for pair in \
              "--suite:${SELECT_SUITE:-}" \
              "--group:${SELECT_GROUP:-}" \
              "--profile:${SELECT_PROFILE:-}" \
              "--environment:${SELECT_ENVIRONMENT:-}" \
              "--case:${SELECT_CASE:-}"
            do
              flag="${pair%%:*}"
              values="${pair#*:}"
              if [ -n "$values" ]; then
                add_values "$flag" "$values"
                explicit=true
              fi
            done
          fi
          if [ "$explicit" = false ] && { [ "$EVENT_NAME" = schedule ] || [ "${SELECT_ALL:-false}" = true ]; }; then
            args+=(--all)
          fi
          catalog_json="$(pnpm --silent test:e2e:runner -- "${args[@]}")"
          {
            echo "matrix=$(jq -c '{include: .include}' <<< "$catalog_json")"
            echo "needs_daytona=$(jq -r '.needsDaytona' <<< "$catalog_json")"
            echo "needs_runner_typescript=$(jq -r '[.include[] | select((.profileId == "runner-opencode") or (.profileId | startswith("runner-acpx-")) or (.suiteId == "openrouter-model-breadth"))] | length > 0' <<< "$catalog_json")"
            echo "needs_native_binaries=$(jq -r '[.include[] | select((.profileId | startswith("runner-")) or (.suiteId == "openrouter-model-breadth"))] | length > 0' <<< "$catalog_json")"
            echo "needs_remote_provider_pack=$(jq -r '[.include[] | select((.environmentId == "daytona") and ((.profileId == "runner-opencode") or (.profileId | startswith("runner-acpx-"))))] | length > 0' <<< "$catalog_json")"
            echo "execution_ids=$(jq -c '.executionIds' <<< "$catalog_json")"
          } >> "$GITHUB_OUTPUT"
          if ! [[ "$MAX_PARALLEL_LIMIT" =~ ^[1-9][0-9]*$ ]] || [ "$MAX_PARALLEL_LIMIT" -gt 100 ]; then
            echo "Runner selection emitted an invalid max-parallel limit." >&2
            exit 1
          fi
          if ! [[ "$MAX_PARALLEL" =~ ^[1-9][0-9]*$ ]] || [ "$MAX_PARALLEL" -gt "$MAX_PARALLEL_LIMIT" ]; then
            echo "RUNNER_E2E_MAX_PARALLEL must be an integer from 1 through $MAX_PARALLEL_LIMIT for the selected runner." >&2
            exit 1
          fi
          echo "max_parallel=$MAX_PARALLEL" >> "$GITHUB_OUTPUT"

  daytona_image:
    name: Publish verified Daytona image
    needs: [authorize, target_lock, catalog]
    runs-on: ubuntu-latest
    timeout-minutes: 45
    permissions:
      contents: read
      packages: write
      id-token: write
    outputs:
      image: ${{ steps.image.outputs.image }}
      source_revision: ${{ steps.image.outputs.source_revision }}
      content_id: ${{ steps.image.outputs.content_id }}
    steps:
      - if: needs.catalog.outputs.needs_daytona == 'true'
        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          ref: ${{ needs.authorize.outputs.target_sha }}
          persist-credentials: false

      - name: Download resolved target lockfile
        if: needs.catalog.outputs.needs_daytona == 'true'
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          artifact-ids: ${{ needs.target_lock.outputs.artifact_id }}
          path: ${{ runner.temp }}/runner-e2e-target-lock

      - name: Restore resolved target lockfile
        if: needs.catalog.outputs.needs_daytona == 'true'
        env:
          TARGET_SHA: ${{ needs.authorize.outputs.target_sha }}
          EXPECTED_LOCK_SHA256: ${{ needs.target_lock.outputs.lock_sha256 }}
        run: |
          set -euo pipefail
          test "$(git rev-parse HEAD)" = "$TARGET_SHA"
          lock="$RUNNER_TEMP/runner-e2e-target-lock/pnpm-lock.yaml"
          test -f "$lock"
          test "$(find "$(dirname "$lock")" -type f | wc -l | tr -d ' ')" = 1
          test "$(sha256sum "$lock" | cut -d ' ' -f 1)" = "$EXPECTED_LOCK_SHA256"
          cp "$lock" pnpm-lock.yaml
          test "$(sha256sum pnpm-lock.yaml | cut -d ' ' -f 1)" = "$EXPECTED_LOCK_SHA256"

      - name: No Daytona image needed
        id: local_only
        if: needs.catalog.outputs.needs_daytona != 'true'
        run: echo "image=" >> "$GITHUB_OUTPUT"

      - name: Set up Docker Buildx
        if: needs.catalog.outputs.needs_daytona == 'true'
        uses: docker/setup-buildx-action@37fe631027851001ddb9b187196cc803df7f5f0e # v4

      - name: Log into GHCR
        if: needs.catalog.outputs.needs_daytona == 'true'
        uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4
        with:
          registry: ghcr.io
          username: ${{ github.actor }}
          password: ${{ secrets.GITHUB_TOKEN }}

      - name: Install cosign
        if: needs.catalog.outputs.needs_daytona == 'true'
        uses: sigstore/cosign-installer@398d4b0eeef1380460a10c8013a76f728fb906ac # v3

      - name: Reuse or publish immutable image
        id: image
        env:
          NEEDS_DAYTONA: ${{ needs.catalog.outputs.needs_daytona }}
          IMAGE_CONTENT_ID: ${{ needs.catalog.outputs.daytona_image_content_id }}
          IMAGE_TAG: ghcr.io/paperclipai/paperclip-daytona-runner:e2e-content-${{ needs.catalog.outputs.daytona_image_content_id }}
          IMAGE_CACHE: ghcr.io/paperclipai/paperclip-daytona-runner:e2e-buildcache-amd64
          TARGET_SHA: ${{ needs.authorize.outputs.target_sha }}
          TARGET_REF: ${{ needs.authorize.outputs.target_ref }}
          DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
        run: |
          set -euo pipefail
          if [ "$NEEDS_DAYTONA" != true ]; then
            {
              echo "image="
              echo "source_revision="
              echo "content_id="
            } >> "$GITHUB_OUTPUT"
            exit 0
          fi
          [[ "$IMAGE_CONTENT_ID" =~ ^[0-9a-f]{64}$ ]]
          identity="^https://github.com/${GITHUB_REPOSITORY}/.github/workflows/runner-full-stack-e2e.yml@"
          if docker buildx imagetools inspect "$IMAGE_TAG" >/dev/null 2>&1; then
            digest="$(docker buildx imagetools inspect "$IMAGE_TAG" --format '{{json .Manifest.Digest}}' | tr -d '"')"
          else
            cache_args=(
              --cache-from "type=registry,ref=${IMAGE_CACHE}"
            )
            if [ "$TARGET_REF" = "refs/heads/$DEFAULT_BRANCH" ]; then
              cache_args+=(
                --cache-to "type=registry,ref=${IMAGE_CACHE},mode=max"
              )
              echo '::notice title=Daytona image cache::Publishing cache from the trusted default-branch target'
            else
              echo '::notice title=Daytona image cache::Using the default-branch cache without publishing development-branch layers'
            fi
            docker buildx build \
              --platform linux/amd64 \
              --build-arg "PAPERCLIP_RUNNER_CONTENT_ID=${IMAGE_CONTENT_ID}" \
              --build-arg "PAPERCLIP_RUNNER_SOURCE_REVISION=${TARGET_SHA}" \
              --file docker/daytona-runner/Dockerfile \
              --tag "$IMAGE_TAG" \
              "${cache_args[@]}" \
              --push \
              .
            digest="$(docker buildx imagetools inspect "$IMAGE_TAG" --format '{{json .Manifest.Digest}}' | tr -d '"')"
            cosign sign --yes "$IMAGE_TAG@$digest"
          fi
          cosign verify \
            --certificate-identity-regexp "$identity" \
            --certificate-oidc-issuer https://token.actions.githubusercontent.com \
            "$IMAGE_TAG@$digest" >/dev/null
          immutable="${IMAGE_TAG%:*}@$digest"
          # The Dockerfile's final two RUN steps execute the runner metadata,
          # transport-mode, provider-pack JSON, and pinned ACP binary checks as
          # root and as the unprivileged Daytona user. Buildx reads the signed
          # digest's OCI config directly from GHCR, so verification does not
          # download the image's large filesystem layers. Logging out first
          # preserves the proof that Daytona can retrieve this public image
          # without the workflow's package credentials.
          docker logout ghcr.io >/dev/null
          image_config="$(docker buildx imagetools inspect "$immutable" \
            --format '{{json .Image}}')"
          published_content_id="$(jq -r '.config.Labels["io.paperclip.runner.content-id"] // empty' <<< "$image_config")"
          source_revision="$(jq -r '.config.Labels["org.opencontainers.image.revision"] // empty' <<< "$image_config")"
          test "$published_content_id" = "$IMAGE_CONTENT_ID"
          [[ "$source_revision" =~ ^[0-9a-f]{40}$ ]]
          jq -e \
            '.architecture == "amd64" and
             .os == "linux" and
             .config.User == "daytona" and
             (.config.Env | any(startswith("PAPERCLIP_RUNNER_PROVIDER_PACK_ROOT=")))' \
            <<< "$image_config" >/dev/null
          {
            echo "image=$immutable"
            echo "source_revision=$source_revision"
            echo "content_id=$published_content_id"
          } >> "$GITHUB_OUTPUT"

  build_runner_artifacts:
    name: Build reusable runner campaign artifacts
    needs: [authorize, target_lock, catalog]
    if: github.event_name != 'schedule' || vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true'
    # Compile native binaries on the same reviewed image used to execute them,
    # avoiding libc/architecture drift between GitHub-hosted and AWS lanes.
    runs-on: ${{ needs.authorize.outputs.test_runner }}
    timeout-minutes: 20
    permissions:
      contents: read
    outputs:
      build_artifact_name: ${{ steps.build_artifact_name.outputs.name }}
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          ref: ${{ needs.authorize.outputs.target_sha }}
          persist-credentials: false

      - name: Download resolved target lockfile
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          artifact-ids: ${{ needs.target_lock.outputs.artifact_id }}
          path: ${{ runner.temp }}/runner-e2e-target-lock

      - name: Restore resolved target lockfile
        env:
          TARGET_SHA: ${{ needs.authorize.outputs.target_sha }}
          EXPECTED_LOCK_SHA256: ${{ needs.target_lock.outputs.lock_sha256 }}
        run: |
          set -euo pipefail
          test "$(git rev-parse HEAD)" = "$TARGET_SHA"
          lock="$RUNNER_TEMP/runner-e2e-target-lock/pnpm-lock.yaml"
          test -f "$lock"
          test "$(find "$(dirname "$lock")" -type f | wc -l | tr -d ' ')" = 1
          test "$(sha256sum "$lock" | cut -d ' ' -f 1)" = "$EXPECTED_LOCK_SHA256"
          cp "$lock" pnpm-lock.yaml
          test "$(sha256sum pnpm-lock.yaml | cut -d ' ' -f 1)" = "$EXPECTED_LOCK_SHA256"

      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24

      - uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
        env:
          NPM_CONFIG_AUDIT: "false"
          NPM_CONFIG_FUND: "false"
          NPM_CONFIG_UPDATE_NOTIFIER: "false"
        with:
          version: 9.15.4

      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24
          cache: pnpm

      - run: pnpm install --frozen-lockfile --ignore-scripts

      # build:typescript also builds the eval-kernel dependency, so the two
      # TypeScript trees are compiled at most once in this campaign.
      - name: Build shared TypeScript and native runner outputs
        env:
          NEEDS_RUNNER_TYPESCRIPT: ${{ needs.catalog.outputs.needs_runner_typescript }}
          NEEDS_NATIVE_BINARIES: ${{ needs.catalog.outputs.needs_native_binaries }}
        run: |
          set -euo pipefail
          if [ "$NEEDS_RUNNER_TYPESCRIPT" = true ]; then
            pnpm --filter @paperclipai/paperclip-runner build:typescript
          else
            pnpm --filter @paperclipai/paperclip-eval-kernel build
          fi
          if [ "$NEEDS_NATIVE_BINARIES" = true ]; then
            pnpm --filter @paperclipai/paperclip-runner build:runner-binaries
          fi

      - name: Package immutable campaign outputs
        env:
          NEEDS_RUNNER_TYPESCRIPT: ${{ needs.catalog.outputs.needs_runner_typescript }}
          NEEDS_NATIVE_BINARIES: ${{ needs.catalog.outputs.needs_native_binaries }}
        run: |
          set -euo pipefail
          binary_root="packages/paperclip-runner/runner/target/debug"
          binaries=(
            conformance-tracer
            paperclip-runnerd
            fake-harness
            fake-codex-app-server
            fake-acpx-sidecar
          )
          archive_paths=(
            packages/paperclip-eval-kernel/dist
          )
          if [ "$NEEDS_RUNNER_TYPESCRIPT" = true ]; then
            test -d packages/paperclip-runner/dist
            archive_paths+=(packages/paperclip-runner/dist)
          fi
          if [ "$NEEDS_NATIVE_BINARIES" = true ]; then
            for binary in "${binaries[@]}"; do
              test -x "$binary_root/$binary"
              archive_paths+=("$binary_root/$binary")
            done
          fi
          tar --create --gzip \
            --file runner-e2e-build-bundle.tar.gz \
            "${archive_paths[@]}"
          sha256sum runner-e2e-build-bundle.tar.gz > runner-e2e-build-bundle.tar.gz.sha256

      - name: Name immutable shared campaign outputs
        id: build_artifact_name
        env:
          TARGET_SHA: ${{ needs.authorize.outputs.target_sha }}
        run: echo "name=runner-e2e-build-${TARGET_SHA}-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}" >> "$GITHUB_OUTPUT"

      - name: Upload immutable shared campaign outputs
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: ${{ steps.build_artifact_name.outputs.name }}
          path: |
            runner-e2e-build-bundle.tar.gz
            runner-e2e-build-bundle.tar.gz.sha256
          retention-days: 1
          compression-level: 0
          if-no-files-found: error

  build_remote_provider_pack:
    name: Build reusable remote provider pack
    needs:
      [authorize, target_lock, catalog, daytona_image, build_runner_artifacts]
    if: github.event_name != 'schedule' || vars.RUNNER_FULL_STACK_E2E_NIGHTLY_ENABLED == 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 15
    permissions:
      contents: read
    outputs:
      provider_pack_artifact_name: ${{ steps.provider_pack_artifact_name.outputs.name }}
    steps:
      - name: No remote provider pack needed
        if: needs.catalog.outputs.needs_remote_provider_pack != 'true'
        run: echo "Selected cells do not require a remote provider pack."

      - if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          ref: ${{ needs.authorize.outputs.target_sha }}
          persist-credentials: false

      - name: Download resolved target lockfile
        if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          artifact-ids: ${{ needs.target_lock.outputs.artifact_id }}
          path: ${{ runner.temp }}/runner-e2e-target-lock

      - name: Restore resolved target lockfile
        if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        env:
          TARGET_SHA: ${{ needs.authorize.outputs.target_sha }}
          EXPECTED_LOCK_SHA256: ${{ needs.target_lock.outputs.lock_sha256 }}
        run: |
          set -euo pipefail
          test "$(git rev-parse HEAD)" = "$TARGET_SHA"
          lock="$RUNNER_TEMP/runner-e2e-target-lock/pnpm-lock.yaml"
          test -f "$lock"
          test "$(find "$(dirname "$lock")" -type f | wc -l | tr -d ' ')" = 1
          test "$(sha256sum "$lock" | cut -d ' ' -f 1)" = "$EXPECTED_LOCK_SHA256"
          cp "$lock" pnpm-lock.yaml
          test "$(sha256sum pnpm-lock.yaml | cut -d ' ' -f 1)" = "$EXPECTED_LOCK_SHA256"

      - if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24

      - if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
        env:
          NPM_CONFIG_AUDIT: "false"
          NPM_CONFIG_FUND: "false"
          NPM_CONFIG_UPDATE_NOTIFIER: "false"
        with:
          version: 9.15.4

      - if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24
          cache: pnpm

      - if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        run: pnpm install --frozen-lockfile --ignore-scripts

      - name: Materialize verified pinned OpenCode executable
        if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        run: node packages/paperclip-runner/scripts/materialize-opencode-binary.mjs

      - name: Download immutable shared campaign outputs
        if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          name: ${{ needs.build_runner_artifacts.outputs.build_artifact_name }}
          path: runner-e2e-build

      - name: Verify and restore shared TypeScript outputs
        if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        run: |
          set -euo pipefail
          (
            cd runner-e2e-build
            sha256sum --check runner-e2e-build-bundle.tar.gz.sha256
          )
          tar --extract --gzip \
            --file runner-e2e-build/runner-e2e-build-bundle.tar.gz \
            --directory "$GITHUB_WORKSPACE"
          test -d packages/paperclip-eval-kernel/dist
          test -d packages/paperclip-runner/dist

      - name: Assemble native remote provider pack
        if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        env:
          # A reused image can have an older source revision with the same
          # content ID. Matching that revision lets remote execution reuse the
          # verified pack already installed in the immutable image.
          PAPERCLIP_RUNNER_SOURCE_REVISION: ${{ needs.daytona_image.outputs.source_revision }}
        run: node packages/paperclip-runner/scripts/build-provider-pack.mjs packages/paperclip-runner/provider-pack

      - name: Package verified remote provider pack
        if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        env:
          IMAGE_SOURCE_REVISION: ${{ needs.daytona_image.outputs.source_revision }}
        run: |
          set -euo pipefail
          test -f packages/paperclip-runner/provider-pack/provider-pack.json
          jq -e \
            --arg revision "$IMAGE_SOURCE_REVISION" \
            '.schema == "paperclip-runner/remote-provider-pack/v1" and
             .payload.runnerSourceRevision == $revision and
             (.digest | test("^sha256:[0-9a-f]{64}$"))' \
            packages/paperclip-runner/provider-pack/provider-pack.json >/dev/null
          tar --create --gzip \
            --file runner-e2e-provider-pack.tar.gz \
            packages/paperclip-runner/provider-pack
          sha256sum runner-e2e-provider-pack.tar.gz > runner-e2e-provider-pack.tar.gz.sha256

      - name: Name immutable remote provider pack
        id: provider_pack_artifact_name
        if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        env:
          TARGET_SHA: ${{ needs.authorize.outputs.target_sha }}
        run: echo "name=runner-e2e-provider-pack-${TARGET_SHA}-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}" >> "$GITHUB_OUTPUT"

      - name: Upload immutable remote provider pack
        if: needs.catalog.outputs.needs_remote_provider_pack == 'true'
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: ${{ steps.provider_pack_artifact_name.outputs.name }}
          path: |
            runner-e2e-provider-pack.tar.gz
            runner-e2e-provider-pack.tar.gz.sha256
          retention-days: 1
          compression-level: 0
          if-no-files-found: error

  test:
    name: ${{ matrix.executionId }}
    needs:
      [
        authorize,
        target_lock,
        catalog,
        daytona_image,
        build_runner_artifacts,
        build_remote_provider_pack,
      ]
    # The authorize job selects only one of two literal, reviewed runner labels;
    # no dispatch input or repository variable can inject an arbitrary label.
    runs-on: ${{ needs.authorize.outputs.test_runner }}
    timeout-minutes: ${{ matrix.timeoutMinutes }}
    permissions:
      contents: read
    environment:
      name: runner-e2e-paid
    strategy:
      fail-fast: false
      max-parallel: ${{ fromJSON(needs.catalog.outputs.max_parallel) }}
      matrix: ${{ fromJSON(needs.catalog.outputs.matrix) }}
    steps:
      - name: Reauthorize paid execution before provider access
        env:
          GH_TOKEN: ${{ github.token }}
          REF: ${{ github.ref }}
          DEFAULT_BRANCH: ${{ github.event.repository.default_branch }}
          ACTOR_ID: ${{ github.actor_id }}
          TRIGGERING_ACTOR: ${{ github.triggering_actor }}
          ALLOWED_ACTOR_IDS: ${{ vars.RUNNER_E2E_ALLOWED_ACTOR_IDS }}
        run: |
          set -euo pipefail
          test "$REF" = "refs/heads/$DEFAULT_BRANCH"
          jq -e 'type == "array" and length > 0 and all(.[]; type == "number" and . > 0 and floor == .)' <<< "${ALLOWED_ACTOR_IDS:-}" >/dev/null
          # Retry transient transport/server failures, but never proceed without
          # a successfully resolved identity and the allowlist checks below.
          for attempt in 1 2 3; do
            if triggering_actor_id="$(timeout 30s gh api "users/$TRIGGERING_ACTOR" --jq .id)"; then
              break
            fi
            if [ "$attempt" = 3 ]; then exit 1; fi
            sleep "$((attempt * 2))"
          done
          jq -e --argjson candidate "$triggering_actor_id" 'index($candidate) != null' <<< "$ALLOWED_ACTOR_IDS" >/dev/null
          jq -e --argjson candidate "$ACTOR_ID" 'index($candidate) != null' <<< "$ALLOWED_ACTOR_IDS" >/dev/null

      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          ref: ${{ needs.authorize.outputs.target_sha }}
          persist-credentials: false

      - name: Download resolved target lockfile
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          artifact-ids: ${{ needs.target_lock.outputs.artifact_id }}
          path: ${{ runner.temp }}/runner-e2e-target-lock

      - name: Restore resolved target lockfile
        env:
          TARGET_SHA: ${{ needs.authorize.outputs.target_sha }}
          EXPECTED_LOCK_SHA256: ${{ needs.target_lock.outputs.lock_sha256 }}
        run: |
          set -euo pipefail
          test "$(git rev-parse HEAD)" = "$TARGET_SHA"
          lock="$RUNNER_TEMP/runner-e2e-target-lock/pnpm-lock.yaml"
          test -f "$lock"
          test "$(find "$(dirname "$lock")" -type f | wc -l | tr -d ' ')" = 1
          test "$(sha256sum "$lock" | cut -d ' ' -f 1)" = "$EXPECTED_LOCK_SHA256"
          cp "$lock" pnpm-lock.yaml
          test "$(sha256sum pnpm-lock.yaml | cut -d ' ' -f 1)" = "$EXPECTED_LOCK_SHA256"

      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24

      - uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
        env:
          NPM_CONFIG_AUDIT: "false"
          NPM_CONFIG_FUND: "false"
          NPM_CONFIG_UPDATE_NOTIFIER: "false"
        with:
          version: 9.15.4

      # This job receives provider credentials only in the final paid-test
      # step. Keep target-selected dependency lifecycle code from running in
      # the protected environment during setup.
      - run: pnpm install --frozen-lockfile --ignore-scripts

      # Sandbox-provider plugins are intentionally excluded from the root
      # workspace. The ordinary root postinstall links the in-repo plugin SDK,
      # but that lifecycle hook is deliberately disabled above. Prepare the
      # one host plugin needed by Daytona explicitly, before this job receives
      # provider credentials, and keep dependency lifecycle scripts disabled.
      - name: Prepare bundled Daytona plugin without dependency lifecycle scripts
        if: matrix.environmentId == 'daytona'
        run: |
          set -euo pipefail
          daytona_root="packages/plugins/sandbox-providers/daytona"
          sdk_root="packages/plugins/sdk"
          test -d "$daytona_root"
          test -d "$sdk_root"
          test ! -L "$daytona_root"
          test ! -L "$sdk_root"
          test -f "$daytona_root/pnpm-lock.yaml"
          test "$(jq -r .name "$daytona_root/package.json")" = "@paperclipai/plugin-daytona"
          test "$(jq -r .name "$sdk_root/package.json")" = "@paperclipai/plugin-sdk"
          (
            cd "$daytona_root"
            pnpm install --ignore-workspace --frozen-lockfile --ignore-scripts
          )
          node scripts/link-plugin-dev-sdk.mjs
          test "$(realpath "$daytona_root/node_modules/@paperclipai/plugin-sdk")" = "$(realpath "$sdk_root")"
          pnpm --dir "$daytona_root" build
          test -f "$daytona_root/dist/manifest.js"
          test -f "$daytona_root/dist/worker.js"
          test -e "$daytona_root/node_modules/@daytonaio/sdk"

      - name: Materialize verified pinned OpenCode executable
        if: matrix.environmentId == 'local' && (matrix.profileId == 'legacy-opencode' || matrix.profileId == 'runner-opencode' || matrix.suiteId == 'openrouter-model-breadth')
        run: node packages/paperclip-runner/scripts/materialize-opencode-binary.mjs

      - name: Download immutable campaign outputs
        if: startsWith(matrix.profileId, 'runner-') || matrix.suiteId == 'openrouter-model-breadth'
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          name: ${{ needs.build_runner_artifacts.outputs.build_artifact_name }}
          path: runner-e2e-build

      - name: Download immutable remote provider pack
        if: matrix.environmentId == 'daytona' && (matrix.profileId == 'runner-opencode' || startsWith(matrix.profileId, 'runner-acpx-'))
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          name: ${{ needs.build_remote_provider_pack.outputs.provider_pack_artifact_name }}
          path: runner-e2e-provider-pack

      - name: Verify and restore campaign outputs
        if: startsWith(matrix.profileId, 'runner-') || matrix.suiteId == 'openrouter-model-breadth'
        env:
          NEEDS_RUNNER_TYPESCRIPT: ${{ matrix.profileId == 'runner-opencode' || startsWith(matrix.profileId, 'runner-acpx-') || matrix.suiteId == 'openrouter-model-breadth' }}
          NEEDS_NATIVE_BINARY: ${{ startsWith(matrix.profileId, 'runner-') || matrix.suiteId == 'openrouter-model-breadth' }}
        run: |
          set -euo pipefail
          (
            cd runner-e2e-build
            sha256sum --check runner-e2e-build-bundle.tar.gz.sha256
          )
          tar --extract --gzip \
            --file runner-e2e-build/runner-e2e-build-bundle.tar.gz \
            --directory "$GITHUB_WORKSPACE"
          test -d packages/paperclip-eval-kernel/dist
          if [ "$NEEDS_RUNNER_TYPESCRIPT" = true ]; then
            test -d packages/paperclip-runner/dist
          fi
          if [ "$NEEDS_NATIVE_BINARY" = true ]; then
            test -x packages/paperclip-runner/runner/target/debug/paperclip-runnerd
          fi

      - name: Verify and restore remote provider pack
        if: matrix.environmentId == 'daytona' && (matrix.profileId == 'runner-opencode' || startsWith(matrix.profileId, 'runner-acpx-'))
        env:
          IMAGE_SOURCE_REVISION: ${{ needs.daytona_image.outputs.source_revision }}
        run: |
          set -euo pipefail
          (
            cd runner-e2e-provider-pack
            sha256sum --check runner-e2e-provider-pack.tar.gz.sha256
          )
          tar --extract --gzip \
            --file runner-e2e-provider-pack/runner-e2e-provider-pack.tar.gz \
            --directory "$GITHUB_WORKSPACE"
          jq -e \
            --arg revision "$IMAGE_SOURCE_REVISION" \
            '.schema == "paperclip-runner/remote-provider-pack/v1" and
             .payload.runnerSourceRevision == $revision and
             (.digest | test("^sha256:[0-9a-f]{64}$"))' \
            packages/paperclip-runner/provider-pack/provider-pack.json >/dev/null

      - name: Qualify local provider Node interpreter
        if: matrix.environmentId == 'local' && (matrix.profileId == 'runner-opencode' || startsWith(matrix.profileId, 'runner-acpx-') || matrix.suiteId == 'openrouter-model-breadth')
        run: |
          node <<'NODE'
          const fs = require("node:fs");
          const mode = fs.statSync(process.execPath).mode & 0o777;
          fs.chmodSync(process.execPath, mode & ~0o022);
          if ((fs.statSync(process.execPath).mode & 0o022) !== 0) {
            throw new Error("provider Node interpreter remains group- or world-writable");
          }
          NODE

      - name: Install pinned legacy Claude CLI
        if: matrix.profileId == 'legacy-claude'
        run: |
          npm install --global --omit=dev --ignore-scripts @anthropic-ai/claude-code@2.1.277
          launcher="$(npm root --global)/@anthropic-ai/claude-code/cli-wrapper.cjs"
          chmod +x "$launcher"
          ln -sf "$launcher" "$(npm prefix --global)/bin/claude"
          claude --version

      - name: Qualify preinstalled Chrome
        if: needs.authorize.outputs.playwright_channel == 'chrome'
        run: |
          set -euo pipefail
          chrome_path="$(command -v google-chrome)"
          test -x "$chrome_path"
          google-chrome --version

      - name: Install Playwright FFmpeg on AWS runner
        if: needs.authorize.outputs.playwright_channel == 'chrome'
        run: |
          set -euo pipefail
          for attempt in 1 2 3; do
            if pnpm exec playwright install ffmpeg; then
              exit 0
            fi
            if [ "$attempt" -eq 3 ]; then
              echo "Playwright FFmpeg installation failed after $attempt attempts." >&2
              exit 1
            fi
            sleep "$((attempt * 10))"
          done

      - name: Install Chromium headless shell on GitHub-hosted fallback
        if: needs.authorize.outputs.playwright_channel != 'chrome'
        run: |
          set -euo pipefail
          for attempt in 1 2 3; do
            if pnpm exec playwright install --with-deps --only-shell chromium; then
              exit 0
            fi
            if [ "$attempt" -eq 3 ]; then
              echo "Chromium headless shell installation failed after $attempt attempts." >&2
              exit 1
            fi
            sleep "$((attempt * 10))"
          done

      # This definition executes only from the authorized default-branch workflow.
      # Provision host policy before credentials reach target-controlled tests.
      - name: Provision Codex sandbox on the disposable trusted runner
        if: matrix.environmentId == 'local' && (matrix.profileId == 'runner-codex' || matrix.profileId == 'runner-codex-mini' || matrix.profileId == 'runner-acpx-codex')
        run: |
          node --input-type=module <<'NODE'
          import { execFileSync } from "node:child_process";
          import { createHash } from "node:crypto";
          import { readFileSync, realpathSync, writeFileSync } from "node:fs";
          import { createRequire } from "node:module";
          import path from "node:path";
          if (process.platform !== "linux") process.exit(0);
          let restricted = "0";
          try { restricted = readFileSync("/proc/sys/kernel/apparmor_restrict_unprivileged_userns", "utf8").trim(); } catch {}
          if (restricted !== "1") process.exit(0);
          const root = realpathSync(process.env.GITHUB_WORKSPACE);
          const runnerRequire = createRequire(path.join(root, "packages/paperclip-runner/package.json"));
          const acpRequire = createRequire(runnerRequire.resolve("@agentclientprotocol/codex-acp/package.json"));
          const codexRequire = createRequire(acpRequire.resolve("@openai/codex/package.json"));
          const arch = process.arch === "x64" ? "x64" : process.arch === "arm64" ? "arm64" : null;
          if (!arch) throw new Error("Unsupported Codex CI architecture");
          const platformPackage = codexRequire.resolve(`@openai/codex-linux-${arch}/package.json`);
          const triple = arch === "x64" ? "x86_64-unknown-linux-musl" : "aarch64-unknown-linux-musl";
          const suffix = `/vendor/${triple}/bin/codex`;
          const binary = realpathSync(path.join(path.dirname(platformPackage), suffix));
          if (!binary.startsWith(root + "/node_modules/.pnpm/") || !binary.endsWith(suffix) || !/^[/A-Za-z0-9_.@+\-]+$/.test(binary)) {
            throw new Error("Codex executable is outside the resolved dependency tree");
          }
          const name = `paperclip-e2e-codex-${createHash("sha256").update(binary).digest("hex").slice(0,16)}`;
          const profilePath = path.join(process.env.RUNNER_TEMP, "paperclip-codex-userns.apparmor");
          writeFileSync(profilePath, `abi <abi/4.0>,\ninclude <tunables/global>\nprofile ${name} "${binary}" flags=(unconfined) {\n  userns,\n}\n`, {mode:0o600, flag:"wx"});
          execFileSync("sudo", ["-n", "apparmor_parser", "-r", profilePath], {timeout:15000, stdio:"pipe"});
          NODE

      - name: Prepare pinned Python artifact oracle image
        if: matrix.suiteId == 'everyday-workflows' && (matrix.caseId == 'build-revise' || matrix.caseId == 'delegate-feedback' || matrix.caseId == 'agent-review-handoff' || matrix.caseId == 'hire-reuse' || matrix.caseId == 'recover-controller' || matrix.caseId == 'stop-redirect')
        run: |
          set -euo pipefail
          oracle_image='python@sha256:9d2e5553305c7c7b0097999bb17187c69b921ccd6bc9d40e4bb5ebe652c00285'
          timeout 30s docker version --format '{{.Server.Version}}'
          timeout 120s docker pull "$oracle_image"
          timeout 30s docker image inspect "$oracle_image" --format '{{.Id}}'

      - name: Run paid cell
        env:
          OPENAI_API_KEY: ${{ matrix.credentialName == 'OPENAI_API_KEY' && secrets.OPENAI_API_KEY || '' }}
          ANTHROPIC_API_KEY: ${{ matrix.credentialName == 'ANTHROPIC_API_KEY' && secrets.ANTHROPIC_API_KEY || '' }}
          OPENROUTER_API_KEY: ${{ matrix.credentialName == 'OPENROUTER_API_KEY' && secrets.OPENROUTER_API_KEY || '' }}
          DAYTONA_API_KEY: ${{ matrix.environmentId == 'daytona' && secrets.DAYTONA_API_KEY || '' }}
          PAPERCLIP_E2E_DAYTONA_IMAGE: ${{ needs.daytona_image.outputs.image }}
          PAPERCLIP_RUNNER_REMOTE_PROVIDER_PACK_PATH: ${{ github.workspace }}/packages/paperclip-runner/provider-pack
          PAPERCLIP_E2E_CAMPAIGN_ID: gha-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.executionId }}
          PAPERCLIP_RUNNER_E2E_SOURCE_SHA: ${{ needs.authorize.outputs.target_sha }}
          PAPERCLIP_RUNNER_E2E_SOURCE_REF: ${{ needs.authorize.outputs.target_ref }}
          PAPERCLIP_PLAYWRIGHT_CHANNEL: ${{ needs.authorize.outputs.playwright_channel }}
        run: pnpm test:e2e:runner -- --id "${{ matrix.executionId }}"

      - name: Upload access-controlled packaged cell evidence
        if: always()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: runner-e2e-${{ github.run_id }}-${{ github.run_attempt }}-${{ matrix.executionId }}
          path: tests/runner-e2e/results/
          retention-days: 30
          if-no-files-found: error

  report:
    name: Merge and enforce campaign result
    if: always() && !cancelled() && needs.catalog.result == 'success'
    needs: [authorize, catalog, daytona_image, test]
    outputs:
      history_source_ready: ${{ steps.history_source_ready.outputs.ready }}
    runs-on: ubuntu-latest
    timeout-minutes: 15
    permissions:
      actions: read
      contents: read
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          # Reporting and sanitization are part of the trusted workflow boundary.
          ref: ${{ github.sha }}
          persist-credentials: false

      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24

      - uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
        env:
          NPM_CONFIG_AUDIT: "false"
          NPM_CONFIG_FUND: "false"
          NPM_CONFIG_UPDATE_NOTIFIER: "false"
        with:
          version: 9.15.4

      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24
          cache: pnpm

      # Resolve from this trusted checkout only. Never use the target branch's
      # lockfile or install scripts in the publication job.
      - run: pnpm install --lockfile-only --ignore-scripts --no-frozen-lockfile
      - run: pnpm install --frozen-lockfile

      - name: Resolve workflow job attempts
        env:
          GH_TOKEN: ${{ github.token }}
          REPOSITORY: ${{ github.repository }}
          RUN_ID: ${{ github.run_id }}
        run: |
          set -euo pipefail
          gh api --paginate --slurp \
            "repos/$REPOSITORY/actions/runs/$RUN_ID/jobs?filter=all&per_page=100" \
            > runner-e2e-job-pages.json
          for attempt in $(seq 1 "${{ github.run_attempt }}"); do
            gh api "repos/$REPOSITORY/actions/runs/$RUN_ID/attempts/$attempt" \
              --jq '{run_attempt, run_started_at}'
          done > runner-e2e-attempts.jsonl
          jq -s '.' runner-e2e-attempts.jsonl > runner-e2e-attempts.json
          jq --slurpfile attempts runner-e2e-attempts.json \
            '{jobs: [.[].jobs[]], attempts: $attempts[0]}' \
            runner-e2e-job-pages.json > runner-e2e-jobs.json

      - name: Download cell evidence
        id: download_evidence
        continue-on-error: true
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          pattern: runner-e2e-${{ github.run_id }}-*-*
          path: downloaded-runner-e2e
          merge-multiple: false

      - name: Retry cell evidence download after transport failure
        if: steps.download_evidence.outcome == 'failure'
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          pattern: runner-e2e-${{ github.run_id }}-*-*
          path: downloaded-runner-e2e
          merge-multiple: false

      - name: Select latest workflow attempt per cell
        if: always()
        env:
          PAPERCLIP_RUNNER_E2E_ARTIFACT_ROOT: ${{ github.workspace }}/downloaded-runner-e2e
          PAPERCLIP_RUNNER_E2E_SELECTED_ROOT: ${{ github.workspace }}/selected-runner-e2e
          PAPERCLIP_RUNNER_E2E_JOBS_JSON: ${{ github.workspace }}/runner-e2e-jobs.json
          PAPERCLIP_RUNNER_E2E_EXPECTED_IDS: ${{ needs.catalog.outputs.execution_ids }}
          PAPERCLIP_RUNNER_E2E_SOURCE_SHA: ${{ needs.authorize.outputs.target_sha }}
          PAPERCLIP_RUNNER_E2E_SOURCE_REF: ${{ needs.authorize.outputs.target_ref }}
        run: node cli/node_modules/tsx/dist/cli.mjs tests/runner-e2e/select-rerun-artifacts.ts

      - name: Collect blob reports
        run: |
          set -euo pipefail
          mkdir -p merged-blob-reports
          while IFS= read -r -d '' report; do
            digest="$(sha256sum "$report" | cut -d ' ' -f 1)"
            target="merged-blob-reports/report-${digest}.zip"
            if [ ! -e "$target" ]; then
              cp "$report" "$target"
            fi
          done < <(find selected-runner-e2e -path '*/blob-report/*.zip' -print0)

      - name: Merge Playwright HTML and JUnit
        if: always()
        env:
          PAPERCLIP_RUNNER_E2E_MERGED_REPORT_DIR: ${{ github.workspace }}/runner-e2e-merged-report
        run: pnpm exec playwright merge-reports --config tests/runner-e2e/merge.config.ts merged-blob-reports

      - name: Aggregate normalized campaign results
        if: always()
        env:
          PAPERCLIP_RUNNER_E2E_REPORT_ROOT: ${{ github.workspace }}/selected-runner-e2e
          PAPERCLIP_RUNNER_E2E_REPORT_OUT: ${{ github.workspace }}/runner-e2e-merged-report/normalized
          PAPERCLIP_RUNNER_E2E_EXPECTED_IDS: ${{ needs.catalog.outputs.execution_ids }}
          PAPERCLIP_E2E_CAMPAIGN_ID: gha-${{ github.run_id }}-${{ github.run_attempt }}
          PAPERCLIP_RUNNER_E2E_SOURCE_SHA: ${{ needs.authorize.outputs.target_sha }}
          PAPERCLIP_RUNNER_E2E_SOURCE_REF: ${{ needs.authorize.outputs.target_ref }}
          PAPERCLIP_RUNNER_E2E_HISTORY_PUBLIC_BASE_URL: ${{ vars.RUNNER_E2E_HISTORY_PUBLIC_BASE_URL }}
          PAPERCLIP_RUNNER_E2E_HISTORY_PREFIX: ${{ vars.RUNNER_E2E_HISTORY_PREFIX || 'runner-e2e' }}
        run: |
          set +e
          pnpm test:e2e:runner:report
          report_status=$?
          set -e
          cat runner-e2e-merged-report/normalized/summary.md >> "$GITHUB_STEP_SUMMARY"
          exit "$report_status"

      - name: Upload access-controlled merged report
        if: always()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7
        with:
          name: runner-e2e-report-${{ github.run_id }}-${{ github.run_attempt }}
          path: runner-e2e-merged-report/
          retention-days: 30
          if-no-files-found: error

      - name: Verify normalized history source report
        id: history_source_ready
        if: always()
        run: |
          set -euo pipefail
          dashboard_root="runner-e2e-merged-report/normalized"
          if [ -f "$dashboard_root/index.html" ] && [ -f "$dashboard_root/normalized-results.json" ]; then
            echo "ready=true" >> "$GITHUB_OUTPUT"
          else
            echo "ready=false" >> "$GITHUB_OUTPUT"
          fi

  publish_history:
    name: Publish S3 history and Pages bundle with declared screenshots
    needs: [authorize, catalog, report]
    if: always() && needs.catalog.result == 'success' && needs.report.outputs.history_source_ready == 'true'
    runs-on: ubuntu-latest
    timeout-minutes: 15
    outputs:
      pages_artifact_name: ${{ steps.pages_artifact_name.outputs.name }}
    concurrency:
      group: runner-e2e-history-publish
      cancel-in-progress: false
    permissions:
      contents: read
      id-token: write
    environment:
      name: runner-e2e-history
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7
        with:
          # Never execute target-controlled publication code with AWS credentials.
          ref: ${{ github.sha }}
          persist-credentials: false

      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7
        with:
          node-version: 24

      - uses: pnpm/action-setup@0977fd99725f1db4007ccb2928dbb4e90d06cc86 # v6
        env:
          NPM_CONFIG_AUDIT: "false"
          NPM_CONFIG_FUND: "false"
          NPM_CONFIG_UPDATE_NOTIFIER: "false"
        with:
          version: 9.15.4

      # Resolve the trusted publication checkout's lockfile without lifecycle
      # scripts, then install the exact result. This matches the report job's
      # frozen-install preparation while keeping target-controlled code out of
      # the AWS credentialed publisher.
      - run: pnpm install --lockfile-only --ignore-scripts --no-frozen-lockfile
      - run: pnpm install --frozen-lockfile

      - name: Install publisher-only Chromium
        run: pnpm exec playwright install --with-deps --only-shell chromium

      - name: Download access-controlled normalized campaign
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          name: runner-e2e-report-${{ github.run_id }}-${{ github.run_attempt }}
          path: runner-e2e-merged-report

      - name: Exchange GitHub OIDC identity for scoped AWS credentials
        uses: aws-actions/configure-aws-credentials@e6de054238d6b7531b4efff3b6587d9aade6a06c # v6
        with:
          role-to-assume: ${{ vars.RUNNER_E2E_HISTORY_AWS_ROLE_ARN }}
          aws-region: ${{ vars.RUNNER_E2E_HISTORY_AWS_REGION }}

      - name: Publish trusted summary and declared screenshots to public bundles
        env:
          PAPERCLIP_RUNNER_E2E_REPORT_DIR: ${{ github.workspace }}/runner-e2e-merged-report/normalized
          RUNNER_E2E_HISTORY_S3_BUCKET: ${{ vars.RUNNER_E2E_HISTORY_S3_BUCKET }}
          RUNNER_E2E_HISTORY_PREFIX: ${{ vars.RUNNER_E2E_HISTORY_PREFIX || 'runner-e2e' }}
          RUNNER_E2E_HISTORY_PUBLIC_BASE_URL: ${{ vars.RUNNER_E2E_HISTORY_PUBLIC_BASE_URL }}
        run: pnpm test:e2e:runner:history:publish

      - name: Resolve Pages artifact name
        id: pages_artifact_name
        if: vars.RUNNER_FULL_STACK_E2E_PUBLISH_PAGES == 'true'
        run: echo "name=github-pages-${{ github.run_id }}-${{ github.run_attempt }}" >> "$GITHUB_OUTPUT"

      - name: Package pruned dashboard with declared screenshots for GitHub Pages
        if: vars.RUNNER_FULL_STACK_E2E_PUBLISH_PAGES == 'true'
        uses: actions/upload-pages-artifact@7b1f4a764d45c48632c6b24a0339c27f5614fb0b # v4
        with:
          name: ${{ steps.pages_artifact_name.outputs.name }}
          path: runner-e2e-merged-report/pages

  pages:
    name: Publish latest dashboard with declared screenshots
    needs: [report, publish_history]
    if: always() && needs.report.outputs.history_source_ready == 'true' && needs.publish_history.result == 'success' && vars.RUNNER_FULL_STACK_E2E_PUBLISH_PAGES == 'true'
    runs-on: ubuntu-latest
    permissions:
      pages: write
      id-token: write
    environment:
      name: github-pages
      url: ${{ steps.deployment.outputs.page_url }}
    steps:
      - name: Deploy to GitHub Pages
        id: deployment
        uses: actions/deploy-pages@d6db90164ac5ed86f2b6aed7e0febac5b3c0c03e # v4
        with:
          # If only this failed job is rerun, GitHub retains the successful
          # publisher job's output from the earlier workflow attempt.
          artifact_name: ${{ needs.publish_history.outputs.pages_artifact_name }}