PaperClipAI/.github/workflows/ci-routing.yml

name: CI routing

on:
  workflow_dispatch:
  workflow_call:
    outputs:
      runner:
        value: ${{ jobs.gate.outputs.runner }}
      full_ci:
        value: ${{ jobs.gate.outputs.full_ci }}
      plan:
        value: ${{ jobs.gate.outputs.plan }}
      profile_ci:
        value: ${{ jobs.gate.outputs.profile_ci }}

permissions:
  actions: read
  contents: read
  pull-requests: read

jobs:
  gate:
    name: Select trusted runner
    runs-on: ${{ vars.AWS_CI_ENABLED == 'true' && vars.AWS_CI_ROUTING_USER_IDS_SOURCE != '' && vars.AWS_CI_TRUSTED_USER_IDS == vars.AWS_CI_ROUTING_USER_IDS_SOURCE && github.repository == 'paperclipai/paperclip' && github.repository_id == '1170821064' && ((github.event_name == 'pull_request' && contains(vars.AWS_CI_ROUTING_USER_IDS, format('|{0}|', github.event.pull_request.user.id)) && contains(vars.AWS_CI_ROUTING_USER_IDS, format('|{0}|', github.event.sender.id))) || (github.event_name == 'workflow_dispatch' && github.ref == 'refs/heads/master' && contains(vars.AWS_CI_ROUTING_USER_IDS, format('|{0}|', github.actor_id)))) && 'runs-on/fleet=paperclip-ci-routing-x64/env=public-ci' || 'ubuntu-latest' }}
    timeout-minutes: 5
    outputs:
      plan: ${{ steps.plan.outputs.plan }}
      runner: ${{ steps.route.outputs.runner }}
      full_ci: ${{ steps.scope.outputs.full_ci }}
      profile_ci: ${{ steps.profile.outputs.profile_ci }}

    steps:
      - name: Validate PR identity and select runner
        id: route
        shell: bash
        env:
          GH_TOKEN: ${{ github.token }}
          AWS_CI_ENABLED: ${{ vars.AWS_CI_ENABLED }}
          TRUSTED_USER_IDS: ${{ vars.AWS_CI_TRUSTED_USER_IDS }}
          EVENT_NAME: ${{ github.event_name }}
          EVENT_REPOSITORY: ${{ github.repository }}
          EVENT_REPOSITORY_ID: ${{ github.repository_id }}
          EVENT_ACTION: ${{ github.event.action }}
          EVENT_LABEL_NAME: ${{ github.event.label.name }}
          EVENT_PR_NUMBER: ${{ github.event.pull_request.number }}
          EVENT_PR_AUTHOR_ID: ${{ github.event.pull_request.user.id }}
          EVENT_SENDER_ID: ${{ github.event.sender.id }}
          EVENT_BASE_REPOSITORY_ID: ${{ github.event.pull_request.base.repo.id }}
          EVENT_BASE_REF: ${{ github.event.pull_request.base.ref }}
          EVENT_BASE_SHA: ${{ github.event.pull_request.base.sha }}
          EVENT_HEAD_SHA: ${{ github.event.pull_request.head.sha }}
          EVENT_MERGE_SHA: ${{ github.sha }}
          RUN_ID: ${{ github.run_id }}
          RUN_ATTEMPT: ${{ github.run_attempt }}
        run: |
          set -u

          github_runner='ubuntu-latest'
          aws_runner='runs-on/fleet=paperclip-public-pr-x64/env=public-ci'

          fail_closed() {
            echo "runner=$github_runner" >> "$GITHUB_OUTPUT"
            echo "::notice title=AWS CI routing::Using GitHub-hosted runner: $1"
            exit 0
          }

          is_positive_integer() {
            [[ "$1" =~ ^[1-9][0-9]*$ ]]
          }

          is_commit_sha() {
            [[ "$1" =~ ^[0-9a-f]{40}$ ]]
          }

          is_allowed() {
            local user_id="$1"
            jq -e --argjson user_id "$user_id" --argjson owners "$owner_ids" \
              'index($user_id) != null and ($owners | index($user_id) != null)' \
              <<< "$TRUSTED_USER_IDS" >/dev/null
          }

          [[ "$AWS_CI_ENABLED" == 'true' ]] || fail_closed 'AWS_CI_ENABLED is not true'
          [[ "$EVENT_NAME" == 'pull_request' ]] || fail_closed 'event is not pull_request'
          [[ "$EVENT_REPOSITORY" == 'paperclipai/paperclip' ]] || fail_closed 'unexpected repository'
          [[ "$EVENT_REPOSITORY_ID" == '1170821064' ]] || fail_closed 'unexpected repository ID'
          [[ "$EVENT_BASE_REPOSITORY_ID" == '1170821064' ]] || fail_closed 'unexpected base repository ID'
          [[ -n "$EVENT_BASE_REF" ]] || fail_closed 'missing base branch'
          [[ "$EVENT_ACTION" =~ ^(opened|reopened|synchronize|labeled)$ ]] || fail_closed 'unsupported pull_request action'
          if [[ "$EVENT_ACTION" == 'labeled' && ! "${EVENT_LABEL_NAME:-}" =~ ^(profile-ci|full-ci)$ ]]; then
            fail_closed 'only the profile-ci or full-ci labels can request CI'
          fi

          jq -e '
            type == "array" and
            length > 0 and
            all(.[]; type == "number" and . > 0 and floor == .)
          ' <<< "$TRUSTED_USER_IDS" >/dev/null 2>&1 || fail_closed 'trusted user ID list is malformed'

          # Both the resolver and CODEOWNERS come from the same protected master
          # revision. Never use the PR's CODEOWNERS or execute its source here.
          trusted_sha="$(gh api /repos/paperclipai/paperclip/git/ref/heads/master --jq .object.sha)" \
            || fail_closed 'could not resolve trusted CODEOWNERS revision'
          is_commit_sha "$trusted_sha" || fail_closed 'invalid trusted CODEOWNERS revision'
          owner_helper="$RUNNER_TEMP/aws-ci-owners.mjs"
          if ! gh api "/repos/paperclipai/paperclip/contents/scripts/ci-profile/authorize.mjs?ref=$trusted_sha" \
              --jq '.content' > "$owner_helper.base64" ||
             ! base64 --decode < "$owner_helper.base64" > "$owner_helper"; then
            fail_closed 'could not load trusted CODEOWNERS resolver'
          fi
          owner_ids="$(node --input-type=module - "$owner_helper" "$trusted_sha" <<'NODE'
          import { pathToFileURL } from 'node:url';
          const { trustedOwnerIds } = await import(pathToFileURL(process.argv[2]));
          console.log(JSON.stringify(trustedOwnerIds(undefined, process.argv[3])));
          NODE
          )" || fail_closed 'could not verify current CI CODEOWNERS'

          for user_id in "$EVENT_PR_AUTHOR_ID" "$EVENT_SENDER_ID"; do
            is_positive_integer "$user_id" || fail_closed 'event contains a malformed user ID'
            is_allowed "$user_id" || fail_closed "GitHub user ID $user_id is not an allowlisted CI CODEOWNER"
          done

          for commit_sha in "$EVENT_BASE_SHA" "$EVENT_HEAD_SHA" "$EVENT_MERGE_SHA"; do
            is_commit_sha "$commit_sha" || fail_closed 'event contains a malformed commit SHA'
          done

          pr_json="$(gh api \
            -H 'Accept: application/vnd.github+json' \
            -H 'X-GitHub-Api-Version: 2022-11-28' \
            "/repos/paperclipai/paperclip/pulls/$EVENT_PR_NUMBER" 2>/dev/null)" \
            || fail_closed 'could not refresh pull request state'

          jq -e \
            --argjson repository_id 1170821064 \
            --argjson author_id "$EVENT_PR_AUTHOR_ID" \
            --arg base_ref "$EVENT_BASE_REF" \
            --arg head_sha "$EVENT_HEAD_SHA" \
            '
              .state == "open" and
              .user.id == $author_id and
              .base.repo.id == $repository_id and
              .base.ref == $base_ref and
              .head.sha == $head_sha
            ' <<< "$pr_json" >/dev/null 2>&1 \
            || fail_closed 'current pull request state does not match the triggering event'

          base_ref_json="$(gh api \
            -H 'Accept: application/vnd.github+json' \
            -H 'X-GitHub-Api-Version: 2022-11-28' \
            "/repos/paperclipai/paperclip/git/ref/heads/$EVENT_BASE_REF" 2>/dev/null)" \
            || fail_closed 'could not inspect the current base branch'
          live_base_ref_sha="$(jq -r '.object.sha // empty' <<< "$base_ref_json")"
          is_commit_sha "$live_base_ref_sha" || fail_closed 'current base branch has no valid commit SHA'

          base_comparison="$(gh api \
            -H 'Accept: application/vnd.github+json' \
            -H 'X-GitHub-Api-Version: 2022-11-28' \
            "/repos/paperclipai/paperclip/compare/$EVENT_BASE_SHA...$live_base_ref_sha" 2>/dev/null)" \
            || fail_closed 'could not compare the triggering and current base branches'
          jq -e \
            --arg event_base_sha "$EVENT_BASE_SHA" '
              .merge_base_commit.sha == $event_base_sha and
              (.status == "ahead" or .status == "identical")
            ' <<< "$base_comparison" >/dev/null 2>&1 \
            || fail_closed 'current base branch does not descend from the triggering base snapshot'

          event_merge_json="$(gh api \
            -H 'Accept: application/vnd.github+json' \
            -H 'X-GitHub-Api-Version: 2022-11-28' \
            "/repos/paperclipai/paperclip/git/commits/$EVENT_MERGE_SHA" 2>/dev/null)" \
            || fail_closed 'could not inspect the event merge commit'

          validate_merge_commit() {
            local merge_json="$1"
            local expected_sha="$2"
            jq -e \
              --arg expected_sha "$expected_sha" \
              --arg head_sha "$EVENT_HEAD_SHA" '
                .sha == $expected_sha and
                (.parents | length) == 2 and
                .parents[1].sha == $head_sha and
                (.parents[0].sha | test("^[0-9a-f]{40}$")) and
                (.tree.sha | test("^[0-9a-f]{40}$"))
              ' <<< "$merge_json" >/dev/null 2>&1
          }

          validate_merge_commit "$event_merge_json" "$EVENT_MERGE_SHA" \
            || fail_closed 'event merge commit does not match the triggering head'

          is_base_snapshot() {
            local snapshot_sha="$1"
            local comparison
            [[ "$snapshot_sha" == "$EVENT_BASE_SHA" || "$snapshot_sha" == "$live_base_ref_sha" ]] && return 0
            comparison="$(gh api "/repos/paperclipai/paperclip/compare/$EVENT_BASE_SHA...$snapshot_sha" 2>/dev/null)" || return 1
            jq -e --arg base "$EVENT_BASE_SHA" '
              .merge_base_commit.sha == $base and
              (.status == "ahead" or .status == "identical")
            ' <<< "$comparison" >/dev/null 2>&1 || return 1
            comparison="$(gh api "/repos/paperclipai/paperclip/compare/$snapshot_sha...$live_base_ref_sha" 2>/dev/null)" || return 1
            jq -e --arg base "$snapshot_sha" '
              .merge_base_commit.sha == $base and
              (.status == "ahead" or .status == "identical")
            ' <<< "$comparison" >/dev/null 2>&1
          }

          event_merge_parent="$(jq -r '.parents[0].sha' <<< "$event_merge_json")"
          if ! is_base_snapshot "$event_merge_parent"; then
            base_merge_json="$(gh api \
              -H 'Accept: application/vnd.github+json' \
              -H 'X-GitHub-Api-Version: 2022-11-28' \
              "/repos/paperclipai/paperclip/git/commits/$event_merge_parent" 2>/dev/null)" \
              || fail_closed 'could not inspect the stacked base merge commit'
            jq -e \
              --arg expected_sha "$event_merge_parent" '
                .sha == $expected_sha and
                (.parents | length) == 2 and
                all(.parents[]; .sha | test("^[0-9a-f]{40}$")) and
                (.tree.sha | test("^[0-9a-f]{40}$"))
              ' <<< "$base_merge_json" >/dev/null 2>&1 \
              || fail_closed 'invalid stacked base merge commit'
            base_snapshot_found=false
            while read -r parent_sha; do
              if is_base_snapshot "$parent_sha"; then
                base_snapshot_found=true
                break
              fi
            done < <(jq -r '.parents[].sha' <<< "$base_merge_json")
            [[ "$base_snapshot_found" == 'true' ]] \
              || fail_closed 'stacked base merge commit does not contain a validated base snapshot'
          fi

          is_positive_integer "$RUN_ID" || fail_closed 'invalid workflow run ID'
          is_positive_integer "$RUN_ATTEMPT" || fail_closed 'invalid workflow run attempt'
          run_json="$(gh api \
            -H 'Accept: application/vnd.github+json' \
            -H 'X-GitHub-Api-Version: 2022-11-28' \
            "/repos/paperclipai/paperclip/actions/runs/$RUN_ID/attempts/$RUN_ATTEMPT" 2>/dev/null)" \
            || fail_closed 'could not refresh workflow run state'

          triggering_actor_id="$(jq -r '.triggering_actor.id // empty' <<< "$run_json")"
          is_positive_integer "$triggering_actor_id" || fail_closed 'workflow run has no valid triggering actor ID'
          is_allowed "$triggering_actor_id" || fail_closed "triggering GitHub user ID $triggering_actor_id is not an allowlisted CI CODEOWNER"

          jq -e \
            --argjson repository_id 1170821064 \
            --argjson run_attempt "$RUN_ATTEMPT" \
            --arg event_name "$EVENT_NAME" '
              .repository.id == $repository_id and
              .run_attempt == $run_attempt and
              .event == $event_name
            ' <<< "$run_json" >/dev/null 2>&1 \
            || fail_closed 'current workflow run does not match the expected repository event'

          echo "runner=$aws_runner" >> "$GITHUB_OUTPUT"
          echo '::notice title=AWS CI routing::Using an ephemeral RunsOn Fleet runner'

      - name: Authorize CODEOWNERS CI profiling
        id: profile
        shell: bash
        env:
          GH_TOKEN: ${{ github.token }}
          PROFILE_REQUESTED: ${{ contains(github.event.pull_request.labels.*.name, 'profile-ci') }}
        run: |
          set -euo pipefail
          if [[ "$PROFILE_REQUESTED" != 'true' ]]; then
            echo 'profile_ci=false' >> "$GITHUB_OUTPUT"
            exit 0
          fi
          # Fetch only from canonical master, never the PR ref. Pin both the
          # authorization program and CODEOWNERS to the same trusted revision.
          if ! TRUSTED_PROFILE_SHA="$(gh api /repos/paperclipai/paperclip/git/ref/heads/master --jq .object.sha)" ||
             [[ ! "$TRUSTED_PROFILE_SHA" =~ ^[0-9a-f]{40}$ ]] ||
             ! gh api -H 'Accept: application/vnd.github.raw+json' \
               "/repos/paperclipai/paperclip/contents/scripts/ci-profile/authorize.mjs?ref=$TRUSTED_PROFILE_SHA" \
               > "$RUNNER_TEMP/ci-profile-authorize.mjs"; then
            echo 'profile_ci=false' >> "$GITHUB_OUTPUT"
            exit 0
          fi
          export TRUSTED_PROFILE_SHA
          node "$RUNNER_TEMP/ci-profile-authorize.mjs"

      - name: Select PR CI scope
        id: scope
        shell: bash
        env:
          GH_TOKEN: ${{ github.token }}
          EVENT_NAME: ${{ github.event_name }}
          EVENT_BASE_SHA: ${{ github.event.pull_request.base.sha }}
          EVENT_HEAD_SHA: ${{ github.event.pull_request.head.sha }}
          PROFILE_CI: ${{ steps.profile.outputs.profile_ci }}
          FORCE_FULL_CI: ${{ contains(github.event.pull_request.labels.*.name, 'full-ci') }}
          CI_INCREMENTAL_MODE: ${{ vars.CI_INCREMENTAL_MODE || 'enabled' }}
          STACK_JSON: ${{ toJSON(github.event.pull_request.stack) }}
          PR_BASE_REF: ${{ github.event.pull_request.base.ref }}
        run: |
          set -euo pipefail

          full_ci='true'
          reason='ordinary pull request'
          # True when the PR's own diff is everything it adds to the stack's
          # base branch: no stack, or the lowest unmerged PR in one. Above
          # that, the diff omits lower PRs' code that this run must still test.
          diff_covers_stack='true'

          # Release notes PRs touch only releases/v*.md or releases/beta/v*.md,
          # which no build, test, or e2e lane reads. The diff is pinned to the
          # event's base and head SHAs, so a later push cannot change the
          # decision for this run. Any lookup failure keeps full CI.
          release_notes_only() {
            [[ "${EVENT_NAME:-}" == 'pull_request' ]] || return 1
            [[ "${EVENT_BASE_SHA:-}" =~ ^[0-9a-f]{40}$ ]] || return 1
            [[ "${EVENT_HEAD_SHA:-}" =~ ^[0-9a-f]{40}$ ]] || return 1

            local comparison
            comparison="$(gh api \
              -H 'Accept: application/vnd.github+json' \
              -H 'X-GitHub-Api-Version: 2022-11-28' \
              "/repos/paperclipai/paperclip/compare/$EVENT_BASE_SHA...$EVENT_HEAD_SHA" 2>/dev/null)" \
              || return 1

            # The compare API lists at most 300 files, so a full page may be
            # truncated. Renames count both the old and the new path.
            jq -e '
              (.files | type == "array") and
              (.files | length > 0 and length < 300) and
              all(.files[];
                (.filename | type == "string") and
                ([.filename, .previous_filename] | map(select(. != null)) |
                  all(.[]; type == "string" and test("^releases/(beta/)?v[^/]+\\.md$"))))
            ' <<< "$comparison" >/dev/null 2>&1
          }

          if jq -e 'type == "object"' <<< "$STACK_JSON" >/dev/null 2>&1; then
            stack_position="$(jq -r '.position // empty' <<< "$STACK_JSON")"
            stack_size="$(jq -r '.size // empty' <<< "$STACK_JSON")"
            stack_base_ref="$(jq -r '.base.ref // empty' <<< "$STACK_JSON")"
            if [[ -z "$stack_base_ref" || "$stack_base_ref" != "$PR_BASE_REF" ]]; then
              diff_covers_stack='false'
            fi

            if [[ ! "$stack_position" =~ ^[1-9][0-9]*$ ]] ||
               [[ ! "$stack_size" =~ ^[1-9][0-9]*$ ]] ||
               (( stack_position > stack_size )) ||
               [[ -z "$stack_base_ref" ]]; then
              reason='malformed stack metadata; defaulting to full CI'
              diff_covers_stack='false'
            elif (( stack_position == stack_size )); then
              reason='top pull request in stack'
            elif [[ "$stack_base_ref" == "$PR_BASE_REF" ]]; then
              reason='lowest unmerged pull request in stack'
            else
              full_ci='false'
              reason='middle pull request in stack'
            fi
          fi

          if [[ "$full_ci" == 'true' && "$diff_covers_stack" == 'true' ]] &&
             release_notes_only; then
            full_ci='false'
            reason='release notes only'
          fi

          if [[ "${PROFILE_CI:-false}" == 'true' || "${FORCE_FULL_CI:-false}" == 'true' || "${CI_INCREMENTAL_MODE:-enabled}" == 'full' ]]; then
            full_ci='true'
            reason='profile-ci, full-ci or full mode requests the complete PR suite'
          fi

          echo "full_ci=$full_ci" >> "$GITHUB_OUTPUT"
          echo "::notice title=PR CI scope::$reason; full_ci=$full_ci"


      - name: Plan affected CI tasks from trusted definitions
        id: plan
        shell: bash
        env:
          GH_TOKEN: ${{ github.token }}
          FULL_CI: ${{ steps.scope.outputs.full_ci }}
          PROFILE_CI: ${{ steps.profile.outputs.profile_ci }}
          FORCE_FULL_CI: ${{ contains(github.event.pull_request.labels.*.name, 'full-ci') }}
          CI_INCREMENTAL_MODE: ${{ vars.CI_INCREMENTAL_MODE || 'enabled' }}
          STACK_JSON: ${{ toJSON(github.event.pull_request.stack) }}
          EVENT_HEAD_SHA: ${{ github.event.pull_request.head.sha }}
          EVENT_MERGE_SHA: ${{ github.sha }}
        run: |
          set -euo pipefail
          fallback() { echo 'plan=' >> "$GITHUB_OUTPUT"; exit 0; }
          [[ "$FULL_CI" == 'true' ]] || fallback
          [[ "$EVENT_HEAD_SHA" =~ ^[0-9a-f]{40}$ && "$EVENT_MERGE_SHA" =~ ^[0-9a-f]{40}$ ]] || fallback
          trusted="$(gh api /repos/paperclipai/paperclip/git/ref/heads/master --jq .object.sha)" || fallback
          [[ "$trusted" =~ ^[0-9a-f]{40}$ ]] || fallback
          directory="$(mktemp -d)"
          trap 'rm -rf "$directory"' EXIT
          for file in .github/scripts/ci-plan.mjs .github/scripts/ci-inputs.mjs .github/scripts/ci-diff.mjs .github/ci-task-matrix.json turbo.json; do
            gh api -H 'Accept: application/vnd.github.raw+json' \
              "/repos/paperclipai/paperclip/contents/$file?ref=$trusted" \
              > "$directory/${file##*/}" || fallback
          done
          # Read the exact tested merge and both parents. The event's base SHA can
          # lag behind its actual first parent. A bare tree diff has no API file cap.
          git init --bare "$directory/repository.git" >/dev/null || fallback
          git -C "$directory/repository.git" fetch --quiet --no-tags --filter=blob:none --depth=2 \
            https://github.com/paperclipai/paperclip.git "$EVENT_MERGE_SHA" || fallback
          if [[ "$PROFILE_CI" == 'true' || "$FORCE_FULL_CI" == 'true' ]]; then
            export CI_FORCE_REASON='Full suite requested by label'
          elif [[ "$STACK_JSON" != 'null' && -n "$STACK_JSON" ]]; then
            export CI_FORCE_REASON='Stack verification includes lower pull requests'
          fi
          export CI_TASK_CONFIG="$directory/turbo.json"
          export CI_TASK_MATRIX="$directory/ci-task-matrix.json"
          export CI_DIFF_REPOSITORY="$directory/repository.git"
          node "$directory/ci-plan.mjs" || fallback