GitNexus/.github/workflows/commit-fork-prebuilds.yml

name: Commit fork prebuilds

# TRUSTED HALF of the vendored-grammar prebuild pipeline — FORK PRs only.
#
# `build-tree-sitter-prebuilds.yml` runs in the UNTRUSTED `pull_request`
# context. On a fork PR it has a read-only token and no secrets, so it can
# build + validate the native prebuilds and upload them as artifacts, but it
# cannot commit them back. This workflow is the trusted consumer: triggered by
# `workflow_run`, it runs from the DEFAULT BRANCH's copy of this file (the trust
# anchor) with a writable token, downloads ONLY the artifacts (data — the
# already-built-and-validated `.node` files + a small metadata.json), verifies
# the metadata against the GitHub-controlled workflow_run authority, then pushes
# the prebuilds onto the fork PR's head branch.
#
# It NEVER checks out or executes fork-controlled code: the producer already
# `require()`-loaded + parsed each `.node` on its target platform in the
# untrusted half (the correct place to run untrusted code). Here we only move
# bytes and run git. The prebuilds touch ONLY gitnexus/vendor/<g>/prebuilds/**,
# never .github/ — so the GITHUB_TOKEN's lack of `workflows` scope is irrelevant.
#
# Pushing to a fork branch with the GITHUB_TOKEN works only when the contributor
# left "Allow edits by maintainers" enabled (the PR default) — the same
# constraint as pr-autofix-apply.yml. When it's off we fall back to a comment.
#
# Same-repo PRs do NOT come here: they have secrets in the producer run, so the
# `aggregate` job in build-tree-sitter-prebuilds.yml commits straight onto their
# branch. This workflow's `if:` filters to forks.

on:
  workflow_run:
    workflows: ['Build tree-sitter prebuilds']
    types: [completed]

concurrency:
  # Per-PR identity, NOT workflow_run.id (which is per-run unique and would
  # defeat serialization). Fork PRs have an empty pull_requests[] in the
  # workflow_run payload, so fall back to head-repo + head-branch.
  group: ${{ github.workflow }}-${{ github.event.workflow_run.pull_requests[0].number || format('{0}/{1}', github.event.workflow_run.head_repository.full_name, github.event.workflow_run.head_branch) }}
  cancel-in-progress: false

permissions: {}

jobs:
  deliver:
    name: deliver-fork-prebuilds
    # Only a SUCCESSFUL fork pull_request producer run. Same-repo PRs
    # (head_repository == base) are handled by the producer's aggregate job.
    if: >-
      github.event.workflow_run.event == 'pull_request'
      && github.event.workflow_run.conclusion == 'success'
      && github.event.workflow_run.head_repository.full_name != github.repository
    runs-on: ubuntu-latest
    timeout-minutes: 15
    permissions:
      contents: write # push the prebuilds commit to the fork PR head branch
      pull-requests: write # comment the delivery outcome
      actions: read # download artifacts produced by the producer run
    steps:
      # Pinned to v8.0.1 (same SHA used across this repo's workflows).
      - name: Download prebuild artifacts
        uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8.0.2
        continue-on-error: true
        with:
          run-id: ${{ github.event.workflow_run.id }}
          github-token: ${{ secrets.GITHUB_TOKEN }}
          pattern: ts-prebuild-*
          path: prebuilds-in

      - name: Download PR meta
        uses: actions/download-artifact@9000827ccba6bdab643e8b6fd33ac0654aef8333 # v8.0.2
        continue-on-error: true
        with:
          name: pr-meta
          run-id: ${{ github.event.workflow_run.id }}
          github-token: ${{ secrets.GITHUB_TOKEN }}
          path: meta-in

      - name: Read and validate metadata
        id: meta
        shell: bash
        run: |
          set -euo pipefail
          # No meta => this producer run had no fork-PR prebuilds to deliver
          # (nothing changed, or it wasn't a fork). Exit cleanly.
          if [ ! -f meta-in/metadata.json ]; then
            echo "No pr-meta artifact — nothing to deliver."
            echo "deliver=false" >> "$GITHUB_OUTPUT"
            exit 0
          fi
          # No prebuild artifacts => same (defensive; producer uploads both together).
          if ! ls prebuilds-in/ts-prebuild-* >/dev/null 2>&1; then
            echo "No ts-prebuild-* artifacts — nothing to deliver."
            echo "deliver=false" >> "$GITHUB_OUTPUT"
            exit 0
          fi
          jq . meta-in/metadata.json

          # The artifact comes from the untrusted producer running fork code.
          # Allowlist EVERY field before it flows into $GITHUB_OUTPUT — a newline
          # in head_ref would otherwise inject a second output line and redirect
          # this job's write-scoped push/comment onto a victim PR.
          assert_field() {
            local key="$1" pattern="$2" value
            value=$(jq -r ".${key} // empty" meta-in/metadata.json)
            if [ -z "$value" ] || ! [[ "$value" =~ $pattern ]]; then
              echo "::error::metadata.${key} failed allowlist (got: $(printf '%q' "$value"))"
              exit 1
            fi
            printf '%s' "$value"
          }

          SCHEMA=$(assert_field    schema    '^gitnexus\.ts-prebuild/v[0-9]+$')
          PR_NUMBER=$(assert_field pr_number  '^[0-9]+$')
          HEAD_SHA=$(assert_field  head_sha   '^[0-9a-f]{40}$')
          HEAD_REF=$(assert_field  head_ref   '^[A-Za-z0-9._/-]+$')
          HEAD_REPO=$(assert_field head_repo  '^[A-Za-z0-9._-]+/[A-Za-z0-9._-]+$')
          BASE_REPO=$(assert_field base_repo  '^[A-Za-z0-9._-]+/[A-Za-z0-9._-]+$')

          # Defence-in-depth: refuse to act if the artifact claims another repo.
          if [ "$BASE_REPO" != "${GITHUB_REPOSITORY}" ]; then
            echo "::error::Artifact base_repo does not match \$GITHUB_REPOSITORY — refusing to deliver."
            exit 1
          fi

          {
            echo "deliver=true"
            echo "schema=${SCHEMA}"
            echo "pr_number=${PR_NUMBER}"
            echo "head_sha=${HEAD_SHA}"
            echo "head_ref=${HEAD_REF}"
            echo "head_repo=${HEAD_REPO}"
          } >> "$GITHUB_OUTPUT"

      # Cross-verify the artifact's claimed identity against the GitHub-controlled
      # workflow_run event. The allowlist above only proves the fields are
      # well-formed — not that they refer to the PR/SHA that actually triggered
      # us. A fork-controlled build could mutate metadata.json to reference
      # another PR/SHA and redirect our write-scoped push.
      #
      # This job's `if:` already restricts to forks, so pull_requests[] is empty
      # by design and GET /repos/{base}/commits/{sha}/pulls is also empty (the
      # fork commit is not in the base graph). Authority is workflow_run.head_sha
      # + head_repository.full_name + head_branch, resolved via
      # pulls?head={owner}:{branch}. The script comes from THIS default-branch
      # checkout (the same trust anchor as this workflow file).
      - name: Checkout identity verifier
        if: steps.meta.outputs.deliver == 'true'
        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          persist-credentials: false
          sparse-checkout: .github/scripts/verify-workflow-run-pr-identity.cjs
          sparse-checkout-cone-mode: false
          path: trusted

      - name: Verify metadata against workflow_run authority
        id: verify
        if: steps.meta.outputs.deliver == 'true'
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          GH_REPO: ${{ github.repository }}
          META_PATH: meta-in/metadata.json
          SCHEMA_PATTERN: '^gitnexus\.ts-prebuild/v[0-9]+$'
          WF_HEAD_SHA: ${{ github.event.workflow_run.head_sha }}
          WF_HEAD_REPO: ${{ github.event.workflow_run.head_repository.full_name }}
          WF_HEAD_BRANCH: ${{ github.event.workflow_run.head_branch }}
        shell: bash
        run: node trusted/.github/scripts/verify-workflow-run-pr-identity.cjs

      # Pinned to v6.0.3 (same SHA used by build-tree-sitter-prebuilds.yml).
      # persist-credentials: false — push auth is provided inline at push time,
      # never written to .git/config on disk.
      - name: Checkout fork PR head
        if: steps.meta.outputs.deliver == 'true' && steps.verify.outcome == 'success'
        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
        with:
          repository: ${{ steps.verify.outputs.head_repo }}
          ref: ${{ steps.verify.outputs.head_sha }}
          token: ${{ secrets.GITHUB_TOKEN }}
          persist-credentials: false
          fetch-depth: 0
          path: pr-checkout

      - name: Place prebuilds into the fork checkout
        if: steps.meta.outputs.deliver == 'true' && steps.verify.outcome == 'success'
        env:
          DL: prebuilds-in
          CHECKOUT: pr-checkout
        shell: bash
        run: |
          set -euo pipefail
          node --input-type=module - <<'NODE'
          import fs from 'node:fs';
          import { execSync } from 'node:child_process';
          const dl = process.env.DL;
          const checkout = process.env.CHECKOUT;
          const PLATFORMS = ['linux-x64', 'linux-arm64', 'darwin-arm64', 'darwin-x64', 'win32-x64', 'win32-arm64'];
          // Reconstruct {grammar -> archs} from the downloaded artifact dir names
          // (ts-prebuild-<grammar>-<platform-arch>; grammar shortnames are dash-free).
          const byGrammar = {};
          for (const d of (fs.existsSync(dl) ? fs.readdirSync(dl) : [])) {
            const m = d.match(/^ts-prebuild-([a-z0-9]+)-(.+)$/);
            if (m) (byGrammar[m[1]] ||= []).push(m[2]);
          }
          const grammars = Object.keys(byGrammar);
          if (grammars.length === 0) throw new Error('no ts-prebuild-* artifacts present');
          const changed = [];
          for (const grammar of grammars) {
            const name = `tree-sitter-${grammar}`;
            const dest = `${checkout}/gitnexus/vendor/${name}/prebuilds`;
            // A grammar with 5/6 prebuilds silently breaks node-gyp-build on the
            // 6th platform — refuse a partial result.
            for (const pa of PLATFORMS) {
              const art = `${dl}/ts-prebuild-${grammar}-${pa}/${name}.node`;
              if (!fs.existsSync(art)) throw new Error(`missing ${grammar} prebuild for ${pa}`);
              fs.mkdirSync(`${dest}/${pa}`, { recursive: true });
              fs.copyFileSync(art, `${dest}/${pa}/${name}.node`);
            }
            execSync(`cd ${dest} && find . -name "*.node" | sort | xargs sha256sum > SHA256SUMS`);
            changed.push(name);
          }
          console.log('Placed prebuilds for:', changed.join(', '));
          NODE

      - name: Commit and push to the fork branch
        id: push
        if: steps.meta.outputs.deliver == 'true' && steps.verify.outcome == 'success'
        working-directory: pr-checkout
        env:
          HEAD_REF: ${{ steps.verify.outputs.head_ref }}
          HEAD_REPO: ${{ steps.verify.outputs.head_repo }}
          HEAD_SHA: ${{ steps.verify.outputs.head_sha }}
          # Push auth only — supplied via env, never interpolated into the command.
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        shell: bash
        run: |
          set -euo pipefail

          git add gitnexus/vendor/tree-sitter-*/prebuilds
          if git diff --cached --quiet; then
            echo "Prebuilds byte-identical to the fork branch — nothing to commit."
            echo "result=nothing-to-commit" >> "$GITHUB_OUTPUT"
            exit 0
          fi

          # Loop guard: if HEAD is already our prebuild bot commit, don't stack
          # another. (The producer's paths filter already excludes prebuilds/**,
          # so a prebuild-only push cannot retrigger it — this is defence in depth.)
          head_author=$(git log -1 --format='%ae' HEAD)
          head_subject=$(git log -1 --format='%s' HEAD)
          if [ "${head_author}" = "41898282+github-actions[bot]@users.noreply.github.com" ] \
             && [[ "${head_subject}" =~ ^chore\(vendor\) ]]; then
            echo "::warning::HEAD is already a prebuild bot commit — refusing to re-apply."
            echo "result=loop-prevented" >> "$GITHUB_OUTPUT"
            exit 0
          fi

          grammars=$(git diff --cached --name-only \
            | sed -n 's#gitnexus/vendor/\(tree-sitter-[a-z0-9]*\)/.*#\1#p' | sort -u | paste -sd, -)

          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
          git config user.name  "github-actions[bot]"
          git commit -q -m "chore(vendor): rebuild native prebuilds (${grammars})" \
            -m "Built + validated by ${GITHUB_SERVER_URL}/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}"

          # Push to the fork head with a lease against the resolved SHA, so a
          # contributor force-push during the build surfaces as lease-failed (not
          # push-failed, which would mislead them into the maintainer-edit fix).
          # Auth via per-invocation http.extraheader (never persisted, never in
          # the process args / git remote -v). Base64-encoded form is masked too.
          push_url="${GITHUB_SERVER_URL}/${HEAD_REPO}.git"
          auth_header="Authorization: Basic $(printf 'x-access-token:%s' "${GITHUB_TOKEN}" | base64 -w0)"
          echo "::add-mask::${auth_header}"
          push_stderr=$(mktemp)
          if git -c http.extraheader="${auth_header}" \
                push --force-with-lease="refs/heads/${HEAD_REF}:${HEAD_SHA}" \
                "${push_url}" "HEAD:${HEAD_REF}" 2>"$push_stderr"; then
            echo "result=applied" >> "$GITHUB_OUTPUT"
          else
            cat "$push_stderr" >&2
            if grep -qE "stale info|force-with-lease|rejected.*non-fast-forward|remote rejected|! \[rejected\]" "$push_stderr"; then
              echo "::error::Push lease failed — fork branch moved during build."
              echo "result=lease-failed" >> "$GITHUB_OUTPUT"
            else
              echo "::error::Push failed — likely a fork without 'Allow edits by maintainers'."
              echo "result=push-failed" >> "$GITHUB_OUTPUT"
            fi
            exit 0
          fi

      - name: Comment delivery outcome
        if: always() && steps.meta.outputs.deliver == 'true' && steps.verify.outcome == 'success' && steps.push.outcome != 'skipped'
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          GH_REPO: ${{ github.repository }}
          PR: ${{ steps.verify.outputs.pr_number }}
          RESULT: ${{ steps.push.outputs.result }}
          RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
        shell: bash
        run: |
          set -euo pipefail
          marker="<!-- gitnexus:ts-prebuild-fork -->"
          case "${RESULT}" in
            applied)
              body="${marker}
          ✅ **Rebuilt native prebuilds pushed to this PR branch.** A grammar source change re-cut the vendored \`tree-sitter\` prebuilds for all 6 platforms and they're now committed on your branch. ([builder run](${RUN_URL}))" ;;
            nothing-to-commit)
              body="${marker}
          ✅ Native prebuilds are already up to date on this branch — nothing to push." ;;
            loop-prevented)
              body="${marker}
          🔁 Skipping prebuild push: the branch HEAD is already an automated prebuild commit." ;;
            lease-failed)
              body="${marker}
          ⏳ The PR head moved while the prebuilds were building, so they weren't pushed. Push another commit (or wait for the next build) and they'll be re-cut. ([builder run](${RUN_URL}))" ;;
            push-failed)
              body="${marker}
          ⚠️ Rebuilt native prebuilds are ready but **couldn't be pushed to your fork branch**. Tick **Allow edits by maintainers** in the PR sidebar so CI can commit them — or download them from the [builder run](${RUN_URL}) artifacts (\`ts-prebuild-*\`) and commit them under \`gitnexus/vendor/<grammar>/prebuilds/\` yourself." ;;
            *)
              body="${marker}
          ❓ Prebuild delivery finished in an unexpected state (\`${RESULT:-unknown}\`). See the [builder run](${RUN_URL})." ;;
          esac
          # Strip the YAML block indent so the rendered comment starts at column 0.
          body="$(printf '%s\n' "$body" | sed 's/^          //')"

          # Upsert a single sticky comment keyed by the marker; only ever edit our
          # own bot comment (PATCH on someone else's 403s and would abort).
          existing=$(gh api "repos/${GH_REPO}/issues/${PR}/comments" --paginate \
            --jq ".[] | select(.user.login == \"github-actions[bot]\" and (.body | contains(\"${marker}\"))) | .id" \
            | head -n1 || true)
          if [ -n "${existing}" ]; then
            gh api -X PATCH "repos/${GH_REPO}/issues/comments/${existing}" -f body="${body}" >/dev/null
            echo "Updated comment ${existing}."
          else
            gh api -X POST "repos/${GH_REPO}/issues/${PR}/comments" -f body="${body}" >/dev/null
            echo "Created delivery comment."
          fi