content-pipelines.yml

name: 'Content pipelines: Update content'

# **What it does**: On a schedule, runs the content pipeline update script for each
#   configured entry. The script clones each source repo, detects changes, and
#   runs a Copilot agent to update content articles. The workflow handles
#   branching, committing, and opening PRs.
# **Why we have it**: Keeps reference documentation in sync with upstream source
#   docs without storing copies of those source docs in this repository.
# **Who does it impact**: Docs content writers, docs engineering.
#
# To add a new entry, add it to src/content-pipelines/config.yml and to the matrix
# `include` list below (only `id` is needed). The update logic lives in
# src/content-pipelines/scripts/update.ts, which reads config.yml for all other
# values. Run locally: npx tsx src/content-pipelines/scripts/update.ts --help

on:
  schedule:
    - cron: '20 16 * * 1-5' # Mon-Fri at 16:20 UTC
  workflow_dispatch:

permissions:
  contents: write
  pull-requests: write

env:
  HUSKY: 0

jobs:
  update:
    if: github.repository == 'github/docs-internal'
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        include:
          # Each entry only needs `id`. Everything else (source-repo,
          # source-path, target-articles, etc.) is read from
          # src/content-pipelines/config.yml by the update script.
          - id: copilot-cli
          # - id: mcp-server

    steps:
      - name: Checkout docs-internal
        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1

      - uses: ./.github/actions/node-npm-setup

      - name: Install Copilot CLI
        run: npm install -g @github/copilot@prerelease

      - name: Derive branch name
        id: branch
        run: echo "update_branch=docs/content-pipeline-${{ matrix.id }}-update" >> "$GITHUB_OUTPUT"

      - name: Check for existing PR
        id: check-pr
        env:
          GH_TOKEN: ${{ github.token }}
          UPDATE_BRANCH: ${{ steps.branch.outputs.update_branch }}
        run: |
          PR_NUMBER=$(gh pr list --head "$UPDATE_BRANCH" --state open --json number --jq '.[0].number // empty' 2>/dev/null || echo "")
          echo "pr_number=$PR_NUMBER" >> "$GITHUB_OUTPUT"

      - name: Setup branch
        id: setup-branch
        env:
          UPDATE_BRANCH: ${{ steps.branch.outputs.update_branch }}
          PR_NUMBER: ${{ steps.check-pr.outputs.pr_number }}
        run: |
          git config user.name "github-actions[bot]"
          git config user.email "github-actions[bot]@users.noreply.github.com"

          if git ls-remote --exit-code --heads origin "$UPDATE_BRANCH" > /dev/null 2>&1; then
            git fetch --unshallow origin "$UPDATE_BRANCH" main 2>/dev/null || git fetch origin "$UPDATE_BRANCH" main
            git checkout "$UPDATE_BRANCH"
            git merge origin/main --no-edit || {
              echo "Merge conflict with main — resetting branch to main"
              git merge --abort 2>/dev/null || true
              git checkout -f main
              git branch -D "$UPDATE_BRANCH"
              if [ -z "$PR_NUMBER" ]; then
                git push origin --delete "$UPDATE_BRANCH" || true
              else
                echo "Skipping remote branch delete — PR #$PR_NUMBER is open"
                echo "force_push=true" >> "$GITHUB_OUTPUT"
              fi
              git checkout -b "$UPDATE_BRANCH"
            }
          else
            git checkout -b "$UPDATE_BRANCH"
          fi

      - name: Run content pipeline update script
        env:
          GH_TOKEN: ${{ secrets.DOCS_BOT_PAT_BASE }}
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          COPILOT_GITHUB_TOKEN: ${{ secrets.DOCS_BOT_PAT_COPILOT }}
        run: npx tsx src/content-pipelines/scripts/update.ts --id "${{ matrix.id }}"

      - name: Commit changes
        id: commit
        env:
          ID: ${{ matrix.id }}
        run: |
          git add content/ data/
          if git diff --cached --quiet; then
            echo "has_changes=false" >> "$GITHUB_OUTPUT"
            echo "No documentation changes to commit"
          else
            git add "src/content-pipelines/state/${ID}.sha"
            git commit -m "docs: update ${ID} content from source docs" \
              -m "Updated by the content-pipeline-update agent (${ID}) via GitHub Actions." \
              -m "Run: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
            echo "has_changes=true" >> "$GITHUB_OUTPUT"
          fi

      - name: Push changes
        if: steps.commit.outputs.has_changes == 'true'
        env:
          UPDATE_BRANCH: ${{ steps.branch.outputs.update_branch }}
          FORCE_PUSH: ${{ steps.setup-branch.outputs.force_push }}
        run: |
          if [ "$FORCE_PUSH" = "true" ]; then
            echo "Force-pushing to align branch after merge conflict reset"
            git push --force-with-lease origin "$UPDATE_BRANCH"
          else
            git push origin "$UPDATE_BRANCH"
          fi

      - name: Read source repo info from config
        id: source-info
        env:
          PIPELINE_ID: ${{ matrix.id }}
        run: |
          SOURCE_REPO=$(yq -r ".[\"${PIPELINE_ID}\"].\"source-repo\"" src/content-pipelines/config.yml)
          SOURCE_PATH=$(yq -r ".[\"${PIPELINE_ID}\"].\"source-path\"" src/content-pipelines/config.yml)
          echo "source_repo=$SOURCE_REPO" >> "$GITHUB_OUTPUT"
          echo "source_path=$SOURCE_PATH" >> "$GITHUB_OUTPUT"

      - name: Create or update PR
        if: steps.commit.outputs.has_changes == 'true'
        env:
          GH_TOKEN: ${{ secrets.DOCS_BOT_PAT_BASE }}
          UPDATE_BRANCH: ${{ steps.branch.outputs.update_branch }}
          PIPELINE_ID: ${{ matrix.id }}
          SOURCE_REPO: ${{ steps.source-info.outputs.source_repo }}
          SOURCE_PATH: ${{ steps.source-info.outputs.source_path }}
        run: |
          PR_NUMBER="${{ steps.check-pr.outputs.pr_number }}"
          PR_TITLE="docs: update ${PIPELINE_ID} content from source docs"
          SOURCE_LINK="See the [upstream repo](https://github.com/${SOURCE_REPO}/tree/main/${SOURCE_PATH}) for changes that triggered this update."

          if [ -n "$PR_NUMBER" ]; then
            echo "PR #$PR_NUMBER already exists"

            echo "Ensuring PR #$PR_NUMBER is marked ready for review"
            gh pr ready "$PR_NUMBER" || echo "Unable to mark PR #$PR_NUMBER as ready (it may already be ready)"
          else
            echo "Creating new PR"

            PR_BODY="_GitHub Copilot generated this pull request._"$'\n\n'
            PR_BODY+="> [!NOTE]"$'\n'
            PR_BODY+="> This PR is **automatically generated** by the [content pipeline update workflow](${{ github.server_url }}/${{ github.repository }}/actions/workflows/content-pipelines.yml). Each run adds a new commit with any documentation changes detected."$'\n\n'
            PR_BODY+="## What this does"$'\n\n'
            PR_BODY+="Runs the \`content-pipeline-update\` agent (${PIPELINE_ID}) against the latest source docs and updates official articles under \`content/\` that have fallen out of sync."$'\n\n'
            PR_BODY+="## Source changes"$'\n\n'
            PR_BODY+="${SOURCE_LINK}"$'\n\n'
            PR_BODY+="## Review"$'\n\n'
            PR_BODY+="* Review each commit for accuracy — the agent uses AI, so spot-check important changes"$'\n'
            PR_BODY+="* To adjust agent behavior, see [Modifying results](${{ github.server_url }}/${{ github.repository }}/blob/main/src/content-pipelines/README.md#modifying-results)"$'\n'
            PR_BODY+="* Once satisfied, merge to keep docs up to date"$'\n'
            PR_BODY+="* A new PR will be created on the next run if there are further changes"

            gh pr create \
              --title "$PR_TITLE" \
              --body "$PR_BODY" \
              --base main \
              --head "$UPDATE_BRANCH" \
              --label "workflow-generated,content-pipeline-update,ready-for-doc-review,skip FR board"
          fi

      - uses: ./.github/actions/slack-alert
        if: ${{ failure() && github.event_name != 'workflow_dispatch' }}
        with:
          slack_channel_id: ${{ secrets.DOCS_ALERTS_SLACK_CHANNEL_ID }}
          slack_token: ${{ secrets.SLACK_DOCS_BOT_TOKEN }}

      - uses: ./.github/actions/create-workflow-failure-issue
        if: ${{ failure() && github.event_name != 'workflow_dispatch' }}
        with:
          token: ${{ secrets.DOCS_BOT_PAT_BASE }}