esphome/.github/workflows/auto-label-pr.yml

name: Auto Label PR

on:
  # Runs only on pull_request_target due to having access to a App token.
  # This means PRs from forks will not be able to alter this workflow to get the tokens
  pull_request_target:
    types: [labeled, opened, reopened, synchronize, edited]

permissions:
  pull-requests: write
  contents: read

env:
  SMALL_PR_THRESHOLD: 30
  MAX_LABELS: 15
  TOO_BIG_THRESHOLD: 1000
  COMPONENT_LABEL_THRESHOLD: 10

jobs:
  label:
    runs-on: ubuntu-latest
    if: github.event.action != 'labeled' || github.event.sender.type != 'Bot'
    steps:
      - name: Checkout
        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0

      - name: Generate a token
        id: generate-token
        uses: actions/create-github-app-token@67018539274d69449ef7c02e8e71183d1719ab42 # v2
        with:
          app-id: ${{ secrets.ESPHOME_GITHUB_APP_ID }}
          private-key: ${{ secrets.ESPHOME_GITHUB_APP_PRIVATE_KEY }}

      - name: Auto Label PR
        uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0
        with:
          github-token: ${{ steps.generate-token.outputs.token }}
          script: |
            const fs = require('fs');

            // Constants
            const SMALL_PR_THRESHOLD = parseInt('${{ env.SMALL_PR_THRESHOLD }}');
            const MAX_LABELS = parseInt('${{ env.MAX_LABELS }}');
            const TOO_BIG_THRESHOLD = parseInt('${{ env.TOO_BIG_THRESHOLD }}');
            const COMPONENT_LABEL_THRESHOLD = parseInt('${{ env.COMPONENT_LABEL_THRESHOLD }}');
            const BOT_COMMENT_MARKER = '<!-- auto-label-pr-bot -->';
            const CODEOWNERS_MARKER = '<!-- codeowners-request -->';
            const TOO_BIG_MARKER = '<!-- too-big-request -->';

            const MANAGED_LABELS = [
              'new-component',
              'new-platform',
              'new-target-platform',
              'merging-to-release',
              'merging-to-beta',
              'chained-pr',
              'core',
              'small-pr',
              'dashboard',
              'github-actions',
              'by-code-owner',
              'has-tests',
              'needs-tests',
              'needs-docs',
              'needs-codeowners',
              'too-big',
              'labeller-recheck',
              'bugfix',
              'new-feature',
              'breaking-change',
              'code-quality'
            ];

            const DOCS_PR_PATTERNS = [
              /https:\/\/github\.com\/esphome\/esphome-docs\/pull\/\d+/,
              /esphome\/esphome-docs#\d+/
            ];

            // Global state
            const { owner, repo } = context.repo;
            const pr_number = context.issue.number;

            // Get current labels and PR data
            const { data: currentLabelsData } = await github.rest.issues.listLabelsOnIssue({
              owner,
              repo,
              issue_number: pr_number
            });
            const currentLabels = currentLabelsData.map(label => label.name);
            const managedLabels = currentLabels.filter(label =>
              label.startsWith('component: ') || MANAGED_LABELS.includes(label)
            );

            // Check for mega-PR early - if present, skip most automatic labeling
            const isMegaPR = currentLabels.includes('mega-pr');

            // Get all PR files with automatic pagination
            const prFiles = await github.paginate(
              github.rest.pulls.listFiles,
              {
                owner,
                repo,
                pull_number: pr_number
              }
            );

            // Calculate data from PR files
            const changedFiles = prFiles.map(file => file.filename);
            const totalAdditions = prFiles.reduce((sum, file) => sum + (file.additions || 0), 0);
            const totalDeletions = prFiles.reduce((sum, file) => sum + (file.deletions || 0), 0);
            const totalChanges = totalAdditions + totalDeletions;

            console.log('Current labels:', currentLabels.join(', '));
            console.log('Changed files:', changedFiles.length);
            console.log('Total changes:', totalChanges);
            if (isMegaPR) {
              console.log('Mega-PR detected - applying limited labeling logic');
            }

            // Fetch API data
            async function fetchApiData() {
              try {
                const response = await fetch('https://data.esphome.io/components.json');
                const componentsData = await response.json();
                return {
                  targetPlatforms: componentsData.target_platforms || [],
                  platformComponents: componentsData.platform_components || []
                };
              } catch (error) {
                console.log('Failed to fetch components data from API:', error.message);
                return { targetPlatforms: [], platformComponents: [] };
              }
            }

            // Strategy: Merge branch detection
            async function detectMergeBranch() {
              const labels = new Set();
              const baseRef = context.payload.pull_request.base.ref;

              if (baseRef === 'release') {
                labels.add('merging-to-release');
              } else if (baseRef === 'beta') {
                labels.add('merging-to-beta');
              } else if (baseRef !== 'dev') {
                labels.add('chained-pr');
              }

              return labels;
            }

            // Strategy: Component and platform labeling
            async function detectComponentPlatforms(apiData) {
              const labels = new Set();
              const componentRegex = /^esphome\/components\/([^\/]+)\//;
              const targetPlatformRegex = new RegExp(`^esphome\/components\/(${apiData.targetPlatforms.join('|')})/`);

              for (const file of changedFiles) {
                const componentMatch = file.match(componentRegex);
                if (componentMatch) {
                  labels.add(`component: ${componentMatch[1]}`);
                }

                const platformMatch = file.match(targetPlatformRegex);
                if (platformMatch) {
                  labels.add(`platform: ${platformMatch[1]}`);
                }
              }

              return labels;
            }

            // Strategy: New component detection
            async function detectNewComponents() {
              const labels = new Set();
              const addedFiles = prFiles.filter(file => file.status === 'added').map(file => file.filename);

              for (const file of addedFiles) {
                const componentMatch = file.match(/^esphome\/components\/([^\/]+)\/__init__\.py$/);
                if (componentMatch) {
                  try {
                    const content = fs.readFileSync(file, 'utf8');
                    if (content.includes('IS_TARGET_PLATFORM = True')) {
                      labels.add('new-target-platform');
                    }
                  } catch (error) {
                    console.log(`Failed to read content of ${file}:`, error.message);
                  }
                  labels.add('new-component');
                }
              }

              return labels;
            }

            // Strategy: New platform detection
            async function detectNewPlatforms(apiData) {
              const labels = new Set();
              const addedFiles = prFiles.filter(file => file.status === 'added').map(file => file.filename);

              for (const file of addedFiles) {
                const platformFileMatch = file.match(/^esphome\/components\/([^\/]+)\/([^\/]+)\.py$/);
                if (platformFileMatch) {
                  const [, component, platform] = platformFileMatch;
                  if (apiData.platformComponents.includes(platform)) {
                    labels.add('new-platform');
                  }
                }

                const platformDirMatch = file.match(/^esphome\/components\/([^\/]+)\/([^\/]+)\/__init__\.py$/);
                if (platformDirMatch) {
                  const [, component, platform] = platformDirMatch;
                  if (apiData.platformComponents.includes(platform)) {
                    labels.add('new-platform');
                  }
                }
              }

              return labels;
            }

            // Strategy: Core files detection
            async function detectCoreChanges() {
              const labels = new Set();
              const coreFiles = changedFiles.filter(file =>
                file.startsWith('esphome/core/') ||
                (file.startsWith('esphome/') && file.split('/').length === 2)
              );

              if (coreFiles.length > 0) {
                labels.add('core');
              }

              return labels;
            }

            // Strategy: PR size detection
            async function detectPRSize() {
              const labels = new Set();

              if (totalChanges <= SMALL_PR_THRESHOLD) {
                labels.add('small-pr');
                return labels;
              }

              const testAdditions = prFiles
                .filter(file => file.filename.startsWith('tests/'))
                .reduce((sum, file) => sum + (file.additions || 0), 0);
              const testDeletions = prFiles
                .filter(file => file.filename.startsWith('tests/'))
                .reduce((sum, file) => sum + (file.deletions || 0), 0);

              const nonTestChanges = (totalAdditions - testAdditions) - (totalDeletions - testDeletions);

              // Don't add too-big if mega-pr label is already present
              if (nonTestChanges > TOO_BIG_THRESHOLD && !isMegaPR) {
                labels.add('too-big');
              }

              return labels;
            }

            // Strategy: Dashboard changes
            async function detectDashboardChanges() {
              const labels = new Set();
              const dashboardFiles = changedFiles.filter(file =>
                file.startsWith('esphome/dashboard/') ||
                file.startsWith('esphome/components/dashboard_import/')
              );

              if (dashboardFiles.length > 0) {
                labels.add('dashboard');
              }

              return labels;
            }

            // Strategy: GitHub Actions changes
            async function detectGitHubActionsChanges() {
              const labels = new Set();
              const githubActionsFiles = changedFiles.filter(file =>
                file.startsWith('.github/workflows/')
              );

              if (githubActionsFiles.length > 0) {
                labels.add('github-actions');
              }

              return labels;
            }

            // Strategy: Code owner detection
            async function detectCodeOwner() {
              const labels = new Set();

              try {
                const { data: codeownersFile } = await github.rest.repos.getContent({
                  owner,
                  repo,
                  path: 'CODEOWNERS',
                });

                const codeownersContent = Buffer.from(codeownersFile.content, 'base64').toString('utf8');
                const prAuthor = context.payload.pull_request.user.login;

                const codeownersLines = codeownersContent.split('\n')
                  .map(line => line.trim())
                  .filter(line => line && !line.startsWith('#'));

                const codeownersRegexes = codeownersLines.map(line => {
                  const parts = line.split(/\s+/);
                  const pattern = parts[0];
                  const owners = parts.slice(1);

                  let regex;
                  if (pattern.endsWith('*')) {
                    const dir = pattern.slice(0, -1);
                    regex = new RegExp(`^${dir.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')}`);
                  } else if (pattern.includes('*')) {
                    // First escape all regex special chars except *, then replace * with .*
                    const regexPattern = pattern
                      .replace(/[.+?^${}()|[\]\\]/g, '\\$&')
                      .replace(/\*/g, '.*');
                    regex = new RegExp(`^${regexPattern}$`);
                  } else {
                    regex = new RegExp(`^${pattern.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')}$`);
                  }

                  return { regex, owners };
                });

                for (const file of changedFiles) {
                  for (const { regex, owners } of codeownersRegexes) {
                    if (regex.test(file) && owners.some(owner => owner === `@${prAuthor}`)) {
                      labels.add('by-code-owner');
                      return labels;
                    }
                  }
                }
              } catch (error) {
                console.log('Failed to read or parse CODEOWNERS file:', error.message);
              }

              return labels;
            }

            // Strategy: Test detection
            async function detectTests() {
              const labels = new Set();
              const testFiles = changedFiles.filter(file => file.startsWith('tests/'));

              if (testFiles.length > 0) {
                labels.add('has-tests');
              }

              return labels;
            }

            // Strategy: PR Template Checkbox detection
            async function detectPRTemplateCheckboxes() {
              const labels = new Set();
              const prBody = context.payload.pull_request.body || '';

              console.log('Checking PR template checkboxes...');

              // Check for checked checkboxes in the "Types of changes" section
              const checkboxPatterns = [
                { pattern: /- \[x\] Bugfix \(non-breaking change which fixes an issue\)/i, label: 'bugfix' },
                { pattern: /- \[x\] New feature \(non-breaking change which adds functionality\)/i, label: 'new-feature' },
                { pattern: /- \[x\] Breaking change \(fix or feature that would cause existing functionality to not work as expected\)/i, label: 'breaking-change' },
                { pattern: /- \[x\] Code quality improvements to existing code or addition of tests/i, label: 'code-quality' }
              ];

              for (const { pattern, label } of checkboxPatterns) {
                if (pattern.test(prBody)) {
                  console.log(`Found checked checkbox for: ${label}`);
                  labels.add(label);
                }
              }

              return labels;
            }

            // Strategy: Requirements detection
            async function detectRequirements(allLabels) {
              const labels = new Set();

              // Check for missing tests
              if ((allLabels.has('new-component') || allLabels.has('new-platform') || allLabels.has('new-feature')) && !allLabels.has('has-tests')) {
                labels.add('needs-tests');
              }

              // Check for missing docs
              if (allLabels.has('new-component') || allLabels.has('new-platform') || allLabels.has('new-feature')) {
                const prBody = context.payload.pull_request.body || '';
                const hasDocsLink = DOCS_PR_PATTERNS.some(pattern => pattern.test(prBody));

                if (!hasDocsLink) {
                  labels.add('needs-docs');
                }
              }

              // Check for missing CODEOWNERS
              if (allLabels.has('new-component')) {
                const codeownersModified = prFiles.some(file =>
                  file.filename === 'CODEOWNERS' &&
                  (file.status === 'modified' || file.status === 'added') &&
                  (file.additions || 0) > 0
                );

                if (!codeownersModified) {
                  labels.add('needs-codeowners');
                }
              }

              return labels;
            }

            // Generate review messages
            function generateReviewMessages(finalLabels) {
              const messages = [];
              const prAuthor = context.payload.pull_request.user.login;

              // Too big message
              if (finalLabels.includes('too-big')) {
                const testAdditions = prFiles
                  .filter(file => file.filename.startsWith('tests/'))
                  .reduce((sum, file) => sum + (file.additions || 0), 0);
                const testDeletions = prFiles
                  .filter(file => file.filename.startsWith('tests/'))
                  .reduce((sum, file) => sum + (file.deletions || 0), 0);
                const nonTestChanges = (totalAdditions - testAdditions) - (totalDeletions - testDeletions);

                const tooManyLabels = finalLabels.length > MAX_LABELS;
                const tooManyChanges = nonTestChanges > TOO_BIG_THRESHOLD;

                let message = `${TOO_BIG_MARKER}\n### 📦 Pull Request Size\n\n`;

                if (tooManyLabels && tooManyChanges) {
                  message += `This PR is too large with ${nonTestChanges} line changes (excluding tests) and affects ${finalLabels.length} different components/areas.`;
                } else if (tooManyLabels) {
                  message += `This PR affects ${finalLabels.length} different components/areas.`;
                } else {
                  message += `This PR is too large with ${nonTestChanges} line changes (excluding tests).`;
                }

                message += ` Please consider breaking it down into smaller, focused PRs to make review easier and reduce the risk of conflicts.\n\n`;
                message += `For guidance on breaking down large PRs, see: https://developers.esphome.io/contributing/submitting-your-work/#how-to-approach-large-submissions`;

                messages.push(message);
              }

              // CODEOWNERS message
              if (finalLabels.includes('needs-codeowners')) {
                const message = `${CODEOWNERS_MARKER}\n### 👥 Code Ownership\n\n` +
                  `Hey there @${prAuthor},\n` +
                  `Thanks for submitting this pull request! Can you add yourself as a codeowner for this integration? ` +
                  `This way we can notify you if a bug report for this integration is reported.\n\n` +
                  `In \`__init__.py\` of the integration, please add:\n\n` +
                  `\`\`\`python\nCODEOWNERS = ["@${prAuthor}"]\n\`\`\`\n\n` +
                  `And run \`script/build_codeowners.py\``;

                messages.push(message);
              }

              return messages;
            }

            // Handle reviews
            async function handleReviews(finalLabels) {
              const reviewMessages = generateReviewMessages(finalLabels);
              const hasReviewableLabels = finalLabels.some(label =>
                ['too-big', 'needs-codeowners'].includes(label)
              );

              const { data: reviews } = await github.rest.pulls.listReviews({
                owner,
                repo,
                pull_number: pr_number
              });

              const botReviews = reviews.filter(review =>
                review.user.type === 'Bot' &&
                review.state === 'CHANGES_REQUESTED' &&
                review.body && review.body.includes(BOT_COMMENT_MARKER)
              );

              if (hasReviewableLabels) {
                const reviewBody = `${BOT_COMMENT_MARKER}\n\n${reviewMessages.join('\n\n---\n\n')}`;

                if (botReviews.length > 0) {
                  // Update existing review
                  await github.rest.pulls.updateReview({
                    owner,
                    repo,
                    pull_number: pr_number,
                    review_id: botReviews[0].id,
                    body: reviewBody
                  });
                  console.log('Updated existing bot review');
                } else {
                  // Create new review
                  await github.rest.pulls.createReview({
                    owner,
                    repo,
                    pull_number: pr_number,
                    body: reviewBody,
                    event: 'REQUEST_CHANGES'
                  });
                  console.log('Created new bot review');
                }
              } else if (botReviews.length > 0) {
                // Dismiss existing reviews
                for (const review of botReviews) {
                  try {
                    await github.rest.pulls.dismissReview({
                      owner,
                      repo,
                      pull_number: pr_number,
                      review_id: review.id,
                      message: 'Review dismissed: All requirements have been met'
                    });
                    console.log(`Dismissed bot review ${review.id}`);
                  } catch (error) {
                    console.log(`Failed to dismiss review ${review.id}:`, error.message);
                  }
                }
              }
            }

            // Main execution
            const apiData = await fetchApiData();
            const baseRef = context.payload.pull_request.base.ref;

            // Early exit for release and beta branches only
            if (baseRef === 'release' || baseRef === 'beta') {
              const branchLabels = await detectMergeBranch();
              const finalLabels = Array.from(branchLabels);

              console.log('Computed labels (merge branch only):', finalLabels.join(', '));

              // Apply labels
              if (finalLabels.length > 0) {
                await github.rest.issues.addLabels({
                  owner,
                  repo,
                  issue_number: pr_number,
                  labels: finalLabels
                });
              }

              // Remove old managed labels
              const labelsToRemove = managedLabels.filter(label => !finalLabels.includes(label));
              for (const label of labelsToRemove) {
                try {
                  await github.rest.issues.removeLabel({
                    owner,
                    repo,
                    issue_number: pr_number,
                    name: label
                  });
                } catch (error) {
                  console.log(`Failed to remove label ${label}:`, error.message);
                }
              }

              return;
            }

            // Run all strategies
            const [
              branchLabels,
              componentLabels,
              newComponentLabels,
              newPlatformLabels,
              coreLabels,
              sizeLabels,
              dashboardLabels,
              actionsLabels,
              codeOwnerLabels,
              testLabels,
              checkboxLabels
            ] = await Promise.all([
              detectMergeBranch(),
              detectComponentPlatforms(apiData),
              detectNewComponents(),
              detectNewPlatforms(apiData),
              detectCoreChanges(),
              detectPRSize(),
              detectDashboardChanges(),
              detectGitHubActionsChanges(),
              detectCodeOwner(),
              detectTests(),
              detectPRTemplateCheckboxes()
            ]);

            // Combine all labels
            const allLabels = new Set([
              ...branchLabels,
              ...componentLabels,
              ...newComponentLabels,
              ...newPlatformLabels,
              ...coreLabels,
              ...sizeLabels,
              ...dashboardLabels,
              ...actionsLabels,
              ...codeOwnerLabels,
              ...testLabels,
              ...checkboxLabels
            ]);

            // Detect requirements based on all other labels
            const requirementLabels = await detectRequirements(allLabels);
            for (const label of requirementLabels) {
              allLabels.add(label);
            }

            let finalLabels = Array.from(allLabels);

            // For mega-PRs, exclude component labels if there are too many
            if (isMegaPR) {
              const componentLabels = finalLabels.filter(label => label.startsWith('component: '));
              if (componentLabels.length > COMPONENT_LABEL_THRESHOLD) {
                finalLabels = finalLabels.filter(label => !label.startsWith('component: '));
                console.log(`Mega-PR detected - excluding ${componentLabels.length} component labels (threshold: ${COMPONENT_LABEL_THRESHOLD})`);
              }
            }

            // Handle too many labels (only for non-mega PRs)
            const tooManyLabels = finalLabels.length > MAX_LABELS;

            if (tooManyLabels && !isMegaPR && !finalLabels.includes('too-big')) {
              finalLabels = ['too-big'];
            }

            console.log('Computed labels:', finalLabels.join(', '));

            // Handle reviews
            await handleReviews(finalLabels);

            // Apply labels
            if (finalLabels.length > 0) {
              console.log(`Adding labels: ${finalLabels.join(', ')}`);
              await github.rest.issues.addLabels({
                owner,
                repo,
                issue_number: pr_number,
                labels: finalLabels
              });
            }

            // Remove old managed labels
            const labelsToRemove = managedLabels.filter(label => !finalLabels.includes(label));
            for (const label of labelsToRemove) {
              console.log(`Removing label: ${label}`);
              try {
                await github.rest.issues.removeLabel({
                  owner,
                  repo,
                  issue_number: pr_number,
                  name: label
                });
              } catch (error) {
                console.log(`Failed to remove label ${label}:`, error.message);
              }
            }