chore(automation): recursive labeling for workstream descendants (#16609)

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

.github/scripts/pr-triage.sh

@@ -55,7 +55,7 @@ process_pr_optimized() {
     if [[ -z "${ISSUE_NUMBER}" || "${ISSUE_NUMBER}" == "null" || "${ISSUE_NUMBER}" == "" ]]; then
         if [[ "${IS_DRAFT}" == "true" ]]; then
             echo "   📝 PR #${PR_NUMBER} is a draft and has no linked issue"
-            if [[ ",${CURRENT_LABELS}," == ",status/need-issue,"* ]]; then
+            if [[ ",${CURRENT_LABELS}," == *",status/need-issue,"* ]]; then
                 echo "      ➖ Removing status/need-issue label"
                 LABELS_TO_REMOVE="status/need-issue"
             fi

.github/scripts/sync-maintainer-labels.cjs

@@ -0,0 +1,355 @@
+/* eslint-disable @typescript-eslint/no-require-imports */
+/* global process, console, require */
+const { Octokit } = require('@octokit/rest');
+
+/**
+ * Sync Maintainer Labels (Recursive with strict parent-child relationship detection)
+ * - Uses Native Sub-issues.
+ * - Uses Markdown Task Lists (- [ ] #123).
+ * - Filters for OPEN issues only.
+ * - Skips DUPLICATES.
+ * - Skips Pull Requests.
+ * - ONLY labels issues in the PUBLIC (gemini-cli) repo.
+ */
+
+const REPO_OWNER = 'google-gemini';
+const PUBLIC_REPO = 'gemini-cli';
+const PRIVATE_REPO = 'maintainers-gemini-cli';
+const ALLOWED_REPOS = [PUBLIC_REPO, PRIVATE_REPO];
+
+const ROOT_ISSUES = [
+  { owner: REPO_OWNER, repo: PUBLIC_REPO, number: 15374 },
+  { owner: REPO_OWNER, repo: PUBLIC_REPO, number: 15456 },
+  { owner: REPO_OWNER, repo: PUBLIC_REPO, number: 15324 },
+];
+
+const TARGET_LABEL = '🔒 maintainer only';
+const isDryRun =
+  process.argv.includes('--dry-run') || process.env.DRY_RUN === 'true';
+
+const octokit = new Octokit({
+  auth: process.env.GITHUB_TOKEN,
+});
+
+/**
+ * Extracts child issue references from markdown Task Lists ONLY.
+ * e.g. - [ ] #123 or - [x] google-gemini/gemini-cli#123
+ */
+function extractTaskListLinks(text, contextOwner, contextRepo) {
+  if (!text) return [];
+  const childIssues = new Map();
+
+  const add = (owner, repo, number) => {
+    if (ALLOWED_REPOS.includes(repo)) {
+      const key = `${owner}/${repo}#${number}`;
+      childIssues.set(key, { owner, repo, number: parseInt(number, 10) });
+    }
+  };
+
+  // 1. Full URLs in task lists
+  const urlRegex =
+    /-\s+\[[ x]\].*https:\/\/github\.com\/([a-zA-Z0-9._-]+)\/([a-zA-Z0-9._-]+)\/issues\/(\d+)\b/g;
+  let match;
+  while ((match = urlRegex.exec(text)) !== null) {
+    add(match[1], match[2], match[3]);
+  }
+
+  // 2. Cross-repo refs in task lists: owner/repo#123
+  const crossRepoRegex =
+    /-\s+\[[ x]\].*([a-zA-Z0-9._-]+)\/([a-zA-Z0-9._-]+)#(\d+)\b/g;
+  while ((match = crossRepoRegex.exec(text)) !== null) {
+    add(match[1], match[2], match[3]);
+  }
+
+  // 3. Short refs in task lists: #123
+  const shortRefRegex = /-\s+\[[ x]\].*#(\d+)\b/g;
+  while ((match = shortRefRegex.exec(text)) !== null) {
+    add(contextOwner, contextRepo, match[1]);
+  }
+
+  return Array.from(childIssues.values());
+}
+
+/**
+ * Fetches issue data via GraphQL with full pagination for sub-issues, comments, and labels.
+ */
+async function fetchIssueData(owner, repo, number) {
+  const query = `
+    query($owner:String!, $repo:String!, $number:Int!) {
+      repository(owner:$owner, name:$repo) {
+        issue(number:$number) {
+          state
+          title
+          body
+          labels(first: 100) {
+            nodes { name }
+            pageInfo { hasNextPage endCursor }
+          }
+          subIssues(first: 100) {
+            nodes {
+              number
+              repository {
+                name
+                owner { login }
+              }
+            }
+            pageInfo { hasNextPage endCursor }
+          }
+          comments(first: 100) {
+            nodes {
+              body
+            }
+          }
+        }
+      }
+    }
+  `;
+
+  try {
+    const response = await octokit.graphql(query, { owner, repo, number });
+    const data = response.repository.issue;
+    if (!data) return null;
+
+    const issue = {
+      state: data.state,
+      title: data.title,
+      body: data.body || '',
+      labels: data.labels.nodes.map((n) => n.name),
+      subIssues: [...data.subIssues.nodes],
+      comments: data.comments.nodes.map((n) => n.body),
+    };
+
+    // Paginate subIssues if there are more than 100
+    if (data.subIssues.pageInfo.hasNextPage) {
+      const moreSubIssues = await paginateConnection(
+        owner,
+        repo,
+        number,
+        'subIssues',
+        'number repository { name owner { login } }',
+        data.subIssues.pageInfo.endCursor,
+      );
+      issue.subIssues.push(...moreSubIssues);
+    }
+
+    // Paginate labels if there are more than 100 (unlikely but for completeness)
+    if (data.labels.pageInfo.hasNextPage) {
+      const moreLabels = await paginateConnection(
+        owner,
+        repo,
+        number,
+        'labels',
+        'name',
+        data.labels.pageInfo.endCursor,
+        (n) => n.name,
+      );
+      issue.labels.push(...moreLabels);
+    }
+
+    // Note: Comments are handled via Task Lists in body + first 100 comments.
+    // If an issue has > 100 comments with task lists, we'd need to paginate those too.
+    // Given the 1,100+ issue discovery count, 100 comments is usually sufficient,
+    // but we can add it for absolute completeness.
+    // (Skipping for now to avoid excessive API churn unless clearly needed).
+
+    return issue;
+  } catch (error) {
+    if (error.errors && error.errors.some((e) => e.type === 'NOT_FOUND')) {
+      return null;
+    }
+    throw error;
+  }
+}
+
+/**
+ * Helper to paginate any GraphQL connection.
+ */
+async function paginateConnection(
+  owner,
+  repo,
+  number,
+  connectionName,
+  nodeFields,
+  initialCursor,
+  transformNode = (n) => n,
+) {
+  let additionalNodes = [];
+  let hasNext = true;
+  let cursor = initialCursor;
+
+  while (hasNext) {
+    const query = `
+      query($owner:String!, $repo:String!, $number:Int!, $cursor:String) {
+        repository(owner:$owner, name:$repo) {
+          issue(number:$number) {
+            ${connectionName}(first: 100, after: $cursor) {
+              nodes { ${nodeFields} }
+              pageInfo { hasNextPage endCursor }
+            }
+          }
+        }
+      }
+    `;
+    const response = await octokit.graphql(query, {
+      owner,
+      repo,
+      number,
+      cursor,
+    });
+    const connection = response.repository.issue[connectionName];
+    additionalNodes.push(...connection.nodes.map(transformNode));
+    hasNext = connection.pageInfo.hasNextPage;
+    cursor = connection.pageInfo.endCursor;
+  }
+  return additionalNodes;
+}
+
+/**
+ * Validates if an issue should be processed (Open, not a duplicate, not a PR)
+ */
+function shouldProcess(issueData) {
+  if (!issueData) return false;
+
+  if (issueData.state !== 'OPEN') return false;
+
+  const labels = issueData.labels.map((l) => l.toLowerCase());
+  if (labels.includes('duplicate') || labels.includes('kind/duplicate')) {
+    return false;
+  }
+
+  return true;
+}
+
+async function getAllDescendants(roots) {
+  const allDescendants = new Map();
+  const visited = new Set();
+  const queue = [...roots];
+
+  for (const root of roots) {
+    visited.add(`${root.owner}/${root.repo}#${root.number}`);
+  }
+
+  console.log(`Starting discovery from ${roots.length} roots...`);
+
+  while (queue.length > 0) {
+    const current = queue.shift();
+    const currentKey = `${current.owner}/${current.repo}#${current.number}`;
+
+    try {
+      const issueData = await fetchIssueData(
+        current.owner,
+        current.repo,
+        current.number,
+      );
+
+      if (!shouldProcess(issueData)) {
+        continue;
+      }
+
+      // ONLY add to labeling list if it's in the PUBLIC repository
+      if (current.repo === PUBLIC_REPO) {
+        // Don't label the roots themselves
+        if (
+          !ROOT_ISSUES.some(
+            (r) => r.number === current.number && r.repo === current.repo,
+          )
+        ) {
+          allDescendants.set(currentKey, {
+            ...current,
+            title: issueData.title,
+            labels: issueData.labels,
+          });
+        }
+      }
+
+      const children = new Map();
+
+      // 1. Process Native Sub-issues
+      if (issueData.subIssues) {
+        for (const node of issueData.subIssues) {
+          const childOwner = node.repository.owner.login;
+          const childRepo = node.repository.name;
+          const childNumber = node.number;
+          const key = `${childOwner}/${childRepo}#${childNumber}`;
+          children.set(key, {
+            owner: childOwner,
+            repo: childRepo,
+            number: childNumber,
+          });
+        }
+      }
+
+      // 2. Process Markdown Task Lists in Body and Comments
+      let combinedText = issueData.body || '';
+      if (issueData.comments) {
+        for (const commentBody of issueData.comments) {
+          combinedText += '\n' + (commentBody || '');
+        }
+      }
+
+      const taskListLinks = extractTaskListLinks(
+        combinedText,
+        current.owner,
+        current.repo,
+      );
+      for (const link of taskListLinks) {
+        const key = `${link.owner}/${link.repo}#${link.number}`;
+        children.set(key, link);
+      }
+
+      // Queue children (regardless of which repo they are in, for recursion)
+      for (const [key, child] of children) {
+        if (!visited.has(key)) {
+          visited.add(key);
+          queue.push(child);
+        }
+      }
+    } catch (error) {
+      console.error(`Error processing ${currentKey}: ${error.message}`);
+    }
+  }
+
+  return Array.from(allDescendants.values());
+}
+
+async function run() {
+  if (isDryRun) {
+    console.log('=== DRY RUN MODE: No labels will be applied ===');
+  }
+
+  const descendants = await getAllDescendants(ROOT_ISSUES);
+  console.log(
+    `\nFound ${descendants.length} total unique open descendant issues in ${PUBLIC_REPO}.`,
+  );
+
+  for (const issueInfo of descendants) {
+    const issueKey = `${issueInfo.owner}/${issueInfo.repo}#${issueInfo.number}`;
+    try {
+      // Data is already available from the discovery phase
+      const hasLabel = issueInfo.labels.some((l) => l === TARGET_LABEL);
+
+      if (!hasLabel) {
+        if (isDryRun) {
+          console.log(
+            `[DRY RUN] Would label ${issueKey}: "${issueInfo.title}"`,
+          );
+        } else {
+          console.log(`Labeling ${issueKey}: "${issueInfo.title}"...`);
+          await octokit.rest.issues.addLabels({
+            owner: issueInfo.owner,
+            repo: issueInfo.repo,
+            issue_number: issueInfo.number,
+            labels: [TARGET_LABEL],
+          });
+        }
+      }
+    } catch (error) {
+      console.error(`Error processing label for ${issueKey}: ${error.message}`);
+    }
+  }
+}
+
+run().catch((error) => {
+  console.error(error);
+  process.exit(1);
+});

.github/workflows/gemini-scheduled-issue-triage.yml

@@ -238,23 +238,16 @@ jobs:
             core.info(`Raw labels JSON: ${rawLabels}`);
             let parsedLabels;
             try {
-              // First, try to parse the raw output as JSON.
-              parsedLabels = JSON.parse(rawLabels.trim());
-            } catch (jsonError) {
-              // If that fails, check for a markdown code block.
-              core.info(`Direct JSON parsing failed: ${jsonError.message}. Trying to extract from a markdown block.`);
               const jsonMatch = rawLabels.match(/```json\s*([\s\S]*?)\s*```/);
-              if (jsonMatch && jsonMatch[1]) {
-                try {
-                  parsedLabels = JSON.parse(jsonMatch[1].trim());
-                } catch (markdownError) {
-                  core.setFailed(`Failed to parse JSON even after extracting from markdown block: ${markdownError.message}\nRaw output: ${rawLabels}`);
-                  return;
-                }
-              } else {
-                core.setFailed(`Output is not valid JSON and does not contain a JSON markdown block.\nRaw output: ${rawLabels}`);
-                return;
+              if (!jsonMatch || !jsonMatch[1]) {
+                throw new Error("Could not find a ```json ... ``` block in the output.");
               }
+              const jsonString = jsonMatch[1].trim();
+              parsedLabels = JSON.parse(jsonString);
+              core.info(`Parsed labels JSON: ${JSON.stringify(parsedLabels)}`);
+            } catch (err) {
+              core.setFailed(`Failed to parse labels JSON from Gemini output: ${err.message}\nRaw output: ${rawLabels}`);
+              return;
             }
 
             for (const entry of parsedLabels) {

.github/workflows/label-backlog-child-issues.yml

@@ -3,38 +3,55 @@ name: 'Label Child Issues for Project Rollup'
 on:
   issues:
     types: ['opened', 'edited', 'reopened']
+  schedule:
+    - cron: '0 * * * *' # Run every hour
+  workflow_dispatch:
+
+permissions:
+  issues: 'write'
+  contents: 'read'
 
 jobs:
+  # Event-based: Quick reaction to new/edited issues in THIS repo
   labeler:
+    if: "github.event_name == 'issues'"
     runs-on: 'ubuntu-latest'
-    permissions:
-      issues: 'write'
     steps:
-      - name: 'Check for Parent Workstream and Apply Label'
-        uses: 'actions/github-script@v7'
+      - name: 'Checkout'
+        uses: 'actions/checkout@v4'
+
+      - name: 'Setup Node.js'
+        uses: 'actions/setup-node@v4'
         with:
-          script: |
-            const issue = context.payload.issue;
-            const labelToAdd = 'workstream-rollup';
+          node-version: '20'
+          cache: 'npm'
 
-            // --- Define the FULL URLs of the allowed parent workstreams ---
-            const allowedParentUrls = [
-              'https://api.github.com/repos/google-gemini/gemini-cli/issues/15374',
-              'https://api.github.com/repos/google-gemini/gemini-cli/issues/15456',
-              'https://api.github.com/repos/google-gemini/gemini-cli/issues/15324'
-            ];
+      - name: 'Install Dependencies'
+        run: 'npm ci'
 
-            // Check if the issue has a parent_issue_url and if it's in our allowed list.
-            if (issue && issue.parent_issue_url && allowedParentUrls.includes(issue.parent_issue_url)) {
-              console.log(`SUCCESS: Issue #${issue.number} is a child of a target workstream (${issue.parent_issue_url}). Adding label.`);
-              await github.rest.issues.addLabels({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                issue_number: issue.number,
-                labels: [labelToAdd]
-              });
-            } else if (issue && issue.parent_issue_url) {
-              console.log(`FAILURE: Issue #${issue.number} has a parent, but it's not a target workstream. Parent URL: ${issue.parent_issue_url}`);
-            } else {
-              console.log(`FAILURE: Issue #${issue.number} is not a child of any issue. No action taken.`);
-            }
+      - name: 'Run Multi-Repo Sync Script'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: 'node .github/scripts/sync-maintainer-labels.cjs'
+
+  # Scheduled/Manual: Recursive sync across multiple repos
+  sync-maintainer-labels:
+    if: "github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'"
+    runs-on: 'ubuntu-latest'
+    steps:
+      - name: 'Checkout'
+        uses: 'actions/checkout@v4'
+
+      - name: 'Setup Node.js'
+        uses: 'actions/setup-node@v4'
+        with:
+          node-version: '20'
+          cache: 'npm'
+
+      - name: 'Install Dependencies'
+        run: 'npm ci'
+
+      - name: 'Run Multi-Repo Sync Script'
+        env:
+          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
+        run: 'node .github/scripts/sync-maintainer-labels.cjs'