issue-pr-bot.yml

name: Issue and PR Duplicate Detection Bot

on:
  issues:
    types: [opened]
  pull_request:
    types: [opened]

permissions:
  contents: read
  issues: write
  pull-requests: write

jobs:
  duplicate-check:
    name: Check for Duplicates
    runs-on: ubuntu-latest

    steps:
      - name: Detect duplicates and triage
        uses: actions/github-script@v7
        with:
          script: |
            const DUPLICATE_LABEL   = 'duplicate';
            const TRIAGE_LABEL      = 'needs-triage';
            // Minimum fraction of shared keywords to consider two items duplicates.
            const SIMILARITY_THRESHOLD = 0.3;
            // Stop words that carry no semantic meaning for matching.
            const STOP_WORDS = new Set([
              'a','an','the','and','or','but','in','on','at','to','for','of',
              'with','is','are','was','were','be','been','being','have','has',
              'had','do','does','did','will','would','could','should','may',
              'might','shall','can','not','no','this','that','it','its',
              'i','we','you','he','she','they','my','your','our','their',
              'how','what','when','where','why','which','who','whom',
            ]);

            const isPR = !!context.payload.pull_request;
            const item = isPR ? context.payload.pull_request : context.payload.issue;
            const itemNumber = item.number;
            const itemTitle  = (item.title  || '').toLowerCase();
            const itemBody   = (item.body   || '').toLowerCase();
            const itemText   = `${itemTitle} ${itemBody}`;

            // ── helpers ──────────────────────────────────────────────────────
            function tokenize(text) {
              return new Set(
                text
                  .replace(/[^a-z0-9\s]/g, ' ')
                  .split(/\s+/)
                  .filter(w => w.length > 2 && !STOP_WORDS.has(w))
              );
            }

            function jaccardSimilarity(setA, setB) {
              // Two empty token sets share no meaningful keywords — treat as dissimilar
              // so that blank issues are not flagged as duplicates of each other.
              if (setA.size === 0 || setB.size === 0) return 0;
              const intersection = [...setA].filter(w => setB.has(w)).length;
              const union = new Set([...setA, ...setB]).size;
              return intersection / union;
            }

            // ── ensure required labels exist ─────────────────────────────────
            async function ensureLabel(name, color, description) {
              try {
                await github.rest.issues.getLabel({
                  owner: context.repo.owner,
                  repo:  context.repo.repo,
                  name,
                });
              } catch (err) {
                if (err.status === 404) {
                  await github.rest.issues.createLabel({
                    owner: context.repo.owner,
                    repo:  context.repo.repo,
                    name,
                    color,
                    description,
                  });
                } else {
                  throw err;
                }
              }
            }

            await ensureLabel(DUPLICATE_LABEL, 'cfd3d7', 'This issue or PR is a duplicate of another');
            await ensureLabel(TRIAGE_LABEL,    'e4e669', 'Needs triage by a maintainer');

            // ── fetch existing open issues (excluding the current one) ───────
            const existingItems = await github.paginate(
              github.rest.issues.listForRepo,
              {
                owner:    context.repo.owner,
                repo:     context.repo.repo,
                state:    'open',
                per_page: 100,
              }
            );

            const candidates = existingItems.filter(i => i.number !== itemNumber);

            // ── compare against each candidate ───────────────────────────────
            const newTokens = tokenize(itemText);
            let bestMatch   = null;
            let bestScore   = 0;

            for (const candidate of candidates) {
              const candidateText = `${(candidate.title || '').toLowerCase()} ${(candidate.body || '').toLowerCase()}`;
              const candidateTokens = tokenize(candidateText);
              const score = jaccardSimilarity(newTokens, candidateTokens);

              if (score > bestScore) {
                bestScore = score;
                bestMatch = candidate;
              }
            }

            const isDuplicate = bestScore >= SIMILARITY_THRESHOLD;
            const itemType    = isPR ? 'Pull Request' : 'Issue';

            // ── act on result ────────────────────────────────────────────────
            if (isDuplicate) {
              core.info(`Duplicate detected: #${bestMatch.number} (score ${bestScore.toFixed(3)})`);

              // Add 'duplicate' label
              await github.rest.issues.addLabels({
                owner:        context.repo.owner,
                repo:         context.repo.repo,
                issue_number: itemNumber,
                labels:       [DUPLICATE_LABEL],
              });

              // Post duplicate comment
              await github.rest.issues.createComment({
                owner:        context.repo.owner,
                repo:         context.repo.repo,
                issue_number: itemNumber,
                body: [
                  `⚠️ This looks like a duplicate of #${bestMatch.number}.`,
                  '',
                  `Please check that ${bestMatch.pull_request ? 'PR' : 'issue'} for updates and continue the discussion there.`,
                  'If you believe this is **not** a duplicate, please leave a comment explaining the difference and a maintainer will re-triage.',
                ].join('\n'),
              });

            } else {
              core.info(`No duplicate found (best score ${bestScore.toFixed(3)})`);

              // Add 'needs-triage' label
              await github.rest.issues.addLabels({
                owner:        context.repo.owner,
                repo:         context.repo.repo,
                issue_number: itemNumber,
                labels:       [TRIAGE_LABEL],
              });

              // Post welcome / acknowledgement comment
              const welcomeLines = [
                `👋 Thanks for opening this ${itemType}!`,
                '',
                'A maintainer will review it shortly. In the meantime:',
                '',
                '- Please make sure your description is as detailed as possible.',
                '- Search existing issues at https://github.com/' + context.repo.owner + '/' + context.repo.repo + '/issues to avoid duplicates.',
                '- Follow the contribution guidelines if they apply.',
              ];
              await github.rest.issues.createComment({
                owner:        context.repo.owner,
                repo:         context.repo.repo,
                issue_number: itemNumber,
                body:         welcomeLines.join('\n'),
              });
            }