name: Claude Issue Dedupe
description: Automatically dedupe GitHub issues using Claude Code
on:
  issues:
    types: [opened]
  workflow_dispatch:
    inputs:
      issue_number:
        description: 'Issue number to process for duplicate detection'
        required: true
        type: string

jobs:
  claude-dedupe-issues:
    runs-on: ubuntu-latest
    timeout-minutes: 10
    permissions:
      contents: read
      issues: write

    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Run Claude Code slash command
        id: claude
        uses: anthropics/claude-code-base-action@beta
        with:
          prompt: "/dedupe ${{ github.repository }}/issues/${{ github.event.issue.number || inputs.issue_number }}"
          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
          claude_args: "--model claude-sonnet-4-5-20250929"
          # Note: GH_TOKEN only provides read access for issue viewing/searching
          # Comment posting is handled in a separate isolated step below
          claude_env: |
            GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

      # SECURITY: This step runs in isolation without access to ANTHROPIC_API_KEY
      # It only has GITHUB_TOKEN for posting comments, preventing secret exfiltration
      - name: Post duplicate comment (isolated from API key)
        if: success()
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          ISSUE_NUMBER=${{ github.event.issue.number || inputs.issue_number }}
          RESULT_FILE="/tmp/dedupe-result.json"

          if [ ! -f "$RESULT_FILE" ]; then
            echo "No dedupe result file found, skipping comment"
            exit 0
          fi

          # Check if we should skip
          if jq -e '.skip' "$RESULT_FILE" > /dev/null 2>&1; then
            REASON=$(jq -r '.reason // "unknown"' "$RESULT_FILE")
            echo "Skipping comment: $REASON"
            exit 0
          fi

          # Get duplicates array
          DUPLICATES=$(jq -r '.duplicates // []' "$RESULT_FILE")
          COUNT=$(echo "$DUPLICATES" | jq 'length')

          if [ "$COUNT" -eq 0 ]; then
            echo "No duplicates found, skipping comment"
            exit 0
          fi

          # Build comment body (limit to 3 duplicates for safety)
          SAFE_COUNT=$((COUNT > 3 ? 3 : COUNT))

          COMMENT="Found $SAFE_COUNT possible duplicate issue"
          if [ "$SAFE_COUNT" -ne 1 ]; then
            COMMENT="${COMMENT}s"
          fi
          COMMENT="${COMMENT}:"
          COMMENT="${COMMENT}
          "

          for i in $(seq 0 $((SAFE_COUNT - 1))); do
            URL=$(echo "$DUPLICATES" | jq -r ".[$i]")
            # Validate URL format to prevent injection
            if [[ "$URL" =~ ^https://github\.com/[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+/issues/[0-9]+$ ]]; then
              COMMENT="${COMMENT}
          $((i + 1)). $URL"
            fi
          done

          COMMENT="${COMMENT}

          This issue will be automatically closed as a duplicate in 3 days.

          - If your issue is a duplicate, please close it and 👍 the existing issue instead
          - To prevent auto-closure, add a comment or 👎 this comment

          🤖 Generated with [Claude Code](https://claude.ai/code)"

          # Post the comment
          gh issue comment "$ISSUE_NUMBER" --repo "${{ github.repository }}" --body "$COMMENT"
          echo "Posted duplicate comment on issue #$ISSUE_NUMBER"

      - name: Log duplicate comment event to Statsig
        if: always()
        env:
          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}
        run: |
          ISSUE_NUMBER=${{ github.event.issue.number || inputs.issue_number }}
          REPO=${{ github.repository }}
          
          if [ -z "$STATSIG_API_KEY" ]; then
            echo "STATSIG_API_KEY not found, skipping Statsig logging"
            exit 0
          fi
          
          # Prepare the event payload
          EVENT_PAYLOAD=$(jq -n \
            --arg issue_number "$ISSUE_NUMBER" \
            --arg repo "$REPO" \
            --arg triggered_by "${{ github.event_name }}" \
            '{
              events: [{
                eventName: "github_duplicate_comment_added",
                value: 1,
                metadata: {
                  repository: $repo,
                  issue_number: ($issue_number | tonumber),
                  triggered_by: $triggered_by,
                  workflow_run_id: "${{ github.run_id }}"
                },
                time: (now | floor | tostring)
              }]
            }')
          
          # Send to Statsig API
          echo "Logging duplicate comment event to Statsig for issue #${ISSUE_NUMBER}"
          
          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST https://events.statsigapi.net/v1/log_event \
            -H "Content-Type: application/json" \
            -H "STATSIG-API-KEY: ${STATSIG_API_KEY}" \
            -d "$EVENT_PAYLOAD")
          
          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
          BODY=$(echo "$RESPONSE" | head -n-1)
          
          if [ "$HTTP_CODE" -eq 200 ] || [ "$HTTP_CODE" -eq 202 ]; then
            echo "Successfully logged duplicate comment event for issue #${ISSUE_NUMBER}"
          else
            echo "Failed to log duplicate comment event for issue #${ISSUE_NUMBER}. HTTP ${HTTP_CODE}: ${BODY}"
          fi