donutbrowser/.github/workflows/duplicate-issues.yml

name: Duplicate Issue Check

on:
  issues:
    types: [opened, edited]

permissions:
  contents: read
  issues: write

env:
  MODEL: z-ai/glm-5.1

jobs:
  check-duplicates:
    if: github.repository == 'zhom/donutbrowser' && github.event.action == 'opened'
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

      - name: Gather context
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          ISSUE_NUMBER: ${{ github.event.issue.number }}
          ISSUE_TITLE: ${{ github.event.issue.title }}
          ISSUE_BODY: ${{ github.event.issue.body }}
        run: |
          printf '%s' "$ISSUE_TITLE" > /tmp/issue-title.txt
          printf '%s' "${ISSUE_BODY:-}" > /tmp/issue-body.txt

          # Pull up to 150 open/closed issues for the LLM to compare against.
          # Exclude the issue under inspection and any PRs (gh issue list does
          # this naturally).
          gh issue list \
            --repo "$GITHUB_REPOSITORY" \
            --state all \
            --limit 150 \
            --json number,title,state,body \
            --jq "[.[] | select(.number != $ISSUE_NUMBER) | {number, title, state, body: (.body[:400] // \"\")}]" \
            > /tmp/existing-issues.json

      - name: Build prompt
        run: |
          cat > /tmp/system.txt <<'PROMPT'
          You are reviewing a new GitHub issue for two things — template compliance and possible duplicates. Return ONLY a single JSON object, no prose, no markdown fences.

          Project: Donut Browser. There are three valid templates:
          - Bug Report (Description + Operating System + Donut Browser version + Which browser is affected + Steps to reproduce + Error logs/screenshots fields)
          - Feature Request (description + verification checkbox)
          - Question (free form)

          ## Compliance — flag NON-compliant ONLY when at least one of these is true
          - The issue body is empty or contains only placeholder text from the template
          - The issue is an obvious AI-generated wall of text with no real specifics
          - A bug report has no reproduction information or no error description
          - A feature request gives no use case at all
          - The author left required fields empty (Operating System, Donut Browser version, Which browser is affected, Steps to reproduce on bug reports)

          Do NOT flag for missing optional fields, missing screenshots, short titles, or stylistic issues. Be conservative.

          ## Duplicates — flag candidates ONLY when at least one of these is true
          - Same error message, exception, or symptom
          - Same feature being requested
          - Same root cause area (e.g. "proxy disconnects on Camoufox/Windows")

          Prefer false negatives over false positives. Two issues about Wayfern are not duplicates if they are about different features.

          ## Output schema
          {
            "is_compliant": true | false,
            "non_compliance_reasons": ["short bullet", ...],
            "duplicates": [{"number": 123, "reason": "short reason"}]
          }

          Empty arrays are fine. If there is nothing to flag, return:
          {"is_compliant": true, "non_compliance_reasons": [], "duplicates": []}
          PROMPT

      - name: Call OpenRouter
        env:
          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
        run: |
          PAYLOAD=$(jq -n \
            --arg model "$MODEL" \
            --rawfile system_prompt /tmp/system.txt \
            --rawfile title /tmp/issue-title.txt \
            --rawfile body /tmp/issue-body.txt \
            --rawfile existing /tmp/existing-issues.json \
            '{
              model: $model,
              messages: [
                { role: "system", content: $system_prompt },
                { role: "user",
                  content: ("New issue title: " + $title + "\n\nNew issue body:\n" + $body + "\n\nExisting issues (JSON array):\n" + $existing) }
              ],
              response_format: { type: "json_object" }
            }')

          RESPONSE=$(curl -fsSL https://openrouter.ai/api/v1/chat/completions \
            -H "Authorization: Bearer $OPENROUTER_API_KEY" \
            -H "Content-Type: application/json" \
            -d "$PAYLOAD")

          jq -r '.choices[0].message.content // empty' <<< "$RESPONSE" > /tmp/raw.txt

          # Strip accidental markdown fences and parse. On parse failure, fall back
          # to a noop result so the workflow doesn't fail the issue author's run.
          sed -E 's/^```(json)?$//; s/```$//' /tmp/raw.txt > /tmp/result.json
          if ! jq -e . /tmp/result.json >/dev/null 2>&1; then
            echo "::warning::Model returned non-JSON; treating as no-op"
            cat /tmp/raw.txt
            echo '{"is_compliant": true, "non_compliance_reasons": [], "duplicates": []}' > /tmp/result.json
          fi
          echo "Result:"
          cat /tmp/result.json

      - name: Build comment
        run: |
          python3 - <<'EOF'
          import json, os
          r = json.load(open('/tmp/result.json'))
          compliant = bool(r.get('is_compliant', True))
          reasons = r.get('non_compliance_reasons') or []
          dups = r.get('duplicates') or []

          parts = []
          if not compliant:
              parts.append('<!-- issue-compliance -->')
              parts.append("This issue doesn't fully meet our [contributing guidelines](../blob/main/CONTRIBUTING.md).")
              parts.append('')
              parts.append('**What needs to be fixed:**')
              for reason in reasons:
                  parts.append(f'- {reason}')
              parts.append('')
              parts.append('Please edit this issue to address the above within **24 hours**, or it will be automatically closed.')

          if dups:
              if parts:
                  parts.append('')
                  parts.append('---')
              parts.append('This issue might duplicate existing reports. Please check:')
              for d in dups:
                  num = d.get('number')
                  reason = d.get('reason', '').strip()
                  if num:
                      parts.append(f'- #{num}{" — " + reason if reason else ""}')

          if not compliant:
              parts.append('')
              parts.append('If you believe this was flagged incorrectly, please let a maintainer know.')

          comment = '\n'.join(parts).strip()
          open('/tmp/comment.md', 'w').write(comment)
          # Expose flags for downstream steps via GITHUB_OUTPUT-style write.
          with open(os.environ['GITHUB_OUTPUT'], 'a') as fh:
              fh.write(f'has_comment={"true" if comment else "false"}\n')
              fh.write(f'non_compliant={"true" if not compliant else "false"}\n')
          EOF
        id: build

      - name: Post comment
        if: steps.build.outputs.has_comment == 'true'
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          ISSUE_NUMBER: ${{ github.event.issue.number }}
        run: |
          gh issue comment "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" --body-file /tmp/comment.md

      - name: Apply needs:compliance label
        if: steps.build.outputs.non_compliant == 'true'
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          ISSUE_NUMBER: ${{ github.event.issue.number }}
        run: |
          gh issue edit "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" --add-label "needs:compliance"

  recheck-compliance:
    # When a flagged issue is edited, re-check. If now compliant: remove label,
    # delete the previous compliance comment, and thank the author. If still
    # non-compliant: leave label and post an updated note.
    if: >
      github.repository == 'zhom/donutbrowser' &&
      github.event.action == 'edited' &&
      contains(github.event.issue.labels.*.name, 'needs:compliance')
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

      - name: Gather context
        env:
          ISSUE_TITLE: ${{ github.event.issue.title }}
          ISSUE_BODY: ${{ github.event.issue.body }}
        run: |
          printf '%s' "$ISSUE_TITLE" > /tmp/issue-title.txt
          printf '%s' "${ISSUE_BODY:-}" > /tmp/issue-body.txt

      - name: Build prompt
        run: |
          cat > /tmp/system.txt <<'PROMPT'
          You are re-checking a GitHub issue that was previously flagged as not meeting template requirements. Return ONLY a single JSON object, no prose, no markdown fences.

          Project: Donut Browser. There are three valid templates:
          - Bug Report (Description + Operating System + Donut Browser version + Which browser is affected + Steps to reproduce + Error logs/screenshots fields)
          - Feature Request (description + verification checkbox)
          - Question (free form)

          ## Flag NON-compliant ONLY when at least one of these is true
          - The issue body is empty or contains only placeholder text from the template
          - The issue is an obvious AI-generated wall of text with no real specifics
          - A bug report has no reproduction information or no error description
          - A feature request gives no use case at all
          - The author left required fields empty (Operating System, Donut Browser version, Which browser is affected, Steps to reproduce on bug reports)

          Do NOT flag for missing optional fields, missing screenshots, short titles, or stylistic issues. Be conservative.

          ## Output schema
          {
            "is_compliant": true | false,
            "non_compliance_reasons": ["short bullet", ...]
          }
          PROMPT

      - name: Call OpenRouter
        env:
          OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
        run: |
          PAYLOAD=$(jq -n \
            --arg model "$MODEL" \
            --rawfile system_prompt /tmp/system.txt \
            --rawfile title /tmp/issue-title.txt \
            --rawfile body /tmp/issue-body.txt \
            '{
              model: $model,
              messages: [
                { role: "system", content: $system_prompt },
                { role: "user", content: ("Title: " + $title + "\n\nBody:\n" + $body) }
              ],
              response_format: { type: "json_object" }
            }')

          RESPONSE=$(curl -fsSL https://openrouter.ai/api/v1/chat/completions \
            -H "Authorization: Bearer $OPENROUTER_API_KEY" \
            -H "Content-Type: application/json" \
            -d "$PAYLOAD")

          jq -r '.choices[0].message.content // empty' <<< "$RESPONSE" > /tmp/raw.txt
          sed -E 's/^```(json)?$//; s/```$//' /tmp/raw.txt > /tmp/result.json
          if ! jq -e . /tmp/result.json >/dev/null 2>&1; then
            echo "::warning::Model returned non-JSON; assuming still non-compliant"
            echo '{"is_compliant": false, "non_compliance_reasons": ["unable to parse model output"]}' > /tmp/result.json
          fi

      - name: Resolve compliance state
        id: resolve
        run: |
          IS_COMPLIANT=$(jq -r '.is_compliant // false' /tmp/result.json)
          echo "is_compliant=$IS_COMPLIANT" >> "$GITHUB_OUTPUT"

      - name: Clear compliance label and acknowledge fix
        if: steps.resolve.outputs.is_compliant == 'true'
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          ISSUE_NUMBER: ${{ github.event.issue.number }}
        run: |
          gh issue edit "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" --remove-label "needs:compliance" || true

          # Delete the previous <!-- issue-compliance --> sentinel comment so
          # the thread is clean once the author has addressed the issue.
          COMMENT_ID=$(gh api "repos/$GITHUB_REPOSITORY/issues/$ISSUE_NUMBER/comments" \
            --jq '[.[] | select(.body | contains("<!-- issue-compliance -->"))][-1].id // empty')
          if [ -n "$COMMENT_ID" ]; then
            gh api -X DELETE "repos/$GITHUB_REPOSITORY/issues/comments/$COMMENT_ID" || true
          fi

          gh issue comment "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" \
            --body "Thanks for updating the issue."

      - name: Build follow-up comment
        if: steps.resolve.outputs.is_compliant != 'true'
        run: |
          python3 - <<'EOF'
          import json
          r = json.load(open('/tmp/result.json'))
          reasons = r.get('non_compliance_reasons') or []
          parts = [
            '<!-- issue-compliance -->',
            'This issue still does not meet our [contributing guidelines](../blob/main/CONTRIBUTING.md).',
            '',
            '**What still needs to be fixed:**',
          ]
          for reason in reasons:
              parts.append(f'- {reason}')
          parts.append('')
          parts.append('Please edit this issue to address the above within **24 hours**, or it will be automatically closed.')
          open('/tmp/comment.md', 'w').write('\n'.join(parts))
          EOF

      - name: Post follow-up comment
        if: steps.resolve.outputs.is_compliant != 'true'
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          ISSUE_NUMBER: ${{ github.event.issue.number }}
        run: |
          gh issue comment "$ISSUE_NUMBER" --repo "$GITHUB_REPOSITORY" --body-file /tmp/comment.md