Implement smart duplicate detection for triage script

- Auto-detects ALL duplicate issue titles without requiring manual config - Groups duplicates by title and processes each group - Keeps most recent issue open, closes all duplicates - Supports optional SEARCH_TITLE filter for specific titles - All tests passing Co-authored-by: johndoe6345789 <224850594+johndoe6345789@users.noreply.github.com>
2026-04-24 13:54:57 +00:00 · 2025-12-27 18:16:21 +00:00
parent 8d67fe8a49
commit 1081dc8934
2 changed files with 325 additions and 137 deletions
--- a/scripts/test-triage-logic.sh
+++ b/scripts/test-triage-logic.sh
@@ -12,6 +12,35 @@ echo ""
 # Source the functions we need to test (extract them from the main script)
 # For testing, we'll recreate them here

+get_issues_by_title() {
+  local issues_data="$1"
+  local title="$2"
+  
+  # Filter issues matching the exact title and sort by date (newest first)
+  echo "$issues_data" | grep -F "|$title" | sort -t'|' -k2 -r
+}
+
+find_duplicate_titles() {
+  local issues_data="$1"
+  local search_filter="$2"
+  
+  if [ -z "$issues_data" ]; then
+    return 0
+  fi
+  
+  # Extract unique titles and count occurrences
+  local title_counts
+  if [ -n "$search_filter" ]; then
+    # Filter by specific title if provided
+    title_counts=$(echo "$issues_data" | cut -d'|' -f3- | grep -F "$search_filter" | sort | uniq -c | awk '$1 > 1 {$1=""; print substr($0,2)}')
+  else
+    # Find all duplicate titles
+    title_counts=$(echo "$issues_data" | cut -d'|' -f3- | sort | uniq -c | awk '$1 > 1 {$1=""; print substr($0,2)}')
+  fi
+  
+  echo "$title_counts"
+}
+
 get_issues_to_close() {
  local issues_data="$1"
  
@@ -31,18 +60,80 @@ get_issues_to_close() {
  echo "$issues_data" | tail -n +2 | cut -d'|' -f1
 }

-# Test 1: Multiple duplicate issues
-echo "Test 1: Multiple duplicate issues (should close all except most recent)"
+# Test 1: Finding duplicate titles across multiple groups
+echo "Test 1: Finding duplicate titles from mixed issues"
+echo "---------------------------------------------------"
+TEST_DATA='199|2025-12-27T18:12:06Z|⚠️ Pre-Deployment Validation Failed
+195|2025-12-27T18:09:38Z|⚠️ Pre-Deployment Validation Failed
+194|2025-12-27T18:01:57Z|⚠️ Pre-Deployment Validation Failed
+100|2025-12-27T10:00:00Z|🚨 Production Deployment Failed
+99|2025-12-27T09:00:00Z|🚨 Production Deployment Failed
+50|2025-12-26T12:00:00Z|Unique issue without duplicates'
+
+DUPLICATES=$(find_duplicate_titles "$TEST_DATA" "")
+DUP_COUNT=$(echo "$DUPLICATES" | wc -l)
+
+echo "  Found duplicate title groups: $DUP_COUNT"
+echo "  Titles with duplicates:"
+while IFS= read -r dup_title; do
+  echo "    - \"$dup_title\""
+done <<< "$DUPLICATES"
+
+if [ "$DUP_COUNT" = "2" ]; then
+  echo "  ✅ PASS: Correctly found 2 groups of duplicates"
+else
+  echo "  ❌ FAIL: Expected 2 duplicate groups, got $DUP_COUNT"
+  exit 1
+fi
+echo ""
+
+# Test 2: Filtering for specific title
+echo "Test 2: Filtering for specific duplicate title"
+echo "----------------------------------------------"
+FILTERED=$(find_duplicate_titles "$TEST_DATA" "Pre-Deployment")
+FILTERED_COUNT=$(echo "$FILTERED" | wc -l)
+
+echo "  Filtered to titles containing 'Pre-Deployment': $FILTERED_COUNT group(s)"
+if [ "$FILTERED_COUNT" = "1" ]; then
+  echo "  ✅ PASS: Correctly filtered to 1 specific title"
+else
+  echo "  ❌ FAIL: Expected 1 filtered title, got $FILTERED_COUNT"
+  exit 1
+fi
+echo ""
+
+# Test 3: Getting issues by specific title
+echo "Test 3: Getting issues by specific title"
+echo "----------------------------------------"
+TITLE="⚠️ Pre-Deployment Validation Failed"
+TITLE_ISSUES=$(get_issues_by_title "$TEST_DATA" "$TITLE")
+TITLE_COUNT=$(echo "$TITLE_ISSUES" | wc -l)
+MOST_RECENT=$(echo "$TITLE_ISSUES" | head -1 | cut -d'|' -f1)
+
+echo "  Title: \"$TITLE\""
+echo "  Issues found: $TITLE_COUNT"
+echo "  Most recent: #$MOST_RECENT"
+
+if [ "$TITLE_COUNT" = "3" ] && [ "$MOST_RECENT" = "199" ]; then
+  echo "  ✅ PASS: Correctly found 3 issues, most recent is #199"
+else
+  echo "  ❌ FAIL: Expected 3 issues with most recent #199"
+  exit 1
+fi
+echo ""
+
+# Test 4: Multiple duplicate issues
+echo "Test 4: Multiple duplicate issues (should close all except most recent)"
 echo "-----------------------------------------------------------------------"
-TEST_DATA_1='124|2025-12-27T10:30:00Z|🚨 Production Deployment Failed
+TEST_DATA_4='124|2025-12-27T10:30:00Z|🚨 Production Deployment Failed
 122|2025-12-27T10:25:00Z|🚨 Production Deployment Failed
 121|2025-12-27T10:20:00Z|🚨 Production Deployment Failed
 119|2025-12-27T10:15:00Z|🚨 Production Deployment Failed
 117|2025-12-27T10:10:00Z|🚨 Production Deployment Failed'

-TOTAL=$(echo "$TEST_DATA_1" | wc -l)
-MOST_RECENT=$(echo "$TEST_DATA_1" | head -1 | cut -d'|' -f1)
-TO_CLOSE=$(get_issues_to_close "$TEST_DATA_1")
+TOTAL=$(echo "$TEST_DATA_4" | wc -l)
+MOST_RECENT=$(echo "$TEST_DATA_4" | head -1 | cut -d'|' -f1)
+TO_CLOSE=$(get_issues_to_close "$TEST_DATA_4")
 TO_CLOSE_COUNT=$(echo "$TO_CLOSE" | wc -l)

 echo "  Total issues found: $TOTAL"
@@ -58,15 +149,15 @@ else
 fi
 echo ""

-# Test 2: Two duplicate issues
-echo "Test 2: Two duplicate issues (should close oldest, keep newest)"
+# Test 5: Two duplicate issues
+echo "Test 5: Two duplicate issues (should close oldest, keep newest)"
 echo "----------------------------------------------------------------"
-TEST_DATA_2='150|2025-12-27T11:00:00Z|Bug in login
+TEST_DATA_5='150|2025-12-27T11:00:00Z|Bug in login
 148|2025-12-27T10:55:00Z|Bug in login'

-TOTAL=$(echo "$TEST_DATA_2" | wc -l)
-MOST_RECENT=$(echo "$TEST_DATA_2" | head -1 | cut -d'|' -f1)
-TO_CLOSE=$(get_issues_to_close "$TEST_DATA_2")
+TOTAL=$(echo "$TEST_DATA_5" | wc -l)
+MOST_RECENT=$(echo "$TEST_DATA_5" | head -1 | cut -d'|' -f1)
+TO_CLOSE=$(get_issues_to_close "$TEST_DATA_5")
 TO_CLOSE_COUNT=$(echo "$TO_CLOSE" | wc -l)

 echo "  Total issues found: $TOTAL"
@@ -82,14 +173,14 @@ else
 fi
 echo ""

-# Test 3: Single issue
-echo "Test 3: Single issue (should not close anything)"
+# Test 6: Single issue
+echo "Test 6: Single issue (should not close anything)"
 echo "-------------------------------------------------"
-TEST_DATA_3='200|2025-12-27T12:00:00Z|Unique issue'
+TEST_DATA_6='200|2025-12-27T12:00:00Z|Unique issue'

-TOTAL=$(echo "$TEST_DATA_3" | wc -l)
-MOST_RECENT=$(echo "$TEST_DATA_3" | head -1 | cut -d'|' -f1)
-TO_CLOSE=$(get_issues_to_close "$TEST_DATA_3" 2>&1)
+TOTAL=$(echo "$TEST_DATA_6" | wc -l)
+MOST_RECENT=$(echo "$TEST_DATA_6" | head -1 | cut -d'|' -f1)
+TO_CLOSE=$(get_issues_to_close "$TEST_DATA_6" 2>&1)

 echo "  Total issues found: $TOTAL"
 echo "  Most recent issue: #$MOST_RECENT"
@@ -102,8 +193,8 @@ else
 fi
 echo ""

-# Test 4: Empty input
-echo "Test 4: Empty input (should handle gracefully)"
+# Test 7: Empty input
+echo "Test 7: Empty input (should handle gracefully)"
 echo "----------------------------------------------"
 TO_CLOSE=$(get_issues_to_close "" 2>&1)

@@ -115,44 +206,19 @@ else
 fi
 echo ""

-# Test 5: Date parsing and sorting verification
-echo "Test 5: Verify sorting by creation date (newest first)"
-echo "-------------------------------------------------------"
-TEST_DATA_5='300|2025-12-27T15:00:00Z|Issue C
+# Test 8: No duplicates in repository
+echo "Test 8: No duplicates (all unique titles)"
+echo "-----------------------------------------"
+TEST_DATA_8='300|2025-12-27T15:00:00Z|Issue C
 299|2025-12-27T14:00:00Z|Issue B
 298|2025-12-27T13:00:00Z|Issue A'

-MOST_RECENT=$(echo "$TEST_DATA_5" | head -1 | cut -d'|' -f1)
-MOST_RECENT_DATE=$(echo "$TEST_DATA_5" | head -1 | cut -d'|' -f2)
-OLDEST=$(echo "$TEST_DATA_5" | tail -1 | cut -d'|' -f1)
+DUPLICATES=$(find_duplicate_titles "$TEST_DATA_8" "")

-echo "  Most recent: #$MOST_RECENT at $MOST_RECENT_DATE"
-echo "  Oldest: #$OLDEST"
-
-if [ "$MOST_RECENT" = "300" ] && [ "$OLDEST" = "298" ]; then
-  echo "  ✅ PASS: Correctly sorted by date (newest first)"
+if [ -z "$DUPLICATES" ]; then
+  echo "  ✅ PASS: Correctly found no duplicates"
 else
-  echo "  ❌ FAIL: Sorting is incorrect"
-  exit 1
-fi
-echo ""
-
-# Test 6: jq parsing simulation (test data format)
-echo "Test 6: Verify data format compatibility with jq"
-echo "-------------------------------------------------"
-MOCK_JSON='{"items": [
-  {"number": 124, "created_at": "2025-12-27T10:30:00Z", "title": "Test"},
-  {"number": 122, "created_at": "2025-12-27T10:25:00Z", "title": "Test"}
-]}'
-
-# Test that jq can parse and format the data correctly
-PARSED=$(echo "$MOCK_JSON" | jq -r '.items | sort_by(.created_at) | reverse | .[] | "\(.number)|\(.created_at)|\(.title)"')
-FIRST_ISSUE=$(echo "$PARSED" | head -1 | cut -d'|' -f1)
-
-if [ "$FIRST_ISSUE" = "124" ]; then
-  echo "  ✅ PASS: jq parsing and formatting works correctly"
-else
-  echo "  ❌ FAIL: jq parsing failed"
+  echo "  ❌ FAIL: Should find no duplicates with all unique titles"
  exit 1
 fi
 echo ""
@@ -161,8 +227,10 @@ echo "============================================="
 echo "✅ All tests passed!"
 echo ""
 echo "Summary:"
+echo "  - Smart duplicate detection works correctly"
+echo "  - Multiple duplicate groups are identified"
+echo "  - Title filtering works as expected"
 echo "  - Correctly identifies most recent issue"
 echo "  - Closes all duplicates except the most recent"
 echo "  - Handles edge cases (single issue, empty input)"
-echo "  - Date sorting works correctly"
-echo "  - Data format compatible with GitHub API response"
+echo "  - Properly detects when no duplicates exist"
--- a/scripts/triage-duplicate-issues.sh
+++ b/scripts/triage-duplicate-issues.sh
@@ -1,22 +1,22 @@
 #!/bin/bash

 # Script to bulk-close duplicate issues found via GitHub API
-# Dynamically finds issues with duplicate titles and closes all except the most recent one
+# Automatically finds all duplicate issue titles and closes all except the most recent one
 #
 # Usage:
 #   export GITHUB_TOKEN="ghp_your_token_here"
 #   ./triage-duplicate-issues.sh
 #
-# Or with custom search pattern:
+# Or with custom search pattern (optional):
 #   export GITHUB_TOKEN="ghp_your_token_here"
 #   export SEARCH_TITLE="Custom Issue Title"
 #   ./triage-duplicate-issues.sh
 #
 # The script will:
-# 1. Search for all open issues matching the SEARCH_TITLE pattern
-# 2. Sort them by creation date (newest first)
-# 3. Keep the most recent issue open
-# 4. Close all other duplicates with an explanatory comment
+# 1. Fetch all open issues in the repository
+# 2. Group issues by exact title match
+# 3. For each group with 2+ issues, keep the most recent and close the rest
+# 4. Close all duplicates with an explanatory comment

 set -e

@@ -25,12 +25,17 @@ usage() {
  echo ""
  echo "Environment variables:"
  echo "  GITHUB_TOKEN     (required) GitHub personal access token with repo access"
-  echo "  SEARCH_TITLE     (optional) Issue title pattern to search for"
-  echo "                   Default: '🚨 Production Deployment Failed - Rollback Required'"
+  echo "  SEARCH_TITLE     (optional) If set, only process duplicates matching this specific title"
+  echo "                   If not set, automatically detects and processes ALL duplicate titles"
  echo ""
-  echo "Example:"
+  echo "Examples:"
+  echo "  # Auto-detect and close all duplicates"
  echo "  export GITHUB_TOKEN='ghp_xxxxxxxxxxxx'"
-  echo "  export SEARCH_TITLE='Duplicate bug report'"
+  echo "  $0"
+  echo ""
+  echo "  # Only process specific title"
+  echo "  export GITHUB_TOKEN='ghp_xxxxxxxxxxxx'"
+  echo "  export SEARCH_TITLE='⚠️ Pre-Deployment Validation Failed'"
  echo "  $0"
  exit 1
 }
@@ -49,34 +54,91 @@ fi
 OWNER="johndoe6345789"
 REPO="metabuilder"

-# Search pattern for duplicate issues (can be customized)
-SEARCH_TITLE="${SEARCH_TITLE:-🚨 Production Deployment Failed - Rollback Required}"
+# Optional: Search pattern for specific title (if not set, processes all duplicates)
+SEARCH_TITLE="${SEARCH_TITLE:-}"

-# Function to fetch issues by title pattern
-fetch_duplicate_issues() {
-  local search_query="$1"
-  echo "🔍 Searching for issues with title: \"$search_query\"" >&2
+# Function to fetch ALL open issues in the repository
+fetch_all_open_issues() {
+  echo "🔍 Fetching all open issues from repository..." >&2
  
-  # Use GitHub API to search for issues by title
-  # Filter by: is:issue, is:open, repo, and title match
-  local encoded_query
-  encoded_query=$(echo "is:issue is:open repo:$OWNER/$REPO in:title $search_query" | jq -sRr @uri)
+  local all_issues=""
+  local page=1
+  local per_page=100
  
-  local response
-  response=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
-    -H "Accept: application/vnd.github.v3+json" \
-    "https://api.github.com/search/issues?q=$encoded_query&sort=created&order=desc&per_page=100")
+  while true; do
+    local response
+    response=$(curl -s -H "Authorization: token $GITHUB_TOKEN" \
+      -H "Accept: application/vnd.github.v3+json" \
+      "https://api.github.com/repos/$OWNER/$REPO/issues?state=open&per_page=$per_page&page=$page&sort=created&direction=desc")
+    
+    # Check for API errors
+    if echo "$response" | jq -e '.[0].message' > /dev/null 2>&1; then
+      local error_msg
+      error_msg=$(echo "$response" | jq -r '.[0].message')
+      echo "❌ GitHub API error: $error_msg" >&2
+      return 1
+    fi
+    
+    # Check if response is empty (no more pages)
+    local item_count
+    item_count=$(echo "$response" | jq 'length')
+    if [ "$item_count" -eq 0 ]; then
+      break
+    fi
+    
+    # Extract issue numbers, creation dates, and titles
+    local page_data
+    page_data=$(echo "$response" | jq -r '.[] | select(.pull_request == null) | "\(.number)|\(.created_at)|\(.title)"')
+    
+    if [ -n "$page_data" ]; then
+      if [ -z "$all_issues" ]; then
+        all_issues="$page_data"
+      else
+        all_issues="$all_issues"$'\n'"$page_data"
+      fi
+    fi
+    
+    # If we got fewer items than per_page, we're on the last page
+    if [ "$item_count" -lt "$per_page" ]; then
+      break
+    fi
+    
+    page=$((page + 1))
+  done
  
-  # Check for API errors
-  if echo "$response" | jq -e '.message' > /dev/null 2>&1; then
-    local error_msg
-    error_msg=$(echo "$response" | jq -r '.message')
-    echo "❌ GitHub API error: $error_msg" >&2
-    return 1
+  echo "$all_issues"
+}
+
+# Function to find duplicate titles and return them grouped
+find_duplicate_titles() {
+  local issues_data="$1"
+  local search_filter="$2"
+  
+  if [ -z "$issues_data" ]; then
+    return 0
  fi
  
-  # Extract issue numbers and creation dates, sorted by creation date (newest first)
-  echo "$response" | jq -r '.items | sort_by(.created_at) | reverse | .[] | "\(.number)|\(.created_at)|\(.title)"'
+  # Extract unique titles and count occurrences
+  # Format: title|count
+  local title_counts
+  if [ -n "$search_filter" ]; then
+    # Filter by specific title if provided
+    title_counts=$(echo "$issues_data" | cut -d'|' -f3- | grep -F "$search_filter" | sort | uniq -c | awk '$1 > 1 {$1=""; print substr($0,2)}')
+  else
+    # Find all duplicate titles
+    title_counts=$(echo "$issues_data" | cut -d'|' -f3- | sort | uniq -c | awk '$1 > 1 {$1=""; print substr($0,2)}')
+  fi
+  
+  echo "$title_counts"
+}
+
+# Function to get issues for a specific title, sorted by creation date (newest first)
+get_issues_by_title() {
+  local issues_data="$1"
+  local title="$2"
+  
+  # Filter issues matching the exact title and sort by date (newest first)
+  echo "$issues_data" | grep -F "|$title" | sort -t'|' -k2 -r
 }

 # Function to determine which issues to close (all except the most recent)
@@ -100,81 +162,89 @@ get_issues_to_close() {
  echo "$issues_data" | tail -n +2 | cut -d'|' -f1
 }

-# Fetch all duplicate issues
-ISSUES_DATA=$(fetch_duplicate_issues "$SEARCH_TITLE")
-
-if [ -z "$ISSUES_DATA" ]; then
-  echo "✨ No duplicate issues found. Nothing to do!"
-  exit 0
-fi
-
-# Parse the data
-TOTAL_ISSUES=$(echo "$ISSUES_DATA" | wc -l)
-MOST_RECENT=$(echo "$ISSUES_DATA" | head -1 | cut -d'|' -f1)
-MOST_RECENT_DATE=$(echo "$ISSUES_DATA" | head -1 | cut -d'|' -f2)
-
-echo "📊 Found $TOTAL_ISSUES duplicate issues"
-echo "📌 Most recent issue: #$MOST_RECENT (created: $MOST_RECENT_DATE)"
+# Fetch all open issues
+echo "🤖 Smart Duplicate Issue Triage"
+echo "==============================="
 echo ""

-# Get list of issues to close
-ISSUES_TO_CLOSE_DATA=$(get_issues_to_close "$ISSUES_DATA")
+ALL_ISSUES=$(fetch_all_open_issues)

-if [ -z "$ISSUES_TO_CLOSE_DATA" ]; then
-  echo "✨ No issues need to be closed!"
+if [ -z "$ALL_ISSUES" ]; then
+  echo "✨ No open issues found in repository!"
  exit 0
 fi

-# Convert to array
-ISSUES_TO_CLOSE=()
-while IFS= read -r issue_num; do
-  ISSUES_TO_CLOSE+=("$issue_num")
-done <<< "$ISSUES_TO_CLOSE_DATA"
+TOTAL_ISSUES=$(echo "$ALL_ISSUES" | wc -l)
+echo "📊 Found $TOTAL_ISSUES total open issues"
+echo ""

-CLOSE_COMMENT='🤖 **Automated Triage: Closing Duplicate Issue**
+# Find duplicate titles
+if [ -n "$SEARCH_TITLE" ]; then
+  echo "🔎 Filtering for specific title: \"$SEARCH_TITLE\""
+  DUPLICATE_TITLES=$(find_duplicate_titles "$ALL_ISSUES" "$SEARCH_TITLE")
+else
+  echo "🔎 Automatically detecting duplicate titles..."
+  DUPLICATE_TITLES=$(find_duplicate_titles "$ALL_ISSUES" "")
+fi
+
+if [ -z "$DUPLICATE_TITLES" ]; then
+  echo "✨ No duplicate issues found. Repository is clean!"
+  exit 0
+fi
+
+# Count how many unique titles have duplicates
+DUPLICATE_TITLE_COUNT=$(echo "$DUPLICATE_TITLES" | wc -l)
+echo "🎯 Found $DUPLICATE_TITLE_COUNT title(s) with duplicates"
+echo ""
+
+close_issue() {
+  local issue_number=$1
+  local most_recent=$2
+  local most_recent_date=$3
+  local title=$4
+  local total_with_title=$5
+  
+  local close_comment='🤖 **Automated Triage: Closing Duplicate Issue**

 This issue has been identified as a duplicate. Multiple issues with the same title were found, and this script automatically closes all duplicates except the most recent one.

 **Resolution:**
- ✅ Keeping the most recent issue (#'"$MOST_RECENT"') as the canonical tracking issue
+- ✅ Keeping the most recent issue (#'"$most_recent"') as the canonical tracking issue
 - ✅ Closing this and other duplicate issues to maintain a clean issue tracker

 **How duplicates were identified:**
- Search pattern: "'"$SEARCH_TITLE"'"
- Total duplicates found: '"$TOTAL_ISSUES"'
- Keeping most recent: Issue #'"$MOST_RECENT"' (created '"$MOST_RECENT_DATE"')
+- Title: "'"$title"'"
+- Total duplicates found: '"$total_with_title"'
+- Keeping most recent: Issue #'"$most_recent"' (created '"$most_recent_date"')

-**No Action Required** - Please refer to issue #'"$MOST_RECENT"' for continued discussion.
+**No Action Required** - Please refer to issue #'"$most_recent"' for continued discussion.

 ---
 *This closure was performed by an automated triage script. For questions, see `scripts/triage-duplicate-issues.sh`*'
-
-close_issue() {
-  local issue_number=$1
  
  # Add comment explaining closure
-  echo "📝 Adding comment to issue #${issue_number}..."
+  echo "  📝 Adding comment to issue #${issue_number}..."
  if curl -s -X POST \
    -H "Authorization: token $GITHUB_TOKEN" \
    -H "Accept: application/vnd.github.v3+json" \
    "https://api.github.com/repos/$OWNER/$REPO/issues/$issue_number/comments" \
-    -d "{\"body\": $(echo "$CLOSE_COMMENT" | jq -Rs .)}" > /dev/null; then
-    echo "✅ Added comment to issue #${issue_number}"
+    -d "{\"body\": $(echo "$close_comment" | jq -Rs .)}" > /dev/null; then
+    echo "  ✅ Added comment to issue #${issue_number}"
  else
-    echo "❌ Failed to add comment to issue #${issue_number}"
+    echo "  ❌ Failed to add comment to issue #${issue_number}"
    return 1
  fi
  
  # Close the issue
-  echo "🔒 Closing issue #${issue_number}..."
+  echo "  🔒 Closing issue #${issue_number}..."
  if curl -s -X PATCH \
    -H "Authorization: token $GITHUB_TOKEN" \
    -H "Accept: application/vnd.github.v3+json" \
    "https://api.github.com/repos/$OWNER/$REPO/issues/$issue_number" \
    -d '{"state": "closed", "state_reason": "not_planned"}' > /dev/null; then
-    echo "✅ Closed issue #${issue_number}"
+    echo "  ✅ Closed issue #${issue_number}"
  else
-    echo "❌ Failed to close issue #${issue_number}"
+    echo "  ❌ Failed to close issue #${issue_number}"
    return 1
  fi
  
@@ -184,20 +254,70 @@ close_issue() {
 main() {
  echo "🔧 Starting bulk issue triage..."
  echo ""
-  echo "📋 Planning to close ${#ISSUES_TO_CLOSE[@]} duplicate issues"
-  echo "📌 Keeping issue #$MOST_RECENT open (most recent)"
-  echo ""
  
-  for issue_number in "${ISSUES_TO_CLOSE[@]}"; do
-    close_issue "$issue_number"
-    # Add a small delay to avoid rate limiting
-    sleep 1
-  done
+  local total_closed=0
+  local title_index=0
  
+  # Process each duplicate title
+  while IFS= read -r duplicate_title; do
+    title_index=$((title_index + 1))
+    
+    echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+    echo "📋 Processing duplicate group $title_index/$DUPLICATE_TITLE_COUNT"
+    echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+    echo "Title: \"$duplicate_title\""
+    echo ""
+    
+    # Get all issues with this title
+    TITLE_ISSUES=$(get_issues_by_title "$ALL_ISSUES" "$duplicate_title")
+    TITLE_ISSUE_COUNT=$(echo "$TITLE_ISSUES" | wc -l)
+    
+    # Get the most recent issue
+    MOST_RECENT=$(echo "$TITLE_ISSUES" | head -1 | cut -d'|' -f1)
+    MOST_RECENT_DATE=$(echo "$TITLE_ISSUES" | head -1 | cut -d'|' -f2)
+    
+    echo "  📊 Found $TITLE_ISSUE_COUNT issues with this title"
+    echo "  📌 Most recent: Issue #$MOST_RECENT (created: $MOST_RECENT_DATE)"
+    echo ""
+    
+    # Get list of issues to close
+    ISSUES_TO_CLOSE_DATA=$(get_issues_to_close "$TITLE_ISSUES")
+    
+    if [ -z "$ISSUES_TO_CLOSE_DATA" ]; then
+      echo "  ℹ️  No duplicates to close for this title"
+      echo ""
+      continue
+    fi
+    
+    # Convert to array
+    ISSUES_TO_CLOSE=()
+    while IFS= read -r issue_num; do
+      ISSUES_TO_CLOSE+=("$issue_num")
+    done <<< "$ISSUES_TO_CLOSE_DATA"
+    
+    echo "  🎯 Planning to close ${#ISSUES_TO_CLOSE[@]} duplicate issues"
+    echo ""
+    
+    for issue_number in "${ISSUES_TO_CLOSE[@]}"; do
+      close_issue "$issue_number" "$MOST_RECENT" "$MOST_RECENT_DATE" "$duplicate_title" "$TITLE_ISSUE_COUNT"
+      total_closed=$((total_closed + 1))
+      # Add a small delay to avoid rate limiting
+      sleep 1
+    done
+    
+    echo "  ✅ Completed processing this duplicate group"
+    echo ""
+  done <<< "$DUPLICATE_TITLES"
+  
+  echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
  echo "✨ Triage complete!"
+  echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+  echo ""
+  echo "📊 Summary:"
+  echo "  • Processed $DUPLICATE_TITLE_COUNT duplicate title group(s)"
+  echo "  • Closed $total_closed duplicate issue(s)"
+  echo "  • Kept the most recent issue open for each title"
  echo ""
-  echo "📌 Kept open: Issue #$MOST_RECENT (most recent, created $MOST_RECENT_DATE)"
-  echo "🔒 Closed: ${#ISSUES_TO_CLOSE[@]} duplicate issues"
 }

 main