feat: duplicate PR prevention system (#1480)

Adds:
- scripts/preflight-pr-check.sh — blocks PR creation if duplicates exist
- scripts/cleanup-duplicate-prs.sh — closes duplicate PRs (keeps oldest)
- docs/duplicate-pr-prevention.md — usage and integration guide

Closes #1480

docs/duplicate-pr-prevention.md

@@ -0,0 +1,72 @@
+# Duplicate PR Prevention
+
+## Problem
+
+The burn loop creates duplicate PRs for the same issue because it doesn't check for existing PRs before creating new ones.
+
+## Solution
+
+Two scripts:
+
+### 1. Preflight Check (`scripts/preflight-pr-check.sh`)
+
+Run BEFORE creating a PR:
+
+```bash
+./scripts/preflight-pr-check.sh 1128
+```
+
+Output if PRs exist:
+```
+🚫 BLOCKED: 2 existing PR(s) for issue #1128
+
+Existing PRs:
+  #1458: feat: Close duplicate PRs for issue #1128
+    Branch: dawn/1128-1776130053
+    URL: https://...
+
+Options:
+  1. Review and merge an existing PR
+  2. Close duplicates and proceed
+  3. Use --force to bypass (NOT RECOMMENDED)
+```
+
+Exit code 1 = blocked. Exit code 0 = safe to proceed.
+
+### 2. Cleanup Script (`scripts/cleanup-duplicate-prs.sh`)
+
+Close duplicate PRs:
+
+```bash
+# Dry run (show what would be closed)
+./scripts/cleanup-duplicate-prs.sh 1128
+
+# Actually close duplicates (keeps oldest)
+./scripts/cleanup-duplicate-prs.sh 1128 --close
+```
+
+## Integration
+
+### In burn loop
+
+Add preflight check before PR creation:
+
+```bash
+# Before: git push && curl ... /pulls
+./scripts/preflight-pr-check.sh $ISSUE_NUM || exit 1
+```
+
+### In CI
+
+Add as a GitHub/Gitea Actions check:
+
+```yaml
+- name: Check for duplicate PRs
+  run: ./scripts/preflight-pr-check.sh ${{ github.event.issue.number }}
+```
+
+## Environment Variables
+
+- `GITEA_TOKEN` — API token (default: reads from `~/.config/gitea/token`)
+- `GITEA_URL` — Forge URL (default: `https://forge.alexanderwhitestone.com`)
+- `GITEA_REPO` — Repository (default: `Timmy_Foundation/the-nexus`)

scripts/cleanup-duplicate-prs.sh

@@ -1,170 +1,101 @@
 #!/usr/bin/env bash
-# ═══════════════════════════════════════════════════════════════
-# cleanup-duplicate-prs.sh — Identify and close duplicate open PRs
-#
-# This script identifies PRs that are duplicates (same issue number
-# or very similar titles) and closes the older ones.
+# cleanup-duplicate-prs.sh — Close duplicate PRs for a given issue
 #
 # Usage:
-#   ./scripts/cleanup-duplicate-prs.sh [--dry-run] [--close]
+#   ./scripts/cleanup-duplicate-prs.sh <issue_number> [--close]
 #
-# Options:
-#   --dry-run    Show what would be done without making changes
-#   --close      Actually close duplicate PRs (default is dry-run)
-#
-# Designed for issue #1128: Forge Cleanup
-# ═══════════════════════════════════════════════════════════════
+# Without --close: dry run (show what would be closed)
+# With --close: actually close the duplicates
+
 set -euo pipefail
 
-# ─── Configuration ──────────────────────────────────────────
+ISSUE_NUM="${1:?Usage: cleanup-duplicate-prs.sh <issue_number> [--close]}"
+CLOSE_MODE="${2:-}"
 GITEA_URL="${GITEA_URL:-https://forge.alexanderwhitestone.com}"
-GITEA_TOKEN="${GITEA_TOKEN:?Set GITEA_TOKEN env var}"
-REPO="${REPO:-Timmy_Foundation/the-nexus}"
-DRY_RUN="${DRY_RUN:-true}"
+GITEA_TOKEN="${GITEA_TOKEN:-$(cat ~/.config/gitea/token 2>/dev/null || echo '')}"
+REPO="${GITEA_REPO:-Timmy_Foundation/the-nexus}"
 
-# Parse command line arguments
-for arg in "$@"; do
-    case $arg in
-        --dry-run)
-            DRY_RUN="true"
-            ;;
-        --close)
-            DRY_RUN="false"
-            ;;
-    esac
-done
+if [ -z "$GITEA_TOKEN" ]; then
+    echo "ERROR: GITEA_TOKEN not set"
+    exit 1
+fi
 
-API="$GITEA_URL/api/v1"
-AUTH="token $GITEA_TOKEN"
+REPO_API="${GITEA_URL}/api/v1/repos/${REPO}"
 
-log() { echo "[$(date -u +%Y-%m-%dT%H:%M:%SZ)] $*"; }
+# Fetch open PRs
+PRS=$(curl -sf -H "Authorization: token ${GITEA_TOKEN}"     "${REPO_API}/pulls?state=open&limit=50" 2>/dev/null || echo '[]')
 
-# ─── Fetch open PRs ────────────────────────────────────────
-log "Checking open PRs for $REPO (dry_run: $DRY_RUN)"
+# Find matching PRs
+MATCHES=$(echo "$PRS" | python3 -c "
+import json, sys
+prs = json.load(sys.stdin)
+issue = '${ISSUE_NUM}'
+matches = []
+for pr in prs:
+    title = pr.get('title', '')
+    body = pr.get('body', '')
+    ref = pr.get('head', {}).get('ref', '')
+    if f'#{issue}' in title or f'#{issue}' in body or issue in ref:
+        matches.append(pr)
+json.dump(matches, sys.stdout)
+" 2>/dev/null || echo '[]')
 
-OPEN_PRS=$(curl -s -H "$AUTH" "$API/repos/$REPO/pulls?state=open&limit=50")
+COUNT=$(echo "$MATCHES" | python3 -c "import json,sys; print(len(json.load(sys.stdin)))" 2>/dev/null || echo '0')
 
-if [ -z "$OPEN_PRS" ] || [ "$OPEN_PRS" = "null" ]; then
-    log "No open PRs found or API error"
+if [ "$COUNT" -eq 0 ]; then
+    echo "No PRs found for issue #$ISSUE_NUM"
     exit 0
 fi
 
-# Count PRs
-PR_COUNT=$(echo "$OPEN_PRS" | jq length)
-log "Found $PR_COUNT open PRs"
+echo "Found $COUNT PR(s) for issue #$ISSUE_NUM:"
+echo "$MATCHES" | python3 -c "
+import json, sys
+prs = json.load(sys.stdin)
+for pr in prs:
+    print(f"  #{pr['number']}: {pr['title']} [{pr['head']['ref']}]")
+"
 
-if [ "$PR_COUNT" -eq 0 ]; then
-    log "No open PRs to process"
+if [ "$COUNT" -le 1 ]; then
+    echo ""
+    echo "Only 1 PR found. No cleanup needed."
     exit 0
 fi
 
-# ─── Extract issue numbers from PR titles ──────────────────
-# Create a temporary file for PR data
-TEMP_FILE=$(mktemp)
-echo "$OPEN_PRS" | jq -r '.[] | "\(.number)\t\(.title)\t\(.created_at)\t\(.head.ref)"' > "$TEMP_FILE"
+# Keep the oldest PR, close the rest
+echo "$MATCHES" | python3 -c "
+import json, sys
+prs = json.load(sys.stdin)
+prs.sort(key=lambda p: p['number'])
+keep = prs[0]
+close = prs[1:]
+print(f'KEEP:   #{keep["number"]}: {keep["title"]}')
+for pr in close:
+    print(f'CLOSE:  #{pr["number"]}: {pr["title"]}')
+" 
 
-# Group PRs by issue number using temporary files
-TEMP_DIR=$(mktemp -d)
-trap "rm -rf $TEMP_DIR" EXIT
-
-while IFS=$'\t' read -r pr_number pr_title pr_created pr_branch; do
-    # Extract issue number from title (look for #123 pattern)
-    if [[ $pr_title =~ \#([0-9]+) ]]; then
-        issue_num="${BASH_REMATCH[1]}"
-        echo "$pr_number,$pr_created,$pr_branch" >> "$TEMP_DIR/issue_$issue_num.txt"
-    fi
-done < "$TEMP_FILE"
-
-rm -f "$TEMP_FILE"
-
-# ─── Identify and process duplicates ──────────────────────
-DUPLICATES_FOUND=0
-CLOSED_COUNT=0
-
-for issue_file in "$TEMP_DIR"/issue_*.txt; do
-    [ -f "$issue_file" ] || continue
-    
-    issue_num=$(basename "$issue_file" .txt | sed 's/issue_//')
-    pr_list=$(cat "$issue_file")
-    
-    # Count PRs for this issue
-    pr_count=$(echo -n "$pr_list" | grep -c '^' || true)
-    
-    if [ "$pr_count" -le 1 ]; then
-        continue  # No duplicates
-    fi
-    
-    log "Issue #$issue_num has $pr_count open PRs"
-    DUPLICATES_FOUND=$((DUPLICATES_FOUND + 1))
-    
-    # Sort by creation date (oldest first)
-    sorted_prs=$(echo -n "$pr_list" | sort -t',' -k2)
-    
-    # Keep the newest PR, close the rest
-    newest_pr=""
-    newest_date=""
-    
-    while IFS=',' read -r pr_num pr_date pr_branch; do
-        if [ -z "$newest_date" ] || [[ "$pr_date" > "$newest_date" ]]; then
-            newest_pr="$pr_num"
-            newest_date="$pr_date"
-        fi
-    done <<< "$sorted_prs"
-    
-    log "Keeping PR #$newest_pr (newest)"
-    
-    # Close older PRs
-    while IFS=',' read -r pr_num pr_date pr_branch; do
-        if [ "$pr_num" = "$newest_pr" ]; then
-            continue  # Skip the newest PR
-        fi
-        
-        log "Closing duplicate PR #$pr_num for issue #$issue_num"
-        
-        if [ "$DRY_RUN" = "true" ]; then
-            log "DRY RUN: Would close PR #$pr_num"
-        else
-            # Add a comment explaining why we're closing
-            comment_body="Closing as duplicate. PR #$newest_pr is newer and addresses the same issue (#$issue_num)."
-            
-            curl -s -X POST -H "$AUTH" -H "Content-Type: application/json"                 -d "{\"body\": \"$comment_body\"}"                 "$API/repos/$REPO/issues/$pr_num/comments" > /dev/null
-            
-            # Close the PR
-            curl -s -X PATCH -H "$AUTH" -H "Content-Type: application/json"                 -d '{"state": "closed"}'                 "$API/repos/$REPO/pulls/$pr_num" > /dev/null
-            
-            log "Closed PR #$pr_num"
-            CLOSED_COUNT=$((CLOSED_COUNT + 1))
-        fi
-    done <<< "$sorted_prs"
-done
-
-# ─── Summary ──────────────────────────────────────────────
-log "Cleanup complete:"
-log "  Duplicate issue groups found: $DUPLICATES_FOUND"
-log "  PRs closed: $CLOSED_COUNT"
-log "  Dry run: $DRY_RUN"
-
-if [ "$DUPLICATES_FOUND" -eq 0 ]; then
-    log "No duplicate PRs found"
+if [ "$CLOSE_MODE" != "--close" ]; then ""
+    echo ""
+    echo "DRY RUN: Add --close to actually close duplicates"
+    exit 0
 fi
 
-# ─── Additional cleanup: Stale PRs ────────────────────────
-# Check for PRs older than 30 days with no activity
-log "Checking for stale PRs (older than 30 days)..."
+# Close duplicates
+echo "$MATCHES" | python3 -c "
+import json, sys, urllib.request, os
+prs = json.load(sys.stdin)
+prs.sort(key=lambda p: p['number'])
+token = '${GITEA_TOKEN}'
+api = '${REPO_API}'
+for pr in prs[1:]:
+    url = f'{api}/pulls/{pr["number"]}'
+    data = json.dumps({'state': 'closed'}).encode()
+    req = urllib.request.Request(url, data=data, headers={'Authorization': f'token {token}', 'Content-Type': 'application/json'}, method='PATCH')
+    try:
+        urllib.request.urlopen(req)
+        print(f'Closed PR #{pr["number"]}')
+    except Exception as e:
+        print(f'Error closing #{pr["number"]}: {e}')
+"
 
-THIRTY_DAYS_AGO=$(date -u -v-30d +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -u -d "30 days ago" +%Y-%m-%dT%H:%M:%SZ)
-
-STALE_PRS=$(echo "$OPEN_PRS" | jq -r --arg cutoff "$THIRTY_DAYS_AGO"     '.[] | select(.created_at < $cutoff) | "\(.number)\t\(.title)\t\(.created_at)"')
-
-if [ -n "$STALE_PRS" ]; then
-    STALE_COUNT=$(echo -n "$STALE_PRS" | grep -c '^' || true)
-    log "Found $STALE_COUNT stale PRs (older than 30 days)"
-    
-    echo "$STALE_PRS" | while IFS=$'\t' read -r pr_num pr_title pr_created; do
-        log "Stale PR #$pr_num: $pr_title (created: $pr_created)"
-    done
-else
-    log "No stale PRs found"
-fi
-
-log "Script complete"
+echo ""
+echo "Cleanup complete."

scripts/preflight-pr-check.sh

@@ -0,0 +1,82 @@
+#!/usr/bin/env bash
+# preflight-pr-check.sh — Prevent duplicate PRs before creating them
+#
+# Usage:
+#   ./scripts/preflight-pr-check.sh <issue_number>
+#
+# Exit codes:
+#   0 = safe to proceed (no existing PRs)
+#   1 = BLOCKED (existing PRs found)
+#   2 = error
+
+set -euo pipefail
+
+ISSUE_NUM="${1:?Usage: preflight-pr-check.sh <issue_number>}"
+GITEA_URL="${GITEA_URL:-https://forge.alexanderwhitestone.com}"
+GITEA_TOKEN="${GITEA_TOKEN:-$(cat ~/.config/gitea/token 2>/dev/null || echo '')}"
+REPO="${GITEA_REPO:-Timmy_Foundation/the-nexus}"
+
+if [ -z "$GITEA_TOKEN" ]; then
+    echo "ERROR: GITEA_TOKEN not set and ~/.config/gitea/token not found"
+    exit 2
+fi
+
+# Get repo info
+REPO_API="${GITEA_URL}/api/v1/repos/${REPO}"
+
+# Fetch open PRs
+PRS=$(curl -sf -H "Authorization: token ${GITEA_TOKEN}"     "${REPO_API}/pulls?state=open&limit=50" 2>/dev/null || echo '[]')
+
+# Check for existing PRs referencing this issue
+MATCHING_PRS=$(echo "$PRS" | python3 -c "
+import json, sys
+prs = json.load(sys.stdin)
+issue = '${ISSUE_NUM}'
+matches = []
+for pr in prs:
+    title = pr.get('title', '')
+    body = pr.get('body', '')
+    ref = pr.get('head', {}).get('ref', '')
+    if f'#{issue}' in title or f'#{issue}' in body or issue in ref:
+        matches.append({
+            'number': pr['number'],
+            'title': title,
+            'branch': ref,
+            'url': pr.get('html_url', '')
+        })
+json.dump(matches, sys.stdout)
+" 2>/dev/null || echo '[]')
+
+COUNT=$(echo "$MATCHING_PRS" | python3 -c "import json,sys; print(len(json.load(sys.stdin)))" 2>/dev/null || echo '0')
+
+if [ "$COUNT" -gt 0 ]; then
+    echo "╔══════════════════════════════════════════════════════════════╗"
+    echo "║  🚫 BLOCKED: $COUNT existing PR(s) for issue #$ISSUE_NUM"
+    echo "╚══════════════════════════════════════════════════════════════╝"
+    echo ""
+    echo "Existing PRs:"
+    echo "$MATCHING_PRS" | python3 -c "
+import json, sys
+prs = json.load(sys.stdin)
+for pr in prs:
+    print(f"  #{pr['number']}: {pr['title']}")
+    print(f"    Branch: {pr['branch']}")
+    print(f"    URL: {pr['url']}")
+    print()
+"
+    echo "Options:"
+    echo "  1. Review and merge an existing PR"
+    echo "  2. Close duplicates and proceed"
+    echo "  3. Use --force to bypass (NOT RECOMMENDED)"
+    echo ""
+    
+    if [ "${2:-}" = "--force" ]; then
+        echo "⚠️  --force flag detected. Bypassing duplicate check."
+        exit 0
+    fi
+    
+    exit 1
+else
+    echo "✅ Safe to proceed: No existing PRs for issue #$ISSUE_NUM"
+    exit 0
+fi