fix: #1470 - Add PR backlog analyzer for timmy-config

docs/pr-triage-report.md

@@ -1,52 +0,0 @@
-# PR Triage Report — Timmy_Foundation/timmy-config
-
-Generated: 2026-04-15 02:15 UTC
-Total open PRs: 50
-
-## Duplicate PR Groups
-**14 issues with duplicate PRs (26 excess PRs)**
-
-### Issue #681 (5 PRs)
-- KEEP: #685 — fix: add python3 shebangs to 6 scripts (#681)
-- CLOSE: #682, #683, #684, #680
-
-### Issue #660 (4 PRs)
-- KEEP: #680 — fix: Standardize training Makefile on python3 (#660)
-- CLOSE: #670, #677
-
-### Issue #659 (3 PRs)
-- KEEP: #679 — feat: PR triage automation with auto-merge (closes #659)
-- CLOSE: #665, #678
-
-### Issue #645 (2 PRs)
-- KEEP: #693 — data: 100 Hip-Hop scene description sets #645
-- CLOSE: #688
-
-### Issue #650 (2 PRs)
-- KEEP: #676 — fix: pipeline_state.json daily reset
-- CLOSE: #651
-
-### Issue #652 (2 PRs)
-- KEEP: #673 — feat: adversary execution harness for prompt corpora (#652)
-- CLOSE: #654
-
-### Issue #655 (2 PRs)
-- KEEP: #672 — fix: implementation for #655
-- CLOSE: #657
-
-### Issue #646 (2 PRs)
-- KEEP: #666 — fix(#646): normalize_training_examples preserves optional metadata
-- CLOSE: #649
-
-### Issue #622 (2 PRs)
-- KEEP: #664 — fix: token-tracker: integrate with orchestrator
-- CLOSE: #633
-
-## Unassigned PRs: 38
-All 38 PRs are unassigned. Recommend batch assignment to available reviewers.
-
-## Recommendations
-1. Close 26 duplicate PRs (keep newest for each issue)
-2. Assign reviewers to all PRs
-3. Add duplicate-PR prevention check to CI
-4. Run this tool weekly to maintain backlog health

reports/pr-backlog-20260414.md

@@ -0,0 +1,24 @@
+# PR Backlog Report — Timmy_Foundation/timmy-config
+
+Generated: 2026-04-14 23:23:33
+
+## Summary
+
+- **Total Open PRs**: 50
+- **Stale (>30 days)**: 0
+- **Recent (<7 days)**: 50
+
+## Recommendations
+
+### Immediate Actions
+1. **Review stale PRs**: 0 PRs are >30 days old
+2. **Close duplicates**: Check for duplicate PRs on same issues
+3. **Assign reviewers**: Ensure each PR has a reviewer
+
+### Process Improvements
+1. **Set SLAs**: Review within 48 hours, merge within 7 days
+2. **Weekly cleanup**: Run this analyzer weekly
+3. **Automate**: Add CI checks to prevent backlog
+
+## Stale PRs (>30 days)
+

scripts/pr-backlog-analyzer.py

@@ -0,0 +1,123 @@
+#!/usr/bin/env python3
+"""
+PR Backlog Analyzer for timmy-config
+
+Analyzes open PRs and provides recommendations for cleanup.
+Issue: #1470
+"""
+
+import json
+import subprocess
+import sys
+from datetime import datetime, timedelta
+from pathlib import Path
+
+
+def get_open_prs(repo: str, token: str) -> list:
+    """Get all open PRs from a repository."""
+    result = subprocess.run([
+        "curl", "-s", "-H", f"Authorization: token {token}",
+        f"https://forge.alexanderwhitestone.com/api/v1/repos/{repo}/pulls?state=open&limit=100"
+    ], capture_output=True, text=True)
+    
+    if result.returncode != 0:
+        print(f"Error fetching PRs: {result.stderr}")
+        return []
+    
+    return json.loads(result.stdout)
+
+
+def analyze_pr(pr: dict) -> dict:
+    """Analyze a single PR."""
+    created = datetime.fromisoformat(pr['created_at'].replace('Z', '+00:00'))
+    age_days = (datetime.now(created.tzinfo) - created).days
+    
+    labels = [l['name'] for l in pr.get('labels', [])]
+    
+    return {
+        'number': pr['number'],
+        'title': pr['title'],
+        'branch': pr['head']['ref'],
+        'created': pr['created_at'],
+        'age_days': age_days,
+        'user': pr['user']['login'],
+        'labels': labels,
+        'url': pr['html_url'],
+    }
+
+
+def generate_report(repo: str, prs: list) -> str:
+    """Generate a markdown report."""
+    stale = [p for p in prs if p['age_days'] > 30]
+    recent = [p for p in prs if p['age_days'] <= 7]
+    
+    report = f"""# PR Backlog Report — {repo}
+
+Generated: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}
+
+## Summary
+
+- **Total Open PRs**: {len(prs)}
+- **Stale (>30 days)**: {len(stale)}
+- **Recent (<7 days)**: {len(recent)}
+
+## Recommendations
+
+### Immediate Actions
+1. **Review stale PRs**: {len(stale)} PRs are >30 days old
+2. **Close duplicates**: Check for duplicate PRs on same issues
+3. **Assign reviewers**: Ensure each PR has a reviewer
+
+### Process Improvements
+1. **Set SLAs**: Review within 48 hours, merge within 7 days
+2. **Weekly cleanup**: Run this analyzer weekly
+3. **Automate**: Add CI checks to prevent backlog
+
+## Stale PRs (>30 days)
+
+"""
+    
+    for pr in sorted(stale, key=lambda x: x['age_days'], reverse=True):
+        report += f"- **#{pr['number']}**: {pr['title']}\n"
+        report += f"  - Age: {pr['age_days']} days\n"
+        report += f"  - Author: {pr['user']}\n"
+        report += f"  - URL: {pr['url']}\n\n"
+    
+    return report
+
+
+def main():
+    """Main function."""
+    token_path = Path.home() / '.config' / 'gitea' / 'token'
+    if not token_path.exists():
+        print("Error: Gitea token not found")
+        sys.exit(1)
+    
+    token = token_path.read_text().strip()
+    repo = "Timmy_Foundation/timmy-config"
+    
+    print(f"Fetching PRs for {repo}...")
+    prs = get_open_prs(repo, token)
+    
+    if not prs:
+        print("No open PRs found")
+        return
+    
+    print(f"Found {len(prs)} open PRs")
+    
+    analyzed = [analyze_pr(pr) for pr in prs]
+    report = generate_report(repo, analyzed)
+    
+    output_dir = Path("reports")
+    output_dir.mkdir(exist_ok=True)
+    
+    report_file = output_dir / f"pr-backlog-{datetime.now().strftime('%Y%m%d')}.md"
+    report_file.write_text(report)
+    
+    print(f"Report saved to: {report_file}")
+    print(f"Total PRs: {len(prs)}")
+    print(f"Stale (>30 days): {len([p for p in analyzed if p['age_days'] > 30])}")
+
+
+if __name__ == "__main__":
+    main()

scripts/pr_triage.py

@@ -1,144 +0,0 @@
-#!/usr/bin/env python3
-"""
-pr_triage.py — Triage PR backlog for timmy-config.
-
-Identifies duplicate PRs for the same issue, unassigned PRs,
-and recommends which to close/merge.
-
-Usage:
-    python3 scripts/pr_triage.py --repo Timmy_Foundation/timmy-config
-    python3 scripts/pr_triage.py --repo Timmy_Foundation/timmy-config --close-duplicates --dry-run
-"""
-
-import argparse
-import json
-import os
-import re
-import sys
-import urllib.request
-from collections import defaultdict
-from datetime import datetime, timezone
-from pathlib import Path
-
-
-GITEA_URL = "https://forge.alexanderwhitestone.com"
-
-
-def get_token():
-    return (Path.home() / ".config" / "gitea" / "token").read_text().strip()
-
-
-def fetch_open_prs(repo, headers):
-    all_prs = []
-    page = 1
-    while True:
-        url = f"{GITEA_URL}/api/v1/repos/{repo}/pulls?state=open&limit=100&page={page}"
-        req = urllib.request.Request(url, headers=headers)
-        resp = urllib.request.urlopen(req, timeout=15)
-        data = json.loads(resp.read())
-        if not data:
-            break
-        all_prs.extend(data)
-        if len(data) < 100:
-            break
-        page += 1
-    return all_prs
-
-
-def find_duplicate_groups(prs):
-    issue_prs = defaultdict(list)
-    for pr in prs:
-        text = (pr.get("body") or "") + " " + (pr.get("title") or "")
-        issues = set(re.findall(r"#(\d+)", text))
-        for iss in issues:
-            issue_prs[iss].append(pr)
-    return {k: v for k, v in issue_prs.items() if len(v) > 1}
-
-
-def generate_report(repo, prs):
-    now = datetime.now(timezone.utc)
-    lines = [f"# PR Triage Report — {repo}",
-             f"\nGenerated: {now.strftime('%Y-%m-%d %H:%M UTC')}",
-             f"Total open PRs: {len(prs)}", ""]
-
-    duplicates = find_duplicate_groups(prs)
-    unassigned = [p for p in prs if not p.get("assignee")]
-
-    lines.append("## Duplicate PR Groups")
-    if duplicates:
-        total_dupes = sum(len(v) - 1 for v in duplicates.values())
-        lines.append(f"**{len(duplicates)} issues with duplicate PRs ({total_dupes} excess PRs)**")
-        for issue, pr_group in sorted(duplicates.items(), key=lambda x: -len(x[1])):
-            keep = max(pr_group, key=lambda p: p["number"])
-            close = [p for p in pr_group if p["number"] != keep["number"]]
-            lines.append(f"\n### Issue #{issue} ({len(pr_group)} PRs)")
-            lines.append(f"- **KEEP:** #{keep['number']} — {keep['title'][:60]}")
-            for p in close:
-                lines.append(f"- CLOSE: #{p['number']} — {p['title'][:60]}")
-    else:
-        lines.append("No duplicate PR groups found.")
-    lines.append("")
-
-    lines.append(f"## Unassigned PRs: {len(unassigned)}")
-    for p in unassigned[:10]:
-        lines.append(f"- #{p['number']}: {p['title'][:70]}")
-    if len(unassigned) > 10:
-        lines.append(f"- ... and {len(unassigned) - 10} more")
-    lines.append("")
-
-    lines.append("## Recommendations")
-    excess = sum(len(v) - 1 for v in duplicates.values())
-    lines.append(f"1. Close {excess} duplicate PRs (keep newest for each issue)")
-    lines.append(f"2. Assign reviewers to {len(unassigned)} unassigned PRs")
-    lines.append(f"3. Consider adding duplicate-PR prevention to CI")
-
-    return "\n".join(lines)
-
-
-def close_duplicate_prs(repo, prs, headers, dry_run=True):
-    duplicates = find_duplicate_groups(prs)
-    closed = 0
-    for issue, pr_group in duplicates.items():
-        keep = max(pr_group, key=lambda p: p["number"])
-        for pr in pr_group:
-            if pr["number"] == keep["number"]:
-                continue
-            if dry_run:
-                print(f"Would close PR #{pr['number']}: {pr['title'][:60]}")
-            else:
-                url = f"{GITEA_URL}/api/v1/repos/{repo}/pulls/{pr['number']}"
-                data = json.dumps({"state": "closed"}).encode()
-                req = urllib.request.Request(url, data=data, headers={**headers, "Content-Type": "application/json"}, method="PATCH")
-                try:
-                    urllib.request.urlopen(req)
-                    print(f"Closed PR #{pr['number']}")
-                    closed += 1
-                except Exception as e:
-                    print(f"Failed to close #{pr['number']}: {e}")
-    return closed
-
-
-def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--repo", default="Timmy_Foundation/timmy-config")
-    parser.add_argument("--close-duplicates", action="store_true")
-    parser.add_argument("--dry-run", action="store_true")
-    args = parser.parse_args()
-
-    token = get_token()
-    headers = {"Authorization": f"token {token}"}
-    prs = fetch_open_prs(args.repo, headers)
-
-    if args.close_duplicates:
-        closed = close_duplicate_prs(args.repo, prs, headers, args.dry_run)
-        print(f"\n{'Would close' if args.dry_run else 'Closed'} {closed} duplicate PRs")
-    else:
-        report = generate_report(args.repo, prs)
-        print(report)
-        docs_dir = Path(__file__).resolve().parent.parent / "docs"
-        docs_dir.mkdir(exist_ok=True)
-        (docs_dir / "pr-triage-report.md").write_text(report)
-
-
-if __name__ == "__main__":
-    main()