rootly-graphify-importer: Instructions file for Codex

rootly-graphify

This project turns Rootly incident data into a knowledge graph. The Rootly corpus lives in graphify-rootly-data/ and the graph output in graphify-out/.

Always-on rules:

• Before answering incident or architecture questions, read graphify-out/GRAPH_REPORT.md for god nodes and community structure
• If graphify-out/wiki/index.md exists, navigate it instead of reading raw files
• After modifying code files, run: python -c "from graphify.watch import _rebuild_code; from pathlib import Path; _rebuild_code(Path('.'))" to keep the graph current

---

graphify pipeline — full instructions

When the user asks you to run graphify on a path (e.g. "run graphify on graphify-rootly-data"), follow these steps in order.

Usage patterns

graphify <path>                  # full pipeline
graphify <path> --mode deep      # richer INFERRED edges
graphify <path> --update         # re-extract only new/changed files
graphify query "<question>"      # BFS traversal of graph.json
graphify path "NodeA" "NodeB"    # shortest path between two nodes
graphify explain "NodeName"      # explain a single node

---

Step 1 — Ensure graphify is installed

python -c "import graphify" 2>/dev/null || pip install graphifyy -q

---

Step 2 — Detect files

python -c "
import json
from graphify.detect import detect
from pathlib import Path
result = detect(Path('INPUT_PATH'))
Path('.graphify_detect.json').write_text(json.dumps(result, indent=2), encoding='utf-8')
print(result['total_files'], 'files,', result['total_words'], 'words')
for k, v in result.get('files', {}).items():
    if v: print(f'  {k}: {len(v)} files')
"

Replace INPUT_PATH with the actual path. Present a clean summary:

Corpus: X files · ~Y words
  docs:   N files
  code:   N files

• If total_files is 0: stop with "No supported files found."
• If total_words > 2,000,000 OR total_files > 500: warn and ask which subfolder to run on.
• Otherwise: proceed directly to Step 3.