Compare commits

..

3 Commits

3 changed files with 260 additions and 249 deletions

View File

@@ -1,249 +0,0 @@
#!/usr/bin/env python3
"""
Cross-Repo Dependency Graph Builder
Scans repos for import/require/reference patterns and builds a directed
dependency graph. Detects circular dependencies. Outputs DOT and Mermaid.
Usage:
python3 scripts/dependency_graph.py /path/to/repos/
python3 scripts/dependency_graph.py --repos repo1,repo2,repo3 --format mermaid
python3 scripts/dependency_graph.py --repos-dir /path/to/ --format dot --output deps.dot
Patterns detected:
- Python: import X, from X import Y
- JavaScript: require("X"), import ... from "X"
- Go: import "X"
- Ansible: include_role, import_role
- Docker/Compose: image: X, depends_on
- Config references: repo-name in YAML/TOML/JSON
"""
import argparse
import json
import os
import re
import sys
from collections import defaultdict
from pathlib import Path
# Known repo names for matching
KNOWN_REPOS = [
"hermes-agent", "timmy-config", "timmy-home", "the-nexus", "the-door",
"the-beacon", "fleet-ops", "burn-fleet", "timmy-dispatch", "turboquant",
"compounding-intelligence", "the-playground", "second-son-of-timmy",
"ai-safety-review", "the-echo-pattern", "timmy-academy", "wolf",
"the-testament",
]
def normalize_repo_name(name: str) -> str:
"""Normalize a repo name for comparison."""
return name.lower().replace("_", "-").replace(".git", "").strip()
def scan_file_for_deps(filepath: str, content: str, own_repo: str) -> set:
"""Scan a file's content for references to other repos."""
deps = set()
own_norm = normalize_repo_name(own_repo)
for repo in KNOWN_REPOS:
repo_norm = normalize_repo_name(repo)
if repo_norm == own_norm:
continue
# Direct name references
patterns = [
repo, # exact name
repo.replace("-", "_"), # underscore variant
repo.replace("-", ""), # no separator
f"/{repo}/", # path reference
f'"{repo}"', # quoted
f"'{repo}'", # single quoted
f"Timmy_Foundation/{repo}", # full Gitea path
f"Timmy_Foundation.{repo}", # Python module path
]
for pattern in patterns:
if pattern in content:
deps.add(repo)
break
return deps
def scan_repo(repo_path: str, repo_name: str = None) -> dict:
"""Scan a repo directory for dependencies."""
path = Path(repo_path)
if not path.is_dir():
return {"error": f"Not a directory: {repo_path}"}
if not repo_name:
repo_name = path.name
deps = set()
files_scanned = 0
exts = {".py", ".js", ".ts", ".go", ".yaml", ".yml", ".toml", ".json",
".md", ".sh", ".bash", ".Dockerfile", ".tf", ".hcl"}
for fpath in path.rglob("*"):
if not fpath.is_file():
continue
if fpath.suffix not in exts:
continue
# Skip common non-source dirs
parts = fpath.parts
if any(p in (".git", "node_modules", "__pycache__", ".venv", "venv",
"vendor", "dist", "build", ".tox") for p in parts):
continue
try:
content = fpath.read_text(errors="ignore")
except:
continue
file_deps = scan_file_for_deps(str(fpath), content, repo_name)
deps.update(file_deps)
files_scanned += 1
return {
"repo": repo_name,
"dependencies": sorted(deps),
"files_scanned": files_scanned,
}
def detect_cycles(graph: dict) -> list:
"""Detect circular dependencies using DFS."""
cycles = []
visited = set()
rec_stack = set()
def dfs(node, path):
visited.add(node)
rec_stack.add(node)
for neighbor in graph.get(node, {}).get("dependencies", []):
if neighbor not in visited:
result = dfs(neighbor, path + [neighbor])
if result:
return result
elif neighbor in rec_stack:
cycle_start = path.index(neighbor)
return path[cycle_start:] + [neighbor]
rec_stack.remove(node)
return None
for node in graph:
if node not in visited:
cycle = dfs(node, [node])
if cycle:
cycles.append(cycle)
return cycles
def to_dot(graph: dict) -> str:
"""Generate DOT format output."""
lines = ["digraph dependencies {"]
lines.append(" rankdir=LR;")
lines.append(" node [shape=box, style=filled, fillcolor="#1a1a2e", fontcolor="#e6edf3"];")
lines.append(" edge [color="#4a4a6a"];")
lines.append("")
for repo, data in sorted(graph.items()):
dep_count = len(data.get("dependencies", []))
fill = "#2d1b69" if dep_count > 2 else "#16213e"
lines.append(f' "{repo}" [fillcolor="{fill}"];')
for dep in data.get("dependencies", []):
lines.append(f' "{repo}" -> "{dep}";')
lines.append("}")
return "\n".join(lines)
def to_mermaid(graph: dict) -> str:
"""Generate Mermaid format output."""
lines = ["graph LR"]
for repo, data in sorted(graph.items()):
for dep in data.get("dependencies", []):
lines.append(f" {repo.replace('-','_')} --> {dep.replace('-','_')}")
# Add node labels
lines.append("")
for repo in sorted(graph.keys()):
lines.append(f" {repo.replace('-','_')}[{repo}]")
return "\n".join(lines)
def main():
parser = argparse.ArgumentParser(description="Build cross-repo dependency graph")
parser.add_argument("repos_dir", nargs="?", help="Directory containing repos")
parser.add_argument("--repos", help="Comma-separated list of repo paths")
parser.add_argument("--format", choices=["dot", "mermaid", "json"], default="json")
parser.add_argument("--output", "-o", help="Output file (default: stdout)")
parser.add_argument("--cycles-only", action="store_true", help="Only report cycles")
args = parser.parse_args()
results = {}
repo_paths = []
if args.repos:
repo_paths = [p.strip() for p in args.repos.split(",")]
elif args.repos_dir:
base = Path(args.repos_dir)
repo_paths = [str(p) for p in base.iterdir() if p.is_dir() and not p.name.startswith(".")]
else:
parser.print_help()
sys.exit(1)
for rpath in repo_paths:
name = Path(rpath).name
print(f"Scanning {name}...", file=sys.stderr)
result = scan_repo(rpath, name)
if "error" not in result:
results[name] = result
# Detect cycles
cycles = detect_cycles(results)
if args.cycles_only:
if cycles:
print("CIRCULAR DEPENDENCIES DETECTED:")
for cycle in cycles:
print(f" {' -> '.join(cycle)}")
sys.exit(1)
else:
print("No circular dependencies found.")
sys.exit(0)
# Output
output = {}
if args.format == "dot":
output = to_dot(results)
elif args.format == "mermaid":
output = to_mermaid(results)
else:
output = json.dumps({
"repos": results,
"cycles": cycles,
"summary": {
"total_repos": len(results),
"total_deps": sum(len(r["dependencies"]) for r in results.values()),
"cycles_found": len(cycles),
}
}, indent=2)
if args.output:
Path(args.output).write_text(output)
print(f"Written to {args.output}", file=sys.stderr)
else:
print(output)
if __name__ == "__main__":
main()

View File

@@ -0,0 +1,131 @@
#!/usr/bin/env python3
"""
Knowledge Store Staleness Detector — Detect stale knowledge entries by comparing source file hashes.
Usage:
python3 scripts/knowledge_staleness_check.py --index knowledge/index.json
python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --json
python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --fix
"""
import argparse
import hashlib
import json
import os
import sys
from datetime import datetime, timezone
from pathlib import Path
from typing import Dict, List, Any, Optional
def compute_file_hash(filepath: str) -> Optional[str]:
"""Compute SHA-256 hash of a file. Returns None if file doesn't exist."""
try:
with open(filepath, "rb") as f:
return "sha256:" + hashlib.sha256(f.read()).hexdigest()
except (FileNotFoundError, IsADirectoryError, PermissionError):
return None
def check_staleness(index_path: str, repo_root: str = ".") -> List[Dict[str, Any]]:
"""Check all entries in knowledge index for staleness.
Returns list of entries with staleness info:
- status: "fresh" | "stale" | "missing_source" | "no_hash"
- current_hash: computed hash (if source exists)
- stored_hash: hash from index
"""
with open(index_path) as f:
data = json.load(f)
facts = data.get("facts", [])
results = []
for entry in facts:
source_file = entry.get("source_file")
stored_hash = entry.get("source_hash")
if not source_file:
results.append({**entry, "status": "no_source", "current_hash": None})
continue
full_path = os.path.join(repo_root, source_file)
current_hash = compute_file_hash(full_path)
if current_hash is None:
results.append({**entry, "status": "missing_source", "current_hash": None})
elif not stored_hash:
results.append({**entry, "status": "no_hash", "current_hash": current_hash})
elif current_hash != stored_hash:
results.append({**entry, "status": "stale", "current_hash": current_hash})
else:
results.append({**entry, "status": "fresh", "current_hash": current_hash})
return results
def fix_hashes(index_path: str, repo_root: str = ".") -> int:
"""Add hashes to entries missing them. Returns count of fixed entries."""
with open(index_path) as f:
data = json.load(f)
fixed = 0
for entry in data.get("facts", []):
if entry.get("source_hash"):
continue
source_file = entry.get("source_file")
if not source_file:
continue
full_path = os.path.join(repo_root, source_file)
h = compute_file_hash(full_path)
if h:
entry["source_hash"] = h
fixed += 1
with open(index_path, "w") as f:
json.dump(data, f, indent=2)
return fixed
def main():
parser = argparse.ArgumentParser(description="Check knowledge store staleness")
parser.add_argument("--index", required=True, help="Path to knowledge/index.json")
parser.add_argument("--repo", default=".", help="Repo root for source file resolution")
parser.add_argument("--json", action="store_true", help="Output as JSON")
parser.add_argument("--fix", action="store_true", help="Add hashes to entries missing them")
args = parser.parse_args()
if args.fix:
fixed = fix_hashes(args.index, args.repo)
print(f"Fixed {fixed} entries with missing hashes.")
return
results = check_staleness(args.index, args.repo)
if args.json:
print(json.dumps(results, indent=2))
else:
stale = [r for r in results if r["status"] != "fresh"]
fresh = [r for r in results if r["status"] == "fresh"]
print(f"Knowledge Store Staleness Check")
print(f" Total entries: {len(results)}")
print(f" Fresh: {len(fresh)}")
print(f" Stale/Issues: {len(stale)}")
print()
if stale:
print("Issues found:")
for r in stale:
status = r["status"]
fact = r.get("fact", "?")[:60]
source = r.get("source_file", "?")
print(f" [{status}] {source}: {fact}")
else:
print("All entries are fresh!")
if __name__ == "__main__":
main()

View File

@@ -0,0 +1,129 @@
#!/usr/bin/env python3
"""Tests for scripts/knowledge_staleness_check.py — 8 tests."""
import json
import os
import sys
import tempfile
sys.path.insert(0, os.path.dirname(__file__) or ".")
import importlib.util
spec = importlib.util.spec_from_file_location("ks", os.path.join(os.path.dirname(__file__) or ".", "knowledge_staleness_check.py"))
mod = importlib.util.module_from_spec(spec)
spec.loader.exec_module(mod)
check_staleness = mod.check_staleness
fix_hashes = mod.fix_hashes
compute_file_hash = mod.compute_file_hash
def test_fresh_entry():
with tempfile.TemporaryDirectory() as tmpdir:
src = os.path.join(tmpdir, "source.py")
with open(src, "w") as f:
f.write("print('hello')")
h = compute_file_hash(src)
idx = os.path.join(tmpdir, "index.json")
with open(idx, "w") as f:
json.dump({"facts": [{"fact": "hello", "source_file": "source.py", "source_hash": h}]}, f)
results = check_staleness(idx, tmpdir)
assert results[0]["status"] == "fresh"
print("PASS: test_fresh_entry")
def test_stale_entry():
with tempfile.TemporaryDirectory() as tmpdir:
src = os.path.join(tmpdir, "source.py")
with open(src, "w") as f:
f.write("original content")
idx = os.path.join(tmpdir, "index.json")
with open(idx, "w") as f:
json.dump({"facts": [{"fact": "old", "source_file": "source.py", "source_hash": "sha256:wrong"}]}, f)
# Now change the source
with open(src, "w") as f:
f.write("modified content")
results = check_staleness(idx, tmpdir)
assert results[0]["status"] == "stale"
print("PASS: test_stale_entry")
def test_missing_source():
with tempfile.TemporaryDirectory() as tmpdir:
idx = os.path.join(tmpdir, "index.json")
with open(idx, "w") as f:
json.dump({"facts": [{"fact": "gone", "source_file": "nonexistent.py", "source_hash": "sha256:abc"}]}, f)
results = check_staleness(idx, tmpdir)
assert results[0]["status"] == "missing_source"
print("PASS: test_missing_source")
def test_no_hash():
with tempfile.TemporaryDirectory() as tmpdir:
src = os.path.join(tmpdir, "source.py")
with open(src, "w") as f:
f.write("content")
idx = os.path.join(tmpdir, "index.json")
with open(idx, "w") as f:
json.dump({"facts": [{"fact": "no hash", "source_file": "source.py"}]}, f)
results = check_staleness(idx, tmpdir)
assert results[0]["status"] == "no_hash"
assert results[0]["current_hash"].startswith("sha256:")
print("PASS: test_no_hash")
def test_no_source_field():
with tempfile.TemporaryDirectory() as tmpdir:
idx = os.path.join(tmpdir, "index.json")
with open(idx, "w") as f:
json.dump({"facts": [{"fact": "orphan"}]}, f)
results = check_staleness(idx, tmpdir)
assert results[0]["status"] == "no_source"
print("PASS: test_no_source_field")
def test_fix_hashes():
with tempfile.TemporaryDirectory() as tmpdir:
src = os.path.join(tmpdir, "source.py")
with open(src, "w") as f:
f.write("content for hashing")
idx = os.path.join(tmpdir, "index.json")
with open(idx, "w") as f:
json.dump({"facts": [{"fact": "needs hash", "source_file": "source.py"}]}, f)
fixed = fix_hashes(idx, tmpdir)
assert fixed == 1
# Verify hash was added
with open(idx) as f:
data = json.load(f)
assert data["facts"][0]["source_hash"].startswith("sha256:")
print("PASS: test_fix_hashes")
def test_empty_index():
with tempfile.TemporaryDirectory() as tmpdir:
idx = os.path.join(tmpdir, "index.json")
with open(idx, "w") as f:
json.dump({"facts": []}, f)
results = check_staleness(idx, tmpdir)
assert results == []
print("PASS: test_empty_index")
def test_compute_hash_nonexistent():
h = compute_file_hash("/nonexistent/path/file.py")
assert h is None
print("PASS: test_compute_hash_nonexistent")
def run_all():
test_fresh_entry()
test_stale_entry()
test_missing_source()
test_no_hash()
test_no_source_field()
test_fix_hashes()
test_empty_index()
test_compute_hash_nonexistent()
print("\nAll 8 tests passed!")
if __name__ == "__main__":
run_all()