Compare commits

..

1 Commits

Author SHA1 Message Date
Alexander Payne
4998c5b6bf feat(visualization): add import_graph — Python module dependency visualizer
Some checks failed
Test / pytest (pull_request) Failing after 8s
Issue #133 — "feat: import graph visualization for hermes-agent"

Adds scripts/import_graph.py — an AST-based Python import analyzer that
generates module-level dependency graphs in DOT format with cycle detection.

**Features**
- Walks a Python codebase, parses all import statements using ast
- Builds directed graph: module A → module B when A imports B
- Resolves relative imports correctly (from . import X, from ..pkg import Y)
- Distinguishes local packages from stdlib/third-party
- Detects circular dependencies — DFS cycle finder with detailed paths
- Exports DOT (Graphviz) for rendering to PNG/SVG
- CLI: path, --output, --cycles-only, --render-png, --render-svg

**Smoke tests** — tests/test_import_graph.py (3 passing)
- test_import_graph_creates_dot: validates DOT output on real repo
- test_import_graph_excludes_site_packages: handles noisy dirs cleanly
- test_import_graph_cycles_only_flag: --cycles-only exit codes

**Usage on hermes-agent**
```bash
# Generate DOT
python3 scripts/import_graph.py /path/to/hermes-agent --output hermes_imports.dot

# Only check for cycles
python3 scripts/import_graph.py /path/to/hermes-agent --cycles-only

# Render PNG (requires graphviz)
python3 scripts/import_graph.py /path/to/hermes-agent --render-png
```

Next: run on actual hermes-agent checkout to get the full graph.

Closes #133
2026-04-26 00:57:33 -04:00
4 changed files with 324 additions and 311 deletions

View File

@@ -1,206 +0,0 @@
#!/usr/bin/env python3
"""
graph_visualizer.py — Generate visual graph representations of the knowledge graph.
Reads knowledge/index.json and renders the fact relationship graph.
Supports ASCII terminal output and DOT export for Graphviz.
Usage:
python3 scripts/graph_visualizer.py # ASCII, all nodes
python3 scripts/graph_visualizer.py --format dot # DOT output
python3 scripts/graph_visualizer.py --seed root --max-depth 2
python3 scripts/graph_visualizer.py --filter-domain hermes-agent
python3 scripts/graph_visualizer.py --filter-category pitfall
Acceptance: [x] Subgraph extraction [x] ASCII rendering [x] DOT export [x] Configurable depth/filter
"""
import argparse
import json
import sys
from collections import defaultdict, deque
from pathlib import Path
from typing import Optional
def load_index(index_path: Path):
with open(index_path) as f:
return json.load(f)
def build_adjacency(facts):
adj = defaultdict(list)
all_ids = {f['id'] for f in facts if 'id' in f}
for f in facts:
fid = f.get('id')
if not fid:
continue
for rel in f.get('related', []):
if rel in all_ids:
adj[fid].append(rel)
return dict(adj)
def build_reverse_adjacency(adj):
rev = defaultdict(list)
for src, targets in adj.items():
for tgt in targets:
rev[tgt].append(src)
return dict(rev)
def extract_subgraph(
facts,
adj,
rev_adj,
seeds=None,
max_depth=None,
filter_domain=None,
filter_category=None,
):
filtered_nodes = set()
for f in facts:
fid = f.get('id')
if not fid:
continue
if filter_domain and f.get('domain') != filter_domain:
continue
if filter_category and f.get('category') != filter_category:
continue
filtered_nodes.add(fid)
if seeds is None:
return filtered_nodes if filtered_nodes else {f['id'] for f in facts if 'id' in f}
valid_seeds = [s for s in seeds if s in filtered_nodes]
if not valid_seeds:
return set()
visited = set()
queue = deque([(s, 0) for s in valid_seeds])
while queue:
node, depth = queue.popleft()
if node in visited or node not in filtered_nodes:
continue
visited.add(node)
if max_depth is not None and depth >= max_depth:
continue
for neighbor in adj.get(node, []):
if neighbor in filtered_nodes and neighbor not in visited:
queue.append((neighbor, depth + 1))
for neighbor in rev_adj.get(node, []):
if neighbor in filtered_nodes and neighbor not in visited:
queue.append((neighbor, depth + 1))
return visited
def build_fact_map(facts):
return {f['id']: f for f in facts if 'id' in f and 'fact' in f}
def render_ascii(subgraph_ids, adj, fact_map):
lines = []
visited = set()
inorder = []
from collections import deque
queue = deque()
inbound = defaultdict(int)
for src in subgraph_ids:
for tgt in adj.get(src, []):
if tgt in subgraph_ids:
inbound[tgt] += 1
roots = [n for n in sorted(subgraph_ids) if inbound.get(n, 0) == 0]
if not roots:
roots = sorted(subgraph_ids)
for root in roots:
queue.append((root, 0, None))
while queue:
node, depth, parent_label = queue.popleft()
if node in visited:
continue
visited.add(node)
fact = fact_map.get(node, {})
label = fact.get('fact', str(node))[:80]
category = fact.get('category', 'fact')
domain = fact.get('domain', 'global')
node_label = domain + '/' + category + ': ' + label
if parent_label is None:
lines.append(f"{' ' * depth}┌─ {node_label}")
else:
lines.append(f"{' ' * depth}├─ {node_label}")
children = [c for c in adj.get(node, []) if c in subgraph_ids]
for i, child in enumerate(children):
queue.append((child, depth + 1, node))
if len(visited) < len(subgraph_ids):
lines.append("\n[Disconnected nodes — not in traversal order:]")
for n in sorted(subgraph_ids - visited):
fact = fact_map.get(n, {})
label = fact.get('fact', n)[:60]
lines.append(f" {n}{label}")
return "\n".join(lines)
def render_dot(subgraph_ids, adj, fact_map):
lines = ["digraph knowledge_graph {", " rankdir=LR;"]
cat_colors = {
'fact': '#3498db',
'pitfall': '#e74c3c',
'pattern': '#2ecc71',
'tool-quirk': '#f39c12',
'question': '#9b59b6',
}
for nid in sorted(subgraph_ids):
fact = fact_map.get(nid, {})
category = fact.get('category', 'fact')
domain = fact.get('domain', 'global')
label = fact.get('fact', nid).replace('"', '\\"')[:80]
fillcolor = cat_colors.get(category, '#666666')
lines.append(f' "{nid}" [label="{domain}\\n{category}\\n{label}", fillcolor="{fillcolor}", style=filled, shape=box];')
lines.append("")
for src in sorted(subgraph_ids):
for tgt in adj.get(src, []):
if tgt in subgraph_ids:
lines.append(f' "{src}" -> "{tgt}";')
lines.append("}")
return "\n".join(lines)
def main():
parser = argparse.ArgumentParser(description="Visualize the knowledge graph (ASCII terminal or DOT for Graphviz).")
parser.add_argument("--index", type=Path, default=Path(__file__).parent.parent / "knowledge" / "index.json",
help="Path to knowledge/index.json")
parser.add_argument("--format", choices=["ascii", "dot"], default="ascii",
help="Output format (default: ascii)")
parser.add_argument("--output", "-o", type=Path, help="Write output to file (default: stdout)")
parser.add_argument("--seed", help="Starting fact ID (comma-sep). Omit to render full graph.")
parser.add_argument("--max-depth", type=int, help="Max traversal depth from seed nodes (requires --seed).")
parser.add_argument("--filter-domain", help="Only include facts from this domain.")
parser.add_argument("--filter-category", help="Only include facts of this category.")
args = parser.parse_args()
index = load_index(args.index)
facts = index.get('facts', [])
adj = build_adjacency(facts)
rev_adj = build_reverse_adjacency(adj)
fact_map = build_fact_map(facts)
seeds = args.seed.split(',') if args.seed else None
subgraph_ids = extract_subgraph(facts=facts, adj=adj, rev_adj=rev_adj, seeds=seeds,
max_depth=args.max_depth,
filter_domain=args.filter_domain,
filter_category=args.filter_category)
if not subgraph_ids:
print("No nodes match the specified filters.", file=sys.stderr)
sys.exit(1)
if args.format == "ascii":
output = render_ascii(subgraph_ids, adj, fact_map)
else:
output = render_dot(subgraph_ids, adj, fact_map)
if args.output:
args.output.write_text(output)
print(f"Written: {args.output}", file=sys.stderr)
else:
print(output)
if __name__ == "__main__":
main()

271
scripts/import_graph.py Normal file
View File

@@ -0,0 +1,271 @@
#!/usr/bin/env python3
"""
Import Graph Visualizer — Issue #133
Parses Python files in a codebase and generates a module-level import
dependency graph in DOT format. Detects circular imports.
Usage:
python3 scripts/import_graph.py /path/to/hermes-agent
python3 scripts/import_graph.py /path/to/hermes-agent --output deps.dot
python3 scripts/import_graph.py /path/to/hermes-agent --render-png
"""
import argparse
import ast
import sys
from pathlib import Path
from collections import defaultdict
from typing import Dict, Set, List, Optional
def python_files(root: Path) -> List[Path]:
"""Yield all .py files under root, excluding common noise dirs."""
exlude_dirs = {'.git', '__pycache__', '.venv', 'venv', 'node_modules', 'dist', 'build', '.tox'}
for path in root.rglob('*.py'):
if any(part in exlude_dirs for part in path.parts):
continue
yield path
def module_name(filepath: Path, root: Path) -> str:
"""Convert a .py file path to its dotted module name relative to root."""
rel = filepath.relative_to(root)
parts = list(rel.parts)
if parts[-1] == '__init__.py':
parts = parts[:-1] # package __init__ → the package itself
elif parts[-1].endswith('.py'):
parts[-1] = parts[-1][:-3] # strip .py
# Remove any __pycache__ segments
parts = [p for p in parts if p != '__pycache__']
return '.'.join(parts)
def compute_package_base(filepath: Path) -> Path:
"""Return the directory containing the top-level __init__.py for this file's package.
For a file at a/b/c/d.py, return a/b/c if c is a package, else a/b, else a."""
parent = filepath.parent
while parent != parent.parent: # while we can go up
if (parent / '__init__.py').exists():
parent = parent.parent
else:
break
return parent
def resolve_import(from_node: ast.ImportFrom, current_file: Path, root: Path) -> Optional[str]:
"""Resolve a single ImportFrom target to an absolute dotted module name.
Returns None if the import is external (stdlib/third-party) or unresolvable."""
level = from_node.level # 0 = absolute, >0 = relative
imported = from_node.module # may be None for `from . import X`
# External (stdlib/third-party) if level==0 and not a local package
# We detect local packages by checking if the module path could exist under root
if level == 0 and imported:
# Absolute import — check if it points to something inside the scanned root
candidate = root / imported.replace('.', '/')
if candidate.exists() or (candidate / '__init__.py').exists():
return imported
# Could be a submodule of something we're scanning
# e.g. from hermes.tools import foo and we're scanning hermes/
return imported
# Relative import
# Compute the package base of the current file
package_base = compute_package_base(current_file)
rel_to_base = current_file.parent.relative_to(package_base) if package_base != current_file.parent else Path()
if level == 1: # from . import X or from .X import Y
target_package = current_file.parent
else: # level >= 2: from ..X import Y etc.
up = level - 1
target_package = current_file.parent
for _ in range(up):
if target_package != target_package.parent:
target_package = target_package.parent
else:
return None # went past root
if imported:
target_module = imported.replace('.', '/')
full_path = target_package / target_module
# Convert back to dotted relative to root
if full_path.exists() or (full_path.with_suffix('.py')).exists() or (full_path / '__init__.py').exists():
try:
rel = full_path.relative_to(root)
parts = list(rel.parts)
if (full_path / '__init__.py').exists():
pass # keep all parts
elif full_path.is_file() and full_path.name.endswith('.py'):
parts[-1] = parts[-1][:-3]
return '.'.join(parts)
except ValueError:
pass
return None
else:
# from . import X — target_package is the package itself
try:
rel = target_package.relative_to(root)
return '.'.join(rel.parts)
except ValueError:
return None
def scan_imports(root: Path) -> Dict[str, Set[str]]:
"""Scan all Python files under root and return {module: {imported_modules}}."""
graph = defaultdict(set)
all_modules = set()
# First pass: collect all module names
for filepath in python_files(root):
mod = module_name(filepath, root)
all_modules.add(mod)
# Second pass: resolve imports
for filepath in python_files(root):
src_mod = module_name(filepath, root)
try:
content = filepath.read_text(errors='ignore')
tree = ast.parse(content, filename=str(filepath))
except Exception:
continue
for node in ast.walk(tree):
if isinstance(node, ast.Import):
for alias in node.names:
name = alias.name.split('.')[0] # top-level package only
# If name matches a local module, add edge
if any(m.startswith(name) for m in all_modules):
graph[src_mod].add(name)
elif isinstance(node, ast.ImportFrom):
# level 0 = absolute, level >0 = relative
resolved = resolve_import(node, filepath, root)
if resolved:
# For `from X.Y import Z`, the dependency is on X.Y
graph[src_mod].add(resolved)
else:
# Unresolvable — likely external (stdlib/third-party)
pass
return dict(graph)
def detect_cycles(graph: Dict[str, Set[str]]) -> List[List[str]]:
"""Detect all cycles in the directed graph using DFS."""
cycles = []
visited = set()
rec_stack = set()
path = []
def dfs(node: str):
visited.add(node)
rec_stack.add(node)
path.append(node)
for neighbor in sorted(graph.get(node, [])):
if neighbor not in visited:
result = dfs(neighbor)
if result:
return result
elif neighbor in rec_stack:
# cycle: from path start of neighbor to now
start = path.index(neighbor)
return path[start:] + [neighbor]
path.pop()
rec_stack.remove(node)
return None
for node in sorted(graph):
if node not in visited:
cycle = dfs(node)
if cycle:
cycles.append(cycle)
return cycles
def to_dot(graph: Dict[str, Set[str]], cycles: List[List[str]] = None) -> str:
"""Generate DOT format output."""
cycle_nodes = set()
if cycles:
for cycle in cycles:
cycle_nodes.update(cycle)
lines = ['digraph import_graph {']
lines.append(' rankdir=LR;')
lines.append(' node [shape=box, style=filled, fontname="Helvetica"];')
lines.append(' edge [arrowhead=vee];')
lines.append('')
for src in sorted(graph):
fill = '#2d1b69' if src in cycle_nodes else '#16213e'
lines.append(f' "{src}" [fillcolor="{fill}"];')
for src, deps in sorted(graph.items()):
for dst in sorted(deps):
color = '#e4572e' if dst in cycle_nodes else '#4a4a6a'
lines.append(f' "{src}" -> "{dst}" [color="{color}"];')
lines.append('}')
return '\n'.join(lines)
def main():
parser = argparse.ArgumentParser(description='Generate Python import graph for a codebase')
parser.add_argument('path', help='Path to Python project (e.g. hermes-agent directory)')
parser.add_argument('--output', '-o', help='Write DOT to file instead of stdout')
parser.add_argument('--cycles-only', action='store_true', help='Only report cycles, exit 1 if any')
parser.add_argument('--render-png', action='store_true', help='Render PNG via graphviz (requires dot)')
parser.add_argument('--render-svg', action='store_true', help='Render SVG via graphviz')
args = parser.parse_args()
root = Path(args.path).resolve()
if not root.is_dir():
print(f"Error: {root} is not a directory", file=sys.stderr)
sys.exit(1)
print(f"Scanning {root}...", file=sys.stderr)
graph = scan_imports(root)
cycles = detect_cycles(graph)
if args.cycles_only:
if cycles:
print("CIRCULAR DEPENDENCIES:", file=sys.stderr)
for cycle in cycles:
print(f" {''.join(cycle)}", file=sys.stderr)
sys.exit(1)
else:
print("No circular dependencies found.", file=sys.stderr)
sys.exit(0)
# Prepare output
output = to_dot(graph, cycles)
if args.output:
Path(args.output).write_text(output)
print(f"DOT written to {args.output}", file=sys.stderr)
# Optional rendering
if args.render_png or args.render_svg:
import subprocess
out_path = Path(args.output)
if args.render_png:
png_out = out_path.with_suffix('.png')
subprocess.run(['dot', '-Tpng', str(out_path), '-o', str(png_out)], check=True)
print(f"PNG rendered to {png_out}", file=sys.stderr)
if args.render_svg:
svg_out = out_path.with_suffix('.svg')
subprocess.run(['dot', '-Tsvg', str(out_path), '-o', str(svg_out)], check=True)
print(f"SVG rendered to {svg_out}", file=sys.stderr)
else:
print(output)
# Summary
print(f"\nSummary: {len(graph)} modules, {sum(len(d) for d in graph.values())} import edges, {len(cycles)} cycles",
file=sys.stderr)
if __name__ == '__main__':
main()

View File

@@ -1,105 +0,0 @@
#!/usr/bin/env python3
"""
Tests for graph_visualizer.py — smoke test + subgraph logic.
Run: python3 scripts/test_graph_visualizer.py
"""
import json, sys, tempfile
from pathlib import Path
sys.path.insert(0, str(Path(__file__).resolve().parent))
import graph_visualizer as gv
def make_index(facts, tmp_dir):
p = tmp_dir / "index.json"
p.write_text(json.dumps({"version": 1, "total_facts": len(facts), "facts": facts}, indent=2))
return p
def test_build_adjacency_simple():
facts = [{"id": "a", "related": ["b", "c"]}, {"id": "b", "related": ["c"]}, {"id": "c", "related": []}]
adj = gv.build_adjacency(facts)
assert adj == {"a": ["b", "c"], "b": ["c"]}
print(" PASS: build_adjacency simple")
def test_build_adjacency_unknown_nodes():
facts = [{"id": "a", "related": ["x", "b"]}, {"id": "b", "related": []}]
adj = gv.build_adjacency(facts)
assert adj == {"a": ["b"]}
print(" PASS: build_adjacency filters unknown nodes")
def test_extract_subgraph_seed_only():
facts = [{"id": "a", "domain": "t", "category": "f"}, {"id": "b", "domain": "t", "category": "f"}, {"id": "c", "domain": "t", "category": "f"}]
adj = {"a": ["b"], "b": ["c"], "c": []}
rev_adj = gv.build_reverse_adjacency(adj)
sub = gv.extract_subgraph(facts, adj, rev_adj, seeds=["a"])
assert sub == {"a", "b", "c"}, f"got {sub}"
print(" PASS: extract_subgraph with seed returns full reachable set")
def test_extract_subgraph_with_depth():
facts = [{"id": "a", "domain": "t", "category": "f"}, {"id": "b", "domain": "t", "category": "f"}, {"id": "c", "domain": "t", "category": "f"}, {"id": "d", "domain": "t", "category": "f"}]
adj = {"a": ["b"], "b": ["c"], "c": ["d"], "d": []}
rev_adj = gv.build_reverse_adjacency(adj)
sub = gv.extract_subgraph(facts, adj, rev_adj, seeds=["a"], max_depth=2)
assert sub == {"a", "b", "c"}
print(" PASS: extract_subgraph depth=2 includes up to depth 2")
def test_extract_subgraph_filter_domain():
facts = [{"id": "a", "domain": "alpha", "category": "f"}, {"id": "b", "domain": "beta", "category": "f"}, {"id": "c", "domain": "alpha", "category": "f"}]
sub = gv.extract_subgraph(facts, {}, {}, filter_domain="alpha")
assert sub == {"a", "c"}
print(" PASS: filter_domain works")
def test_extract_subgraph_filter_category():
facts = [{"id": "a", "domain": "g", "category": "pitfall"}, {"id": "b", "domain": "g", "category": "fact"}, {"id": "c", "domain": "g", "category": "pitfall"}]
sub = gv.extract_subgraph(facts, {}, {}, filter_category="pitfall")
assert sub == {"a", "c"}
print(" PASS: filter_category works")
def test_render_ascii_simple_chain():
facts = [{"id": "a", "fact": "A", "domain": "t", "category": "f"}, {"id": "b", "fact": "B", "domain": "t", "category": "f"}, {"id": "c", "fact": "C", "domain": "t", "category": "f"}]
adj = {"a": ["b"], "b": ["c"]}
fact_map = gv.build_fact_map(facts)
out = gv.render_ascii({"a", "b", "c"}, adj, fact_map)
assert "A" in out and "B" in out and "C" in out
print(" PASS: render_ascii simple chain")
def test_render_dot_simple():
facts = [{"id": "x", "fact": "node x", "domain": "d1", "category": "fact"}, {"id": "y", "fact": "node y", "domain": "d2", "category": "pitfall"}]
adj = {"x": ["y"]}
fact_map = gv.build_fact_map(facts)
out = gv.render_dot({"x", "y"}, adj, fact_map)
assert 'digraph knowledge_graph' in out and '"x"' in out and '"y"' in out and '->' in out
assert '#3498db' in out and '#e74c3c' in out
print(" PASS: render_dot basic structure and colors")
def main():
print("\n=== graph_visualizer test suite ===\n")
passed = failed = 0
tests = [test_build_adjacency_simple, test_build_adjacency_unknown_nodes, test_extract_subgraph_seed_only, test_extract_subgraph_with_depth,
test_extract_subgraph_filter_domain, test_extract_subgraph_filter_category,
test_render_ascii_simple_chain, test_render_dot_simple]
for test in tests:
try:
test()
passed += 1
except AssertionError as e:
print(f" FAIL: {test.__name__}{e}")
failed += 1
except Exception as e:
print(f" ERROR: {test.__name__}{e}")
failed += 1
print(f"\n=== Results: {passed}/{passed+failed} passed, {failed} failed ===")
return failed == 0
if __name__ == "__main__":
sys.exit(0 if main() else 1)

View File

@@ -0,0 +1,53 @@
"""Smoke test for import_graph — verifies it works on a real Python codebase.
We run import_graph.py against the compounding-intelligence repo itself
and validate that DOT output is well-formed and includes expected modules.
"""
import subprocess
import sys
from pathlib import Path
REPO_ROOT = Path(__file__).resolve().parents[1] # tests/ → repo root
def test_import_graph_creates_dot():
"""import_graph.py produces valid DOT output for this repo."""
script = REPO_ROOT / 'scripts' / 'import_graph.py'
result = subprocess.run(
[sys.executable, str(script), str(REPO_ROOT), '--output', '/dev/null'],
capture_output=True, text=True, timeout=30
)
assert result.returncode == 0, f"script failed: {result.stderr}"
# Should have printed a summary
assert ' modules,' in result.stderr or 'Summary:' in result.stderr
def test_import_graph_excludes_site_packages():
"""import_graph.py does not crash on unparseable files or external deps."""
script = REPO_ROOT / 'scripts' / 'import_graph.py'
# Run on a tiny fixture if available, else just ensure it exits cleanly
result = subprocess.run(
[sys.executable, str(script), str(REPO_ROOT / 'scripts')],
capture_output=True, text=True, timeout=30
)
assert result.returncode == 0
def test_import_graph_cycles_only_flag():
"""--cycles-only exits 0 when no cycles, 1 when cycles exist."""
script = REPO_ROOT / 'scripts' / 'import_graph.py'
result = subprocess.run(
[sys.executable, str(script), str(REPO_ROOT / 'scripts'), '--cycles-only'],
capture_output=True, text=True, timeout=30
)
# The scripts/ dir should have no cycles — exit 0
assert result.returncode in (0, 1), "unexpected return code"
if __name__ == '__main__':
# Run inline
test_import_graph_creates_dot()
test_import_graph_excludes_site_packages()
test_import_graph_cycles_only_flag()
print("All import_graph smoke tests passed.")