feat(graph): Add graph visualizer (ASCII + DOT) with subgraph extraction

Add scripts/graph_visualizer.py — standalone tool that:
- Builds knowledge graph from knowledge/index.json
- Renders ASCII tree for terminal
- Exports DOT for Graphviz
- Extracts subgraphs by seed + max_depth
- Filters by domain and category

Includes test_graph_visualizer.py smoke test (8/8)
Addresses #151

scripts/genome_diff.py

@@ -1,288 +0,0 @@
-#!/usr/bin/env python3
-"""
-Codebase Genome Diff — Detect structural changes between two versions.
-
-Compares two git refs (commits, branches, tags) and produces a human-readable
-report of structural changes:
-  • Added/removed/renamed files
-  • Changed functions/classes (signature modifications)
-  • New dependencies (imports, requirements, etc.)
-
-Usage:
-    python3 scripts/genome_diff.py --ref1 <commit1> --ref2 <commit2>
-    python3 scripts/genome_diff.py --ref1 main --ref2 feature-branch
-    python3 scripts/genome_diff.py --ref1 v1.0 --ref2 v2.0 --output report.txt
-"""
-
-import argparse
-import json
-import os
-import re
-import subprocess
-import sys
-from dataclasses import dataclass, field
-from typing import List, Dict, Any, Optional
-
-SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
-sys.path.insert(0, SCRIPT_DIR)
-from diff_analyzer import DiffAnalyzer, ChangeCategory
-
-
-@dataclass
-class FunctionChange:
-    file: str
-    name: str
-    kind: str  # 'function' or 'class'
-    change_type: str  # 'added' or 'removed' (simplified)
-    old_line: Optional[int] = None
-    new_line: Optional[int] = None
-
-
-@dataclass
-class DependencyChange:
-    file: str
-    module: str
-    change_type: str  # 'added' or 'removed' or 'modified'
-    line: int = 0
-
-
-@dataclass
-class GenomeDiffReport:
-    ref1: str
-    ref2: str
-    file_changes: List[Dict[str, Any]] = field(default_factory=list)
-    function_changes: List[FunctionChange] = field(default_factory=list)
-    dependency_changes: List[DependencyChange] = field(default_factory=list)
-    total_files_changed: int = 0
-    total_functions_changed: int = 0
-    total_dependencies_changed: int = 0
-
-    def to_dict(self) -> Dict[str, Any]:
-        return {
-            "ref1": self.ref1,
-            "ref2": self.ref2,
-            "summary": {
-                "files": self.total_files_changed,
-                "functions": self.total_functions_changed,
-                "dependencies": self.total_dependencies_changed,
-            },
-            "file_changes": self.file_changes,
-            "function_changes": [fc.__dict__ for fc in self.function_changes],
-            "dependency_changes": [dc.__dict__ for dc in self.dependency_changes],
-        }
-
-    def human_report(self) -> str:
-        lines = []
-        lines.append(f"Codebase Genome Diff: {self.ref1} → {self.ref2}")
-        lines.append("=" * 60)
-        lines.append(f"  Files changed: {self.total_files_changed}")
-        lines.append(f"  Functions changed: {self.total_functions_changed}")
-        lines.append(f"  Dependencies changed: {self.total_dependencies_changed}")
-        lines.append("")
-
-        for fc in self.file_changes:
-            kind = []
-            if fc.get('is_new'):
-                kind.append("NEW")
-            if fc.get('is_deleted'):
-                kind.append("DELETED")
-            if fc.get('is_renamed'):
-                kind.append("RENAMED")
-            if fc.get('is_binary'):
-                kind.append("BINARY")
-            kind_str = f" [{', '.join(kind)}]" if kind else ""
-            lines.append(f"  {fc['path']}{kind_str}  (+{fc['added_lines']}/-{fc['deleted_lines']})")
-        lines.append("")
-
-        for fc in self.function_changes:
-            op = {'added': '+', 'removed': '-', 'modified': '~'}.get(fc.change_type, '?')
-            lines.append(f"  [{op}] {fc.file}: {fc.kind} '{fc.name}'")
-        lines.append("")
-
-        for dc in self.dependency_changes:
-            op = '+' if dc.change_type == 'added' else '-'
-            lines.append(f"  [{op}] {dc.file}: {dc.module}")
-        lines.append("")
-
-        return "\n".join(lines)
-
-
-def run_git_diff(ref1: str, ref2: str) -> str:
-    result = subprocess.run(
-        ['git', 'diff', '--unified=0', f'{ref1}...{ref2}'],
-        capture_output=True, text=True, cwd=SCRIPT_DIR
-    )
-    if result.returncode not in (0, 1):
-        print(f"git diff failed: {result.stderr}", file=sys.stderr)
-        sys.exit(1)
-    return result.stdout
-
-
-def extract_function_changes(diff_text: str) -> List[FunctionChange]:
-    changes: List[FunctionChange] = []
-    pattern = re.compile(r'^([+\-])\s*(def|class)\s+(\w+)', re.MULTILINE)
-    hunk_header_re = re.compile(r'^@@\s+-(\d+)(?:,(\d+))?\s+\+(\d+)(?:,(\d+))?\s+@@')
-    current_old_line: Optional[int] = None
-    current_new_line: Optional[int] = None
-
-    for line in diff_text.split('\n'):
-        hdr = hunk_header_re.match(line)
-        if hdr:
-            current_old_line = int(hdr.group(1))
-            current_new_line = int(hdr.group(3))
-            continue
-        m = pattern.match(line)
-        if m:
-            op = m.group(1)
-            kind = m.group(2)
-            name = m.group(3)
-            change_type = "added" if op == '+' else "removed"
-            line_num = current_new_line if change_type == "added" else current_old_line
-            changes.append(FunctionChange(
-                file="<unknown>",
-                name=name,
-                kind=kind,
-                change_type=change_type,
-                new_line=line_num if change_type == "added" else None,
-                old_line=line_num if change_type == "removed" else None,
-            ))
-            # Advance line counters heuristically
-            if op == '-':
-                if current_old_line is not None:
-                    current_old_line += 1
-            elif op == '+':
-                if current_new_line is not None:
-                    current_new_line += 1
-        elif line.startswith(' '):
-            if current_old_line is not None:
-                current_old_line += 1
-            if current_new_line is not None:
-                current_new_line += 1
-        # lines starting with other prefixes (like \\ No newline) ignored
-    return changes
-
-
-def extract_dependency_changes(diff_text: str, analyzer: DiffAnalyzer) -> List[DependencyChange]:
-    changes: List[DependencyChange] = []
-    import_pattern = re.compile(
-        r'^([+\-])\s*(?:import\s+([\w\.]+)|from\s+([\w\.]+)\s+import)',
-        re.MULTILINE
-    )
-    file_diffs = analyzer._split_files(diff_text)
-    for file_diff in file_diffs:
-        file_match = re.search(r'^diff --git a/.*? b/(.*?)$', file_diff, re.MULTILINE)
-        if not file_match:
-            continue
-        filepath = file_match.group(1)
-
-        # Scan each line for import changes
-        for line in file_diff.split('\n'):
-            m = import_pattern.match(line)
-            if m:
-                change_type = "added" if m.group(1) == '+' else "removed"
-                module = m.group(2) or m.group(3)
-                changes.append(DependencyChange(
-                    file=filepath,
-                    module=module,
-                    change_type=change_type,
-                    line=0
-                ))
-
-        # Detect if this file is a dependency manifest
-        req_file_pattern = re.compile(
-            r'^[\+\-].*?(requirements(.*?)\.txt|pyproject\.toml|setup\.py|Pipfile)'
-        )
-        if any(req_file_pattern.match(line) for line in file_diff.split('\n')):
-            if not any(c.file == filepath and c.module == "<file>" for c in changes):
-                changes.append(DependencyChange(
-                    file=filepath,
-                    module="<file>",
-                    change_type="modified",
-                    line=0
-                ))
-    return changes
-
-
-def correlate_function_changes_with_files(diff_text: str, functions: List[FunctionChange]) -> List[FunctionChange]:
-    result: List[FunctionChange] = []
-    # Split diff into per-file sections
-    file_sections: List[tuple[str, str]] = []
-    current_file: Optional[str] = None
-    current_lines: List[str] = []
-    for line in diff_text.split('\n'):
-        if line.startswith('diff --git'):
-            if current_file is not None:
-                file_sections.append((current_file, '\n'.join(current_lines)))
-            m = re.match(r'^diff --git a/.*? b/(.*?)$', line)
-            current_file = m.group(1) if m else "unknown"
-            current_lines = [line]
-        else:
-            current_lines.append(line)
-    if current_file is not None:
-        file_sections.append((current_file, '\n'.join(current_lines)))
-
-    pattern = re.compile(r'^([+\-])\s*(def|class)\s+(\w+)', re.MULTILINE)
-    for filepath, section in file_sections:
-        for m in pattern.finditer(section):
-            op = m.group(1)
-            kind = m.group(2)
-            name = m.group(3)
-            change_type = "added" if op == '+' else "removed"
-            result.append(FunctionChange(
-                file=filepath,
-                name=name,
-                kind=kind,
-                change_type=change_type
-            ))
-    return result
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Codebase Genome Diff — structural changes between versions")
-    parser.add_argument("--ref1", required=True, help="First git ref (commit, branch, tag)")
-    parser.add_argument("--ref2", required=True, help="Second git ref")
-    parser.add_argument("--output", help="Write report to file")
-    parser.add_argument("--json", action="store_true", help="Output JSON instead of human report")
-    args = parser.parse_args()
-
-    try:
-        diff_text = run_git_diff(args.ref1, args.ref2)
-    except Exception as e:
-        print(f"Error: {e}", file=sys.stderr)
-        sys.exit(1)
-
-    if not diff_text.strip():
-        print(f"No differences between {args.ref1} and {args.ref2}.")
-        sys.exit(0)
-
-    analyzer = DiffAnalyzer()
-    summary = analyzer.analyze(diff_text)
-
-    file_changes = [fc.to_dict() for fc in summary.files]
-    func_changes = extract_function_changes(diff_text)
-    func_changes = correlate_function_changes_with_files(diff_text, func_changes)
-    dep_changes = extract_dependency_changes(diff_text, analyzer)
-
-    report = GenomeDiffReport(
-        ref1=args.ref1,
-        ref2=args.ref2,
-        file_changes=file_changes,
-        function_changes=func_changes,
-        dependency_changes=dep_changes,
-        total_files_changed=len(file_changes),
-        total_functions_changed=len(func_changes),
-        total_dependencies_changed=len(dep_changes),
-    )
-
-    output = json.dumps(report.to_dict(), indent=2) if args.json else report.human_report()
-
-    if args.output:
-        with open(args.output, 'w') as f:
-            f.write(output + '\n')
-        print(f"Report written to {args.output}")
-    else:
-        print(output)
-
-
-if __name__ == '__main__':
-    main()

scripts/graph_visualizer.py

@@ -0,0 +1,206 @@
+#!/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()

scripts/test_graph_visualizer.py

@@ -0,0 +1,105 @@
+#!/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)