feat: add Test Coverage Checker — 6.6

Add automated script that identifies changed source files, checks for
corresponding test changes, and reports coverage gaps.

Acceptance — #124:
  - Identifies changed source files  (git diff --name-only HEAD)
  - Checks for corresponding test changes (source→test file mapping)
  - Reports: code without tests       (lists uncovered sources)
  - Output: coverage gap             (structured text/JSON)

Closes #124
Task: 6.6 — Test Coverage Checker

scripts/coverage_checker.py

@@ -0,0 +1,169 @@
+#!/usr/bin/env python3
+"""
+Test Coverage Checker — 6.6
+
+Identifies changed source files, checks for corresponding test changes,
+and reports code without test coverage.
+
+Usage:
+    python3 scripts/test_coverage_checker.py
+    python3 scripts/test_coverage_checker.py --format json
+    python3 scripts/test_coverage_checker.py --compare HEAD~1  # Compare against a specific ref
+
+Acceptance:
+  - Identifies changed source files   (git diff --name-only HEAD)
+  - Checks for corresponding test changes (matches source→test file mapping)
+  - Reports: code without tests        (lists coverage gaps)
+  - Output: coverage gap              (structured text/JSON)
+"""
+
+import argparse
+import json
+import subprocess
+import sys
+from pathlib import Path
+from typing import List, Tuple, Optional
+
+REPO_ROOT = Path(__file__).resolve().parent.parent
+
+
+def run_git_diff(ref: str = "HEAD") -> List[str]:
+    """Return list of changed file paths relative to given ref."""
+    result = subprocess.run(
+        ["git", "diff", "--name-only", ref],
+        capture_output=True, text=True, cwd=REPO_ROOT
+    )
+    if result.returncode != 0:
+        print(f"ERROR: git diff failed: {result.stderr}")
+        sys.exit(1)
+    return [p for p in result.stdout.splitlines() if p.strip()]
+
+
+def is_source_file(path: str) -> bool:
+    """True if path is a Python source file (not test)."""
+    return path.endswith(".py") and not path.startswith("tests/") and "/test" not in Path(path).name
+
+
+def is_test_file(path: str) -> bool:
+    """True if path is a test file."""
+    if not path.endswith(".py"):
+        return False
+    name = Path(path).name
+    # Test files: test_*.py or *_test.py or in tests/ directory
+    return (name.startswith("test_") or name.endswith("_test.py") or path.startswith("tests/"))
+
+
+def source_to_test_path(src_path: str) -> str:
+    """
+    Map a source file path to its expected test file path.
+    Convention: scripts/<name>.py -> tests/test_<name>.py
+                <module>.py -> tests/test_<module>.py
+    """
+    name = Path(src_path).name
+    stem = Path(name).stem  # without .py
+    # Common mapping: script name -> test_ prefix in tests/
+    test_name = f"test_{stem}.py"
+    return str(Path("tests") / test_name)
+
+
+def test_file_exists() -> bool:
+    """Check if the test file exists in the repo."""
+    return (REPO_ROOT / test_rel).exists()
+
+
+def analyze_coverage(changed_files: List[str]) -> dict:
+    """
+    For each changed source file, check if corresponding test file also changed.
+    Returns structured coverage gap report.
+    """
+    changed_sources = [f for f in changed_files if is_source_file(f)]
+    changed_tests = [f for f in changed_files if is_test_file(f)]
+
+    # Build set of test file paths that changed (relative paths)
+    changed_test_set = set(changed_tests)
+
+    # Build coverage gap
+    uncovered_sources = []
+    covered_sources = []
+    for src in changed_sources:
+        coverage_entry = {"file": src}
+        # Check: does the corresponding test file also appear in changed files?
+        test_rel = source_to_test_path(src)
+        if test_rel in changed_test_set:
+            coverage_entry["status"] = "covered"
+            coverage_entry["test_file"] = test_rel
+            covered_sources.append(coverage_entry)
+        else:
+            coverage_entry["status"] = "missing"
+            coverage_entry["suggested_test"] = test_rel
+            uncovered_sources.append(coverage_entry)
+
+    return {
+        "repo": REPO_ROOT.name,
+        "changed_sources": len(changed_sources),
+        "changed_tests": len(changed_tests),
+        "covered_sources": len(covered_sources),
+        "uncovered_sources": len(uncovered_sources),
+        "coverage_ratio": (
+            len(covered_sources) / len(changed_sources)
+            if changed_sources else 1.0
+        ),
+        "covered": covered_sources,
+        "uncovered": uncovered_sources,
+        "all_changed": changed_files,
+    }
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Test Coverage Checker")
+    parser.add_argument("--format", choices=["text", "json"], default="text",
+                        help="Output format")
+    parser.add_argument("--compare", default="HEAD",
+                        help="Git ref to compare against (default: HEAD)")
+    args = parser.parse_args()
+
+    # Step 1: Identify changed files
+    print(f"Scanning changes vs {args.compare}...")
+    changed_files = run_git_diff(args.compare)
+    if not changed_files:
+        print("No changed files detected.")
+        sys.exit(0)
+
+    # Step 2: Analyze coverage
+    report = analyze_coverage(changed_files)
+
+    if args.format == "json":
+        print(json.dumps(report, indent=2))
+        sys.exit(0)
+
+    # Text output
+    print("=" * 60)
+    print("  TEST COVERAGE CHECKER")
+    print("=" * 60)
+    print(f"  Repository:  {report['repo']}")
+    print(f"  Changed files total: {len(changed_files)}")
+    print(f"  Source files changed: {report['changed_sources']}")
+    print(f"  Test files changed:   {report['changed_tests']}")
+    print()
+    print(f"  Coverage (sources with test changes): {report['coverage_ratio']:.0%}")
+    print(f"    Covered:   {report['covered_sources']} source file(s)")
+    print(f"    Uncovered: {report['uncovered_sources']} source file(s)")
+    print()
+
+    if report["uncovered"]:
+        print("  COVERAGE GAP — Source files without corresponding test changes:")
+        print("  " + "-" * 54)
+        for item in report["uncovered"]:
+            print(f"    {item['file']}")
+            print(f"      Suggested test: {item['suggested_test']}")
+        print()
+        print("  ACTION: Write or update tests for the files above.")
+        sys.exit(1)  # Non-zero exit to flag coverage gap
+    else:
+        print("  All changed source files have corresponding test coverage.")
+
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()

scripts/graph_visualizer.py

@@ -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()

scripts/test_graph_visualizer.py

@@ -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)

tests/test_coverage_checker.py

@@ -0,0 +1,116 @@
+#!/usr/bin/env python3
+"""Tests for coverage_checker — Issue #124 acceptance validation."""
+
+import subprocess
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent.parent / "scripts"))
+
+from coverage_checker import (
+    is_source_file,
+    is_test_file,
+    source_to_test_path,
+    analyze_coverage,
+)
+
+
+class TestSourceFileDetection:
+    def test_script_in_scripts_dir(self):
+        assert is_source_file("scripts/freshness.py") is True
+
+    def test_module_in_root(self):
+        assert is_source_file("knowledge_staleness_check.py") is True
+
+    def test_excludes_test_files(self):
+        assert is_source_file("tests/test_freshness.py") is False
+
+    def test_excludes_non_py(self):
+        assert is_source_file("README.md") is False
+
+
+class TestTestFileDetection:
+    def test_test_prefix(self):
+        assert is_test_file("tests/test_freshness.py") is True
+
+    def test_test_suffix(self):
+        assert is_test_file("scripts/freshness_test.py") is True
+
+    def test_regular_py_is_not_test(self):
+        assert is_test_file("scripts/freshness.py") is False
+
+
+class TestSourceToTestMapping:
+    def test_scripts_mapping(self):
+        assert source_to_test_path("scripts/freshness.py") == "tests/test_freshness.py"
+
+    def test_root_module_mapping(self):
+        assert source_to_test_path("knowledge_staleness_check.py") == "tests/test_knowledge_staleness_check.py"
+
+
+class TestAnalyzeCoverage:
+    def test_no_changes(self):
+        report = analyze_coverage([])
+        assert report["changed_sources"] == 0
+        assert report["uncovered_sources"] == 0
+        assert report["coverage_ratio"] == 1.0
+
+    def test_all_covered(self):
+        changed = [
+            "scripts/freshness.py",
+            "tests/test_freshness.py",
+            "scripts/dedup.py",
+            "tests/test_dedup.py",
+        ]
+        report = analyze_coverage(changed)
+        assert report["uncovered_sources"] == 0
+        assert report["covered_sources"] == 2
+
+    def test_gap_detected(self):
+        changed = [
+            "scripts/new_feature.py",
+            "README.md",
+        ]
+        report = analyze_coverage(changed)
+        assert report["uncovered_sources"] == 1
+        assert report["uncovered"][0]["file"] == "scripts/new_feature.py"
+        assert report["uncovered"][0]["suggested_test"] == "tests/test_new_feature.py"
+
+    def test_mixed_coverage(self):
+        changed = [
+            "scripts/covered.py",
+            "tests/test_covered.py",
+            "scripts/uncovered.py",
+        ]
+        report = analyze_coverage(changed)
+        assert report["covered_sources"] == 1
+        assert report["uncovered_sources"] == 1
+
+
+def run_all():
+    t = TestSourceFileDetection()
+    t.test_script_in_scripts_dir()
+    t.test_module_in_root()
+    t.test_excludes_test_files()
+    t.test_excludes_non_py()
+
+    t2 = TestTestFileDetection()
+    t2.test_test_prefix()
+    t2.test_test_suffix()
+    t2.test_regular_py_is_not_test()
+
+    t3 = TestSourceToTestMapping()
+    t3.test_scripts_mapping()
+    t3.test_root_module_mapping()
+
+    t4 = TestAnalyzeCoverage()
+    t4.test_no_changes()
+    t4.test_all_covered()
+    t4.test_gap_detected()
+    t4.test_mixed_coverage()
+
+    print("All 11 tests passed!")
+
+
+if __name__ == "__main__":
+    run_all()