feat: dead code detector for Python codebases (#94)

scripts/dead_code_detector.py

@@ -0,0 +1,282 @@
+#!/usr/bin/env python3
+"""
+Dead Code Detector for Python Codebases
+
+AST-based analysis to find defined but never-called functions and classes.
+Excludes entry points, plugin hooks, __init__ exports.
+
+Usage:
+  python3 scripts/dead_code_detector.py /path/to/repo/
+  python3 scripts/dead_code_detector.py hermes-agent/ --format json
+  python3 scripts/dead_code_detector.py . --exclude tests/,venv/
+
+Output: file:line, function/class name, last git author (if available)
+"""
+
+import argparse
+import ast
+import json
+import os
+import subprocess
+import sys
+from collections import defaultdict
+from pathlib import Path
+from typing import Optional
+
+
+# Names that are expected to be unused (entry points, protocol methods, etc.)
+SAFE_UNUSED_PATTERNS = {
+    # Python dunders
+    "__init__", "__str__", "__repr__", "__eq__", "__hash__", "__len__",
+    "__getitem__", "__setitem__", "__contains__", "__iter__", "__next__",
+    "__enter__", "__exit__", "__call__", "__bool__", "__del__",
+    "__post_init__", "__class_getitem__",
+    # Common entry points
+    "main", "app", "handler", "setup", "teardown", "fixture",
+    # pytest
+    "conftest", "test_", "pytest_",  # prefix patterns
+    # Protocols / abstract
+    "abstractmethod", "abc_",
+}
+
+
+def is_safe_unused(name: str, filepath: str) -> bool:
+    """Check if an unused name is expected to be unused."""
+    # Test files are exempt
+    if "test" in filepath.lower():
+        return True
+
+    # Known patterns
+    for pattern in SAFE_UNUSED_PATTERNS:
+        if name.startswith(pattern) or name == pattern:
+            return True
+
+    # __init__.py exports are often unused internally
+    if filepath.endswith("__init__.py"):
+        return True
+
+    return False
+
+
+def get_git_blame(filepath: str, lineno: int) -> Optional[str]:
+    """Get last author of a line via git blame."""
+    try:
+        result = subprocess.run(
+            ["git", "blame", "-L", f"{lineno},{lineno}", "--porcelain", filepath],
+            capture_output=True, text=True, timeout=5
+        )
+        for line in result.stdout.split("\n"):
+            if line.startswith("author "):
+                return line[7:]
+    except:
+        pass
+    return None
+
+
+class DefinitionCollector(ast.NodeVisitor):
+    """Collect all function and class definitions."""
+
+    def __init__(self):
+        self.definitions = []  # (name, type, lineno, filepath)
+
+    def visit_FunctionDef(self, node):
+        self.definitions.append((node.name, "function", node.lineno))
+        self.generic_visit(node)
+
+    def visit_AsyncFunctionDef(self, node):
+        self.definitions.append((node.name, "async_function", node.lineno))
+        self.generic_visit(node)
+
+    def visit_ClassDef(self, node):
+        self.definitions.append((node.name, "class", node.lineno))
+        self.generic_visit(node)
+
+
+class NameUsageCollector(ast.NodeVisitor):
+    """Collect all name references (calls, imports, attribute access)."""
+
+    def __init__(self):
+        self.names = set()
+        self.calls = set()
+        self.imports = set()
+
+    def visit_Name(self, node):
+        self.names.add(node.id)
+        self.generic_visit(node)
+
+    def visit_Attribute(self, node):
+        if isinstance(node.value, ast.Name):
+            self.names.add(node.value.id)
+        self.generic_visit(node)
+
+    def visit_Call(self, node):
+        if isinstance(node.func, ast.Name):
+            self.calls.add(node.func.id)
+        elif isinstance(node.func, ast.Attribute):
+            if isinstance(node.func.value, ast.Name):
+                self.names.add(node.func.value.id)
+            self.calls.add(node.func.attr)
+        self.generic_visit(node)
+
+    def visit_Import(self, node):
+        for alias in node.names:
+            self.imports.add(alias.asname or alias.name)
+        self.generic_visit(node)
+
+    def visit_ImportFrom(self, node):
+        for alias in node.names:
+            self.imports.add(alias.asname or alias.name)
+        self.generic_visit(node)
+
+
+def analyze_file(filepath: str) -> dict:
+    """Analyze a single Python file for dead code."""
+    path = Path(filepath)
+    try:
+        content = path.read_text()
+        tree = ast.parse(content, filename=str(filepath))
+    except (SyntaxError, UnicodeDecodeError):
+        return {"error": f"Could not parse {filepath}"}
+
+    # Collect definitions
+    def_collector = DefinitionCollector()
+    def_collector.visit(tree)
+    definitions = def_collector.definitions
+
+    # Collect usage
+    usage_collector = NameUsageCollector()
+    usage_collector.visit(tree)
+    used_names = usage_collector.names | usage_collector.calls | usage_collector.imports
+
+    # Also scan the entire repo for references to this file's definitions
+    # (this is done at the repo level, not file level)
+
+    dead = []
+    for name, def_type, lineno in definitions:
+        if name.startswith("_") and not name.startswith("__"):
+            # Private functions — might be used externally, less likely dead
+            pass
+
+        if name not in used_names:
+            if not is_safe_unused(name, filepath):
+                dead.append({
+                    "name": name,
+                    "type": def_type,
+                    "file": filepath,
+                    "line": lineno,
+                })
+
+    return {"definitions": len(definitions), "dead": dead}
+
+
+def scan_repo(repo_path: str, exclude_patterns: list = None) -> dict:
+    """Scan an entire repo for dead code."""
+    path = Path(repo_path)
+    exclude = exclude_patterns or ["venv", ".venv", "node_modules", "__pycache__",
+                                    ".git", "dist", "build", ".tox", "vendor"]
+
+    all_definitions = {}  # name -> [{file, line, type}]
+    all_files = []
+    dead_code = []
+
+    # First pass: collect all definitions across repo
+    for fpath in path.rglob("*.py"):
+        parts = fpath.parts
+        if any(ex in parts for ex in exclude):
+            continue
+        if fpath.name.startswith("."):
+            continue
+
+        try:
+            content = fpath.read_text(errors="ignore")
+            tree = ast.parse(content, filename=str(fpath))
+        except:
+            continue
+
+        all_files.append(str(fpath))
+        collector = DefinitionCollector()
+        collector.visit(tree)
+
+        for name, def_type, lineno in collector.definitions:
+            rel_path = str(fpath.relative_to(path))
+            if name not in all_definitions:
+                all_definitions[name] = []
+            all_definitions[name].append({
+                "file": rel_path,
+                "line": lineno,
+                "type": def_type,
+            })
+
+    # Second pass: check each name for usage across entire repo
+    all_used_names = set()
+    for fpath_str in all_files:
+        try:
+            content = Path(fpath_str).read_text(errors="ignore")
+            tree = ast.parse(content)
+        except:
+            continue
+        usage = NameUsageCollector()
+        usage.visit(tree)
+        all_used_names.update(usage.names)
+        all_used_names.update(usage.calls)
+        all_used_names.update(usage.imports)
+
+    # Find dead code
+    for name, locations in all_definitions.items():
+        if name not in all_used_names:
+            for loc in locations:
+                if not is_safe_unused(name, loc["file"]):
+                    dead_code.append({
+                        "name": name,
+                        "type": loc["type"],
+                        "file": loc["file"],
+                        "line": loc["line"],
+                    })
+
+    return {
+        "repo": path.name,
+        "files_scanned": len(all_files),
+        "total_definitions": sum(len(v) for v in all_definitions.values()),
+        "dead_code_count": len(dead_code),
+        "dead_code": sorted(dead_code, key=lambda x: (x["file"], x["line"])),
+    }
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Find dead code in Python codebases")
+    parser.add_argument("repo", help="Repository path to scan")
+    parser.add_argument("--format", choices=["text", "json"], default="text")
+    parser.add_argument("--exclude", help="Comma-separated patterns to exclude")
+    parser.add_argument("--git-blame", action="store_true", help="Include git blame info")
+    args = parser.parse_args()
+
+    exclude = args.exclude.split(",") if args.exclude else None
+    result = scan_repo(args.repo, exclude)
+
+    if args.format == "json":
+        print(json.dumps(result, indent=2))
+    else:
+        print(f"Dead Code Report: {result['repo']}")
+        print(f"Files scanned: {result['files_scanned']}")
+        print(f"Total definitions: {result['total_definitions']}")
+        print(f"Dead code found: {result['dead_code_count']}")
+        print()
+
+        if result["dead_code"]:
+            print(f"{'File':<45} {'Line':>4} {'Type':<10} {'Name'}")
+            print("-" * 85)
+            for item in result["dead_code"]:
+                author = ""
+                if args.git_blame:
+                    author = get_git_blame(
+                        os.path.join(args.repo, item["file"]),
+                        item["line"]
+                    ) or ""
+                    author = f" ({author})" if author else ""
+                print(f"{item['file']:<45} {item['line']:>4} {item['type']:<10} {item['name']}{author}")
+        else:
+            print("No dead code detected!")
+
+
+if __name__ == "__main__":
+    main()

scripts/knowledge_staleness_check.py

@@ -1,221 +0,0 @@
-#!/usr/bin/env python3
-"""
-Knowledge Store Staleness Detector
-
-Checks knowledge entries against their source files to detect staleness.
-An entry is stale when its source file has been modified since extraction.
-
-Usage:
-  python3 scripts/knowledge_staleness_check.py knowledge/index.json
-  python3 scripts/knowledge_staleness_check.py --repo /path/to/repo --index knowledge/index.json
-  python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --fix
-
-Expected index.json format:
-{
-  "version": 1,
-  "facts": [
-    {
-      "fact": "...",
-      "category": "fact|pitfall|pattern|tool-quirk",
-      "repo": "repo-name",
-      "confidence": 0.8,
-      "source_file": "path/to/file.py",
-      "source_hash": "sha256:abcdef...",
-      "extracted_at": "2026-04-13T20:00:00Z"
-    }
-  ]
-}
-"""
-
-import argparse
-import hashlib
-import json
-import sys
-from pathlib import Path
-from typing import Optional
-
-
-def compute_file_hash(filepath: str) -> Optional[str]:
-    """Compute SHA-256 hash of a file. Returns None if file not found."""
-    path = Path(filepath)
-    if not path.exists():
-        return None
-    content = path.read_bytes()
-    return hashlib.sha256(content).hexdigest()[:16]
-
-
-def check_staleness(index_path: str, repo_root: str = None) -> dict:
-    """Check all entries in the knowledge index for staleness."""
-    index = Path(index_path)
-    if not index.exists():
-        return {"error": f"Index not found: {index_path}"}
-
-    data = json.loads(index.read_text())
-    facts = data.get("facts", [])
-
-    if not facts:
-        return {
-            "total": 0,
-            "stale": 0,
-            "fresh": 0,
-            "no_source": 0,
-            "missing_files": 0,
-            "stale_entries": [],
-        }
-
-    # Determine repo root
-    if repo_root:
-        root = Path(repo_root)
-    else:
-        root = index.parent.parent  # knowledge/index.json -> repo root
-
-    results = {
-        "total": len(facts),
-        "stale": 0,
-        "fresh": 0,
-        "no_source": 0,
-        "missing_files": 0,
-        "stale_entries": [],
-    }
-
-    for i, entry in enumerate(facts):
-        source_file = entry.get("source_file")
-        stored_hash = entry.get("source_hash")
-
-        if not source_file:
-            results["no_source"] += 1
-            continue
-
-        if not stored_hash:
-            # Entry has source file but no hash — consider stale
-            results["stale"] += 1
-            results["stale_entries"].append({
-                "index": i,
-                "fact": entry.get("fact", "")[:100],
-                "source_file": source_file,
-                "reason": "no_hash",
-            })
-            continue
-
-        # Compute current hash
-        full_path = root / source_file
-        current_hash = compute_file_hash(str(full_path))
-
-        if current_hash is None:
-            results["missing_files"] += 1
-            results["stale_entries"].append({
-                "index": i,
-                "fact": entry.get("fact", "")[:100],
-                "source_file": source_file,
-                "reason": "file_missing",
-            })
-        elif current_hash != stored_hash:
-            results["stale"] += 1
-            results["stale_entries"].append({
-                "index": i,
-                "fact": entry.get("fact", "")[:100],
-                "source_file": source_file,
-                "stored_hash": stored_hash,
-                "current_hash": current_hash,
-                "reason": "hash_mismatch",
-            })
-        else:
-            results["fresh"] += 1
-
-    return results
-
-
-def add_hashes_to_index(index_path: str, repo_root: str = None) -> dict:
-    """Add source hashes to entries that are missing them."""
-    index = Path(index_path)
-    data = json.loads(index.read_text())
-    facts = data.get("facts", [])
-
-    if repo_root:
-        root = Path(repo_root)
-    else:
-        root = index.parent.parent
-
-    updated = 0
-    skipped = 0
-
-    for entry in facts:
-        source_file = entry.get("source_file")
-        if not source_file or entry.get("source_hash"):
-            skipped += 1
-            continue
-
-        full_path = root / source_file
-        file_hash = compute_file_hash(str(full_path))
-        if file_hash:
-            entry["source_hash"] = file_hash
-            updated += 1
-
-    if updated > 0:
-        index.write_text(json.dumps(data, indent=2) + "\n")
-
-    return {"updated": updated, "skipped": skipped, "total": len(facts)}
-
-
-def report_staleness(results: dict) -> str:
-    """Format staleness check results as a report."""
-    lines = []
-    lines.append("=" * 50)
-    lines.append("KNOWLEDGE STORE STALENESS REPORT")
-    lines.append("=" * 50)
-    lines.append(f"Total entries:  {results['total']}")
-    lines.append(f"Fresh:          {results['fresh']}")
-    lines.append(f"Stale:          {results['stale']}")
-    lines.append(f"No source:      {results['no_source']}")
-    lines.append(f"Missing files:  {results['missing_files']}")
-    lines.append("")
-
-    if results["stale_entries"]:
-        lines.append("STALE ENTRIES:")
-        lines.append("-" * 50)
-        for entry in results["stale_entries"]:
-            lines.append(f"  [{entry['reason']}] {entry['source_file']}")
-            lines.append(f"    {entry['fact']}")
-            if entry.get("stored_hash") and entry.get("current_hash"):
-                lines.append(f"    stored:  {entry['stored_hash']}")
-                lines.append(f"    current: {entry['current_hash']}")
-            lines.append("")
-
-    if results["total"] > 0:
-        staleness_pct = results["stale"] / results["total"] * 100
-        lines.append(f"Staleness rate: {staleness_pct:.1f}%")
-    else:
-        lines.append("No entries to check.")
-
-    return "\n".join(lines)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Check knowledge store for stale entries")
-    parser.add_argument("--index", default="knowledge/index.json", help="Path to index.json")
-    parser.add_argument("--repo", help="Repository root (default: auto-detect from index path)")
-    parser.add_argument("--fix", action="store_true", help="Add missing hashes to index")
-    parser.add_argument("--json", action="store_true", help="Output JSON instead of report")
-    args = parser.parse_args()
-
-    if args.fix:
-        result = add_hashes_to_index(args.index, args.repo)
-        if args.json:
-            print(json.dumps(result, indent=2))
-        else:
-            print(f"Updated {result['updated']} entries with source hashes.")
-            print(f"Skipped {result['skipped']} (already had hashes or no source file).")
-    else:
-        results = check_staleness(args.index, args.repo)
-        if "error" in results:
-            print(f"Error: {results['error']}", file=sys.stderr)
-            sys.exit(1)
-
-        if args.json:
-            print(json.dumps(results, indent=2))
-        else:
-            print(report_staleness(results))
-
-
-if __name__ == "__main__":
-    main()