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/dependency_graph.py

@@ -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()