Merge pull request 'feat: Knowledge store staleness detector (closes #179)' (#185) from feat/179-staleness-check into main

scripts/dead_code_detector.py

@@ -1,282 +0,0 @@
-#!/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

@@ -0,0 +1,131 @@
+#!/usr/bin/env python3
+"""
+Knowledge Store Staleness Detector — Detect stale knowledge entries by comparing source file hashes.
+
+Usage:
+    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json
+    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --json
+    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --fix
+"""
+
+import argparse
+import hashlib
+import json
+import os
+import sys
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Dict, List, Any, Optional
+
+
+def compute_file_hash(filepath: str) -> Optional[str]:
+    """Compute SHA-256 hash of a file. Returns None if file doesn't exist."""
+    try:
+        with open(filepath, "rb") as f:
+            return "sha256:" + hashlib.sha256(f.read()).hexdigest()
+    except (FileNotFoundError, IsADirectoryError, PermissionError):
+        return None
+
+
+def check_staleness(index_path: str, repo_root: str = ".") -> List[Dict[str, Any]]:
+    """Check all entries in knowledge index for staleness.
+    
+    Returns list of entries with staleness info:
+    - status: "fresh" | "stale" | "missing_source" | "no_hash"
+    - current_hash: computed hash (if source exists)
+    - stored_hash: hash from index
+    """
+    with open(index_path) as f:
+        data = json.load(f)
+
+    facts = data.get("facts", [])
+    results = []
+
+    for entry in facts:
+        source_file = entry.get("source_file")
+        stored_hash = entry.get("source_hash")
+
+        if not source_file:
+            results.append({**entry, "status": "no_source", "current_hash": None})
+            continue
+
+        full_path = os.path.join(repo_root, source_file)
+        current_hash = compute_file_hash(full_path)
+
+        if current_hash is None:
+            results.append({**entry, "status": "missing_source", "current_hash": None})
+        elif not stored_hash:
+            results.append({**entry, "status": "no_hash", "current_hash": current_hash})
+        elif current_hash != stored_hash:
+            results.append({**entry, "status": "stale", "current_hash": current_hash})
+        else:
+            results.append({**entry, "status": "fresh", "current_hash": current_hash})
+
+    return results
+
+
+def fix_hashes(index_path: str, repo_root: str = ".") -> int:
+    """Add hashes to entries missing them. Returns count of fixed entries."""
+    with open(index_path) as f:
+        data = json.load(f)
+
+    fixed = 0
+    for entry in data.get("facts", []):
+        if entry.get("source_hash"):
+            continue
+        source_file = entry.get("source_file")
+        if not source_file:
+            continue
+        full_path = os.path.join(repo_root, source_file)
+        h = compute_file_hash(full_path)
+        if h:
+            entry["source_hash"] = h
+            fixed += 1
+
+    with open(index_path, "w") as f:
+        json.dump(data, f, indent=2)
+
+    return fixed
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Check knowledge store staleness")
+    parser.add_argument("--index", required=True, help="Path to knowledge/index.json")
+    parser.add_argument("--repo", default=".", help="Repo root for source file resolution")
+    parser.add_argument("--json", action="store_true", help="Output as JSON")
+    parser.add_argument("--fix", action="store_true", help="Add hashes to entries missing them")
+
+    args = parser.parse_args()
+
+    if args.fix:
+        fixed = fix_hashes(args.index, args.repo)
+        print(f"Fixed {fixed} entries with missing hashes.")
+        return
+
+    results = check_staleness(args.index, args.repo)
+
+    if args.json:
+        print(json.dumps(results, indent=2))
+    else:
+        stale = [r for r in results if r["status"] != "fresh"]
+        fresh = [r for r in results if r["status"] == "fresh"]
+
+        print(f"Knowledge Store Staleness Check")
+        print(f"  Total entries: {len(results)}")
+        print(f"  Fresh: {len(fresh)}")
+        print(f"  Stale/Issues: {len(stale)}")
+        print()
+
+        if stale:
+            print("Issues found:")
+            for r in stale:
+                status = r["status"]
+                fact = r.get("fact", "?")[:60]
+                source = r.get("source_file", "?")
+                print(f"  [{status}] {source}: {fact}")
+        else:
+            print("All entries are fresh!")
+
+
+if __name__ == "__main__":
+    main()

scripts/test_knowledge_staleness.py

@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+"""Tests for scripts/knowledge_staleness_check.py — 8 tests."""
+
+import json
+import os
+import sys
+import tempfile
+
+sys.path.insert(0, os.path.dirname(__file__) or ".")
+import importlib.util
+spec = importlib.util.spec_from_file_location("ks", os.path.join(os.path.dirname(__file__) or ".", "knowledge_staleness_check.py"))
+mod = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(mod)
+check_staleness = mod.check_staleness
+fix_hashes = mod.fix_hashes
+compute_file_hash = mod.compute_file_hash
+
+
+def test_fresh_entry():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("print('hello')")
+        h = compute_file_hash(src)
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "hello", "source_file": "source.py", "source_hash": h}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "fresh"
+        print("PASS: test_fresh_entry")
+
+
+def test_stale_entry():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("original content")
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "old", "source_file": "source.py", "source_hash": "sha256:wrong"}]}, f)
+        # Now change the source
+        with open(src, "w") as f:
+            f.write("modified content")
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "stale"
+        print("PASS: test_stale_entry")
+
+
+def test_missing_source():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "gone", "source_file": "nonexistent.py", "source_hash": "sha256:abc"}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "missing_source"
+        print("PASS: test_missing_source")
+
+
+def test_no_hash():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("content")
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "no hash", "source_file": "source.py"}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "no_hash"
+        assert results[0]["current_hash"].startswith("sha256:")
+        print("PASS: test_no_hash")
+
+
+def test_no_source_field():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "orphan"}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "no_source"
+        print("PASS: test_no_source_field")
+
+
+def test_fix_hashes():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("content for hashing")
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "needs hash", "source_file": "source.py"}]}, f)
+        fixed = fix_hashes(idx, tmpdir)
+        assert fixed == 1
+        # Verify hash was added
+        with open(idx) as f:
+            data = json.load(f)
+        assert data["facts"][0]["source_hash"].startswith("sha256:")
+        print("PASS: test_fix_hashes")
+
+
+def test_empty_index():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": []}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results == []
+        print("PASS: test_empty_index")
+
+
+def test_compute_hash_nonexistent():
+    h = compute_file_hash("/nonexistent/path/file.py")
+    assert h is None
+    print("PASS: test_compute_hash_nonexistent")
+
+
+def run_all():
+    test_fresh_entry()
+    test_stale_entry()
+    test_missing_source()
+    test_no_hash()
+    test_no_source_field()
+    test_fix_hashes()
+    test_empty_index()
+    test_compute_hash_nonexistent()
+    print("\nAll 8 tests passed!")
+
+
+if __name__ == "__main__":
+    run_all()