manual_slop/scripts/focused_entropy_audit.py

#!/usr/bin/env python3
"""
Focused Entropy Audit for Manual Slop - Muratori Style
Focuses on ACTUAL issues, not style:
1. Duplicate logic (same thing done in multiple places)
2. State inconsistencies (parallel representations)
3. Logic errors / bugs
4. Performance concerns
"""

import os
import re
import ast
from pathlib import Path
from collections import defaultdict
from typing import List, Dict, Set, Tuple, Optional

def find_duplicate_logic_files():
    """Find files with similar patterns that might indicate duplicate logic."""
    patterns = {
        'calculate_track_progress': [],
        'cascade_blocks': [],
        'topological_sort': [],
        'push_mma_state': [],
        'active_tickets': [],
    }

    for f in Path('src').glob('*.py'):
        content = f.read_text(encoding='utf-8', errors='ignore')
        for pattern in patterns:
            if re.search(pattern, content):
                patterns[pattern].append(f.name)

    return patterns

def check_ticket_state_management():
    """Check for state management issues in ticket handling."""
    issues = []

    # Check if there are parallel ticket representations
    gui_2_content = Path('src/gui_2.py').read_text(encoding='utf-8', errors='ignore')
    app_ctrl_content = Path('src/app_controller.py').read_text(encoding='utf-8', errors='ignore')
    dag_content = Path('src/dag_engine.py').read_text(encoding='utf-8', errors='ignore')

    # gui_2 uses dict-based tickets
    if 'active_tickets' in gui_2_content:
        if 'ticket["status"]' in gui_2_content or "t['status']" in gui_2_content:
            issues.append(("gui_2.py", "Dict-based ticket access pattern found"))

    # Check for blocking logic duplication
    gui_blocking = len(re.findall(r'_cb_block_ticket|_cb_unblock_ticket', gui_2_content))
    dag_blocking = len(re.findall(r'cascade_blocks', dag_content))

    if gui_blocking > 0 and dag_blocking > 0:
        issues.append(("architecture", "GUI has manual block/unblock that could conflict with DAG cascade_blocks"))

    return issues

def check_import_issues():
    """Check for actual import problems - nested imports causing runtime issues."""
    issues = []

    for f in Path('src').glob('*.py'):
        try:
            content = f.read_text(encoding='utf-8', errors='ignore')
            tree = ast.parse(content, filename=str(f))

            for node in ast.walk(tree):
                if isinstance(node, ast.FunctionDef):
                    for child in ast.walk(node):
                        if isinstance(child, (ast.Import, ast.ImportFrom)):
                            line = child.lineno or 0
                            # Check if this import is inside a HOT PATH function
                            if node.name in ['_process_pending_gui_tasks', '_gui_func', 'run', 'tick']:
                                issues.append((f.name, f"Nested import `{ast.unparse(child).strip()[:50]}` in hot path `{node.name}` line {line}"))
        except:
            pass

    return issues

def check_potential_bugs():
    """Check for potential bugs - undefined variables, etc."""
    bugs = []

    # Check for == None vs is None patterns
    for f in Path('src').glob('*.py'):
        content = f.read_text(encoding='utf-8', errors='ignore')
        lines = content.split('\n')

        for i, line in enumerate(lines, 1):
            # Skip comments
            if line.strip().startswith('#'):
                continue

            # Check for mutable default arguments (common bug)
            if re.search(r'def\s+\w+\([^)]*=\s*\[\s*\]', line):
                bugs.append((f.name, i, "Mutable default argument", line.strip()[:60]))
            if re.search(r'def\s+\w+\([^)]*=\s*\{\s*\}', line):
                bugs.append((f.name, i, "Mutable default argument", line.strip()[:60]))

    return bugs

def check_actual_duplicates():
    """Check for ACTUAL duplicate code - same logic copied."""
    duplicates = []
    seen_snippets = defaultdict(list)

    # Look for duplicate patterns (3+ lines identical)
    for f in sorted(Path('src').glob('*.py')):
        try:
            content = f.read_text(encoding='utf-8', errors='ignore')
            lines = content.split('\n')

            # Normalize and check consecutive duplicate lines
            prev_normalized = None
            dup_start = None

            for i, line in enumerate(lines, 1):
                if line.strip().startswith('#'):
                    prev_normalized = None
                    dup_start = None
                    continue

                normalized = line.strip()
                if not normalized:
                    prev_normalized = None
                    dup_start = None
                    continue

                if normalized == prev_normalized:
                    if dup_start is None:
                        dup_start = i - 1
                else:
                    if dup_start and i - dup_start >= 3:
                        # Found 3+ consecutive duplicate lines
                        duplicates.append((f.name, dup_start, i - 1, lines[dup_start-1].strip()[:60]))
                    dup_start = None
                    prev_normalized = normalized
        except:
            pass

    return duplicates

def main():
    print("=" * 70)
    print("FOCUSED ENTROPY AUDIT - Muratori Style")
    print("=" * 70)
    print()

    print("1. TICKET STATE MANAGEMENT ISSUES")
    print("-" * 40)
    issues = check_ticket_state_management()
    if issues:
        for issue in issues:
            print(f"  [{issue[0]}] {issue[1]}")
    else:
        print("  None found")
    print()

    print("2. NESTED IMPORTS IN HOT PATH FUNCTIONS")
    print("-" * 40)
    issues = check_import_issues()
    if issues:
        for fname, msg in issues[:10]:
            print(f"  [{fname}] {msg}")
    else:
        print("  None found")
    print()

    print("3. POTENTIAL BUGS (mutable defaults, etc)")
    print("-" * 40)
    issues = check_potential_bugs()
    if issues:
        for fname, line, bugtype, code in issues[:10]:
            print(f"  [{fname}:{line}] {bugtype}: {code}")
    else:
        print("  None found")
    print()

    print("4. ACTUAL DUPLICATE CODE (3+ consecutive lines)")
    print("-" * 40)
    duplicates = check_actual_duplicates()
    if duplicates:
        for fname, start, end, code in duplicates[:10]:
            print(f"  [{fname}:{start}-{end}] {code}")
    else:
        print("  None found")
    print()

    print("5. PATTERN USAGE ACROSS FILES")
    print("-" * 40)
    patterns = find_duplicate_logic_files()
    for pattern, files in patterns.items():
        if len(files) > 1:
            print(f"  {pattern}: {files}")
    print()

if __name__ == "__main__":
    main()