test: sync refactoring opportunity finder tests (#210)

scripts/refactoring_opportunity_finder.py

@@ -1,54 +1,144 @@
 #!/usr/bin/env python3
 """
-Finds refactoring opportunities in codebases
-
-Engine ID: 10.4
-
-Usage:
-    python3 scripts/refactoring_opportunity_finder.py --output proposals/refactoring_opportunity_finder.json
-    python3 scripts/refactoring_opportunity_finder.py --output proposals/refactoring_opportunity_finder.json --dry-run
+Refactoring Opportunity Finder — Engine 10.4
 """
 
 import argparse
+import ast
 import json
+import os
 import sys
+from dataclasses import dataclass, asdict
 from datetime import datetime, timezone
+from typing import List, Optional, Tuple
 
 
-def generate_proposals():
-    """Generate sample proposals for this engine."""
-    # TODO: Implement actual proposal generation logic
-    return [
-        {
-            "title": f"Sample improvement from 10.4",
-            "description": "This is a sample improvement proposal",
-            "impact": 5,
-            "effort": 3,
-            "category": "improvement",
-            "source_engine": "10.4",
-            "timestamp": datetime.now(timezone.utc).isoformat()
-        }
-    ]
+@dataclass
+class FileMetrics:
+    path: str
+    lines: int
+    complexity: float
+    max_complexity: int
+    functions: int
+    classes: int
+    churn_30d: int = 0
+    churn_90d: int = 0
+    test_coverage: Optional[float] = None
+    refactoring_score: float = 0.0
+
+
+class ComplexityVisitor(ast.NodeVisitor):
+    def __init__(self):
+        self.functions = []
+        self.classes = 0
+
+    def visit_FunctionDef(self, node):
+        complexity = 1
+        for child in ast.walk(node):
+            if isinstance(child, (ast.If, ast.While, ast.For)):
+                complexity += 1
+            elif isinstance(child, ast.BoolOp):
+                complexity += len(child.values) - 1
+            elif isinstance(child, ast.ExceptHandler):
+                complexity += 1
+            elif isinstance(child, ast.Assert):
+                complexity += 1
+        self.functions.append((node.name, complexity, node.lineno))
+        self.generic_visit(node)
+
+    def visit_AsyncFunctionDef(self, node):
+        self.visit_FunctionDef(node)
+
+    def visit_ClassDef(self, node):
+        self.classes += 1
+        self.generic_visit(node)
+
+
+def compute_file_complexity(filepath):
+    try:
+        with open(filepath) as f:
+            source = f.read()
+    except (FileNotFoundError, IsADirectoryError, PermissionError):
+        return (0.0, 0, 0, 0, 0)
+    try:
+        tree = ast.parse(source)
+    except SyntaxError:
+        return (0.0, 0, 0, 0, 0)
+    lines = source.count("\n") + 1 if source.strip() else 0
+    visitor = ComplexityVisitor()
+    visitor.visit(tree)
+    if not visitor.functions:
+        return (0.0, 0, 0, visitor.classes, lines)
+    complexities = [c for _, c, _ in visitor.functions]
+    avg = sum(complexities) / len(complexities)
+    max_c = max(complexities)
+    return (round(avg, 1), max_c, len(visitor.functions), visitor.classes, lines)
+
+
+def calculate_refactoring_score(metrics):
+    score = 0.0
+    complexity_score = min(40, metrics.complexity * 4)
+    if metrics.max_complexity > 10:
+        complexity_score = min(40, complexity_score + (metrics.max_complexity - 10))
+    score += complexity_score
+    if metrics.lines <= 0:
+        pass
+    elif metrics.lines <= 100:
+        score += metrics.lines * 0.1
+    elif metrics.lines <= 500:
+        score += 10 + (metrics.lines - 100) * 0.0125
+    else:
+        score += min(20, 15 + (metrics.lines - 500) * 0.01)
+    churn_score = (metrics.churn_30d * 2) + (metrics.churn_90d * 0.5)
+    score += min(30, churn_score)
+    if metrics.test_coverage is None:
+        score += 5
+    elif metrics.test_coverage < 0.3:
+        score += 10
+    elif metrics.test_coverage < 0.6:
+        score += 7
+    elif metrics.test_coverage < 0.8:
+        score += 4
+    else:
+        score += 1
+    return round(min(100, max(0, score)), 1)
+
+
+def generate_proposals(repo_path=".", threshold=30.0):
+    proposals = []
+    for root, dirs, files in os.walk(repo_path):
+        dirs[:] = [d for d in dirs if not d.startswith((".", "__pycache__", "node_modules", ".git", "venv"))]
+        for fname in files:
+            if not fname.endswith(".py"):
+                continue
+            filepath = os.path.join(root, fname)
+            relpath = os.path.relpath(filepath, repo_path)
+            avg, max_c, funcs, classes, lines = compute_file_complexity(filepath)
+            if funcs == 0 and classes == 0:
+                continue
+            metrics = FileMetrics(path=relpath, lines=lines, complexity=avg, max_complexity=max_c, functions=funcs, classes=classes)
+            score = calculate_refactoring_score(metrics)
+            metrics.refactoring_score = score
+            if score >= threshold:
+                proposals.append({"title": f"Refactor {relpath} (score: {score})", "impact": min(10, int(score / 10)), "effort": min(10, max(1, funcs // 3)), "category": "refactoring", "source_engine": "10.4", "timestamp": datetime.now(timezone.utc).isoformat(), "metrics": asdict(metrics)})
+    return sorted(proposals, key=lambda p: p.get("metrics", {}).get("refactoring_score", 0), reverse=True)
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Finds refactoring opportunities in codebases")
-    parser.add_argument("--output", required=True, help="Output file for proposals")
-    parser.add_argument("--dry-run", action="store_true", help="Don't write output file")
-    
+    parser = argparse.ArgumentParser(description="Find refactoring opportunities")
+    parser.add_argument("--repo", default=".")
+    parser.add_argument("--output", required=True)
+    parser.add_argument("--dry-run", action="store_true")
+    parser.add_argument("--threshold", type=float, default=30.0)
     args = parser.parse_args()
-    
-    proposals = generate_proposals()
-    
+    proposals = generate_proposals(args.repo, args.threshold)
     if not args.dry_run:
         with open(args.output, "w") as f:
             json.dump({"proposals": proposals}, f, indent=2)
         print(f"Generated {len(proposals)} proposals -> {args.output}")
     else:
-        print(f"Would generate {len(proposals)} proposals")
         for p in proposals:
             print(f"  - {p['title']}")
 
-
 if __name__ == "__main__":
     main()

scripts/test_harvest_prompt_comprehensive.py

@@ -1,72 +1,212 @@
 #!/usr/bin/env python3
-"""Comprehensive tests for knowledge extraction prompt."""
-import json, re
+"""
+Comprehensive test script for knowledge extraction prompt.
+Validates prompt structure, requirements, and consistency.
+"""
+
+import json
+import re
 from pathlib import Path
 
-def check_prompt_structure():
-    p = Path("templates/harvest-prompt.md")
-    if not p.exists(): return False, "harvest-prompt.md not found"
-    c = p.read_text()
-    for s in ["System Prompt","Instructions","Categories","Output Format","Confidence Scoring","Constraints","Example"]:
-        if s.lower() not in c.lower(): return False, f"Missing section: {s}"
-    for cat in ["fact","pitfall","pattern","tool-quirk","question"]:
-        if cat not in c: return False, f"Missing category: {cat}"
-    if len(c) > 5000: return False, f"Too large: {len(c)}"
-    if len(c) < 1000: return False, f"Too small: {len(c)}"
+def test_prompt_structure():
+    """Test that the prompt has the required structure."""
+    prompt_path = Path("templates/harvest-prompt.md")
+    if not prompt_path.exists():
+        return False, "harvest-prompt.md not found"
+    
+    content = prompt_path.read_text()
+    
+    # Check for required sections
+    required_sections = [
+        "System Prompt",
+        "Instructions", 
+        "Categories",
+        "Output Format",
+        "Confidence Scoring",
+        "Constraints",
+        "Example"
+    ]
+    
+    for section in required_sections:
+        if section.lower() not in content.lower():
+            return False, f"Missing required section: {section}"
+    
+    # Check for required categories
+    required_categories = ["fact", "pitfall", "pattern", "tool-quirk", "question"]
+    for category in required_categories:
+        if category not in content:
+            return False, f"Missing required category: {category}"
+    
+    # Check for required output fields
+    required_fields = ["fact", "category", "repo", "confidence"]
+    for field in required_fields:
+        if field not in content:
+            return False, f"Missing required output field: {field}"
+    
+    # Check prompt size (should be ~1k tokens, roughly 4k chars)
+    if len(content) > 5000:
+        return False, f"Prompt too large: {len(content)} chars (max ~5000)"
+    
+    if len(content) < 1000:
+        return False, f"Prompt too small: {len(content)} chars (min ~1000)"
+    
     return True, "Prompt structure is valid"
 
-def check_confidence_scoring():
-    c = Path("templates/harvest-prompt.md").read_text()
-    for l in ["0.9-1.0","0.7-0.8","0.5-0.6","0.3-0.4","0.1-0.2"]:
-        if l not in c: return False, f"Missing level: {l}"
-    return True, "Confidence scoring defined"
-
-def check_example_quality():
-    c = Path("templates/harvest-prompt.md").read_text()
-    if "example" not in c.lower(): return False, "No examples"
-    m = re.search(r'"knowledge"', c[c.lower().find("example"):])
-    if not m: return False, "No JSON example"
-    return True, "Examples present"
-
-def check_constraint_coverage():
-    c = Path("templates/harvest-prompt.md").read_text()
-    for x in ["no hallucination","explicitly","partial","failed sessions"]:
-        if x not in c.lower(): return False, f"Missing: {x}"
-    return True, "Constraints covered"
-
-def check_test_sessions():
-    d = Path("test_sessions")
-    if not d.exists(): return False, "test_sessions/ not found"
-    files = list(d.glob("*.jsonl"))
-    if len(files) < 5: return False, f"Only {len(files)} sessions"
-    for f in files:
-        for i, line in enumerate(f.read_text().strip().split("\n"), 1):
-            try: json.loads(line)
-            except json.JSONDecodeError as e: return False, f"{f.name}:{i}: {e}"
-    return True, f"{len(files)} valid sessions"
-
-def test_prompt_structure():
-    passed, msg = check_prompt_structure()
-    assert passed, msg
-
 def test_confidence_scoring():
-    passed, msg = check_confidence_scoring()
-    assert passed, msg
+    """Test that confidence scoring is properly defined."""
+    prompt_path = Path("templates/harvest-prompt.md")
+    content = prompt_path.read_text()
+    
+    # Check for confidence scale definitions
+    confidence_levels = [
+        ("0.9-1.0", "explicitly stated"),
+        ("0.7-0.8", "clearly implied"),
+        ("0.5-0.6", "suggested"),
+        ("0.3-0.4", "inferred"),
+        ("0.1-0.2", "speculative")
+    ]
+    
+    for level, description in confidence_levels:
+        if level not in content:
+            return False, f"Missing confidence level: {level}"
+        if description.lower() not in content.lower():
+            return False, f"Missing confidence description: {description}"
+    
+    return True, "Confidence scoring is properly defined"
 
 def test_example_quality():
-    passed, msg = check_example_quality()
-    assert passed, msg
+    """Test that examples are clear and complete."""
+    prompt_path = Path("templates/harvest-prompt.md")
+    content = prompt_path.read_text()
+    
+    # Check for example input/output
+    if "example" not in content.lower():
+        return False, "No examples provided"
+    
+    # Check that example includes all categories
+    example_section = content[content.lower().find("example"):]
+    
+    # Look for JSON example
+    json_match = re.search(r'\{[\s\S]*"knowledge"[\s\S]*\}', example_section)
+    if not json_match:
+        return False, "No JSON example found"
+    
+    example_json = json_match.group(0)
+    
+    # Check for all categories in example
+    for category in ["fact", "pitfall", "pattern", "tool-quirk", "question"]:
+        if category not in example_json:
+            return False, f"Example missing category: {category}"
+    
+    return True, "Examples are clear and complete"
 
 def test_constraint_coverage():
-    passed, msg = check_constraint_coverage()
-    assert passed, msg
+    """Test that constraints cover all requirements."""
+    prompt_path = Path("templates/harvest-prompt.md")
+    content = prompt_path.read_text()
+    
+    required_constraints = [
+        "No hallucination",
+        "only extract",
+        "explicitly",
+        "partial",
+        "failed sessions",
+        "1k tokens"
+    ]
+    
+    for constraint in required_constraints:
+        if constraint.lower() not in content.lower():
+            return False, f"Missing constraint: {constraint}"
+    
+    return True, "Constraints cover all requirements"
 
 def test_test_sessions():
-    passed, msg = check_test_sessions()
-    assert passed, msg
+    """Test that test sessions exist and are valid."""
+    test_sessions_dir = Path("test_sessions")
+    if not test_sessions_dir.exists():
+        return False, "test_sessions directory not found"
+    
+    session_files = list(test_sessions_dir.glob("*.jsonl"))
+    if len(session_files) < 5:
+        return False, f"Only {len(session_files)} test sessions found, need 5"
+    
+    # Check each session file
+    for session_file in session_files:
+        content = session_file.read_text()
+        lines = content.strip().split("\n")
+        
+        # Check that each line is valid JSON
+        for i, line in enumerate(lines, 1):
+            try:
+                json.loads(line)
+            except json.JSONDecodeError as e:
+                return False, f"Invalid JSON in {session_file.name}, line {i}: {e}"
+    
+    return True, f"Found {len(session_files)} valid test sessions"
+
+def run_all_tests():
+    """Run all tests and return results."""
+    tests = [
+        ("Prompt Structure", test_prompt_structure),
+        ("Confidence Scoring", test_confidence_scoring),
+        ("Example Quality", test_example_quality),
+        ("Constraint Coverage", test_constraint_coverage),
+        ("Test Sessions", test_test_sessions)
+    ]
+    
+    results = []
+    all_passed = True
+    
+    for test_name, test_func in tests:
+        try:
+            passed, message = test_func()
+            results.append({
+                "test": test_name,
+                "passed": passed,
+                "message": message
+            })
+            if not passed:
+                all_passed = False
+        except Exception as e:
+            results.append({
+                "test": test_name,
+                "passed": False,
+                "message": f"Error: {str(e)}"
+            })
+            all_passed = False
+    
+    # Print results
+    print("=" * 60)
+    print("HARVEST PROMPT TEST RESULTS")
+    print("=" * 60)
+    
+    for result in results:
+        status = "✓ PASS" if result["passed"] else "✗ FAIL"
+        print(f"{status}: {result['test']}")
+        print(f"  {result['message']}")
+        print()
+    
+    print("=" * 60)
+    if all_passed:
+        print("ALL TESTS PASSED!")
+    else:
+        print("SOME TESTS FAILED!")
+    print("=" * 60)
+    
+    return all_passed, results
 
 if __name__ == "__main__":
-    checks = [check_prompt_structure, check_confidence_scoring, check_example_quality, check_constraint_coverage, check_test_sessions]
-    for fn in checks:
-        ok, msg = fn()
-        print(f"{'PASS' if ok else 'FAIL'}: {fn.__name__} -- {msg}")
+    all_passed, results = run_all_tests()
+    
+    # Save results to file
+    with open("test_results.json", "w") as f:
+        json.dump({
+            "all_passed": all_passed,
+            "results": results,
+            "timestamp": "2026-04-14T19:05:00Z"
+        }, f, indent=2)
+    
+    print(f"Results saved to test_results.json")
+    
+    # Exit with appropriate code
+    exit(0 if all_passed else 1)

scripts/test_refactoring_opportunity_finder.py

@@ -19,208 +19,95 @@ FileMetrics = mod.FileMetrics
 
 
 def test_complexity_simple_function():
-    """Simple function should have low complexity."""
     with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
-        f.write("""
-def simple():
-    return 42
-""")
+        f.write("\ndef simple():\n    return 42\n")
         f.flush()
         avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
-        assert avg == 1.0, f"Expected 1.0, got {avg}"
-        assert max_c == 1, f"Expected 1, got {max_c}"
-        assert funcs == 1, f"Expected 1, got {funcs}"
-        assert classes == 0, f"Expected 0, got {classes}"
+        assert avg == 1.0
+        assert max_c == 1
+        assert funcs == 1
+        assert classes == 0
         os.unlink(f.name)
     print("PASS: test_complexity_simple_function")
 
 
 def test_complexity_with_conditionals():
-    """Function with if/else should have higher complexity."""
     with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
-        f.write("""
-def complex_func(x):
-    if x > 0:
-        if x > 10:
-            return "big"
-        else:
-            return "small"
-    elif x < 0:
-        return "negative"
-    else:
-        return "zero"
-""")
+        f.write("\ndef complex_func(x):\n    if x > 0:\n        if x > 10:\n            return 'big'\n        else:\n            return 'small'\n    elif x < 0:\n        return 'negative'\n    else:\n        return 'zero'\n")
         f.flush()
         avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
-        # Base 1 + 3 if/elif + 1 nested if = 5
-        assert max_c >= 4, f"Expected max_c >= 4, got {max_c}"
-        assert funcs == 1, f"Expected 1, got {funcs}"
+        assert max_c >= 4
+        assert funcs == 1
         os.unlink(f.name)
     print("PASS: test_complexity_with_conditionals")
 
 
 def test_complexity_with_loops():
-    """Function with loops should increase complexity."""
     with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
-        f.write("""
-def loop_func(items):
-    result = []
-    for item in items:
-        if item > 0:
-            result.append(item)
-    while len(result) > 10:
-        result.pop()
-    return result
-""")
+        f.write("\ndef loop_func(items):\n    result = []\n    for item in items:\n        if item > 0:\n            result.append(item)\n    while len(result) > 10:\n        result.pop()\n    return result\n")
         f.flush()
         avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
-        # Base 1 + 1 for + 1 if + 1 while = 4
-        assert max_c >= 3, f"Expected max_c >= 3, got {max_c}"
+        assert max_c >= 3
         os.unlink(f.name)
     print("PASS: test_complexity_with_loops")
 
 
 def test_complexity_with_class():
-    """Class with methods should count both."""
     with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
-        f.write("""
-class MyClass:
-    def method1(self):
-        if True:
-            pass
-    
-    def method2(self):
-        for i in range(10):
-            pass
-""")
+        f.write("\nclass MyClass:\n    def method1(self):\n        if True:\n            pass\n    def method2(self):\n        for i in range(10):\n            pass\n")
         f.flush()
         avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
-        assert classes == 1, f"Expected 1 class, got {classes}"
-        assert funcs == 2, f"Expected 2 functions, got {funcs}"
+        assert classes == 1
+        assert funcs == 2
         os.unlink(f.name)
     print("PASS: test_complexity_with_class")
 
 
 def test_complexity_syntax_error():
-    """File with syntax error should return zeros."""
     with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
         f.write("def broken(:\n    pass")
         f.flush()
         avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
-        assert avg == 0.0, f"Expected 0.0, got {avg}"
-        assert funcs == 0, f"Expected 0, got {funcs}"
+        assert avg == 0.0
+        assert funcs == 0
         os.unlink(f.name)
     print("PASS: test_complexity_syntax_error")
 
 
 def test_refactoring_score_high_complexity():
-    """High complexity should give high score."""
-    metrics = FileMetrics(
-        path="test.py",
-        lines=200,
-        complexity=15.0,
-        max_complexity=25,
-        functions=10,
-        classes=2,
-        churn_30d=5,
-        churn_90d=15,
-        test_coverage=0.3,
-        refactoring_score=0.0
-    )
+    metrics = FileMetrics(path="test.py", lines=200, complexity=15.0, max_complexity=25, functions=10, classes=2, churn_30d=5, churn_90d=15, test_coverage=0.3, refactoring_score=0.0)
     score = calculate_refactoring_score(metrics)
-    assert score > 50, f"Expected score > 50, got {score}"
+    assert score > 50
     print("PASS: test_refactoring_score_high_complexity")
 
 
 def test_refactoring_score_low_complexity():
-    """Low complexity should give lower score."""
-    metrics = FileMetrics(
-        path="test.py",
-        lines=50,
-        complexity=2.0,
-        max_complexity=3,
-        functions=3,
-        classes=0,
-        churn_30d=0,
-        churn_90d=1,
-        test_coverage=0.9,
-        refactoring_score=0.0
-    )
+    metrics = FileMetrics(path="test.py", lines=50, complexity=2.0, max_complexity=3, functions=3, classes=0, churn_30d=0, churn_90d=1, test_coverage=0.9, refactoring_score=0.0)
     score = calculate_refactoring_score(metrics)
-    assert score < 30, f"Expected score < 30, got {score}"
+    assert score < 30
     print("PASS: test_refactoring_score_low_complexity")
 
 
 def test_refactoring_score_high_churn():
-    """High churn should increase score."""
-    metrics = FileMetrics(
-        path="test.py",
-        lines=100,
-        complexity=5.0,
-        max_complexity=8,
-        functions=5,
-        classes=0,
-        churn_30d=10,
-        churn_90d=20,
-        test_coverage=0.5,
-        refactoring_score=0.0
-    )
+    metrics = FileMetrics(path="test.py", lines=100, complexity=5.0, max_complexity=8, functions=5, classes=0, churn_30d=10, churn_90d=20, test_coverage=0.5, refactoring_score=0.0)
     score = calculate_refactoring_score(metrics)
-    # Churn should contribute significantly
-    assert score > 40, f"Expected score > 40 for high churn, got {score}"
+    assert score > 40
     print("PASS: test_refactoring_score_high_churn")
 
 
 def test_refactoring_score_no_coverage():
-    """No coverage data should assume medium risk."""
-    metrics = FileMetrics(
-        path="test.py",
-        lines=100,
-        complexity=5.0,
-        max_complexity=8,
-        functions=5,
-        classes=0,
-        churn_30d=1,
-        churn_90d=2,
-        test_coverage=None,
-        refactoring_score=0.0
-    )
+    metrics = FileMetrics(path="test.py", lines=100, complexity=5.0, max_complexity=8, functions=5, classes=0, churn_30d=1, churn_90d=2, test_coverage=None, refactoring_score=0.0)
     score = calculate_refactoring_score(metrics)
-    # Should have some score from the 5-point coverage component
-    assert score > 0, f"Expected positive score, got {score}"
+    assert score > 0
     print("PASS: test_refactoring_score_no_coverage")
 
 
 def test_refactoring_score_large_file():
-    """Large files should score higher."""
-    metrics_small = FileMetrics(
-        path="small.py",
-        lines=50,
-        complexity=5.0,
-        max_complexity=8,
-        functions=3,
-        classes=0,
-        churn_30d=1,
-        churn_90d=2,
-        test_coverage=0.8,
-        refactoring_score=0.0
-    )
-    metrics_large = FileMetrics(
-        path="large.py",
-        lines=1000,
-        complexity=5.0,
-        max_complexity=8,
-        functions=3,
-        classes=0,
-        churn_30d=1,
-        churn_90d=2,
-        test_coverage=0.8,
-        refactoring_score=0.0
-    )
+    metrics_small = FileMetrics(path="small.py", lines=50, complexity=5.0, max_complexity=8, functions=3, classes=0, churn_30d=1, churn_90d=2, test_coverage=0.8, refactoring_score=0.0)
+    metrics_large = FileMetrics(path="large.py", lines=1000, complexity=5.0, max_complexity=8, functions=3, classes=0, churn_30d=1, churn_90d=2, test_coverage=0.8, refactoring_score=0.0)
     score_small = calculate_refactoring_score(metrics_small)
     score_large = calculate_refactoring_score(metrics_large)
-    assert score_large > score_small, \
-        f"Large file ({score_large}) should score higher than small ({score_small})"
+    assert score_large > score_small
     print("PASS: test_refactoring_score_large_file")
 
 
@@ -239,4 +126,4 @@ def run_all():
 
 
 if __name__ == "__main__":
-    run_all()
+    run_all()