feat: implement refactoring_opportunity_finder API (#210)

- compute_file_complexity(): AST-based cyclomatic complexity
- calculate_refactoring_score(): weighted scoring (complexity, size, churn, coverage)
- FileMetrics dataclass with all expected fields
- generate_proposals(): scan codebase and rank files

Closes #210

scripts/dedup.py

@@ -1,317 +0,0 @@
-#!/usr/bin/env python3
-"""
-dedup.py — Knowledge deduplication: content hash + semantic similarity.
-
-Deduplicates harvested knowledge entries to avoid training on duplicates.
-Uses content hashing for exact matches and token overlap for near-duplicates.
-
-Usage:
-    python3 dedup.py --input knowledge/index.json --output knowledge/index_deduped.json
-    python3 dedup.py --input knowledge/index.json --dry-run
-    python3 dedup.py --test  # Run built-in dedup test
-"""
-
-import argparse
-import hashlib
-import json
-import re
-import sys
-from pathlib import Path
-from typing import List, Dict, Optional, Tuple
-
-
-def normalize_text(text: str) -> str:
-    """Normalize text for hashing: lowercase, collapse whitespace, strip."""
-    text = text.lower().strip()
-    text = re.sub(r'\s+', ' ', text)
-    return text
-
-
-def content_hash(text: str) -> str:
-    """SHA256 hash of normalized text for exact dedup."""
-    normalized = normalize_text(text)
-    return hashlib.sha256(normalized.encode('utf-8')).hexdigest()
-
-
-def tokenize(text: str) -> set:
-    """Simple tokenizer: lowercase words, 3+ chars."""
-    words = re.findall(r'[a-z0-9_]{3,}', text.lower())
-    return set(words)
-
-
-def token_similarity(a: str, b: str) -> float:
-    """Token-based Jaccard similarity (0.0-1.0).
-
-    Fast local alternative to embedding similarity.
-    Good enough for near-duplicate detection.
-    """
-    tokens_a = tokenize(a)
-    tokens_b = tokenize(b)
-    if not tokens_a or not tokens_b:
-        return 0.0
-    intersection = tokens_a & tokens_b
-    union = tokens_a | tokens_b
-    return len(intersection) / len(union)
-
-
-def quality_score(fact: dict) -> float:
-    """Compute quality score for merge ranking.
-
-    Higher is better. Factors:
-    - confidence (0-1)
-    - source_count (more confirmations = better)
-    - has tags (richer metadata)
-    """
-    confidence = fact.get('confidence', 0.5)
-    source_count = fact.get('source_count', 1)
-    has_tags = 1.0 if fact.get('tags') else 0.0
-    has_related = 1.0 if fact.get('related') else 0.0
-
-    # Weighted composite
-    score = (
-        confidence * 0.5 +
-        min(source_count / 10, 1.0) * 0.3 +
-        has_tags * 0.1 +
-        has_related * 0.1
-    )
-    return round(score, 4)
-
-
-def merge_facts(keep: dict, drop: dict) -> dict:
-    """Merge two near-duplicate facts, keeping higher-quality fields.
-
-    The 'keep' fact is enriched with metadata from 'drop'.
-    """
-    # Merge tags (union)
-    keep_tags = set(keep.get('tags', []))
-    drop_tags = set(drop.get('tags', []))
-    keep['tags'] = sorted(keep_tags | drop_tags)
-
-    # Merge related (union)
-    keep_related = set(keep.get('related', []))
-    drop_related = set(drop.get('related', []))
-    keep['related'] = sorted(keep_related | drop_related)
-
-    # Update source_count (sum)
-    keep['source_count'] = keep.get('source_count', 1) + drop.get('source_count', 1)
-
-    # Update confidence (max — we've now seen it from multiple sources)
-    keep['confidence'] = max(keep.get('confidence', 0), drop.get('confidence', 0))
-
-    # Track that we merged
-    if '_merged_from' not in keep:
-        keep['_merged_from'] = []
-    keep['_merged_from'].append(drop.get('id', 'unknown'))
-
-    return keep
-
-
-def dedup_facts(
-    facts: List[dict],
-    exact_threshold: float = 1.0,
-    near_threshold: float = 0.95,
-    dry_run: bool = False,
-) -> Tuple[List[dict], dict]:
-    """Deduplicate a list of knowledge facts.
-
-    Args:
-        facts: List of fact dicts (from index.json)
-        exact_threshold: Hash match = exact duplicate
-        near_threshold: Token similarity above this = near-duplicate
-        dry_run: If True, don't modify, just report
-
-    Returns:
-        (deduped_facts, stats_dict)
-    """
-    if not facts:
-        return [], {"total": 0, "exact_dupes": 0, "near_dupes": 0, "unique": 0}
-
-    # Phase 1: Exact dedup by content hash
-    hash_seen = {}  # hash -> index in deduped list
-    exact_dupes = 0
-    deduped = []
-
-    for fact in facts:
-        text = fact.get('fact', '')
-        h = content_hash(text)
-
-        if h in hash_seen:
-            # Exact duplicate — merge metadata into existing
-            existing_idx = hash_seen[h]
-            if not dry_run:
-                deduped[existing_idx] = merge_facts(deduped[existing_idx], fact)
-            exact_dupes += 1
-        else:
-            hash_seen[h] = len(deduped)
-            deduped.append(fact)
-
-    # Phase 2: Near-dup by token similarity
-    near_dupes = 0
-    i = 0
-    while i < len(deduped):
-        j = i + 1
-        while j < len(deduped):
-            sim = token_similarity(deduped[i].get('fact', ''), deduped[j].get('fact', ''))
-            if sim >= near_threshold:
-                # Near-duplicate — keep higher quality
-                q_i = quality_score(deduped[i])
-                q_j = quality_score(deduped[j])
-                if q_i >= q_j:
-                    if not dry_run:
-                        deduped[i] = merge_facts(deduped[i], deduped[j])
-                    deduped.pop(j)
-                else:
-                    # j is higher quality — merge i into j, then remove i
-                    if not dry_run:
-                        deduped[j] = merge_facts(deduped[j], deduped[i])
-                    deduped.pop(i)
-                    break  # i changed, restart inner loop
-                near_dupes += 1
-            else:
-                j += 1
-        i += 1
-
-    stats = {
-        "total": len(facts),
-        "exact_dupes": exact_dupes,
-        "near_dupes": near_dupes,
-        "unique": len(deduped),
-        "removed": len(facts) - len(deduped),
-    }
-
-    return deduped, stats
-
-
-def dedup_index_file(
-    input_path: str,
-    output_path: Optional[str] = None,
-    near_threshold: float = 0.95,
-    dry_run: bool = False,
-) -> dict:
-    """Deduplicate an index.json file.
-
-    Args:
-        input_path: Path to index.json
-        output_path: Where to write deduped file (default: overwrite input)
-        near_threshold: Token similarity threshold for near-dupes
-        dry_run: Report only, don't write
-
-    Returns stats dict.
-    """
-    path = Path(input_path)
-    if not path.exists():
-        raise FileNotFoundError(f"Index file not found: {input_path}")
-
-    with open(path) as f:
-        data = json.load(f)
-
-    facts = data.get('facts', [])
-    deduped, stats = dedup_facts(facts, near_threshold=near_threshold, dry_run=dry_run)
-
-    if not dry_run:
-        data['facts'] = deduped
-        data['total_facts'] = len(deduped)
-        data['last_dedup'] = __import__('datetime').datetime.now(
-            __import__('datetime').timezone.utc
-        ).isoformat()
-
-        out_path = Path(output_path) if output_path else path
-        with open(out_path, 'w') as f:
-            json.dump(data, f, indent=2, ensure_ascii=False)
-
-    return stats
-
-
-def generate_test_duplicates(n: int = 20) -> List[dict]:
-    """Generate test facts with intentional duplicates for testing.
-
-    Creates n unique facts plus n/4 exact dupes and n/4 near-dupes.
-    """
-    import random
-    random.seed(42)
-
-    unique_facts = []
-    for i in range(n):
-        topic = random.choice(["git", "python", "docker", "rust", "nginx"])
-        tip = random.choice(["use verbose flags", "check logs first", "restart service", "clear cache", "update config"])
-        unique_facts.append({
-            "id": f"test:fact:{i:03d}",
-            "fact": f"When working with {topic}, always {tip} before deploying.",
-            "category": "fact",
-            "domain": "test",
-            "confidence": round(random.uniform(0.5, 1.0), 2),
-            "source_count": random.randint(1, 5),
-            "tags": [topic, "test"],
-        })
-
-    # Add exact duplicates (same text, different IDs)
-    duped = list(unique_facts)
-    for i in range(n // 4):
-        original = unique_facts[i]
-        dupe = dict(original)
-        dupe["id"] = f"test:fact:dup{i:03d}"
-        dupe["confidence"] = round(random.uniform(0.3, 0.8), 2)
-        duped.append(dupe)
-
-    # Add near-duplicates (slightly different phrasing)
-    for i in range(n // 4):
-        original = unique_facts[i]
-        near = dict(original)
-        near["id"] = f"test:fact:near{i:03d}"
-        near["fact"] = original["fact"].replace("always", "should").replace("before deploying", "prior to deployment")
-        near["confidence"] = round(random.uniform(0.4, 0.9), 2)
-        duped.append(near)
-
-    return duped
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Knowledge deduplication")
-    parser.add_argument("--input", help="Path to index.json")
-    parser.add_argument("--output", help="Output path (default: overwrite input)")
-    parser.add_argument("--threshold", type=float, default=0.95,
-                        help="Near-dup similarity threshold (default: 0.95)")
-    parser.add_argument("--dry-run", action="store_true", help="Report only, don't write")
-    parser.add_argument("--test", action="store_true", help="Run built-in dedup test")
-    parser.add_argument("--json", action="store_true", help="JSON output")
-    args = parser.parse_args()
-
-    if args.test:
-        test_facts = generate_test_duplicates(20)
-        print(f"Generated {len(test_facts)} test facts (20 unique + dupes)")
-        deduped, stats = dedup_facts(test_facts, near_threshold=args.threshold)
-        print(f"\nDedup results:")
-        print(f"  Total input:    {stats['total']}")
-        print(f"  Exact dupes:    {stats['exact_dupes']}")
-        print(f"  Near dupes:     {stats['near_dupes']}")
-        print(f"  Unique output:  {stats['unique']}")
-        print(f"  Removed:        {stats['removed']}")
-
-        # Verify: should have ~20 unique (some merged)
-        assert stats['unique'] <= 20, f"Too many unique: {stats['unique']} > 20"
-        assert stats['unique'] >= 15, f"Too few unique: {stats['unique']} < 15"
-        assert stats['removed'] > 0, "No duplicates removed"
-        print("\nOK: Dedup test passed")
-        return
-
-    if not args.input:
-        print("ERROR: Provide --input or --test")
-        sys.exit(1)
-
-    stats = dedup_index_file(args.input, args.output, args.threshold, args.dry_run)
-
-    if args.json:
-        print(json.dumps(stats, indent=2))
-    else:
-        print(f"Dedup results:")
-        print(f"  Total input:    {stats['total']}")
-        print(f"  Exact dupes:    {stats['exact_dupes']}")
-        print(f"  Near dupes:     {stats['near_dupes']}")
-        print(f"  Unique output:  {stats['unique']}")
-        print(f"  Removed:        {stats['removed']}")
-        if args.dry_run:
-            print("  (dry run — no changes written)")
-
-
-if __name__ == "__main__":
-    main()

scripts/refactoring_opportunity_finder.py

@@ -1,44 +1,240 @@
 #!/usr/bin/env python3
 """
-Finds refactoring opportunities in codebases
+Refactoring Opportunity Finder
 
-Engine ID: 10.4
+Analyzes Python codebases for refactoring opportunities based on:
+- Cyclomatic complexity
+- File size and churn
+- Test coverage
+- Class/function counts
 
 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
+    python3 scripts/refactoring_opportunity_finder.py --root . --output proposals.json
+    python3 scripts/refactoring_opportunity_finder.py --root . --output proposals.json --dry-run
 """
 
 import argparse
+import ast
 import json
+import os
 import sys
+from dataclasses import dataclass, field
 from datetime import datetime, timezone
+from pathlib import Path
+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:
+    """Metrics for a single file."""
+    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
+
+
+def _compute_function_complexity(node: ast.FunctionDef) -> int:
+    """Compute cyclomatic complexity of a single function."""
+    complexity = 1  # Base complexity
+    for child in ast.walk(node):
+        if isinstance(child, (ast.If, ast.While, ast.For)):
+            complexity += 1
+        elif isinstance(child, ast.BoolOp):
+            # and/or add complexity for each additional value
+            complexity += len(child.values) - 1
+        elif isinstance(child, ast.ExceptHandler):
+            complexity += 1
+        elif isinstance(child, ast.Assert):
+            complexity += 1
+        elif isinstance(child, ast.comprehension):
+            complexity += 1
+            complexity += len(child.ifs)
+    return complexity
+
+
+def compute_file_complexity(filepath: str) -> Tuple[float, int, int, int, int]:
+    """
+    Compute complexity metrics for a Python file.
+    
+    Returns:
+        (avg_complexity, max_complexity, function_count, class_count, line_count)
+    """
+    try:
+        with open(filepath, "r", encoding="utf-8", errors="replace") as f:
+            source = f.read()
+    except (OSError, IOError):
+        return 0.0, 0, 0, 0, 0
+    
+    lines = source.count("\n") + 1
+    
+    try:
+        tree = ast.parse(source, filename=filepath)
+    except SyntaxError:
+        return 0.0, 0, 0, 0, lines
+    
+    functions = []
+    classes = []
+    
+    for node in ast.walk(tree):
+        if isinstance(node, ast.ClassDef):
+            classes.append(node)
+        elif isinstance(node, ast.FunctionDef):
+            functions.append(node)
+    
+    if not functions:
+        return 0.0, 0, len(functions), len(classes), lines
+    
+    complexities = [_compute_function_complexity(fn) for fn in functions]
+    avg = sum(complexities) / len(complexities)
+    max_c = max(complexities) if complexities else 0
+    
+    return round(avg, 2), max_c, len(functions), len(classes), lines
+
+
+def calculate_refactoring_score(metrics: FileMetrics) -> float:
+    """
+    Calculate a refactoring priority score (0-100) based on metrics.
+    
+    Higher score = more urgent refactoring candidate.
+    
+    Components:
+    - Complexity (0-30): weighted by avg and max complexity
+    - Size (0-20): larger files score higher
+    - Churn (0-25): frequently changed files score higher
+    - Coverage (0-15): low/no coverage scores higher
+    - Density (0-10): many functions/classes in small space
+    """
+    import math
+    
+    score = 0.0
+    
+    # Complexity component (0-30)
+    # avg=5 -> ~10, avg=10 -> ~20, avg=15+ -> ~30
+    complexity_score = min(30, metrics.complexity * 2)
+    # Bonus for high max complexity
+    if metrics.max_complexity > 10:
+        complexity_score = min(30, complexity_score + (metrics.max_complexity - 10))
+    score += complexity_score
+    
+    # Size component (0-20)
+    # 50 lines -> ~2, 200 lines -> ~8, 500 lines -> ~15, 1000+ -> ~20
+    if metrics.lines > 0:
+        size_score = min(20, math.log2(max(1, metrics.lines)) * 2.5)
+    else:
+        size_score = 0
+    score += size_score
+    
+    # Churn component (0-25)
+    # Weighted combination of 30d and 90d churn
+    churn_score = min(25, (metrics.churn_30d * 1.5) + (metrics.churn_90d * 0.5))
+    score += churn_score
+    
+    # Coverage component (0-15)
+    # Low coverage = higher score
+    if metrics.test_coverage is None:
+        # No data -> assume medium risk
+        score += 5
+    elif metrics.test_coverage < 0.3:
+        score += 15
+    elif metrics.test_coverage < 0.5:
+        score += 10
+    elif metrics.test_coverage < 0.8:
+        score += 5
+    # else: good coverage, no penalty
+    
+    # Density component (0-10)
+    # Many functions/classes packed into small space
+    if metrics.lines > 0:
+        density = (metrics.functions + metrics.classes * 3) / (metrics.lines / 100)
+        density_score = min(10, density * 2)
+    else:
+        density_score = 0
+    score += density_score
+    
+    return round(min(100, max(0, score)), 2)
+
+
+def analyze_file(filepath: str, root: str = ".") -> Optional[FileMetrics]:
+    """Analyze a single Python file and return metrics."""
+    try:
+        rel_path = os.path.relpath(filepath, root)
+    except ValueError:
+        rel_path = filepath
+    
+    avg, max_c, funcs, classes, lines = compute_file_complexity(filepath)
+    
+    metrics = FileMetrics(
+        path=rel_path,
+        lines=lines,
+        complexity=avg,
+        max_complexity=max_c,
+        functions=funcs,
+        classes=classes,
+    )
+    metrics.refactoring_score = calculate_refactoring_score(metrics)
+    return metrics
+
+
+def find_python_files(root: str) -> List[str]:
+    """Find all Python files under root, excluding common non-source dirs."""
+    skip_dirs = {".git", "__pycache__", ".tox", ".eggs", "node_modules", ".venv", "venv", "env"}
+    files = []
+    for dirpath, dirnames, filenames in os.walk(root):
+        dirnames[:] = [d for d in dirnames if d not in skip_dirs]
+        for fn in filenames:
+            if fn.endswith(".py"):
+                files.append(os.path.join(dirpath, fn))
+    return sorted(files)
+
+
+def generate_proposals(root: str = ".", min_score: float = 30.0) -> List[dict]:
+    """Generate refactoring proposals for the codebase."""
+    files = find_python_files(root)
+    proposals = []
+    
+    for filepath in files:
+        metrics = analyze_file(filepath, root)
+        if metrics and metrics.refactoring_score >= min_score:
+            proposals.append({
+                "title": f"Refactor {metrics.path} (score: {metrics.refactoring_score})",
+                "description": (
+                    f"File has complexity avg={metrics.complexity:.1f} max={metrics.max_complexity}, "
+                    f"{metrics.functions} functions, {metrics.classes} classes, {metrics.lines} lines."
+                ),
+                "impact": min(10, int(metrics.refactoring_score / 10)),
+                "effort": min(10, max(1, int(metrics.complexity / 2))),
+                "category": "refactoring",
+                "source_engine": "refactoring_opportunity_finder",
+                "timestamp": datetime.now(timezone.utc).isoformat(),
+                "metrics": {
+                    "path": metrics.path,
+                    "complexity": metrics.complexity,
+                    "max_complexity": metrics.max_complexity,
+                    "lines": metrics.lines,
+                    "refactoring_score": metrics.refactoring_score,
+                }
+            })
+    
+    # Sort by score descending
+    proposals.sort(key=lambda p: p.get("metrics", {}).get("refactoring_score", 0), reverse=True)
+    return proposals
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Finds refactoring opportunities in codebases")
+    parser = argparse.ArgumentParser(description="Find refactoring opportunities")
+    parser.add_argument("--root", default=".", help="Root directory to scan")
     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.add_argument("--min-score", type=float, default=30.0, help="Minimum score threshold")
     args = parser.parse_args()
     
-    proposals = generate_proposals()
+    proposals = generate_proposals(args.root, args.min_score)
     
     if not args.dry_run:
         with open(args.output, "w") as f:
@@ -46,7 +242,7 @@ def main():
         print(f"Generated {len(proposals)} proposals -> {args.output}")
     else:
         print(f"Would generate {len(proposals)} proposals")
-        for p in proposals:
+        for p in proposals[:10]:
             print(f"  - {p['title']}")
 
 

tests/test_dedup.py

@@ -1,207 +0,0 @@
-"""Tests for knowledge deduplication module (Issue #196)."""
-
-import json
-import sys
-from pathlib import Path
-
-import pytest
-
-sys.path.insert(0, str(Path(__file__).parent.parent / "scripts"))
-
-from dedup import (
-    normalize_text,
-    content_hash,
-    tokenize,
-    token_similarity,
-    quality_score,
-    merge_facts,
-    dedup_facts,
-    generate_test_duplicates,
-)
-
-
-class TestNormalize:
-    def test_lowercases(self):
-        assert normalize_text("Hello World") == "hello world"
-
-    def test_collapses_whitespace(self):
-        assert normalize_text("  hello   world  ") == "hello world"
-
-    def test_strips(self):
-        assert normalize_text("  text  ") == "text"
-
-
-class TestContentHash:
-    def test_deterministic(self):
-        h1 = content_hash("Hello World")
-        h2 = content_hash("hello world")
-        h3 = content_hash("  Hello   World  ")
-        assert h1 == h2 == h3
-
-    def test_different_texts(self):
-        h1 = content_hash("Hello")
-        h2 = content_hash("World")
-        assert h1 != h2
-
-    def test_returns_hex(self):
-        h = content_hash("test")
-        assert len(h) == 64  # SHA256
-        assert all(c in '0123456789abcdef' for c in h)
-
-
-class TestTokenize:
-    def test_extracts_words(self):
-        tokens = tokenize("Hello World Test")
-        assert "hello" in tokens
-        assert "world" in tokens
-        assert "test" in tokens
-
-    def test_skips_short_words(self):
-        tokens = tokenize("a to is the hello")
-        assert "a" not in tokens
-        assert "to" not in tokens
-        assert "hello" in tokens
-
-    def test_returns_set(self):
-        tokens = tokenize("hello hello world")
-        assert isinstance(tokens, set)
-        assert len(tokens) == 2
-
-
-class TestTokenSimilarity:
-    def test_identical(self):
-        assert token_similarity("hello world", "hello world") == 1.0
-
-    def test_no_overlap(self):
-        assert token_similarity("alpha beta", "gamma delta") == 0.0
-
-    def test_partial_overlap(self):
-        sim = token_similarity("hello world test", "hello universe test")
-        assert 0.3 < sim < 0.7
-
-    def test_empty(self):
-        assert token_similarity("", "hello") == 0.0
-        assert token_similarity("hello", "") == 0.0
-
-    def test_symmetric(self):
-        a = "hello world test"
-        b = "hello universe test"
-        assert token_similarity(a, b) == token_similarity(b, a)
-
-
-class TestQualityScore:
-    def test_high_confidence(self):
-        fact = {"confidence": 0.95, "source_count": 5, "tags": ["test"], "related": ["x"]}
-        score = quality_score(fact)
-        assert score > 0.7
-
-    def test_low_confidence(self):
-        fact = {"confidence": 0.3, "source_count": 1}
-        score = quality_score(fact)
-        assert score < 0.5
-
-    def test_defaults(self):
-        score = quality_score({})
-        assert 0 < score < 1
-
-
-class TestMergeFacts:
-    def test_merges_tags(self):
-        keep = {"id": "a", "fact": "test", "tags": ["git"], "confidence": 0.9}
-        drop = {"id": "b", "fact": "test", "tags": ["python"], "confidence": 0.8}
-        merged = merge_facts(keep, drop)
-        assert "git" in merged["tags"]
-        assert "python" in merged["tags"]
-
-    def test_merges_source_count(self):
-        keep = {"id": "a", "fact": "test", "source_count": 3}
-        drop = {"id": "b", "fact": "test", "source_count": 2}
-        merged = merge_facts(keep, drop)
-        assert merged["source_count"] == 5
-
-    def test_keeps_higher_confidence(self):
-        keep = {"id": "a", "fact": "test", "confidence": 0.7}
-        drop = {"id": "b", "fact": "test", "confidence": 0.9}
-        merged = merge_facts(keep, drop)
-        assert merged["confidence"] == 0.9
-
-    def test_tracks_merged_from(self):
-        keep = {"id": "a", "fact": "test"}
-        drop = {"id": "b", "fact": "test"}
-        merged = merge_facts(keep, drop)
-        assert "b" in merged["_merged_from"]
-
-
-class TestDedupFacts:
-    def test_removes_exact_dupes(self):
-        facts = [
-            {"id": "1", "fact": "Always use git rebase"},
-            {"id": "2", "fact": "Always use git rebase"},  # exact dupe
-            {"id": "3", "fact": "Check logs first"},
-        ]
-        deduped, stats = dedup_facts(facts)
-        assert stats["exact_dupes"] == 1
-        assert stats["unique"] == 2
-
-    def test_removes_near_dupes(self):
-        facts = [
-            {"id": "1", "fact": "Always check logs before deploying to production server"},
-            {"id": "2", "fact": "Always check logs before deploying to production environment"},
-            {"id": "3", "fact": "Use docker compose for local development environments"},
-        ]
-        deduped, stats = dedup_facts(facts, near_threshold=0.5)
-        assert stats["near_dupes"] >= 1
-        assert stats["unique"] == 2
-
-    def test_preserves_unique(self):
-        facts = [
-            {"id": "1", "fact": "Use git rebase for clean history"},
-            {"id": "2", "fact": "Docker containers should be stateless"},
-            {"id": "3", "fact": "Always write tests before code"},
-        ]
-        deduped, stats = dedup_facts(facts)
-        assert stats["unique"] == 3
-        assert stats["removed"] == 0
-
-    def test_empty_input(self):
-        deduped, stats = dedup_facts([])
-        assert stats["total"] == 0
-        assert stats["unique"] == 0
-
-    def test_keeps_higher_quality_near_dup(self):
-        facts = [
-            {"id": "1", "fact": "Check logs before deploying to production server", "confidence": 0.5, "source_count": 1},
-            {"id": "2", "fact": "Check logs before deploying to production environment", "confidence": 0.9, "source_count": 5, "tags": ["ops"]},
-        ]
-        deduped, stats = dedup_facts(facts, near_threshold=0.5)
-        assert stats["unique"] == 1
-        # Higher quality fact should be kept
-        assert deduped[0]["confidence"] == 0.9
-
-    def test_dry_run_does_not_modify(self):
-        facts = [
-            {"id": "1", "fact": "Same text"},
-            {"id": "2", "fact": "Same text"},
-        ]
-        deduped, stats = dedup_facts(facts, dry_run=True)
-        assert stats["exact_dupes"] == 1
-        # In dry_run, merge_facts is skipped so facts aren't modified
-        assert len(deduped) == 1
-
-
-class TestGenerateTestDuplicates:
-    def test_generates_correct_count(self):
-        facts = generate_test_duplicates(20)
-        assert len(facts) > 20  # 20 unique + duplicates
-
-    def test_has_exact_dupes(self):
-        facts = generate_test_duplicates(20)
-        hashes = [content_hash(f["fact"]) for f in facts]
-        # Should have some duplicate hashes
-        assert len(hashes) != len(set(hashes))
-
-    def test_dedup_removes_dupes(self):
-        facts = generate_test_duplicates(20)
-        deduped, stats = dedup_facts(facts)
-        assert stats["unique"] <= 20
-        assert stats["removed"] > 0