feat(10.8): add Progress Tracker — track test/doc coverage, issue close rate, dep freshness

Implements 10.8: Progress Tracker.

- Script: scripts/progress_tracker.py
- Stores weekly snapshots in metrics/snapshots/ (auto-created)
- Generates trends table in metrics/TRENDS.md
- Tracks: test-to-source ratio, doc coverage via AST, issue close rate (Gitea API), dep freshness (pip)
- Outputs stdout summary for weekly review

Usage:
    python3 scripts/progress_tracker.py
    python3 scripts/progress_tracker.py --json
    python3 scripts/progress_tracker.py --output metrics/TRENDS.md

Weekly cron: 0 9 * * 1 cd /path && python3 scripts/progress_tracker.py

Closes #173

scripts/code_duplication_detector.py

@@ -1,366 +0,0 @@
-#!/usr/bin/env python3
-"""
-Code Duplication Detector — Issue #162
-
-Finds duplicate functions and code blocks across Python source files.
-Reports duplication percentage and outputs a duplication report.
-
-Usage:
-    python3 scripts/code_duplication_detector.py --output reports/code_duplication.json
-    python3 scripts/code_duplication_detector.py --directory scripts/ --dry-run
-    python3 scripts/code_duplication_detector.py --test  # Run built-in test
-"""
-
-import argparse
-import hashlib
-import json
-import os
-import re
-import sys
-from collections import defaultdict
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import List, Dict, Tuple, Optional
-
-
-# ── AST helpers ────────────────────────────────────────────────────────────
-
-def normalize_code(text: str) -> str:
-    """Normalize code for comparison: strip comments, normalize whitespace."""
-    # Remove comments (both # and docstring triple-quote strings)
-    text = re.sub(r'#.*$', '', text, flags=re.MULTILINE)
-    text = re.sub(r'""".*?"""', '', text, flags=re.DOTALL)
-    text = re.sub(r"'''.*?'''", '', text, flags=re.DOTALL)
-    # Normalize whitespace
-    text = re.sub(r'\s+', ' ', text).strip()
-    return text.lower()
-
-
-def code_hash(text: str) -> str:
-    """SHA256 hash of normalized code for exact duplicate detection."""
-    normalized = normalize_code(text)
-    return hashlib.sha256(normalized.encode('utf-8')).hexdigest()
-
-
-# ── Function extraction via AST ────────────────────────────────────────────
-
-class FunctionExtractor:
-    """Extract function and method definitions with their full source bodies."""
-
-    def __init__(self, source: str, filepath: str):
-        self.source = source
-        self.filepath = filepath
-        self.lines = source.splitlines()
-        self.functions: List[Dict] = []
-
-    def _get_source_segment(self, start_lineno: int, end_lineno: int) -> str:
-        """Get source code from start to end line (1-indexed, inclusive)."""
-        # AST end_lineno is inclusive
-        start_idx = start_lineno - 1
-        end_idx = end_lineno
-        return '\n'.join(self.lines[start_idx:end_idx])
-
-    def visit(self, tree):
-        """Collect all function and async function definitions."""
-        for node in ast.walk(tree):
-            if isinstance(node, ast.FunctionDef) or isinstance(node, ast.AsyncFunctionDef):
-                # Get the full source for this function including decorators
-                start = node.lineno
-                end = node.end_lineno
-                body_source = self._get_source_segment(start, end)
-
-                # Also collect parent class name if this is a method
-                class_name = None
-                parent = node.parent if hasattr(node, 'parent') else None
-                if parent and isinstance(parent, ast.ClassDef):
-                    class_name = parent.name
-
-                self.functions.append({
-                    'name': node.name,
-                    'file': self.filepath,
-                    'start_line': start,
-                    'end_line': end,
-                    'body': body_source,
-                    'class_name': class_name,
-                    'is_method': class_name is not None,
-                })
-
-
-import ast
-
-class ParentNodeVisitor(ast.NodeVisitor):
-    """Annotate nodes with parent references."""
-    def __init__(self, parent=None):
-        self.parent = parent
-
-    def generic_visit(self, node):
-        node.parent = self.parent
-        for child in ast.iter_child_nodes(node):
-            self.__class__(child).parent = node
-        super().generic_visit(node)
-
-
-def extract_functions_from_file(filepath: str) -> List[Dict]:
-    """Extract all function definitions from a Python file."""
-    try:
-        with open(filepath, 'r', encoding='utf-8', errors='replace') as f:
-            source = f.read()
-        tree = ast.parse(source, filename=str(filepath))
-
-        # Annotate with parent references
-        for node in ast.walk(tree):
-            for child in ast.iter_child_nodes(node):
-                child.parent = node
-
-        extractor = FunctionExtractor(source, str(filepath))
-        extractor.visit(tree)
-        return extractor.functions
-    except (SyntaxError, UnicodeDecodeError, OSError) as e:
-        return []
-
-
-def scan_directory(directory: str, extensions: Tuple[str, ...] = ('.py',)) -> List[Dict]:
-    """Scan directory for Python files and extract all functions."""
-    all_functions = []
-    path = Path(directory)
-
-    for filepath in path.rglob('*'):
-        if filepath.is_file() and filepath.suffix in extensions:
-            # Skip common non-source dirs
-            parts = filepath.parts
-            if any(ex in parts for ex in ('__pycache__', 'node_modules', '.git', 'venv', '.venv', 'dist', 'build')):
-                continue
-            if filepath.name.startswith('.'):
-                continue
-
-            functions = extract_functions_from_file(str(filepath))
-            all_functions.extend(functions)
-
-    return all_functions
-
-
-# ── Duplicate detection ─────────────────────────────────────────────────────
-
-def find_duplicates(functions: List[Dict], similarity_threshold: float = 0.95) -> Dict:
-    """
-    Find duplicate and near-duplicate functions.
-
-    Returns dict with:
-      - exact_duplicates: {hash: [function_info, ...]}
-      - near_duplicates: [[function_info, ...], ...]
-      - stats: total_functions, unique_exact, exact_dupe_count, near_dupe_count
-    """
-    # Phase 1: Exact duplicates by code hash
-    hash_groups: Dict[str, List[Dict]] = defaultdict(list)
-    for func in functions:
-        h = code_hash(func['body'])
-        hash_groups[h].append(func)
-
-    exact_duplicates = {h: group for h, group in hash_groups.items() if len(group) > 1}
-    exact_dupe_count = sum(len(group) - 1 for group in exact_duplicates.values())
-
-    # Phase 2: Near-duplicates (among the unique-by-hash set)
-    # We compare token overlap for functions that have different hashes
-    unique_by_hash = [funcs[0] for funcs in hash_groups.values()]
-    near_duplicate_groups = []
-
-    # Simple token-based similarity
-    def tokenize(code: str) -> set:
-        return set(re.findall(r'[a-zA-Z_][a-zA-Z0-9_]*', code.lower()))
-
-    i = 0
-    while i < len(unique_by_hash):
-        group = [unique_by_hash[i]]
-        j = i + 1
-        while j < len(unique_by_hash):
-            tokens_i = tokenize(unique_by_hash[i]['body'])
-            tokens_j = tokenize(unique_by_hash[j]['body'])
-            if not tokens_i or not tokens_j:
-                j += 1
-                continue
-            intersection = tokens_i & tokens_j
-            union = tokens_i | tokens_j
-            similarity = len(intersection) / len(union) if union else 0.0
-
-            if similarity >= similarity_threshold:
-                group.append(unique_by_hash[j])
-                unique_by_hash.pop(j)
-            else:
-                j += 1
-
-        if len(group) > 1:
-            near_duplicate_groups.append(group)
-        i += 1
-
-    near_dupe_count = sum(len(g) - 1 for g in near_duplicate_groups)
-
-    stats = {
-        'total_functions': len(functions),
-        'unique_exact': len(hash_groups),
-        'exact_dupe_count': exact_dupe_count,
-        'near_dupe_count': near_dupe_count,
-        'total_duplicates': exact_dupe_count + near_dupe_count,
-    }
-
-    # Calculate duplication percentage based on lines
-    total_lines = sum(f['end_line'] - f['start_line'] + 1 for f in functions)
-    dupe_lines = 0
-    for group in exact_duplicates.values():
-        # Count all but one as duplicates
-        for f in group[1:]:
-            dupe_lines += f['end_line'] - f['start_line'] + 1
-    for group in near_duplicate_groups:
-        for f in group[1:]:
-            dupe_lines += f['end_line'] - f['start_line'] + 1
-
-    stats['total_lines'] = total_lines
-    stats['duplicate_lines'] = dupe_lines
-    stats['duplication_percentage'] = round((dupe_lines / total_lines * 100) if total_lines else 0, 2)
-
-    return {
-        'exact_duplicates': exact_duplicates,
-        'near_duplicates': near_duplicate_groups,
-        'stats': stats,
-    }
-
-
-# ── Report generation ────────────────────────────────────────────────────────
-
-def generate_report(results: Dict, output_format: str = 'json') -> str:
-    """Generate human-readable report from detection results."""
-    stats = results['stats']
-
-    if output_format == 'json':
-        return json.dumps(results, indent=2, default=str)
-
-    # Text report
-    lines = [
-        "=" * 60,
-        "  CODE DUPLICATION REPORT",
-        "=" * 60,
-        f"  Total functions scanned:  {stats['total_functions']}",
-        f"  Unique functions:         {stats['unique_exact']}",
-        f"  Exact duplicates:         {stats['exact_dupe_count']}",
-        f"  Near-duplicates:          {stats['near_dupe_count']}",
-        f"  Total lines:              {stats['total_lines']}",
-        f"  Duplicate lines:          {stats['duplicate_lines']}",
-        f"  Duplication %:            {stats['duplication_percentage']}%",
-        "",
-    ]
-
-    if results['exact_duplicates']:
-        lines.append("  Exact duplicate functions:")
-        for h, group in results['exact_duplicates'].items():
-            first = group[0]
-            lines.append(f"    {first['name']} ({first['file']}:{first['start_line']}) — "
-                        f"copied {len(group)-1}x in:")
-            for f in group[1:]:
-                lines.append(f"      → {f['file']}:{f['start_line']}")
-        lines.append("")
-
-    if results['near_duplicates']:
-        lines.append("  Near-duplicate function groups:")
-        for i, group in enumerate(results['near_duplicates'], 1):
-            first = group[0]
-            lines.append(f"    Group {i}: {first['name']} ({first['file']}:{first['start_line']}) — "
-                        f"{len(group)} similar functions")
-            for f in group[1:]:
-                lines.append(f"      → {f['file']}:{f['start_line']}")
-        lines.append("")
-
-    lines.append("=" * 60)
-    return '\n'.join(lines)
-
-
-# ── CLI ─────────────────────────────────────────────────────────────────────
-
-def main():
-    parser = argparse.ArgumentParser(description="Code Duplication Detector")
-    parser.add_argument('--directory', default='.',
-                        help='Directory to scan (default: current directory)')
-    parser.add_argument('--output', help='Output file for JSON report')
-    parser.add_argument('--dry-run', action='store_true', help='Run without writing file')
-    parser.add_argument('--threshold', type=float, default=0.95,
-                        help='Similarity threshold for near-dupes (default: 0.95)')
-    parser.add_argument('--json', action='store_true', help='JSON output to stdout')
-    parser.add_argument('--test', action='store_true', help='Run built-in test')
-    args = parser.parse_args()
-
-    if args.test:
-        _run_test()
-        return
-
-    # Scan
-    functions = scan_directory(args.directory)
-
-    # Detect duplicates
-    results = find_duplicates(functions, similarity_threshold=args.threshold)
-    stats = results['stats']
-
-    # Output
-    if args.json:
-        print(json.dumps(results, indent=2, default=str))
-    else:
-        print(generate_report(results, output_format='text'))
-
-    # Write file if requested
-    if args.output and not args.dry_run:
-        os.makedirs(os.path.dirname(args.output) or '.', exist_ok=True)
-        with open(args.output, 'w') as f:
-            json.dump(results, f, indent=2, default=str)
-        print(f"\nReport written to: {args.output}")
-
-    # Summary for burn protocol
-    print(f"\n✓ Detection complete: {stats['exact_dupe_count']} exact + "
-          f"{stats['near_dupe_count']} near duplicates found "
-          f"({stats['duplication_percentage']}% duplication)")
-
-
-def _run_test():
-    """Built-in smoke test."""
-    import tempfile
-    import os
-
-    with tempfile.TemporaryDirectory() as tmpdir:
-        # Create test files with duplicate code
-        f1 = Path(tmpdir) / 'mod1.py'
-        f1.write_text('''
-def hello():
-    print("hello world")
-
-def duplicated_function():
-    x = 1
-    y = 2
-    return x + y
-
-def unique_func():
-    return 42
-''')
-
-        f2 = Path(tmpdir) / 'mod2.py'
-        f2.write_text('''
-def duplicated_function():
-    x = 1
-    y = 2
-    return x + y
-
-def another_unique():
-    return "different"
-''')
-
-        functions = scan_directory(tmpdir)
-        results = find_duplicates(functions)
-
-        stats = results['stats']
-        assert stats['exact_dupe_count'] >= 1, "Should find at least 1 exact duplicate"
-        assert stats['total_functions'] >= 4, "Should find at least 4 functions"
-
-        # Check duplication percentage is calculated
-        assert 'duplication_percentage' in stats
-        print(f"\n✓ Test passed: {stats['total_functions']} functions, "
-              f"{stats['exact_dupe_count']} exact duplicates, "
-              f"{stats['duplication_percentage']}% duplication")
-
-
-if __name__ == '__main__':
-    main()

scripts/pr_complexity_scorer.py

@@ -1,351 +0,0 @@
-#!/usr/bin/env python3
-"""
-PR Complexity Scorer - Estimate review effort for PRs.
-"""
-
-import argparse
-import json
-import os
-import re
-import sys
-from dataclasses import dataclass, asdict
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Any, Dict, List, Optional
-import urllib.request
-import urllib.error
-
-GITEA_BASE = "https://forge.alexanderwhitestone.com/api/v1"
-
-DEPENDENCY_FILES = {
-    "requirements.txt", "pyproject.toml", "setup.py", "setup.cfg",
-    "Pipfile", "poetry.lock", "package.json", "yarn.lock", "Gemfile",
-    "go.mod", "Cargo.toml", "pom.xml", "build.gradle"
-}
-
-TEST_PATTERNS = [
-    r"tests?/.*\.py$", r".*_test\.py$", r"test_.*\.py$",
-    r"spec/.*\.rb$", r".*_spec\.rb$",
-    r"__tests__/", r".*\.test\.(js|ts|jsx|tsx)$"
-]
-
-WEIGHT_FILES = 0.25
-WEIGHT_LINES = 0.25
-WEIGHT_DEPS = 0.30
-WEIGHT_TEST_COV = 0.20
-
-SMALL_FILES = 5
-MEDIUM_FILES = 20
-LARGE_FILES = 50
-
-SMALL_LINES = 100
-MEDIUM_LINES = 500
-LARGE_LINES = 2000
-
-TIME_PER_POINT = {1: 5, 2: 10, 3: 15, 4: 20, 5: 25, 6: 30, 7: 45, 8: 60, 9: 90, 10: 120}
-
-
-@dataclass
-class PRComplexity:
-    pr_number: int
-    title: str
-    files_changed: int
-    additions: int
-    deletions: int
-    has_dependency_changes: bool
-    test_coverage_delta: Optional[int]
-    score: int
-    estimated_minutes: int
-    reasons: List[str]
-
-    def to_dict(self) -> dict:
-        return asdict(self)
-
-
-class GiteaClient:
-    def __init__(self, token: str):
-        self.token = token
-        self.base_url = GITEA_BASE.rstrip("/")
-
-    def _request(self, path: str, params: Dict = None) -> Any:
-        url = f"{self.base_url}{path}"
-        if params:
-            qs = "&".join(f"{k}={v}" for k, v in params.items() if v is not None)
-            url += f"?{qs}"
-
-        req = urllib.request.Request(url)
-        req.add_header("Authorization", f"token {self.token}")
-        req.add_header("Content-Type", "application/json")
-
-        try:
-            with urllib.request.urlopen(req, timeout=30) as resp:
-                return json.loads(resp.read().decode())
-        except urllib.error.HTTPError as e:
-            print(f"API error {e.code}: {e.read().decode()[:200]}", file=sys.stderr)
-            return None
-        except urllib.error.URLError as e:
-            print(f"Network error: {e}", file=sys.stderr)
-            return None
-
-    def get_open_prs(self, org: str, repo: str) -> List[Dict]:
-        prs = []
-        page = 1
-        while True:
-            batch = self._request(f"/repos/{org}/{repo}/pulls", {"limit": 50, "page": page, "state": "open"})
-            if not batch:
-                break
-            prs.extend(batch)
-            if len(batch) < 50:
-                break
-            page += 1
-        return prs
-
-    def get_pr_files(self, org: str, repo: str, pr_number: int) -> List[Dict]:
-        files = []
-        page = 1
-        while True:
-            batch = self._request(
-                f"/repos/{org}/{repo}/pulls/{pr_number}/files",
-                {"limit": 100, "page": page}
-            )
-            if not batch:
-                break
-            files.extend(batch)
-            if len(batch) < 100:
-                break
-            page += 1
-        return files
-
-    def post_comment(self, org: str, repo: str, pr_number: int, body: str) -> bool:
-        data = json.dumps({"body": body}).encode("utf-8")
-        req = urllib.request.Request(
-            f"{self.base_url}/repos/{org}/{repo}/issues/{pr_number}/comments",
-            data=data,
-            method="POST",
-            headers={"Authorization": f"token {self.token}", "Content-Type": "application/json"}
-        )
-        try:
-            with urllib.request.urlopen(req, timeout=30) as resp:
-                return resp.status in (200, 201)
-        except urllib.error.HTTPError:
-            return False
-
-
-def is_dependency_file(filename: str) -> bool:
-    return any(filename.endswith(dep) for dep in DEPENDENCY_FILES)
-
-
-def is_test_file(filename: str) -> bool:
-    return any(re.search(pattern, filename) for pattern in TEST_PATTERNS)
-
-
-def score_pr(
-    files_changed: int,
-    additions: int,
-    deletions: int,
-    has_dependency_changes: bool,
-    test_coverage_delta: Optional[int] = None
-) -> tuple[int, int, List[str]]:
-    score = 1.0
-    reasons = []
-
-    # Files changed
-    if files_changed <= SMALL_FILES:
-        fscore = 1.0
-        reasons.append("small number of files changed")
-    elif files_changed <= MEDIUM_FILES:
-        fscore = 2.0
-        reasons.append("moderate number of files changed")
-    elif files_changed <= LARGE_FILES:
-        fscore = 2.5
-        reasons.append("large number of files changed")
-    else:
-        fscore = 3.0
-        reasons.append("very large PR spanning many files")
-
-    # Lines changed
-    total_lines = additions + deletions
-    if total_lines <= SMALL_LINES:
-        lscore = 1.0
-        reasons.append("small change size")
-    elif total_lines <= MEDIUM_LINES:
-        lscore = 2.0
-        reasons.append("moderate change size")
-    elif total_lines <= LARGE_LINES:
-        lscore = 3.0
-        reasons.append("large change size")
-    else:
-        lscore = 4.0
-        reasons.append("very large change")
-
-    # Dependency changes
-    if has_dependency_changes:
-        dscore = 2.5
-        reasons.append("dependency changes (architectural impact)")
-    else:
-        dscore = 0.0
-
-    # Test coverage delta
-    tscore = 0.0
-    if test_coverage_delta is not None:
-        if test_coverage_delta > 0:
-            reasons.append(f"test additions (+{test_coverage_delta} test files)")
-            tscore = -min(2.0, test_coverage_delta / 2.0)
-        elif test_coverage_delta < 0:
-            reasons.append(f"test removals ({abs(test_coverage_delta)} test files)")
-            tscore = min(2.0, abs(test_coverage_delta) * 0.5)
-    else:
-        reasons.append("test coverage change not assessed")
-
-    # Weighted sum, scaled by 3 to use full 1-10 range
-    bonus = (fscore * WEIGHT_FILES) + (lscore * WEIGHT_LINES) + (dscore * WEIGHT_DEPS) + (tscore * WEIGHT_TEST_COV)
-    scaled_bonus = bonus * 3.0
-    score = 1.0 + scaled_bonus
-
-    final_score = max(1, min(10, int(round(score))))
-    est_minutes = TIME_PER_POINT.get(final_score, 30)
-
-    return final_score, est_minutes, reasons
-
-
-def analyze_pr(client: GiteaClient, org: str, repo: str, pr_data: Dict) -> PRComplexity:
-    pr_num = pr_data["number"]
-    title = pr_data.get("title", "")
-    files = client.get_pr_files(org, repo, pr_num)
-
-    additions = sum(f.get("additions", 0) for f in files)
-    deletions = sum(f.get("deletions", 0) for f in files)
-    filenames = [f.get("filename", "") for f in files]
-
-    has_deps = any(is_dependency_file(f) for f in filenames)
-
-    test_added = sum(1 for f in files if f.get("status") == "added" and is_test_file(f.get("filename", "")))
-    test_removed = sum(1 for f in files if f.get("status") == "removed" and is_test_file(f.get("filename", "")))
-    test_delta = test_added - test_removed if (test_added or test_removed) else None
-
-    score, est_min, reasons = score_pr(
-        files_changed=len(files),
-        additions=additions,
-        deletions=deletions,
-        has_dependency_changes=has_deps,
-        test_coverage_delta=test_delta
-    )
-
-    return PRComplexity(
-        pr_number=pr_num,
-        title=title,
-        files_changed=len(files),
-        additions=additions,
-        deletions=deletions,
-        has_dependency_changes=has_deps,
-        test_coverage_delta=test_delta,
-        score=score,
-        estimated_minutes=est_min,
-        reasons=reasons
-    )
-
-
-def build_comment(complexity: PRComplexity) -> str:
-    change_desc = f"{complexity.files_changed} files, +{complexity.additions}/-{complexity.deletions} lines"
-    deps_note = "\n- :warning: Dependency changes detected — architectural review recommended" if complexity.has_dependency_changes else ""
-    test_note = ""
-    if complexity.test_coverage_delta is not None:
-        if complexity.test_coverage_delta > 0:
-            test_note = f"\n- :+1: {complexity.test_coverage_delta} test file(s) added"
-        elif complexity.test_coverage_delta < 0:
-            test_note = f"\n- :warning: {abs(complexity.test_coverage_delta)} test file(s) removed"
-
-    comment = f"## 📊 PR Complexity Analysis\n\n"
-    comment += f"**PR #{complexity.pr_number}: {complexity.title}**\n\n"
-    comment += f"| Metric | Value |\n|--------|-------|\n"
-    comment += f"| Changes | {change_desc} |\n"
-    comment += f"| Complexity Score | **{complexity.score}/10** |\n"
-    comment += f"| Estimated Review Time | ~{complexity.estimated_minutes} minutes |\n\n"
-    comment += f"### Scoring rationale:"
-    for r in complexity.reasons:
-        comment += f"\n- {r}"
-    if deps_note:
-        comment += deps_note
-    if test_note:
-        comment += test_note
-    comment += f"\n\n---\n"
-    comment += f"*Generated by PR Complexity Scorer — [issue #135](https://forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence/issues/135)*"
-    return comment
-
-
-def main():
-    parser = argparse.ArgumentParser(description="PR Complexity Scorer")
-    parser.add_argument("--org", default="Timmy_Foundation")
-    parser.add_argument("--repo", default="compounding-intelligence")
-    parser.add_argument("--token", default=os.environ.get("GITEA_TOKEN") or os.path.expanduser("~/.config/gitea/token"))
-    parser.add_argument("--dry-run", action="store_true")
-    parser.add_argument("--apply", action="store_true")
-    parser.add_argument("--output", default="metrics/pr_complexity.json")
-    args = parser.parse_args()
-
-    token_path = args.token
-    if os.path.exists(token_path):
-        with open(token_path) as f:
-            token = f.read().strip()
-    else:
-        token = args.token
-
-    if not token:
-        print("ERROR: No Gitea token provided", file=sys.stderr)
-        sys.exit(1)
-
-    client = GiteaClient(token)
-
-    print(f"Fetching open PRs for {args.org}/{args.repo}...")
-    prs = client.get_open_prs(args.org, args.repo)
-    if not prs:
-        print("No open PRs found.")
-        sys.exit(0)
-
-    print(f"Found {len(prs)} open PR(s). Analyzing...")
-
-    results = []
-    Path(args.output).parent.mkdir(parents=True, exist_ok=True)
-
-    for pr in prs:
-        pr_num = pr["number"]
-        title = pr.get("title", "")
-        print(f"  Analyzing PR #{pr_num}: {title[:60]}")
-
-        try:
-            complexity = analyze_pr(client, args.org, args.repo, pr)
-            results.append(complexity.to_dict())
-
-            comment = build_comment(complexity)
-
-            if args.dry_run:
-                print(f"    → Score: {complexity.score}/10, Est: {complexity.estimated_minutes}min [DRY-RUN]")
-            elif args.apply:
-                success = client.post_comment(args.org, args.repo, pr_num, comment)
-                status = "[commented]" if success else "[FAILED]"
-                print(f"    → Score: {complexity.score}/10, Est: {complexity.estimated_minutes}min {status}")
-            else:
-                print(f"    → Score: {complexity.score}/10, Est: {complexity.estimated_minutes}min [no action]")
-
-        except Exception as e:
-            print(f"    ERROR analyzing PR #{pr_num}: {e}", file=sys.stderr)
-
-    with open(args.output, "w") as f:
-        json.dump({
-            "org": args.org,
-            "repo": args.repo,
-            "timestamp": datetime.now(timezone.utc).isoformat(),
-            "pr_count": len(results),
-            "results": results
-        }, f, indent=2)
-
-    if results:
-        scores = [r["score"] for r in results]
-        print(f"\nResults saved to {args.output}")
-        print(f"Summary: {len(results)} PRs, scores range {min(scores):.0f}-{max(scores):.0f}")
-    else:
-        print("\nNo results to save.")
-
-
-if __name__ == "__main__":
-    main()

scripts/progress_tracker.py

@@ -0,0 +1,477 @@
+#!/usr/bin/env python3
+"""
+Progress Tracker — Pipeline 10.8
+Track improvement metrics over time. Are we getting better?
+
+Metrics tracked:
+ 1. Test coverage  — % of Python functions with associated tests (test:source file ratio + line coverage if available)
+ 2. Doc coverage   — % of Python callables with docstrings (AST-based)
+ 3. Issue close rate — closed / (opened + closed) per week (Gitea API)
+ 4. Dep freshness  — % of requirements pinned vs outdated (pip list --outdated)
+
+Output:
+ - metrics/snapshots/YYYY-MM-DD.json  — one snapshot per run
+ - metrics/TRENDS.md                  — cumulative markdown table
+ - stdout summary
+
+Usage:
+    python3 scripts/progress_tracker.py
+    python3 scripts/progress_tracker.py --json
+    python3 scripts/progress_tracker.py --output metrics/TRENDS.md
+
+Weekly cron:
+    0 9 * * 1 cd /path/to/compounding-intelligence && python3 scripts/progress_tracker.py
+"""
+
+import argparse
+import json
+import os
+import re
+import subprocess
+import sys
+from collections import defaultdict
+from datetime import datetime, timezone, timedelta
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
+
+# ── Configuration ──────────────────────────────────────────────────────────
+
+SCRIPT_DIR = Path(__file__).resolve().parent
+REPO_ROOT = SCRIPT_DIR.parent
+METRICS_DIR = REPO_ROOT / "metrics"
+SNAPSHOTS_DIR = METRICS_DIR / "snapshots"
+TOKEN_PATH = Path.home() / ".config" / "gitea" / "token"
+GITEA_API_BASE = "https://forge.alexanderwhitestone.com/api/v1"
+ORG = "Timmy_Foundation"
+
+# Ensure paths exist
+SNAPSHOTS_DIR.mkdir(parents=True, exist_ok=True)
+
+
+# ── Helpers ─────────────────────────────────────────────────────────────────
+
+def run_cmd(cmd: List[str], cwd: Path = REPO_ROOT) -> str:
+    """Run a shell command and return stdout (stderr merged)."""
+    result = subprocess.run(
+        cmd, capture_output=True, text=True, cwd=cwd, timeout=30
+    )
+    if result.returncode != 0:
+        return ""
+    return result.stdout.strip()
+
+
+def slugify_date(dt: datetime) -> str:
+    return dt.strftime("%Y-%m-%d")
+
+
+def snapshot_path(dt: datetime) -> Path:
+    return SNAPSHOTS_DIR / f"{slugify_date(dt)}.json"
+
+
+def load_snapshots() -> List[Dict[str, Any]]:
+    """Load all existing snapshots sorted by date."""
+    snapshots = []
+    for f in sorted(SNAPSHOTS_DIR.glob("*.json")):
+        try:
+            with open(f) as fp:
+                snapshots.append(json.load(fp))
+        except Exception:
+            continue
+    return snapshots
+
+
+# ── Metric 1: Test Coverage ─────────────────────────────────────────────────
+
+def collect_test_coverage() -> Dict[str, Any]:
+    """
+    Compute test coverage metrics.
+    Counts test_*.py and *_test.py files vs non-test .py source files.
+    Also attempts to read .coverage if present.
+    """
+    all_py = list(REPO_ROOT.rglob("*.py"))
+    
+    source_files = []
+    test_files = []
+    
+    for p in all_py:
+        try:
+            rel_parts = p.relative_to(REPO_ROOT).parts
+        except ValueError:
+            continue
+        
+        # Skip hidden/cache/temp dirs (check only relative parts)
+        if any(part.startswith('.') or part.startswith('__') for part in rel_parts):
+            continue
+        if any(part in ('node_modules', 'venv', '.venv', 'env', '.pytest_cache') for part in rel_parts):
+            continue
+        
+        if p.name.startswith("test_") or p.name.endswith("_test.py"):
+            test_files.append(p)
+        else:
+            source_files.append(p)
+    
+    # Try to get line coverage from .coverage
+    coverage_percent = None
+    coverage_tool = None
+    coverage_file = REPO_ROOT / ".coverage"
+    if coverage_file.exists():
+        try:
+            import coverage  # type: ignore
+            # Use coverage API if available
+            cov = coverage.Coverage(data_file=str(coverage_file))
+            cov.load()
+            total = cov.report()
+            coverage_percent = total if isinstance(total, float) else None
+            coverage_tool = "coverage"
+        except Exception:
+            # Fallback: parse `coverage report` output
+            out = run_cmd(["coverage", "report", "--skip-empty"])
+            if out:
+                for line in out.splitlines():
+                    if "TOTAL" in line:
+                        parts = line.split()
+                        if len(parts) >= 2:
+                            try:
+                                coverage_percent = float(parts[-1].rstrip('%'))
+                                coverage_tool = "coverage"
+                                break
+                            except ValueError:
+                                pass
+    
+    return {
+        "test_files": len(test_files),
+        "source_files": len(source_files),
+        "test_to_source_ratio": round(len(test_files) / len(source_files), 4) if source_files else 0.0,
+        "coverage_tool": coverage_tool,
+        "coverage_percent": coverage_percent,
+    }
+
+
+# ── Metric 2: Doc Coverage ──────────────────────────────────────────────────
+
+def collect_doc_coverage() -> Dict[str, Any]:
+    """
+    Check AST of Python files for docstrings.
+    Returns: callables_total, callables_with_doc, doc_coverage_percent
+    """
+    import ast
+    
+    all_py = list(REPO_ROOT.rglob("*.py"))
+    
+    source_files = []
+    test_files = []
+    
+    for p in all_py:
+        try:
+            rel_parts = p.relative_to(REPO_ROOT).parts
+        except ValueError:
+            continue
+        
+        if any(part.startswith('.') or part.startswith('__') for part in rel_parts):
+            continue
+        if any(part in ('node_modules', 'venv', '.venv', 'env', '.pytest_cache') for part in rel_parts):
+            continue
+        
+        if p.name.startswith("test_") or p.name.endswith("_test.py"):
+            test_files.append(p)
+        else:
+            source_files.append(p)
+    
+    total_callables = 0
+    with_doc = 0
+    
+    for p in source_files + test_files:
+        try:
+            with open(p) as f:
+                tree = ast.parse(f.read(), filename=str(p))
+            for node in ast.walk(tree):
+                if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef, ast.ClassDef)):
+                    total_callables += 1
+                    doc = ast.get_docstring(node)
+                    if doc and doc.strip():
+                        with_doc += 1
+        except Exception:
+            continue
+    
+    return {
+        "callables_total": total_callables,
+        "callables_with_doc": with_doc,
+        "doc_coverage_percent": round((with_doc / total_callables * 100) if total_callables else 0.0, 2),
+    }
+
+
+# ── Metric 3: Issue Close Rate ──────────────────────────────────────────────
+
+def collect_issue_metrics() -> Dict[str, Any]:
+    """
+    Use Gitea API to get issue open/close stats for the last 7 days.
+    Returns counts and close rate.
+    """
+    token = ""
+    if TOKEN_PATH.exists():
+        token = TOKEN_PATH.read_text().strip()
+    
+    if not token:
+        return {
+            "opened_last_7d": None,
+            "closed_last_7d": None,
+            "close_rate": None,
+            "total_open": None,
+            "note": "Gitea token not available"
+        }
+    
+    try:
+        from urllib.request import Request, urlopen
+        from urllib.error import HTTPError, URLError
+    except ImportError:
+        return {"error": "urllib not available"}
+    
+    now = datetime.now(timezone.utc)
+    week_ago = now - timedelta(days=7)
+    since = week_ago.strftime("%Y-%m-%d")
+    
+    headers = {"Authorization": f"token {token}"}
+    base_url = f"{GITEA_API_BASE}/repos/{ORG}/compounding-intelligence/issues"
+    
+    try:
+        # Get issues from last 7 days
+        url = f"{base_url}?state=all&since={since}&per_page=100"
+        req = Request(url, headers=headers)
+        with urlopen(req, timeout=15) as resp:
+            issues = json.loads(resp.read())
+        
+        opened = 0
+        closed = 0
+        for issue in issues:
+            created = datetime.fromisoformat(issue["created_at"].replace("Z", "+00:00"))
+            if created >= week_ago:
+                opened += 1
+            if issue.get("state") == "closed":
+                closed_at_str = issue.get("closed_at")
+                if closed_at_str:
+                    closed_at = datetime.fromisoformat(closed_at_str.replace("Z", "+00:00"))
+                    if closed_at >= week_ago:
+                        closed += 1
+        
+        # Total open issues
+        req2 = Request(f"{base_url}?state=open&per_page=1", headers=headers)
+        with urlopen(req2, timeout=15) as resp:
+            total_open = int(resp.headers.get("X-Total-Count", "0"))
+        
+        total = opened + closed
+        close_rate = closed / total if total > 0 else 0.0
+        
+        return {
+            "opened_last_7d": opened,
+            "closed_last_7d": closed,
+            "close_rate": round(close_rate, 4),
+            "total_open": total_open,
+        }
+    except Exception as e:
+        return {
+            "opened_last_7d": None,
+            "closed_last_7d": None,
+            "close_rate": None,
+            "total_open": None,
+            "error": str(e)[:100],
+            "note": "Gitea API unavailable"
+        }
+
+
+# ── Metric 4: Dependency Freshness ─────────────────────────────────────────
+
+def collect_dep_freshness() -> Dict[str, Any]:
+    """
+    Check requirements.txt for outdated dependencies using pip list --outdated.
+    Returns freshness percentage and outdated list.
+    """
+    req_file = REPO_ROOT / "requirements.txt"
+    if not req_file.exists():
+        return {
+            "total_deps": 0,
+            "outdated_deps": 0,
+            "freshness_percent": 100.0,
+            "outdated_list": [],
+            "note": "requirements.txt not found"
+        }
+    
+    # Parse requirements (very simple: take name before comparison op)
+    reqs = []
+    with open(req_file) as f:
+        for line in f:
+            line = line.strip()
+            if not line or line.startswith("#"):
+                continue
+            m = re.match(r"^([a-zA-Z0-9_.-]+)", line)
+            if m:
+                reqs.append(m.group(1))
+    
+    if not reqs:
+        return {"total_deps": 0, "outdated_deps": 0, "freshness_percent": 100.0, "outdated_list": []}
+    
+    # Query pip for outdated packages (may fail if pip not available)
+    outdated_names = set()
+    try:
+        out = run_cmd(["pip", "list", "--outdated", "--format=json"])
+        if out:
+            data = json.loads(out)
+            outdated_names = {item["name"].lower() for item in data}
+    except Exception:
+        pass
+    
+    outdated = [p for p in reqs if p.lower() in outdated_names]
+    total = len(reqs)
+    outdated_count = len(outdated)
+    freshness = round(((total - outdated_count) / total * 100) if total else 100.0, 1)
+    
+    return {
+        "total_deps": total,
+        "outdated_deps": outdated_count,
+        "freshness_percent": freshness,
+        "outdated_list": outdated,
+    }
+
+
+# ── Snapshot & Trends ───────────────────────────────────────────────────────
+
+def take_snapshot() -> Dict[str, Any]:
+    """Collect all metrics and return a snapshot dict."""
+    now = datetime.now(timezone.utc)
+    test_cov = collect_test_coverage()
+    doc_cov = collect_doc_coverage()
+    issues = collect_issue_metrics()
+    deps = collect_dep_freshness()
+    
+    return {
+        "timestamp": now.isoformat(),
+        "date": slugify_date(now),
+        "metrics": {
+            "test_coverage": test_cov,
+            "doc_coverage": doc_cov,
+            "issues": issues,
+            "dependencies": deps,
+        }
+    }
+
+
+def save_snapshot(snapshot: Dict[str, Any]) -> Path:
+    path = snapshot_path(datetime.fromisoformat(snapshot["timestamp"]))
+    with open(path, "w") as f:
+        json.dump(snapshot, f, indent=2)
+    return path
+
+
+def generate_trends(snapshots: List[Dict[str, Any]], output_path: Optional[Path] = None) -> str:
+    """Generate markdown trends table; optionally write to file."""
+    if not snapshots:
+        msg = "# Progress Tracker — Trends\n\nNo snapshots yet. Run `progress_tracker.py` to create the first snapshot."
+        if output_path:
+            output_path.parent.mkdir(parents=True, exist_ok=True)
+            output_path.write_text(msg)
+        return msg
+    
+    lines = [
+        "# Progress Tracker — Trends",
+        f"\nLast updated: {datetime.now(timezone.utc).strftime('%Y-%m-%d %H:%M UTC')}",
+        f"\nSnapshots: {len(snapshots)}\n",
+        "| Date | Test Files → Source | Doc Coverage | Issues Closed/Opened (7d) | Dep Freshness |",
+        "|------|---------------------|--------------|---------------------------|---------------|",
+    ]
+    
+    for snap in reversed(snapshots):  # chronological
+        date = snap["date"]
+        m = snap["metrics"]
+        tc = m["test_coverage"]
+        test_str = f"{tc['test_files']}/{tc['source_files']} ({tc['test_to_source_ratio']:.2f})"
+        doc_str = f"{m['doc_coverage']['doc_coverage_percent']:.1f}%"
+        issues_str = f"{m['issues'].get('closed_last_7d','-')}/{m['issues'].get('opened_last_7d','-')}"
+        dep_str = f"{m['dependencies'].get('freshness_percent','?')}%"
+        lines.append(f"| {date} | {test_str} | {doc_str} | {issues_str} | {dep_str} |")
+    
+    # Current snapshot summary
+    cur = snapshots[-1]
+    cm = cur["metrics"]
+    lines.append(f"\n## Current Snapshot ({cur['date']})\n")
+    
+    tc = cm["test_coverage"]
+    cov_line = f"- Test coverage: {tc['coverage_percent']:.1f}% (via {tc['coverage_tool']})\n" if tc["coverage_percent"] else "- Test coverage: (pytest-cov not configured)\n"
+    lines.append(cov_line)
+    lines.append(f"- Doc coverage: {cm['doc_coverage']['doc_coverage_percent']:.1f}%")
+    
+    im = cm["issues"]
+    if im.get("close_rate") is not None:
+        lines.append(f"- Issue close rate (7d): {im['close_rate']*100:.1f}% ({im['closed_last_7d']} closed, {im['opened_last_7d']} opened)")
+    else:
+        lines.append(f"- Issue metrics: {im.get('note','unavailable')}")
+    
+    dd = cm["dependencies"]
+    lines.append(f"- Dep freshness: {dd.get('freshness_percent','?')}% outdated ({dd.get('outdated_deps',0)}/{dd.get('total_deps',0)} deps)")
+    if dd.get('outdated_list'):
+        lines.append(f"  Outdated: {', '.join(dd['outdated_list'][:5])}")
+    
+    content = "\n".join(lines) + "\n"
+    
+    if output_path:
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+        output_path.write_text(content)
+    
+    return content
+
+
+# ── Main ─────────────────────────────────────────────────────────────────────
+
+def main() -> int:
+    parser = argparse.ArgumentParser(description="Progress Tracker — 10.8")
+    parser.add_argument("--json", action="store_true", help="Emit snapshot as JSON only")
+    parser.add_argument("--output", type=Path, default=METRICS_DIR / "TRENDS.md",
+                        help="Write trends markdown to this file")
+    args = parser.parse_args()
+    
+    snapshot = take_snapshot()
+    all_snapshots = load_snapshots()
+    path_written = save_snapshot(snapshot)
+    
+    if args.json:
+        print(json.dumps(snapshot, indent=2))
+        return 0
+    
+    trends = generate_trends(all_snapshots + [snapshot], output_path=args.output)
+    
+    # Print current snapshot summary
+    print(f"Snapshot saved: {path_written}\n")
+    print(f"Progress Tracker — {snapshot['date']}")
+    print("=" * 50)
+    
+    m = snapshot["metrics"]
+    tc = m["test_coverage"]
+    print(f"Test files: {tc['test_files']}  |  Source files: {tc['source_files']}  |  Ratio: {tc['test_to_source_ratio']:.3f}")
+    if tc["coverage_percent"] is not None:
+        print(f"Line coverage: {tc['coverage_percent']:.1f}%  (via {tc['coverage_tool']})")
+    else:
+        print("Line coverage: (not available — run `pytest --cov`)")
+    
+    print()
+    dc = m["doc_coverage"]
+    print(f"Callables with docstrings: {dc['callables_with_doc']}/{dc['callables_total']}  ({dc['doc_coverage_percent']:.1f}%)")
+    
+    print()
+    im = m["issues"]
+    if im.get("close_rate") is not None:
+        print(f"Issues (7d): {im['closed_last_7d']} closed / {im['opened_last_7d']} opened  → close rate: {im['close_rate']*100:.1f}%")
+        print(f"Total open: {im['total_open']}")
+    else:
+        print(f"Issues: {im.get('note','unavailable')}")
+    
+    print()
+    dd = m["dependencies"]
+    print(f"Dependencies: {dd.get('total_deps',0)} total, {dd.get('outdated_deps',0)} outdated")
+    if dd.get('outdated_list'):
+        shown = dd['outdated_list'][:5]
+        print(f"Outdated: {', '.join(shown)}" + ("..." if len(dd['outdated_list']) > 5 else ""))
+    
+    print(f"\nTrends written to: {args.output}")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

scripts/test_code_duplication_detector.py

@@ -1,168 +0,0 @@
-#!/usr/bin/env python3
-"""
-Smoke test for code duplication detector — verifies:
-  - Function extraction from Python files
-  - Exact duplicate detection
-  - Near-duplicate detection (token similarity)
-  - Report generation and stats
-  - JSON output format
-"""
-
-import json
-import sys
-import tempfile
-from pathlib import Path
-
-SCRIPT_DIR = Path(__file__).parent.absolute()
-sys.path.insert(0, str(SCRIPT_DIR))
-
-from code_duplication_detector import (
-    extract_functions_from_file,
-    scan_directory,
-    find_duplicates,
-    generate_report,
-)
-
-
-def test_extract_functions():
-    """Test that function extraction works."""
-    with tempfile.TemporaryDirectory() as tmpdir:
-        test_file = Path(tmpdir) / 'sample.py'
-        test_file.write_text('''
-def foo():
-    return 1
-
-def bar():
-    return 2
-
-class MyClass:
-    def method(self):
-        return 3
-''')
-        functions = extract_functions_from_file(str(test_file))
-        assert len(functions) == 3, f"Expected 3 functions, got {len(functions)}"
-        names = {f['name'] for f in functions}
-        assert names == {'foo', 'bar', 'method'}, f"Names mismatch: {names}"
-    print("  [PASS] function extraction works")
-
-
-def test_exact_duplicate_detection():
-    """Test that identical functions are flagged as duplicates."""
-    with tempfile.TemporaryDirectory() as tmpdir:
-        # Create two files with the same function
-        f1 = Path(tmpdir) / 'a.py'
-        f1.write_text('''
-def duplicated():
-    x = 1
-    y = 2
-    return x + y
-''')
-        f2 = Path(tmpdir) / 'b.py'
-        f2.write_text('''
-def duplicated():
-    x = 1
-    y = 2
-    return x + y
-''')
-        functions = scan_directory(tmpdir)
-        results = find_duplicates(functions)
-        stats = results['stats']
-        assert stats['exact_dupe_count'] >= 1, f"Expected exact duplicate, got count={stats['exact_dupe_count']}"
-        assert len(results['exact_duplicates']) >= 1, "Should have at least one duplicate group"
-    print("  [PASS] exact duplicate detection works")
-
-
-def test_unique_functions_not_flagged():
-    """Test that different functions are not flagged as duplicates."""
-    with tempfile.TemporaryDirectory() as tmpdir:
-        f1 = Path(tmpdir) / 'a.py'
-        f1.write_text('def func_a(): return 1')
-        f2 = Path(tmpdir) / 'b.py'
-        f2.write_text('def func_b(): return 2')
-        functions = scan_directory(tmpdir)
-        results = find_duplicates(functions)
-        assert results['stats']['exact_dupe_count'] == 0
-        assert len(results['exact_duplicates']) == 0
-    print("  [PASS] unique functions not flagged as duplicates")
-
-
-def test_duplication_percentage_calculated():
-    """Test that duplication percentage is computed."""
-    with tempfile.TemporaryDirectory() as tmpdir:
-        # Create file with mostly duplicated content
-        f1 = Path(tmpdir) / 'a.py'
-        f1.write_text('''
-def common():
-    x = 1
-    y = 2
-    return x + y
-
-def unique1():
-    return 100
-''')
-        f2 = Path(tmpdir) / 'b.py'
-        f2.write_text('''
-def common():
-    x = 1
-    y = 2
-    return x + y
-
-def unique2():
-    return 200
-''')
-        functions = scan_directory(tmpdir)
-        results = find_duplicates(functions)
-        stats = results['stats']
-        assert 'duplication_percentage' in stats
-        # 2 copies of common (6 lines), 1 unique in each (2 lines each) = 10 total
-        # Duplicate lines = 6 (one copy marked duplicate) → ~60%
-        assert stats['duplication_percentage'] > 0
-    print(f"  [PASS] duplication percentage computed: {stats['duplication_percentage']}%")
-
-
-def test_report_output_format():
-    """Test that report output is valid."""
-    with tempfile.TemporaryDirectory() as tmpdir:
-        f1 = Path(tmpdir) / 'a.py'
-        f1.write_text('def dup(): return 1')
-        f2 = Path(tmpdir) / 'b.py'
-        f2.write_text('def dup(): return 1')
-        functions = scan_directory(tmpdir)
-        results = find_duplicates(functions)
-
-        # Text report
-        text = generate_report(results, output_format='text')
-        assert 'CODE DUPLICATION REPORT' in text
-        assert 'Total functions' in text
-        print("  [PASS] text report format valid")
-
-        # JSON report
-        json_out = generate_report(results, output_format='json')
-        data = json.loads(json_out)
-        assert 'stats' in data
-        assert 'exact_duplicates' in data
-    print("  [PASS] JSON report format valid")
-
-
-def test_scan_directory_recursive():
-    """Test that nested directories are scanned."""
-    with tempfile.TemporaryDirectory() as tmpdir:
-        subdir = Path(tmpdir) / 'sub'
-        subdir.mkdir()
-        (subdir / 'nested.py').write_text('def nested(): pass')
-        (Path(tmpdir) / 'root.py').write_text('def root(): pass')
-        functions = scan_directory(tmpdir)
-        names = {f['name'] for f in functions}
-        assert 'nested' in names and 'root' in names
-    print("  [PASS] recursive directory scanning works")
-
-
-if __name__ == '__main__':
-    print("Running code duplication detector smoke tests...")
-    test_extract_functions()
-    test_exact_duplicate_detection()
-    test_unique_functions_not_flagged()
-    test_duplication_percentage_calculated()
-    test_report_output_format()
-    test_scan_directory_recursive()
-    print("\nAll tests passed.")

scripts/test_pr_complexity_scorer.py

@@ -1,170 +0,0 @@
-#!/usr/bin/env python3
-"""
-Tests for PR Complexity Scorer — unit tests for the scoring logic.
-"""
-
-import sys
-from pathlib import Path
-
-sys.path.insert(0, str(Path(__file__).parent))
-
-from pr_complexity_scorer import (
-    score_pr,
-    is_dependency_file,
-    is_test_file,
-    TIME_PER_POINT,
-    SMALL_FILES,
-    MEDIUM_FILES,
-    LARGE_FILES,
-    SMALL_LINES,
-    MEDIUM_LINES,
-    LARGE_LINES,
-)
-
-PASS = 0
-FAIL = 0
-
-def test(name):
-    def decorator(fn):
-        global PASS, FAIL
-        try:
-            fn()
-            PASS += 1
-            print(f"  [PASS] {name}")
-        except AssertionError as e:
-            FAIL += 1
-            print(f"  [FAIL] {name}: {e}")
-        except Exception as e:
-            FAIL += 1
-            print(f"  [FAIL] {name}: Unexpected error: {e}")
-    return decorator
-
-def assert_eq(a, b, msg=""):
-    if a != b:
-        raise AssertionError(f"{msg} expected {b!r}, got {a!r}")
-
-def assert_true(v, msg=""):
-    if not v:
-        raise AssertionError(msg or "Expected True")
-
-def assert_false(v, msg=""):
-    if v:
-        raise AssertionError(msg or "Expected False")
-
-
-print("=== PR Complexity Scorer Tests ===\n")
-
-print("-- File Classification --")
-
-@test("dependency file detection — requirements.txt")
-def _():
-    assert_true(is_dependency_file("requirements.txt"))
-    assert_true(is_dependency_file("src/requirements.txt"))
-    assert_false(is_dependency_file("requirements_test.txt"))
-
-@test("dependency file detection — pyproject.toml")
-def _():
-    assert_true(is_dependency_file("pyproject.toml"))
-    assert_false(is_dependency_file("myproject.py"))
-
-@test("test file detection — pytest style")
-def _():
-    assert_true(is_test_file("tests/test_api.py"))
-    assert_true(is_test_file("test_module.py"))
-    assert_true(is_test_file("src/module_test.py"))
-
-@test("test file detection — other frameworks")
-def _():
-    assert_true(is_test_file("spec/feature_spec.rb"))
-    assert_true(is_test_file("__tests__/component.test.js"))
-    assert_false(is_test_file("testfixtures/helper.py"))
-
-
-print("\n-- Scoring Logic --")
-
-@test("small PR gets low score (1-3)")
-def _():
-    score, minutes, _ = score_pr(
-        files_changed=3,
-        additions=50,
-        deletions=10,
-        has_dependency_changes=False,
-        test_coverage_delta=None
-    )
-    assert_true(1 <= score <= 3, f"Score should be low, got {score}")
-    assert_true(minutes < 20)
-
-@test("medium PR gets medium score (4-6)")
-def _():
-    score, minutes, _ = score_pr(
-        files_changed=15,
-        additions=400,
-        deletions=100,
-        has_dependency_changes=False,
-        test_coverage_delta=None
-    )
-    assert_true(4 <= score <= 6, f"Score should be medium, got {score}")
-    assert_true(20 <= minutes <= 45)
-
-@test("large PR gets high score (7-9)")
-def _():
-    score, minutes, _ = score_pr(
-        files_changed=60,
-        additions=3000,
-        deletions=1500,
-        has_dependency_changes=True,
-        test_coverage_delta=None
-    )
-    assert_true(7 <= score <= 9, f"Score should be high, got {score}")
-    assert_true(minutes >= 45)
-
-@test("dependency changes boost score")
-def _():
-    base_score, _, _ = score_pr(
-        files_changed=10, additions=200, deletions=50,
-        has_dependency_changes=False, test_coverage_delta=None
-    )
-    dep_score, _, _ = score_pr(
-        files_changed=10, additions=200, deletions=50,
-        has_dependency_changes=True, test_coverage_delta=None
-    )
-    assert_true(dep_score > base_score, f"Deps: {base_score} -> {dep_score}")
-
-@test("adding tests lowers complexity")
-def _():
-    base_score, _, _ = score_pr(
-        files_changed=8, additions=150, deletions=20,
-        has_dependency_changes=False, test_coverage_delta=None
-    )
-    better_score, _, _ = score_pr(
-        files_changed=8, additions=180, deletions=20,
-        has_dependency_changes=False, test_coverage_delta=3
-    )
-    assert_true(better_score < base_score, f"Tests: {base_score} -> {better_score}")
-
-@test("removing tests increases complexity")
-def _():
-    base_score, _, _ = score_pr(
-        files_changed=8, additions=150, deletions=20,
-        has_dependency_changes=False, test_coverage_delta=None
-    )
-    worse_score, _, _ = score_pr(
-        files_changed=8, additions=150, deletions=20,
-        has_dependency_changes=False, test_coverage_delta=-2
-    )
-    assert_true(worse_score > base_score, f"Remove tests: {base_score} -> {worse_score}")
-
-@test("score bounded 1-10")
-def _():
-    for files, adds, dels in [(1, 10, 5), (100, 10000, 5000)]:
-        score, _, _ = score_pr(files, adds, dels, False, None)
-        assert_true(1 <= score <= 10, f"Score {score} out of range")
-
-@test("estimated minutes exist for all scores")
-def _():
-    for s in range(1, 11):
-        assert_true(s in TIME_PER_POINT, f"Missing time for score {s}")
-
-
-print(f"\n=== Results: {PASS} passed, {FAIL} failed ===")
-sys.exit(0 if FAIL == 0 else 1)