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/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_generation_orchestrator.py

@@ -1,357 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test Generation Orchestrator — 3.10 (Compounding Intelligence)
-
-Implements a continuous pipeline that:
-  1. Maintains a queue of repositories to process.
-  2. Runs all 9 test generators per repository.
-  3. Stores results (tests written, pass rate, coverage delta).
-  4. After processing all repos, checks for new code changes and re-queues.
-  5. Runs continuously — never idle (loop with sleep).
-
-Usage:
-  python3 scripts/test_generation_orchestrator.py [--once] [--queue PATH] [--sleep N]
-
-Options:
-  --once        Run a single cycle then exit (for cron/debug).
-  --queue FILE  Path to queue file (default: test_queue.txt at repo root).
-  --sleep N     Sleep seconds between cycles (default: 3600).
-"""
-
-import argparse
-import json
-import subprocess
-import sys
-import time
-from dataclasses import dataclass, asdict
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Dict, List, Optional
-
-# ── Configuration ────────────────────────────────────────────────────────────
-SCRIPT_DIR = Path(__file__).resolve().parent
-REPO_ROOT = SCRIPT_DIR.parent
-DEFAULT_QUEUE = REPO_ROOT / "test_queue.txt"
-RESULTS_DIR = REPO_ROOT / "metrics" / "test_generation"
-GENERATED_TESTS_DIR = REPO_ROOT / "generated_tests"
-GENERATED_TESTS_DIR.mkdir(exist_ok=True)
-RESULTS_DIR.mkdir(parents=True, exist_ok=True)
-
-# Nine test generator names (registered below)
-GENERATOR_NAMES = [
-    "regression",
-    "gap",
-    "dead_code",
-    "perf",
-    "dependency",
-    "diff",
-    "refactoring",
-    "automation",
-    "security",
-]
-
-# ── Data Classes ─────────────────────────────────────────────────────────────
-
-@dataclass
-class GenResult:
-    generator: str
-    repo: str
-    tests_written: int
-    pass_rate: float
-    coverage_delta: Optional[float] = None
-    error: Optional[str] = None
-
-    def as_dict(self):
-        d = asdict(self)
-        d["timestamp"] = datetime.now(timezone.utc).isoformat()
-        return d
-
-# ── Queue Management ─────────────────────────────────────────────────────────
-
-def load_queue(path: Path) -> List[str]:
-    if not path.exists():
-        return []
-    return [line.strip() for line in path.read_text().splitlines()
-            if line.strip() and not line.startswith('#')]
-
-def save_queue(path: Path, queue: List[str]) -> None:
-    path.write_text('\n'.join(queue) + '\n')
-
-# ── Code Change Detection ────────────────────────────────────────────────────
-
-def has_new_code(repo_path: Path, last_commit: Optional[str]) -> bool:
-    """Return True if repo has new commits since last_commit SHA."""
-    try:
-        current = subprocess.run(
-            ["git", "rev-parse", "HEAD"],
-            capture_output=True, text=True, cwd=repo_path, timeout=10
-        )
-        if current.returncode != 0:
-            return True
-        current_sha = current.stdout.strip()
-        if last_commit is None:
-            return True
-        if current_sha == last_commit:
-            return False  # exactly up to date
-        merge_base = subprocess.run(
-            ["git", "merge-base", "--is-ancestor", last_commit, current_sha],
-            capture_output=True, cwd=repo_path, timeout=10
-        )
-        # Returncode 0 means last_commit IS an ancestor of current_sha => new commits exist
-        return merge_base.returncode == 0
-    except Exception:
-        return True
-
-# ── Test Generation Implementations ─────────────────────────────────────────
-
-def generate_regression_tests(repo_path: Path, out_dir: Path) -> GenResult:
-    """Generate regression tests from fix commits."""
-    try:
-        out_dir.mkdir(parents=True, exist_ok=True)
-        log = subprocess.run(
-            ["git", "log", "--since=30 days ago", "--grep=fix", "--oneline"],
-            capture_output=True, text=True, cwd=repo_path, timeout=30
-        )
-        fixes = [line.split()[0] for line in log.stdout.strip().splitlines() if line]
-        test_lines = []
-        for sha in fixes[:20]:
-            files_out = subprocess.run(
-                ["git", "show", "--name-only", "--pretty=format:", sha],
-                capture_output=True, text=True, cwd=repo_path, timeout=10
-            )
-            files = [f.strip() for f in files_out.stdout.splitlines() if f.strip()]
-            for f in files[:3]:
-                test_lines.append(
-                    f'''def test_regression_{sha[:7]}_{Path(f).stem}():
-    """Regression guard: commit {sha} touched {f}"""
-    repo = Path("{repo_path}")
-    assert (repo / "{f}").exists(), "File missing after fix commit"
-'''
-                )
-        test_file = out_dir / "test_regression_autogenerated.py"
-        test_file.write_text('''"""Auto-generated regression tests from fix commits."""
-import pytest
-from pathlib import Path
-
-''' + '\n'.join(test_lines))
-        return GenResult("regression", str(repo_path), tests_written=len(test_lines),
-                        pass_rate=1.0, coverage_delta=0.0)
-    except Exception as e:
-        return GenResult("regression", str(repo_path), 0, 0.0, error=str(e))
-
-def generate_gap_tests(repo_path: Path, out_dir: Path) -> GenResult:
-    """Generate tests for untested modules using knowledge_gap_identifier."""
-    try:
-        out_dir.mkdir(parents=True, exist_ok=True)
-        sys.path.insert(0, str(SCRIPT_DIR))
-        from knowledge_gap_identifier import KnowledgeGapIdentifier, GapType
-        kgi = KnowledgeGapIdentifier()
-        report = kgi.analyze(str(repo_path))
-        untested = [g for g in report.gaps if g.gap_type == GapType.UNTESTED]
-        test_lines = []
-        for gap in untested[:50]:
-            module_name = gap.name
-            file_rel = gap.file
-            module_path = repo_path / file_rel
-            if module_path.exists():
-                test_lines.append(
-                    f'''def test_{module_name}_exists():
-    """Ensure {module_name} module exists (auto-generated from gap)."""
-    import importlib.util
-    spec = importlib.util.spec_from_file_location("{module_name}", "{module_path}")
-    mod = importlib.util.module_from_spec(spec)
-    spec.loader.exec_module(mod)
-    assert mod is not None
-'''
-                )
-        test_file = out_dir / "test_gap_autogenerated.py"
-        test_file.write_text('''"""Auto-generated tests for previously untested modules."""
-import pytest
-
-''' + '\n'.join(test_lines))
-        return GenResult("gap", str(repo_path), tests_written=len(test_lines),
-                        pass_rate=1.0, coverage_delta=0.0)
-    except Exception as e:
-        return GenResult("gap", str(repo_path), 0, 0.0, error=str(e))
-
-def _stub(name: str, desc: str):
-    """Factory for stub generators that emit a single passing test."""
-    def _gen(repo_path: Path, out_dir: Path) -> GenResult:
-        try:
-            out_dir.mkdir(parents=True, exist_ok=True)
-            test_file = out_dir / f"test_{name}_autogenerated.py"
-            test_file.write_text(f'''"""Auto-generated {desc} tests (stub)."""
-import pytest
-
-def test_{name}_placeholder():
-    assert True  # {name} test placeholder
-''')
-            return GenResult(name, str(repo_path), tests_written=1, pass_rate=1.0)
-        except Exception as e:
-            return GenResult(name, str(repo_path), 0, 0.0, error=str(e))
-    return _gen
-
-GENERATORS = {
-    "regression": generate_regression_tests,
-    "gap": generate_gap_tests,
-    "dead_code": _stub("dead_code", "dead-code"),
-    "perf": _stub("perf", "performance"),
-    "dependency": _stub("dependency", "dependency"),
-    "diff": _stub("diff", "diff"),
-    "refactoring": _stub("refactoring", "refactoring"),
-    "automation": _stub("automation", "automation"),
-    "security": _stub("security", "security"),
-}
-
-# ── Pytest Runner ─────────────────────────────────────────────────────────────
-
-def run_pytest(generated_dir: Path, repo_path: Path) -> Dict:
-    if not any(generated_dir.iterdir()):
-        return {"passed": 0, "failed": 0, "pass_rate": 1.0, "coverage": None, "exit_code": 0, "raw_output": ""}
-    cmd = [sys.executable, "-m", "pytest", str(generated_dir), "--tb=short", "-q"]
-    cov_flag = False
-    try:
-        import coverage  # noqa
-        cov_dir = generated_dir.parent / "coverage_data"
-        cov_dir.mkdir(exist_ok=True)
-        cmd = [
-            sys.executable, "-m", "pytest",
-            str(generated_dir),
-            f"--cov={repo_path}",
-            f"--cov-report=json:{cov_dir / 'coverage.json'}",
-            "--tb=short", "-q"
-        ]
-        cov_flag = True
-    except ImportError:
-        pass
-    result = subprocess.run(cmd, capture_output=True, text=True, timeout=120, cwd=repo_path)
-    output = result.stdout + result.stderr
-    import re
-    passed = failed = 0
-    m = re.search(r'(\d+) passed', output)
-    if m:
-        passed = int(m.group(1))
-    m2 = re.search(r'(\d+) failed', output)
-    if m2:
-        failed = int(m2.group(1))
-    total = passed + failed
-    pass_rate = passed / total if total > 0 else 1.0
-    coverage = None
-    if cov_flag:
-        try:
-            cov_dir = generated_dir.parent / "coverage_data"
-            cov_file = cov_dir / "coverage.json"
-            if cov_file.exists():
-                with open(cov_file) as f:
-                    cov_data = json.load(f)
-                totals = cov_data.get('totals', {})
-                coverage = float(totals.get('percent_covered', 0.0))
-        except Exception:
-            coverage = None
-    return {
-        "passed": passed, "failed": failed, "pass_rate": pass_rate,
-        "coverage": coverage, "exit_code": result.returncode,
-        "raw_output": output[:500]
-    }
-
-# ── Per-Repo Processor ────────────────────────────────────────────────────────
-
-def process_repo(repo_path: Path, queue: List[str]) -> None:
-    repo_key = repo_path.name
-    if not (repo_path / ".git").exists():
-        print(f"  Skipping {repo_key}: not a git repo")
-        return
-
-    cycle_id = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S")
-    cycle_dir = GENERATED_TESTS_DIR / cycle_id / repo_key
-    cycle_dir.mkdir(parents=True, exist_ok=True)
-
-    cycle_results = []
-    for gname in GENERATOR_NAMES:
-        gen_func = GENERATORS.get(gname)
-        if gen_func is None:
-            print(f"  [{gname}] not registered, skipping")
-            continue
-        gen_out = cycle_dir / gname
-        res = gen_func(repo_path, gen_out)
-        pytest_res = run_pytest(gen_out, repo_path)
-        res.pass_rate = pytest_res["pass_rate"]
-        # Adjust tests_written to reflect actual discovered tests
-        total_tests = pytest_res["passed"] + pytest_res["failed"]
-        if total_tests > 0:
-            res.tests_written = total_tests
-        if pytest_res["coverage"] is not None:
-            res.coverage_delta = pytest_res["coverage"]
-        if pytest_res["exit_code"] not in (0, 1, 2, 3, 4):
-            res.error = (res.error or '') + f" pytest exit {pytest_res['exit_code']}"
-        cycle_results.append(res.as_dict())
-        status = "PASS" if pytest_res["passed"] == total_tests and total_tests>0 else f"{pytest_res['failed']} fails"
-        print(f"  [{gname}] {res.tests_written} tests, pass rate {pytest_res['pass_rate']:.0%} — {status}")
-
-    # Store summary
-    summary = {
-        "repo": str(repo_path),
-        "cycle": cycle_id,
-        "generators": cycle_results,
-        "summary": {
-            "total_tests_written": sum(r.get("tests_written", 0) for r in cycle_results),
-            "avg_pass_rate": (sum(r.get("tests_passed",0) for r in cycle_results) /
-                              sum(r.get("tests_passed",0) + sum(r.get("tests_failed",0) for r in cycle_results) or 1)),
-        }
-    }
-    out_json = RESULTS_DIR / f"{repo_key}_{cycle_id}.json"
-    out_json.write_text(json.dumps(summary, indent=2))
-    print(f"  Stored results: {out_json}")
-
-    # Re-queue if new code
-    last_commit_file = REPO_ROOT / ".orchestrator" / f"last_{repo_key}.txt"
-    last_commit = last_commit_file.read_text().strip() if last_commit_file.exists() else None
-    if has_new_code(repo_path, last_commit):
-        print(f"  New commits detected — re-queuing {repo_key}")
-        queue.append(str(repo_path))
-    cur = subprocess.run(["git", "rev-parse", "HEAD"], capture_output=True, text=True, cwd=repo_path)
-    if cur.returncode == 0:
-        last_commit_file.parent.mkdir(parents=True, exist_ok=True)
-        last_commit_file.write_text(cur.stdout.strip())
-
-# ── Main ──────────────────────────────────────────────────────────────────────
-
-def main():
-    parser = argparse.ArgumentParser(description="Test Generation Orchestrator")
-    parser.add_argument("--once", action="store_true", help="Run single cycle then exit")
-    parser.add_argument("--queue", type=Path, default=DEFAULT_QUEUE, help="Queue file path")
-    parser.add_argument("--sleep", type=int, default=3600, help="Sleep seconds between cycles")
-    args = parser.parse_args()
-
-    queue = load_queue(args.queue)
-    if not queue:
-        print("[Orchestrator] Queue empty. Add repo paths (one per line) to test_queue.txt.")
-        sys.exit(1)
-
-    try:
-        cycle = 0
-        while True:
-            cycle += 1
-            print(f"\n[Orchestrator] Cycle {cycle} — {len(queue)} repos to process")
-            # Process all repos that were in queue at start of cycle
-            current_cycle_queue = queue.copy()
-            # We'll clear queue and let process_repo re-add if needed
-            queue.clear()
-            for repo_str in current_cycle_queue:
-                repo_path = Path(repo_str).expanduser().resolve()
-                if not repo_path.exists():
-                    print(f"  Path missing: {repo_str} — skipping")
-                    continue
-                process_repo(repo_path, queue)  # queue may get appended during loop
-            print(f"[Orchestrator] Cycle {cycle} complete. {len(queue)} repos re-queued for next cycle.")
-            save_queue(args.queue, queue)
-            if args.once:
-                break
-            print(f"[Orchestrator] Sleeping for {args.sleep} seconds...")
-            time.sleep(args.sleep)
-    except KeyboardInterrupt:
-        save_queue(args.queue, queue)
-        sys.exit(0)
-
-if __name__ == "__main__":
-    main()

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)

scripts/test_test_generation_orchestrator.py

@@ -1,101 +0,0 @@
-#!/usr/bin/env python3
-"""
-Smoke tests for test_generation_orchestrator.py
-"""
-
-import json
-import subprocess
-import sys
-import tempfile
-from pathlib import Path
-
-# Add scripts dir to path for imports (orchestrator.py lives in scripts/)
-SCRIPT_DIR = Path(__file__).resolve().parent
-sys.path.insert(0, str(SCRIPT_DIR))
-
-from test_generation_orchestrator import (
-    load_queue, save_queue, GenResult, has_new_code,
-    _stub, GENERATOR_NAMES, GENERATORS
-)
-
-def test_load_queue_empty_when_missing():
-    with tempfile.TemporaryDirectory() as tmp:
-        p = Path(tmp) / "nofile.txt"
-        assert load_queue(p) == []
-
-def test_save_and_load_queue_roundtrip():
-    with tempfile.TemporaryDirectory() as tmp:
-        p = Path(tmp) / "queue.txt"
-        items = ["repo1", "# comment", "", "repo2"]
-        save_queue(p, items)
-        loaded = load_queue(p)
-        assert loaded == ["repo1", "repo2"]
-
-def test_stub_generator_creates_test_file():
-    with tempfile.TemporaryDirectory() as tmp:
-        repo = Path(tmp) / "repo"
-        repo.mkdir()
-        out = Path(tmp) / "out"
-        gen = _stub("testme", "testme-desc")
-        res = gen(repo, out)
-        assert res.tests_written == 1
-        assert res.pass_rate == 1.0
-        assert (out / "test_testme_autogenerated.py").exists()
-        content = (out / "test_testme_autogenerated.py").read_text()
-        assert "test_testme_placeholder" in content
-        assert "assert True" in content
-
-def test_all_nine_generators_registered():
-    assert len(GENERATOR_NAMES) == 9
-    for name in GENERATOR_NAMES:
-        assert name in GENERATORS, f"Generator {name} not in GENERATORS dict"
-
-def test_genresult_serialization():
-    gr = GenResult("gap", "/fake", 5, 0.8, coverage_delta=2.5, error=None)
-    d = gr.as_dict()
-    assert d["generator"] == "gap"
-    assert d["tests_written"] == 5
-    assert d["pass_rate"] == 0.8
-    assert d["coverage_delta"] == 2.5
-    assert "timestamp" in d
-
-def test_has_new_code_when_no_last():
-    with tempfile.TemporaryDirectory() as tmp:
-        repo = Path(tmp) / "repo"
-        repo.mkdir()
-        # initialize git
-        subprocess.run(["git", "init"], cwd=repo, check=True, capture_output=True)
-        (repo / "file.txt").write_text("hello")
-        subprocess.run(["git", "add", "."], cwd=repo, check=True, capture_output=True)
-        subprocess.run(["git", "commit", "-m", "init"], cwd=repo, check=True, capture_output=True)
-        assert has_new_code(repo, None) is True
-
-def test_has_new_code_when_behind():
-    with tempfile.TemporaryDirectory() as tmp:
-        repo = Path(tmp) / "repo"
-        repo.mkdir()
-        subprocess.run(["git", "init"], cwd=repo, check=True, capture_output=True)
-        (repo / "f1").write_text("a")
-        subprocess.run(["git", "add", "."], cwd=repo, check=True, capture_output=True)
-        subprocess.run(["git", "commit", "-m", "first"], cwd=repo, check=True, capture_output=True)
-        first_sha = subprocess.run(["git", "rev-parse", "HEAD"], capture_output=True, text=True, cwd=repo).stdout.strip()
-        # make a new commit
-        (repo / "f2").write_text("b")
-        subprocess.run(["git", "add", "."], cwd=repo, check=True, capture_output=True)
-        subprocess.run(["git", "commit", "-m", "second"], cwd=repo, check=True, capture_output=True)
-        assert has_new_code(repo, first_sha) is True
-
-def test_has_new_code_when_up_to_date():
-    with tempfile.TemporaryDirectory() as tmp:
-        repo = Path(tmp) / "repo"
-        repo.mkdir()
-        subprocess.run(["git", "init"], cwd=repo, check=True, capture_output=True)
-        (repo / "f").write_text("a")
-        subprocess.run(["git", "add", "."], cwd=repo, check=True, capture_output=True)
-        subprocess.run(["git", "commit", "-m", "c"], cwd=repo, check=True, capture_output=True)
-        cur = subprocess.run(["git", "rev-parse", "HEAD"], capture_output=True, text=True, cwd=repo).stdout.strip()
-        assert has_new_code(repo, cur) is False
-
-if __name__ == "__main__":
-    import pytest
-    sys.exit(pytest.main([__file__, "-v"]))