test: add tests for Performance Bottleneck Finder

Refs #171

scripts/knowledge_staleness_check.py

@@ -0,0 +1,131 @@
+#!/usr/bin/env python3
+"""
+Knowledge Store Staleness Detector — Detect stale knowledge entries by comparing source file hashes.
+
+Usage:
+    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json
+    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --json
+    python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --fix
+"""
+
+import argparse
+import hashlib
+import json
+import os
+import sys
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Dict, List, Any, Optional
+
+
+def compute_file_hash(filepath: str) -> Optional[str]:
+    """Compute SHA-256 hash of a file. Returns None if file doesn't exist."""
+    try:
+        with open(filepath, "rb") as f:
+            return "sha256:" + hashlib.sha256(f.read()).hexdigest()
+    except (FileNotFoundError, IsADirectoryError, PermissionError):
+        return None
+
+
+def check_staleness(index_path: str, repo_root: str = ".") -> List[Dict[str, Any]]:
+    """Check all entries in knowledge index for staleness.
+    
+    Returns list of entries with staleness info:
+    - status: "fresh" | "stale" | "missing_source" | "no_hash"
+    - current_hash: computed hash (if source exists)
+    - stored_hash: hash from index
+    """
+    with open(index_path) as f:
+        data = json.load(f)
+
+    facts = data.get("facts", [])
+    results = []
+
+    for entry in facts:
+        source_file = entry.get("source_file")
+        stored_hash = entry.get("source_hash")
+
+        if not source_file:
+            results.append({**entry, "status": "no_source", "current_hash": None})
+            continue
+
+        full_path = os.path.join(repo_root, source_file)
+        current_hash = compute_file_hash(full_path)
+
+        if current_hash is None:
+            results.append({**entry, "status": "missing_source", "current_hash": None})
+        elif not stored_hash:
+            results.append({**entry, "status": "no_hash", "current_hash": current_hash})
+        elif current_hash != stored_hash:
+            results.append({**entry, "status": "stale", "current_hash": current_hash})
+        else:
+            results.append({**entry, "status": "fresh", "current_hash": current_hash})
+
+    return results
+
+
+def fix_hashes(index_path: str, repo_root: str = ".") -> int:
+    """Add hashes to entries missing them. Returns count of fixed entries."""
+    with open(index_path) as f:
+        data = json.load(f)
+
+    fixed = 0
+    for entry in data.get("facts", []):
+        if entry.get("source_hash"):
+            continue
+        source_file = entry.get("source_file")
+        if not source_file:
+            continue
+        full_path = os.path.join(repo_root, source_file)
+        h = compute_file_hash(full_path)
+        if h:
+            entry["source_hash"] = h
+            fixed += 1
+
+    with open(index_path, "w") as f:
+        json.dump(data, f, indent=2)
+
+    return fixed
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Check knowledge store staleness")
+    parser.add_argument("--index", required=True, help="Path to knowledge/index.json")
+    parser.add_argument("--repo", default=".", help="Repo root for source file resolution")
+    parser.add_argument("--json", action="store_true", help="Output as JSON")
+    parser.add_argument("--fix", action="store_true", help="Add hashes to entries missing them")
+
+    args = parser.parse_args()
+
+    if args.fix:
+        fixed = fix_hashes(args.index, args.repo)
+        print(f"Fixed {fixed} entries with missing hashes.")
+        return
+
+    results = check_staleness(args.index, args.repo)
+
+    if args.json:
+        print(json.dumps(results, indent=2))
+    else:
+        stale = [r for r in results if r["status"] != "fresh"]
+        fresh = [r for r in results if r["status"] == "fresh"]
+
+        print(f"Knowledge Store Staleness Check")
+        print(f"  Total entries: {len(results)}")
+        print(f"  Fresh: {len(fresh)}")
+        print(f"  Stale/Issues: {len(stale)}")
+        print()
+
+        if stale:
+            print("Issues found:")
+            for r in stale:
+                status = r["status"]
+                fact = r.get("fact", "?")[:60]
+                source = r.get("source_file", "?")
+                print(f"  [{status}] {source}: {fact}")
+        else:
+            print("All entries are fresh!")
+
+
+if __name__ == "__main__":
+    main()

scripts/perf_bottleneck_finder.py

@@ -0,0 +1,551 @@
+#!/usr/bin/env python3
+"""
+Performance Bottleneck Finder — Identify slow tests, builds, and CI steps.
+
+Analyzes:
+  1. Pytest output for slow tests
+  2. Build logs for slow steps
+  3. CI workflow durations
+  4. File system for large/slow artifacts
+
+Usage:
+    python3 scripts/perf_bottleneck_finder.py --repo /path/to/repo
+    python3 scripts/perf_bottleneck_finder.py --repo /path/to/repo --json
+    python3 scripts/perf_bottleneck_finder.py --repo /path/to/repo --report metrics/perf_report.md
+
+Weekly cron:
+    0 9 * * 1 cd /path/to/compounding-intelligence && python3 scripts/perf_bottleneck_finder.py --repo /path/to/target --report metrics/perf_report.md
+"""
+
+import argparse
+import json
+import os
+import re
+import subprocess
+import sys
+from collections import defaultdict
+from dataclasses import dataclass, field, asdict
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
+
+
+# ── Configuration ──────────────────────────────────────────────────
+
+SLOW_TEST_THRESHOLD_S = 2.0      # Tests slower than this are flagged
+SLOW_BUILD_STEP_THRESHOLD_S = 10.0
+TOP_N_BOTTLENECKS = 10           # Report top N bottlenecks
+PYTEST_DURATIONS_COUNT = 20      # Number of slow tests to collect
+LOG_EXTENSIONS = {".log", ".txt"}
+
+
+@dataclass
+class Bottleneck:
+    """A single performance bottleneck."""
+    category: str          # "test", "build", "ci", "artifact", "import"
+    name: str              # What's slow
+    duration_s: float      # How long it takes
+    severity: str          # "critical", "warning", "info"
+    recommendation: str    # How to fix
+    file_path: Optional[str] = None
+    line_number: Optional[int] = None
+
+
+@dataclass
+class PerfReport:
+    """Full performance report."""
+    timestamp: str
+    repo_path: str
+    bottlenecks: List[Bottleneck] = field(default_factory=list)
+    summary: Dict[str, Any] = field(default_factory=dict)
+    test_stats: Dict[str, Any] = field(default_factory=dict)
+    build_stats: Dict[str, Any] = field(default_factory=dict)
+    ci_stats: Dict[str, Any] = field(default_factory=dict)
+
+    def to_dict(self) -> dict:
+        d = asdict(self)
+        return d
+
+
+# ── Test Analysis ──────────────────────────────────────────────────
+
+def find_slow_tests_pytest(repo_path: str) -> List[Bottleneck]:
+    """Run pytest --durations and parse slow tests."""
+    bottlenecks = []
+
+    # Try to run pytest with durations
+    try:
+        result = subprocess.run(
+            ["python3", "-m", "pytest", "--co", "-q", "--durations=0"],
+            cwd=repo_path, capture_output=True, text=True, timeout=30
+        )
+        # If tests exist, try to get durations from last run
+        durations_file = os.path.join(repo_path, ".pytest_cache", "v", "cache", "durations")
+        if os.path.exists(durations_file):
+            with open(durations_file) as f:
+                for line in f:
+                    parts = line.strip().split()
+                    if len(parts) >= 2:
+                        try:
+                            duration = float(parts[0])
+                            test_name = " ".join(parts[1:])
+                            if duration > SLOW_TEST_THRESHOLD_S:
+                                severity = "critical" if duration > 10 else "warning"
+                                bottlenecks.append(Bottleneck(
+                                    category="test",
+                                    name=test_name,
+                                    duration_s=duration,
+                                    severity=severity,
+                                    recommendation=f"Test takes {duration:.1f}s. Consider mocking slow I/O, using fixtures, or marking with @pytest.mark.slow."
+                                ))
+                        except ValueError:
+                            continue
+    except (subprocess.TimeoutExpired, FileNotFoundError):
+        pass
+
+    return bottlenecks
+
+
+def find_slow_tests_by_scan(repo_path: str) -> List[Bottleneck]:
+    """Scan test files for patterns that indicate slow tests."""
+    bottlenecks = []
+    test_patterns = [
+        (r"time\.sleep\((\d+(?:\.\d+)?)\)", "Contains time.sleep() — consider using mock or async wait"),
+        (r"subprocess\.run\(.*timeout=(\d+)", "Subprocess with timeout — may block test"),
+        (r"requests\.(get|post|put|delete)\(", "Real HTTP call — mock with responses or httpretty"),
+        (r"open\([^)]*['"]w['"]", "File I/O in test — use tmp_path fixture"),
+    ]
+
+    for root, dirs, files in os.walk(repo_path):
+        # Skip hidden and cache dirs
+        dirs[:] = [d for d in dirs if not d.startswith(('.', '__pycache__', 'node_modules', '.git'))]
+
+        for fname in files:
+            if not (fname.startswith("test_") or fname.endswith("_test.py")):
+                continue
+            if not fname.endswith(".py"):
+                continue
+
+            fpath = os.path.join(root, fname)
+            rel_path = os.path.relpath(fpath, repo_path)
+
+            try:
+                with open(fpath) as f:
+                    lines = f.readlines()
+            except (PermissionError, UnicodeDecodeError):
+                continue
+
+            for i, line in enumerate(lines):
+                for pattern, recommendation in test_patterns:
+                    match = re.search(pattern, line)
+                    if match:
+                        duration = 1.0  # Default estimate
+                        if "sleep" in pattern:
+                            try:
+                                duration = float(match.group(1))
+                            except (ValueError, IndexError):
+                                duration = 1.0
+                        elif "timeout" in pattern:
+                            try:
+                                duration = float(match.group(1))
+                            except (ValueError, IndexError):
+                                duration = 10.0
+                        else:
+                            duration = 2.0  # Estimated
+
+                        bottlenecks.append(Bottleneck(
+                            category="test",
+                            name=f"{rel_path}:{i+1}",
+                            duration_s=duration,
+                            severity="warning" if duration < 5 else "critical",
+                            recommendation=recommendation,
+                            file_path=rel_path,
+                            line_number=i + 1
+                        ))
+
+    return bottlenecks
+
+
+# ── Build Analysis ─────────────────────────────────────────────────
+
+def analyze_build_artifacts(repo_path: str) -> List[Bottleneck]:
+    """Find large build artifacts that slow down builds."""
+    bottlenecks = []
+    large_dirs = {
+        "node_modules": "Consider using npm ci --production or yarn --production",
+        "__pycache__": "Consider .gitignore and cleaning before builds",
+        ".tox": "Consider caching tox environments",
+        ".pytest_cache": "Consider cleaning between CI runs",
+        "dist": "Check if dist/ artifacts are being rebuilt unnecessarily",
+        "build": "Check if build/ artifacts are being rebuilt unnecessarily",
+        ".next": "Next.js cache — consider incremental builds",
+        "venv": "Virtual env in repo — move outside or use Docker",
+    }
+
+    for dirname, recommendation in large_dirs.items():
+        dirpath = os.path.join(repo_path, dirname)
+        if os.path.isdir(dirpath):
+            total_size = 0
+            file_count = 0
+            for root, dirs, files in os.walk(dirpath):
+                for f in files:
+                    try:
+                        fpath = os.path.join(root, f)
+                        total_size += os.path.getsize(fpath)
+                        file_count += 1
+                    except OSError:
+                        pass
+
+            if total_size > 10 * 1024 * 1024:  # > 10MB
+                size_mb = total_size / (1024 * 1024)
+                bottlenecks.append(Bottleneck(
+                    category="build",
+                    name=f"{dirname}/ ({size_mb:.1f}MB, {file_count} files)",
+                    duration_s=size_mb * 0.5,  # Rough estimate
+                    severity="critical" if size_mb > 100 else "warning",
+                    recommendation=recommendation
+                ))
+
+    return bottlenecks
+
+
+def analyze_makefile_targets(repo_path: str) -> List[Bottleneck]:
+    """Analyze Makefile for potentially slow targets."""
+    bottlenecks = []
+    makefiles = []
+
+    for root, dirs, files in os.walk(repo_path):
+        dirs[:] = [d for d in dirs if not d.startswith(('.', '__pycache__'))]
+        for f in files:
+            if f in ("Makefile", "makefile", "GNUmakefile"):
+                makefiles.append(os.path.join(root, f))
+
+    slow_patterns = [
+        (r"pip install", "pip install without --no-deps or constraints"),
+        (r"npm install(?!.*--production)", "npm install without --production flag"),
+        (r"docker build", "Docker build — consider multi-stage and layer caching"),
+        (r"pytest(?!.*-x|--maxfail)", "pytest without early exit on failure"),
+        (r"mypy|mypy --strict", "Type checking — consider incremental mode"),
+    ]
+
+    for mfile in makefiles:
+        rel_path = os.path.relpath(mfile, repo_path)
+        try:
+            with open(mfile) as f:
+                content = f.read()
+        except (PermissionError, UnicodeDecodeError):
+            continue
+
+        for pattern, recommendation in slow_patterns:
+            if re.search(pattern, content):
+                bottlenecks.append(Bottleneck(
+                    category="build",
+                    name=f"{rel_path}: {pattern}",
+                    duration_s=5.0,
+                    severity="info",
+                    recommendation=recommendation,
+                    file_path=rel_path
+                ))
+
+    return bottlenecks
+
+
+# ── CI Analysis ────────────────────────────────────────────────────
+
+def analyze_github_actions(repo_path: str) -> List[Bottleneck]:
+    """Analyze GitHub Actions workflow files for inefficiencies."""
+    bottlenecks = []
+    workflow_dir = os.path.join(repo_path, ".github", "workflows")
+
+    if not os.path.isdir(workflow_dir):
+        return bottlenecks
+
+    slow_patterns = [
+        (r"runs-on:\s*ubuntu-latest", 0, "Consider caching dependencies between runs"),
+        (r"npm install", 2, "Use npm ci instead of npm install for reproducible builds"),
+        (r"pip install(?!.*--cache-dir)", 2, "Add --cache-dir or use pip cache action"),
+        (r"docker build(?!.*--cache-from)", 5, "Use Docker layer caching"),
+        (r"python -m pytest(?!.*-n|--numprocesses)", 3, "Consider pytest-xdist for parallel test execution"),
+    ]
+
+    for fname in os.listdir(workflow_dir):
+        if not fname.endswith(('.yml', '.yaml')):
+            continue
+
+        fpath = os.path.join(workflow_dir, fname)
+        try:
+            with open(fpath) as f:
+                content = f.read()
+        except (PermissionError, UnicodeDecodeError):
+            continue
+
+        for pattern, est_savings, recommendation in slow_patterns:
+            if re.search(pattern, content):
+                bottlenecks.append(Bottleneck(
+                    category="ci",
+                    name=f"{fname}: {pattern}",
+                    duration_s=est_savings,
+                    severity="info",
+                    recommendation=recommendation,
+                    file_path=f".github/workflows/{fname}"
+                ))
+
+    return bottlenecks
+
+
+def analyze_gitea_ci(repo_path: str) -> List[Bottleneck]:
+    """Analyze Gitea/Drone CI config files."""
+    bottlenecks = []
+    ci_files = [".gitea/workflows", ".drone.yml", ".woodpecker.yml"]
+
+    for ci_path in ci_files:
+        full_path = os.path.join(repo_path, ci_path)
+        if os.path.isfile(full_path):
+            try:
+                with open(full_path) as f:
+                    content = f.read()
+            except (PermissionError, UnicodeDecodeError):
+                continue
+
+            if "pip install" in content and "--cache-dir" not in content:
+                bottlenecks.append(Bottleneck(
+                    category="ci",
+                    name=f"{ci_path}: pip without cache",
+                    duration_s=5.0,
+                    severity="warning",
+                    recommendation="Add --cache-dir or mount pip cache volume",
+                    file_path=ci_path
+                ))
+
+        elif os.path.isdir(full_path):
+            for fname in os.listdir(full_path):
+                if not fname.endswith(('.yml', '.yaml')):
+                    continue
+                fpath = os.path.join(full_path, fname)
+                try:
+                    with open(fpath) as f:
+                        content = f.read()
+                except (PermissionError, UnicodeDecodeError):
+                    continue
+
+                if "pip install" in content and "--cache-dir" not in content:
+                    bottlenecks.append(Bottleneck(
+                        category="ci",
+                        name=f"{ci_path}/{fname}: pip without cache",
+                        duration_s=5.0,
+                        severity="warning",
+                        recommendation="Add --cache-dir or mount pip cache volume",
+                        file_path=f"{ci_path}/{fname}"
+                    ))
+
+    return bottlenecks
+
+
+# ── Import Analysis ────────────────────────────────────────────────
+
+def find_slow_imports(repo_path: str) -> List[Bottleneck]:
+    """Find Python files with heavy import chains."""
+    bottlenecks = []
+    heavy_imports = {
+        "pandas": 0.5,
+        "numpy": 0.3,
+        "torch": 2.0,
+        "tensorflow": 3.0,
+        "scipy": 0.5,
+        "matplotlib": 0.8,
+        "sklearn": 0.5,
+        "transformers": 1.5,
+    }
+
+    for root, dirs, files in os.walk(repo_path):
+        dirs[:] = [d for d in dirs if not d.startswith(('.', '__pycache__', 'node_modules'))]
+        for fname in files:
+            if not fname.endswith(".py"):
+                continue
+
+            fpath = os.path.join(root, fname)
+            rel_path = os.path.relpath(fpath, repo_path)
+
+            try:
+                with open(fpath) as f:
+                    lines = f.readlines()
+            except (PermissionError, UnicodeDecodeError):
+                continue
+
+            for i, line in enumerate(lines):
+                stripped = line.strip()
+                if stripped.startswith("import ") or stripped.startswith("from "):
+                    for heavy, est_time in heavy_imports.items():
+                        if heavy in stripped:
+                            bottlenecks.append(Bottleneck(
+                                category="import",
+                                name=f"{rel_path}:{i+1}: import {heavy}",
+                                duration_s=est_time,
+                                severity="info" if est_time < 1.0 else "warning",
+                                recommendation=f"Heavy import ({heavy} ~{est_time}s). Consider lazy import or conditional import.",
+                                file_path=rel_path,
+                                line_number=i + 1
+                            ))
+
+    return bottlenecks
+
+
+# ── Report Generation ──────────────────────────────────────────────
+
+def severity_sort_key(b: Bottleneck) -> Tuple[int, float]:
+    """Sort by severity then duration."""
+    sev_order = {"critical": 0, "warning": 1, "info": 2}
+    return (sev_order.get(b.severity, 3), -b.duration_s)
+
+
+def generate_report(repo_path: str) -> PerfReport:
+    """Run all analyses and generate a performance report."""
+    report = PerfReport(
+        timestamp=datetime.now(timezone.utc).isoformat(),
+        repo_path=os.path.abspath(repo_path)
+    )
+
+    # Collect all bottlenecks
+    all_bottlenecks = []
+
+    print("Scanning for slow tests (pytest cache)...")
+    all_bottlenecks.extend(find_slow_tests_pytest(repo_path))
+
+    print("Scanning for slow test patterns...")
+    all_bottlenecks.extend(find_slow_tests_by_scan(repo_path))
+
+    print("Analyzing build artifacts...")
+    all_bottlenecks.extend(analyze_build_artifacts(repo_path))
+
+    print("Analyzing Makefiles...")
+    all_bottlenecks.extend(analyze_makefile_targets(repo_path))
+
+    print("Analyzing CI workflows...")
+    all_bottlenecks.extend(analyze_github_actions(repo_path))
+    all_bottlenecks.extend(analyze_gitea_ci(repo_path))
+
+    print("Scanning for heavy imports...")
+    all_bottlenecks.extend(find_slow_imports(repo_path))
+
+    # Sort by severity and duration
+    all_bottlenecks.sort(key=severity_sort_key)
+    report.bottlenecks = all_bottlenecks[:TOP_N_BOTTLENECKS * 2]  # Keep more for stats
+
+    # Compute summary
+    by_category = defaultdict(list)
+    for b in all_bottlenecks:
+        by_category[b.category].append(b)
+
+    report.summary = {
+        "total_bottlenecks": len(all_bottlenecks),
+        "critical": sum(1 for b in all_bottlenecks if b.severity == "critical"),
+        "warning": sum(1 for b in all_bottlenecks if b.severity == "warning"),
+        "info": sum(1 for b in all_bottlenecks if b.severity == "info"),
+        "estimated_total_slowdown_s": sum(b.duration_s for b in all_bottlenecks),
+        "by_category": {cat: len(items) for cat, items in by_category.items()},
+    }
+
+    report.test_stats = {
+        "slow_tests": len(by_category.get("test", [])),
+        "total_estimated_s": sum(b.duration_s for b in by_category.get("test", [])),
+    }
+
+    report.build_stats = {
+        "build_issues": len(by_category.get("build", [])),
+        "total_estimated_s": sum(b.duration_s for b in by_category.get("build", [])),
+    }
+
+    report.ci_stats = {
+        "ci_issues": len(by_category.get("ci", [])),
+        "total_estimated_s": sum(b.duration_s for b in by_category.get("ci", [])),
+    }
+
+    return report
+
+
+def format_markdown(report: PerfReport) -> str:
+    """Format report as markdown."""
+    lines = []
+    lines.append(f"# Performance Bottleneck Report")
+    lines.append(f"")
+    lines.append(f"Generated: {report.timestamp}")
+    lines.append(f"Repository: {report.repo_path}")
+    lines.append(f"")
+
+    # Summary
+    s = report.summary
+    lines.append(f"## Summary")
+    lines.append(f"")
+    lines.append(f"- **Total bottlenecks:** {s['total_bottlenecks']}")
+    lines.append(f"- **Critical:** {s['critical']} | **Warning:** {s['warning']} | **Info:** {s['info']}")
+    lines.append(f"- **Estimated total slowdown:** {s['estimated_total_slowdown_s']:.1f}s")
+    lines.append(f"- **By category:** {', '.join(f'{k}: {v}' for k, v in s['by_category'].items())}")
+    lines.append(f"")
+
+    # Top bottlenecks
+    lines.append(f"## Top {min(TOP_N_BOTTLENECKS, len(report.bottlenecks))} Bottlenecks")
+    lines.append(f"")
+
+    for i, b in enumerate(report.bottlenecks[:TOP_N_BOTTLENECKS], 1):
+        icon = {"critical": "🔴", "warning": "🟡", "info": "🔵"}.get(b.severity, "⚪")
+        loc = f" ({b.file_path}:{b.line_number})" if b.file_path else ""
+        lines.append(f"{i}. {icon} **{b.category}** — {b.name}{loc}")
+        lines.append(f"   - Duration: ~{b.duration_s:.1f}s | Severity: {b.severity}")
+        lines.append(f"   - Fix: {b.recommendation}")
+        lines.append(f"")
+
+    # Category breakdowns
+    for cat in ["test", "build", "ci", "import"]:
+        items = [b for b in report.bottlenecks if b.category == cat]
+        if items:
+            lines.append(f"## {cat.title()} Bottlenecks")
+            lines.append(f"")
+            for b in items:
+                icon = {"critical": "🔴", "warning": "🟡", "info": "🔵"}.get(b.severity, "⚪")
+                loc = f" ({b.file_path}:{b.line_number})" if b.file_path else ""
+                lines.append(f"- {icon} {b.name}{loc} — ~{b.duration_s:.1f}s — {b.recommendation}")
+            lines.append(f"")
+
+    return "
+".join(lines)
+
+
+# ── Main ───────────────────────────────────────────────────────────
+
+def main():
+    parser = argparse.ArgumentParser(description="Performance Bottleneck Finder")
+    parser.add_argument("--repo", default=".", help="Path to repository to analyze")
+    parser.add_argument("--json", action="store_true", help="Output as JSON")
+    parser.add_argument("--report", help="Write markdown report to file")
+    parser.add_argument("--threshold", type=float, default=SLOW_TEST_THRESHOLD_S,
+                        help="Slow test threshold in seconds")
+    args = parser.parse_args()
+
+    global SLOW_TEST_THRESHOLD_S
+    SLOW_TEST_THRESHOLD_S = args.threshold
+
+    if not os.path.isdir(args.repo):
+        print(f"Error: {args.repo} is not a directory", file=sys.stderr)
+        sys.exit(1)
+
+    report = generate_report(args.repo)
+
+    if args.json:
+        print(json.dumps(report.to_dict(), indent=2))
+    else:
+        md = format_markdown(report)
+        if args.report:
+            os.makedirs(os.path.dirname(args.report) or ".", exist_ok=True)
+            with open(args.report, "w") as f:
+                f.write(md)
+            print(f"Report written to {args.report}")
+        else:
+            print(md)
+
+    # Exit code: 1 if critical bottlenecks found
+    if report.summary.get("critical", 0) > 0:
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

scripts/test_harvest_prompt_comprehensive.py

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

scripts/test_knowledge_staleness.py

@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+"""Tests for scripts/knowledge_staleness_check.py — 8 tests."""
+
+import json
+import os
+import sys
+import tempfile
+
+sys.path.insert(0, os.path.dirname(__file__) or ".")
+import importlib.util
+spec = importlib.util.spec_from_file_location("ks", os.path.join(os.path.dirname(__file__) or ".", "knowledge_staleness_check.py"))
+mod = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(mod)
+check_staleness = mod.check_staleness
+fix_hashes = mod.fix_hashes
+compute_file_hash = mod.compute_file_hash
+
+
+def test_fresh_entry():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("print('hello')")
+        h = compute_file_hash(src)
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "hello", "source_file": "source.py", "source_hash": h}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "fresh"
+        print("PASS: test_fresh_entry")
+
+
+def test_stale_entry():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("original content")
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "old", "source_file": "source.py", "source_hash": "sha256:wrong"}]}, f)
+        # Now change the source
+        with open(src, "w") as f:
+            f.write("modified content")
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "stale"
+        print("PASS: test_stale_entry")
+
+
+def test_missing_source():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "gone", "source_file": "nonexistent.py", "source_hash": "sha256:abc"}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "missing_source"
+        print("PASS: test_missing_source")
+
+
+def test_no_hash():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("content")
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "no hash", "source_file": "source.py"}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "no_hash"
+        assert results[0]["current_hash"].startswith("sha256:")
+        print("PASS: test_no_hash")
+
+
+def test_no_source_field():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "orphan"}]}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results[0]["status"] == "no_source"
+        print("PASS: test_no_source_field")
+
+
+def test_fix_hashes():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        src = os.path.join(tmpdir, "source.py")
+        with open(src, "w") as f:
+            f.write("content for hashing")
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": [{"fact": "needs hash", "source_file": "source.py"}]}, f)
+        fixed = fix_hashes(idx, tmpdir)
+        assert fixed == 1
+        # Verify hash was added
+        with open(idx) as f:
+            data = json.load(f)
+        assert data["facts"][0]["source_hash"].startswith("sha256:")
+        print("PASS: test_fix_hashes")
+
+
+def test_empty_index():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        idx = os.path.join(tmpdir, "index.json")
+        with open(idx, "w") as f:
+            json.dump({"facts": []}, f)
+        results = check_staleness(idx, tmpdir)
+        assert results == []
+        print("PASS: test_empty_index")
+
+
+def test_compute_hash_nonexistent():
+    h = compute_file_hash("/nonexistent/path/file.py")
+    assert h is None
+    print("PASS: test_compute_hash_nonexistent")
+
+
+def run_all():
+    test_fresh_entry()
+    test_stale_entry()
+    test_missing_source()
+    test_no_hash()
+    test_no_source_field()
+    test_fix_hashes()
+    test_empty_index()
+    test_compute_hash_nonexistent()
+    print("\nAll 8 tests passed!")
+
+
+if __name__ == "__main__":
+    run_all()

test_sessions/session_failure.jsonl

@@ -0,0 +1,18 @@
+{"role": "user", "content": "Deploy the application to production"}
+{"role": "assistant", "content": "I'll deploy the application to production.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh deploy@prod-server 'cd /app && git pull && docker-compose up -d'"}}]}
+{"role": "tool", "content": "ssh: connect to host prod-server port 22: Connection refused"}
+{"role": "assistant", "content": "Connection refused. Let me check the server status.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ping -c 3 prod-server"}}]}
+{"role": "tool", "content": "PING prod-server (192.168.1.100): 56 data bytes\nRequest timeout for icmp_seq 0\nRequest timeout for icmp_seq 1\nRequest timeout for icmp_seq 2\n--- prod-server ping statistics ---\n3 packets transmitted, 0 packets received, 100.0% packet loss"}
+{"role": "assistant", "content": "The server appears to be down. Let me check if there's an alternative deployment method."}
+{"role": "user", "content": "Try using the VPS instead"}
+{"role": "assistant", "content": "I'll try deploying to the VPS.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh deploy@vps-server 'cd /app && git pull && docker-compose up -d'"}}]}
+{"role": "tool", "content": "Permission denied (publickey)."}
+{"role": "assistant", "content": "Permission denied. The SSH key might not be set up correctly. Let me check the SSH configuration.", "tool_calls": [{"function": "terminal", "arguments": {"command": "cat ~/.ssh/config"}}]}
+{"role": "tool", "content": "Host vps-server\n    HostName 167.99.126.228\n    User deploy\n    IdentityFile ~/.ssh/id_rsa_vps"}
+{"role": "assistant", "content": "The SSH config looks correct. Let me check if the key exists.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la ~/.ssh/id_rsa_vps"}}]}
+{"role": "tool", "content": "ls: /Users/user/.ssh/id_rsa_vps: No such file or directory"}
+{"role": "assistant", "content": "The SSH key doesn't exist. This is a pitfall - we need to generate the SSH key first."}
+{"role": "user", "content": "Generate a new SSH key for the VPS"}
+{"role": "assistant", "content": "I'll generate a new SSH key.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ssh-keygen -t rsa -b 4096 -f ~/.ssh/id_rsa_vps -N ''"}}]}
+{"role": "tool", "content": "Generating public/private rsa key pair.\nYour identification has been saved in /Users/user/.ssh/id_rsa_vps\nYour public key has been saved in /Users/user/.ssh/id_rsa_vps.pub\nThe key fingerprint is:\nSHA256:abc123... user@machine"}
+{"role": "assistant", "content": "SSH key generated. Now I need to add it to the VPS."}

test_sessions/session_partial.jsonl

@@ -0,0 +1,14 @@
+{"role": "user", "content": "Check the Gitea API for open issues"}
+{"role": "assistant", "content": "I'll check the Gitea API for open issues.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -H 'Authorization: token $GITEA_TOKEN' https://forge.alexanderwhitestone.com/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
+{"role": "tool", "content": "curl: (6) Could not resolve host: forge.alexanderwhitestone.com"}
+{"role": "assistant", "content": "DNS resolution failed. Let me check the network connectivity.", "tool_calls": [{"function": "terminal", "arguments": {"command": "nslookup forge.alexanderwhitestone.com"}}]}
+{"role": "tool", "content": "Server:		8.8.8.8\nAddress:	8.8.8.8#53\n\n** server can't find forge.alexanderwhitestone.com: NXDOMAIN"}
+{"role": "assistant", "content": "The domain doesn't resolve. This might be a DNS issue. Let me try using the IP address directly.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
+{"role": "tool", "content": "curl: (60) SSL certificate problem: self signed certificate"}
+{"role": "assistant", "content": "SSL certificate issue. The server is using a self-signed certificate. Let me try with -k flag to skip SSL verification.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -k -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/issues?state=open"}}]}
+{"role": "tool", "content": "[]"}
+{"role": "assistant", "content": "No open issues found. The API returned an empty array."}
+{"role": "user", "content": "Check if there are any pull requests"}
+{"role": "assistant", "content": "Let me check for pull requests.", "tool_calls": [{"function": "terminal", "arguments": {"command": "curl -k -H 'Authorization: token $GITEA_TOKEN' https://167.99.126.228/api/v1/repos/Timmy_Foundation/compounding-intelligence/pulls?state=open"}}]}
+{"role": "tool", "content": "[{"id": 20, "title": "feat: add harvester.py + session_reader.py — session knowledge extractor (closes #8)", "state": "open", "user": {"login": "Rockachopa"}, "created_at": "2026-04-14T17:28:20Z"}]"}
+{"role": "assistant", "content": "Found 1 open pull request: PR #20 - "feat: add harvester.py + session_reader.py — session knowledge extractor (closes #8)" by Rockachopa."}

test_sessions/session_patterns.jsonl

@@ -0,0 +1,10 @@
+{"role": "user", "content": "How do I deploy a new version of the application?"}
+{"role": "assistant", "content": "Here's the deployment process:\n1. Run tests: pytest\n2. Build Docker image: docker build -t app:latest .\n3. Push to registry: docker push registry.example.com/app:latest\n4. Update production: ssh prod 'cd /app && docker-compose pull && docker-compose up -d'\n5. Verify: curl https://app.example.com/health"}
+{"role": "user", "content": "What if tests fail?"}
+{"role": "assistant", "content": "If tests fail:\n1. Check the error logs: pytest -v\n2. Fix the failing tests\n3. Re-run tests: pytest\n4. If still failing, check recent changes: git log --oneline -10\n5. Consider reverting: git revert HEAD"}
+{"role": "user", "content": "What if the Docker build fails?"}
+{"role": "assistant", "content": "If Docker build fails:\n1. Check Dockerfile syntax: docker build --no-cache -t app:latest .\n2. Check for missing dependencies: cat requirements.txt\n3. Check disk space: df -h\n4. Clean up Docker: docker system prune -f\n5. Try building with verbose output: docker build --progress=plain -t app:latest ."}
+{"role": "user", "content": "What if the push to registry fails?"}
+{"role": "assistant", "content": "If push to registry fails:\n1. Check registry credentials: docker login registry.example.com\n2. Check registry space: curl https://registry.example.com/v2/_catalog\n3. Check image size: docker images app:latest\n4. Try tagging with version: docker tag app:latest registry.example.com/app:v1.0.0\n5. Push with version tag: docker push registry.example.com/app:v1.0.0"}
+{"role": "user", "content": "What if the production update fails?"}
+{"role": "assistant", "content": "If production update fails:\n1. Check SSH connection: ssh prod 'echo connected'\n2. Check disk space on prod: ssh prod 'df -h'\n3. Check Docker status: ssh prod 'docker ps -a'\n4. Check logs: ssh prod 'docker-compose logs --tail=100'\n5. Rollback: ssh prod 'cd /app && git checkout HEAD~1 && docker-compose up -d'"}

test_sessions/session_questions.jsonl

@@ -0,0 +1,12 @@
+{"role": "user", "content": "I need to implement a new feature for the application"}
+{"role": "assistant", "content": "I can help you implement a new feature. What feature would you like to add?"}
+{"role": "user", "content": "I want to add user authentication"}
+{"role": "assistant", "content": "User authentication is a good feature. I have a few questions:\n1. What authentication method do you prefer? (JWT, OAuth, Session-based)\n2. Do you need social login? (Google, GitHub, etc.)\n3. What user data do you need to store?\n4. Do you need role-based access control?\n5. What's your database? (PostgreSQL, MySQL, SQLite)"}
+{"role": "user", "content": "I prefer JWT, no social login, just email and password, no roles, PostgreSQL"}
+{"role": "assistant", "content": "Great choices. Here's the implementation plan:\n1. Create user model with email and password hash\n2. Create JWT token generation and validation\n3. Create login endpoint: POST /api/auth/login\n4. Create register endpoint: POST /api/auth/register\n5. Create middleware for protected routes\n6. Add password hashing with bcrypt\n7. Add rate limiting for login attempts\n8. Add password reset functionality\n9. Add email verification\n10. Test all endpoints"}
+{"role": "user", "content": "What about password reset?"}
+{"role": "assistant", "content": "For password reset:\n1. Create reset token table\n2. Create forgot password endpoint: POST /api/auth/forgot-password\n3. Send reset email with token\n4. Create reset password endpoint: POST /api/auth/reset-password\n5. Validate reset token and expiration\n6. Update password and delete token\n7. Send confirmation email"}
+{"role": "user", "content": "What about email verification?"}
+{"role": "assistant", "content": "For email verification:\n1. Add email_verified field to user model\n2. Create verification token table\n3. Send verification email on registration\n4. Create verify email endpoint: GET /api/auth/verify-email?token=...\n5. Validate token and update email_verified\n6. Add middleware to check email_verified for certain routes\n7. Add resend verification email endpoint"}
+{"role": "user", "content": "What about rate limiting?"}
+{"role": "assistant", "content": "For rate limiting:\n1. Use Redis for rate limit storage\n2. Create rate limit middleware\n3. Set limits: 5 login attempts per minute, 3 password resets per hour\n4. Return 429 Too Many Requests when limit exceeded\n5. Add X-RateLimit headers to responses\n6. Log rate limit violations\n7. Add whitelist for trusted IPs"}

test_sessions/session_success.jsonl

@@ -0,0 +1,13 @@
+{"role": "user", "content": "Clone the repo at forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence"}
+{"role": "assistant", "content": "I'll clone the repository for you.", "tool_calls": [{"function": "terminal", "arguments": {"command": "git clone https://forge.alexanderwhitestone.com/Timmy_Foundation/compounding-intelligence.git"}}]}
+{"role": "tool", "content": "Cloning into 'compounding-intelligence'...\nremote: Enumerating objects: 15, done.\nremote: Counting objects: 100% (15/15), done.\nremote: Compressing objects: 100% (12/12), done.\nremote: Total 15 (delta 2), reused 0 (delta 0), pack-reused 0\nReceiving objects: 100% (15/15), done.\nResolving deltas: 100% (2/2), done."}
+{"role": "assistant", "content": "Repository cloned successfully. Let me check the structure.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la compounding-intelligence/"}}]}
+{"role": "tool", "content": "total 8\ndrwxr-xr-x   5 user  staff  160 Apr 14 17:21 .\ndrwxr-xr-x  12 user  staff  384 Apr 14 17:21 ..\ndrwxr-xr-x  13 user  staff  416 Apr 14 17:21 .git\n-rw-r--r--   1 user  staff  1234 Apr 14 17:21 README.md\ndrwxr-xr-x   3 user  staff   96 Apr 14 17:21 knowledge\n-rw-r--r--   1 user  staff   456 Apr 14 17:21 metrics\ndrwxr-xr-x   4 user  staff  128 Apr 14 17:21 scripts\ndrwxr-xr-x   3 user  staff   96 Apr 14 17:21 templates"}
+{"role": "user", "content": "What files are in the templates directory?"}
+{"role": "assistant", "content": "Let me check the templates directory.", "tool_calls": [{"function": "terminal", "arguments": {"command": "ls -la compounding-intelligence/templates/"}}]}
+{"role": "tool", "content": "total 0\ndrwxr-xr-x  3 user  staff   96 Apr 14 17:21 .\ndrwxr-xr-x  5 user  staff  160 Apr 14 17:21 ..\n-rw-r--r--  1 user  staff    0 Apr 14 17:21 .gitkeep"}
+{"role": "assistant", "content": "The templates directory currently only contains a .gitkeep file. No templates have been added yet."}
+{"role": "user", "content": "Create a harvest-prompt.md template in the templates directory."}
+{"role": "assistant", "content": "I'll create the harvest-prompt.md template for you.", "tool_calls": [{"function": "terminal", "arguments": {"command": "cat > compounding-intelligence/templates/harvest-prompt.md << 'EOF'\n# Knowledge Extraction Prompt\n\nExtract knowledge from session transcripts.\nEOF"}}]}
+{"role": "tool", "content": ""}
+{"role": "assistant", "content": "Template created successfully. The harvest-prompt.md file is now in the templates directory."}

tests/test_perf_bottleneck_finder.py

@@ -0,0 +1,319 @@
+#!/usr/bin/env python3
+"""
+Tests for Performance Bottleneck Finder.
+"""
+
+import json
+import os
+import tempfile
+import textwrap
+from pathlib import Path
+
+import pytest
+
+# Add scripts to path
+import sys
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "scripts"))
+
+from perf_bottleneck_finder import (
+    Bottleneck,
+    PerfReport,
+    find_slow_tests_by_scan,
+    analyze_build_artifacts,
+    analyze_makefile_targets,
+    find_slow_imports,
+    generate_report,
+    format_markdown,
+    severity_sort_key,
+)
+
+
+class TestBottleneck:
+    """Test Bottleneck dataclass."""
+
+    def test_creation(self):
+        b = Bottleneck(
+            category="test",
+            name="test_foo",
+            duration_s=5.0,
+            severity="warning",
+            recommendation="Mock it"
+        )
+        assert b.category == "test"
+        assert b.name == "test_foo"
+        assert b.duration_s == 5.0
+        assert b.severity == "warning"
+        assert b.recommendation == "Mock it"
+        assert b.file_path is None
+        assert b.line_number is None
+
+    def test_with_location(self):
+        b = Bottleneck(
+            category="test",
+            name="test_bar",
+            duration_s=2.0,
+            severity="info",
+            recommendation="Consider",
+            file_path="tests/test_bar.py",
+            line_number=42
+        )
+        assert b.file_path == "tests/test_bar.py"
+        assert b.line_number == 42
+
+    def test_to_dict(self):
+        b = Bottleneck("test", "x", 1.0, "info", "y")
+        d = b.__dict__
+        assert "category" in d
+        assert "duration_s" in d
+
+
+class TestPerfReport:
+    """Test PerfReport dataclass."""
+
+    def test_creation(self):
+        report = PerfReport(
+            timestamp="2026-01-01T00:00:00Z",
+            repo_path="/tmp/repo"
+        )
+        assert report.timestamp == "2026-01-01T00:00:00Z"
+        assert report.bottlenecks == []
+        assert report.summary == {}
+
+    def test_to_dict(self):
+        report = PerfReport(
+            timestamp="2026-01-01T00:00:00Z",
+            repo_path="/tmp/repo",
+            bottlenecks=[Bottleneck("test", "x", 1.0, "info", "y")]
+        )
+        d = report.to_dict()
+        assert "bottlenecks" in d
+        assert len(d["bottlenecks"]) == 1
+
+
+class TestSeveritySort:
+    """Test severity sorting."""
+
+    def test_critical_first(self):
+        items = [
+            Bottleneck("test", "a", 1.0, "info", ""),
+            Bottleneck("test", "b", 0.5, "critical", ""),
+            Bottleneck("test", "c", 2.0, "warning", ""),
+        ]
+        items.sort(key=severity_sort_key)
+        assert items[0].severity == "critical"
+        assert items[1].severity == "warning"
+        assert items[2].severity == "info"
+
+    def test_duration_within_severity(self):
+        items = [
+            Bottleneck("test", "slow", 10.0, "warning", ""),
+            Bottleneck("test", "fast", 1.0, "warning", ""),
+        ]
+        items.sort(key=severity_sort_key)
+        assert items[0].name == "slow"  # Higher duration first within same severity
+
+
+class TestSlowTestScan:
+    """Test slow test pattern scanning."""
+
+    def test_finds_sleep(self, tmp_path):
+        test_file = tmp_path / "test_sleepy.py"
+        test_file.write_text(textwrap.dedent('''
+            import time
+
+            def test_slow():
+                time.sleep(5)
+                assert True
+        '''))
+
+        bottlenecks = find_slow_tests_by_scan(str(tmp_path))
+        assert len(bottlenecks) >= 1
+        assert any("sleep" in b.recommendation.lower() for b in bottlenecks)
+
+    def test_finds_http_calls(self, tmp_path):
+        test_file = tmp_path / "test_http.py"
+        test_file.write_text(textwrap.dedent('''
+            import requests
+
+            def test_api():
+                resp = requests.get("https://example.com")
+                assert resp.status_code == 200
+        '''))
+
+        bottlenecks = find_slow_tests_by_scan(str(tmp_path))
+        assert len(bottlenecks) >= 1
+        assert any("HTTP" in b.recommendation or "mock" in b.recommendation.lower() for b in bottlenecks)
+
+    def test_skips_non_test_files(self, tmp_path):
+        src_file = tmp_path / "main.py"
+        src_file.write_text("import time\ntime.sleep(10)\n")
+
+        bottlenecks = find_slow_tests_by_scan(str(tmp_path))
+        assert len(bottlenecks) == 0
+
+    def test_handles_missing_dir(self):
+        bottlenecks = find_slow_tests_by_scan("/nonexistent/path")
+        assert bottlenecks == []
+
+    def test_file_path_populated(self, tmp_path):
+        test_file = tmp_path / "test_example.py"
+        test_file.write_text("import time\n\ndef test_it():\n    time.sleep(2)\n")
+
+        bottlenecks = find_slow_tests_by_scan(str(tmp_path))
+        assert len(bottlenecks) >= 1
+        assert bottlenecks[0].file_path is not None
+        assert bottlenecks[0].line_number is not None
+
+
+class TestBuildArtifacts:
+    """Test build artifact analysis."""
+
+    def test_finds_large_node_modules(self, tmp_path):
+        nm = tmp_path / "node_modules"
+        nm.mkdir()
+        # Create a file > 10MB
+        big_file = nm / "big.txt"
+        big_file.write_bytes(b"x" * (11 * 1024 * 1024))
+
+        bottlenecks = analyze_build_artifacts(str(tmp_path))
+        assert len(bottlenecks) >= 1
+        assert any("node_modules" in b.name for b in bottlenecks)
+
+    def test_ignores_small_dirs(self, tmp_path):
+        nm = tmp_path / "node_modules"
+        nm.mkdir()
+        small_file = nm / "small.txt"
+        small_file.write_bytes(b"x" * 100)
+
+        bottlenecks = analyze_build_artifacts(str(tmp_path))
+        assert not any("node_modules" in b.name for b in bottlenecks)
+
+    def test_finds_pycache(self, tmp_path):
+        cache = tmp_path / "__pycache__"
+        cache.mkdir()
+        big_file = cache / "big.pyc"
+        big_file.write_bytes(b"x" * (11 * 1024 * 1024))
+
+        bottlenecks = analyze_build_artifacts(str(tmp_path))
+        assert any("__pycache__" in b.name for b in bottlenecks)
+
+
+class TestMakefileAnalysis:
+    """Test Makefile analysis."""
+
+    def test_finds_pip_install(self, tmp_path):
+        makefile = tmp_path / "Makefile"
+        makefile.write_text(textwrap.dedent('''
+            install:
+                pip install -r requirements.txt
+
+            test:
+                pytest
+        '''))
+
+        bottlenecks = analyze_makefile_targets(str(tmp_path))
+        assert len(bottlenecks) >= 1
+
+    def test_no_makefile(self, tmp_path):
+        bottlenecks = analyze_makefile_targets(str(tmp_path))
+        assert bottlenecks == []
+
+
+class TestImportAnalysis:
+    """Test heavy import detection."""
+
+    def test_finds_pandas(self, tmp_path):
+        src = tmp_path / "analysis.py"
+        src.write_text("import pandas as pd\n")
+
+        bottlenecks = find_slow_imports(str(tmp_path))
+        assert len(bottlenecks) >= 1
+        assert any("pandas" in b.name for b in bottlenecks)
+
+    def test_finds_torch(self, tmp_path):
+        src = tmp_path / "model.py"
+        src.write_text("import torch\n")
+
+        bottlenecks = find_slow_imports(str(tmp_path))
+        assert any("torch" in b.name for b in bottlenecks)
+
+    def test_skips_light_imports(self, tmp_path):
+        src = tmp_path / "utils.py"
+        src.write_text("import json\nimport os\nimport sys\n")
+
+        bottlenecks = find_slow_imports(str(tmp_path))
+        assert len(bottlenecks) == 0
+
+
+class TestGenerateReport:
+    """Test full report generation."""
+
+    def test_empty_repo(self, tmp_path):
+        report = generate_report(str(tmp_path))
+        assert report.summary["total_bottlenecks"] >= 0
+        assert "critical" in report.summary
+        assert "warning" in report.summary
+
+    def test_with_findings(self, tmp_path):
+        # Create a test file with issues
+        test_file = tmp_path / "test_slow.py"
+        test_file.write_text(textwrap.dedent('''
+            import time
+            import requests
+
+            def test_sleepy():
+                time.sleep(3)
+
+            def test_http():
+                requests.get("https://example.com")
+        '''))
+
+        report = generate_report(str(tmp_path))
+        assert report.summary["total_bottlenecks"] >= 2
+        assert len(report.bottlenecks) > 0
+
+    def test_summary_categories(self, tmp_path):
+        report = generate_report(str(tmp_path))
+        assert "by_category" in report.summary
+
+
+class TestMarkdownReport:
+    """Test markdown output."""
+
+    def test_format(self):
+        report = PerfReport(
+            timestamp="2026-01-01T00:00:00Z",
+            repo_path="/tmp/repo",
+            bottlenecks=[
+                Bottleneck("test", "slow_test", 5.0, "critical", "Fix it")
+            ],
+            summary={
+                "total_bottlenecks": 1,
+                "critical": 1,
+                "warning": 0,
+                "info": 0,
+                "estimated_total_slowdown_s": 5.0,
+                "by_category": {"test": 1},
+            }
+        )
+        md = format_markdown(report)
+        assert "# Performance Bottleneck Report" in md
+        assert "slow_test" in md
+        assert "🔴" in md
+        assert "Fix it" in md
+
+    def test_empty_report(self):
+        report = PerfReport(
+            timestamp="2026-01-01T00:00:00Z",
+            repo_path="/tmp/repo",
+            summary={
+                "total_bottlenecks": 0,
+                "critical": 0,
+                "warning": 0,
+                "info": 0,
+                "estimated_total_slowdown_s": 0,
+                "by_category": {},
+            }
+        )
+        md = format_markdown(report)
+        assert "Total bottlenecks:** 0" in md