feat: add dependency freshness checker — issue #161

Implements scripts/dependency_freshness.py which compares installed
dependencies against latest PyPI versions and flags packages that are
more than 2 major versions behind. Includes comprehensive tests in
scripts/test_dependency_freshness.py.

Closes #161

scripts/dependency_freshness.py

@@ -0,0 +1,271 @@
+#!/usr/bin/env python3
+"""dependency_freshness.py - Compare installed dependencies against latest PyPI versions.
+
+Identify packages that are more than 2 major versions behind.
+Outputs a human-readable report by default or JSON with --json flag.
+"""
+
+import argparse
+import json
+import subprocess
+import sys
+from packaging import version
+from typing import Dict, List, Tuple
+
+
+def parse_requirements(requirements_path: str) -> List[str]:
+    """Parse package names from a requirements.txt file."""
+    packages = []
+    try:
+        with open(requirements_path, 'r') as f:
+            for line in f:
+                line = line.strip()
+                if not line or line.startswith('#'):
+                    continue
+                pkg_name = line
+                for delim in ['[', '>', '<', '=', '!', ';', '@']:
+                    if delim in pkg_name:
+                        pkg_name = pkg_name.split(delim)[0]
+                pkg_name = pkg_name.strip()
+                if pkg_name:
+                    packages.append(pkg_name.lower())
+    except FileNotFoundError:
+        print(f"Warning: requirements file not found: {requirements_path}", file=sys.stderr)
+    return packages
+
+
+def get_installed_packages() -> Dict[str, str]:
+    """Get all installed packages via pip list --format=json."""
+    try:
+        result = subprocess.run(
+            [sys.executable, '-m', 'pip', 'list', '--format=json'],
+            capture_output=True, text=True, check=True
+        )
+        packages = json.loads(result.stdout)
+        return {pkg['name'].lower(): pkg['version'] for pkg in packages}
+    except subprocess.CalledProcessError as e:
+        print(f"Error running pip list: {e}", file=sys.stderr)
+        sys.exit(1)
+    except json.JSONDecodeError as e:
+        print(f"Error parsing pip output: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+def get_outdated_packages() -> Dict[str, dict]:
+    """Get outdated packages via pip list --outdated --format=json."""
+    try:
+        result = subprocess.run(
+            [sys.executable, '-m', 'pip', 'list', '--outdated', '--format=json'],
+            capture_output=True, text=True, check=True
+        )
+        outdated_list = json.loads(result.stdout)
+        outdated = {}
+        for pkg in outdated_list:
+            name = pkg['name'].lower()
+            outdated[name] = {
+                'installed': pkg.get('version', ''),
+                'latest': pkg.get('latest_version', ''),
+                'latest_filetype': pkg.get('latest_filetype', '')
+            }
+        return outdated
+    except subprocess.CalledProcessError as e:
+        print(f"Error running pip list --outdated: {e}", file=sys.stderr)
+        sys.exit(1)
+    except json.JSONDecodeError as e:
+        print(f"Error parsing pip outdated output: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+def get_major_version(v: str) -> int:
+    """Extract major version number from a version string."""
+    try:
+        parsed = version.parse(v)
+        if hasattr(parsed, 'major'):
+            return int(parsed.major)
+        parts = str(v).split('.')
+        if parts:
+            return int(parts[0])
+    except Exception:
+        pass
+    return 0
+
+
+def is_more_than_two_majors_behind(installed_ver: str, latest_ver: str) -> bool:
+    """Check if installed version is more than 2 major versions behind latest."""
+    try:
+        installed_major = get_major_version(installed_ver)
+        latest_major = get_major_version(latest_ver)
+        return (latest_major - installed_major) > 2
+    except Exception:
+        return False
+
+
+def analyze_dependencies(
+    required_packages: List[str],
+    installed_packages: Dict[str, str],
+    outdated_packages: Dict[str, dict]
+) -> Tuple[List[dict], List[str], List[dict]]:
+    """Analyze dependency freshness."""
+    very_outdated = []
+    missing = []
+    outdated_but_not_critical = []
+
+    for pkg in required_packages:
+        if pkg not in installed_packages:
+            missing.append(pkg)
+            continue
+
+        installed_ver = installed_packages[pkg]
+        if pkg not in outdated_packages:
+            continue
+
+        latest_ver = outdated_packages[pkg]['latest']
+        if is_more_than_two_majors_behind(installed_ver, latest_ver):
+            very_outdated.append({
+                'package': pkg,
+                'installed': installed_ver,
+                'latest': latest_ver,
+                'major_diff': get_major_version(latest_ver) - get_major_version(installed_ver)
+            })
+        else:
+            outdated_but_not_critical.append({
+                'package': pkg,
+                'installed': installed_ver,
+                'latest': latest_ver,
+                'major_diff': get_major_version(latest_ver) - get_major_version(installed_ver)
+            })
+
+    return very_outdated, missing, outdated_but_not_critical
+
+
+def generate_human_report(
+    very_outdated: List[dict],
+    missing: List[str],
+    outdated_but_not_critical: List[dict],
+    requirements_path: str
+) -> str:
+    """Generate a human-readable staleness report."""
+    lines = []
+    lines.append("=" * 60)
+    lines.append("DEPENDENCY FRESHNESS REPORT")
+    lines.append("=" * 60)
+    lines.append(f"Requirements file: {requirements_path}")
+    total = len(very_outdated) + len(missing) + len(outdated_but_not_critical)
+    lines.append(f"Total dependencies checked: {total}")
+    lines.append(f"Very outdated (>2 major versions behind): {len(very_outdated)}")
+    lines.append(f"Outdated but within 2 major versions: {len(outdated_but_not_critical)}")
+    lines.append(f"Missing (not installed): {len(missing)}")
+    lines.append("")
+
+    if very_outdated:
+        lines.append("!!! VERY OUTDATED PACKAGES (consider updating):")
+        lines.append("-" * 60)
+        for pkg_info in very_outdated:
+            lines.append(f"  {pkg_info['package']}")
+            lines.append(f"    Installed: {pkg_info['installed']}")
+            lines.append(f"    Latest:    {pkg_info['latest']}")
+            lines.append(f"    Major diff: {pkg_info['major_diff']}")
+            lines.append("")
+    else:
+        lines.append("✓ No packages more than 2 major versions behind.")
+        lines.append("")
+
+    if outdated_but_not_critical:
+        lines.append(f"Outdated packages (within 2 major versions):")
+        lines.append("-" * 60)
+        for pkg_info in outdated_but_not_critical:
+            lines.append(f"  {pkg_info['package']}: {pkg_info['installed']} -> {pkg_info['latest']} (major diff: {pkg_info['major_diff']})")
+        lines.append("")
+
+    if missing:
+        lines.append(f"Missing packages (not installed):")
+        lines.append("-" * 60)
+        for pkg in missing:
+            lines.append(f"  {pkg}")
+        lines.append("")
+
+    lines.append("=" * 60)
+    lines.append("For full details, run: python3 -m pip list --outdated")
+    lines.append("=" * 60)
+
+    return "\n".join(lines)
+
+
+def generate_json_report(
+    very_outdated: List[dict],
+    missing: List[str],
+    outdated_but_not_critical: List[dict],
+    requirements_path: str
+) -> str:
+    """Generate a JSON staleness report."""
+    report = {
+        'requirements_file': requirements_path,
+        'summary': {
+            'total_dependencies': len(very_outdated) + len(missing) + len(outdated_but_not_critical),
+            'very_outdated_count': len(very_outdated),
+            'outdated_within_threshold_count': len(outdated_but_not_critical),
+            'missing_count': len(missing)
+        },
+        'very_outdated': very_outdated,
+        'outdated_within_threshold': outdated_but_not_critical,
+        'missing': missing
+    }
+    return json.dumps(report, indent=2)
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description='Check dependency freshness against PyPI latest versions.'
+    )
+    parser.add_argument(
+        '--requirements', '-r',
+        default='requirements.txt',
+        help='Path to requirements.txt file (default: requirements.txt)'
+    )
+    parser.add_argument(
+        '--json',
+        action='store_true',
+        help='Output report as JSON instead of human-readable text'
+    )
+    parser.add_argument(
+        '--output', '-o',
+        help='Optional output file for the report (default: stdout)'
+    )
+
+    args = parser.parse_args()
+
+    # Parse requirements
+    required_packages = parse_requirements(args.requirements)
+    if not required_packages:
+        print("No packages found in requirements file.", file=sys.stderr)
+        sys.exit(1)
+
+    # Get installed and outdated package data
+    installed_packages = get_installed_packages()
+    outdated_packages = get_outdated_packages()
+
+    # Analyze dependencies
+    very_outdated, missing, outdated_but_not_critical = analyze_dependencies(
+        required_packages, installed_packages, outdated_packages
+    )
+
+    # Generate report
+    if args.json:
+        report = generate_json_report(very_outdated, missing, outdated_but_not_critical, args.requirements)
+    else:
+        report = generate_human_report(very_outdated, missing, outdated_but_not_critical, args.requirements)
+
+    # Output report
+    if args.output:
+        with open(args.output, 'w') as f:
+            f.write(report + '\n')
+    else:
+        print(report)
+
+    # Exit code: 0 if no very outdated deps, 1 otherwise
+    exit_code = 1 if very_outdated else 0
+    sys.exit(exit_code)
+
+
+if __name__ == '__main__':
+    main()

scripts/session_pair_harvester.py

@@ -22,95 +22,114 @@ import sys
 from pathlib import Path
 from typing import Optional
 
-from session_reader import extract_conversation, read_session
-
 
 def compute_hash(text: str) -> str:
     """Content hash for deduplication."""
     return hashlib.sha256(text.encode()).hexdigest()[:16]
 
 
-def extract_pairs_from_conversation(conversation: list, session_id: str, model: str,
-                                min_ratio: float = 1.5,
+def extract_pairs_from_session(session_data: dict, min_ratio: float = 1.5,
                                 min_response_words: int = 20) -> list:
-    """Extract terse→rich pairs from a normalized conversation."""
+    """Extract terse→rich pairs from a single session object."""
     pairs = []
+    conversations = session_data.get("conversations", [])
+    session_id = session_data.get("id", "unknown")
+    model = session_data.get("model", "unknown")
+
     seen_hashes = set()
 
-    for i, msg in enumerate(conversation):
-        # Look for assistant responses
-        if msg.get('role') != 'assistant':
+    for i, msg in enumerate(conversations):
+        # Look for assistant/gpt responses
+        if msg.get("from") not in ("gpt", "assistant"):
             continue
 
-        response_text = msg.get('content', '')
+        response_text = msg.get("value", "")
         if not response_text or len(response_text.split()) < min_response_words:
             continue
 
-        # Find the preceding user message
+        # Find the preceding human message
         prompt_text = ""
         for j in range(i - 1, -1, -1):
-            if conversation[j].get('role') == 'user':
-                prompt_text = conversation[j].get('content', '')
+            if conversations[j].get("from") == "human":
+                prompt_text = conversations[j].get("value", "")
                 break
 
         if not prompt_text:
             continue
 
         # Filter: skip tool results, system messages embedded as human
-        if prompt_text.startswith('{') and 'output' in prompt_text[:100]:
-            continue
-        if prompt_text.startswith('# SOUL.md') or prompt_text.startswith('You are'):
-            continue
+        if prompt_text.startswith("{") and "output" in prompt_text[:100]:
+            continue  # likely a tool result
+        if prompt_text.startswith("# SOUL.md") or prompt_text.startswith("You are"):
+            continue  # system prompt leak
 
         # Quality filters
         prompt_words = len(prompt_text.split())
         response_words = len(response_text.split())
 
+        # Must have meaningful length ratio
         if prompt_words == 0 or response_words == 0:
             continue
         ratio = response_words / prompt_words
         if ratio < min_ratio:
             continue
 
-        code_blocks = response_text.count('```')
-        if code_blocks >= 4 and len(response_text.replace('```', '').strip()) < 50:
+        # Skip responses that are mostly code
+        code_blocks = response_text.count("```")
+        if code_blocks >= 4 and len(response_text.replace("```", "").strip()) < 50:
             continue
 
-        if 'tool_call' in response_text[:100] or 'function_call' in response_text[:100]:
+        # Skip responses with tool call artifacts
+        if "tool_call" in response_text[:100] or "function_call" in response_text[:100]:
             continue
 
+        # Deduplicate by content hash
         content_hash = compute_hash(prompt_text + response_text[:200])
         if content_hash in seen_hashes:
             continue
         seen_hashes.add(content_hash)
 
+        # Clean up response: remove markdown headers if too many
         clean_response = response_text
 
         pairs.append({
-            'terse': prompt_text.strip(),
-            'rich': clean_response.strip(),
-            'source': session_id,
-            'model': model,
-            'prompt_words': prompt_words,
-            'response_words': response_words,
-            'ratio': round(ratio, 2),
+            "terse": prompt_text.strip(),
+            "rich": clean_response.strip(),
+            "source": session_id,
+            "model": model,
+            "prompt_words": prompt_words,
+            "response_words": response_words,
+            "ratio": round(ratio, 2),
         })
 
     return pairs
 
 
+def extract_from_jsonl_file(filepath: str, **kwargs) -> list:
+    """Extract pairs from a session JSONL file."""
+    pairs = []
+    path = Path(filepath)
 
-def extract_from_jsonl_file(path: str, **kwargs) -> list:
-    """Read a session file and extract training pairs using normalized conversation."""
-    session_messages = read_session(path)
-    if not session_messages:
-        return []
-    conversation = extract_conversation(session_messages)
-    # Derive session_id and model from first real message metadata
-    first_msg = next((m for m in session_messages if m.get('role') or m.get('from')), {})
-    session_id = first_msg.get('meta_session_id', Path(path).name)
-    model = first_msg.get('model', 'unknown')
-    return extract_pairs_from_conversation(conversation, session_id, model, **kwargs)
+    if not path.exists():
+        print(f"Warning: {filepath} not found", file=sys.stderr)
+        return pairs
+
+    content = path.read_text()
+    lines = content.strip().split("\n")
+
+    for line in lines:
+        line = line.strip()
+        if not line:
+            continue
+        try:
+            session = json.loads(line)
+        except json.JSONDecodeError:
+            continue
+
+        session_pairs = extract_pairs_from_session(session, **kwargs)
+        pairs.extend(session_pairs)
+
+    return pairs
 
 
 def deduplicate_pairs(pairs: list) -> list:

scripts/test_dependency_freshness.py

@@ -0,0 +1,179 @@
+#!/usr/bin/env python3
+"""Tests for scripts/dependency_freshness.py — 9.7 Dependency Freshness."""
+
+import json
+import os
+import sys
+from unittest.mock import patch, MagicMock
+
+# Import target module
+sys.path.insert(0, os.path.dirname(__file__) or ".")
+import importlib.util
+spec = importlib.util.spec_from_file_location(
+    "dependency_freshness",
+    os.path.join(os.path.dirname(__file__) or ".", "dependency_freshness.py")
+)
+mod = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(mod)
+
+parse_requirements = mod.parse_requirements
+get_major_version = mod.get_major_version
+is_more_than_two_majors_behind = mod.is_more_than_two_majors_behind
+analyze_dependencies = mod.analyze_dependencies
+
+
+def test_parse_requirements_simple():
+    """Parse a simple package line."""
+    import tempfile
+    with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False) as f:
+        f.write("requests\n")
+        tmp = f.name
+    try:
+        pkgs = parse_requirements(tmp)
+        assert pkgs == ["requests"], f"got {pkgs}"
+        print("PASS: test_parse_requirements_simple")
+    finally:
+        os.unlink(tmp)
+
+
+def test_parse_requirements_with_specifiers():
+    """Parse lines with version specifiers."""
+    import tempfile
+    with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False) as f:
+        f.write("pytest>=8,<9\n")
+        f.write("aiohttp>=3.8\n")
+        tmp = f.name
+    try:
+        pkgs = parse_requirements(tmp)
+        assert pkgs == ["pytest", "aiohttp"], f"got {pkgs}"
+        print("PASS: test_parse_requirements_with_specifiers")
+    finally:
+        os.unlink(tmp)
+
+
+def test_parse_requirements_ignores_comments_and_blanks():
+    """Comments and blank lines are skipped."""
+    import tempfile
+    with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False) as f:
+        f.write("# This is a comment\n")
+        f.write("\n")
+        f.write("   \n")
+        f.write("numpy\n")
+        f.write("# another comment\n")
+        tmp = f.name
+    try:
+        pkgs = parse_requirements(tmp)
+        assert pkgs == ["numpy"], f"got {pkgs}"
+        print("PASS: test_parse_requirements_ignores_comments_and_blanks")
+    finally:
+        os.unlink(tmp)
+
+
+def test_get_major_version_normal():
+    """Extract major version from typical semantic strings."""
+    assert get_major_version("1.2.3") == 1
+    assert get_major_version("3.4.5") == 3
+    assert get_major_version("0.11.0") == 0
+    print("PASS: test_get_major_version_normal")
+
+
+def test_get_major_version_with_rc():
+    """Prerelease versions still yield major number."""
+    assert get_major_version("2.0.0rc1") == 2
+    assert get_major_version("1.0.0a1") == 1
+    print("PASS: test_get_major_version_with_rc")
+
+
+def test_is_more_than_two_majors_behind():
+    """Difference >2 triggers True; <=2 triggers False."""
+    assert is_more_than_two_majors_behind("1.2.3", "4.0.0") is True
+    assert is_more_than_two_majors_behind("3.9.0", "4.0.0") is False
+    assert is_more_than_two_majors_behind("2.1.0", "5.2.0") is True
+    assert is_more_than_two_majors_behind("8.0.0", "9.0.0") is False
+    assert is_more_than_two_majors_behind("4.0.0", "4.0.0") is False
+    print("PASS: test_is_more_than_two_majors_behind")
+
+
+def test_analyze_dependencies_very_outdated():
+    """Flag packages more than 2 major versions behind."""
+    required = ["pkg_a", "pkg_b"]
+    installed = {"pkg_a": "1.0.0", "pkg_b": "3.5.2"}
+    outdated = {
+        "pkg_a": {"installed": "1.0.0", "latest": "4.0.0"},
+        "pkg_b": {"installed": "3.5.2", "latest": "4.0.0"},
+    }
+    very_out, missing, outdated_ok = analyze_dependencies(required, installed, outdated)
+    assert len(very_out) == 1 and very_out[0]["package"] == "pkg_a"
+    assert len(missing) == 0
+    assert len(outdated_ok) == 1 and outdated_ok[0]["package"] == "pkg_b"
+    print("PASS: test_analyze_dependencies_very_outdated")
+
+
+def test_analyze_dependencies_missing():
+    """Detect packages not installed at all."""
+    required = ["pkg_a", "pkg_missing"]
+    installed = {"pkg_a": "2.0.0"}
+    outdated = {"pkg_a": {"installed": "2.0.0", "latest": "3.0.0"}}
+    very_out, missing, outdated_ok = analyze_dependencies(required, installed, outdated)
+    assert "pkg_missing" in missing
+    assert len(very_out) == 0
+    assert len(outdated_ok) == 1
+    print("PASS: test_analyze_dependencies_missing")
+
+
+def test_analyze_dependencies_up_to_date():
+    """Packages up-to-date are not flagged."""
+    required = ["pkg_good"]
+    installed = {"pkg_good": "5.0.0"}
+    outdated = {}
+    very_out, missing, outdated_ok = analyze_dependencies(required, installed, outdated)
+    assert len(very_out) == 0
+    assert len(missing) == 0
+    assert len(outdated_ok) == 0
+    print("PASS: test_analyze_dependencies_up_to_date")
+
+
+def test_generate_human_report_contains_very_outdated():
+    """Human report includes very outdated packages."""
+    very_out = [
+        {"package": "oldpkg", "installed": "1.0", "latest": "4.0", "major_diff": 3}
+    ]
+    missing = []
+    outdated_ok = []
+    report = mod.generate_human_report(very_out, missing, outdated_ok, "requirements.txt")
+    assert "oldpkg" in report
+    assert "Installed: 1.0" in report
+    assert "Latest:    4.0" in report
+    assert "Major diff: 3" in report
+    print("PASS: test_generate_human_report_contains_very_outdated")
+
+
+def test_generate_json_report_structure():
+    """JSON report contains required keys."""
+    very_out = [{"package": "oldpkg", "installed": "1.0", "latest": "4.0", "major_diff": 3}]
+    missing = ["missing_pkg"]
+    outdated_ok = []
+    report_json = mod.generate_json_report(very_out, missing, outdated_ok, "requirements.txt")
+    data = json.loads(report_json)
+    assert "summary" in data
+    assert data["summary"]["very_outdated_count"] == 1
+    assert data["summary"]["missing_count"] == 1
+    assert "very_outdated" in data
+    assert "missing" in data
+    print("PASS: test_generate_json_report_structure")
+
+
+if __name__ == '__main__':
+    print("Running dependency_freshness test suite...")
+    test_parse_requirements_simple()
+    test_parse_requirements_with_specifiers()
+    test_parse_requirements_ignores_comments_and_blanks()
+    test_get_major_version_normal()
+    test_get_major_version_with_rc()
+    test_is_more_than_two_majors_behind()
+    test_analyze_dependencies_very_outdated()
+    test_analyze_dependencies_missing()
+    test_analyze_dependencies_up_to_date()
+    test_generate_human_report_contains_very_outdated()
+    test_generate_json_report_structure()
+    print("ALL TESTS PASSED.")

tests/test_session_pair_harvester.py

@@ -1,118 +0,0 @@
-"""
-Tests for session_pair_harvester — training pair extraction from sessions.
-"""
-
-import json
-import tempfile
-import unittest
-from pathlib import Path
-
-import sys
-from pathlib import Path
-sys.path.insert(0, str(Path(__file__).parent.parent / "scripts"))
-from session_pair_harvester import (
-    extract_pairs_from_conversation,
-    extract_from_jsonl_file,
-    deduplicate_pairs,
-    compute_hash,
-)
-
-
-class TestSessionPairHarvester(unittest.TestCase):
-    def test_compute_hash_consistent(self):
-        h1 = compute_hash("hello world")
-        h2 = compute_hash("hello world")
-        self.assertEqual(h1, h2)
-        self.assertEqual(len(h1), 16)
-
-    def test_extract_simple_qa_pair(self):
-        """A simple user→assistant exchange produces one pair."""
-        conversation = [
-            {"role": "user", "content": "What is the capital of France?"},
-            {"role": "assistant", "content": "The capital of France is Paris. It is a major European city renowned for its art, fashion, gastronomy, cultural heritage, and historical significance. The city attracts millions of tourists annually."},
-        ]
-        pairs = extract_pairs_from_conversation(conversation, "test_session", "test-model")
-        self.assertEqual(len(pairs), 1)
-        self.assertEqual(pairs[0]["terse"], "What is the capital of France?")
-        self.assertIn("Paris", pairs[0]["rich"])
-        self.assertEqual(pairs[0]["source"], "test_session")
-
-    def test_min_ratio_filter(self):
-        """Very short responses are filtered out."""
-        conversation = [
-            {"role": "user", "content": "Yes"},
-            {"role": "assistant", "content": "No."},
-        ]
-        # Default min_ratio = 1.5, min_words = 20 for response
-        pairs = extract_pairs_from_conversation(conversation, "s", "m", min_response_words=3)
-        self.assertEqual(len(pairs), 0)
-
-    def test_min_words_filter(self):
-        """Assistant responses below min word count are skipped."""
-        conversation = [
-            {"role": "user", "content": "Explain the project architecture in detail"},
-            {"role": "assistant", "content": "OK."},
-        ]
-        pairs = extract_pairs_from_conversation(conversation, "s", "m", min_response_words=5)
-        self.assertEqual(len(pairs), 0)
-
-    def test_skip_non_assistant_messages(self):
-        """System and tool messages are ignored."""
-        conversation = [
-            {"role": "system", "content": "You are a helpful assistant."},
-            {"role": "user", "content": "Hello"},
-            {"role": "assistant", "content": "Hi there! How can I help you today?"},
-        ]
-        pairs = extract_pairs_from_conversation(conversation, "s", "m", min_response_words=3)
-        self.assertEqual(len(pairs), 1)
-        self.assertEqual(pairs[0]["terse"], "Hello")
-
-    def test_multiple_pairs_from_one_session(self):
-        """A conversation with several Q&A turns yields multiple pairs."""
-        conversation = [
-            {"role": "user", "content": "First question?"},
-            {"role": "assistant", "content": "Here is a detailed and comprehensive answer that thoroughly explores multiple aspects of the subject. It provides background context and practical implications for the reader."},
-            {"role": "user", "content": "Second?"},
-            {"role": "assistant", "content": "Another comprehensive response with detailed examples. This includes practical code blocks and thorough explanations to ensure deep understanding of the topic at hand."},
-        ]
-        pairs = extract_pairs_from_conversation(conversation, "s", "m", min_ratio=1.0)
-        self.assertEqual(len(pairs), 2)
-
-    def test_deduplication_removes_duplicates(self):
-        """Identical pairs across sessions are deduplicated."""
-        pairs = [
-            {"terse": "q1", "rich": "a1", "source": "s1", "model": "m"},
-            {"terse": "q1", "rich": "a1", "source": "s2", "model": "m"},
-            {"terse": "q2", "rich": "a2", "source": "s1", "model": "m"},
-        ]
-        unique = deduplicate_pairs(pairs)
-        self.assertEqual(len(unique), 2)
-        sources = {p["source"] for p in unique}
-        # First unique pair can be from either s1 or s2
-        self.assertIn("s1", sources)
-
-    def test_integration_with_test_sessions(self):
-        """Harvester finds pairs in real test session files."""
-        repo_root = Path(__file__).parent.parent
-        test_sessions_dir = repo_root / "test_sessions"
-        if not test_sessions_dir.exists():
-            self.skipTest("test_sessions not found")
-
-        pairs = []
-        for jsonl_file in sorted(test_sessions_dir.glob("*.jsonl")):
-            pairs.extend(extract_from_jsonl_file(str(jsonl_file)))
-
-        self.assertGreater(len(pairs), 0, "Should extract at least one pair from test_sessions")
-        for p in pairs:
-            self.assertIn("terse", p)
-            self.assertIn("rich", p)
-            self.assertIn("source", p)
-            self.assertIn("model", p)
-            # Verify content exists
-            self.assertGreater(len(p["terse"]), 0)
-            self.assertGreater(len(p["rich"]), 0)
-
-
-if __name__ == "__main__":
-    unittest.main()
-