feat: Add staleness detector tests (closes #179)

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/session_pair_harvester.py

@@ -1,234 +0,0 @@
-#!/usr/bin/env python3
-"""
-Session Transcript → Training Pair Harvester
-
-Scans Hermes session JSONL files for Q&A patterns and extracts
-terse→rich training pairs. Outputs JSONL matching the timmy-config
-training pairs spec.
-
-Usage:
-  python3 scripts/session_pair_harvester.py ~/.hermes/sessions/
-  python3 scripts/session_pair_harvester.py session.jsonl --output pairs.jsonl
-  python3 scripts/session_pair_harvester.py --dir ~/.hermes/sessions/ --min-ratio 2.0
-
-Output format:
-  {"terse": "user short prompt", "rich": "ai detailed response", "source": "session_id", "model": "..."}
-"""
-
-import argparse
-import hashlib
-import json
-import sys
-from pathlib import Path
-from typing import Optional
-
-
-def compute_hash(text: str) -> str:
-    """Content hash for deduplication."""
-    return hashlib.sha256(text.encode()).hexdigest()[:16]
-
-
-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 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(conversations):
-        # Look for assistant/gpt responses
-        if msg.get("from") not in ("gpt", "assistant"):
-            continue
-
-        response_text = msg.get("value", "")
-        if not response_text or len(response_text.split()) < min_response_words:
-            continue
-
-        # Find the preceding human message
-        prompt_text = ""
-        for j in range(i - 1, -1, -1):
-            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  # 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
-
-        # Skip responses that are mostly code
-        code_blocks = response_text.count("```")
-        if code_blocks >= 4 and len(response_text.replace("```", "").strip()) < 50:
-            continue
-
-        # 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),
-        })
-
-    return pairs
-
-
-def extract_from_jsonl_file(filepath: str, **kwargs) -> list:
-    """Extract pairs from a session JSONL file."""
-    pairs = []
-    path = Path(filepath)
-
-    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:
-    """Remove duplicate pairs across files."""
-    seen = set()
-    unique = []
-    for pair in pairs:
-        key = compute_hash(pair["terse"] + pair["rich"][:200])
-        if key not in seen:
-            seen.add(key)
-            unique.append(pair)
-    return unique
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Harvest training pairs from session transcripts")
-    parser.add_argument("input", nargs="?", help="Session JSONL file or directory")
-    parser.add_argument("--dir", "-d", help="Directory to scan for session files")
-    parser.add_argument("--output", "-o", default="harvested_pairs.jsonl", help="Output file")
-    parser.add_argument("--min-ratio", type=float, default=1.5, help="Min response/prompt word ratio")
-    parser.add_argument("--min-words", type=int, default=20, help="Min response word count")
-    parser.add_argument("--dry-run", action="store_true", help="Print stats without writing")
-    args = parser.parse_args()
-
-    all_pairs = []
-    files_scanned = 0
-
-    scan_dir = args.dir or args.input
-    if not scan_dir:
-        parser.print_help()
-        sys.exit(1)
-
-    scan_path = Path(scan_dir)
-    if scan_path.is_dir():
-        jsonl_files = sorted(scan_path.rglob("*.jsonl"))
-        print(f"Scanning {len(jsonl_files)} files in {scan_dir}...", file=sys.stderr)
-        for fpath in jsonl_files:
-            pairs = extract_from_jsonl_file(
-                str(fpath),
-                min_ratio=args.min_ratio,
-                min_response_words=args.min_words
-            )
-            all_pairs.extend(pairs)
-            files_scanned += 1
-    else:
-        pairs = extract_from_jsonl_file(
-            str(scan_path),
-            min_ratio=args.min_ratio,
-            min_response_words=args.min_words
-        )
-        all_pairs.extend(pairs)
-        files_scanned = 1
-
-    # Deduplicate
-    unique_pairs = deduplicate_pairs(all_pairs)
-
-    # Stats
-    if unique_pairs:
-        avg_prompt = sum(p["prompt_words"] for p in unique_pairs) / len(unique_pairs)
-        avg_response = sum(p["response_words"] for p in unique_pairs) / len(unique_pairs)
-        avg_ratio = sum(p["ratio"] for p in unique_pairs) / len(unique_pairs)
-    else:
-        avg_prompt = avg_response = avg_ratio = 0
-
-    stats = {
-        "files_scanned": files_scanned,
-        "raw_pairs": len(all_pairs),
-        "unique_pairs": len(unique_pairs),
-        "duplicates_removed": len(all_pairs) - len(unique_pairs),
-        "avg_prompt_words": round(avg_prompt, 1),
-        "avg_response_words": round(avg_response, 1),
-        "avg_ratio": round(avg_ratio, 2),
-    }
-
-    print(json.dumps(stats, indent=2), file=sys.stderr)
-
-    if args.dry_run:
-        # Print sample pairs
-        for pair in unique_pairs[:3]:
-            print(f"\n--- Source: {pair['source']} (ratio: {pair['ratio']}) ---", file=sys.stderr)
-            print(f"TERSE: {pair['terse'][:100]}...", file=sys.stderr)
-            print(f"RICH: {pair['rich'][:150]}...", file=sys.stderr)
-        return
-
-    # Write output
-    output_path = Path(args.output)
-    with open(output_path, "w") as f:
-        for pair in unique_pairs:
-            # Strip internal fields for output
-            output = {
-                "terse": pair["terse"],
-                "rich": pair["rich"],
-                "source": pair["source"],
-                "model": pair["model"],
-            }
-            f.write(json.dumps(output) + "\n")
-
-    print(f"\nWrote {len(unique_pairs)} pairs to {output_path}", file=sys.stderr)
-
-
-if __name__ == "__main__":
-    main()

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()

scripts/test_session_pair_harvester.py

@@ -1,90 +0,0 @@
-#!/usr/bin/env python3
-"""Tests for session_pair_harvester."""
-
-import json
-import sys
-import os
-import tempfile
-
-sys.path.insert(0, os.path.dirname(__file__))
-from session_pair_harvester import extract_pairs_from_session, deduplicate_pairs, compute_hash
-
-
-def test_basic_extraction():
-    session = {
-        "id": "test_001",
-        "model": "test-model",
-        "conversations": [
-            {"from": "system", "value": "You are helpful."},
-            {"from": "human", "value": "What is Python?"},
-            {"from": "gpt", "value": "Python is a high-level programming language known for its readability and versatility. It supports multiple paradigms including procedural, object-oriented, and functional programming. Python is widely used in web development, data science, machine learning, and automation."},
-        ]
-    }
-    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
-    assert len(pairs) == 1
-    assert pairs[0]["terse"] == "What is Python?"
-    assert "programming language" in pairs[0]["rich"]
-    assert pairs[0]["source"] == "test_001"
-    print("PASS: test_basic_extraction")
-
-
-def test_filters_short_responses():
-    session = {
-        "id": "test_002",
-        "model": "test",
-        "conversations": [
-            {"from": "human", "value": "Hi"},
-            {"from": "gpt", "value": "Hello!"},
-        ]
-    }
-    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=20)
-    assert len(pairs) == 0
-    print("PASS: test_filters_short_responses")
-
-
-def test_skips_tool_results():
-    session = {
-        "id": "test_003",
-        "model": "test",
-        "conversations": [
-            {"from": "human", "value": '{"output": "file content", "exit_code": 0}'},
-            {"from": "gpt", "value": "The file was read successfully. Now let me analyze the content and provide a detailed summary of what was found in the file system."},
-        ]
-    }
-    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
-    assert len(pairs) == 0
-    print("PASS: test_skips_tool_results")
-
-
-def test_deduplication():
-    pairs = [
-        {"terse": "What is X?", "rich": "X is Y.", "source": "s1", "model": "m"},
-        {"terse": "What is X?", "rich": "X is Y.", "source": "s2", "model": "m"},
-        {"terse": "What is Z?", "rich": "Z is W.", "source": "s1", "model": "m"},
-    ]
-    unique = deduplicate_pairs(pairs)
-    assert len(unique) == 2
-    print("PASS: test_deduplication")
-
-
-def test_ratio_filter():
-    session = {
-        "id": "test_005",
-        "model": "test",
-        "conversations": [
-            {"from": "human", "value": "Explain quantum computing in detail with examples and applications"},
-            {"from": "gpt", "value": "OK."},
-        ]
-    }
-    pairs = extract_pairs_from_session(session, min_ratio=1.5, min_response_words=10)
-    assert len(pairs) == 0  # response too short relative to prompt
-    print("PASS: test_ratio_filter")
-
-
-if __name__ == "__main__":
-    test_basic_extraction()
-    test_filters_short_responses()
-    test_skips_tool_results()
-    test_deduplication()
-    test_ratio_filter()
-    print("\nAll tests passed.")