feat: knowledge store staleness detector (#92)

scripts/knowledge_staleness_check.py

@@ -0,0 +1,221 @@
+#!/usr/bin/env python3
+"""
+Knowledge Store Staleness Detector
+
+Checks knowledge entries against their source files to detect staleness.
+An entry is stale when its source file has been modified since extraction.
+
+Usage:
+  python3 scripts/knowledge_staleness_check.py knowledge/index.json
+  python3 scripts/knowledge_staleness_check.py --repo /path/to/repo --index knowledge/index.json
+  python3 scripts/knowledge_staleness_check.py --index knowledge/index.json --fix
+
+Expected index.json format:
+{
+  "version": 1,
+  "facts": [
+    {
+      "fact": "...",
+      "category": "fact|pitfall|pattern|tool-quirk",
+      "repo": "repo-name",
+      "confidence": 0.8,
+      "source_file": "path/to/file.py",
+      "source_hash": "sha256:abcdef...",
+      "extracted_at": "2026-04-13T20:00:00Z"
+    }
+  ]
+}
+"""
+
+import argparse
+import hashlib
+import json
+import sys
+from pathlib import Path
+from typing import Optional
+
+
+def compute_file_hash(filepath: str) -> Optional[str]:
+    """Compute SHA-256 hash of a file. Returns None if file not found."""
+    path = Path(filepath)
+    if not path.exists():
+        return None
+    content = path.read_bytes()
+    return hashlib.sha256(content).hexdigest()[:16]
+
+
+def check_staleness(index_path: str, repo_root: str = None) -> dict:
+    """Check all entries in the knowledge index for staleness."""
+    index = Path(index_path)
+    if not index.exists():
+        return {"error": f"Index not found: {index_path}"}
+
+    data = json.loads(index.read_text())
+    facts = data.get("facts", [])
+
+    if not facts:
+        return {
+            "total": 0,
+            "stale": 0,
+            "fresh": 0,
+            "no_source": 0,
+            "missing_files": 0,
+            "stale_entries": [],
+        }
+
+    # Determine repo root
+    if repo_root:
+        root = Path(repo_root)
+    else:
+        root = index.parent.parent  # knowledge/index.json -> repo root
+
+    results = {
+        "total": len(facts),
+        "stale": 0,
+        "fresh": 0,
+        "no_source": 0,
+        "missing_files": 0,
+        "stale_entries": [],
+    }
+
+    for i, entry in enumerate(facts):
+        source_file = entry.get("source_file")
+        stored_hash = entry.get("source_hash")
+
+        if not source_file:
+            results["no_source"] += 1
+            continue
+
+        if not stored_hash:
+            # Entry has source file but no hash — consider stale
+            results["stale"] += 1
+            results["stale_entries"].append({
+                "index": i,
+                "fact": entry.get("fact", "")[:100],
+                "source_file": source_file,
+                "reason": "no_hash",
+            })
+            continue
+
+        # Compute current hash
+        full_path = root / source_file
+        current_hash = compute_file_hash(str(full_path))
+
+        if current_hash is None:
+            results["missing_files"] += 1
+            results["stale_entries"].append({
+                "index": i,
+                "fact": entry.get("fact", "")[:100],
+                "source_file": source_file,
+                "reason": "file_missing",
+            })
+        elif current_hash != stored_hash:
+            results["stale"] += 1
+            results["stale_entries"].append({
+                "index": i,
+                "fact": entry.get("fact", "")[:100],
+                "source_file": source_file,
+                "stored_hash": stored_hash,
+                "current_hash": current_hash,
+                "reason": "hash_mismatch",
+            })
+        else:
+            results["fresh"] += 1
+
+    return results
+
+
+def add_hashes_to_index(index_path: str, repo_root: str = None) -> dict:
+    """Add source hashes to entries that are missing them."""
+    index = Path(index_path)
+    data = json.loads(index.read_text())
+    facts = data.get("facts", [])
+
+    if repo_root:
+        root = Path(repo_root)
+    else:
+        root = index.parent.parent
+
+    updated = 0
+    skipped = 0
+
+    for entry in facts:
+        source_file = entry.get("source_file")
+        if not source_file or entry.get("source_hash"):
+            skipped += 1
+            continue
+
+        full_path = root / source_file
+        file_hash = compute_file_hash(str(full_path))
+        if file_hash:
+            entry["source_hash"] = file_hash
+            updated += 1
+
+    if updated > 0:
+        index.write_text(json.dumps(data, indent=2) + "\n")
+
+    return {"updated": updated, "skipped": skipped, "total": len(facts)}
+
+
+def report_staleness(results: dict) -> str:
+    """Format staleness check results as a report."""
+    lines = []
+    lines.append("=" * 50)
+    lines.append("KNOWLEDGE STORE STALENESS REPORT")
+    lines.append("=" * 50)
+    lines.append(f"Total entries:  {results['total']}")
+    lines.append(f"Fresh:          {results['fresh']}")
+    lines.append(f"Stale:          {results['stale']}")
+    lines.append(f"No source:      {results['no_source']}")
+    lines.append(f"Missing files:  {results['missing_files']}")
+    lines.append("")
+
+    if results["stale_entries"]:
+        lines.append("STALE ENTRIES:")
+        lines.append("-" * 50)
+        for entry in results["stale_entries"]:
+            lines.append(f"  [{entry['reason']}] {entry['source_file']}")
+            lines.append(f"    {entry['fact']}")
+            if entry.get("stored_hash") and entry.get("current_hash"):
+                lines.append(f"    stored:  {entry['stored_hash']}")
+                lines.append(f"    current: {entry['current_hash']}")
+            lines.append("")
+
+    if results["total"] > 0:
+        staleness_pct = results["stale"] / results["total"] * 100
+        lines.append(f"Staleness rate: {staleness_pct:.1f}%")
+    else:
+        lines.append("No entries to check.")
+
+    return "\n".join(lines)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Check knowledge store for stale entries")
+    parser.add_argument("--index", default="knowledge/index.json", help="Path to index.json")
+    parser.add_argument("--repo", help="Repository root (default: auto-detect from index path)")
+    parser.add_argument("--fix", action="store_true", help="Add missing hashes to index")
+    parser.add_argument("--json", action="store_true", help="Output JSON instead of report")
+    args = parser.parse_args()
+
+    if args.fix:
+        result = add_hashes_to_index(args.index, args.repo)
+        if args.json:
+            print(json.dumps(result, indent=2))
+        else:
+            print(f"Updated {result['updated']} entries with source hashes.")
+            print(f"Skipped {result['skipped']} (already had hashes or no source file).")
+    else:
+        results = check_staleness(args.index, args.repo)
+        if "error" in results:
+            print(f"Error: {results['error']}", file=sys.stderr)
+            sys.exit(1)
+
+        if args.json:
+            print(json.dumps(results, indent=2))
+        else:
+            print(report_staleness(results))
+
+
+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_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.")