ci: add pytest workflow for #190

.gitea/workflows/test.yml

@@ -0,0 +1,22 @@
+name: Test
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  pytest:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+      - name: Install test dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+      - name: Run test suite
+        run: |
+          make test

Makefile

@@ -0,0 +1,4 @@
+.PHONY: test
+
+test:
+	python3 -m pytest tests/test_ci_config.py scripts/test_*.py -v

requirements.txt

@@ -0,0 +1 @@
+pytest>=8,<9

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_metadata.py

@@ -1,276 +0,0 @@
-#!/usr/bin/env python3
-"""
-session_metadata.py - Extract structured metadata from Hermes session transcripts.
-Works alongside session_reader.py to provide higher-level session analysis.
-"""
-
-import json
-import re
-import sys
-from dataclasses import dataclass, asdict
-from datetime import datetime
-from pathlib import Path
-from typing import Dict, List, Optional, Any
-
-# Import from session_reader (the canonical reader)
-from session_reader import read_session
-
-
-@dataclass
-class SessionSummary:
-    """Structured summary of a Hermes session transcript."""
-    session_id: str
-    model: str
-    repo: str
-    outcome: str
-    message_count: int
-    tool_calls: int
-    duration_estimate: str
-    key_actions: List[str]
-    errors_encountered: List[str]
-    start_time: Optional[str] = None
-    end_time: Optional[str] = None
-    total_tokens_estimate: int = 0
-    user_messages: int = 0
-    assistant_messages: int = 0
-    tool_outputs: int = 0
-
-
-def extract_session_metadata(file_path: str) -> SessionSummary:
-    """
-    Extract structured metadata from a Hermes session JSONL transcript.
-    Uses session_reader.read_session() for file reading.
-    """
-    session_id = Path(file_path).stem
-    messages = []
-    model = "unknown"
-    repo = "unknown"
-    tool_calls_count = 0
-    key_actions = []
-    errors = []
-    start_time = None
-    end_time = None
-    total_tokens = 0
-    
-    # Common repo patterns to look for
-    repo_patterns = [
-        r"(?:the-nexus|compounding-intelligence|timmy-config|hermes-agent)",
-        r"(?:forge\.alexanderwhitestone\.com/([^/]+/[^/\\s]+))",
-        r"(?:github\.com/([^/]+/[^/\\s]+))",
-        r"(?:Timmy_Foundation/([^/\\s]+))",
-    ]
-    
-    try:
-        # Use the canonical reader from session_reader.py
-        messages = read_session(file_path)
-    except FileNotFoundError:
-        return SessionSummary(
-            session_id=session_id,
-            model="unknown",
-            repo="unknown",
-            outcome="failure",
-            message_count=0,
-            tool_calls=0,
-            duration_estimate="0m",
-            key_actions=[],
-            errors_encountered=[f"File not found: {file_path}"]
-        )
-    
-    # Process messages for metadata
-    for entry in messages:
-        # Extract model from assistant messages
-        if entry.get("role") == "assistant" and entry.get("model"):
-            model = entry["model"]
-        
-        # Extract timestamps
-        if entry.get("timestamp"):
-            ts = entry["timestamp"]
-            if start_time is None:
-                start_time = ts
-            end_time = ts
-        
-        # Count tool calls
-        if entry.get("tool_calls"):
-            tool_calls_count += len(entry["tool_calls"])
-            for tc in entry["tool_calls"]:
-                if tc.get("function", {}).get("name"):
-                    action = f"{tc['function']['name']}"
-                    if action not in key_actions:
-                        key_actions.append(action)
-        
-        # Estimate tokens from content length
-        content = entry.get("content", "")
-        if isinstance(content, str):
-            total_tokens += len(content.split())
-        elif isinstance(content, list):
-            for item in content:
-                if isinstance(item, dict) and "text" in item:
-                    total_tokens += len(item["text"].split())
-        
-        # Look for repo mentions in content
-        if entry.get("content"):
-            content_str = str(entry["content"])
-            for pattern in repo_patterns:
-                match = re.search(pattern, content_str, re.IGNORECASE)
-                if match:
-                    if match.groups():
-                        repo = match.group(1)
-                    else:
-                        repo = match.group(0)
-                    break
-        
-        # Look for error messages
-        if entry.get("role") == "tool" and entry.get("is_error"):
-            error_msg = entry.get("content", "Unknown error")
-            if isinstance(error_msg, str) and len(error_msg) < 200:
-                errors.append(error_msg[:200])
-    
-    # Count message types
-    user_messages = sum(1 for m in messages if m.get("role") == "user")
-    assistant_messages = sum(1 for m in messages if m.get("role") == "assistant")
-    tool_outputs = sum(1 for m in messages if m.get("role") == "tool")
-    
-    # Calculate duration estimate
-    duration_estimate = "unknown"
-    if start_time and end_time:
-        try:
-            # Try to parse timestamps
-            start_dt = None
-            end_dt = None
-            
-            # Handle various timestamp formats
-            for fmt in ["%Y-%m-%dT%H:%M:%S.%fZ", "%Y-%m-%dT%H:%M:%SZ", "%Y-%m-%d %H:%M:%S"]:
-                try:
-                    if start_dt is None:
-                        start_dt = datetime.strptime(start_time, fmt)
-                    if end_dt is None:
-                        end_dt = datetime.strptime(end_time, fmt)
-                except ValueError:
-                    continue
-            
-            if start_dt and end_dt:
-                duration = end_dt - start_dt
-                minutes = duration.total_seconds() / 60
-                duration_estimate = f"{minutes:.0f}m"
-        except Exception:
-            pass
-    
-    # Classify outcome
-    outcome = "unknown"
-    if errors:
-        # Check if any errors are fatal
-        fatal_errors = any("405" in e or "permission" in e.lower() or "authentication" in e.lower() 
-                          for e in errors)
-        if fatal_errors:
-            outcome = "failure"
-        else:
-            outcome = "partial"
-    elif messages:
-        # Check last message for success indicators
-        last_msg = messages[-1]
-        if last_msg.get("role") == "assistant":
-            content = last_msg.get("content", "")
-            if isinstance(content, str):
-                success_indicators = ["done", "completed", "success", "merged", "pushed"]
-                if any(indicator in content.lower() for indicator in success_indicators):
-                    outcome = "success"
-                else:
-                    outcome = "unknown"
-    
-    # Deduplicate key actions (keep unique, limit to 10)
-    unique_actions = []
-    for action in key_actions:
-        if action not in unique_actions:
-            unique_actions.append(action)
-        if len(unique_actions) >= 10:
-            break
-    
-    # Deduplicate errors (keep unique, limit to 5)
-    unique_errors = []
-    for error in errors:
-        if error not in unique_errors:
-            unique_errors.append(error)
-        if len(unique_errors) >= 5:
-            break
-    
-    return SessionSummary(
-        session_id=session_id,
-        model=model,
-        repo=repo,
-        outcome=outcome,
-        message_count=len(messages),
-        tool_calls=tool_calls_count,
-        duration_estimate=duration_estimate,
-        key_actions=unique_actions,
-        errors_encountered=unique_errors,
-        start_time=start_time,
-        end_time=end_time,
-        total_tokens_estimate=total_tokens,
-        user_messages=user_messages,
-        assistant_messages=assistant_messages,
-        tool_outputs=tool_outputs
-    )
-
-
-def process_session_directory(directory_path: str, output_file: Optional[str] = None) -> List[SessionSummary]:
-    """
-    Process all JSONL files in a directory.
-    """
-    directory = Path(directory_path)
-    if not directory.exists():
-        print(f"Error: Directory {directory_path} does not exist", file=sys.stderr)
-        return []
-    
-    jsonl_files = list(directory.glob("*.jsonl"))
-    if not jsonl_files:
-        print(f"Warning: No JSONL files found in {directory_path}", file=sys.stderr)
-        return []
-    
-    summaries = []
-    for jsonl_file in sorted(jsonl_files):
-        print(f"Processing {jsonl_file.name}...", file=sys.stderr)
-        summary = extract_session_metadata(str(jsonl_file))
-        summaries.append(summary)
-    
-    if output_file:
-        with open(output_file, 'w', encoding='utf-8') as f:
-            json.dump([asdict(s) for s in summaries], f, indent=2)
-        print(f"Wrote {len(summaries)} summaries to {output_file}", file=sys.stderr)
-    
-    return summaries
-
-
-def main():
-    """CLI entry point."""
-    import argparse
-    
-    parser = argparse.ArgumentParser(description="Extract metadata from Hermes session JSONL transcripts")
-    parser.add_argument("path", help="Path to JSONL file or directory of session files")
-    parser.add_argument("-o", "--output", help="Output JSON file (default: stdout)")
-    parser.add_argument("-v", "--verbose", action="store_true", help="Verbose output")
-    
-    args = parser.parse_args()
-    
-    path = Path(args.path)
-    
-    if path.is_file():
-        summary = extract_session_metadata(str(path))
-        if args.output:
-            with open(args.output, 'w') as f:
-                json.dump(asdict(summary), f, indent=2)
-            print(f"Wrote summary to {args.output}", file=sys.stderr)
-        else:
-            print(json.dumps(asdict(summary), indent=2))
-    
-    elif path.is_dir():
-        summaries = process_session_directory(str(path), args.output)
-        if not args.output:
-            print(json.dumps([asdict(s) for s in summaries], indent=2))
-    
-    else:
-        print(f"Error: {args.path} is not a file or directory", file=sys.stderr)
-        sys.exit(1)
-
-
-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()

tests/test_ci_config.py

@@ -0,0 +1,19 @@
+from pathlib import Path
+
+
+def test_requirements_makefile_and_workflow_exist() -> None:
+    assert Path("requirements.txt").exists()
+    assert Path("Makefile").exists()
+    assert Path(".gitea/workflows/test.yml").exists()
+
+
+def test_ci_workflow_runs_project_test_command() -> None:
+    workflow = Path(".gitea/workflows/test.yml").read_text(encoding="utf-8")
+    requirements = Path("requirements.txt").read_text(encoding="utf-8")
+    makefile = Path("Makefile").read_text(encoding="utf-8")
+
+    assert "pytest" in requirements
+    assert "test:" in makefile
+    assert "python3 -m pytest tests/test_ci_config.py scripts/test_*.py -v" in makefile
+    assert "pip install -r requirements.txt" in workflow
+    assert "make test" in workflow