Compare commits

..

1 Commits

5 changed files with 276 additions and 556 deletions

View File

@@ -1,131 +0,0 @@
#!/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()

View File

@@ -1,54 +0,0 @@
#!/usr/bin/env python3
"""
Finds refactoring opportunities in codebases
Engine ID: 10.4
Usage:
python3 scripts/refactoring_opportunity_finder.py --output proposals/refactoring_opportunity_finder.json
python3 scripts/refactoring_opportunity_finder.py --output proposals/refactoring_opportunity_finder.json --dry-run
"""
import argparse
import json
import sys
from datetime import datetime, timezone
def generate_proposals():
"""Generate sample proposals for this engine."""
# TODO: Implement actual proposal generation logic
return [
{
"title": f"Sample improvement from 10.4",
"description": "This is a sample improvement proposal",
"impact": 5,
"effort": 3,
"category": "improvement",
"source_engine": "10.4",
"timestamp": datetime.now(timezone.utc).isoformat()
}
]
def main():
parser = argparse.ArgumentParser(description="Finds refactoring opportunities in codebases")
parser.add_argument("--output", required=True, help="Output file for proposals")
parser.add_argument("--dry-run", action="store_true", help="Don't write output file")
args = parser.parse_args()
proposals = generate_proposals()
if not args.dry_run:
with open(args.output, "w") as f:
json.dump({"proposals": proposals}, f, indent=2)
print(f"Generated {len(proposals)} proposals -> {args.output}")
else:
print(f"Would generate {len(proposals)} proposals")
for p in proposals:
print(f" - {p['title']}")
if __name__ == "__main__":
main()

276
scripts/session_metadata.py Normal file
View File

@@ -0,0 +1,276 @@
#!/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()

View File

@@ -1,129 +0,0 @@
#!/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()

View File

@@ -1,242 +0,0 @@
#!/usr/bin/env python3
"""Tests for scripts/refactoring_opportunity_finder.py — 10 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(
"rof", os.path.join(os.path.dirname(__file__) or ".", "refactoring_opportunity_finder.py"))
mod = importlib.util.module_from_spec(spec)
spec.loader.exec_module(mod)
compute_file_complexity = mod.compute_file_complexity
calculate_refactoring_score = mod.calculate_refactoring_score
FileMetrics = mod.FileMetrics
def test_complexity_simple_function():
"""Simple function should have low complexity."""
with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
f.write("""
def simple():
return 42
""")
f.flush()
avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
assert avg == 1.0, f"Expected 1.0, got {avg}"
assert max_c == 1, f"Expected 1, got {max_c}"
assert funcs == 1, f"Expected 1, got {funcs}"
assert classes == 0, f"Expected 0, got {classes}"
os.unlink(f.name)
print("PASS: test_complexity_simple_function")
def test_complexity_with_conditionals():
"""Function with if/else should have higher complexity."""
with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
f.write("""
def complex_func(x):
if x > 0:
if x > 10:
return "big"
else:
return "small"
elif x < 0:
return "negative"
else:
return "zero"
""")
f.flush()
avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
# Base 1 + 3 if/elif + 1 nested if = 5
assert max_c >= 4, f"Expected max_c >= 4, got {max_c}"
assert funcs == 1, f"Expected 1, got {funcs}"
os.unlink(f.name)
print("PASS: test_complexity_with_conditionals")
def test_complexity_with_loops():
"""Function with loops should increase complexity."""
with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
f.write("""
def loop_func(items):
result = []
for item in items:
if item > 0:
result.append(item)
while len(result) > 10:
result.pop()
return result
""")
f.flush()
avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
# Base 1 + 1 for + 1 if + 1 while = 4
assert max_c >= 3, f"Expected max_c >= 3, got {max_c}"
os.unlink(f.name)
print("PASS: test_complexity_with_loops")
def test_complexity_with_class():
"""Class with methods should count both."""
with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
f.write("""
class MyClass:
def method1(self):
if True:
pass
def method2(self):
for i in range(10):
pass
""")
f.flush()
avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
assert classes == 1, f"Expected 1 class, got {classes}"
assert funcs == 2, f"Expected 2 functions, got {funcs}"
os.unlink(f.name)
print("PASS: test_complexity_with_class")
def test_complexity_syntax_error():
"""File with syntax error should return zeros."""
with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
f.write("def broken(:\n pass")
f.flush()
avg, max_c, funcs, classes, lines = compute_file_complexity(f.name)
assert avg == 0.0, f"Expected 0.0, got {avg}"
assert funcs == 0, f"Expected 0, got {funcs}"
os.unlink(f.name)
print("PASS: test_complexity_syntax_error")
def test_refactoring_score_high_complexity():
"""High complexity should give high score."""
metrics = FileMetrics(
path="test.py",
lines=200,
complexity=15.0,
max_complexity=25,
functions=10,
classes=2,
churn_30d=5,
churn_90d=15,
test_coverage=0.3,
refactoring_score=0.0
)
score = calculate_refactoring_score(metrics)
assert score > 50, f"Expected score > 50, got {score}"
print("PASS: test_refactoring_score_high_complexity")
def test_refactoring_score_low_complexity():
"""Low complexity should give lower score."""
metrics = FileMetrics(
path="test.py",
lines=50,
complexity=2.0,
max_complexity=3,
functions=3,
classes=0,
churn_30d=0,
churn_90d=1,
test_coverage=0.9,
refactoring_score=0.0
)
score = calculate_refactoring_score(metrics)
assert score < 30, f"Expected score < 30, got {score}"
print("PASS: test_refactoring_score_low_complexity")
def test_refactoring_score_high_churn():
"""High churn should increase score."""
metrics = FileMetrics(
path="test.py",
lines=100,
complexity=5.0,
max_complexity=8,
functions=5,
classes=0,
churn_30d=10,
churn_90d=20,
test_coverage=0.5,
refactoring_score=0.0
)
score = calculate_refactoring_score(metrics)
# Churn should contribute significantly
assert score > 40, f"Expected score > 40 for high churn, got {score}"
print("PASS: test_refactoring_score_high_churn")
def test_refactoring_score_no_coverage():
"""No coverage data should assume medium risk."""
metrics = FileMetrics(
path="test.py",
lines=100,
complexity=5.0,
max_complexity=8,
functions=5,
classes=0,
churn_30d=1,
churn_90d=2,
test_coverage=None,
refactoring_score=0.0
)
score = calculate_refactoring_score(metrics)
# Should have some score from the 5-point coverage component
assert score > 0, f"Expected positive score, got {score}"
print("PASS: test_refactoring_score_no_coverage")
def test_refactoring_score_large_file():
"""Large files should score higher."""
metrics_small = FileMetrics(
path="small.py",
lines=50,
complexity=5.0,
max_complexity=8,
functions=3,
classes=0,
churn_30d=1,
churn_90d=2,
test_coverage=0.8,
refactoring_score=0.0
)
metrics_large = FileMetrics(
path="large.py",
lines=1000,
complexity=5.0,
max_complexity=8,
functions=3,
classes=0,
churn_30d=1,
churn_90d=2,
test_coverage=0.8,
refactoring_score=0.0
)
score_small = calculate_refactoring_score(metrics_small)
score_large = calculate_refactoring_score(metrics_large)
assert score_large > score_small, \
f"Large file ({score_large}) should score higher than small ({score_small})"
print("PASS: test_refactoring_score_large_file")
def run_all():
test_complexity_simple_function()
test_complexity_with_conditionals()
test_complexity_with_loops()
test_complexity_with_class()
test_complexity_syntax_error()
test_refactoring_score_high_complexity()
test_refactoring_score_low_complexity()
test_refactoring_score_high_churn()
test_refactoring_score_no_coverage()
test_refactoring_score_large_file()
print("\nAll 10 tests passed!")
if __name__ == "__main__":
run_all()