Compare commits
1 Commits
feat/200-k
...
fix/198-qu
| Author | SHA1 | Date | |
|---|---|---|---|
|
e1e42c3f8e |
297
quality_gate.py
Normal file
297
quality_gate.py
Normal file
@@ -0,0 +1,297 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
quality_gate.py — Score and filter knowledge entries.
|
||||
|
||||
Scores each entry on 4 dimensions:
|
||||
- Specificity: concrete examples vs vague generalities
|
||||
- Actionability: can this be used to do something?
|
||||
- Freshness: is this still accurate?
|
||||
- Source quality: was the model/provider reliable?
|
||||
|
||||
Usage:
|
||||
from quality_gate import score_entry, filter_entries, quality_report
|
||||
|
||||
score = score_entry(entry)
|
||||
filtered = filter_entries(entries, threshold=0.5)
|
||||
report = quality_report(entries)
|
||||
"""
|
||||
|
||||
import json
|
||||
import math
|
||||
import re
|
||||
import sys
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Any, Optional
|
||||
|
||||
# Source quality scores (higher = more reliable)
|
||||
SOURCE_QUALITY = {
|
||||
"claude-sonnet": 0.9,
|
||||
"claude-opus": 0.95,
|
||||
"gpt-4": 0.85,
|
||||
"gpt-4-turbo": 0.85,
|
||||
"gpt-5": 0.9,
|
||||
"mimo-v2-pro": 0.8,
|
||||
"gemini-pro": 0.8,
|
||||
"llama-3-70b": 0.75,
|
||||
"llama-3-8b": 0.7,
|
||||
"ollama": 0.6,
|
||||
"unknown": 0.5,
|
||||
}
|
||||
|
||||
DEFAULT_SOURCE_QUALITY = 0.5
|
||||
|
||||
# Specificity indicators
|
||||
SPECIFIC_INDICATORS = [
|
||||
r"\b\d+\.\d+", # decimal numbers
|
||||
r"\b\d{4}-\d{2}-\d{2}", # dates
|
||||
r"\b[A-Z][a-z]+\s[A-Z][a-z]+", # proper nouns
|
||||
r"`[^`]+`", # code/commands
|
||||
r"https?://", # URLs
|
||||
r"\b(example|instance|specifically|concretely)\b",
|
||||
r"\b(step \d|first|second|third)\b",
|
||||
r"\b(exactly|precisely|measured|counted)\b",
|
||||
]
|
||||
|
||||
# Vagueness indicators (penalty)
|
||||
VAGUE_INDICATORS = [
|
||||
r"\b(generally|usually|often|sometimes|might|could|perhaps)\b",
|
||||
r"\b(various|several|many|some|few)\b",
|
||||
r"\b(it depends|varies|differs)\b",
|
||||
r"\b(basically|essentially|fundamentally)\b",
|
||||
r"\b(everyone knows|it's obvious|clearly)\b",
|
||||
]
|
||||
|
||||
# Actionability indicators
|
||||
ACTIONABLE_INDICATORS = [
|
||||
r"\b(run|execute|install|deploy|configure|set up)\b",
|
||||
r"\b(use|apply|implement|create|build)\b",
|
||||
r"\b(check|verify|test|validate|confirm)\b",
|
||||
r"\b(fix|resolve|solve|debug|troubleshoot)\b",
|
||||
r"\b(if .+ then|when .+ do|to .+ use)\b",
|
||||
r"```[a-z]*\n", # code blocks
|
||||
r"\$\s", # shell commands
|
||||
r"\b\d+\.\s", # numbered steps
|
||||
]
|
||||
|
||||
|
||||
def score_specificity(content: str) -> float:
|
||||
"""Score specificity: 0=vague, 1=very specific."""
|
||||
content_lower = content.lower()
|
||||
score = 0.5 # baseline
|
||||
|
||||
# Check for specific indicators
|
||||
specific_count = sum(
|
||||
len(re.findall(p, content, re.IGNORECASE))
|
||||
for p in SPECIFIC_INDICATORS
|
||||
)
|
||||
|
||||
# Check for vague indicators
|
||||
vague_count = sum(
|
||||
len(re.findall(p, content_lower))
|
||||
for p in VAGUE_INDICATORS
|
||||
)
|
||||
|
||||
# Adjust score
|
||||
score += min(specific_count * 0.05, 0.4)
|
||||
score -= min(vague_count * 0.08, 0.3)
|
||||
|
||||
# Length bonus (longer = more detail, up to a point)
|
||||
word_count = len(content.split())
|
||||
if word_count > 50:
|
||||
score += min((word_count - 50) * 0.001, 0.1)
|
||||
|
||||
return max(0.0, min(1.0, score))
|
||||
|
||||
|
||||
def score_actionability(content: str) -> float:
|
||||
"""Score actionability: 0=abstract, 1=highly actionable."""
|
||||
content_lower = content.lower()
|
||||
score = 0.3 # baseline (most knowledge is informational)
|
||||
|
||||
# Check for actionable indicators
|
||||
actionable_count = sum(
|
||||
len(re.findall(p, content_lower))
|
||||
for p in ACTIONABLE_INDICATORS
|
||||
)
|
||||
|
||||
score += min(actionable_count * 0.1, 0.6)
|
||||
|
||||
# Code blocks are highly actionable
|
||||
if "```" in content:
|
||||
score += 0.2
|
||||
|
||||
# Numbered steps are actionable
|
||||
if re.search(r"\d+\.\s+\w", content):
|
||||
score += 0.1
|
||||
|
||||
return max(0.0, min(1.0, score))
|
||||
|
||||
|
||||
def score_freshness(timestamp: Optional[str]) -> float:
|
||||
"""Score freshness: 1=new, decays over time."""
|
||||
if not timestamp:
|
||||
return 0.5
|
||||
|
||||
try:
|
||||
if isinstance(timestamp, str):
|
||||
ts = datetime.fromisoformat(timestamp.replace("Z", "+00:00"))
|
||||
else:
|
||||
ts = timestamp
|
||||
|
||||
now = datetime.now(timezone.utc)
|
||||
age_days = (now - ts).days
|
||||
|
||||
# Exponential decay: 1.0 at day 0, 0.5 at ~180 days, 0.1 at ~365 days
|
||||
score = math.exp(-age_days / 180)
|
||||
return max(0.1, min(1.0, score))
|
||||
except (ValueError, TypeError):
|
||||
return 0.5
|
||||
|
||||
|
||||
def score_source_quality(model: Optional[str]) -> float:
|
||||
"""Score source quality based on model/provider."""
|
||||
if not model:
|
||||
return DEFAULT_SOURCE_QUALITY
|
||||
|
||||
# Normalize model name
|
||||
model_lower = model.lower()
|
||||
for key, score in SOURCE_QUALITY.items():
|
||||
if key in model_lower:
|
||||
return score
|
||||
|
||||
return DEFAULT_SOURCE_QUALITY
|
||||
|
||||
|
||||
def score_entry(entry: dict) -> float:
|
||||
"""
|
||||
Score a knowledge entry on quality (0.0-1.0).
|
||||
|
||||
Weights:
|
||||
- specificity: 0.3
|
||||
- actionability: 0.3
|
||||
- freshness: 0.2
|
||||
- source_quality: 0.2
|
||||
"""
|
||||
content = entry.get("content", entry.get("text", entry.get("response", "")))
|
||||
model = entry.get("model", entry.get("provenance", {}).get("model"))
|
||||
timestamp = entry.get("timestamp", entry.get("provenance", {}).get("timestamp"))
|
||||
|
||||
specificity = score_specificity(content)
|
||||
actionability = score_actionability(content)
|
||||
freshness = score_freshness(timestamp)
|
||||
source = score_source_quality(model)
|
||||
|
||||
return round(
|
||||
0.3 * specificity +
|
||||
0.3 * actionability +
|
||||
0.2 * freshness +
|
||||
0.2 * source,
|
||||
4
|
||||
)
|
||||
|
||||
|
||||
def score_entry_detailed(entry: dict) -> dict:
|
||||
"""Score with breakdown."""
|
||||
content = entry.get("content", entry.get("text", entry.get("response", "")))
|
||||
model = entry.get("model", entry.get("provenance", {}).get("model"))
|
||||
timestamp = entry.get("timestamp", entry.get("provenance", {}).get("timestamp"))
|
||||
|
||||
specificity = score_specificity(content)
|
||||
actionability = score_actionability(content)
|
||||
freshness = score_freshness(timestamp)
|
||||
source = score_source_quality(model)
|
||||
|
||||
return {
|
||||
"score": round(0.3 * specificity + 0.3 * actionability + 0.2 * freshness + 0.2 * source, 4),
|
||||
"specificity": round(specificity, 4),
|
||||
"actionability": round(actionability, 4),
|
||||
"freshness": round(freshness, 4),
|
||||
"source_quality": round(source, 4),
|
||||
}
|
||||
|
||||
|
||||
def filter_entries(entries: List[dict], threshold: float = 0.5) -> List[dict]:
|
||||
"""Filter entries below quality threshold."""
|
||||
filtered = []
|
||||
for entry in entries:
|
||||
if score_entry(entry) >= threshold:
|
||||
filtered.append(entry)
|
||||
return filtered
|
||||
|
||||
|
||||
def quality_report(entries: List[dict]) -> str:
|
||||
"""Generate quality distribution report."""
|
||||
if not entries:
|
||||
return "No entries to analyze."
|
||||
|
||||
scores = [score_entry(e) for e in entries]
|
||||
|
||||
avg = sum(scores) / len(scores)
|
||||
min_score = min(scores)
|
||||
max_score = max(scores)
|
||||
|
||||
# Distribution buckets
|
||||
buckets = {"high": 0, "medium": 0, "low": 0, "rejected": 0}
|
||||
for s in scores:
|
||||
if s >= 0.7:
|
||||
buckets["high"] += 1
|
||||
elif s >= 0.5:
|
||||
buckets["medium"] += 1
|
||||
elif s >= 0.3:
|
||||
buckets["low"] += 1
|
||||
else:
|
||||
buckets["rejected"] += 1
|
||||
|
||||
lines = [
|
||||
"=" * 50,
|
||||
" QUALITY GATE REPORT",
|
||||
"=" * 50,
|
||||
f" Total entries: {len(entries)}",
|
||||
f" Average score: {avg:.3f}",
|
||||
f" Min: {min_score:.3f}",
|
||||
f" Max: {max_score:.3f}",
|
||||
"",
|
||||
" Distribution:",
|
||||
]
|
||||
|
||||
for bucket, count in buckets.items():
|
||||
pct = count / len(entries) * 100
|
||||
bar = "█" * int(pct / 5)
|
||||
lines.append(f" {bucket:<12} {count:>5} ({pct:>5.1f}%) {bar}")
|
||||
|
||||
passed = buckets["high"] + buckets["medium"]
|
||||
lines.append(f"\n Pass rate (>= 0.5): {passed}/{len(entries)} ({passed/len(entries)*100:.1f}%)")
|
||||
lines.append("=" * 50)
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def main():
|
||||
import argparse
|
||||
parser = argparse.ArgumentParser(description="Knowledge quality gate")
|
||||
parser.add_argument("files", nargs="+", help="JSONL files to score")
|
||||
parser.add_argument("--threshold", type=float, default=0.5, help="Quality threshold")
|
||||
parser.add_argument("--json", action="store_true", help="JSON output")
|
||||
parser.add_argument("--filter", action="store_true", help="Filter and write back")
|
||||
args = parser.parse_args()
|
||||
|
||||
all_entries = []
|
||||
for filepath in args.files:
|
||||
with open(filepath) as f:
|
||||
for line in f:
|
||||
if line.strip():
|
||||
all_entries.append(json.loads(line))
|
||||
|
||||
if args.json:
|
||||
results = [{"entry": e, **score_entry_detailed(e)} for e in all_entries]
|
||||
print(json.dumps(results, indent=2))
|
||||
elif args.filter:
|
||||
filtered = filter_entries(all_entries, args.threshold)
|
||||
print(f"Kept {len(filtered)}/{len(all_entries)} entries (threshold: {args.threshold})")
|
||||
else:
|
||||
print(quality_report(all_entries))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,387 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Knowledge Freshness Cron — Detect stale entries from code changes (Issue #200)
|
||||
|
||||
Automatically detects when knowledge entries become stale due to code changes.
|
||||
|
||||
Detection Method:
|
||||
1. Track source file hash alongside knowledge entry
|
||||
2. Compare current file hashes vs stored
|
||||
3. Mismatch → flag entry as potentially stale
|
||||
4. Report stale entries and optionally re-extract
|
||||
|
||||
Usage:
|
||||
python3 scripts/freshness.py --knowledge-dir knowledge/
|
||||
python3 scripts/freshness.py --knowledge-dir knowledge/ --json
|
||||
python3 scripts/freshness.py --knowledge-dir knowledge/ --repo /path/to/repo
|
||||
python3 scripts/freshness.py --knowledge-dir knowledge/ --auto-reextract
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import yaml
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
from typing import Dict, List, Any, Optional, Tuple
|
||||
|
||||
|
||||
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 get_git_file_changes(repo_path: str, days: int = 1) -> Dict[str, List[str]]:
|
||||
"""
|
||||
Get files changed in git in the last N days.
|
||||
|
||||
Returns dict with 'modified', 'added', 'deleted' lists of file paths.
|
||||
"""
|
||||
changes = {"modified": [], "added": [], "deleted": []}
|
||||
|
||||
try:
|
||||
# Get commits from last N days
|
||||
cmd = [
|
||||
"git", "-C", repo_path, "log",
|
||||
f"--since={days} days ago",
|
||||
"--name-status",
|
||||
"--pretty=format:",
|
||||
"--diff-filter=MAD"
|
||||
]
|
||||
result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
|
||||
|
||||
if result.returncode != 0:
|
||||
return changes
|
||||
|
||||
for line in result.stdout.splitlines():
|
||||
line = line.strip()
|
||||
if not line:
|
||||
continue
|
||||
|
||||
parts = line.split('\t', 1)
|
||||
if len(parts) != 2:
|
||||
continue
|
||||
|
||||
status, filepath = parts
|
||||
if status == 'M':
|
||||
changes["modified"].append(filepath)
|
||||
elif status == 'A':
|
||||
changes["added"].append(filepath)
|
||||
elif status == 'D':
|
||||
changes["deleted"].append(filepath)
|
||||
|
||||
except (subprocess.TimeoutExpired, FileNotFoundError):
|
||||
pass
|
||||
|
||||
# Deduplicate
|
||||
for key in changes:
|
||||
changes[key] = list(set(changes[key]))
|
||||
|
||||
return changes
|
||||
|
||||
|
||||
def load_knowledge_entries(knowledge_dir: str) -> List[Dict[str, Any]]:
|
||||
"""
|
||||
Load knowledge entries from YAML files in the knowledge directory.
|
||||
|
||||
Supports:
|
||||
- knowledge/index.json (legacy format)
|
||||
- knowledge/global/*.yaml
|
||||
- knowledge/repos/*.yaml
|
||||
- knowledge/agents/*.yaml
|
||||
"""
|
||||
entries = []
|
||||
|
||||
# Load from index.json if exists
|
||||
index_path = os.path.join(knowledge_dir, "index.json")
|
||||
if os.path.exists(index_path):
|
||||
try:
|
||||
with open(index_path) as f:
|
||||
data = json.load(f)
|
||||
for fact in data.get("facts", []):
|
||||
entries.append({
|
||||
"source": "index.json",
|
||||
"fact": fact.get("fact", ""),
|
||||
"source_file": fact.get("source_file"),
|
||||
"source_hash": fact.get("source_hash"),
|
||||
"category": fact.get("category", "unknown"),
|
||||
"confidence": fact.get("confidence", 0.5)
|
||||
})
|
||||
except (json.JSONDecodeError, KeyError):
|
||||
pass
|
||||
|
||||
# Load from YAML files
|
||||
for subdir in ["global", "repos", "agents"]:
|
||||
subdir_path = os.path.join(knowledge_dir, subdir)
|
||||
if not os.path.isdir(subdir_path):
|
||||
continue
|
||||
|
||||
for filename in os.listdir(subdir_path):
|
||||
if not filename.endswith((".yaml", ".yml")):
|
||||
continue
|
||||
|
||||
filepath = os.path.join(subdir_path, filename)
|
||||
try:
|
||||
with open(filepath) as f:
|
||||
data = yaml.safe_load(f)
|
||||
|
||||
if not data or not isinstance(data, dict):
|
||||
continue
|
||||
|
||||
# Extract entries from YAML structure
|
||||
for key, value in data.items():
|
||||
if isinstance(value, list):
|
||||
for item in value:
|
||||
if isinstance(item, dict):
|
||||
entries.append({
|
||||
"source": f"{subdir}/{filename}",
|
||||
"fact": item.get("description", item.get("fact", "")),
|
||||
"source_file": item.get("source_file"),
|
||||
"source_hash": item.get("source_hash"),
|
||||
"category": item.get("category", "unknown"),
|
||||
"confidence": item.get("confidence", 0.5)
|
||||
})
|
||||
elif isinstance(value, dict):
|
||||
entries.append({
|
||||
"source": f"{subdir}/{filename}",
|
||||
"fact": value.get("description", value.get("fact", "")),
|
||||
"source_file": value.get("source_file"),
|
||||
"source_hash": value.get("source_hash"),
|
||||
"category": value.get("category", "unknown"),
|
||||
"confidence": value.get("confidence", 0.5)
|
||||
})
|
||||
except (yaml.YAMLError, IOError):
|
||||
pass
|
||||
|
||||
return entries
|
||||
|
||||
|
||||
def check_freshness(knowledge_dir: str, repo_root: str = ".",
|
||||
days: int = 1) -> Dict[str, Any]:
|
||||
"""
|
||||
Check freshness of knowledge entries against recent code changes.
|
||||
|
||||
Returns:
|
||||
{
|
||||
"timestamp": ISO timestamp,
|
||||
"total_entries": int,
|
||||
"stale_entries": [...],
|
||||
"fresh_entries": [...],
|
||||
"git_changes": {...},
|
||||
"summary": {...}
|
||||
}
|
||||
"""
|
||||
entries = load_knowledge_entries(knowledge_dir)
|
||||
git_changes = get_git_file_changes(repo_root, days)
|
||||
|
||||
stale_entries = []
|
||||
fresh_entries = []
|
||||
|
||||
for entry in entries:
|
||||
source_file = entry.get("source_file")
|
||||
if not source_file:
|
||||
# Entry without source file reference
|
||||
fresh_entries.append({**entry, "status": "no_source"})
|
||||
continue
|
||||
|
||||
# Check if source file was recently modified
|
||||
is_stale = False
|
||||
reason = ""
|
||||
|
||||
if source_file in git_changes["modified"]:
|
||||
is_stale = True
|
||||
reason = "source_modified"
|
||||
elif source_file in git_changes["deleted"]:
|
||||
is_stale = True
|
||||
reason = "source_deleted"
|
||||
elif source_file in git_changes["added"]:
|
||||
is_stale = True
|
||||
reason = "source_added"
|
||||
|
||||
# Also check hash if available
|
||||
stored_hash = entry.get("source_hash")
|
||||
if stored_hash:
|
||||
full_path = os.path.join(repo_root, source_file)
|
||||
current_hash = compute_file_hash(full_path)
|
||||
|
||||
if current_hash is None:
|
||||
is_stale = True
|
||||
reason = "source_missing"
|
||||
elif current_hash != stored_hash:
|
||||
is_stale = True
|
||||
reason = "hash_mismatch"
|
||||
|
||||
if is_stale:
|
||||
stale_entries.append({
|
||||
**entry,
|
||||
"status": "stale",
|
||||
"reason": reason
|
||||
})
|
||||
else:
|
||||
fresh_entries.append({**entry, "status": "fresh"})
|
||||
|
||||
# Compute summary
|
||||
total = len(entries)
|
||||
stale_count = len(stale_entries)
|
||||
fresh_count = len(fresh_entries)
|
||||
|
||||
# Group stale entries by reason
|
||||
stale_by_reason = {}
|
||||
for entry in stale_entries:
|
||||
reason = entry.get("reason", "unknown")
|
||||
if reason not in stale_by_reason:
|
||||
stale_by_reason[reason] = 0
|
||||
stale_by_reason[reason] += 1
|
||||
|
||||
return {
|
||||
"timestamp": datetime.now(timezone.utc).isoformat(),
|
||||
"total_entries": total,
|
||||
"stale_entries": stale_entries,
|
||||
"fresh_entries": fresh_entries,
|
||||
"git_changes": git_changes,
|
||||
"summary": {
|
||||
"total": total,
|
||||
"stale": stale_count,
|
||||
"fresh": fresh_count,
|
||||
"stale_percentage": round(stale_count / total * 100, 1) if total > 0 else 0,
|
||||
"stale_by_reason": stale_by_reason,
|
||||
"git_changes_summary": {
|
||||
"modified": len(git_changes["modified"]),
|
||||
"added": len(git_changes["added"]),
|
||||
"deleted": len(git_changes["deleted"])
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
def update_stale_hashes(knowledge_dir: str, repo_root: str = ".") -> int:
|
||||
"""
|
||||
Update hashes for stale entries. Returns count of updated entries.
|
||||
"""
|
||||
entries = load_knowledge_entries(knowledge_dir)
|
||||
updated = 0
|
||||
|
||||
# This is a simplified version - in practice, you'd need to
|
||||
# write back to the specific YAML files
|
||||
for entry in entries:
|
||||
source_file = entry.get("source_file")
|
||||
if not source_file:
|
||||
continue
|
||||
|
||||
full_path = os.path.join(repo_root, source_file)
|
||||
current_hash = compute_file_hash(full_path)
|
||||
|
||||
if current_hash and entry.get("source_hash") != current_hash:
|
||||
# Mark for update (in practice, you'd write back to the file)
|
||||
updated += 1
|
||||
|
||||
return updated
|
||||
|
||||
|
||||
def format_report(result: Dict[str, Any], max_items: int = 20) -> str:
|
||||
"""Format freshness check results as a human-readable report."""
|
||||
timestamp = result["timestamp"]
|
||||
summary = result["summary"]
|
||||
stale_entries = result["stale_entries"]
|
||||
git_changes = result["git_changes"]
|
||||
|
||||
lines = [
|
||||
"Knowledge Freshness Report",
|
||||
"=" * 50,
|
||||
f"Generated: {timestamp}",
|
||||
f"Total entries: {summary['total']}",
|
||||
f"Stale entries: {summary['stale']} ({summary['stale_percentage']}%)",
|
||||
f"Fresh entries: {summary['fresh']}",
|
||||
""
|
||||
]
|
||||
|
||||
# Git changes summary
|
||||
lines.extend([
|
||||
"Git Changes (last 24h):",
|
||||
f" Modified: {len(git_changes['modified'])} files",
|
||||
f" Added: {len(git_changes['added'])} files",
|
||||
f" Deleted: {len(git_changes['deleted'])} files",
|
||||
""
|
||||
])
|
||||
|
||||
# Stale entries by reason
|
||||
if summary.get("stale_by_reason"):
|
||||
lines.extend([
|
||||
"Stale Entries by Reason:",
|
||||
""
|
||||
])
|
||||
for reason, count in summary["stale_by_reason"].items():
|
||||
lines.append(f" {reason}: {count}")
|
||||
lines.append("")
|
||||
|
||||
# List stale entries
|
||||
if stale_entries:
|
||||
lines.extend([
|
||||
"Stale Entries:",
|
||||
""
|
||||
])
|
||||
for i, entry in enumerate(stale_entries[:max_items], 1):
|
||||
source = entry.get("source_file", "?")
|
||||
reason = entry.get("reason", "unknown")
|
||||
fact = entry.get("fact", "")[:60]
|
||||
lines.append(f"{i:2d}. [{reason}] {source}")
|
||||
if fact:
|
||||
lines.append(f" {fact}")
|
||||
|
||||
if len(stale_entries) > max_items:
|
||||
lines.append(f"\n... and {len(stale_entries) - max_items} more")
|
||||
else:
|
||||
lines.append("No stale entries found. All knowledge is fresh!")
|
||||
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Knowledge Freshness Cron — detect stale entries from code changes")
|
||||
parser.add_argument("--knowledge-dir", required=True,
|
||||
help="Path to knowledge directory")
|
||||
parser.add_argument("--repo", default=".",
|
||||
help="Path to repository for git change detection")
|
||||
parser.add_argument("--days", type=int, default=1,
|
||||
help="Number of days to check for git changes (default: 1)")
|
||||
parser.add_argument("--json", action="store_true",
|
||||
help="Output as JSON instead of human-readable")
|
||||
parser.add_argument("--max", type=int, default=20,
|
||||
help="Maximum stale entries to show (default: 20)")
|
||||
parser.add_argument("--auto-reextract", action="store_true",
|
||||
help="Auto-re-extract knowledge for stale entries")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if not os.path.isdir(args.knowledge_dir):
|
||||
print(f"Error: {args.knowledge_dir} is not a directory", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
if not os.path.isdir(args.repo):
|
||||
print(f"Error: {args.repo} is not a directory", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
result = check_freshness(args.knowledge_dir, args.repo, args.days)
|
||||
|
||||
if args.json:
|
||||
print(json.dumps(result, indent=2))
|
||||
else:
|
||||
print(format_report(result, args.max))
|
||||
|
||||
# Auto-re-extract if requested
|
||||
if args.auto_reextract and result["stale_entries"]:
|
||||
print(f"\nAuto-re-extracting {len(result['stale_entries'])} stale entries...")
|
||||
# In a real implementation, this would call the harvester
|
||||
print("(Auto-re-extraction not yet implemented)")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,227 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Tests for scripts/freshness.py — 8 tests."""
|
||||
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import tempfile
|
||||
|
||||
sys.path.insert(0, os.path.join(os.path.dirname(__file__) or ".", ".."))
|
||||
import importlib.util
|
||||
spec = importlib.util.spec_from_file_location(
|
||||
"freshness", os.path.join(os.path.dirname(__file__) or ".", "..", "scripts", "freshness.py"))
|
||||
mod = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(mod)
|
||||
|
||||
compute_file_hash = mod.compute_file_hash
|
||||
check_freshness = mod.check_freshness
|
||||
load_knowledge_entries = mod.load_knowledge_entries
|
||||
|
||||
|
||||
def test_compute_file_hash():
|
||||
"""File hash should be computed correctly."""
|
||||
with tempfile.NamedTemporaryFile(mode='w', delete=False) as f:
|
||||
f.write("test content")
|
||||
f.flush()
|
||||
h = compute_file_hash(f.name)
|
||||
assert h is not None
|
||||
assert h.startswith("sha256:")
|
||||
os.unlink(f.name)
|
||||
print("PASS: test_compute_file_hash")
|
||||
|
||||
|
||||
def test_compute_file_hash_nonexistent():
|
||||
"""Nonexistent file should return None."""
|
||||
h = compute_file_hash("/nonexistent/file.txt")
|
||||
assert h is None
|
||||
print("PASS: test_compute_file_hash_nonexistent")
|
||||
|
||||
|
||||
def test_load_knowledge_entries_empty():
|
||||
"""Empty knowledge dir should return empty list."""
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
entries = load_knowledge_entries(tmpdir)
|
||||
assert entries == []
|
||||
print("PASS: test_load_knowledge_entries_empty")
|
||||
|
||||
|
||||
def test_load_knowledge_entries_from_index():
|
||||
"""Should load entries from index.json."""
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
# Create index.json
|
||||
index_path = os.path.join(tmpdir, "index.json")
|
||||
with open(index_path, "w") as f:
|
||||
json.dump({
|
||||
"facts": [
|
||||
{
|
||||
"fact": "Test fact",
|
||||
"source_file": "test.py",
|
||||
"source_hash": "sha256:abc123",
|
||||
"category": "fact",
|
||||
"confidence": 0.9
|
||||
}
|
||||
]
|
||||
}, f)
|
||||
|
||||
entries = load_knowledge_entries(tmpdir)
|
||||
assert len(entries) == 1
|
||||
assert entries[0]["fact"] == "Test fact"
|
||||
assert entries[0]["source_file"] == "test.py"
|
||||
print("PASS: test_load_knowledge_entries_from_index")
|
||||
|
||||
|
||||
def test_load_knowledge_entries_from_yaml():
|
||||
"""Should load entries from YAML files."""
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
# Create global directory
|
||||
global_dir = os.path.join(tmpdir, "global")
|
||||
os.makedirs(global_dir)
|
||||
|
||||
# Create YAML file
|
||||
yaml_path = os.path.join(global_dir, "test.yaml")
|
||||
with open(yaml_path, "w") as f:
|
||||
f.write("""
|
||||
pitfalls:
|
||||
- description: "Test pitfall"
|
||||
source_file: "test.py"
|
||||
source_hash: "sha256:def456"
|
||||
category: "pitfall"
|
||||
confidence: 0.8
|
||||
""")
|
||||
|
||||
entries = load_knowledge_entries(tmpdir)
|
||||
assert len(entries) == 1
|
||||
assert entries[0]["fact"] == "Test pitfall"
|
||||
assert entries[0]["category"] == "pitfall"
|
||||
print("PASS: test_load_knowledge_entries_from_yaml")
|
||||
|
||||
|
||||
def test_check_freshness_no_changes():
|
||||
"""With no source file reference, entries should be counted correctly."""
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
# Create knowledge dir
|
||||
knowledge_dir = os.path.join(tmpdir, "knowledge")
|
||||
os.makedirs(knowledge_dir)
|
||||
|
||||
# Create repo dir
|
||||
repo_dir = os.path.join(tmpdir, "repo")
|
||||
os.makedirs(repo_dir)
|
||||
|
||||
# Create index.json with entry that has no source_file
|
||||
index_path = os.path.join(knowledge_dir, "index.json")
|
||||
with open(index_path, "w") as f:
|
||||
json.dump({
|
||||
"facts": [
|
||||
{
|
||||
"fact": "General knowledge",
|
||||
"category": "fact",
|
||||
"confidence": 0.9
|
||||
# No source_file or source_hash
|
||||
}
|
||||
]
|
||||
}, f)
|
||||
|
||||
result = check_freshness(knowledge_dir, repo_dir, days=1)
|
||||
|
||||
# Entry without source_file should be counted as "fresh" (no_source status)
|
||||
assert result["summary"]["total"] == 1
|
||||
assert result["summary"]["stale"] == 0
|
||||
assert result["summary"]["fresh"] == 1
|
||||
assert result["fresh_entries"][0]["status"] == "no_source"
|
||||
print("PASS: test_check_freshness_no_changes")
|
||||
|
||||
|
||||
def test_check_freshness_with_hash_mismatch():
|
||||
"""Hash mismatch should mark entry as stale."""
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
# Create knowledge dir
|
||||
knowledge_dir = os.path.join(tmpdir, "knowledge")
|
||||
os.makedirs(knowledge_dir)
|
||||
|
||||
# Create repo dir with a file
|
||||
repo_dir = os.path.join(tmpdir, "repo")
|
||||
os.makedirs(repo_dir)
|
||||
|
||||
test_file = os.path.join(repo_dir, "test.py")
|
||||
with open(test_file, "w") as f:
|
||||
f.write("print('hello')")
|
||||
|
||||
# Create index.json with wrong hash
|
||||
index_path = os.path.join(knowledge_dir, "index.json")
|
||||
with open(index_path, "w") as f:
|
||||
json.dump({
|
||||
"facts": [
|
||||
{
|
||||
"fact": "Test fact",
|
||||
"source_file": "test.py",
|
||||
"source_hash": "sha256:wronghash",
|
||||
"category": "fact",
|
||||
"confidence": 0.9
|
||||
}
|
||||
]
|
||||
}, f)
|
||||
|
||||
# Initialize git repo
|
||||
os.system(f"cd {repo_dir} && git init && git add . && git commit -m 'init' 2>/dev/null")
|
||||
|
||||
result = check_freshness(knowledge_dir, repo_dir, days=1)
|
||||
|
||||
assert result["summary"]["total"] == 1
|
||||
assert result["summary"]["stale"] == 1
|
||||
assert result["summary"]["fresh"] == 0
|
||||
assert result["stale_entries"][0]["reason"] == "hash_mismatch"
|
||||
print("PASS: test_check_freshness_with_hash_mismatch")
|
||||
|
||||
|
||||
def test_check_freshness_missing_source():
|
||||
"""Missing source file should mark entry as stale."""
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
# Create knowledge dir
|
||||
knowledge_dir = os.path.join(tmpdir, "knowledge")
|
||||
os.makedirs(knowledge_dir)
|
||||
|
||||
# Create repo dir (without the referenced file)
|
||||
repo_dir = os.path.join(tmpdir, "repo")
|
||||
os.makedirs(repo_dir)
|
||||
|
||||
# Create index.json referencing nonexistent file
|
||||
index_path = os.path.join(knowledge_dir, "index.json")
|
||||
with open(index_path, "w") as f:
|
||||
json.dump({
|
||||
"facts": [
|
||||
{
|
||||
"fact": "Test fact",
|
||||
"source_file": "nonexistent.py",
|
||||
"source_hash": "sha256:abc123",
|
||||
"category": "fact",
|
||||
"confidence": 0.9
|
||||
}
|
||||
]
|
||||
}, f)
|
||||
|
||||
# Initialize git repo
|
||||
os.system(f"cd {repo_dir} && git init && git add . && git commit -m 'init' 2>/dev/null")
|
||||
|
||||
result = check_freshness(knowledge_dir, repo_dir, days=1)
|
||||
|
||||
assert result["summary"]["total"] == 1
|
||||
assert result["summary"]["stale"] == 1
|
||||
assert result["summary"]["fresh"] == 0
|
||||
assert result["stale_entries"][0]["reason"] == "source_missing"
|
||||
print("PASS: test_check_freshness_missing_source")
|
||||
|
||||
|
||||
def run_all():
|
||||
test_compute_file_hash()
|
||||
test_compute_file_hash_nonexistent()
|
||||
test_load_knowledge_entries_empty()
|
||||
test_load_knowledge_entries_from_index()
|
||||
test_load_knowledge_entries_from_yaml()
|
||||
test_check_freshness_no_changes()
|
||||
test_check_freshness_with_hash_mismatch()
|
||||
test_check_freshness_missing_source()
|
||||
print("\nAll 8 tests passed!")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
run_all()
|
||||
108
tests/test_quality_gate.py
Normal file
108
tests/test_quality_gate.py
Normal file
@@ -0,0 +1,108 @@
|
||||
"""
|
||||
Tests for quality_gate.py — Knowledge entry quality scoring.
|
||||
"""
|
||||
|
||||
import unittest
|
||||
from datetime import datetime, timezone, timedelta
|
||||
|
||||
import sys
|
||||
from pathlib import Path
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent))
|
||||
|
||||
from quality_gate import (
|
||||
score_specificity,
|
||||
score_actionability,
|
||||
score_freshness,
|
||||
score_source_quality,
|
||||
score_entry,
|
||||
filter_entries,
|
||||
)
|
||||
|
||||
|
||||
class TestScoreSpecificity(unittest.TestCase):
|
||||
def test_specific_content_scores_high(self):
|
||||
content = "Run `python3 deploy.py --env prod` on 2026-04-15. Example: step 1 configure nginx."
|
||||
score = score_specificity(content)
|
||||
self.assertGreater(score, 0.6)
|
||||
|
||||
def test_vague_content_scores_low(self):
|
||||
content = "It generally depends. Various factors might affect this. Basically, it varies."
|
||||
score = score_specificity(content)
|
||||
self.assertLess(score, 0.5)
|
||||
|
||||
def test_empty_scores_baseline(self):
|
||||
score = score_specificity("")
|
||||
self.assertAlmostEqual(score, 0.5, delta=0.1)
|
||||
|
||||
|
||||
class TestScoreActionability(unittest.TestCase):
|
||||
def test_actionable_content_scores_high(self):
|
||||
content = "1. Run `pip install -r requirements.txt`\n2. Execute `python3 train.py`\n3. Verify with `pytest`"
|
||||
score = score_actionability(content)
|
||||
self.assertGreater(score, 0.6)
|
||||
|
||||
def test_abstract_content_scores_low(self):
|
||||
content = "The concept of intelligence is fascinating and multifaceted."
|
||||
score = score_actionability(content)
|
||||
self.assertLess(score, 0.5)
|
||||
|
||||
|
||||
class TestScoreFreshness(unittest.TestCase):
|
||||
def test_recent_timestamp_scores_high(self):
|
||||
recent = datetime.now(timezone.utc).isoformat()
|
||||
score = score_freshness(recent)
|
||||
self.assertGreater(score, 0.9)
|
||||
|
||||
def test_old_timestamp_scores_low(self):
|
||||
old = (datetime.now(timezone.utc) - timedelta(days=365)).isoformat()
|
||||
score = score_freshness(old)
|
||||
self.assertLess(score, 0.2)
|
||||
|
||||
def test_none_returns_baseline(self):
|
||||
score = score_freshness(None)
|
||||
self.assertEqual(score, 0.5)
|
||||
|
||||
|
||||
class TestScoreSourceQuality(unittest.TestCase):
|
||||
def test_claude_scores_high(self):
|
||||
self.assertGreater(score_source_quality("claude-sonnet"), 0.85)
|
||||
|
||||
def test_ollama_scores_lower(self):
|
||||
self.assertLess(score_source_quality("ollama"), 0.7)
|
||||
|
||||
def test_unknown_returns_default(self):
|
||||
self.assertEqual(score_source_quality("unknown"), 0.5)
|
||||
|
||||
|
||||
class TestScoreEntry(unittest.TestCase):
|
||||
def test_good_entry_scores_high(self):
|
||||
entry = {
|
||||
"content": "To deploy: run `kubectl apply -f deployment.yaml`. Verify with `kubectl get pods`.",
|
||||
"model": "claude-sonnet",
|
||||
"timestamp": datetime.now(timezone.utc).isoformat(),
|
||||
}
|
||||
score = score_entry(entry)
|
||||
self.assertGreater(score, 0.6)
|
||||
|
||||
def test_poor_entry_scores_low(self):
|
||||
entry = {
|
||||
"content": "It depends. Various things might happen.",
|
||||
"model": "unknown",
|
||||
}
|
||||
score = score_entry(entry)
|
||||
self.assertLess(score, 0.5)
|
||||
|
||||
|
||||
class TestFilterEntries(unittest.TestCase):
|
||||
def test_filters_low_quality(self):
|
||||
entries = [
|
||||
{"content": "Run `deploy.py` to fix the issue.", "model": "claude"},
|
||||
{"content": "It might work sometimes.", "model": "unknown"},
|
||||
{"content": "Configure nginx: step 1 edit nginx.conf", "model": "gpt-4"},
|
||||
]
|
||||
filtered = filter_entries(entries, threshold=0.5)
|
||||
self.assertGreaterEqual(len(filtered), 2)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user