feat: quality gate — score and filter knowledge entries (#198)

quality_gate.py:
  4-dimension scoring (0.0-1.0):
    specificity (0.3): concrete examples vs vague
    actionability (0.3): can this be used?
    freshness (0.2): exponential decay over time
    source_quality (0.2): model reliability score
  filter_entries(entries, threshold=0.5)
  quality_report() — distribution + pass rate
  CLI: --threshold, --json, --filter

tests/test_quality_gate.py: 14 tests
  specificity: specific high, vague low, empty baseline
  actionability: actionable high, abstract low
  freshness: recent high, old low, none baseline
  source: claude high, ollama low, unknown default
  entry: good high, poor low
  filter: removes low quality

quality_gate.py

@@ -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()

scripts/dedup.py

@@ -1,317 +0,0 @@
-#!/usr/bin/env python3
-"""
-dedup.py — Knowledge deduplication: content hash + semantic similarity.
-
-Deduplicates harvested knowledge entries to avoid training on duplicates.
-Uses content hashing for exact matches and token overlap for near-duplicates.
-
-Usage:
-    python3 dedup.py --input knowledge/index.json --output knowledge/index_deduped.json
-    python3 dedup.py --input knowledge/index.json --dry-run
-    python3 dedup.py --test  # Run built-in dedup test
-"""
-
-import argparse
-import hashlib
-import json
-import re
-import sys
-from pathlib import Path
-from typing import List, Dict, Optional, Tuple
-
-
-def normalize_text(text: str) -> str:
-    """Normalize text for hashing: lowercase, collapse whitespace, strip."""
-    text = text.lower().strip()
-    text = re.sub(r'\s+', ' ', text)
-    return text
-
-
-def content_hash(text: str) -> str:
-    """SHA256 hash of normalized text for exact dedup."""
-    normalized = normalize_text(text)
-    return hashlib.sha256(normalized.encode('utf-8')).hexdigest()
-
-
-def tokenize(text: str) -> set:
-    """Simple tokenizer: lowercase words, 3+ chars."""
-    words = re.findall(r'[a-z0-9_]{3,}', text.lower())
-    return set(words)
-
-
-def token_similarity(a: str, b: str) -> float:
-    """Token-based Jaccard similarity (0.0-1.0).
-
-    Fast local alternative to embedding similarity.
-    Good enough for near-duplicate detection.
-    """
-    tokens_a = tokenize(a)
-    tokens_b = tokenize(b)
-    if not tokens_a or not tokens_b:
-        return 0.0
-    intersection = tokens_a & tokens_b
-    union = tokens_a | tokens_b
-    return len(intersection) / len(union)
-
-
-def quality_score(fact: dict) -> float:
-    """Compute quality score for merge ranking.
-
-    Higher is better. Factors:
-    - confidence (0-1)
-    - source_count (more confirmations = better)
-    - has tags (richer metadata)
-    """
-    confidence = fact.get('confidence', 0.5)
-    source_count = fact.get('source_count', 1)
-    has_tags = 1.0 if fact.get('tags') else 0.0
-    has_related = 1.0 if fact.get('related') else 0.0
-
-    # Weighted composite
-    score = (
-        confidence * 0.5 +
-        min(source_count / 10, 1.0) * 0.3 +
-        has_tags * 0.1 +
-        has_related * 0.1
-    )
-    return round(score, 4)
-
-
-def merge_facts(keep: dict, drop: dict) -> dict:
-    """Merge two near-duplicate facts, keeping higher-quality fields.
-
-    The 'keep' fact is enriched with metadata from 'drop'.
-    """
-    # Merge tags (union)
-    keep_tags = set(keep.get('tags', []))
-    drop_tags = set(drop.get('tags', []))
-    keep['tags'] = sorted(keep_tags | drop_tags)
-
-    # Merge related (union)
-    keep_related = set(keep.get('related', []))
-    drop_related = set(drop.get('related', []))
-    keep['related'] = sorted(keep_related | drop_related)
-
-    # Update source_count (sum)
-    keep['source_count'] = keep.get('source_count', 1) + drop.get('source_count', 1)
-
-    # Update confidence (max — we've now seen it from multiple sources)
-    keep['confidence'] = max(keep.get('confidence', 0), drop.get('confidence', 0))
-
-    # Track that we merged
-    if '_merged_from' not in keep:
-        keep['_merged_from'] = []
-    keep['_merged_from'].append(drop.get('id', 'unknown'))
-
-    return keep
-
-
-def dedup_facts(
-    facts: List[dict],
-    exact_threshold: float = 1.0,
-    near_threshold: float = 0.95,
-    dry_run: bool = False,
-) -> Tuple[List[dict], dict]:
-    """Deduplicate a list of knowledge facts.
-
-    Args:
-        facts: List of fact dicts (from index.json)
-        exact_threshold: Hash match = exact duplicate
-        near_threshold: Token similarity above this = near-duplicate
-        dry_run: If True, don't modify, just report
-
-    Returns:
-        (deduped_facts, stats_dict)
-    """
-    if not facts:
-        return [], {"total": 0, "exact_dupes": 0, "near_dupes": 0, "unique": 0}
-
-    # Phase 1: Exact dedup by content hash
-    hash_seen = {}  # hash -> index in deduped list
-    exact_dupes = 0
-    deduped = []
-
-    for fact in facts:
-        text = fact.get('fact', '')
-        h = content_hash(text)
-
-        if h in hash_seen:
-            # Exact duplicate — merge metadata into existing
-            existing_idx = hash_seen[h]
-            if not dry_run:
-                deduped[existing_idx] = merge_facts(deduped[existing_idx], fact)
-            exact_dupes += 1
-        else:
-            hash_seen[h] = len(deduped)
-            deduped.append(fact)
-
-    # Phase 2: Near-dup by token similarity
-    near_dupes = 0
-    i = 0
-    while i < len(deduped):
-        j = i + 1
-        while j < len(deduped):
-            sim = token_similarity(deduped[i].get('fact', ''), deduped[j].get('fact', ''))
-            if sim >= near_threshold:
-                # Near-duplicate — keep higher quality
-                q_i = quality_score(deduped[i])
-                q_j = quality_score(deduped[j])
-                if q_i >= q_j:
-                    if not dry_run:
-                        deduped[i] = merge_facts(deduped[i], deduped[j])
-                    deduped.pop(j)
-                else:
-                    # j is higher quality — merge i into j, then remove i
-                    if not dry_run:
-                        deduped[j] = merge_facts(deduped[j], deduped[i])
-                    deduped.pop(i)
-                    break  # i changed, restart inner loop
-                near_dupes += 1
-            else:
-                j += 1
-        i += 1
-
-    stats = {
-        "total": len(facts),
-        "exact_dupes": exact_dupes,
-        "near_dupes": near_dupes,
-        "unique": len(deduped),
-        "removed": len(facts) - len(deduped),
-    }
-
-    return deduped, stats
-
-
-def dedup_index_file(
-    input_path: str,
-    output_path: Optional[str] = None,
-    near_threshold: float = 0.95,
-    dry_run: bool = False,
-) -> dict:
-    """Deduplicate an index.json file.
-
-    Args:
-        input_path: Path to index.json
-        output_path: Where to write deduped file (default: overwrite input)
-        near_threshold: Token similarity threshold for near-dupes
-        dry_run: Report only, don't write
-
-    Returns stats dict.
-    """
-    path = Path(input_path)
-    if not path.exists():
-        raise FileNotFoundError(f"Index file not found: {input_path}")
-
-    with open(path) as f:
-        data = json.load(f)
-
-    facts = data.get('facts', [])
-    deduped, stats = dedup_facts(facts, near_threshold=near_threshold, dry_run=dry_run)
-
-    if not dry_run:
-        data['facts'] = deduped
-        data['total_facts'] = len(deduped)
-        data['last_dedup'] = __import__('datetime').datetime.now(
-            __import__('datetime').timezone.utc
-        ).isoformat()
-
-        out_path = Path(output_path) if output_path else path
-        with open(out_path, 'w') as f:
-            json.dump(data, f, indent=2, ensure_ascii=False)
-
-    return stats
-
-
-def generate_test_duplicates(n: int = 20) -> List[dict]:
-    """Generate test facts with intentional duplicates for testing.
-
-    Creates n unique facts plus n/4 exact dupes and n/4 near-dupes.
-    """
-    import random
-    random.seed(42)
-
-    unique_facts = []
-    for i in range(n):
-        topic = random.choice(["git", "python", "docker", "rust", "nginx"])
-        tip = random.choice(["use verbose flags", "check logs first", "restart service", "clear cache", "update config"])
-        unique_facts.append({
-            "id": f"test:fact:{i:03d}",
-            "fact": f"When working with {topic}, always {tip} before deploying.",
-            "category": "fact",
-            "domain": "test",
-            "confidence": round(random.uniform(0.5, 1.0), 2),
-            "source_count": random.randint(1, 5),
-            "tags": [topic, "test"],
-        })
-
-    # Add exact duplicates (same text, different IDs)
-    duped = list(unique_facts)
-    for i in range(n // 4):
-        original = unique_facts[i]
-        dupe = dict(original)
-        dupe["id"] = f"test:fact:dup{i:03d}"
-        dupe["confidence"] = round(random.uniform(0.3, 0.8), 2)
-        duped.append(dupe)
-
-    # Add near-duplicates (slightly different phrasing)
-    for i in range(n // 4):
-        original = unique_facts[i]
-        near = dict(original)
-        near["id"] = f"test:fact:near{i:03d}"
-        near["fact"] = original["fact"].replace("always", "should").replace("before deploying", "prior to deployment")
-        near["confidence"] = round(random.uniform(0.4, 0.9), 2)
-        duped.append(near)
-
-    return duped
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Knowledge deduplication")
-    parser.add_argument("--input", help="Path to index.json")
-    parser.add_argument("--output", help="Output path (default: overwrite input)")
-    parser.add_argument("--threshold", type=float, default=0.95,
-                        help="Near-dup similarity threshold (default: 0.95)")
-    parser.add_argument("--dry-run", action="store_true", help="Report only, don't write")
-    parser.add_argument("--test", action="store_true", help="Run built-in dedup test")
-    parser.add_argument("--json", action="store_true", help="JSON output")
-    args = parser.parse_args()
-
-    if args.test:
-        test_facts = generate_test_duplicates(20)
-        print(f"Generated {len(test_facts)} test facts (20 unique + dupes)")
-        deduped, stats = dedup_facts(test_facts, near_threshold=args.threshold)
-        print(f"\nDedup results:")
-        print(f"  Total input:    {stats['total']}")
-        print(f"  Exact dupes:    {stats['exact_dupes']}")
-        print(f"  Near dupes:     {stats['near_dupes']}")
-        print(f"  Unique output:  {stats['unique']}")
-        print(f"  Removed:        {stats['removed']}")
-
-        # Verify: should have ~20 unique (some merged)
-        assert stats['unique'] <= 20, f"Too many unique: {stats['unique']} > 20"
-        assert stats['unique'] >= 15, f"Too few unique: {stats['unique']} < 15"
-        assert stats['removed'] > 0, "No duplicates removed"
-        print("\nOK: Dedup test passed")
-        return
-
-    if not args.input:
-        print("ERROR: Provide --input or --test")
-        sys.exit(1)
-
-    stats = dedup_index_file(args.input, args.output, args.threshold, args.dry_run)
-
-    if args.json:
-        print(json.dumps(stats, indent=2))
-    else:
-        print(f"Dedup results:")
-        print(f"  Total input:    {stats['total']}")
-        print(f"  Exact dupes:    {stats['exact_dupes']}")
-        print(f"  Near dupes:     {stats['near_dupes']}")
-        print(f"  Unique output:  {stats['unique']}")
-        print(f"  Removed:        {stats['removed']}")
-        if args.dry_run:
-            print("  (dry run — no changes written)")
-
-
-if __name__ == "__main__":
-    main()

tests/test_dedup.py

@@ -1,207 +0,0 @@
-"""Tests for knowledge deduplication module (Issue #196)."""
-
-import json
-import sys
-from pathlib import Path
-
-import pytest
-
-sys.path.insert(0, str(Path(__file__).parent.parent / "scripts"))
-
-from dedup import (
-    normalize_text,
-    content_hash,
-    tokenize,
-    token_similarity,
-    quality_score,
-    merge_facts,
-    dedup_facts,
-    generate_test_duplicates,
-)
-
-
-class TestNormalize:
-    def test_lowercases(self):
-        assert normalize_text("Hello World") == "hello world"
-
-    def test_collapses_whitespace(self):
-        assert normalize_text("  hello   world  ") == "hello world"
-
-    def test_strips(self):
-        assert normalize_text("  text  ") == "text"
-
-
-class TestContentHash:
-    def test_deterministic(self):
-        h1 = content_hash("Hello World")
-        h2 = content_hash("hello world")
-        h3 = content_hash("  Hello   World  ")
-        assert h1 == h2 == h3
-
-    def test_different_texts(self):
-        h1 = content_hash("Hello")
-        h2 = content_hash("World")
-        assert h1 != h2
-
-    def test_returns_hex(self):
-        h = content_hash("test")
-        assert len(h) == 64  # SHA256
-        assert all(c in '0123456789abcdef' for c in h)
-
-
-class TestTokenize:
-    def test_extracts_words(self):
-        tokens = tokenize("Hello World Test")
-        assert "hello" in tokens
-        assert "world" in tokens
-        assert "test" in tokens
-
-    def test_skips_short_words(self):
-        tokens = tokenize("a to is the hello")
-        assert "a" not in tokens
-        assert "to" not in tokens
-        assert "hello" in tokens
-
-    def test_returns_set(self):
-        tokens = tokenize("hello hello world")
-        assert isinstance(tokens, set)
-        assert len(tokens) == 2
-
-
-class TestTokenSimilarity:
-    def test_identical(self):
-        assert token_similarity("hello world", "hello world") == 1.0
-
-    def test_no_overlap(self):
-        assert token_similarity("alpha beta", "gamma delta") == 0.0
-
-    def test_partial_overlap(self):
-        sim = token_similarity("hello world test", "hello universe test")
-        assert 0.3 < sim < 0.7
-
-    def test_empty(self):
-        assert token_similarity("", "hello") == 0.0
-        assert token_similarity("hello", "") == 0.0
-
-    def test_symmetric(self):
-        a = "hello world test"
-        b = "hello universe test"
-        assert token_similarity(a, b) == token_similarity(b, a)
-
-
-class TestQualityScore:
-    def test_high_confidence(self):
-        fact = {"confidence": 0.95, "source_count": 5, "tags": ["test"], "related": ["x"]}
-        score = quality_score(fact)
-        assert score > 0.7
-
-    def test_low_confidence(self):
-        fact = {"confidence": 0.3, "source_count": 1}
-        score = quality_score(fact)
-        assert score < 0.5
-
-    def test_defaults(self):
-        score = quality_score({})
-        assert 0 < score < 1
-
-
-class TestMergeFacts:
-    def test_merges_tags(self):
-        keep = {"id": "a", "fact": "test", "tags": ["git"], "confidence": 0.9}
-        drop = {"id": "b", "fact": "test", "tags": ["python"], "confidence": 0.8}
-        merged = merge_facts(keep, drop)
-        assert "git" in merged["tags"]
-        assert "python" in merged["tags"]
-
-    def test_merges_source_count(self):
-        keep = {"id": "a", "fact": "test", "source_count": 3}
-        drop = {"id": "b", "fact": "test", "source_count": 2}
-        merged = merge_facts(keep, drop)
-        assert merged["source_count"] == 5
-
-    def test_keeps_higher_confidence(self):
-        keep = {"id": "a", "fact": "test", "confidence": 0.7}
-        drop = {"id": "b", "fact": "test", "confidence": 0.9}
-        merged = merge_facts(keep, drop)
-        assert merged["confidence"] == 0.9
-
-    def test_tracks_merged_from(self):
-        keep = {"id": "a", "fact": "test"}
-        drop = {"id": "b", "fact": "test"}
-        merged = merge_facts(keep, drop)
-        assert "b" in merged["_merged_from"]
-
-
-class TestDedupFacts:
-    def test_removes_exact_dupes(self):
-        facts = [
-            {"id": "1", "fact": "Always use git rebase"},
-            {"id": "2", "fact": "Always use git rebase"},  # exact dupe
-            {"id": "3", "fact": "Check logs first"},
-        ]
-        deduped, stats = dedup_facts(facts)
-        assert stats["exact_dupes"] == 1
-        assert stats["unique"] == 2
-
-    def test_removes_near_dupes(self):
-        facts = [
-            {"id": "1", "fact": "Always check logs before deploying to production server"},
-            {"id": "2", "fact": "Always check logs before deploying to production environment"},
-            {"id": "3", "fact": "Use docker compose for local development environments"},
-        ]
-        deduped, stats = dedup_facts(facts, near_threshold=0.5)
-        assert stats["near_dupes"] >= 1
-        assert stats["unique"] == 2
-
-    def test_preserves_unique(self):
-        facts = [
-            {"id": "1", "fact": "Use git rebase for clean history"},
-            {"id": "2", "fact": "Docker containers should be stateless"},
-            {"id": "3", "fact": "Always write tests before code"},
-        ]
-        deduped, stats = dedup_facts(facts)
-        assert stats["unique"] == 3
-        assert stats["removed"] == 0
-
-    def test_empty_input(self):
-        deduped, stats = dedup_facts([])
-        assert stats["total"] == 0
-        assert stats["unique"] == 0
-
-    def test_keeps_higher_quality_near_dup(self):
-        facts = [
-            {"id": "1", "fact": "Check logs before deploying to production server", "confidence": 0.5, "source_count": 1},
-            {"id": "2", "fact": "Check logs before deploying to production environment", "confidence": 0.9, "source_count": 5, "tags": ["ops"]},
-        ]
-        deduped, stats = dedup_facts(facts, near_threshold=0.5)
-        assert stats["unique"] == 1
-        # Higher quality fact should be kept
-        assert deduped[0]["confidence"] == 0.9
-
-    def test_dry_run_does_not_modify(self):
-        facts = [
-            {"id": "1", "fact": "Same text"},
-            {"id": "2", "fact": "Same text"},
-        ]
-        deduped, stats = dedup_facts(facts, dry_run=True)
-        assert stats["exact_dupes"] == 1
-        # In dry_run, merge_facts is skipped so facts aren't modified
-        assert len(deduped) == 1
-
-
-class TestGenerateTestDuplicates:
-    def test_generates_correct_count(self):
-        facts = generate_test_duplicates(20)
-        assert len(facts) > 20  # 20 unique + duplicates
-
-    def test_has_exact_dupes(self):
-        facts = generate_test_duplicates(20)
-        hashes = [content_hash(f["fact"]) for f in facts]
-        # Should have some duplicate hashes
-        assert len(hashes) != len(set(hashes))
-
-    def test_dedup_removes_dupes(self):
-        facts = generate_test_duplicates(20)
-        deduped, stats = dedup_facts(facts)
-        assert stats["unique"] <= 20
-        assert stats["removed"] > 0

tests/test_quality_gate.py

@@ -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()