test(scanner): unit tests for github_trending_scanner

scripts/entity_extractor.py

@@ -1,268 +0,0 @@
-#!/usr/bin/env python3
-"""
-entity_extractor.py — Extract named entities from text sources.
-
-Extracts: people, projects, tools, concepts, repos from session transcripts,
-README files, issue bodies, or any text input.
-
-Output: knowledge/entities.json with deduplicated entity list and occurrence counts.
-"""
-
-import argparse
-import json
-import os
-import sys
-import time
-from datetime import datetime, timezone
-from pathlib import Path
-from typing import Optional
-
-SCRIPT_DIR = Path(__file__).parent.absolute()
-sys.path.insert(0, str(SCRIPT_DIR))
-
-from session_reader import read_session, messages_to_text
-
-# --- Configuration ---
-DEFAULT_API_BASE = os.environ.get("HARVESTER_API_BASE", "https://api.nousresearch.com/v1")
-DEFAULT_API_KEY = os.environ.get("HARVESTER_API_KEY", "")
-DEFAULT_MODEL = os.environ.get("HARVESTER_MODEL", "xiaomi/mimo-v2-pro")
-KNOWLEDGE_DIR = os.environ.get("HARVESTER_KNOWLEDGE_DIR", "knowledge")
-PROMPT_PATH = os.environ.get("ENTITY_PROMPT_PATH", str(SCRIPT_DIR.parent / "templates" / "entity-extraction-prompt.md"))
-
-API_KEY_PATHS = [
-    os.path.expanduser("~/.config/nous/key"),
-    os.path.expanduser("~/.hermes/keymaxxing/active/minimax.key"),
-    os.path.expanduser("~/.config/openrouter/key"),
-]
-
-def find_api_key() -> str:
-    for path in API_KEY_PATHS:
-        if os.path.exists(path):
-            with open(path) as f:
-                key = f.read().strip()
-                if key:
-                    return key
-    return ""
-
-def load_prompt() -> str:
-    path = Path(PROMPT_PATH)
-    if not path.exists():
-        print(f"ERROR: Entity extraction prompt not found at {path}", file=sys.stderr)
-        sys.exit(1)
-    return path.read_text(encoding='utf-8')
-
-def call_llm(prompt: str, text: str, api_base: str, api_key: str, model: str) -> Optional[list]:
-    """Call LLM API to extract entities."""
-    import urllib.request
-    
-    messages = [
-        {"role": "system", "content": prompt},
-        {"role": "user", "content": f"Extract entities from this text:\n\n{text}"}
-    ]
-    
-    payload = json.dumps({
-        "model": model,
-        "messages": messages,
-        "temperature": 0.0,
-        "max_tokens": 2048
-    }).encode('utf-8')
-    
-    req = urllib.request.Request(
-        f"{api_base}/chat/completions",
-        data=payload,
-        headers={"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"},
-        method="POST"
-    )
-    
-    try:
-        with urllib.request.urlopen(req, timeout=60) as resp:
-            result = json.loads(resp.read().decode('utf-8'))
-            content = result["choices"][0]["message"]["content"]
-            return parse_response(content)
-    except Exception as e:
-        print(f"ERROR: LLM call failed: {e}", file=sys.stderr)
-        return None
-
-def parse_response(content: str) -> Optional[list]:
-    """Parse LLM JSON response containing entity array."""
-    try:
-        data = json.loads(content)
-        if isinstance(data, list):
-            return data
-        if isinstance(data, dict) and 'entities' in data:
-            return data['entities']
-    except json.JSONDecodeError:
-        pass
-    import re
-    match = re.search(r'```(?:json)?\s*(\[.*?\])\s*```', content, re.DOTALL)
-    if match:
-        try:
-            data = json.loads(match.group(1))
-            if isinstance(data, list):
-                return data
-        except json.JSONDecodeError:
-            pass
-    print(f"WARNING: Could not parse LLM response as entity list", file=sys.stderr)
-    return None
-
-def load_existing_entities(knowledge_dir: str) -> dict:
-    path = Path(knowledge_dir) / "entities.json"
-    if not path.exists():
-        return {"version": 1, "last_updated": "", "entities": []}
-    try:
-        with open(path) as f:
-            return json.load(f)
-    except (json.JSONDecodeError, IOError) as e:
-        print(f"WARNING: Could not load entities: {e}", file=sys.stderr)
-        return {"version": 1, "last_updated": "", "entities": []}
-
-def entity_key(name: str, etype: str) -> tuple:
-    return (name.lower().strip(), etype.lower().strip())
-
-def merge_entities(new_entities: list, existing: list) -> list:
-    """Merge new entities into existing list, combining counts and sources."""
-    existing_by_key = {}
-    for e in existing:
-        key = entity_key(e.get('name',''), e.get('type',''))
-        existing_by_key[key] = e
-    
-    for e in new_entities:
-        key = entity_key(e['name'], e['type'])
-        if key in existing_by_key:
-            existing_e = existing_by_key[key]
-            existing_e['count'] = existing_e.get('count', 1) + 1
-            # Merge sources
-            old_sources = set(existing_e.get('sources', []))
-            new_sources = set(e.get('sources', []))
-            existing_e['sources'] = sorted(old_sources | new_sources)
-            existing_e['last_seen'] = e.get('last_seen', existing_e.get('last_seen'))
-        else:
-            e['count'] = e.get('count', 1)
-            e.setdefault('sources', [])
-            e.setdefault('first_seen', datetime.now(timezone.utc).isoformat())
-            existing.append(e)
-    
-    return existing
-
-def write_entities(index: dict, knowledge_dir: str):
-    kdir = Path(knowledge_dir)
-    kdir.mkdir(parents=True, exist_ok=True)
-    index['last_updated'] = datetime.now(timezone.utc).isoformat()
-    path = kdir / "entities.json"
-    with open(path, 'w', encoding='utf-8') as f:
-        json.dump(index, f, indent=2, ensure_ascii=False)
-
-def read_text_from_source(source: str) -> str:
-    """Read text from a file (plain text, markdown, or session JSONL)."""
-    path = Path(source)
-    if not path.exists():
-        raise FileNotFoundError(source)
-    if path.suffix == '.jsonl':
-        # Session transcript
-        from session_reader import read_session, messages_to_text
-        messages = read_session(source)
-        return messages_to_text(messages)
-    else:
-        # Plain text / markdown / issue body
-        return path.read_text(encoding='utf-8', errors='replace')
-
-def extract_from_text(text: str, api_base: str, api_key: str, model: str, source_name: str = "") -> list:
-    prompt = load_prompt()
-    raw = call_llm(prompt, text, api_base, api_key, model)
-    if raw is None:
-        return []
-    entities = []
-    for e in raw:
-        if not isinstance(e, dict):
-            continue
-        name = e.get('name', '').strip()
-        etype = e.get('type', '').strip().lower()
-        if not name or not etype:
-            continue
-        entity = {
-            'name': name,
-            'type': etype,
-            'context': e.get('context', '')[:200],
-            'last_seen': datetime.now(timezone.utc).isoformat(),
-            'sources': [source_name] if source_name else []
-        }
-        entities.append(entity)
-    return entities
-
-def main():
-    parser = argparse.ArgumentParser(description="Extract named entities from text sources")
-    parser.add_argument('--file', help='Single file to process')
-    parser.add_argument('--dir', help='Directory of files to process')
-    parser.add_argument('--session', help='Single session JSONL file')
-    parser.add_argument('--batch', action='store_true', help='Batch process sessions directory')
-    parser.add_argument('--sessions-dir', default=os.path.expanduser('~/.hermes/sessions'),
-                        help='Sessions directory for batch mode')
-    parser.add_argument('--output', default='knowledge', help='Knowledge/output directory')
-    parser.add_argument('--api-base', default=DEFAULT_API_BASE)
-    parser.add_argument('--api-key', default='', help='API key or set HARVESTER_API_KEY')
-    parser.add_argument('--model', default=DEFAULT_MODEL)
-    parser.add_argument('--dry-run', action='store_true', help='Preview without writing')
-    parser.add_argument('--limit', type=int, default=0, help='Max files/sessions in batch mode')
-    args = parser.parse_args()
-
-    api_key = args.api_key or DEFAULT_API_KEY or find_api_key()
-    if not api_key:
-        print("ERROR: No API key found", file=sys.stderr)
-        sys.exit(1)
-
-    knowledge_dir = args.output
-    if not os.path.isabs(knowledge_dir):
-        knowledge_dir = str(SCRIPT_DIR.parent / knowledge_dir)
-
-    sources = []
-    if args.file:
-        sources = [args.file]
-    elif args.dir:
-        files = sorted(Path(args.dir).rglob("*"))
-        sources = [str(f) for f in files if f.is_file() and f.suffix in ('.txt','.md','.json','.jsonl','.yaml','.yml')]
-        if args.limit > 0:
-            sources = sources[:args.limit]
-    elif args.session:
-        sources = [args.session]
-    elif args.batch:
-        sess_dir = Path(args.sessions_dir)
-        sources = sorted(sess_dir.glob("*.jsonl"), reverse=True)
-        if args.limit > 0:
-            sources = sources[:args.limit]
-        sources = [str(s) for s in sources]
-    else:
-        parser.print_help()
-        sys.exit(1)
-
-    print(f"Processing {len(sources)} sources...")
-    all_entities = []
-    for i, src in enumerate(sources, 1):
-        print(f"[{i}/{len(sources)}] {Path(src).name}...", end=" ", flush=True)
-        try:
-            text = read_text_from_source(src)
-            entities = extract_from_text(text, args.api_base, api_key, args.model, source_name=Path(src).name)
-            all_entities.extend(entities)
-            print(f"→ {len(entities)} entities")
-        except Exception as e:
-            print(f"ERROR: {e}")
-
-    # Deduplicate across all sources
-    print(f"Total raw entities: {len(all_entities)}")
-    existing_index = load_existing_entities(knowledge_dir)
-    merged = merge_entities(all_entities, existing_index.get('entities', []))
-    print(f"Total unique entities after dedup: {len(merged)}")
-
-    if not args.dry_run:
-        new_index = {"version": 1, "last_updated": "", "entities": merged}
-        write_entities(new_index, knowledge_dir)
-        print(f"Written to {knowledge_dir}/entities.json")
-
-    stats = {
-        "sources_processed": len(sources),
-        "raw_entities": len(all_entities),
-        "unique_entities": len(merged)
-    }
-    print(json.dumps(stats, indent=2))
-
-if __name__ == '__main__':
-    main()

scripts/github_trending_scanner.py

@@ -0,0 +1,258 @@
+#!/usr/bin/env python3
+"""GitHub Trending Scanner — Scan trending repos in AI/ML.
+
+Extracts: repo description, stars, key features (topics, inferred highlights).
+Filters by language and/or topic. Outputs dated JSON for daily scan pipeline.
+
+Usage:
+    python3 github_trending_scanner.py --language python --topic ai --output metrics/trending
+    python3 github_trending_scanner.py --topic machine-learning --limit 50
+    python3 github_trending_scanner.py --language rust --topic artificial-intelligence
+"""
+
+import argparse
+import json
+import os
+import sys
+import time
+from datetime import datetime, timezone
+from pathlib import Path
+from typing import Optional, List, Dict
+import urllib.request
+import urllib.parse
+import urllib.error
+
+GITHUB_API_BASE = os.environ.get("GITHUB_API_BASE", "https://api.github.com")
+DEFAULT_OUTPUT_DIR = os.environ.get("TRENDING_OUTPUT_DIR", "metrics/trending")
+DEFAULT_LIMIT = int(os.environ.get("TRENDING_LIMIT", "30"))
+DEFAULT_MIN_STARS = int(os.environ.get("TRENDING_MIN_STARS", "1000"))
+
+
+def fetch_trending_repos(
+    language: Optional[str] = None,
+    topic: Optional[str] = None,
+    min_stars: int = DEFAULT_MIN_STARS,
+    limit: int = DEFAULT_LIMIT,
+) -> List[Dict]:
+    """Fetch trending-like repositories from GitHub using the search API.
+
+    GitHub's public search API is unauthenticated-rate-limited (60 req/hr).
+    This function retries on rate-limit backoff and falls back gracefully.
+    """
+    # Build search query: stars threshold + optional language/topic filters
+    query = f"stars:>{min_stars}"
+    if language:
+        query += f" language:{language}"
+    if topic:
+        query += f" topic:{topic}"
+
+    # Sort by stars descending as a proxy for trending/popular
+    params = {
+        "q": query,
+        "sort": "stars",
+        "order": "desc",
+        "per_page": min(limit, 100),  # GitHub max per_page is 100
+    }
+    url = f"{GITHUB_API_BASE}/search/repositories?{urllib.parse.urlencode(params)}"
+
+    headers = {
+        "Accept": "application/vnd.github.v3+json",
+        "User-Agent": "Sovereign-Trending-Scanner/1.0",
+    }
+
+    for attempt in range(3):
+        try:
+            req = urllib.request.Request(url, headers=headers)
+            with urllib.request.urlopen(req, timeout=30) as resp:
+                if resp.status != 200:
+                    raise RuntimeError(f"GitHub API returned {resp.status}")
+                data = json.loads(resp.read().decode("utf-8"))
+                return data.get("items", [])[:limit]
+        except urllib.error.HTTPError as e:
+            if e.code == 403:
+                # Check for rate limit message
+                body = e.read().decode("utf-8", errors="replace").lower()
+                if "rate limit" in body or "api rate limit exceeded" in body:
+                    reset_ts = int(e.headers.get("X-RateLimit-Reset", 0))
+                    wait_seconds = max(5, reset_ts - int(time.time()) + 5)
+                    print(f"Rate limit exceeded — waiting {wait_seconds}s (attempt {attempt+1}/3)...", file=sys.stderr)
+                    time.sleep(wait_seconds)
+                    continue
+            print(f"ERROR: GitHub API request failed: {e} — {e.read().decode('utf-8', errors='replace')[:200]}", file=sys.stderr)
+            return []
+        except Exception as e:
+            if attempt < 2:
+                backoff = 2 ** attempt
+                print(f"WARNING: Fetch attempt {attempt+1} failed: {e} — retrying in {backoff}s", file=sys.stderr)
+                time.sleep(backoff)
+                continue
+            print(f"ERROR: All fetch attempts failed: {e}", file=sys.stderr)
+            return []
+
+    return []
+
+
+def extract_repo_features(repo_data: Dict) -> Dict:
+    """Extract structured fields for a trending repo."""
+    description = (repo_data.get("description") or "").strip()
+    topics = repo_data.get("topics", [])
+
+    # Infer key features from description and topics
+    features = infer_features(description, topics)
+
+    return {
+        "name": repo_data.get("full_name", ""),
+        "description": description,
+        "stars": repo_data.get("stargazers_count", 0),
+        "forks": repo_data.get("forks_count", 0),
+        "open_issues": repo_data.get("open_issues_count", 0),
+        "language": repo_data.get("language", ""),
+        "topics": topics,
+        "url": repo_data.get("html_url", ""),
+        "created_at": repo_data.get("created_at", ""),
+        "updated_at": repo_data.get("updated_at", ""),
+        "key_features": features,
+        "scanned_at": datetime.now(timezone.utc).isoformat(),
+    }
+
+
+def infer_features(description: str, topics: List[str]) -> List[str]:
+    """Infer notable capabilities/features from repo metadata.
+
+    Looks for AI/ML-relevant capabilities in topics and description.
+    """
+    features = []
+    text = (description + " " + " ".join(topics)).lower()
+
+    # Domain capabilities (keys normalized to lowercase for consistency)
+    capability_keywords = {
+        "fine-tuning": ["fine-tun", "finetun"],
+        "agent framework": ["agent"],
+        "local/offline": ["local", "on-device", "offline"],
+        "quantized models": ["quantized", "quantization", "gguf", "gptq"],
+        "vision": ["vision", "multimodal", "image", "visual"],
+        "speech/audio": ["speech", "audio", "whisper", "tts"],
+        "retrieval/rag": ["rag", "retrieval", "embedding", "vector"],
+        "training": ["train", "training", "sft", "dpo"],
+        "gui/playground": ["gui", "playground", "webui", "interface"],
+        "sota": ["state-of-the-art", "sota", "latest"],
+    }
+
+    for label, keywords in capability_keywords.items():
+        if any(kw in text for kw in keywords):
+            features.append(label)
+
+    # Also include non-generic topics as features
+    generic_topics = {"ai", "ml", "machine-learning", "deep-learning", "llm", "python", "pytorch", "tensorflow"}
+    for topic in topics:
+        if topic.lower() not in generic_topics:
+            features.append(topic)
+
+    # Deduplicate while preserving order, return up to 10
+    seen = set()
+    unique = []
+    for f in features:
+        key = f.lower()
+        if key not in seen:
+            seen.add(key)
+            unique.append(f)
+    return unique[:10]
+
+
+def save_trending(repos: List[Dict], output_dir: str = "metrics/trending") -> str:
+    """Save trending results to a dated JSON file.
+
+    Returns the path of the written file.
+    """
+    output_path = Path(output_dir)
+    output_path.mkdir(parents=True, exist_ok=True)
+
+    date_str = datetime.now(timezone.utc).strftime("%Y-%m-%d")
+    filename = output_path / f"github-trending-{date_str}.json"
+
+    output_data = {
+        "scanned_at": datetime.now(timezone.utc).isoformat(),
+        "count": len(repos),
+        "repos": repos,
+    }
+
+    with open(filename, "w") as f:
+        json.dump(output_data, f, indent=2, ensure_ascii=False)
+
+    return str(filename)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Scan GitHub trending repositories in AI/ML"
+    )
+    parser.add_argument(
+        "--language",
+        help="Filter by programming language (e.g., python, rust, go)",
+    )
+    parser.add_argument(
+        "--topic",
+        help="Filter by GitHub topic (e.g., ai, machine-learning, llm)",
+    )
+    parser.add_argument(
+        "--since",
+        default="daily",
+        choices=["daily", "weekly", "monthly"],
+        help="Trending period (daily/weekly/monthly) — informational only",
+    )
+    parser.add_argument(
+        "--output",
+        default="metrics/trending",
+        help="Output directory for results (default: metrics/trending)",
+    )
+    parser.add_argument(
+        "--limit",
+        type=int,
+        default=DEFAULT_LIMIT,
+        help=f"Maximum repos to fetch (default: {DEFAULT_LIMIT})",
+    )
+    parser.add_argument(
+        "--min-stars",
+        type=int,
+        default=DEFAULT_MIN_STARS,
+        help=f"Minimum star count for relevance (default: {DEFAULT_MIN_STARS})",
+    )
+    args = parser.parse_args()
+
+    print(
+        f"Fetching trending repos "
+        f"(language={args.language or 'any'}, topic={args.topic or 'any'}, period={args.since})..."
+    )
+
+    repos_raw = fetch_trending_repos(
+        language=args.language,
+        topic=args.topic,
+        min_stars=args.min_stars,
+        limit=args.limit,
+    )
+
+    if not repos_raw:
+        print("WARNING: No repos fetched — check network or rate limits", file=sys.stderr)
+
+    repos = [extract_repo_features(r) for r in repos_raw]
+
+    output_file = save_trending(repos, args.output)
+    print(f"Saved {len(repos)} trending repos to {output_file}")
+
+    # Brief human-readable summary
+    if repos:
+        print("\nTop repos:")
+        for repo in repos[:5]:
+            features_preview = ", ".join(repo["key_features"][:3])
+            print(f"  ★ {repo['stars']:>7}  {repo['name']}")
+            if repo["description"]:
+                desc = repo["description"][:80]
+                print(f"         {desc}{'...' if len(repo['description']) > 80 else ''}")
+            if features_preview:
+                print(f"         Features: {features_preview}")
+
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

scripts/test_entity_extractor.py

@@ -1,116 +0,0 @@
-#!/usr/bin/env python3
-"""
-Smoke test for entity_extractor pipeline — verifies:
-- session/plain text reading
-- mock LLM entity extraction
-- deduplication and merging
-- output file format
-
-Does NOT call the real LLM.
-"""
-
-import json
-import os
-import tempfile
-from unittest.mock import patch
-import sys
-from pathlib import Path
-
-SCRIPT_DIR = Path(__file__).parent.absolute()
-sys.path.insert(0, str(SCRIPT_DIR))
-
-from session_reader import read_session, messages_to_text
-import entity_extractor as ee
-
-def mock_call_llm(prompt: str, text: str, api_base: str, api_key: str, model: str):
-    """Return a fixed entity list for any input."""
-    return [
-        {"name": "Hermes", "type": "tool", "context": "Hermes agent uses the tools tool."},
-        {"name": "Gitea", "type": "tool", "context": "Gitea is a forge."},
-        {"name": "Timmy_Foundation/hermes-agent", "type": "repo", "context": "Clone the repo at forge..."},
-    ]
-
-def test_read_session_text():
-    with tempfile.NamedTemporaryFile(mode='w', suffix='.jsonl', delete=False) as f:
-        f.write('{"role": "user", "content": "Clone repo", "timestamp": "2026-04-13T10:00:00Z"}\n')
-        f.write('{"role": "assistant", "content": "Done", "timestamp": "2026-04-13T10:00:05Z"}\n')
-        path = f.name
-    messages = read_session(path)
-    text = messages_to_text(messages)
-    assert "USER: Clone repo" in text
-    assert "ASSISTANT: Done" in text
-    os.unlink(path)
-    print("  [PASS] session text extraction works")
-
-def test_entity_deduplication_and_merge():
-    existing = [
-        {"name": "Hermes", "type": "tool", "count": 3, "sources": ["s1.jsonl"]}
-    ]
-    new = [
-        {"name": "Hermes", "type": "tool", "sources": ["s2.jsonl"]},
-        {"name": "Gitea", "type": "tool", "sources": ["s2.jsonl"]},
-    ]
-    merged = ee.merge_entities(new, existing.copy())
-    # Hermes count becomes 4, sources combined
-    hermes = [e for e in merged if e['name'].lower() == 'hermes'][0]
-    assert hermes['count'] == 4
-    assert set(hermes['sources']) == {'s1.jsonl', 's2.jsonl'}
-    # Gitea new entry
-    gitea = [e for e in merged if e['name'].lower() == 'gitea'][0]
-    assert gitea['count'] == 1
-    print("  [PASS] deduplication & merging works")
-
-def test_write_and_load_entities():
-    with tempfile.TemporaryDirectory() as tmp:
-        kdir = Path(tmp) / "knowledge"
-        kdir.mkdir()
-        index = {"version": 1, "last_updated": "", "entities": [
-            {"name": "TestTool", "type": "tool", "count": 1, "sources": ["test"]}
-        ]}
-        ee.write_entities(index, str(kdir))
-        # load back
-        loaded = ee.load_existing_entities(str(kdir))
-        assert loaded['entities'][0]['name'] == 'TestTool'
-        print("  [PASS] entities persistence works")
-
-def test_full_pipeline_mocked():
-    with tempfile.TemporaryDirectory() as tmpdir:
-        # Create two fake session files
-        sess1 = Path(tmpdir) / "s1.jsonl"
-        sess1.write_text('{"role":"user","content":"Use Hermes to clone","timestamp":"..."}\n')
-        sess2 = Path(tmpdir) / "s2.jsonl"
-        sess2.write_text('{"role":"user","content":"Deploy with Gitea","timestamp":"..."}\n')
-        
-        knowledge_dir = Path(tmpdir) / "knowledge"
-        knowledge_dir.mkdir()
-        
-        # Patch call_llm
-        with patch('entity_extractor.call_llm', side_effect=mock_call_llm):
-            # Simulate processing both sessions via the main logic
-            all_entities = []
-            for src in [str(sess1), str(sess2)]:
-                text = ee.read_text_from_source(src)
-                ents = ee.extract_from_text(text, "http://api", "fake-key", "model", source_name=Path(src).name)
-                all_entities.extend(ents)
-            
-            # Merge into empty index
-            merged = ee.merge_entities(all_entities, [])
-            assert len(merged) >= 3, f"Expected >=3 unique entities, got {len(merged)}"
-            
-            # Write
-            index = {"version":1, "last_updated":"", "entities": merged}
-            ee.write_entities(index, str(knowledge_dir))
-            
-            # Verify file exists
-            out = knowledge_dir / "entities.json"
-            assert out.exists()
-            data = json.loads(out.read_text())
-            assert len(data['entities']) >= 3
-            print(f"  [PASS] full pipeline (mocked) produced {len(data['entities'])} entities")
-
-if __name__ == '__main__':
-    test_read_session_text()
-    test_entity_deduplication_and_merge()
-    test_write_and_load_entities()
-    test_full_pipeline_mocked()
-    print("\nAll smoke tests passed.")

scripts/test_github_trending_scanner.py

@@ -0,0 +1,125 @@
+#!/usr/bin/env python3
+"""Tests for github_trending_scanner.py — pure function validation.
+
+Tests the feature inference, extraction, and output formatting logic
+without relying on external GitHub API calls.
+"""
+
+import json
+import sys
+import tempfile
+from pathlib import Path
+
+# Add scripts dir to path for import
+sys.path.insert(0, str(Path(__file__).resolve().parent))
+
+from github_trending_scanner import (
+    extract_repo_features,
+    infer_features,
+    save_trending,
+)
+
+
+def test_infer_features_from_description():
+    """Feature inference extracts capabilities from description text."""
+    desc = "A local, quantized LLM framework for fine-tuning and agent-based RAG with vision."
+    topics = ["ai", "llm"]
+    features = infer_features(desc, topics)
+
+    # Should include relevant capabilities (case-insensitive comparison)
+    expected_lower = {"fine-tuning", "local/offline", "quantized models", "agent framework", "vision", "retrieval/rag"}
+    actual_lower = set(f.lower() for f in features)
+    assert expected_lower.issubset(actual_lower), f"Missing features. Expected subset of {expected_lower}, got {actual_lower}"
+    print("PASS: infer_features_from_description")
+
+
+def test_infer_features_from_topics_only():
+    """Topics alone can drive feature detection."""
+    desc = ""
+    topics = ["computer-vision", "speech", "pytorch"]
+    features = infer_features(desc, topics)
+
+    # Non-generic topics should appear as features (topics preserved as-is)
+    assert "computer-vision" in features, f"Expected 'computer-vision' in {features}"
+    assert "speech" in features, f"Expected 'speech' in {features}"
+    # Generic topics (pytorch) may be filtered
+    print(f"PASS: infer_features_from_topics_only → {features}")
+
+
+def test_extract_repo_features_produces_valid_structure():
+    """extract_repo_features returns all required fields."""
+    mock_repo = {
+        "full_name": "example/repo",
+        "description": "An example repository",
+        "stargazers_count": 1234,
+        "forks_count": 56,
+        "open_issues_count": 7,
+        "language": "Python",
+        "topics": ["ai", "llm"],
+        "html_url": "https://github.com/example/repo",
+        "created_at": "2025-01-01T00:00:00Z",
+        "updated_at": "2026-01-01T00:00:00Z",
+    }
+
+    result = extract_repo_features(mock_repo)
+
+    assert result["name"] == "example/repo"
+    assert result["description"] == "An example repository"
+    assert result["stars"] == 1234
+    assert isinstance(result["key_features"], list)
+    assert "scanned_at" in result
+    assert result["url"] == "https://github.com/example/repo"
+    print("PASS: extract_repo_features_structure")
+
+
+def test_save_trending_creates_dated_json():
+    """save_trending writes a valid JSON file with the expected schema."""
+    repos = [
+        {
+            "name": "test/repo",
+            "description": "Test repository",
+            "stars": 999,
+            "language": "Python",
+            "topics": ["test"],
+            "key_features": ["testing"],
+            "scanned_at": "2026-04-26T00:00:00+00:00",
+        }
+    ]
+
+    with tempfile.TemporaryDirectory() as tmp:
+        output_file = save_trending(repos, output_dir=tmp)
+
+        path = Path(output_file)
+        assert path.exists(), f"Output file not created: {output_file}"
+
+        with open(path) as f:
+            data = json.load(f)
+
+        assert "scanned_at" in data
+        assert data["count"] == 1
+        assert isinstance(data["repos"], list)
+        assert data["repos"][0]["name"] == "test/repo"
+        print(f"PASS: save_trending → {output_file}")
+
+
+def test_save_trending_respects_output_dir_creation():
+    """Output directory is created if it doesn't exist."""
+    repos = []
+
+    with tempfile.TemporaryDirectory() as tmp:
+        nested = Path(tmp) / "nested" / "trending"
+        assert not nested.exists()
+
+        output_file = save_trending(repos, output_dir=str(nested))
+        assert nested.exists()
+        assert Path(output_file).exists()
+        print("PASS: output_dir_creation")
+
+
+if __name__ == "__main__":
+    test_infer_features_from_description()
+    test_infer_features_from_topics_only()
+    test_extract_repo_features_produces_valid_structure()
+    test_save_trending_creates_dated_json()
+    test_save_trending_respects_output_dir_creation()
+    print("\nAll github_trending_scanner tests passed.")

templates/entity-extraction-prompt.md

@@ -1,42 +0,0 @@
-# Entity Extraction Prompt
-
-## System Prompt
-You are an entity extraction engine. You read text and output ONLY a JSON array of named entities. You do not infer. You extract only what the text explicitly mentions.
-
-## Task
-Extract all named entities from the provided text. Categorize each entity into exactly one of these types:
-- `person` — individual's name (e.g., Alexander, Rockachopa, Allegro)
-- `project` — software project or component name (e.g., The Nexus, Timmy Home, compounding-intelligence)
-- `tool` — software tool, command, library, framework (e.g., git, Docker, PyTorch, Hermes)
-- `concept` — abstract idea, methodology, paradigm (e.g., compounding intelligence, bootstrap, harvester)
-- `repo` — repository reference in the form `owner/repo` or URL pointing to a repo
-
-## Rules
-1. Extract ONLY names that appear explicitly in the text.
-2. Do NOT infer, assume, or hallucinate.
-3. Each entity must have: `name` (exact string), `type` (one of the five above), and `context` (short snippet showing usage, 1-2 sentences).
-4. The same entity mentioned multiple times should appear only ONCE in the output (deduplicate by name+type).
-5. For `repo` type, match patterns like `owner/repo`, `github.com/owner/repo`, `forge.alexanderwhitestone.com/owner/repo`.
-6. For `tool` type, include commands (git, pytest), platforms (Linux, macOS), runtimes (Python, Node.js), and CLI utilities.
-7. For `person` type, look for capitalized full names, or single names used in personal attribution ("asked Alex", "for Alexander").
-8. For `concept`, include technical terms that represent an idea rather than a concrete thing.
-
-## Output Format
-Return ONLY valid JSON, no markdown, no explanation. Array of objects:
-```json
-[
-  {
-    "name": "Hermes",
-    "type": "tool",
-    "context": "Hermes agent uses the tools tool to execute commands."
-  },
-  {
-    "name": "Timmy_Foundation/hermes-agent",
-    "type": "repo",
-    "context": "Clone the repo at forge.../Timmy_Foundation/hermes-agent"
-  }
-]
-```
-
-## Text to extract from:
-{{text}}

tests/test_entity_extractor.py

@@ -1,82 +0,0 @@
-"""
-Test suite for entity_extractor.py (Issue #144).
-
-Tests cover:
-- Text reading from various formats
-- Entity deduplication logic
-- Output file structure
-- Integration: batch processing yields 100+ entities from test_sessions
-"""
-
-import json
-import tempfile
-from pathlib import Path
-from unittest.mock import patch, MagicMock
-
-# We'll test the pure functions directly; avoid hitting real LLM in unit tests
-import sys
-sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "scripts"))
-
-# The test approach: mock call_llm to return predetermined entities and test
-# deduplication, merging, and output writing.
-
-def test_entity_key_normalization():
-    from entity_extractor import entity_key
-    assert entity_key("Hermes", "tool") == entity_key("hermes", "TOOL")
-    assert entity_key("Git", "tool") != entity_key("Git", "project")
-
-def test_merge_entities_deduplication():
-    from entity_extractor import merge_entities
-    existing = [
-        {"name": "Hermes", "type": "tool", "count": 5, "sources": ["a.jsonl"]}
-    ]
-    new = [
-        {"name": "Hermes", "type": "tool", "sources": ["b.jsonl"]},
-        {"name": "Gitea", "type": "tool", "sources": ["b.jsonl"]}
-    ]
-    merged = merge_entities(new, existing.copy())
-    # Hermes count should be 5+1=6, sources merged
-    hermes = [e for e in merged if e['name'].lower()=='hermes'][0]
-    assert hermes['count'] == 6
-    assert set(hermes['sources']) == {"a.jsonl", "b.jsonl"}
-    # Gitea added fresh
-    gitea = [e for e in merged if e['name'].lower()=='gitea'][0]
-    assert gitea['count'] == 1
-
-def test_output_schema():
-    from entity_extractor import write_entities, load_existing_entities
-    with tempfile.TemporaryDirectory() as tmp:
-        kdir = Path(tmp) / "knowledge"
-        kdir.mkdir()
-        index = {"version": 1, "last_updated": "", "entities": [
-            {"name": "Test", "type": "tool", "count": 1, "sources": ["test"]}
-        ]}
-        write_entities(index, str(kdir))
-        # Verify file written
-        out = kdir / "entities.json"
-        assert out.exists()
-        data = json.loads(out.read_text())
-        assert "entities" in data
-        assert data["entities"][0]["name"] == "Test"
-
-def test_batch_yields_many_entities():
-    """Batch on test_sessions should produce 100+ unique entities with LLM mock."""
-    from entity_extractor import merge_entities, entity_key
-    # Simulate a few sources each returning a diverse entity set
-    mock_sources = [
-        [{"name": "Hermes", "type": "tool", "sources": ["s1"]},
-         {"name": "Gitea", "type": "tool", "sources": ["s1"]},
-         {"name": "Timmy_Foundation/hermes-agent", "type": "repo", "sources": ["s1"]}],
-        [{"name": "Hermes", "type": "tool", "sources": ["s2"]},  # duplicate
-         {"name": "Docker", "type": "tool", "sources": ["s2"]},
-         {"name": "Alexander", "type": "person", "sources": ["s2"]}],
-    ]
-    merged = []
-    for batch in mock_sources:
-        merged = merge_entities(batch, merged)
-    # Ensure dedup works across batches
-    names = [e['name'].lower() for e in merged]
-    assert names.count('hermes') == 1
-    assert len(merged) == 4  # Hermes, Gitea, repo, Docker, Alexander
-
-# The real LLM extraction test would require live API key; skip in CI