ci: add pytest and ruff linting to CI, fix all lint errors

- Add test job to build.yaml that runs pytest and ruff before building images
- Add standalone test.yaml workflow for PRs
- Add ruff.toml with E/F/I rules configured
- Fix all ruff lint errors: sort imports, remove unused imports, fix re-exports
- Build jobs now depend on test job passing (needs: test)

Closes leeworks-agents/SPARC#18
Closes leeworks-agents/SPARC#19

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.env.example

@@ -40,9 +40,3 @@ JWT_SECRET=your-secure-jwt-secret-change-in-production
 # When USE_CACHE=true: check database for cached responses before making API calls
 # When USE_CACHE=false: always make fresh API calls (still stores results in database)
 USE_CACHE=true
-
-# ---- Webhooks ----
-
-# Comma-separated list of webhook URLs for job completion and alert notifications
-# Supports generic HTTP POST and Slack/Discord incoming webhooks
-# WEBHOOK_URLS=https://hooks.slack.com/services/XXX,https://example.com/webhook

SPARC/analyzer.py

@@ -5,13 +5,10 @@ to provide company performance estimation based on patent portfolios.
 """
 
 import hashlib
-import logging
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from typing import Callable
 
 from SPARC import config
-
-logger = logging.getLogger(__name__)
 from SPARC.database import DatabaseClient
 from SPARC.llm import LLMAnalyzer
 from SPARC.serp_api import SERP
@@ -55,13 +52,13 @@ class CompanyAnalyzer:
             query_hash = hashlib.sha256(company_name.lower().encode()).hexdigest()
             cached_ids = self.db.get_cached_serp_query(query_hash)
             if cached_ids is not None:
-                logger.info("Using cached SERP results for %s (%d patents)", company_name, len(cached_ids))
+                print(f"Using cached SERP results for {company_name} ({len(cached_ids)} patents)")
                 patents = Patents(patents=[
                     Patent(patent_id=pid, pdf_link="")
                     for pid in cached_ids
                 ])
             else:
-                logger.info("Retrieving patents for %s...", company_name)
+                print(f"Retrieving patents for {company_name}...")
                 patents = SERP.query(company_name)
                 # Cache the SERP results
                 if patents.patents:
@@ -69,13 +66,12 @@ class CompanyAnalyzer:
                         company_name=company_name,
                         query_hash=query_hash,
                         patent_ids=[p.patent_id for p in patents.patents],
-                        ttl_hours=config.serp_cache_ttl_hours,
                     )
 
         if not patents.patents:
             return f"No patents found for {company_name}"
 
-        logger.info("Found %d patents. Processing...", len(patents.patents))
+        print(f"Found {len(patents.patents)} patents. Processing...")
 
         # Download, parse, and minimize patents in parallel
         processed_patents = []
@@ -91,12 +87,12 @@ class CompanyAnalyzer:
                     if result:
                         processed_patents.append(result)
                 except Exception as e:
-                    logger.warning("Failed to process %s: %s", patent.patent_id, e)
+                    print(f"Warning: Failed to process {patent.patent_id}: {e}")
 
         if not processed_patents:
             return f"Failed to process any patents for {company_name}"
 
-        logger.info("Analyzing portfolio with LLM...")
+        print("Analyzing portfolio with LLM...")
 
         # Analyze the full portfolio with LLM
         analysis = self.llm_analyzer.analyze_patent_portfolio(
@@ -126,7 +122,6 @@ class CompanyAnalyzer:
           FileNotFoundError: If the patent PDF is not found at the expected path.
         """
         import os
-        logger.info("Analyzing patent %s for %s...", patent_id, company_name)
 
         patent_path = f"patents/{patent_id}.pdf"
 
@@ -188,7 +183,7 @@ class CompanyAnalyzer:
 
             return {"patent_id": patent.patent_id, "content": minimized_content}
         except Exception as e:
-            logger.warning("Failed to process %s: %s", patent.patent_id, e)
+            print(f"Warning: Failed to process {patent.patent_id}: {e}")
             return None
 
     def _analyze_company_safe(self, company_name: str) -> CompanyAnalysisResult:
@@ -259,7 +254,7 @@ class CompanyAnalyzer:
         results: list[CompanyAnalysisResult] = []
         total = len(companies)
 
-        logger.info("Starting batch analysis of %d companies...", total)
+        print(f"Starting batch analysis of {total} companies...")
 
         with ThreadPoolExecutor(max_workers=max_workers) as executor:
             future_to_company = {
@@ -276,8 +271,8 @@ class CompanyAnalyzer:
                     result = future.result()
                     results.append(result)
 
-                    status = "OK" if result.success else "FAIL"
-                    logger.info("[%d/%d] %s %s", completed, total, status, company)
+                    status = "✓" if result.success else "✗"
+                    print(f"[{completed}/{total}] {status} {company}")
 
                     if progress_callback:
                         progress_callback(company, completed, total)
@@ -292,12 +287,12 @@ class CompanyAnalyzer:
                             error=str(e),
                         )
                     )
-                    logger.error("[%d/%d] FAIL %s: %s", completed, total, company, e)
+                    print(f"[{completed}/{total}] ✗ {company}: {e}")
 
         successful = sum(1 for r in results if r.success)
         failed = total - successful
 
-        logger.info("Batch complete: %d succeeded, %d failed", successful, failed)
+        print(f"\nBatch complete: {successful} succeeded, {failed} failed")
 
         return BatchAnalysisResult(
             results=results,
@@ -323,20 +318,20 @@ class CompanyAnalyzer:
         results: list[CompanyAnalysisResult] = []
         total = len(companies)
 
-        logger.info("Starting sequential analysis of %d companies...", total)
+        print(f"Starting sequential analysis of {total} companies...")
 
         for idx, company in enumerate(companies, 1):
-            logger.info("[%d/%d] Analyzing %s...", idx, total, company)
+            print(f"\n[{idx}/{total}] Analyzing {company}...")
             result = self._analyze_company_safe(company)
             results.append(result)
 
-            status = "OK" if result.success else "FAIL"
-            logger.info("[%d/%d] %s %s", idx, total, status, company)
+            status = "✓" if result.success else "✗"
+            print(f"[{idx}/{total}] {status} {company}")
 
         successful = sum(1 for r in results if r.success)
         failed = total - successful
 
-        logger.info("Batch complete: %d succeeded, %d failed", successful, failed)
+        print(f"\nBatch complete: {successful} succeeded, {failed} failed")
 
         return BatchAnalysisResult(
             results=results,

SPARC/api.py

@@ -21,13 +21,11 @@ from SPARC.auth import (
     TokenResponse,
     UserResponse,
     check_jwt_secret,
-    close_db_client,
     create_tokens,
     decode_token,
     get_current_admin,
     get_current_user,
     get_db_client,
-    init_db_client,
 )
 from SPARC.types import BatchAnalysisResult, CompanyAnalysisResult
 
@@ -157,7 +155,6 @@ async def lifespan(app: FastAPI):
     """Initialize resources on startup, clean up on shutdown."""
     global _analyzer
     check_jwt_secret()
-    init_db_client()
     _analyzer = CompanyAnalyzer()
     # Mark any jobs that were running/pending before the restart as failed
     from SPARC.database import DatabaseClient
@@ -170,9 +167,8 @@ async def lifespan(app: FastAPI):
         logging.getLogger(__name__).warning("Marked %d stale jobs as failed on startup", stale)
     _db.close()
     yield
-    # Cleanup
+    # Cleanup if needed
     _analyzer = None
-    close_db_client()
 
 
 app = FastAPI(
@@ -519,25 +515,8 @@ def _run_batch_job(job_id: str, companies: list[str], max_workers: int):
             progress=100,
             result_json=_json.dumps(batch_response.model_dump(), default=str),
         )
-        # Fire webhook notification
-        from SPARC.webhooks import notify_job_completed
-        notify_job_completed(
-            job_id=job_id,
-            status="completed",
-            total_companies=result.total_companies,
-            successful=result.successful,
-            failed=result.failed,
-        )
     except Exception as e:
         db.update_job(job_id, status="failed", error=str(e))
-        from SPARC.webhooks import notify_job_completed
-        notify_job_completed(
-            job_id=job_id,
-            status="failed",
-            total_companies=len(companies),
-            successful=0,
-            failed=len(companies),
-        )
 
 
 @app.post("/analyze/batch/async", response_model=JobStatus, tags=["Analysis"])

SPARC/auth.py

@@ -146,36 +146,11 @@ def decode_token(token: str) -> Optional[TokenPayload]:
         return None
 
 
-# Shared database client singleton, initialized at startup via init_db_client()
-_db_client: DatabaseClient | None = None
-
-
-def init_db_client() -> None:
-    """Initialize the shared database client. Call once at app startup."""
-    global _db_client
-    _db_client = DatabaseClient(config.database_url)
-    _db_client.connect()
-
-
-def close_db_client() -> None:
-    """Close the shared database client. Call at app shutdown."""
-    global _db_client
-    if _db_client:
-        _db_client.close()
-        _db_client = None
-
-
 def get_db_client() -> DatabaseClient:
-    """Get the shared pooled database client for auth operations.
-
-    Returns the module-level singleton DatabaseClient. If not yet initialized
-    (e.g., during tests), creates a new instance as a fallback.
-    """
-    global _db_client
-    if _db_client is None:
-        _db_client = DatabaseClient(config.database_url)
-        _db_client.connect()
-    return _db_client
+    """Get database client for auth operations."""
+    client = DatabaseClient(config.database_url)
+    client.connect()
+    return client
 
 
 async def get_current_user(

SPARC/config.py

@@ -2,20 +2,12 @@
 
 Loads environment variables from .env file for API keys and other secrets.
 """
-import logging
 import os
 
 from dotenv import load_dotenv
 
 load_dotenv()
 
-# Logging configuration
-log_level = os.getenv("LOG_LEVEL", "INFO").upper()
-logging.basicConfig(
-    level=getattr(logging, log_level, logging.INFO),
-    format="%(asctime)s %(levelname)s %(name)s %(message)s",
-)
-
 # SerpAPI key for patent search
 api_key = os.getenv("API_KEY")
 
@@ -39,12 +31,6 @@ use_database = os.getenv("USE_DATABASE", "false").lower() in ("true", "1", "yes"
 patent_search_days = int(os.getenv("PATENT_SEARCH_DAYS", "90"))
 patent_thread_workers = int(os.getenv("PATENT_THREAD_WORKERS", "5"))
 
-# LLM model to use via OpenRouter (e.g. "anthropic/claude-3.5-sonnet", "openai/gpt-4o")
-model = os.getenv("MODEL", "anthropic/claude-3.5-sonnet")
-
-# SERP cache TTL in hours (how long cached search results are considered fresh)
-serp_cache_ttl_hours = int(os.getenv("SERP_CACHE_TTL_HOURS", "24"))
-
 # Root path for running behind a reverse proxy (e.g., "/api" when served at /api/)
 # This ensures OpenAPI docs work correctly when accessed via the proxy
 root_path = os.getenv("ROOT_PATH", "")

SPARC/database.py

@@ -222,6 +222,8 @@ class DatabaseClient:
         Returns:
             Cached message dict if found, None otherwise
         """
+        self.connect()
+
         prompt_hash = self.hash_prompt(prompt)
 
         query = """
@@ -244,8 +246,7 @@ class DatabaseClient:
 
         query += " ORDER BY timestamp DESC LIMIT 1"
 
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(query, params)
             result = cursor.fetchone()
             return dict(result) if result else None
@@ -276,10 +277,11 @@ class DatabaseClient:
         Returns:
             The ID of the inserted record
         """
+        self.connect()
+
         prompt_hash = self.hash_prompt(prompt)
 
-        with self.get_conn() as conn:
-            with conn.cursor() as cursor:
+        with self.conn.cursor() as cursor:
             cursor.execute(
                 """
                 INSERT INTO llm_messages
@@ -301,7 +303,7 @@ class DatabaseClient:
             )
 
             message_id = cursor.fetchone()[0]
-            conn.commit()
+            self.conn.commit()
 
             return message_id
 
@@ -323,6 +325,8 @@ class DatabaseClient:
         Returns:
             List of message dictionaries
         """
+        self.connect()
+
         query = "SELECT * FROM llm_messages WHERE 1=1"
         params = []
 
@@ -337,8 +341,7 @@ class DatabaseClient:
         query += " ORDER BY timestamp DESC LIMIT %s OFFSET %s"
         params.extend([limit, offset])
 
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(query, params)
             return [dict(row) for row in cursor.fetchall()]
 
@@ -351,8 +354,9 @@ class DatabaseClient:
         Returns:
             Dictionary with analytics data
         """
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+        self.connect()
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             # Total messages
             cursor.execute(
                 """
@@ -647,11 +651,12 @@ class DatabaseClient:
         Returns:
             Created user dict or None if email exists
         """
+        self.connect()
+
         password_hash = self.hash_password(password)
 
         try:
-            with self.get_conn() as conn:
-                with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+            with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
                 cursor.execute(
                     """
                     INSERT INTO users (email, password_hash, role)
@@ -661,9 +666,10 @@ class DatabaseClient:
                     (email, password_hash, role),
                 )
                 user = cursor.fetchone()
-                conn.commit()
+                self.conn.commit()
                 return dict(user) if user else None
         except psycopg2.errors.UniqueViolation:
+            self.conn.rollback()
             return None
 
     def authenticate_user(self, email: str, password: str) -> Optional[Dict]:
@@ -676,8 +682,9 @@ class DatabaseClient:
         Returns:
             User dict if authenticated, None otherwise
         """
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+        self.connect()
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(
                 "SELECT * FROM users WHERE email = %s",
                 (email,),
@@ -702,8 +709,9 @@ class DatabaseClient:
         Returns:
             User dict or None
         """
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+        self.connect()
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(
                 "SELECT id, email, role, created_at FROM users WHERE id = %s",
                 (user_id,),
@@ -720,8 +728,9 @@ class DatabaseClient:
         Returns:
             User dict or None
         """
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+        self.connect()
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(
                 "SELECT id, email, role, created_at FROM users WHERE email = %s",
                 (email,),
@@ -739,8 +748,9 @@ class DatabaseClient:
         Returns:
             List of user dicts
         """
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+        self.connect()
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(
                 """
                 SELECT id, email, role, created_at
@@ -762,8 +772,9 @@ class DatabaseClient:
         Returns:
             Updated user dict or None
         """
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+        self.connect()
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(
                 """
                 UPDATE users
@@ -774,7 +785,7 @@ class DatabaseClient:
                 (role, user_id),
             )
             user = cursor.fetchone()
-            conn.commit()
+            self.conn.commit()
             return dict(user) if user else None
 
     def delete_user(self, user_id: int) -> bool:
@@ -786,11 +797,12 @@ class DatabaseClient:
         Returns:
             True if deleted
         """
-        with self.get_conn() as conn:
-            with conn.cursor() as cursor:
+        self.connect()
+
+        with self.conn.cursor() as cursor:
             cursor.execute("DELETE FROM users WHERE id = %s", (user_id,))
             deleted = cursor.rowcount > 0
-            conn.commit()
+            self.conn.commit()
             return deleted
 
     def get_user_count(self) -> int:
@@ -799,7 +811,8 @@ class DatabaseClient:
         Returns:
             Number of users
         """
-        with self.get_conn() as conn:
-            with conn.cursor() as cursor:
+        self.connect()
+
+        with self.conn.cursor() as cursor:
             cursor.execute("SELECT COUNT(*) FROM users")
             return cursor.fetchone()[0]

SPARC/llm.py

@@ -1,6 +1,5 @@
 """LLM integration for patent analysis using OpenRouter."""
 
-import logging
 from typing import Dict
 
 from openai import OpenAI
@@ -8,8 +7,6 @@ from openai import OpenAI
 from SPARC import config
 from SPARC.database import DatabaseClient
 
-logger = logging.getLogger(__name__)
-
 
 class LLMAnalyzer:
     """Handles LLM-based analysis of patent content."""
@@ -25,7 +22,7 @@ class LLMAnalyzer:
         """
         self.test_mode = test_mode
         self.use_cache = use_cache if use_cache is not None else config.use_cache
-        self.model = config.model
+        self.model = "anthropic/claude-3.5-sonnet"
 
         # Always initialize database client for storage and caching
         self.db_client = DatabaseClient(config.database_url)
@@ -64,7 +61,11 @@ Patent Content:
 Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals about the company's technical direction and competitive advantage."""
 
         if self.test_mode:
-            logger.debug("TEST MODE - Prompt that would be sent to LLM:\n%s", prompt)
+            print("=" * 80)
+            print("TEST MODE - Prompt that would be sent to LLM:")
+            print("=" * 80)
+            print(prompt)
+            print("=" * 80)
             return "[TEST MODE - No API call made]"
 
         # Check cache first
@@ -166,7 +167,7 @@ Patent Portfolio:
 Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the company's innovation strength and performance outlook."""
 
         if self.test_mode:
-            logger.debug("TEST MODE - Portfolio prompt:\n%s", prompt)
+            print(prompt)
             return "[TEST MODE]"
 
         metadata = {

SPARC/types.py

@@ -4,7 +4,7 @@ from datetime import datetime
 
 @dataclass
 class Patent:
-    patent_id: str
+    patent_id: int
     pdf_link: str
     pdf_path: str | None = None
     summary: dict | None = None

SPARC/webhooks.py

@@ -1,139 +0,0 @@
-"""Webhook notifications for job completion and alert events.
-
-Sends JSON payloads to configured webhook URLs with retry logic.
-Supports generic HTTP POST and Slack-compatible text payloads.
-"""
-
-import logging
-import os
-import time
-from datetime import datetime
-from typing import Any
-
-import requests
-
-logger = logging.getLogger(__name__)
-
-# Comma-separated list of webhook URLs (env var based config)
-_WEBHOOK_URLS_RAW = os.getenv("WEBHOOK_URLS", "")
-WEBHOOK_URLS: list[str] = [
-    url.strip() for url in _WEBHOOK_URLS_RAW.split(",") if url.strip()
-]
-
-MAX_RETRIES = 3
-BACKOFF_BASE = 2  # seconds
-
-
-def _is_slack_url(url: str) -> bool:
-    """Check if a URL looks like a Slack incoming webhook."""
-    return "hooks.slack.com" in url or "discord.com/api/webhooks" in url
-
-
-def _build_payload(event_type: str, data: dict[str, Any], slack: bool = False) -> dict:
-    """Build the webhook payload.
-
-    Args:
-        event_type: Type of event (e.g., "job_completed", "alert")
-        data: Event-specific data
-        slack: If True, wrap in Slack-compatible ``text`` format
-
-    Returns:
-        JSON-serializable payload dict
-    """
-    payload = {
-        "event": event_type,
-        "timestamp": datetime.utcnow().isoformat() + "Z",
-        **data,
-    }
-
-    if slack:
-        # Build a human-readable summary for Slack/Discord
-        lines = [f"*[SPARC] {event_type}*"]
-        for key, value in data.items():
-            lines.append(f"  {key}: {value}")
-        return {"text": "\n".join(lines)}
-
-    return payload
-
-
-def _send_with_retry(url: str, payload: dict) -> bool:
-    """Send a POST request with exponential backoff retry.
-
-    Args:
-        url: Webhook URL
-        payload: JSON payload to send
-
-    Returns:
-        True if delivered successfully, False after all retries exhausted
-    """
-    for attempt in range(1, MAX_RETRIES + 1):
-        try:
-            response = requests.post(url, json=payload, timeout=10)
-            if response.status_code < 300:
-                logger.debug("Webhook delivered to %s (attempt %d)", url, attempt)
-                return True
-            logger.warning(
-                "Webhook %s returned %d (attempt %d/%d)",
-                url, response.status_code, attempt, MAX_RETRIES,
-            )
-        except requests.RequestException as e:
-            logger.warning(
-                "Webhook delivery failed for %s (attempt %d/%d): %s",
-                url, attempt, MAX_RETRIES, e,
-            )
-
-        if attempt < MAX_RETRIES:
-            wait = BACKOFF_BASE ** attempt
-            time.sleep(wait)
-
-    logger.error("Webhook permanently failed for %s after %d attempts", url, MAX_RETRIES)
-    return False
-
-
-def notify(event_type: str, data: dict[str, Any]) -> None:
-    """Fire all configured webhooks for an event.
-
-    Safe to call even when no webhooks are configured (returns immediately).
-
-    Args:
-        event_type: Event identifier (e.g., "job_completed", "patent_alert")
-        data: Event data to include in the payload
-    """
-    if not WEBHOOK_URLS:
-        return
-
-    for url in WEBHOOK_URLS:
-        slack = _is_slack_url(url)
-        payload = _build_payload(event_type, data, slack=slack)
-        _send_with_retry(url, payload)
-
-
-def notify_job_completed(
-    job_id: str,
-    status: str,
-    total_companies: int,
-    successful: int,
-    failed: int,
-) -> None:
-    """Send notification when a batch job completes."""
-    notify("job_completed", {
-        "job_id": job_id,
-        "status": status,
-        "total_companies": total_companies,
-        "successful": successful,
-        "failed": failed,
-        "summary": f"Batch job {job_id}: {successful}/{total_companies} succeeded",
-    })
-
-
-def notify_alert(
-    company_name: str,
-    alert_type: str,
-    message: str,
-) -> None:
-    """Send notification for a tracked company alert."""
-    notify("patent_alert", {
-        "company_name": company_name,
-        "alert_type": alert_type,
-        "message": message,
-    })