feat: add structured logging to serp_api.py

Add module-level logger to serp_api.py with INFO-level messages for
patent queries and PDF downloads, and DEBUG-level messages for cache
hits and parsing details. All three target files (analyzer.py,
serp_api.py, llm.py) now use structured logging with no print() calls.

Closes leeworks-agents/SPARC#46

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

SPARC/analyzer.py

@@ -5,10 +5,13 @@ 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
@@ -52,13 +55,13 @@ 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:
-                print(f"Using cached SERP results for {company_name} ({len(cached_ids)} patents)")
+                logger.info("Using cached SERP results for %s (%d patents)", company_name, len(cached_ids))
                 patents = Patents(patents=[
                     Patent(patent_id=pid, pdf_link="")
                     for pid in cached_ids
                 ])
             else:
-                print(f"Retrieving patents for {company_name}...")
+                logger.info("Retrieving patents for %s...", company_name)
                 patents = SERP.query(company_name)
                 # Cache the SERP results
                 if patents.patents:
@@ -66,12 +69,13 @@ 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}"
 
-        print(f"Found {len(patents.patents)} patents. Processing...")
+        logger.info("Found %d patents. Processing...", len(patents.patents))
 
         # Download, parse, and minimize patents in parallel
         processed_patents = []
@@ -87,12 +91,12 @@ class CompanyAnalyzer:
                     if result:
                         processed_patents.append(result)
                 except Exception as e:
-                    print(f"Warning: Failed to process {patent.patent_id}: {e}")
+                    logger.warning("Failed to process %s: %s", patent.patent_id, e)
 
         if not processed_patents:
             return f"Failed to process any patents for {company_name}"
 
-        print("Analyzing portfolio with LLM...")
+        logger.info("Analyzing portfolio with LLM...")
 
         # Analyze the full portfolio with LLM
         analysis = self.llm_analyzer.analyze_patent_portfolio(
@@ -122,6 +126,7 @@ 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"
 
@@ -183,7 +188,7 @@ class CompanyAnalyzer:
 
             return {"patent_id": patent.patent_id, "content": minimized_content}
         except Exception as e:
-            print(f"Warning: Failed to process {patent.patent_id}: {e}")
+            logger.warning("Failed to process %s: %s", patent.patent_id, e)
             return None
 
     def _analyze_company_safe(self, company_name: str) -> CompanyAnalysisResult:
@@ -254,7 +259,7 @@ class CompanyAnalyzer:
         results: list[CompanyAnalysisResult] = []
         total = len(companies)
 
-        print(f"Starting batch analysis of {total} companies...")
+        logger.info("Starting batch analysis of %d companies...", total)
 
         with ThreadPoolExecutor(max_workers=max_workers) as executor:
             future_to_company = {
@@ -271,8 +276,8 @@ class CompanyAnalyzer:
                     result = future.result()
                     results.append(result)
 
-                    status = "✓" if result.success else "✗"
-                    print(f"[{completed}/{total}] {status} {company}")
+                    status = "OK" if result.success else "FAIL"
+                    logger.info("[%d/%d] %s %s", completed, total, status, company)
 
                     if progress_callback:
                         progress_callback(company, completed, total)
@@ -287,12 +292,12 @@ class CompanyAnalyzer:
                             error=str(e),
                         )
                     )
-                    print(f"[{completed}/{total}] ✗ {company}: {e}")
+                    logger.error("[%d/%d] FAIL %s: %s", completed, total, company, e)
 
         successful = sum(1 for r in results if r.success)
         failed = total - successful
 
-        print(f"\nBatch complete: {successful} succeeded, {failed} failed")
+        logger.info("Batch complete: %d succeeded, %d failed", successful, failed)
 
         return BatchAnalysisResult(
             results=results,
@@ -318,20 +323,20 @@ class CompanyAnalyzer:
         results: list[CompanyAnalysisResult] = []
         total = len(companies)
 
-        print(f"Starting sequential analysis of {total} companies...")
+        logger.info("Starting sequential analysis of %d companies...", total)
 
         for idx, company in enumerate(companies, 1):
-            print(f"\n[{idx}/{total}] Analyzing {company}...")
+            logger.info("[%d/%d] Analyzing %s...", idx, total, company)
             result = self._analyze_company_safe(company)
             results.append(result)
 
-            status = "✓" if result.success else "✗"
-            print(f"[{idx}/{total}] {status} {company}")
+            status = "OK" if result.success else "FAIL"
+            logger.info("[%d/%d] %s %s", idx, total, status, company)
 
         successful = sum(1 for r in results if r.success)
         failed = total - successful
 
-        print(f"\nBatch complete: {successful} succeeded, {failed} failed")
+        logger.info("Batch complete: %d succeeded, %d failed", successful, failed)
 
         return BatchAnalysisResult(
             results=results,

SPARC/api.py

@@ -21,11 +21,13 @@ 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
 
@@ -155,6 +157,7 @@ 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
@@ -167,8 +170,9 @@ async def lifespan(app: FastAPI):
         logging.getLogger(__name__).warning("Marked %d stale jobs as failed on startup", stale)
     _db.close()
     yield
-    # Cleanup if needed
+    # Cleanup
     _analyzer = None
+    close_db_client()
 
 
 app = FastAPI(

SPARC/auth.py

@@ -146,11 +146,36 @@ 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 database client for auth operations."""
-    client = DatabaseClient(config.database_url)
-    client.connect()
-    return client
+    """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
 
 
 async def get_current_user(

SPARC/config.py

@@ -2,12 +2,20 @@
 
 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")
 
@@ -31,6 +39,12 @@ 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

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

SPARC/llm.py

@@ -1,5 +1,6 @@
 """LLM integration for patent analysis using OpenRouter."""
 
+import logging
 from typing import Dict
 
 from openai import OpenAI
@@ -7,6 +8,8 @@ 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."""
@@ -22,7 +25,7 @@ class LLMAnalyzer:
         """
         self.test_mode = test_mode
         self.use_cache = use_cache if use_cache is not None else config.use_cache
-        self.model = "anthropic/claude-3.5-sonnet"
+        self.model = config.model
 
         # Always initialize database client for storage and caching
         self.db_client = DatabaseClient(config.database_url)
@@ -61,11 +64,7 @@ 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:
-            print("=" * 80)
-            print("TEST MODE - Prompt that would be sent to LLM:")
-            print("=" * 80)
-            print(prompt)
-            print("=" * 80)
+            logger.debug("TEST MODE - Prompt that would be sent to LLM:\n%s", prompt)
             return "[TEST MODE - No API call made]"
 
         # Check cache first
@@ -167,7 +166,7 @@ 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:
-            print(prompt)
+            logger.debug("TEST MODE - Portfolio prompt:\n%s", prompt)
             return "[TEST MODE]"
 
         metadata = {

SPARC/serp_api.py

@@ -1,3 +1,4 @@
+import logging
 import os
 import re
 from datetime import datetime, timedelta
@@ -10,6 +11,8 @@ import serpapi
 from SPARC import config
 from SPARC.types import Patent, Patents
 
+logger = logging.getLogger(__name__)
+
 
 class SERP:
   def query(company: str, days_back: int = None) -> Patents:
@@ -44,6 +47,7 @@ class SERP:
       "tbs": date_filter,
       "api_key": config.api_key,
     }
+    logger.info("Querying Google Patents for '%s' (last %d days)", company, days_back)
     search = serpapi.search(params)
     # Convert results to Patent objects, skipping any without PDF links
     patent_ids = []
@@ -52,8 +56,10 @@ class SERP:
         pdf_link = patent.get("pdf")
         if pdf_link:
             patent_ids.append(Patent(patent_id=patent["publication_number"], pdf_link=pdf_link, summary=None))
-        # Patents without PDF links are skipped (see docstring for details)
+        else:
+            logger.debug("Skipping patent %s (no PDF link)", patent.get("publication_number", "unknown"))
 
+    logger.info("Found %d patents with PDF links for '%s'", len(patent_ids), company)
     return Patents(patents=patent_ids)
 
   def save_patents(patent: Patent) -> Patent:
@@ -70,9 +76,13 @@ class SERP:
     os.makedirs("patents", exist_ok=True)
 
     if not (os.path.exists(pdf_path) and os.path.getsize(pdf_path) > 0):
+      logger.info("Downloading PDF for %s", patent.patent_id)
       response = requests.get(patent.pdf_link)
       with open(pdf_path, "wb") as f:
         f.write(response.content)
+      logger.debug("Saved %d bytes to %s", len(response.content), pdf_path)
+    else:
+      logger.debug("Using cached PDF for %s at %s", patent.patent_id, pdf_path)
 
     patent.pdf_path = pdf_path
     return patent
@@ -90,11 +100,13 @@ class SERP:
       Dictionary containing all extracted sections
     """
 
+    logger.debug("Parsing patent PDF: %s", pdf_path)
     with pdfplumber.open(pdf_path) as pdf:
       # Extract all text
       full_text = ""
       for page in pdf.pages:
         full_text += page.extract_text() + "\n"
+      logger.debug("Extracted text from %d pages (%d chars)", len(pdf.pages), len(full_text))
 
     # Define section patterns (common in patents)
     sections = {

SPARC/types.py

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