docs: document patent PDF storage, add FileNotFoundError, commit lockfile

- Add docstring to analyze_single_patent explaining the PDF prerequisite
- Raise FileNotFoundError with helpful message when PDF is missing
- Add patent PDF storage section to README with Docker volume mount example
- Commit frontend/package-lock.json for reproducible builds

Closes leeworks-agents/SPARC#15
Closes leeworks-agents/SPARC#17

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

README.md

@@ -54,6 +54,21 @@ docker-compose up -d
 # - API Docs: http://localhost:8000/docs
 ```
 
+#### Patent PDF Storage
+
+The API stores downloaded patent PDFs in a `patents/` directory. In Docker,
+this is mounted as a bind mount (`./patents:/app/patents`) so that PDFs persist
+across container restarts.
+
+If you deploy to a different environment, ensure the `patents/` directory is a
+persistent volume. Without it, PDFs will be re-downloaded on every analysis.
+
+```yaml
+# docker-compose.yml excerpt
+volumes:
+  - ./patents:/app/patents
+```
+
 ### NixOS
 
 ```bash

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.serp_api import SERP
 from SPARC.llm import LLMAnalyzer
@@ -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(f"Analyzing portfolio with LLM...")
 
         # Analyze the full portfolio with LLM
         analysis = self.llm_analyzer.analyze_patent_portfolio(
@@ -108,21 +104,33 @@ class CompanyAnalyzer:
     def analyze_single_patent(self, patent_id: str, company_name: str) -> str:
         """Analyze a single patent by ID.
 
-        Useful for focused analysis of specific innovations.
+        Prerequisite:
+            The patent PDF must already exist at ``patents/{patent_id}.pdf``
+            before calling this method. PDFs are downloaded automatically when
+            using the batch analysis pipeline (``analyze_company`` or the
+            ``/analyze/batch`` API endpoint). For standalone usage, download
+            the PDF manually or call ``SERP.save_patents()`` first.
 
         Args:
-          patent_id: Publication ID of the patent
+          patent_id: Publication ID of the patent (e.g. "US-11234567-B2")
           company_name: Name of the company (for context)
 
         Returns:
           Analysis of the specific patent's innovation quality
+
+        Raises:
+          FileNotFoundError: If the patent PDF is not found at the expected path.
         """
-        # Note: This simplified version assumes the patent PDF is already downloaded
+        import os
-        # A more complete implementation would support direct patent ID lookup
-        logger.info("Analyzing patent %s for %s...", patent_id, company_name)
 
         patent_path = f"patents/{patent_id}.pdf"
 
+        if not os.path.exists(patent_path):
+            raise FileNotFoundError(
+                f"Patent PDF not found at '{patent_path}'. "
+                f"Download the PDF first using SERP.save_patents() or the batch analysis pipeline."
+            )
+
         try:
             sections = SERP.parse_patent_pdf(patent_path)
             minimized_content = SERP.minimize_patent_for_llm(sections)
@@ -133,6 +141,8 @@ class CompanyAnalyzer:
 
             return analysis
 
+        except FileNotFoundError:
+            raise
         except Exception as e:
             return f"Failed to analyze patent {patent_id}: {e}"
 
@@ -173,7 +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:
@@ -244,7 +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 = {
@@ -261,8 +271,8 @@ class CompanyAnalyzer:
                     result = future.result()
                     results.append(result)
 
-                    status = "OK" if result.success else "FAIL"
+                    status = "✓" if result.success else "✗"
-                    logger.info("[%d/%d] %s %s", completed, total, status, company)
+                    print(f"[{completed}/{total}] {status} {company}")
 
                     if progress_callback:
                         progress_callback(company, completed, total)
@@ -277,12 +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,
@@ -308,20 +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"
+            status = "✓" if result.success else "✗"
-            logger.info("[%d/%d] %s %s", idx, total, status, company)
+            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/config.py

@@ -2,20 +2,11 @@
 
 Loads environment variables from .env file for API keys and other secrets.
 """
-import logging
+from dotenv import load_dotenv
 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 +30,6 @@ 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/llm.py

@@ -1,14 +1,9 @@
 """LLM integration for patent analysis using OpenRouter."""
 
-import logging
-from typing import Dict
-
 from openai import OpenAI
-
 from SPARC import config
 from SPARC.database import DatabaseClient
-
+from typing import Dict
-logger = logging.getLogger(__name__)
 
 
 class LLMAnalyzer:
@@ -25,7 +20,7 @@ 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 +59,11 @@ 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 +165,7 @@ 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