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

@@ -35,26 +35,8 @@ JWT_SECRET=your-secure-jwt-secret-change-in-production
 # Defaults to http://localhost:3000,http://localhost:5173 when unset
 # CORS_ORIGINS=https://sparc.example.com,https://app.example.com
 
-# ---- Storage ----
-
-# Backend for patent PDF storage: "local" (default) or "s3"
-STORAGE_BACKEND=local
-
-# S3/MinIO settings (only used when STORAGE_BACKEND=s3)
-# S3_BUCKET=sparc-patents
-# S3_ENDPOINT_URL=http://localhost:9000
-# AWS_ACCESS_KEY_ID=minioadmin
-# AWS_SECRET_ACCESS_KEY=minioadmin
-# To start MinIO locally: docker compose --profile s3 up -d minio
-
 # ---- Cache ----
 
 # 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

.gitea/workflows/test.yaml

@@ -34,17 +34,6 @@ jobs:
         run: |
           ruff check SPARC/ tests/
 
-      - name: Install Node.js and frontend dependencies
-        shell: sh
-        run: |
-          apk add --no-cache nodejs npm
-          cd frontend && npm ci
-
-      - name: Run TypeScript type check
-        shell: sh
-        run: |
-          cd frontend && npx tsc --noEmit
-
       - name: Run pytest
         shell: sh
         env:

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(
@@ -108,10 +104,12 @@ class CompanyAnalyzer:
     def analyze_single_patent(self, patent_id: str, company_name: str) -> str:
         """Analyze a single patent by ID.
 
-        If the patent PDF is not already on disk, this method attempts to
+        Prerequisite:
-        download it automatically by looking up the PDF link in the database
+            The patent PDF must already exist at ``patents/{patent_id}.pdf``
-        cache. If the link is not cached either, a ``FileNotFoundError`` is
+            before calling this method. PDFs are downloaded automatically when
-        raised with instructions on how to obtain the PDF.
+            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 (e.g. "US-11234567-B2")
@@ -121,29 +119,16 @@ class CompanyAnalyzer:
           Analysis of the specific patent's innovation quality
 
         Raises:
-          FileNotFoundError: If the patent PDF cannot be found or downloaded.
+          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"
 
         if not os.path.exists(patent_path):
-            # Attempt to download the PDF automatically from cached metadata
-            cached = self.db.get_cached_patent(patent_id)
-            pdf_link = cached.get("pdf_link") if cached else None
-
-            if pdf_link:
-                logger.info("PDF not on disk; downloading %s from cached link", patent_id)
-                patent = SERP.save_patents(
-                    Patent(patent_id=patent_id, pdf_link=pdf_link)
-                )
-                patent_path = patent.pdf_path
-            else:
             raise FileNotFoundError(
-                    f"Patent PDF not found at '{patent_path}' and no download link is "
+                f"Patent PDF not found at '{patent_path}'. "
-                    f"cached for '{patent_id}'. Run a company analysis first to populate "
+                f"Download the PDF first using SERP.save_patents() or the batch analysis pipeline."
-                    f"the cache, or call SERP.save_patents() with the patent's PDF link."
             )
 
         try:
@@ -198,7 +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:
@@ -269,7 +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 = {
@@ -286,8 +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)
@@ -302,12 +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,
@@ -333,20 +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/api.py

@@ -9,7 +9,7 @@ from typing import Annotated, List
 
 from fastapi import BackgroundTasks, Depends, FastAPI, HTTPException, Query, Request
 from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import JSONResponse, StreamingResponse
+from fastapi.responses import JSONResponse
 from pydantic import BaseModel, EmailStr, Field
 from slowapi import Limiter
 from slowapi.errors import RateLimitExceeded
@@ -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
 
@@ -77,13 +75,6 @@ class JobStatus(BaseModel):
     error: str | None = None
 
 
-class PaginatedJobsResponse(BaseModel):
-    """Paginated response for job listings."""
-
-    items: list["JobStatus"]
-    next_cursor: str | None = None
-
-
 class HealthResponse(BaseModel):
     """Health check response."""
 
@@ -164,7 +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
@@ -176,13 +166,9 @@ async def lifespan(app: FastAPI):
         import logging
         logging.getLogger(__name__).warning("Marked %d stale jobs as failed on startup", stale)
     _db.close()
-    # Start scheduled analysis if tracked companies are configured
-    from SPARC.scheduler import start_scheduler
-    start_scheduler()
     yield
-    # Cleanup
+    # Cleanup if needed
     _analyzer = None
-    close_db_client()
 
 
 app = FastAPI(
@@ -379,60 +365,6 @@ async def delete_user(
     return {"message": "User deleted"}
 
 
-# ============== Tracked Companies Endpoints ==============
-
-
-class TrackCompanyRequest(BaseModel):
-    """Request to add a company to tracking."""
-
-    company_name: str = Field(..., min_length=1, max_length=255)
-
-
-@app.get("/admin/tracked", tags=["Admin"])
-async def list_tracked_companies(
-    _: UserResponse = Depends(get_current_admin),
-):
-    """List all tracked companies (admin only)."""
-    db = get_db_client()
-    return db.list_tracked_companies()
-
-
-@app.post("/admin/tracked", tags=["Admin"])
-async def add_tracked_company(
-    request: TrackCompanyRequest,
-    _: UserResponse = Depends(get_current_admin),
-):
-    """Add a company to the tracked list (admin only)."""
-    db = get_db_client()
-    result = db.add_tracked_company(request.company_name)
-    if not result:
-        raise HTTPException(status_code=409, detail="Company already tracked")
-    return result
-
-
-@app.delete("/admin/tracked/{company_name}", tags=["Admin"])
-async def remove_tracked_company(
-    company_name: str,
-    _: UserResponse = Depends(get_current_admin),
-):
-    """Remove a company from the tracked list (admin only)."""
-    db = get_db_client()
-    removed = db.remove_tracked_company(company_name)
-    if not removed:
-        raise HTTPException(status_code=404, detail="Company not found in tracking list")
-    return {"message": f"Stopped tracking {company_name}"}
-
-
-@app.get("/admin/alerts", tags=["Admin"])
-async def list_alerts(
-    limit: int = Query(default=50, ge=1, le=200),
-    _: UserResponse = Depends(get_current_admin),
-):
-    """List recent alerts from scheduled analysis (admin only)."""
-    db = get_db_client()
-    return db.list_alerts(limit=limit)
-
-
 # ============== Analytics Endpoint ==============
 
 
@@ -453,61 +385,6 @@ async def get_analytics(
     )
 
 
-# ============== Export Endpoints ==============
-
-
-@app.get("/export/{company_name}", tags=["Export"])
-async def export_company_csv(
-    company_name: str,
-    _: UserResponse = Depends(get_current_user),
-):
-    """Export analysis results for a company as a CSV file.
-
-    Returns all stored analysis records for the given company, including
-    analysis type, model used, response text, and timestamp.
-
-    Args:
-        company_name: Company name to export results for
-
-    Returns:
-        CSV file download
-    """
-    import csv
-    import io
-
-    db = get_db_client()
-    # Query all non-cached analysis results for this company
-    with db.get_conn() as conn:
-        with conn.cursor() as cur:
-            cur.execute(
-                """
-                SELECT company_name, analysis_type, model, response, timestamp
-                FROM llm_messages
-                WHERE LOWER(company_name) = LOWER(%s) AND is_cached = FALSE
-                ORDER BY timestamp DESC
-                """,
-                (company_name,),
-            )
-            rows = cur.fetchall()
-
-    if not rows:
-        raise HTTPException(status_code=404, detail=f"No analysis results found for '{company_name}'")
-
-    output = io.StringIO()
-    writer = csv.writer(output)
-    writer.writerow(["company_name", "analysis_type", "model", "analysis", "timestamp"])
-    for row in rows:
-        writer.writerow(row)
-
-    output.seek(0)
-    safe_name = company_name.replace(" ", "_").lower()
-    return StreamingResponse(
-        iter([output.getvalue()]),
-        media_type="text/csv",
-        headers={"Content-Disposition": f'attachment; filename="sparc_{safe_name}_export.csv"'},
-    )
-
-
 # ============== System Endpoints ==============
 
 
@@ -548,38 +425,6 @@ async def analyze_company(
     return _convert_result(result)
 
 
-@app.get(
-    "/analyze/patent/{patent_id}",
-    tags=["Analysis"],
-)
-async def analyze_single_patent(
-    patent_id: str,
-    company_name: str = Query(description="Company name for analysis context"),
-    _: UserResponse = Depends(get_current_user),
-):
-    """Analyze a single patent by its publication ID.
-
-    If the patent PDF is not already cached locally, the system will attempt
-    to download it automatically from a previously cached link. If no link
-    is available, a 404 error is returned.
-
-    Args:
-        patent_id: Patent publication ID (e.g. "US-11234567-B2")
-        company_name: Company name for analysis context
-
-    Returns:
-        Analysis text for the patent
-    """
-    if not _analyzer:
-        raise HTTPException(status_code=503, detail="Analyzer not initialized")
-
-    try:
-        analysis = _analyzer.analyze_single_patent(patent_id, company_name)
-        return {"patent_id": patent_id, "company_name": company_name, "analysis": analysis}
-    except FileNotFoundError as e:
-        raise HTTPException(status_code=404, detail=str(e))
-
-
 @app.post(
     "/analyze/batch",
     response_model=BatchAnalysisResponse,
@@ -670,25 +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"])
@@ -745,51 +573,24 @@ async def get_job_status(
     return _job_row_to_status(job_row)
 
 
-@app.get("/jobs", response_model=PaginatedJobsResponse, tags=["Jobs"])
+@app.get("/jobs", response_model=list[JobStatus], tags=["Jobs"])
 async def list_jobs(
     status: Annotated[
         str | None,
         Query(description="Filter by status: pending, running, completed, failed"),
     ] = None,
     limit: Annotated[int, Query(ge=1, le=100)] = 10,
-    cursor: Annotated[
-        str | None,
-        Query(description="Opaque cursor from a previous response's next_cursor field"),
-    ] = None,
     _: UserResponse = Depends(get_current_user),
 ):
-    """List analysis jobs with cursor-based pagination.
+    """List all analysis jobs.
-
-    Pass ``limit`` to control page size. The response includes a ``next_cursor``
-    field; pass it back as the ``cursor`` query parameter to fetch the next page.
-    When ``next_cursor`` is ``null``, there are no more results.
-
-    Existing clients that use only ``limit`` (without ``cursor``) continue to
-    work without modification.
 
     Args:
         status: Optional filter by job status
         limit: Maximum number of jobs to return (default 10, max 100)
-        cursor: Opaque pagination cursor from a previous response
 
     Returns:
-        Paginated list of job statuses
+        List of job statuses
     """
     db = _get_job_db()
-    # Fetch one extra to determine if there is a next page
+    job_rows = db.list_jobs(status=status, limit=limit)
-    job_rows = db.list_jobs(status=status, limit=limit + 1, cursor=cursor)
+    return [_job_row_to_status(row) for row in job_rows]
-
-    has_next = len(job_rows) > limit
-    if has_next:
-        job_rows = job_rows[:limit]
-
-    items = [_job_row_to_status(row) for row in job_rows]
-
-    next_cursor = None
-    if has_next and job_rows:
-        last = job_rows[-1]
-        created = last["created_at"]
-        ts = created.isoformat() if hasattr(created, "isoformat") else str(created)
-        next_cursor = f"{ts}|{last['job_id']}"
-
-    return PaginatedJobsResponse(items=items, next_cursor=next_cursor)

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.
+    """Get database client for auth operations."""
-
+    client = DatabaseClient(config.database_url)
-    Returns the module-level singleton DatabaseClient. If not yet initialized
+    client.connect()
-    (e.g., during tests), creates a new instance as a fallback.
+    return client
-    """
-    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

@@ -2,20 +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", "")
@@ -53,13 +39,6 @@ root_path = os.getenv("ROOT_PATH", "")
 # Used for safety checks (e.g., refusing default JWT secret in production)
 app_env = os.getenv("APP_ENV", "development")
 
-# Storage backend: "local" (default) or "s3" for S3/MinIO object storage
-storage_backend = os.getenv("STORAGE_BACKEND", "local")
-s3_bucket = os.getenv("S3_BUCKET", "sparc-patents")
-s3_endpoint_url = os.getenv("S3_ENDPOINT_URL", "")
-s3_access_key = os.getenv("AWS_ACCESS_KEY_ID", "")
-s3_secret_key = os.getenv("AWS_SECRET_ACCESS_KEY", "")
-
 # CORS allowed origins (comma-separated)
 # Defaults to localhost dev origins when unset
 _cors_origins_raw = os.getenv("CORS_ORIGINS", "")

SPARC/database.py

@@ -192,35 +192,6 @@ class DatabaseClient:
                 ON jobs(status)
             """)
 
-            # Create tracked companies table for scheduled analysis
-            cursor.execute("""
-                CREATE TABLE IF NOT EXISTS tracked_companies (
-                    id SERIAL PRIMARY KEY,
-                    company_name VARCHAR(255) UNIQUE NOT NULL,
-                    last_patent_count INTEGER DEFAULT 0,
-                    last_analysis_at TIMESTAMP,
-                    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
-                )
-            """)
-
-            # Create alerts table for significant changes
-            cursor.execute("""
-                CREATE TABLE IF NOT EXISTS alerts (
-                    id SERIAL PRIMARY KEY,
-                    company_name VARCHAR(255) NOT NULL,
-                    alert_type VARCHAR(50) NOT NULL,
-                    message TEXT NOT NULL,
-                    old_value NUMERIC,
-                    new_value NUMERIC,
-                    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
-                )
-            """)
-
-            cursor.execute("""
-                CREATE INDEX IF NOT EXISTS idx_alerts_company
-                ON alerts(company_name)
-            """)
-
             self.conn.commit()
 
     @staticmethod
@@ -251,6 +222,8 @@ class DatabaseClient:
         Returns:
             Cached message dict if found, None otherwise
         """
+        self.connect()
+
         prompt_hash = self.hash_prompt(prompt)
 
         query = """
@@ -273,8 +246,7 @@ class DatabaseClient:
 
         query += " ORDER BY timestamp DESC LIMIT 1"
 
-        with self.get_conn() as conn:
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(query, params)
             result = cursor.fetchone()
             return dict(result) if result else None
@@ -305,10 +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 self.conn.cursor() as cursor:
-            with conn.cursor() as cursor:
             cursor.execute(
                 """
                 INSERT INTO llm_messages
@@ -330,7 +303,7 @@ class DatabaseClient:
             )
 
             message_id = cursor.fetchone()[0]
-            conn.commit()
+            self.conn.commit()
 
             return message_id
 
@@ -352,6 +325,8 @@ class DatabaseClient:
         Returns:
             List of message dictionaries
         """
+        self.connect()
+
         query = "SELECT * FROM llm_messages WHERE 1=1"
         params = []
 
@@ -366,8 +341,7 @@ class DatabaseClient:
         query += " ORDER BY timestamp DESC LIMIT %s OFFSET %s"
         params.extend([limit, offset])
 
-        with self.get_conn() as conn:
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(query, params)
             return [dict(row) for row in cursor.fetchall()]
 
@@ -380,8 +354,9 @@ class DatabaseClient:
         Returns:
             Dictionary with analytics data
         """
-        with self.get_conn() as conn:
+        self.connect()
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             # Total messages
             cursor.execute(
                 """
@@ -597,45 +572,20 @@ class DatabaseClient:
         self,
         status: Optional[str] = None,
         limit: int = 10,
-        cursor: Optional[str] = None,
     ) -> List[Dict]:
-        """List jobs with optional status filter and cursor-based pagination.
+        """List jobs, optionally filtered by status."""
-
-        Args:
-            status: Optional status filter (pending, running, completed, failed).
-            limit: Maximum number of jobs to return.
-            cursor: Opaque cursor (``created_at|job_id``) from a previous
-                response. When provided, only jobs older than the cursor are
-                returned.
-
-        Returns:
-            List of job dicts ordered by created_at descending.
-        """
-        conditions: list[str] = []
-        params: list = []
-
-        if status:
-            conditions.append("status = %s")
-            params.append(status)
-
-        if cursor:
-            try:
-                ts_str, cursor_job_id = cursor.rsplit("|", 1)
-                conditions.append("(created_at, job_id) < (%s, %s)")
-                params.extend([ts_str, cursor_job_id])
-            except ValueError:
-                pass  # Ignore malformed cursors; return from start
-
         query = "SELECT * FROM jobs"
-        if conditions:
+        params: list = []
-            query += " WHERE " + " AND ".join(conditions)
+        if status:
-        query += " ORDER BY created_at DESC, job_id DESC LIMIT %s"
+            query += " WHERE status = %s"
+            params.append(status)
+        query += " ORDER BY created_at DESC LIMIT %s"
         params.append(limit)
 
         with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cur:
+            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
-                cur.execute(query, params)
+                cursor.execute(query, params)
-                return [dict(row) for row in cur.fetchall()]
+                return [dict(row) for row in cursor.fetchall()]
 
     def mark_stale_jobs_failed(self) -> int:
         """Mark any jobs in 'running' or 'pending' state as 'failed'.
@@ -701,11 +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 self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
-                with conn.cursor(cursor_factory=RealDictCursor) as cursor:
                 cursor.execute(
                     """
                     INSERT INTO users (email, password_hash, role)
@@ -715,9 +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]:
@@ -730,8 +682,9 @@ class DatabaseClient:
         Returns:
             User dict if authenticated, None otherwise
         """
-        with self.get_conn() as conn:
+        self.connect()
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(
                 "SELECT * FROM users WHERE email = %s",
                 (email,),
@@ -756,8 +709,9 @@ class DatabaseClient:
         Returns:
             User dict or None
         """
-        with self.get_conn() as conn:
+        self.connect()
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(
                 "SELECT id, email, role, created_at FROM users WHERE id = %s",
                 (user_id,),
@@ -774,8 +728,9 @@ class DatabaseClient:
         Returns:
             User dict or None
         """
-        with self.get_conn() as conn:
+        self.connect()
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(
                 "SELECT id, email, role, created_at FROM users WHERE email = %s",
                 (email,),
@@ -793,8 +748,9 @@ class DatabaseClient:
         Returns:
             List of user dicts
         """
-        with self.get_conn() as conn:
+        self.connect()
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(
                 """
                 SELECT id, email, role, created_at
@@ -816,8 +772,9 @@ class DatabaseClient:
         Returns:
             Updated user dict or None
         """
-        with self.get_conn() as conn:
+        self.connect()
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
+
+        with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
             cursor.execute(
                 """
                 UPDATE users
@@ -828,7 +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:
@@ -840,11 +797,12 @@ class DatabaseClient:
         Returns:
             True if deleted
         """
-        with self.get_conn() as conn:
+        self.connect()
-            with conn.cursor() as cursor:
+
+        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:
@@ -853,85 +811,8 @@ class DatabaseClient:
         Returns:
             Number of users
         """
-        with self.get_conn() as conn:
+        self.connect()
-            with conn.cursor() as cursor:
+
+        with self.conn.cursor() as cursor:
             cursor.execute("SELECT COUNT(*) FROM users")
             return cursor.fetchone()[0]
-
-    # Tracked Companies Methods
-
-    def add_tracked_company(self, company_name: str) -> Optional[Dict]:
-        """Add a company to the tracking list."""
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
-                try:
-                    cursor.execute(
-                        "INSERT INTO tracked_companies (company_name) VALUES (%s) RETURNING *",
-                        (company_name,),
-                    )
-                    row = cursor.fetchone()
-                    conn.commit()
-                    return dict(row) if row else None
-                except Exception:
-                    conn.rollback()
-                    return None
-
-    def remove_tracked_company(self, company_name: str) -> bool:
-        """Remove a company from the tracking list."""
-        with self.get_conn() as conn:
-            with conn.cursor() as cursor:
-                cursor.execute(
-                    "DELETE FROM tracked_companies WHERE LOWER(company_name) = LOWER(%s)",
-                    (company_name,),
-                )
-                conn.commit()
-                return cursor.rowcount > 0
-
-    def list_tracked_companies(self) -> List[Dict]:
-        """List all tracked companies."""
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
-                cursor.execute("SELECT * FROM tracked_companies ORDER BY company_name")
-                return [dict(row) for row in cursor.fetchall()]
-
-    def update_tracked_company(
-        self, company_name: str, patent_count: int
-    ) -> None:
-        """Update the last analysis stats for a tracked company."""
-        with self.get_conn() as conn:
-            with conn.cursor() as cursor:
-                cursor.execute(
-                    """UPDATE tracked_companies
-                       SET last_patent_count = %s, last_analysis_at = CURRENT_TIMESTAMP
-                       WHERE LOWER(company_name) = LOWER(%s)""",
-                    (patent_count, company_name),
-                )
-                conn.commit()
-
-    def store_alert(
-        self,
-        company_name: str,
-        alert_type: str,
-        message: str,
-        old_value: float | None = None,
-        new_value: float | None = None,
-    ) -> None:
-        """Record an alert for a significant change."""
-        with self.get_conn() as conn:
-            with conn.cursor() as cursor:
-                cursor.execute(
-                    """INSERT INTO alerts (company_name, alert_type, message, old_value, new_value)
-                       VALUES (%s, %s, %s, %s, %s)""",
-                    (company_name, alert_type, message, old_value, new_value),
-                )
-                conn.commit()
-
-    def list_alerts(self, limit: int = 50) -> List[Dict]:
-        """List recent alerts."""
-        with self.get_conn() as conn:
-            with conn.cursor(cursor_factory=RealDictCursor) as cursor:
-                cursor.execute(
-                    "SELECT * FROM alerts ORDER BY created_at DESC LIMIT %s",
-                    (limit,),
-                )
-                return [dict(row) for row in cursor.fetchall()]

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/scheduler.py

@@ -1,109 +0,0 @@
-"""Scheduled patent analysis for tracked companies.
-
-Uses APScheduler to periodically re-analyze tracked companies and
-detect significant changes in patent counts.
-"""
-
-import logging
-import os
-
-from SPARC import config
-from SPARC.analyzer import CompanyAnalyzer
-from SPARC.database import DatabaseClient
-
-logger = logging.getLogger(__name__)
-
-# Configurable via environment variable (in hours, default 24)
-SCHEDULE_INTERVAL_HOURS = int(os.getenv("SCHEDULE_INTERVAL_HOURS", "24"))
-
-# Patent count change threshold (percentage) to trigger an alert
-CHANGE_THRESHOLD_PERCENT = int(os.getenv("CHANGE_THRESHOLD_PERCENT", "20"))
-
-
-def run_scheduled_analysis() -> None:
-    """Re-analyze all tracked companies and check for significant changes."""
-    db = DatabaseClient(config.database_url)
-    db.connect()
-    db.initialize_schema()
-
-    tracked = db.list_tracked_companies()
-    if not tracked:
-        logger.info("No tracked companies configured; skipping scheduled analysis")
-        return
-
-    logger.info("Running scheduled analysis for %d tracked companies", len(tracked))
-
-    analyzer = CompanyAnalyzer(db_client=db)
-
-    for company_row in tracked:
-        name = company_row["company_name"]
-        old_count = company_row.get("last_patent_count", 0) or 0
-
-        try:
-            result = analyzer._analyze_company_safe(name)
-
-            if result.success:
-                new_count = result.patent_count
-
-                # Update tracking record
-                db.update_tracked_company(name, new_count)
-
-                # Check for significant change
-                if old_count > 0:
-                    delta_pct = abs(new_count - old_count) / old_count * 100
-                    if delta_pct >= CHANGE_THRESHOLD_PERCENT:
-                        direction = "increased" if new_count > old_count else "decreased"
-                        message = (
-                            f"Patent count for {name} {direction} by {delta_pct:.0f}% "
-                            f"({old_count} -> {new_count})"
-                        )
-                        logger.warning("ALERT: %s", message)
-                        db.store_alert(
-                            company_name=name,
-                            alert_type="patent_count_change",
-                            message=message,
-                            old_value=old_count,
-                            new_value=new_count,
-                        )
-                elif new_count > 0:
-                    # First analysis -- record baseline
-                    logger.info("Baseline for %s: %d patents", name, new_count)
-            else:
-                logger.warning("Scheduled analysis failed for %s: %s", name, result.error)
-
-        except Exception as e:
-            logger.error("Error analyzing tracked company %s: %s", name, e)
-
-    db.close()
-    logger.info("Scheduled analysis complete")
-
-
-def start_scheduler() -> None:
-    """Start the APScheduler background scheduler.
-
-    Safe to call at application startup. If apscheduler is not installed,
-    the function logs a warning and returns without starting anything.
-    """
-    try:
-        from apscheduler.schedulers.background import BackgroundScheduler
-    except ImportError:
-        logger.warning(
-            "apscheduler not installed; scheduled analysis disabled. "
-            "Install with: pip install apscheduler"
-        )
-        return
-
-    scheduler = BackgroundScheduler()
-    scheduler.add_job(
-        run_scheduled_analysis,
-        "interval",
-        hours=SCHEDULE_INTERVAL_HOURS,
-        id="scheduled_patent_analysis",
-        replace_existing=True,
-    )
-    scheduler.start()
-    logger.info(
-        "Scheduled patent analysis started (every %d hours, threshold %d%%)",
-        SCHEDULE_INTERVAL_HOURS,
-        CHANGE_THRESHOLD_PERCENT,
-    )

SPARC/serp_api.py

@@ -1,5 +1,4 @@
-import io
+import os
-import logging
 import re
 from datetime import datetime, timedelta
 from typing import Dict
@@ -9,21 +8,8 @@ import requests
 import serpapi
 
 from SPARC import config
-from SPARC.storage import StorageBackend, get_storage_backend
 from SPARC.types import Patent, Patents
 
-logger = logging.getLogger(__name__)
-
-# Module-level storage instance (lazy-initialized)
-_storage: StorageBackend | None = None
-
-
-def _get_storage() -> StorageBackend:
-    global _storage
-    if _storage is None:
-        _storage = get_storage_backend()
-    return _storage
-
 
 class SERP:
   def query(company: str, days_back: int = None) -> Patents:
@@ -58,7 +44,6 @@ 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 = []
@@ -67,16 +52,13 @@ 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))
-        else:
+        # Patents without PDF links are skipped (see docstring for details)
-            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:
-    """Save the patent PDF to storage, skipping download if already cached.
+    """
-
+    Save the patent PDF to the patents folder, skipping download if already cached.
-    Uses the configured storage backend (local filesystem or S3).
 
     Args:
       patent: Patent object
@@ -84,51 +66,35 @@ class SERP:
     Returns:
       Patent object with updated PDF path
     """
-    storage = _get_storage()
+    pdf_path = f"patents/{patent.patent_id}.pdf"
-    key = f"{patent.patent_id}.pdf"
+    os.makedirs("patents", exist_ok=True)
 
-    if not storage.exists(key):
+    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)
-      storage.write(key, response.content)
+      with open(pdf_path, "wb") as f:
-      logger.debug("Saved %d bytes for %s", len(response.content), patent.patent_id)
+        f.write(response.content)
-    else:
-      logger.debug("Using cached PDF for %s", patent.patent_id)
 
-    patent.pdf_path = storage.path_for(key)
+    patent.pdf_path = pdf_path
     return patent
 
   def parse_patent_pdf(pdf_path: str) -> Dict:
     """Extract structured sections from patent PDF.
 
     Extracts all major sections from a patent PDF including abstract,
-    claims, summary, and detailed description. Supports both local file
+    claims, summary, and detailed description.
-    paths and S3 URIs (s3://bucket/key).
 
     Args:
-      pdf_path: Local path or S3 URI to the patent PDF file
+      pdf_path: Path to the patent PDF file
 
     Returns:
       Dictionary containing all extracted sections
     """
-    logger.debug("Parsing patent PDF: %s", pdf_path)
 
-    if pdf_path.startswith("s3://"):
+    with pdfplumber.open(pdf_path) as pdf:
-      # Read from S3 via storage backend
-      storage = _get_storage()
-      # Extract key from "s3://bucket/key"
-      key = pdf_path.split("/", 3)[-1]
-      data = storage.read(key)
-      pdf_file: io.BytesIO | str = io.BytesIO(data)
-    else:
-      pdf_file = pdf_path
-
-    with pdfplumber.open(pdf_file) 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/storage.py

@@ -1,171 +0,0 @@
-"""Patent PDF storage abstraction.
-
-Provides a unified interface for reading and writing patent PDF files,
-with pluggable backends for local filesystem and S3-compatible object
-storage (e.g., MinIO, AWS S3).
-"""
-
-import logging
-import os
-from abc import ABC, abstractmethod
-
-from SPARC import config
-
-logger = logging.getLogger(__name__)
-
-
-class StorageBackend(ABC):
-    """Abstract base class for patent PDF storage."""
-
-    @abstractmethod
-    def read(self, key: str) -> bytes:
-        """Read a file by key.
-
-        Args:
-            key: Storage key (e.g., "US-12345678-B2.pdf")
-
-        Returns:
-            File contents as bytes.
-
-        Raises:
-            FileNotFoundError: If the file does not exist.
-        """
-
-    @abstractmethod
-    def write(self, key: str, data: bytes) -> None:
-        """Write data to storage.
-
-        Args:
-            key: Storage key (e.g., "US-12345678-B2.pdf")
-            data: File contents as bytes.
-        """
-
-    @abstractmethod
-    def exists(self, key: str) -> bool:
-        """Check if a file exists in storage.
-
-        Args:
-            key: Storage key.
-
-        Returns:
-            True if the file exists and has non-zero size.
-        """
-
-    @abstractmethod
-    def path_for(self, key: str) -> str:
-        """Return a path or URI suitable for downstream consumers.
-
-        For local storage this is a filesystem path; for S3 it is the
-        object key (callers that need a local file should use read()
-        and write to a temporary location).
-        """
-
-
-class LocalStorageBackend(StorageBackend):
-    """Store patent PDFs on the local filesystem under a directory."""
-
-    def __init__(self, base_dir: str = "patents"):
-        self.base_dir = base_dir
-        os.makedirs(self.base_dir, exist_ok=True)
-
-    def _full_path(self, key: str) -> str:
-        return os.path.join(self.base_dir, key)
-
-    def read(self, key: str) -> bytes:
-        path = self._full_path(key)
-        if not os.path.exists(path):
-            raise FileNotFoundError(f"File not found: {path}")
-        with open(path, "rb") as f:
-            return f.read()
-
-    def write(self, key: str, data: bytes) -> None:
-        path = self._full_path(key)
-        os.makedirs(os.path.dirname(path) or self.base_dir, exist_ok=True)
-        with open(path, "wb") as f:
-            f.write(data)
-        logger.debug("Wrote %d bytes to %s", len(data), path)
-
-    def exists(self, key: str) -> bool:
-        path = self._full_path(key)
-        return os.path.exists(path) and os.path.getsize(path) > 0
-
-    def path_for(self, key: str) -> str:
-        return self._full_path(key)
-
-
-class S3StorageBackend(StorageBackend):
-    """Store patent PDFs in an S3-compatible bucket."""
-
-    def __init__(
-        self,
-        bucket: str,
-        endpoint_url: str = "",
-        access_key: str = "",
-        secret_key: str = "",
-    ):
-        import boto3
-
-        kwargs: dict = {}
-        if endpoint_url:
-            kwargs["endpoint_url"] = endpoint_url
-        if access_key and secret_key:
-            kwargs["aws_access_key_id"] = access_key
-            kwargs["aws_secret_access_key"] = secret_key
-
-        self.s3 = boto3.client("s3", **kwargs)
-        self.bucket = bucket
-
-        # Ensure bucket exists (useful for MinIO local dev)
-        try:
-            self.s3.head_bucket(Bucket=self.bucket)
-        except Exception:
-            try:
-                self.s3.create_bucket(Bucket=self.bucket)
-                logger.info("Created S3 bucket: %s", self.bucket)
-            except Exception as e:
-                logger.warning("Could not create bucket %s: %s", self.bucket, e)
-
-    def read(self, key: str) -> bytes:
-        try:
-            response = self.s3.get_object(Bucket=self.bucket, Key=key)
-            return response["Body"].read()
-        except self.s3.exceptions.NoSuchKey:
-            raise FileNotFoundError(f"S3 object not found: s3://{self.bucket}/{key}")
-        except Exception as e:
-            if "NoSuchKey" in str(e) or "404" in str(e):
-                raise FileNotFoundError(f"S3 object not found: s3://{self.bucket}/{key}")
-            raise
-
-    def write(self, key: str, data: bytes) -> None:
-        self.s3.put_object(
-            Bucket=self.bucket,
-            Key=key,
-            Body=data,
-            ContentType="application/pdf",
-        )
-        logger.debug("Wrote %d bytes to s3://%s/%s", len(data), self.bucket, key)
-
-    def exists(self, key: str) -> bool:
-        try:
-            response = self.s3.head_object(Bucket=self.bucket, Key=key)
-            return response["ContentLength"] > 0
-        except Exception:
-            return False
-
-    def path_for(self, key: str) -> str:
-        return f"s3://{self.bucket}/{key}"
-
-
-def get_storage_backend() -> StorageBackend:
-    """Factory: return the configured storage backend instance."""
-    backend = config.storage_backend.lower()
-    if backend == "s3":
-        logger.info("Using S3 storage backend (bucket=%s)", config.s3_bucket)
-        return S3StorageBackend(
-            bucket=config.s3_bucket,
-            endpoint_url=config.s3_endpoint_url,
-            access_key=config.s3_access_key,
-            secret_key=config.s3_secret_key,
-        )
-    logger.info("Using local storage backend")
-    return LocalStorageBackend()

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,
-    })

docker-compose.yml

@@ -52,29 +52,6 @@ services:
       - ./patents:/app/patents
     restart: unless-stopped
 
-  # Optional: MinIO for S3-compatible local object storage
-  # Enable by setting STORAGE_BACKEND=s3 in .env
-  minio:
-    image: minio/minio:latest
-    container_name: sparc-minio
-    command: server /data --console-address ":9001"
-    environment:
-      MINIO_ROOT_USER: ${AWS_ACCESS_KEY_ID:-minioadmin}
-      MINIO_ROOT_PASSWORD: ${AWS_SECRET_ACCESS_KEY:-minioadmin}
-    ports:
-      - "9000:9000"
-      - "9001:9001"
-    volumes:
-      - minio_data:/data
-    healthcheck:
-      test: ["CMD", "mc", "ready", "local"]
-      interval: 10s
-      timeout: 5s
-      retries: 3
-    restart: unless-stopped
-    profiles:
-      - s3
-
   dashboard:
     build: ./frontend
     container_name: sparc-dashboard
@@ -86,4 +63,3 @@ services:
 
 volumes:
   postgres_data:
-  minio_data:

frontend/index.html

@@ -7,15 +7,6 @@
     <title>SPARC Dashboard</title>
   </head>
   <body>
-    <script>
-      // Prevent FOUC: apply saved theme before first render
-      (function() {
-        var theme = localStorage.getItem('theme');
-        if (theme === 'dark' || (!theme && window.matchMedia('(prefers-color-scheme: dark)').matches)) {
-          document.documentElement.classList.add('dark');
-        }
-      })();
-    </script>
     <div id="root"></div>
     <script type="module" src="/src/main.tsx"></script>
   </body>

frontend/package-lock.json

@@ -10,7 +10,7 @@
       "dependencies": {
         "@tanstack/react-query": "^5.51.0",
         "axios": "^1.7.2",
-        "lucide-react": "^1.7.0",
+        "lucide-react": "^0.400.0",
         "react": "^18.3.1",
         "react-dom": "^18.3.1",
         "react-router-dom": "^6.24.0",
@@ -3452,9 +3452,9 @@
       }
     },
     "node_modules/lucide-react": {
-      "version": "1.7.0",
+      "version": "0.400.0",
-      "resolved": "https://registry.npmjs.org/lucide-react/-/lucide-react-1.7.0.tgz",
+      "resolved": "https://registry.npmjs.org/lucide-react/-/lucide-react-0.400.0.tgz",
-      "integrity": "sha512-yI7BeItCLZJTXikmK4KNUGCKoGzSvbKlfCvw44bU4fXAL6v3gYS4uHD1jzsLkfwODYwI6Drw5Tu9Z5ulDe0TSg==",
+      "integrity": "sha512-rpp7pFHh3Xd93KHixNgB0SqThMHpYNzsGUu69UaQbSZ75Q/J3m5t6EhKyMT3m4w2WOxmJ2mY0tD3vebnXqQryQ==",
       "license": "ISC",
       "peerDependencies": {
         "react": "^16.5.1 || ^17.0.0 || ^18.0.0 || ^19.0.0"

frontend/package.json

@@ -7,13 +7,12 @@
     "dev": "vite",
     "build": "tsc -b && vite build",
     "lint": "eslint .",
-    "typecheck": "tsc --noEmit",
     "preview": "vite preview"
   },
   "dependencies": {
     "@tanstack/react-query": "^5.51.0",
     "axios": "^1.7.2",
-    "lucide-react": "^1.7.0",
+    "lucide-react": "^0.400.0",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "react-router-dom": "^6.24.0",

frontend/src/App.tsx

@@ -1,7 +1,6 @@
 import { BrowserRouter, Routes, Route, Navigate } from 'react-router-dom';
 import { QueryClient, QueryClientProvider } from '@tanstack/react-query';
 import { AuthProvider } from './context/AuthContext';
-import { ThemeProvider } from './context/ThemeContext';
 import { Layout } from './components/Layout';
 import { ProtectedRoute } from './components/ProtectedRoute';
 import { Login } from './pages/Login';
@@ -23,7 +22,6 @@ const queryClient = new QueryClient({
 
 function App() {
   return (
-    <ThemeProvider>
     <QueryClientProvider client={queryClient}>
       <AuthProvider>
         <BrowserRouter>
@@ -63,7 +61,6 @@ function App() {
         </BrowserRouter>
       </AuthProvider>
     </QueryClientProvider>
-    </ThemeProvider>
   );
 }
 

frontend/src/api/client.ts

@@ -126,23 +126,6 @@ export const analysisApi = {
   },
 };
 
-// Export API
-export const exportApi = {
-  exportCsv: async (companyName: string): Promise<void> => {
-    const response = await api.get(`/export/${encodeURIComponent(companyName)}`, {
-      responseType: 'blob',
-    });
-    const url = window.URL.createObjectURL(new Blob([response.data]));
-    const link = document.createElement('a');
-    link.href = url;
-    link.setAttribute('download', `sparc_${companyName.toLowerCase().replace(/\s+/g, '_')}_export.csv`);
-    document.body.appendChild(link);
-    link.click();
-    link.remove();
-    window.URL.revokeObjectURL(url);
-  },
-};
-
 // Analytics API
 export const analyticsApi = {
   getAnalytics: async (days = 30): Promise<Analytics> => {

frontend/src/components/Layout.tsx

@@ -1,11 +1,9 @@
 import { Outlet, NavLink, useNavigate } from 'react-router-dom';
 import { useAuth } from '../context/AuthContext';
-import { useTheme } from '../context/ThemeContext';
+import { Search, Layers, BarChart3, Info, Users, LogOut } from 'lucide-react';
-import { Search, Layers, BarChart3, Info, Users, LogOut, Sun, Moon } from 'lucide-react';
 
 export function Layout() {
   const { user, isAdmin, logout } = useAuth();
-  const { theme, toggleTheme } = useTheme();
   const navigate = useNavigate();
 
   const handleLogout = () => {
@@ -25,7 +23,7 @@ export function Layout() {
   }
 
   return (
-    <div className="min-h-screen bg-gradient-to-br from-bg-dark to-slate-100 dark:to-indigo-950">
+    <div className="min-h-screen bg-gradient-to-br from-bg-dark to-indigo-950">
       {/* Header */}
       <header className="bg-bg-card/80 backdrop-blur-lg border-b border-primary/20">
         <div className="max-w-7xl mx-auto px-4 sm:px-6 lg:px-8">
@@ -65,13 +63,6 @@ export function Layout() {
 
             {/* User menu */}
             <div className="flex items-center gap-4">
-              <button
-                onClick={toggleTheme}
-                className="p-2 rounded-lg text-text-secondary hover:text-text-primary hover:bg-bg-card-hover transition-all"
-                aria-label={theme === 'dark' ? 'Switch to light mode' : 'Switch to dark mode'}
-              >
-                {theme === 'dark' ? <Sun size={18} /> : <Moon size={18} />}
-              </button>
               <div className="text-right hidden sm:block">
                 <div className="text-sm font-medium text-text-primary">{user?.email}</div>
                 <div className="text-xs text-text-secondary capitalize">{user?.role}</div>

frontend/src/components/ProtectedRoute.tsx

@@ -12,7 +12,7 @@ export function ProtectedRoute({ children, requireAdmin = false }: ProtectedRout
 
   if (isLoading) {
     return (
-      <div className="min-h-screen bg-gradient-to-br from-bg-dark to-slate-100 dark:to-indigo-950 flex items-center justify-center">
+      <div className="min-h-screen bg-gradient-to-br from-bg-dark to-indigo-950 flex items-center justify-center">
         <div className="animate-spin rounded-full h-12 w-12 border-t-2 border-b-2 border-primary"></div>
       </div>
     );

frontend/src/context/ThemeContext.tsx

@@ -1,48 +0,0 @@
-import { createContext, useContext, useEffect, useState } from 'react';
-
-type Theme = 'light' | 'dark';
-
-interface ThemeContextType {
-  theme: Theme;
-  toggleTheme: () => void;
-}
-
-const ThemeContext = createContext<ThemeContextType | undefined>(undefined);
-
-function getInitialTheme(): Theme {
-  const stored = localStorage.getItem('theme');
-  if (stored === 'light' || stored === 'dark') return stored;
-  return window.matchMedia('(prefers-color-scheme: dark)').matches ? 'dark' : 'light';
-}
-
-export function ThemeProvider({ children }: { children: React.ReactNode }) {
-  const [theme, setTheme] = useState<Theme>(getInitialTheme);
-
-  useEffect(() => {
-    const root = document.documentElement;
-    if (theme === 'dark') {
-      root.classList.add('dark');
-    } else {
-      root.classList.remove('dark');
-    }
-    localStorage.setItem('theme', theme);
-  }, [theme]);
-
-  const toggleTheme = () => {
-    setTheme((prev) => (prev === 'dark' ? 'light' : 'dark'));
-  };
-
-  return (
-    <ThemeContext.Provider value={{ theme, toggleTheme }}>
-      {children}
-    </ThemeContext.Provider>
-  );
-}
-
-export function useTheme() {
-  const context = useContext(ThemeContext);
-  if (!context) {
-    throw new Error('useTheme must be used within a ThemeProvider');
-  }
-  return context;
-}

frontend/src/index.css

@@ -2,26 +2,6 @@
 @tailwind components;
 @tailwind utilities;
 
-/* Light mode (default) */
-:root {
-  --color-bg-dark: #f1f5f9;
-  --color-bg-card: #ffffff;
-  --color-bg-card-hover: #e2e8f0;
-  --color-text-primary: #0f172a;
-  --color-text-secondary: #475569;
-  --color-border: #cbd5e1;
-}
-
-/* Dark mode */
-.dark {
-  --color-bg-dark: #0f172a;
-  --color-bg-card: #1e293b;
-  --color-bg-card-hover: #334155;
-  --color-text-primary: #f8fafc;
-  --color-text-secondary: #94a3b8;
-  --color-border: #334155;
-}
-
 body {
   font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, 'Helvetica Neue', Arial, sans-serif;
   -webkit-font-smoothing: antialiased;
@@ -35,7 +15,7 @@ body {
 }
 
 ::-webkit-scrollbar-track {
-  background: var(--color-bg-card);
+  background: #1e293b;
 }
 
 ::-webkit-scrollbar-thumb {
@@ -50,5 +30,5 @@ body {
 /* Selection */
 ::selection {
   background: rgba(99, 102, 241, 0.3);
-  color: var(--color-text-primary);
+  color: #f8fafc;
 }

frontend/src/pages/Analysis.tsx

@@ -1,7 +1,7 @@
 import { useState } from 'react';
 import { useMutation } from '@tanstack/react-query';
-import { analysisApi, exportApi } from '../api/client';
+import { analysisApi } from '../api/client';
-import { Search, CheckCircle, AlertCircle, Clock, FileText, Download } from 'lucide-react';
+import { Search, CheckCircle, AlertCircle, Clock, FileText } from 'lucide-react';
 import type { CompanyAnalysis } from '../types';
 
 export function Analysis() {
@@ -106,18 +106,9 @@ export function Analysis() {
           {/* Analysis Content */}
           {result.success && result.analysis && (
             <div className="bg-bg-card/60 backdrop-blur-lg border border-primary/15 rounded-2xl p-6">
-              <div className="flex items-center justify-between border-b-2 border-primary/30 pb-2 mb-4">
+              <h3 className="text-lg font-semibold text-text-primary border-b-2 border-primary/30 pb-2 mb-4">
-                <h3 className="text-lg font-semibold text-text-primary">
                 AI Analysis Results
               </h3>
-                <button
-                  onClick={() => exportApi.exportCsv(result.company_name)}
-                  className="flex items-center gap-2 text-sm bg-primary/20 hover:bg-primary/30 text-primary font-medium px-3 py-1.5 rounded-lg transition-colors"
-                >
-                  <Download size={14} />
-                  Export CSV
-                </button>
-              </div>
               <div className="prose prose-invert max-w-none">
                 <div className="text-text-primary whitespace-pre-wrap leading-relaxed">
                   {result.analysis}

frontend/src/pages/Analytics.tsx

@@ -9,38 +9,15 @@ const COLORS = ['#6366f1', '#0ea5e9', '#10b981', '#f59e0b', '#ef4444', '#8b5cf6'
 export function AnalyticsPage() {
   const [days, setDays] = useState(30);
 
-  const { data, isLoading, isError, refetch } = useQuery({
+  const { data, isLoading, isError } = useQuery({
     queryKey: ['analytics', days],
     queryFn: () => analyticsApi.getAnalytics(days),
   });
 
   if (isLoading) {
     return (
-      <div className="space-y-6">
+      <div className="flex items-center justify-center min-h-[400px]">
-        <div>
+        <div className="animate-spin rounded-full h-12 w-12 border-t-2 border-b-2 border-primary"></div>
-          <h2 className="text-xl font-semibold text-text-primary border-b-2 border-primary/30 pb-2 mb-2">
-            Analytics Dashboard
-          </h2>
-          <p className="text-text-secondary">Loading analytics data...</p>
-        </div>
-        {/* Skeleton cards */}
-        <div className="grid grid-cols-1 md:grid-cols-3 gap-4">
-          {[1, 2, 3].map((i) => (
-            <div key={i} className="bg-gradient-to-br from-primary/10 to-secondary/10 border border-primary/20 rounded-xl p-5 text-center animate-pulse">
-              <div className="h-9 w-16 bg-primary/20 rounded mx-auto mb-2" />
-              <div className="h-4 w-24 bg-primary/10 rounded mx-auto" />
-            </div>
-          ))}
-        </div>
-        {/* Skeleton charts */}
-        <div className="grid grid-cols-1 lg:grid-cols-2 gap-6">
-          {[1, 2].map((i) => (
-            <div key={i} className="bg-bg-card/60 border border-primary/15 rounded-2xl p-6 animate-pulse">
-              <div className="h-5 w-40 bg-primary/20 rounded mb-4" />
-              <div className="h-[300px] bg-primary/5 rounded" />
-            </div>
-          ))}
-        </div>
       </div>
     );
   }
@@ -56,18 +33,15 @@ export function AnalyticsPage() {
         <div className="bg-gradient-to-br from-primary/10 to-secondary/5 border border-primary/20 rounded-xl p-6">
           <div className="flex items-center gap-3 text-warning mb-2">
             <Database size={24} />
-            <span className="font-semibold">Unable to Load Analytics</span>
+            <span className="font-semibold">Database Not Connected</span>
           </div>
           <p className="text-text-secondary">
-            Could not connect to the analytics database. Ensure PostgreSQL is running and
+            Set <code className="bg-bg-card px-2 py-1 rounded">USE_DATABASE=true</code> in your .env file to enable analytics tracking.
-            <code className="bg-bg-card px-2 py-1 rounded mx-1">DATABASE_URL</code> is configured correctly.
           </p>
-          <button
+        </div>
-            onClick={() => refetch()}
+        <div className="flex items-center gap-2 bg-secondary/10 border border-secondary/20 text-secondary rounded-xl px-4 py-3">
-            className="mt-3 text-sm bg-primary/20 hover:bg-primary/30 text-primary font-medium px-4 py-2 rounded-lg transition-colors"
+          <AlertCircle size={18} />
-          >
+          <span>Analytics features require storing analysis results in PostgreSQL for historical tracking.</span>
-            Retry
-          </button>
         </div>
       </div>
     );

frontend/src/pages/Batch.tsx

@@ -114,21 +114,9 @@ export function Batch() {
 
       {/* Error */}
       {mutation.isError && (
-        <div className="bg-error/10 border border-error/20 rounded-xl px-4 py-3">
+        <div className="flex items-center gap-2 bg-error/10 border border-error/20 text-error rounded-xl px-4 py-3">
-          <div className="flex items-center gap-2 text-error">
           <AlertCircle size={18} />
-            <span className="font-semibold">Batch analysis failed</span>
+          <span>Batch analysis failed. Please try again.</span>
-          </div>
-          <p className="text-text-secondary text-sm mt-1 ml-7">
-            {mutation.error instanceof Error ? mutation.error.message : 'An unexpected error occurred.'}
-            {' '}Check your connection and try again.
-          </p>
-          <button
-            onClick={() => mutation.reset()}
-            className="ml-7 mt-2 text-sm text-primary hover:text-primary-dark underline"
-          >
-            Dismiss
-          </button>
         </div>
       )}
 

frontend/src/pages/Login.tsx

@@ -31,7 +31,7 @@ export function Login() {
   };
 
   return (
-    <div className="min-h-screen bg-gradient-to-br from-bg-dark to-slate-100 dark:to-indigo-950 flex items-center justify-center px-4">
+    <div className="min-h-screen bg-gradient-to-br from-bg-dark to-indigo-950 flex items-center justify-center px-4">
       <div className="w-full max-w-md">
         {/* Brand */}
         <div className="text-center mb-8">

frontend/src/pages/Register.tsx

@@ -40,7 +40,7 @@ export function Register() {
   };
 
   return (
-    <div className="min-h-screen bg-gradient-to-br from-bg-dark to-slate-100 dark:to-indigo-950 flex items-center justify-center px-4">
+    <div className="min-h-screen bg-gradient-to-br from-bg-dark to-indigo-950 flex items-center justify-center px-4">
       <div className="w-full max-w-md">
         {/* Brand */}
         <div className="text-center mb-8">

frontend/tailwind.config.js

@@ -4,7 +4,6 @@ export default {
     "./index.html",
     "./src/**/*.{js,ts,jsx,tsx}",
   ],
-  darkMode: 'class',
   theme: {
     extend: {
       colors: {
@@ -17,15 +16,15 @@ export default {
         warning: '#f59e0b',
         error: '#ef4444',
         bg: {
-          dark: 'var(--color-bg-dark)',
+          dark: '#0f172a',
-          card: 'var(--color-bg-card)',
+          card: '#1e293b',
-          'card-hover': 'var(--color-bg-card-hover)',
+          'card-hover': '#334155',
         },
         text: {
-          primary: 'var(--color-text-primary)',
+          primary: '#f8fafc',
-          secondary: 'var(--color-text-secondary)',
+          secondary: '#94a3b8',
         },
-        border: 'var(--color-border)',
+        border: '#334155',
       },
     },
   },

requirements.txt

@@ -15,5 +15,3 @@ pandas
 bcrypt
 PyJWT
 slowapi
-apscheduler
-boto3