fix pricing not being entered

b

.env.example

@@ -1,72 +1,29 @@
-# studspider Environment Configuration
+# Brickset.com credentials - LEGO database for pricing, images, UPC codes
+BRICKSET_USERNAME = "your_brickset_username"
+BRICKSET_PASS = "your_brickset_password"
+BRICKSET_API_KEY = "your_brickset_api_key"
 
-# ============================================================================
-# Square API Configuration
-# ============================================================================
+# Square environment - "sandbox" for testing, "production" for live store
+SQUARE_ENV = "sandbox"  # or "production"
 
-# Environment: "production" or "sandbox"
-SQUARE_ENV=sandbox
+# Public webhook URL that Square will POST events to
+SQUARE_WEBHOOK_URL = "https://yourdomain.com/webhook"
 
-# Sandbox credentials
-SANDBOX_SQUARE_APP_ID=your_sandbox_app_id
-SANDBOX_SQUARE_TOKEN=your_sandbox_access_token
+# Sandbox credentials - test environment (fake data, safe for development)
+SANDBOX_SQUARE_APP_ID = "your_sandbox_app_id"
+SANDBOX_SQUARE_TOKEN = "your_sandbox_access_token"
 
-# Production credentials
-PROD_SQUARE_APP_ID=your_production_app_id
-PROD_SQUARE_TOKEN=your_production_access_token
+# Sandbox webhook subscription ID and signature key for verifying webhook requests
+SANDBOX_SQUARE_WEBHOOK_SUB_ID = "your_sandbox_webhook_subscription_id"
+SANDBOX_SQUARE_WEBHOOK_SIGNATURE_KEY = "your_sandbox_webhook_signature_key"
 
-# Square LEGO category ID (find this in Square Dashboard)
-SQUARE_LEGO_CAT_ID=your_lego_category_id
+# Production credentials - live store (real inventory and sales)
+PROD_SQUARE_APP_ID = "your_production_app_id"
+PROD_SQUARE_TOKEN = "your_production_access_token"
 
-# ============================================================================
-# Brickset API Configuration
-# ============================================================================
+# Production webhook subscription ID and signature key for verifying webhook requests
+PROD_SQUARE_WEBHOOK_SUB_ID = "your_production_webhook_subscription_id"
+PROD_SQUARE_WEBHOOK_SIGNATURE_KEY = "your_production_webhook_signature_key"
 
-BRICKSET_USERNAME=your_brickset_username
-BRICKSET_PASS=your_brickset_password
-BRICKSET_API_KEY=your_brickset_api_key
-
-# ============================================================================
-# SSL Certificate Configuration (Optional)
-# ============================================================================
-
-# NOTE: Only needed if running HTTPS directly (not recommended with nginx)
-# For nginx reverse proxy setup, leave these empty
-
-# Path to SSL certificate in PEM format
-# SSL_CERT_PATH=/path/to/cert.pem
-
-# Path to SSL private key in PEM format
-# SSL_KEY_PATH=/path/to/key.pem
-
-# ============================================================================
-# Square Webhook Certificate (P7B Format)
-# ============================================================================
-
-# Path to P7B certificate file for Square webhook signature verification
-# This file is UPLOADED to Square Dashboard, not used by your server
-# Generate with: python convert_to_p7b.py
-SQUARE_P7B_PATH=./cert.p7b
-
-# ============================================================================
-# Server Configuration (Optional)
-# ============================================================================
-
-# Default host and port (can override with command line args)
-# SERVER_HOST=0.0.0.0
-# SERVER_PORT=7432
-# SERVER_HOOK_PORT=8080
-
-# ============================================================================
-# Usage Examples
-# ============================================================================
-
-# Basic HTTP server (recommended with nginx):
-#   python src/test_server.py
-#
-# With SSL from .env:
-#   Set SSL_CERT_PATH and SSL_KEY_PATH above, then:
-#   python src/test_server.py --hook-port 8443 --hook-ssl-only
-#
-# Override SSL from command line:
-#   python src/test_server.py --ssl-cert /custom/cert.pem --ssl-key /custom/key.pem
+# Category ID for LEGO items in Square catalog (find in Dashboard → Items → Categories)
+SQUARE_LEGO_CAT_ID = "your_lego_category_id"

.gitignore

@@ -38,3 +38,6 @@ win/
 bin/
 activate/
 build/
+.pem
+.p7b
+nginx/

.version

@@ -0,0 +1 @@
+0.3.0

README.md

@@ -5,14 +5,14 @@
 
 
 
-is a tool used to talk to brickset.com and a square inventory to pull lego set information for entering in the square db
+is a tool used to talk to brickset.com, pull lego set information and automatically enter it into the square inventory!
 ## Run me
 
 Clone the project
 
 ```bash
   git clone http://git.traps.moe/ph0sgene/studspider.git
-  git checkout uv 
+  git checkout branch 
 ```
 
 Go to the project directory
@@ -30,14 +30,15 @@ Install dependencies
 Start the server
 
 ```bash
-  uvx run studspider.py
+  uv run studspider.py
 ```
 
 
 ## Tech 
 
+- gunicorn
+- uvicorn
 - aiohttp
 - squareup
 - apscheduler
 - aiosqlite
-

config/gunicorn.conf.py

@@ -0,0 +1,108 @@
+import multiprocessing
+import os
+import git
+import src.banner as banner
+
+
+def get_git_commit():
+    """Get first 6 characters of current git commit hash"""
+    try:
+        repo = git.Repo(search_parent_directories=True)
+        return repo.head.commit.hexsha[:6]
+    except Exception:
+        return "unknown"
+
+
+# Server socket
+bind = "127.0.0.1:7433"  # nginx will proxy to this
+backlog = 2048
+
+# Worker processes
+workers = multiprocessing.cpu_count() * 2 + 1  # Recommended formula
+worker_class = "uvicorn.workers.UvicornWorker"  # Async worker for FastAPI
+worker_connections = 1000
+max_requests = 1000  # Restart workers after this many requests
+max_requests_jitter = 50  # Add randomness to prevent all workers restarting at once
+
+# Timeouts
+timeout = 30  # Workers silent for more than this are killed
+keepalive = 2  # Wait this long for requests on Keep-Alive connections
+
+# Logging
+accesslog = "./logs/webhook_access.log"
+errorlog = "./logs/webhook_error.log"
+loglevel = "info"
+access_log_format = '%(h)s %(l)s %(u)s %(t)s "%(r)s" %(s)s %(b)s "%(f)s" "%(a)s" %(D)s'
+
+# Process naming
+proc_name = "studspider"
+
+# Server mechanics
+daemon = False  # Run in foreground (systemd will handle daemonization)
+pidfile = "./logs/studspider.pid"
+umask = 0
+user = None  # Run as current user (systemd will set user)
+group = None
+tmp_upload_dir = None
+
+# SSL (not needed with nginx, but here for reference)
+# keyfile = None
+# certfile = None
+
+# Security
+limit_request_line = 4096
+limit_request_fields = 100
+limit_request_field_size = 8190
+
+# Debugging (disable in production)
+reload = os.getenv("GUNICORN_RELOAD", "false").lower() == "true"
+reload_engine = "auto"
+
+
+# Hooks
+def on_starting(server):
+    """Called just before the master process is initialized."""
+    print("Studspider WEB starting...")
+
+    # Verify .env file exists (workers will load it via get_sq_env.py)
+    from pathlib import Path
+
+    env_path = Path(__file__).parent.parent / ".env"
+    print(f"[@DEBUG] Looking for .env at: {env_path.absolute()}")
+    if env_path.exists():
+        print(f"✓ .env file found (workers will load via get_sq_env.py)")
+    else:
+        print(f"⚠ No .env file found at {env_path.absolute()}")
+
+
+def on_reload(server):
+    """Called to recycle workers during a reload via SIGHUP."""
+    print("🔄 Reloading workers...")
+
+
+def when_ready(server):
+    commit_hash = get_git_commit()
+    banner_text = banner.generate("studspider v0.3.0")
+
+    # Add commit hash to the last line of banner
+    banner_lines = banner_text.rstrip("\n").split("\n")
+    if banner_lines:
+        banner_lines[-1] += f"  - {commit_hash}"
+
+    print("\n".join(banner_lines))
+    print("Built for PLAY-WELL TEKNOLOGIES by contact@studspider.sh\n\n")
+    print("PRODUCTION MODE\n" if os.getenv("SQUARE_ENV") == "production" else "SANDBOX MODE\n")
+    print(f"HOST:\t{bind}")
+    print(f"WORKERS:\t{workers}")
+    print(f"WORKER TYPE:\t{worker_class}")
+    print(f"{'=' * 60}\n")
+
+
+def worker_int(worker):
+    """Called just after a worker exited on SIGINT or SIGQUIT."""
+    print(f"⚠️  Worker {worker.pid} received INT or QUIT signal")
+
+
+def worker_abort(worker):
+    """Called when a worker received the SIGABRT signal."""
+    print(f"❌ Worker {worker.pid} aborted")

edderkop.code-workspace

@@ -1,11 +0,0 @@
-{
-	"folders": [
-		{
-			"path": "."
-		},
-		{
-			"path": "../kopling"
-		}
-	],
-	"settings": {}
-}

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "studpider"
-version = "0.1.0"
+version = "0.3.0"
 description = ""
 authors = [{ name = "CF", email = "ph0sgene@pm.me" }]
 requires-python = ">=3.13,<3.14"
@@ -18,6 +18,11 @@ dependencies = [
     "aiosqlite (>=0.21.0,<0.22.0)",
     "bs4>=0.0.2",
     "reflex>=0.8.14.post1",
+    "fastapi>=0.128.0",
+    "uvicorn>=0.40.0",
+    "gunicorn>=23.0.0",
+    "async-lru>=2.0.4",
+    "gitpython>=3.1.0",
 ]
 
 [build-system]

setup.py

@@ -2,7 +2,7 @@ from setuptools import setup
 
 setup(
     name="studspider",
-    version="0.1",
+    version="0.3.0",
     description="Bricket + Square integration application",
     author="CF",
     author_email="chris-forst@pm.me",

src/abricksetapi.py

@@ -7,9 +7,13 @@ import asyncio
 import os
 import aiohttp
 import json
+import math
 import dotenv
-from typing import Dict, Any
-import throttler
+from typing import Dict, Any, Optional
+from datetime import datetime, timedelta
+from async_lru import alru_cache
+from . import throttler
+from . import get_sq_env
 
 Throttler = throttler.GlobalThrottler
 
@@ -19,16 +23,115 @@ dotenv.load_dotenv()
 class AsyncBricksetAPI:
     """Asynchronous client for the Brickset API"""
 
-    def __init__(self, debug: bool = False, logger=None):
+    def __init__(self, debug: bool = None, logger=None):
         self.username = os.getenv("BRICKSET_USERNAME")
         self.password = os.getenv("BRICKSET_PASS")
         self.api_key = os.getenv("BRICKSET_API_KEY")
-        self.debug = debug
+        # Use DEBUG_MODE from env if debug not explicitly set
+        self.debug = debug if debug is not None else get_sq_env.DEBUG_MODE
         self.headers = {"UserAgent": "studspider/0.1"}
         self.throttler = Throttler(rate_limit=500, period=60)
         self.user_hash = None
         self.logger = logger
 
+        # API usage tracking
+        self.daily_requests_used: Optional[int] = None
+        self.daily_requests_limit = 1000
+        self.usage_last_checked: Optional[datetime] = None
+        self.usage_check_interval = timedelta(hours=1)  # Check usage every hour
+
+    async def get_key_usage_stats(self) -> Dict[str, Any]:
+        """
+        Fetch API key usage statistics from Brickset.
+
+        Returns:
+            dict: Usage stats including dateStamp and apiCalls
+        """
+        url = "https://brickset.com/api/v3.asmx/getKeyUsageStats"
+        params = {"apiKey": self.api_key}
+
+        async with aiohttp.ClientSession() as session:
+            async with session.get(
+                url, params=params, headers=self.headers
+            ) as response:
+                if response.status == 200:
+                    data = await response.read()
+                    result = json.loads(data.decode("utf-8"))
+
+                    if self.debug:
+                        print(f"[@DEBUG] API usage stats: {result}")
+                    if self.logger:
+                        self.logger.debug(f"API usage stats: {result}")
+
+                    return result
+                else:
+                    error_msg = f"Failed to get usage stats: HTTP {response.status}"
+                    if self.logger:
+                        self.logger.error(error_msg)
+                    raise Exception(error_msg)
+
+    async def check_and_update_usage(self) -> bool:
+        """
+        Check current API usage and update internal counter.
+        Automatically called before each request if needed.
+
+        Returns:
+            bool: True if under limit, False if at/over limit
+        """
+        now = datetime.now()
+
+        # Check usage if we haven't checked yet or if it's been over an hour
+        should_check = (
+            self.daily_requests_used is None
+            or self.usage_last_checked is None
+            or (now - self.usage_last_checked) > self.usage_check_interval
+        )
+
+        if should_check:
+            try:
+                stats = await self.get_key_usage_stats()
+                # Brickset returns {"status": "success", "apiKeyUsage": [...]}
+                usage_array = stats.get("apiKeyUsage", [])
+                if usage_array and len(usage_array) > 0:
+                    today_stats = usage_array[0]  # Most recent day
+                    self.daily_requests_used = today_stats.get("count", 0)
+                    self.usage_last_checked = now
+
+                    if self.logger:
+                        self.logger.info(
+                            f"API usage: {self.daily_requests_used}/{self.daily_requests_limit}"
+                        )
+
+                    if self.debug:
+                        print(
+                            f"[@DEBUG] API usage: {self.daily_requests_used}/{self.daily_requests_limit}"
+                        )
+            except Exception as e:
+                if self.logger:
+                    self.logger.warning(f"Failed to check API usage: {e}")
+                # Don't block requests if usage check fails
+                return True
+
+        # Check if we're over the limit
+        if self.daily_requests_used is not None:
+            if self.daily_requests_used >= self.daily_requests_limit:
+                error_msg = f"Daily API limit reached: {self.daily_requests_used}/{self.daily_requests_limit}"
+                if self.logger:
+                    self.logger.error(error_msg)
+                if self.debug:
+                    print(f"[@ERROR] {error_msg}")
+                return False
+
+            # Warn when approaching limit
+            if self.daily_requests_used >= self.daily_requests_limit * 0.9:
+                warning_msg = f"Approaching daily API limit: {self.daily_requests_used}/{self.daily_requests_limit}"
+                if self.logger:
+                    self.logger.warning(warning_msg)
+                if self.debug:
+                    print(f"[@WARNING] {warning_msg}")
+
+        return True
+
     async def login(self) -> Dict[str, Any]:
         """Asynchronously authenticate with Brickset API"""
         url = "https://brickset.com/api/v3.asmx/login"
@@ -55,16 +158,27 @@ class AsyncBricksetAPI:
                     self.logger.info("Successfully authenticated with Brickset API")
                 return result
 
+    @alru_cache(maxsize=1000, ttl=604800)  # Cache 1000 sets, 7 days TTL
     async def get_set(self, set_number: int) -> Dict[str, Any]:
         """
-        Fetch LEGO set information asynchronously
+        Fetch LEGO set information asynchronously (cached for 7 days)
 
         Args:
             set_number (str): LEGO set number
 
         Returns:
             Dict containing set information
+
+        Raises:
+            Exception: If daily API limit exceeded or API error
         """
+        # Check API usage before making request
+        if not await self.check_and_update_usage():
+            raise Exception(
+                f"Brickset API daily limit reached ({self.daily_requests_limit} requests/day). "
+                "Please try again tomorrow."
+            )
+
         if not self.user_hash:
             await self.login()
 
@@ -101,26 +215,30 @@ class AsyncBricksetAPI:
                         )
 
                     set_data = result["sets"][0]
+
+                    # Try to get UPC barcode, fall back to EAN if not available
+                    barcode_data = set_data.get("barcode", {})
+                    upc_code = barcode_data.get("UPC") or barcode_data.get("EAN")
+
+                    # Get retail price before rounding
+                    retail_price = set_data["LEGOCom"]["US"]["retailPrice"]
+
                     our_set = {
                         "set_num": set_data["number"],
                         "set_name": set_data["name"],
                         "set_theme": set_data["theme"],
                         "set_image": set_data["image"]["thumbnailURL"],
-                        "set_barcode": set_data["barcode"]["UPC"],
-                        "set_retailprice": round(
-                            set_data["LEGOCom"]["US"]["retailPrice"]
-                        ),
+                        "set_barcode": upc_code,
+                        "set_retailprice": round(retail_price),
                     }
 
-                    # Calculate adjusted price (10% markup)
-                    retail_price = our_set["set_retailprice"]
-                    our_set["set_adjustredprice"] = retail_price + (
-                        (10 / 100) * retail_price
-                    )
+                    # Calculate adjusted price (10% markup), then round up
+                    adjusted_price = retail_price * 1.10
+                    our_set["set_adjustredprice"] = math.ceil(adjusted_price)
 
                     # Set PW inventory name with theme
                     our_set["pw_name"] = (
-                        f"{our_set['set_num']} - {our_set['set_theme'].upper()} {our_set['set_name']}"
+                        f"{our_set['set_num']} - {our_set['set_theme'].upper()} - {our_set['set_name']}"
                     )
 
                     # Flag for manual price review if needed

src/asquare.py

@@ -4,11 +4,15 @@ import json
 import asyncio
 import uuid
 import re
+import traceback
 from time import time
+import aiohttp
+from io import BytesIO
 
-import db
+from square.core.api_error import ApiError
 
-import get_sq_env
+from . import db
+from . import get_sq_env
 
 
 def get_set_number(text: str) -> int:
@@ -51,33 +55,462 @@ async def get_itm(sku: str):
     return {"name": name, "id": itm_id}
 
 
-async def update_itm(lego_set: dict):
+async def get_item_by_id(item_id: str) -> dict:
+    """
+    Retrieve full item details by Square catalog item ID.
+
+    Uses batch_get API for direct ID lookup.
+
+    Args:
+        item_id: Square catalog item ID
+
+    Returns:
+        dict: Item details including name, category_id, variations, etc.
+
+    Raises:
+        ValueError: If item not found
+        Exception: If API error
+    """
+    try:
+        # Use batch_get to retrieve item directly by ID
+        result = await client.catalog.batch_get(
+            object_ids=[item_id],
+            include_related_objects=False,
+        )
+        result_json = json.loads(result.model_dump_json())
+
+        if not result_json.get("objects"):
+            raise ValueError(f"Item {item_id} not found (may have been deleted)")
+
+        obj = result_json["objects"][0]
+        item_data = obj.get("item_data", {})
+
+        return {
+            "id": obj["id"],
+            "item_data": item_data,  # Return the entire item_data object
+            "updated_at": obj.get("updated_at"),
+            "version": obj.get("version"),
+        }
+
+    except ValueError:
+        raise
+    except Exception as e:
+        print(f"[@ERROR] Failed to get item {item_id}: {e}")
+        raise
+
+
+async def get_item_by_variation_id(variation_id: str) -> dict:
+    """
+    Retrieve parent item details from a variation ID.
+
+    Webhooks send variation IDs (inventory.count.updated), but we need
+    the parent item to extract the set number from the name.
+
+    Since async Square API lacks direct object retrieval, we search all items
+    in the LEGO category and match variations.
+
+    Args:
+        variation_id: Square catalog item variation ID
+
+    Returns:
+        dict: Parent item details
+
+    Raises:
+        Exception: If variation/item not found or API error
+    """
+    try:
+        # Search LEGO category items to find which one has this variation
+        print(f"[@DEBUG] Searching for variation {variation_id} in LEGO category")
+
+        cursor = None
+        page_count = 0
+        max_pages = 50  # Safety limit to prevent infinite loops
+
+        while page_count < max_pages:
+            page_count += 1
+            print(f"[@DEBUG] Searching page {page_count}...")
+
+            search_params = {
+                "object_types": ["ITEM"],
+                "query": {
+                    "exact_query": {
+                        "attribute_name": "category_id",
+                        "attribute_value": LEGO_CAT_ID,
+                    }
+                },
+                "limit": 1000,
+            }
+
+            if cursor:
+                search_params["cursor"] = cursor
+
+            result = await client.catalog.search(**search_params)
+            result_json = json.loads(result.model_dump_json())
+
+            if not result_json.get("objects"):
+                if page_count == 1:
+                    raise ValueError(f"No items found in LEGO category")
+                else:
+                    # No more results
+                    print(f"[@DEBUG] No more results on page {page_count}")
+                    break
+
+            # Search through items on this page to find which has this variation
+            for obj in result_json["objects"]:
+                item_data = obj.get("item_data", {})
+                variations = item_data.get("variations", [])
+
+                for variation in variations:
+                    if variation.get("id") == variation_id:
+                        # Found the parent item!
+                        print(
+                            f"[@DEBUG] Found parent item: {obj['id']} on page {page_count}"
+                        )
+
+                        # Since we searched by category, we know it's in LEGO_CAT_ID
+                        # But also try to get from item_data as fallback
+                        category_id = item_data.get("category_id") or LEGO_CAT_ID
+
+                        print(
+                            f"[@DEBUG] Item category_id from data: {item_data.get('category_id')}"
+                        )
+                        print(f"[@DEBUG] Using category_id: {category_id}")
+
+                        return {
+                            "id": obj["id"],
+                            "name": item_data.get("name", ""),
+                            "description": item_data.get("description", ""),
+                            "category_id": category_id,
+                            "variations": variations,
+                            "updated_at": obj.get("updated_at"),
+                            "version": obj.get("version"),
+                        }
+
+            # Check if there are more pages
+            cursor = result_json.get("cursor")
+            if not cursor:
+                # No more pages
+                print(f"[@DEBUG] No more pages after page {page_count}")
+                break
+
+        # If we get here, variation wasn't found
+        if page_count >= max_pages:
+            raise ValueError(
+                f"Variation {variation_id} not found after searching {max_pages} pages (possible infinite loop prevented)"
+            )
+
+        raise ValueError(
+            f"Variation {variation_id} not found in any LEGO category item (searched {page_count} pages)"
+        )
+
+    except Exception as e:
+        print(f"[@ERROR] Failed to get item from variation {variation_id}: {e}")
+        raise
+
+
+async def upload_item_image(item_id: str, image_url: str) -> bool:
+    """
+    Download image from URL and upload to Square catalog item.
+
+    Args:
+        item_id: Square catalog item ID
+        image_url: URL to download image from (e.g., Brickset thumbnail)
+
+    Returns:
+        bool: True if upload successful, False otherwise
+    """
+    try:
+        print(f"[@DEBUG] Downloading image from {image_url}")
+
+        # Download image from URL
+        async with aiohttp.ClientSession() as session:
+            async with session.get(image_url) as resp:
+                if resp.status != 200:
+                    print(f"[@ERROR] Failed to download image: HTTP {resp.status}")
+                    return False
+
+                image_data = await resp.read()
+
+        # Determine content type from URL extension
+        content_type = "image/jpeg"
+        if image_url.lower().endswith(".png"):
+            content_type = "image/png"
+        elif image_url.lower().endswith(".gif"):
+            content_type = "image/gif"
+
+        print(
+            f"[@DEBUG] Uploading {len(image_data)} bytes as {content_type} to item {item_id}"
+        )
+
+        # Upload to Square
+        result = await client.catalog.images.create(
+            image_file=image_data,
+            request={
+                "idempotency_key": str(uuid.uuid4()),
+                "image": {
+                    "type": "IMAGE",
+                    "id": f"#IMAGE_{item_id}",
+                    "image_data": {
+                        "name": f"LEGO Set Image",
+                    },
+                },
+                "object_id": item_id,
+            },
+            image_file_name=f"lego_{item_id}.jpg",
+            content_type=content_type,
+        )
+
+        result_json = json.loads(result.model_dump_json())
+
+        if result_json.get("image"):
+            print(f"[@DEBUG] ✓ Successfully uploaded image for item {item_id}")
+            return True
+        else:
+            print(f"[@ERROR] Image upload failed: {result_json}")
+            return False
+
+    except Exception as e:
+        print(f"[@ERROR] Failed to upload image for item {item_id}: {e}")
+        return False
+
+
+async def update_itm(item_id: str, lego_set: dict, item_data: dict = None):
     """
     Asynchronously updates an item in the Square catalog based on the provided LEGO set information.
     Args:
-        lego_set (dict): A dictionary containing LEGO set details. Expected keys include:
-            - "sets": List of set dictionaries, each with "name", "number", "barcode" (with "UPC"), and "image" (with "thumbnailURL").
-            - "pw_name": The name associated with the LEGO set in another system.
-            - "set_adjustredprice": The adjusted price for the set.
+        item_id (str): Square catalog item ID to update
+        lego_set (dict): A dictionary containing LEGO set details from abricksetapi. Expected keys include:
+            - "set_num": LEGO set number (e.g., "75192")
+            - "set_name": Official LEGO set name
+            - "set_theme": LEGO theme (e.g., "Star Wars")
+            - "set_barcode": UPC barcode
+            - "set_image": Thumbnail URL
+            - "pw_name": Formatted name for Square inventory (e.g., "75192 - STAR WARS UCS Millennium Falcon")
+            - "set_adjustredprice": Retail price with 10% markup applied
+        item_data (dict): Optional pre-fetched item data to avoid redundant API call
     Returns:
         bool: True if the update operation was successful.
     Raises:
         KeyError: If expected keys are missing from the input dictionary.
         Exception: For errors during Square API interaction.
     """
-
-    set_name = lego_set["sets"][0]["name"]
-    set_number = lego_set["sets"][0]["number"]
-    set_upc = lego_set["sets"][0]["barcode"]["UPC"]
-    set_image = lego_set["sets"][0]["image"]["thumbnailURL"]
+    try:
+        set_number = lego_set["set_num"]
+        set_name = lego_set["set_name"]
+        set_theme = lego_set["set_theme"]
+        set_upc = lego_set["set_barcode"]
+        set_image = lego_set["set_image"]
         pw_name = lego_set["pw_name"]
         set_adjustedprice = lego_set["set_adjustredprice"]
 
-    result = await client.catalog.search_items(text_filter=set_number, limit=1)
-    itm_id = json.loads(result.model_dump_json())["items"][0]["id"]
+        price_in_cents = int(set_adjustedprice * 100)
+
+        # Retry logic for version conflicts (race conditions with concurrent updates)
+        max_retries = 3
+        retry_delay = 0.5  # seconds
+
+        for attempt in range(max_retries):
+            try:
+                # ALWAYS fetch fresh item data right before update to get latest version
+                print(
+                    f"[@DEBUG] Fetching fresh item data (attempt {attempt + 1}/{max_retries})..."
+                )
+                fresh_item = await get_item_by_id(item_id)
+            except ValueError as e:
+                # Item was deleted between webhook and enrichment
+                print(f"[@WARNING] {e} - skipping update (item may have been deleted)")
+                return
+
+            variations = fresh_item.get("item_data", {}).get("variations", [])
+
+            if not variations:
+                print(
+                    f"[@WARNING] Item {item_id} has no variations, creating new variation"
+                )
+                variation_id = None
+                variation_version = None
+                present_at_location_ids = []
+                present_at_all_locations = False
+            else:
+                variation_id = variations[0]["id"]
+                variation_version = variations[0].get("version")
+                # Check if variation is at all locations
+                present_at_all_locations = variations[0].get(
+                    "present_at_all_locations", False
+                )
+                # Extract location IDs from variation (only if not at all locations)
+                present_at_location_ids = variations[0].get(
+                    "present_at_location_ids", []
+                )
+
+            # Get current version for version control
+            current_version = fresh_item.get("version")
+
+            # CRITICAL: batch_get NEVER returns category_id (always None)
+            # We MUST use the category from initial item_data (from search which includes category)
+            # or fallback to LEGO_CAT_ID since we know this is a LEGO item
+            if item_data and item_data.get("category_id"):
+                category_id = item_data.get("category_id")
+                print(f"[@DEBUG] Using category_id from item_data: {category_id}")
+            else:
+                # Fallback to LEGO_CAT_ID (we know it's a LEGO item if enrichment was triggered)
+                category_id = LEGO_CAT_ID
+                print(
+                    f"[@WARNING] No category_id in item_data, using LEGO_CAT_ID: {LEGO_CAT_ID}"
+                )
+
+            print(f"[@DEBUG] Fresh item version: {current_version}")
+            print(f"[@DEBUG] Fresh variation version: {variation_version}")
+            print(f"[@DEBUG] Final category_id for upsert: {category_id}")
+
+            # Get the full existing item_data and modify only what we need
+            # This preserves ALL existing fields (location settings, tax, etc)
+            existing_item_data = fresh_item.get("item_data", {})
+
+            # Update item-level fields
+            existing_item_data["name"] = pw_name
+            existing_item_data["description"] = f"{set_name} - {set_theme}"
+            existing_item_data["category_id"] = category_id
+
+            # Update only the specific variation, keep all others unchanged
+            existing_variations = existing_item_data.get("variations", [])
+            updated_variations = []
+            variation_found = False
+
+            for existing_var in existing_variations:
+                if existing_var.get("id") == variation_id:
+                    # Preserve all variation fields and only update what we need
+                    updated_var = existing_var.copy()
+                    updated_var_data = existing_var.get(
+                        "item_variation_data", {}
+                    ).copy()
+
+                    # Check if this variation has VARIABLE_PRICING
+                    current_pricing_type = updated_var_data.get("pricing_type")
+                    
+                    # Only set price if not using variable pricing
+                    if current_pricing_type != "VARIABLE_PRICING":
+                        updated_var_data["price_money"] = {
+                            "amount": price_in_cents,
+                            "currency": "USD",
+                        }
+                        print(f"[@DEBUG] Setting price: ${set_adjustedprice} for variation {variation_id}")
+                    else:
+                        print(f"[@WARNING] Skipping price update for {variation_id} - has VARIABLE_PRICING enabled")
+
+                    updated_var_data["sku"] = set_number  # LEGO set number
+                    updated_var_data["upc"] = (
+                        set_upc if set_upc else None
+                    )  # Barcode/GTIN
+
+                    updated_var["item_variation_data"] = updated_var_data
+
+                    # Update version (required for updates)
+                    if variation_version is not None:
+                        updated_var["version"] = variation_version
+
+                    updated_variations.append(updated_var)
+                    variation_found = True
+                else:
+                    # Keeprice_money": {
+                            "amount": price_in_cents,
+                            "currency": "USD",
+                        },
+                        "p other variations as-is
+                    updated_variations.append(existing_var)
+
+            # If variation wasn't found (shouldn't happen), create new one
+            if not variation_found:
+                new_variation = {
+                    "type": "ITEM_VARIATION",
+                    "id": variation_id if variation_id else "#TEMP_VARIATION_ID",
+                    "item_variation_data": {
+                        "item_id": item_id,
+                        "name": "Regular",
+                        "pricing_type": "FIXED_PRICING",
+                        "sku": set_number,
+                        "upc": set_upc if set_upc else None,
+                    },
+                }
+                if variation_version is not None:
+                    new_variation["version"] = variation_version
+                updated_variations.append(new_variation)
+
+            existing_item_data["variations"] = updated_variations
+
+            item_obj = {
+                "type": "ITEM",
+                "id": item_id,
+                "version": current_version,
+                "item_data": existing_item_data,
+            }
+
+            upsert_body = {
+                "idempotency_key": str(uuid.uuid4()),
+                "object": item_obj,
+            }
+
+            # Remove None values
+            if not set_upc:
+                del variation_obj["item_variation_data"]["sku"]
+
+            print(f"[@DEBUG] Upserting item {item_id} with name: {pw_name}")
+            print(f"[@DEBUG] Upsert body: {json.dumps(upsert_body, indent=2)}")
+
+            # Perform upsert using catalog.object.upsert
+            try:
+                result = await client.catalog.object.upsert(
+                    idempotency_key=upsert_body["idempotency_key"],
+                    object=upsert_body["object"],
+                )
+                result_json = json.loads(result.model_dump_json())
+
+                if result_json.get("catalog_object"):
+                    print(f"[@DEBUG] ✓ Successfully updated item {item_id}")
+
+                    # DEBUG: Check what Square actually returned
+                    returned_item = result_json["catalog_object"]
+                    returned_category = returned_item.get("item_data", {}).get(
+                        "category_id"
+                    )
+                    print(f"[@DEBUG] Square returned category_id: {returned_category}")
+
+                    # Upload image if available (DISABLED - concerns about storage costs)
+                    # if set_image:
+                    #     print(f"[@DEBUG] Uploading image from {set_image}")
+                    #     await upload_item_image(item_id, set_image)
 
-    # await sq.catalog.object.upsert()
                     return True
+                else:
+                    print(
+                        f"[@ERROR] Failed to update item {item_id}: No catalog_object in response"
+                    )
+                    return False
+
+            except ApiError as e:
+                # Check if this is a VERSION_MISMATCH error
+                if e.status_code == 400 and e.body and isinstance(e.body, dict):
+                    errors = e.body.get("errors", [])
+                    if any(err.get("code") == "VERSION_MISMATCH" for err in errors):
+                        if attempt < max_retries - 1:
+                            print(
+                                f"[@WARNING] Version conflict on attempt {attempt + 1}, retrying in {retry_delay}s..."
+                            )
+                            await asyncio.sleep(retry_delay)
+                            retry_delay *= 2  # Exponential backoff
+                            continue  # Retry with fresh data
+                        else:
+                            print(
+                                f"[@ERROR] Version conflict persists after {max_retries} attempts, giving up"
+                            )
+                            return False
+                # Re-raise other API errors
+                raise
+
+    except Exception as e:
+        print(f"[@ERROR] Failed to update item {item_id}: {e}")
+        traceback.print_exc()
+        return False
 
 
 async def acat2id(cat_id: str):

src/get_sq_env.py

@@ -1,16 +1,29 @@
 import os
 import dotenv
+from pathlib import Path
 from square.environment import SquareEnvironment
 
-dotenv.load_dotenv()
+# Load .env from project root (parent of src/)
+env_path = Path(__file__).parent.parent / ".env"
+dotenv.load_dotenv(env_path)
 
 LEGO_CAT_ID = os.getenv("SQUARE_LEGO_CAT_ID")
 
-if os.getenv("SQUARE_ENV") == "production":
+SQUARE_WEBHOOK_URL = os.getenv("SQUARE_WEBHOOK_URL")
+
+# Check environment mode
+IS_PRODUCTION = os.getenv("SQUARE_ENV") == "production"
+DEBUG_MODE = not IS_PRODUCTION  # Debug logging enabled in sandbox/dev
+
+if IS_PRODUCTION:
     SQUARE_APP_ID = os.getenv("PROD_SQUARE_APP_ID")
     SQUARE_TOKEN = os.getenv("PROD_SQUARE_TOKEN")
+    SQUARE_WEBHOOK_SIGNATURE_KEY = os.getenv("PROD_SQUARE_WEBHOOK_SIGNATURE_KEY")
+    SQUARE_WEBHOOK_SUB_ID = os.getenv("PROD_SQUARE_WEBHOOK_SUB_ID")
     environment = SquareEnvironment.PRODUCTION
 else:
     SQUARE_APP_ID = os.getenv("SANDBOX_SQUARE_APP_ID")
     SQUARE_TOKEN = os.getenv("SANDBOX_SQUARE_TOKEN")
+    SQUARE_WEBHOOK_SIGNATURE_KEY = os.getenv("SANDBOX_SQUARE_WEBHOOK_SIGNATURE_KEY")
+    SQUARE_WEBHOOK_SUB_ID = os.getenv("SANDBOX_SQUARE_WEBHOOK_SUB_ID")
     environment = SquareEnvironment.SANDBOX

src/glue.py

@@ -9,33 +9,209 @@ from . import asquare
 from . import db
 from . import abricksetapi
 from . import throttler
+
 Throttler = throttler.GlobalThrottler
 
 
 LEGO_CAT_ID = get_sq_env.LEGO_CAT_ID
 
-# big glue boy
-async def do_review() -> bool:
-    result = await asquare.acat2id(LEGO_CAT_ID) # type: ignore
-    for item in result:
-        if not re.match(r".*\d{5}.*", item["name"]):
-            missing = []
-            print(f"{item} is missing its set number!")
-            #print(f"[@DEBUG] Upserting {item['id']} into REVIEW table")
-            item_sanitized = {
-                "sq_object": item["id"],
-                "set_name": item["name"],
-                "set_number": None,
-                "time_added": time
-            }
-            missing.append(item_sanitized)
 
-    for item in missing:
-        print(item)
-        # sq_item = await db.fetch(item["id"])  
-        if item["id"] != sq_item["sq_object"]:
-            print(f"[@DEBUG] {item['id']} is missing)")
-            #await db.upsert("MISSING", item_sanitized, "sq_object")
-        #    #print(f"[@DEBUG] Upserted {item['id']} into REVIEW table")
-        #print(f"[@DEBUG] {item['id']} already in REVIEW table")
+async def enrich_single_item(item_id: str, item_data: dict = None, logger=None) -> bool:
+    r"""
+    Enrich a single Square catalog item with Brickset data.
+
+    Flow:
+    1. Get item details from Square (by item_id) - skip if item_data provided
+    2. Extract 5-digit set number from name (regex \d{5})
+    3. Fetch Brickset data (with throttling)
+    4. Update Square item with enriched data
+    5. Handle errors (no set number → MISSING table)
+
+    Args:
+        item_id: Square catalog item ID
+        item_data: Optional pre-fetched item data (avoids redundant API call)
+        logger: Optional logger instance for debug output
+
+    Returns:
+        True if successful, False otherwise
+    """
+    try:
+        if logger:
+            logger.info(f"Starting enrichment for item {item_id}")
+        else:
+            print(f"[@DEBUG] Starting enrichment for item {item_id}")
+
+        # Get item details from Square (only if not already provided)
+        if item_data is None:
+            item = await asquare.get_item_by_id(item_id)
+        else:
+            item = item_data
+
+        item_name = item.get("name", "")
+
+        if logger:
+            logger.debug(f"Item name: {item_name}")
+        else:
+            print(f"[@DEBUG] Item name: {item_name}")
+
+        # Extract 5-digit set number
+        set_numbers = re.findall(r"\d{5}", item_name)
+
+        if not set_numbers:
+            # No set number found - log to MISSING table
+            if logger:
+                logger.warning(f"No set number found in item {item_id}: {item_name}")
+            else:
+                print(f"[@WARNING] No set number found in item {item_id}: {item_name}")
+
+            await db.upsert(
+                "MISSING",
+                {
+                    "sq_object": item_id,
+                    "time_added": int(time()),
+                    "set_number": None,
+                    "set_name": item_name,
+                },
+                "sq_object",
+            )
+
+            return False
+
+        set_number = set_numbers[0]
+
+        # Check if item is already enriched (format: "XXXXX - THEME Name")
+        # Pattern: 5 digits, space, dash, space, uppercase theme
+        if re.match(r"^\d{5}\s-\s[A-Z]", item_name):
+            if logger:
+                logger.info(f"Item {item_id} already enriched, skipping: {item_name}")
+            else:
+                print(
+                    f"[@DEBUG] Item {item_id} already enriched, skipping: {item_name}"
+                )
             return True
+
+        if logger:
+            logger.info(f"Extracted set number: {set_number}")
+        else:
+            print(f"[@DEBUG] Extracted set number: {set_number}")
+
+        # Fetch Brickset data (with throttling)
+        # debug flag will be auto-set based on SQUARE_ENV
+        brickset_client = abricksetapi.AsyncBricksetAPI(logger=logger)
+        lego_set = await brickset_client.throttled_get_set(set_number)
+
+        if logger:
+            logger.info(f"Retrieved Brickset data for {lego_set['pw_name']}")
+        else:
+            print(f"[@DEBUG] Retrieved Brickset data for {lego_set['pw_name']}")
+
+        # Note: Price updates disabled - enriching without price
+        # REVIEW table logic skipped
+
+        # Update Square item with enriched data (without price)
+        success = await asquare.update_itm(item_id, lego_set, item_data=item)
+
+        if success:
+            if logger:
+                logger.info(f"✓ Successfully enriched item {item_id}")
+            else:
+                print(f"[@DEBUG] ✓ Successfully enriched item {item_id}")
+            return True
+        else:
+            if logger:
+                logger.error(f"Failed to update Square item {item_id}")
+            else:
+                print(f"[@ERROR] Failed to update Square item {item_id}")
+            return False
+
+    except ValueError as e:
+        if logger:
+            logger.error(f"Value error enriching item {item_id}: {e}")
+        else:
+            print(f"[@ERROR] Value error enriching item {item_id}: {e}")
+        return False
+
+    except Exception as e:
+        if logger:
+            logger.error(f"Unexpected error enriching item {item_id}: {e}")
+        else:
+            print(f"[@ERROR] Unexpected error enriching item {item_id}: {e}")
+        import traceback
+
+        traceback.print_exc()
+        return False
+
+
+async def enrich_bulk(logger=None) -> None:
+    """
+    Enrich all items in the LEGO category (bulk operation).
+
+    This is the refactored RUNUPDATE command logic.
+    Iterates all items in LEGO category and enriches each one.
+
+    Args:
+        logger: Optional logger instance for debug output
+    """
+    try:
+        if logger:
+            logger.info("Starting bulk enrichment for LEGO category")
+        else:
+            print(f"[@DEBUG] Starting bulk enrichment for LEGO category {LEGO_CAT_ID}")
+
+        # Get all items in LEGO category
+        items = await asquare.acat2id(LEGO_CAT_ID)
+
+        if logger:
+            logger.info(f"Found {len(items)} items in LEGO category")
+        else:
+            print(f"[@DEBUG] Found {len(items)} items in LEGO category")
+
+        # Enrich each item with concurrent batches
+        successful = 0
+        failed = 0
+        batch_size = 20  # Process 20 items concurrently
+
+        for i in range(0, len(items), batch_size):
+            batch = items[i : i + batch_size]
+            batch_num = (i // batch_size) + 1
+            total_batches = (len(items) + batch_size - 1) // batch_size
+
+            if logger:
+                logger.info(
+                    f"Processing batch {batch_num}/{total_batches} ({len(batch)} items)"
+                )
+            else:
+                print(
+                    f"[@DEBUG] Processing batch {batch_num}/{total_batches} ({len(batch)} items)"
+                )
+
+            # Process batch concurrently
+            tasks = [enrich_single_item(item["id"], logger=logger) for item in batch]
+            results = await asyncio.gather(*tasks, return_exceptions=True)
+
+            # Count results
+            for result in results:
+                if isinstance(result, Exception):
+                    failed += 1
+                elif result:
+                    successful += 1
+                else:
+                    failed += 1
+
+        if logger:
+            logger.info(
+                f"Bulk enrichment complete: {successful} successful, {failed} failed"
+            )
+        else:
+            print(
+                f"[@DEBUG] Bulk enrichment complete: {successful} successful, {failed} failed"
+            )
+
+    except Exception as e:
+        if logger:
+            logger.error(f"Error during bulk enrichment: {e}")
+        else:
+            print(f"[@ERROR] Error during bulk enrichment: {e}")
+        import traceback
+
+        traceback.print_exc()

src/prod/abricksetapi_clean.py

@@ -0,0 +1,277 @@
+"""
+Clean refactored version of abricksetapi.py without debug logging.
+
+This module provides async functions for interacting with Brickset API
+to retrieve LEGO set information.
+"""
+
+import os
+import aiohttp
+import json
+import dotenv
+from typing import Dict, Any, Optional
+from datetime import datetime, timedelta
+
+from . import throttler
+
+dotenv.load_dotenv()
+
+
+class AsyncBricksetAPI:
+    """Asynchronous client for the Brickset API."""
+
+    def __init__(self, logger=None):
+        """
+        Initialize Brickset API client.
+
+        Args:
+            logger: Optional logger instance for structured logging
+        """
+        self.username = os.getenv("BRICKSET_USERNAME")
+        self.password = os.getenv("BRICKSET_PASS")
+        self.api_key = os.getenv("BRICKSET_API_KEY")
+        self.headers = {"UserAgent": "studspider/0.1"}
+        self.throttler = throttler.GlobalThrottler(rate_limit=500, period=60)
+        self.user_hash: Optional[str] = None
+        self.logger = logger
+
+        # API usage tracking (1000 requests per day limit)
+        self.daily_requests_used: Optional[int] = None
+        self.daily_requests_limit = 1000
+        self.usage_last_checked: Optional[datetime] = None
+        self.usage_check_interval = timedelta(hours=1)
+
+    async def login(self) -> Dict[str, Any]:
+        """
+        Authenticate with Brickset API.
+
+        Returns:
+            dict: Authentication response containing user hash
+
+        Raises:
+            Exception: If authentication fails
+        """
+        url = "https://brickset.com/api/v3.asmx/login"
+        params = {
+            "username": self.username,
+            "password": self.password,
+            "apiKey": self.api_key,
+        }
+
+        async with aiohttp.ClientSession() as session:
+            async with session.get(
+                url, params=params, headers=self.headers
+            ) as response:
+                if self.logger:
+                    self.logger.debug(f"Login response status: {response.status}")
+
+                data = await response.read()
+                result = json.loads(data.decode("utf-8"))
+                self.user_hash = result.get("hash")
+
+                if self.logger:
+                    self.logger.info("Successfully authenticated with Brickset API")
+
+                return result
+
+    async def get_key_usage_stats(self) -> Dict[str, Any]:
+        """
+        Fetch API key usage statistics from Brickset.
+
+        Returns:
+            dict: Usage stats with apiKeyUsage array containing dateStamp and count
+        """
+        url = "https://brickset.com/api/v3.asmx/getKeyUsageStats"
+        params = {"apiKey": self.api_key}
+
+        async with aiohttp.ClientSession() as session:
+            async with session.get(
+                url, params=params, headers=self.headers
+            ) as response:
+                if response.status == 200:
+                    data = await response.read()
+                    return json.loads(data.decode("utf-8"))
+                else:
+                    raise Exception(
+                        f"Failed to get usage stats: HTTP {response.status}"
+                    )
+
+    async def check_and_update_usage(self) -> bool:
+        """
+        Check current API usage and update internal counter.
+        Automatically called before each request if needed.
+
+        Returns:
+            bool: True if under limit, False if at/over limit
+        """
+        now = datetime.now()
+
+        # Check usage if we haven't checked yet or if it's been over an hour
+        should_check = (
+            self.daily_requests_used is None
+            or self.usage_last_checked is None
+            or (now - self.usage_last_checked) > self.usage_check_interval
+        )
+
+        if should_check:
+            try:
+                stats = await self.get_key_usage_stats()
+                usage_array = stats.get("apiKeyUsage", [])
+                if usage_array and len(usage_array) > 0:
+                    today_stats = usage_array[0]  # Most recent day
+                    self.daily_requests_used = today_stats.get("count", 0)
+                    self.usage_last_checked = now
+
+                    if self.logger:
+                        self.logger.info(
+                            f"API usage: {self.daily_requests_used}/{self.daily_requests_limit}"
+                        )
+            except Exception as e:
+                if self.logger:
+                    self.logger.warning(f"Failed to check API usage: {e}")
+                return True  # Don't block requests if usage check fails
+
+        # Check if we're over the limit
+        if self.daily_requests_used is not None:
+            if self.daily_requests_used >= self.daily_requests_limit:
+                if self.logger:
+                    self.logger.error(
+                        f"Daily API limit reached: {self.daily_requests_used}/{self.daily_requests_limit}"
+                    )
+                return False
+
+            # Warn when approaching limit (90%)
+            if self.daily_requests_used >= self.daily_requests_limit * 0.9:
+                if self.logger:
+                    self.logger.warning(
+                        f"Approaching daily API limit: {self.daily_requests_used}/{self.daily_requests_limit}"
+                    )
+
+        return True
+
+    async def get_set(self, set_number: int) -> Dict[str, Any]:
+        """
+        Fetch LEGO set information from Brickset API.
+
+        Args:
+            set_number: LEGO set number (e.g., 10338)
+
+        Returns:
+            dict: Set information including:
+                - set_num: LEGO set number
+                - set_name: Official set name
+                - set_theme: Theme (e.g., "Icons")
+                - set_image: Thumbnail URL
+                - set_barcode: UPC or EAN barcode
+                - set_retailprice: US retail price
+                - set_adjustredprice: Retail price + 10% markup
+                - pw_name: Formatted name for Square (e.g., "10338 - ICONS - Bumblebee")
+                - requires_manual_price: True if price >= $110
+
+        Raises:
+            ValueError: If set not found
+            Exception: For API errors or if daily limit exceeded
+        """
+        # Check API usage before making request
+        if not await self.check_and_update_usage():
+            raise Exception(
+                f"Brickset API daily limit reached ({self.daily_requests_limit} requests/day). "
+                "Please try again tomorrow."
+            )
+
+        if not self.user_hash:
+            await self.login()
+
+        url = "https://brickset.com/api/v3.asmx/getSets"
+        params = {
+            "apiKey": self.api_key,
+            "userHash": self.user_hash,
+            "params": json.dumps({"setNumber": f"{set_number}-1"}),
+        }
+
+        async with aiohttp.ClientSession() as session:
+            async with session.get(
+                url, params=params, headers=self.headers
+            ) as response:
+                if self.logger:
+                    self.logger.debug(f"Get set response status: {response.status}")
+
+                if response.status == 200:
+                    data = await response.read()
+                    result = json.loads(data.decode("utf-8"))
+
+                    if not result.get("sets"):
+                        error_msg = f"No data found for set {set_number}"
+                        if self.logger:
+                            self.logger.error(error_msg)
+                        raise ValueError(error_msg)
+
+                    if self.logger:
+                        self.logger.info(
+                            f"Successfully retrieved data for set {set_number}"
+                        )
+
+                    set_data = result["sets"][0]
+
+                    # Get UPC barcode, fall back to EAN if not available
+                    barcode_data = set_data.get("barcode", {})
+                    upc_code = barcode_data.get("UPC") or barcode_data.get("EAN")
+
+                    # Extract set information
+                    our_set = {
+                        "set_num": set_data["number"],
+                        "set_name": set_data["name"],
+                        "set_theme": set_data["theme"],
+                        "set_image": set_data["image"]["thumbnailURL"],
+                        "set_barcode": upc_code,
+                        "set_retailprice": round(
+                            set_data["LEGOCom"]["US"]["retailPrice"]
+                        ),
+                    }
+
+                    # Calculate adjusted price (10% markup)
+                    retail_price = our_set["set_retailprice"]
+                    our_set["set_adjustredprice"] = retail_price + (
+                        (10 / 100) * retail_price
+                    )
+
+                    # Format name for Square inventory
+                    our_set["pw_name"] = (
+                        f"{our_set['set_num']} - {our_set['set_theme'].upper()} - {our_set['set_name']}"
+                    )
+
+                    # Flag for manual price review if needed
+                    if our_set["set_retailprice"] >= 110:
+                        our_set["requires_manual_price"] = True
+
+                    return our_set
+
+                elif response.status == 500:
+                    error_msg = (
+                        "Internal Server Error: Please check API key and parameters."
+                    )
+                    if self.logger:
+                        self.logger.error(error_msg)
+                    raise Exception(error_msg)
+                else:
+                    error_msg = f"Unexpected response: {response.status}"
+                    if self.logger:
+                        self.logger.error(error_msg)
+                    raise Exception(error_msg)
+
+    async def throttled_get_set(self, set_number: int) -> Dict[str, Any]:
+        """
+        Get set information with rate limiting (500 requests per 60 seconds).
+
+        Args:
+            set_number: LEGO set number
+
+        Returns:
+            dict: Set information
+
+        Raises:
+            ValueError: If set not found
+            Exception: For API errors
+        """
+        async with self.throttler:
+            return await self.get_set(set_number)

src/prod/asquare_clean.py

@@ -0,0 +1,426 @@
+"""
+This module provides async functions for interacting with Square Catalog API
+to manage LEGO inventory items.
+"""
+
+import json
+import asyncio
+import uuid
+import re
+import aiohttp
+
+from square.core.api_error import ApiError
+from square import AsyncSquare
+
+from . import get_sq_env
+
+
+def get_set_number(text: str) -> int:
+    """Extract 5-digit LEGO set number from text."""
+    numbers = re.findall(r"\d{5}", text)
+    if not numbers:
+        raise ValueError("No five-digit number found in string")
+    return int(numbers[0])
+
+
+# Configuration
+SQUARE_TOKEN = get_sq_env.SQUARE_TOKEN
+LEGO_CAT_ID = get_sq_env.LEGO_CAT_ID
+ENVIRONMENT = get_sq_env.environment
+
+# Initialize Square client
+client = AsyncSquare(token=SQUARE_TOKEN, environment=ENVIRONMENT)
+
+
+async def get_itm(sku: str) -> dict:
+    """
+    Retrieve item details from Square Catalog using a SKU.
+
+    Args:
+        sku: The SKU or text filter to search for
+
+    Returns:
+        dict: Item name and ID
+
+    Raises:
+        IndexError: If no items found
+        Exception: For API errors
+    """
+    result = await client.catalog.search_items(text_filter=sku, limit=1)
+    result_json = json.loads(result.model_dump_json())
+    name = result_json["items"][0]["item_data"]["name"]
+    itm_id = result_json["items"][0]["id"]
+    return {"name": name, "id": itm_id}
+
+
+async def get_item_by_id(item_id: str) -> dict:
+    """
+    Retrieve full item details by Square catalog item ID.
+
+    Args:
+        item_id: Square catalog item ID
+
+    Returns:
+        dict: Item details including name, category_id, variations, version
+
+    Raises:
+        ValueError: If item not found
+        Exception: For API errors
+    """
+    result = await client.catalog.batch_get(
+        object_ids=[item_id],
+        include_related_objects=False,
+    )
+    result_json = json.loads(result.model_dump_json())
+
+    if not result_json.get("objects"):
+        raise ValueError(f"Item {item_id} not found (may have been deleted)")
+
+    obj = result_json["objects"][0]
+    item_data = obj.get("item_data", {})
+
+    return {
+        "id": obj["id"],
+        "item_data": item_data,
+        "updated_at": obj.get("updated_at"),
+        "version": obj.get("version"),
+    }
+
+
+async def get_item_by_variation_id(variation_id: str) -> dict:
+    """
+    Retrieve parent item details from a variation ID.
+
+    Webhooks send variation IDs, but we need the parent item.
+    Searches all items in LEGO category to find the matching variation.
+
+    Args:
+        variation_id: Square catalog item variation ID
+
+    Returns:
+        dict: Parent item details
+
+    Raises:
+        ValueError: If variation/item not found
+        Exception: For API errors
+    """
+    cursor = None
+    page_count = 0
+
+    while True:
+        page_count += 1
+
+        search_params = {
+            "object_types": ["ITEM"],
+            "query": {
+                "exact_query": {
+                    "attribute_name": "category_id",
+                    "attribute_value": LEGO_CAT_ID,
+                }
+            },
+            "limit": 1000,
+        }
+
+        if cursor:
+            search_params["cursor"] = cursor
+
+        result = await client.catalog.search(**search_params)
+        result_json = json.loads(result.model_dump_json())
+
+        if not result_json.get("objects"):
+            if page_count == 1:
+                raise ValueError("No items found in LEGO category")
+            break
+
+        # Search items on this page for matching variation
+        for obj in result_json["objects"]:
+            item_data = obj.get("item_data", {})
+            variations = item_data.get("variations", [])
+
+            for variation in variations:
+                if variation.get("id") == variation_id:
+                    # Found parent item
+                    category_id = item_data.get("category_id") or LEGO_CAT_ID
+
+                    return {
+                        "id": obj["id"],
+                        "name": item_data.get("name", ""),
+                        "description": item_data.get("description", ""),
+                        "category_id": category_id,
+                        "variations": variations,
+                        "updated_at": obj.get("updated_at"),
+                        "version": obj.get("version"),
+                    }
+
+        cursor = result_json.get("cursor")
+        if not cursor:
+            break
+
+    raise ValueError(
+        f"Variation {variation_id} not found in LEGO category (searched {page_count} pages)"
+    )
+
+
+async def upload_item_image(item_id: str, image_url: str) -> bool:
+    """
+    Download image from URL and upload to Square catalog item.
+
+    Args:
+        item_id: Square catalog item ID
+        image_url: URL to download image from (e.g., Brickset thumbnail)
+
+    Returns:
+        bool: True if successful
+    """
+    try:
+        # Download image
+        async with aiohttp.ClientSession() as session:
+            async with session.get(image_url) as resp:
+                if resp.status != 200:
+                    return False
+                image_data = await resp.read()
+
+        # Determine content type
+        content_type = "image/jpeg"
+        if image_url.lower().endswith(".png"):
+            content_type = "image/png"
+        elif image_url.lower().endswith(".gif"):
+            content_type = "image/gif"
+
+        # Upload to Square
+        result = await client.catalog.images.create(
+            image_file=image_data,
+            request={
+                "idempotency_key": str(uuid.uuid4()),
+                "image": {
+                    "type": "IMAGE",
+                    "id": f"#IMAGE_{item_id}",
+                    "image_data": {"name": "LEGO Set Image"},
+                },
+                "object_id": item_id,
+            },
+            image_file_name=f"lego_{item_id}.jpg",
+            content_type=content_type,
+        )
+
+        result_json = json.loads(result.model_dump_json())
+        return result_json.get("image") is not None
+
+    except Exception:
+        return False
+
+
+async def update_itm(item_id: str, lego_set: dict, item_data: dict = None) -> bool:
+    """
+    Update Square catalog item with Brickset LEGO set data.
+
+    Updates name, description, price, SKU, UPC, and category while preserving
+    all other item fields (location settings, tax, etc).
+
+    Args:
+        item_id: Square catalog item ID to update
+        lego_set: Dict containing LEGO set details from Brickset:
+            - set_num: LEGO set number (e.g., "75192")
+            - set_name: Official LEGO set name
+            - set_theme: LEGO theme (e.g., "Star Wars")
+            - set_barcode: UPC barcode
+            - set_image: Thumbnail URL
+            - pw_name: Formatted name (e.g., "75192 - STAR WARS - Millennium Falcon")
+            - set_adjustredprice: Retail price with 10% markup
+        item_data: Optional pre-fetched item data with category_id
+
+    Returns:
+        bool: True if successful
+
+    Raises:
+        KeyError: If expected keys missing from lego_set
+        Exception: For API errors
+    """
+    try:
+        # Extract LEGO set data
+        set_number = lego_set["set_num"]
+        set_name = lego_set["set_name"]
+        set_theme = lego_set["set_theme"]
+        set_upc = lego_set["set_barcode"]
+        set_image = lego_set["set_image"]
+        pw_name = lego_set["pw_name"]
+        set_adjustedprice = lego_set["set_adjustredprice"]
+
+        price_in_cents = int(set_adjustedprice * 100)
+
+        # Retry logic for version conflicts
+        max_retries = 3
+        retry_delay = 0.5
+
+        for attempt in range(max_retries):
+            try:
+                # Fetch fresh item data for latest version
+                fresh_item = await get_item_by_id(item_id)
+            except ValueError:
+                # Item was deleted
+                return False
+
+            variations = fresh_item.get("item_data", {}).get("variations", [])
+            current_version = fresh_item.get("version")
+
+            # Get variation details
+            if variations:
+                variation_id = variations[0]["id"]
+                variation_version = variations[0].get("version")
+            else:
+                variation_id = None
+                variation_version = None
+
+            # Determine category ID
+            # batch_get doesn't return category_id, so use from item_data or fallback
+            if item_data and item_data.get("category_id"):
+                category_id = item_data.get("category_id")
+            else:
+                category_id = LEGO_CAT_ID
+
+            # Preserve all existing item_data and update only what we need
+            existing_item_data = fresh_item.get("item_data", {})
+            existing_item_data["name"] = pw_name
+            existing_item_data["description"] = f"{set_name} - {set_theme}"
+            existing_item_data["category_id"] = category_id
+
+            # Update only the specific variation
+            existing_variations = existing_item_data.get("variations", [])
+            updated_variations = []
+            variation_found = False
+
+            for existing_var in existing_variations:
+                if existing_var.get("id") == variation_id:
+                    # Preserve all variation fields, update only specific ones
+                    updated_var = existing_var.copy()
+                    updated_var_data = existing_var.get(
+                        "item_variation_data", {}
+                    ).copy()
+
+                    updated_var_data["price_money"] = {
+                        "amount": price_in_cents,
+                        "currency": "USD",
+                    }
+                    updated_var_data["sku"] = set_number
+                    updated_var_data["upc"] = set_upc if set_upc else None
+
+                    updated_var["item_variation_data"] = updated_var_data
+
+                    if variation_version is not None:
+                        updated_var["version"] = variation_version
+
+                    updated_variations.append(updated_var)
+                    variation_found = True
+                else:
+                    updated_variations.append(existing_var)
+
+            # Create new variation if not found
+            if not variation_found:
+                new_variation = {
+                    "type": "ITEM_VARIATION",
+                    "id": variation_id if variation_id else "#TEMP_VARIATION_ID",
+                    "item_variation_data": {
+                        "item_id": item_id,
+                        "name": "Regular",
+                        "pricing_type": "FIXED_PRICING",
+                        "price_money": {
+                            "amount": price_in_cents,
+                            "currency": "USD",
+                        },
+                        "sku": set_number,
+                        "upc": set_upc if set_upc else None,
+                    },
+                }
+                if variation_version is not None:
+                    new_variation["version"] = variation_version
+                updated_variations.append(new_variation)
+
+            existing_item_data["variations"] = updated_variations
+
+            # Build upsert request
+            upsert_body = {
+                "idempotency_key": str(uuid.uuid4()),
+                "object": {
+                    "type": "ITEM",
+                    "id": item_id,
+                    "version": current_version,
+                    "item_data": existing_item_data,
+                },
+            }
+
+            # Perform upsert
+            try:
+                result = await client.catalog.object.upsert(
+                    idempotency_key=upsert_body["idempotency_key"],
+                    object=upsert_body["object"],
+                )
+                result_json = json.loads(result.model_dump_json())
+
+                if result_json.get("catalog_object"):
+                    # Upload image if available (currently disabled)
+                    # if set_image:
+                    #     await upload_item_image(item_id, set_image)
+                    return True
+                else:
+                    return False
+
+            except ApiError as e:
+                # Handle version conflicts with retry
+                if e.status_code == 400 and e.body and isinstance(e.body, dict):
+                    errors = e.body.get("errors", [])
+                    if any(err.get("code") == "VERSION_MISMATCH" for err in errors):
+                        if attempt < max_retries - 1:
+                            await asyncio.sleep(retry_delay)
+                            retry_delay *= 2
+                            continue
+                        else:
+                            return False
+                raise
+
+    except Exception:
+        return False
+
+
+async def acat2id(cat_id: str) -> list[dict]:
+    """
+    List all items in a category.
+
+    Args:
+        cat_id: Category ID to search
+
+    Returns:
+        list[dict]: List of items with id, name, set number, updated_at, version
+    """
+    result = await client.catalog.search(
+        object_types=["ITEM"],
+        query={
+            "exact_query": {
+                "attribute_name": "category_id",
+                "attribute_value": cat_id,
+            }
+        },
+    )
+    result_json = json.loads(result.model_dump_json())
+    items = []
+
+    for obj in result_json.get("objects", []):
+        item_name = obj.get("item_data", {}).get("name", "")
+        set_number = None
+
+        if re.findall(r"\d{5}", item_name):
+            try:
+                set_number = get_set_number(item_name)
+            except ValueError:
+                pass
+
+        items.append(
+            {
+                "id": obj["id"],
+                "name": item_name or "Unknown",
+                "number": set_number,
+                "updated_at": obj.get("updated_at"),
+                "version": obj.get("version"),
+            }
+        )
+
+    return items

src/scripts/list_categories.py

@@ -0,0 +1,89 @@
+"""
+List all Square categories with their IDs to help identify the correct LEGO category ID
+"""
+
+import asyncio
+import json
+from .. import asquare
+from .. import get_sq_env
+
+
+async def list_categories():
+    """List all categories in Square catalog"""
+    try:
+        print("\n" + "=" * 60)
+        print("SQUARE CATALOG CATEGORIES")
+        print("=" * 60 + "\n")
+
+        cursor = None
+        page_count = 0
+        total_categories = 0
+
+        while True:
+            page_count += 1
+            print(f"Fetching page {page_count}...")
+
+            search_params = {
+                "object_types": ["CATEGORY"],
+                "limit": 1000,
+            }
+
+            if cursor:
+                search_params["cursor"] = cursor
+
+            result = await asquare.client.catalog.search(**search_params)
+            result_json = json.loads(result.model_dump_json())
+
+            if not result_json.get("objects"):
+                if page_count == 1:
+                    print("No categories found!")
+                break
+
+            for obj in result_json["objects"]:
+                category_data = obj.get("category_data", {})
+                category_id = obj.get("id")
+                category_name = category_data.get("name", "Unnamed")
+
+                print(f"\nCategory: {category_name}")
+                print(f"  ID: {category_id}")
+
+                # Count items in this category
+                items_result = await asquare.client.catalog.search(
+                    object_types=["ITEM"],
+                    query={
+                        "exact_query": {
+                            "attribute_name": "category_id",
+                            "attribute_value": category_id,
+                        }
+                    },
+                    limit=1,
+                )
+                items_json = json.loads(items_result.model_dump_json())
+                item_count = len(items_json.get("objects", []))
+
+                print(f"  Items: {item_count}+ items")
+                total_categories += 1
+
+            cursor = result_json.get("cursor")
+            if not cursor:
+                break
+
+        print("\n" + "=" * 60)
+        print(f"Total categories found: {total_categories}")
+        print("=" * 60 + "\n")
+
+        # Show current configured category
+        print(f"Currently configured LEGO_CAT_ID: {get_sq_env.LEGO_CAT_ID}")
+        print("\nUpdate .env file with the correct category ID if needed:")
+        print('SQUARE_LEGO_CAT_ID = "YOUR_CATEGORY_ID_HERE"')
+        print()
+
+    except Exception as e:
+        print(f"Error listing categories: {e}")
+        import traceback
+
+        traceback.print_exc()
+
+
+if __name__ == "__main__":
+    asyncio.run(list_categories())

src/scripts/migrate_sku_to_gtin.py

@@ -0,0 +1,162 @@
+"""
+Migrate SKU values to GTIN/UPC field for all LEGO items.
+
+This script reads existing Square catalog items in the LEGO category,
+and for each variation that has a SKU but no UPC, it moves the SKU
+value to the UPC field (leaving SKU empty or optionally extracting
+set number from item name).
+"""
+
+import asyncio
+import json
+import re
+import sys
+import uuid
+from pathlib import Path
+
+# Add parent directory to path for imports
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+import get_sq_env
+from square import AsyncSquare
+
+SQUARE_LEGO_CAT_ID = get_sq_env.LEGO_CAT_ID
+
+
+async def migrate_sku_to_gtin():
+    """Migrate SKU values to GTIN for all LEGO items."""
+    client = AsyncSquare(
+        token=get_sq_env.SQUARE_TOKEN,
+        environment=get_sq_env.environment,
+    )
+
+    print(f"[@INFO] Searching for items in LEGO category {SQUARE_LEGO_CAT_ID}...")
+
+    # Search all items in LEGO category
+    cursor = None
+    page = 1
+    total_items = 0
+    updated_items = 0
+
+    while True:
+        print(f"[@INFO] Processing page {page}...")
+
+        search_params = {
+            "object_types": ["ITEM"],
+            "query": {
+                "exact_query": {
+                    "attribute_name": "category_id",
+                    "attribute_value": SQUARE_LEGO_CAT_ID,
+                }
+            },
+            "limit": 100,
+        }
+
+        if cursor:
+            search_params["cursor"] = cursor
+
+        result = await client.catalog.search(**search_params)
+
+        result_json = json.loads(result.model_dump_json())
+        items = result_json.get("objects", [])
+        cursor = result_json.get("cursor")
+
+        if not items:
+            break
+
+        # Process each item
+        for item in items:
+            item_id = item["id"]
+            item_data = item.get("item_data", {})
+            item_name = item_data.get("name", "")
+            variations = item_data.get("variations", [])
+            item_version = item.get("version")
+
+            total_items += 1
+            needs_update = False
+            updated_variations = []
+
+            # Extract set number from item name if it matches LEGO format
+            set_number = None
+            match = re.search(r"^(\d{5})\s*-", item_name)
+            if match:
+                set_number = match.group(1)
+
+            # Check each variation
+            for var in variations:
+                var_data = var.get("item_variation_data", {})
+                var_id = var.get("id")
+                var_version = var.get("version")
+                sku = var_data.get("sku")
+                upc = var_data.get("upc")
+
+                # If SKU exists but UPC doesn't, migrate
+                if sku and not upc:
+                    print(f"[@INFO]   Item {item_id} ({item_name})")
+                    print(f"[@INFO]     Variation {var_id}: Moving SKU '{sku}' to UPC")
+
+                    # Preserve all existing variation data and only modify what we need
+                    updated_var = var.copy()  # Shallow copy the entire variation
+                    updated_var_data = var_data.copy()  # Copy the variation_data
+
+                    # Update only UPC and SKU fields
+                    updated_var_data["upc"] = sku  # Move SKU value to UPC
+                    updated_var_data["sku"] = (
+                        set_number if set_number else None
+                    )  # Set to LEGO set number
+
+                    updated_var["item_variation_data"] = updated_var_data
+                    updated_variations.append(updated_var)
+                    needs_update = True
+                else:
+                    # Keep variation as-is
+                    updated_variations.append(var)
+
+            # Update item if needed
+            if needs_update:
+                try:
+                    # Get fresh item data to ensure we have latest version
+                    fresh_result = await client.catalog.batch_get(
+                        object_ids=[item_id],
+                        include_related_objects=False,
+                    )
+                    fresh_json = json.loads(fresh_result.model_dump_json())
+                    fresh_item = fresh_json["objects"][0]
+                    fresh_item_data = fresh_item.get("item_data", {})
+                    fresh_version = fresh_item.get("version")
+
+                    # Update variations while preserving all other fields
+                    fresh_item_data["variations"] = updated_variations
+
+                    await client.catalog.object.upsert(
+                        idempotency_key=str(uuid.uuid4()),
+                        object={
+                            "type": "ITEM",
+                            "id": item_id,
+                            "version": fresh_version,
+                            "item_data": fresh_item_data,
+                        },
+                    )
+                    print(f"[@INFO]   ✓ Successfully updated item {item_id}")
+                    updated_items += 1
+
+                    # Small delay to avoid rate limits
+                    await asyncio.sleep(0.1)
+
+                except Exception as e:
+                    print(f"[@ERROR]   Failed to update item {item_id}: {e}")
+
+        page += 1
+
+        # If no cursor, we're done
+        if not cursor:
+            break
+
+    print(f"\n[@INFO] Migration complete!")
+    print(f"[@INFO]   Total items processed: {total_items}")
+    print(f"[@INFO]   Items updated: {updated_items}")
+
+
+if __name__ == "__main__":
+    print("[@INFO] Starting SKU to GTIN migration...\n")
+    asyncio.run(migrate_sku_to_gtin())

src/scripts/syncro/bricksetapi.py

@@ -38,12 +38,17 @@ def get_set(set_number: int) -> dict:
             return False
 
         print(f"[@DEBUG]\t{data}")
+
+        # Try to get UPC barcode, fall back to EAN if not available
+        barcode_data = data["sets"][0].get("barcode", {})
+        upc_code = barcode_data.get("UPC") or barcode_data.get("EAN")
+
         our_set = {
             "set_num": data["sets"][0]["number"],
             "set_name": data["sets"][0]["name"],
             "set_theme": data["sets"][0]["theme"],
             "set_image": data["sets"][0]["image"]["thumbnailURL"],
-            "set_barcode": data["sets"][0]["barcode"]["UPC"],
+            "set_barcode": upc_code,
             "set_retailprice": round(data["sets"][0]["LEGOCom"]["US"]["retailPrice"]),
         }
         # add PW 10% b4 tax
@@ -51,7 +56,7 @@ def get_set(set_number: int) -> dict:
             {"set_adjustredprice": our_set + ((10 / 100) * our_set["set_retailprice"])}
         )
         our_set["pw_name"] = (
-            f"{our_set['set_num']} - {our_set["set_theme"].upper()} {our_set['set_name']}"
+            f"{our_set['set_num']} - {our_set["set_theme"].upper()} - {our_set['set_name']}"
         )
         if our_set["set_retailprice"] >= 110:
             our_set["requires_manual_price"] = True

src/stats.py

@@ -0,0 +1,359 @@
+"""
+Statistics gathering functions for daily_stats table.
+Queries Square catalog to collect metrics about LEGO inventory quality.
+"""
+
+import json
+import git
+from typing import Dict, Any
+from square import AsyncSquare
+from . import get_sq_env
+from . import abricksetapi
+
+
+def get_git_commit() -> str:
+    """Get first 6 characters of current git commit hash"""
+    try:
+        repo = git.Repo(search_parent_directories=True)
+        return repo.head.commit.hexsha[:6]
+    except Exception:
+        return "unknown"
+
+
+# Initialize Square client
+client = AsyncSquare(token=get_sq_env.SQUARE_TOKEN, environment=get_sq_env.environment)
+
+LEGO_CAT_ID = get_sq_env.LEGO_CAT_ID
+
+
+async def get_daily_stats() -> Dict[str, Any]:
+    """
+    Gather all metrics for daily_stats table in a single pass.
+
+    Returns:
+        dict: {
+            "total_items": int,
+            "enriched_items": int,
+            "missing_upcs": int,
+            "missing_images": int,
+            "total_catalog_value": float
+        }
+    """
+    # Get all items in LEGO category
+    result = await client.catalog.search(
+        object_types=["ITEM"],
+        query={
+            "exact_query": {
+                "attribute_name": "category_id",
+                "attribute_value": LEGO_CAT_ID,
+            }
+        },
+    )
+
+    result_json = json.loads(result.model_dump_json())
+    objects = result_json.get("objects", [])
+
+    # Initialize counters
+    total_items = 0
+    enriched_items = 0
+    missing_upcs = 0
+    missing_images = 0
+    total_catalog_value = 0.0
+
+    for obj in objects:
+        total_items += 1
+        item_data = obj.get("item_data", {})
+
+        # Check if item has all enrichment data
+        has_upc = False
+        has_image = False
+        has_proper_name = False
+        item_price = 0.0
+
+        # Check variations for UPC and price
+        variations = item_data.get("variations", [])
+        if variations:
+            var_data = variations[0].get("item_variation_data", {})
+
+            # Check UPC
+            if var_data.get("upc"):
+                has_upc = True
+            else:
+                missing_upcs += 1
+
+            # Get price (stored in cents)
+            price_money = var_data.get("price_money", {})
+            if price_money and price_money.get("amount"):
+                item_price = price_money["amount"] / 100.0  # Convert cents to dollars
+                total_catalog_value += item_price
+        else:
+            missing_upcs += 1
+
+        # Check for image
+        if item_data.get("image_ids"):
+            has_image = True
+        else:
+            missing_images += 1
+
+        # Check if name follows format: "12345 - THEME Set Name"
+        name = item_data.get("name", "")
+        if " - " in name and name.split()[0].isdigit() and len(name.split()[0]) == 5:
+            has_proper_name = True
+
+        # Item is "enriched" if it has UPC, image, and proper name format
+        if has_upc and has_image and has_proper_name:
+            enriched_items += 1
+
+    return {
+        "total_items": total_items,
+        "enriched_items": enriched_items,
+        "missing_upcs": missing_upcs,
+        "missing_images": missing_images,
+        "total_catalog_value": round(total_catalog_value, 2),
+    }
+
+
+async def get_brickset_cache_stats() -> Dict[str, Any]:
+    """
+    Get Brickset API cache statistics.
+
+    Returns:
+        dict: {
+            "cache_enabled": bool,
+            "cache_hits": int,
+            "cache_misses": int,
+            "cache_size": int,
+            "cache_maxsize": int,
+            "hit_rate": float (0-100%)
+        }
+    """
+    # Create a temporary client instance to access cache info
+    temp_client = abricksetapi.AsyncBricksetAPI()
+
+    # Check if get_set has cache_info (it should with @alru_cache)
+    if hasattr(temp_client.get_set, "cache_info"):
+        info = await temp_client.get_set.cache_info()
+        hits = info.hits
+        misses = info.misses
+        total = hits + misses
+        hit_rate = (hits / total * 100) if total > 0 else 0.0
+
+        return {
+            "cache_enabled": True,
+            "cache_hits": hits,
+            "cache_misses": misses,
+            "cache_size": info.currsize,
+            "cache_maxsize": info.maxsize,
+            "hit_rate": round(hit_rate, 2),
+        }
+    else:
+        return {
+            "cache_enabled": False,
+            "cache_hits": 0,
+            "cache_misses": 0,
+            "cache_size": 0,
+            "cache_maxsize": 0,
+            "hit_rate": 0.0,
+        }
+
+
+async def get_daily_stats() -> Dict[str, Any]:
+    """
+    Gather all metrics for daily_stats table in a single pass.
+
+    Returns:
+        dict: {
+            "total_items": int,
+            "enriched_items": int,
+            "missing_upcs": int,
+            "missing_images": int,
+            "total_catalog_value": float
+        }
+    """
+    result = await client.catalog.search(
+        object_types=["ITEM"],
+        query={
+            "exact_query": {
+                "attribute_name": "category_id",
+                "attribute_value": LEGO_CAT_ID,
+            }
+        },
+    )
+
+    result_json = json.loads(result.model_dump_json())
+    return len(result_json.get("objects", []))
+
+
+async def get_enriched_count() -> int:
+    """
+    Count items with complete enrichment (UPC + image + proper name format).
+
+    Returns:
+        int: Number of fully enriched items
+    """
+    result = await client.catalog.search(
+        object_types=["ITEM"],
+        query={
+            "exact_query": {
+                "attribute_name": "category_id",
+                "attribute_value": LEGO_CAT_ID,
+            }
+        },
+    )
+
+    result_json = json.loads(result.model_dump_json())
+    objects = result_json.get("objects", [])
+
+    enriched_count = 0
+
+    for obj in objects:
+        item_data = obj.get("item_data", {})
+
+        # Check UPC
+        has_upc = False
+        variations = item_data.get("variations", [])
+        if variations:
+            var_data = variations[0].get("item_variation_data", {})
+            has_upc = bool(var_data.get("upc"))
+
+        # Check image
+        has_image = bool(item_data.get("image_ids"))
+
+        # Check name format: "12345 - THEME Set Name"
+        name = item_data.get("name", "")
+        has_proper_name = False
+        if " - " in name:
+            first_part = name.split()[0]
+            if first_part.isdigit() and len(first_part) == 5:
+                has_proper_name = True
+
+        if has_upc and has_image and has_proper_name:
+            enriched_count += 1
+
+    return enriched_count
+
+
+async def get_missing_upcs() -> int:
+    """
+    Count items without UPC barcodes.
+
+    Returns:
+        int: Number of items missing UPCs
+    """
+    result = await client.catalog.search(
+        object_types=["ITEM"],
+        query={
+            "exact_query": {
+                "attribute_name": "category_id",
+                "attribute_value": LEGO_CAT_ID,
+            }
+        },
+    )
+
+    result_json = json.loads(result.model_dump_json())
+    objects = result_json.get("objects", [])
+
+    missing_count = 0
+
+    for obj in objects:
+        item_data = obj.get("item_data", {})
+        variations = item_data.get("variations", [])
+
+        if not variations:
+            missing_count += 1
+            continue
+
+        var_data = variations[0].get("item_variation_data", {})
+        if not var_data.get("upc"):
+            missing_count += 1
+
+    return missing_count
+
+
+async def get_missing_images() -> int:
+    """
+    Count items without images.
+
+    Returns:
+        int: Number of items missing images
+    """
+    result = await client.catalog.search(
+        object_types=["ITEM"],
+        query={
+            "exact_query": {
+                "attribute_name": "category_id",
+                "attribute_value": LEGO_CAT_ID,
+            }
+        },
+    )
+
+    result_json = json.loads(result.model_dump_json())
+    objects = result_json.get("objects", [])
+
+    missing_count = 0
+
+    for obj in objects:
+        item_data = obj.get("item_data", {})
+        if not item_data.get("image_ids"):
+            missing_count += 1
+
+    return missing_count
+
+
+async def get_total_catalog_value() -> float:
+    """
+    Calculate total dollar value of all items in LEGO category.
+
+    Returns:
+        float: Total catalog value in dollars
+    """
+    result = await client.catalog.search(
+        object_types=["ITEM"],
+        query={
+            "exact_query": {
+                "attribute_name": "category_id",
+                "attribute_value": LEGO_CAT_ID,
+            }
+        },
+    )
+
+    result_json = json.loads(result.model_dump_json())
+    objects = result_json.get("objects", [])
+
+    total_value = 0.0
+
+    for obj in objects:
+        item_data = obj.get("item_data", {})
+        variations = item_data.get("variations", [])
+
+        if variations:
+            var_data = variations[0].get("item_variation_data", {})
+            price_money = var_data.get("price_money", {})
+
+            if price_money and price_money.get("amount"):
+                # Price is stored in cents, convert to dollars
+                total_value += price_money["amount"] / 100.0
+
+    return round(total_value, 2)
+
+
+# Example usage
+if __name__ == "__main__":
+    import asyncio
+
+    async def main():
+        print("Gathering daily statistics for LEGO catalog...")
+
+        stats = await get_daily_stats()
+
+        print(f"\n=== Daily Stats ===")
+        print(f"Total Items:          {stats['total_items']}")
+        print(f"Enriched Items:       {stats['enriched_items']}")
+        print(f"Missing UPCs:         {stats['missing_upcs']}")
+        print(f"Missing Images:       {stats['missing_images']}")
+        print(f"Total Catalog Value:  ${stats['total_catalog_value']:,.2f}")
+        print(
+            f"Completion Rate:      {(stats['enriched_items'] / stats['total_items'] * 100):.1f}%"
+        )
+
+    asyncio.run(main())

src/throttler.py

@@ -1,19 +1,24 @@
 import asyncio
 from asyncio_throttle import Throttler as AsyncThrottler
 
+
 class GlobalThrottler:
     _instance = None
     _lock = asyncio.Lock()
 
     def __init__(self, rate_limit: int = 500, period: int = 60) -> None:
-        if not hasattr(self, '_initialized'):
+        if not hasattr(self, "_initialized"):
             self.rate_limit = rate_limit
             self.period = period
-            self.throttler = AsyncThrottler(rate_limit=self.rate_limit, period=self.period)
+            self.throttler = AsyncThrottler(
+                rate_limit=self.rate_limit, period=self.period
+            )
             self._initialized = True
 
     @classmethod
-    async def get_instance(cls, rate_limit: int = 500, period: int = 60) -> 'GlobalThrottler':
+    async def get_instance(
+        cls, rate_limit: int = 500, period: int = 60
+    ) -> "GlobalThrottler":
         async with cls._lock:
             if not cls._instance:
                 cls._instance = cls(rate_limit, period)
@@ -22,12 +27,11 @@ class GlobalThrottler:
     async def acquire(self):
         await self.throttler.acquire()
 
-    def release(self):
-        self.throttler.release()
-    
     async def __aenter__(self):
         await self.acquire()
         return self
 
     async def __aexit__(self, exc_type, exc_val, exc_tb):
-        self.release()
+        # asyncio_throttle.Throttler doesn't have a release() method
+        # It automatically manages rate limiting via acquire()
+        pass

studspider.py

@@ -1,14 +1,372 @@
-import src.test_server
+import os
+import json
+import asyncio
+from typing import Dict, Any
+from fastapi import FastAPI, Request, Response, status
+from fastapi.responses import JSONResponse
+import src.get_sq_env as sq_env
+import src.stats as stats
+
+# Square webhook validation
+from square.utils.webhooks_helper import verify_signature
+
+# Configuration
+SQUARE_WEBHOOK_SIGNATURE_KEY = sq_env.SQUARE_WEBHOOK_SIGNATURE_KEY
+SQUARE_WEBHOOK_URL = sq_env.SQUARE_WEBHOOK_URL
+SQUARE_LEGO_CAT_ID = sq_env.LEGO_CAT_ID
+
+# In-memory store for processed event IDs (idempotency)
+processed_event_ids = set()
+MAX_STORED_EVENT_IDS = 10000
+
+# Create FastAPI app
+app = FastAPI(title="Studspider")
 
 
-class Studspider:
-    def __init__(self):
-        self.name = "Studspider"
-        self.version = "0.0.1"
-        self.description = """
-        studspider is an application designed to interact with the Brickset API and directly with Square.
-        It allows users to search for items, manage collections, and perform various operations related to bricksets.
+@app.get("/")
+async def root():
+    """Landing page"""
+    return {
+        "service": "Studspider",
+        "status": "running",
+        "endpoints": {
+            "webhook": "/hook (POST)",
+            "health": "/health (GET)",
+            "stats": "/stats (GET)",
+        },
+    }
+
+
+@app.get("/health")
+async def health_check():
+    """Health check endpoint for monitoring"""
+    return {
+        "status": "healthy",
+        "signature_verification": (
+            "enabled" if SQUARE_WEBHOOK_SIGNATURE_KEY else "disabled"
+        ),
+    }
+
+
+@app.get("/stats")
+async def get_stats():
+    """
+    Get daily statistics for LEGO inventory.
+
+    Returns metrics about enrichment progress, missing data, catalog value, and cache stats.
+    """
+    try:
+        daily_stats = await stats.get_daily_stats()
+        cache_stats = await stats.get_brickset_cache_stats()
+
+        # Calculate completion percentage
+        if daily_stats["total_items"] > 0:
+            completion_rate = (
+                daily_stats["enriched_items"] / daily_stats["total_items"] * 100
+            )
+        else:
+            completion_rate = 0.0
+
+        return {
+            "status": "success",
+            "version": "0.3.0",
+            "git_commit": stats.get_git_commit(),
+            "stats": daily_stats,
+            "completion_rate": round(completion_rate, 1),
+            "brickset_cache": cache_stats,
+        }
+    except Exception as e:
+        return JSONResponse(
+            status_code=500,
+            content={"status": "error", "message": str(e)},
+        )
+
+
+@app.post("/hook")
+async def webhook_handler(request: Request):
+    """
+    Handle Square webhook events - MUST respond within 2 seconds!
+
+    Square sends POST requests with:
+    - x-square-hmacsha256-signature header
+    - JSON body with event data
+    - event_id for idempotency
     """
 
-    def run(self):
-        print(f"{self.name} v{self.version} is running.")
+    try:
+        # Log incoming request
+        print(f"\n[WEBHOOK] Incoming request from {request.client.host}")
+        print(f"[WEBHOOK] Method: {request.method}")
+        print(f"[WEBHOOK] URL: {request.url}")
+        print(f"[WEBHOOK] Headers: {dict(request.headers)}")
+
+        # Read raw body for signature verification
+        body = await request.body()
+        body_str = body.decode("utf-8")
+        print(f"[WEBHOOK] Body length: {len(body_str)} bytes")
+
+        # Get signature header
+        signature_header = request.headers.get("x-square-hmacsha256-signature", "")
+
+        # Verify Square webhook signature (if configured)
+        if SQUARE_WEBHOOK_SIGNATURE_KEY and SQUARE_WEBHOOK_URL:
+            if not signature_header:
+                print(
+                    f"[ERROR] Missing x-square-hmacsha256-signature header from {request.client.host}"
+                )
+                return JSONResponse(
+                    status_code=status.HTTP_401_UNAUTHORIZED,
+                    content={"error": "Missing signature header"},
+                )
+
+            # Debug signature verification inputs
+            print(f"[DEBUG] Signature header: {signature_header[:20]}...")
+            print(
+                f"[DEBUG] Signature key (first 10 chars): {SQUARE_WEBHOOK_SIGNATURE_KEY[:10]}..."
+            )
+            print(f"[DEBUG] Notification URL: {SQUARE_WEBHOOK_URL}")
+            print(f"[DEBUG] Body (first 100 chars): {body_str[:100]}...")
+
+            try:
+                is_valid = verify_signature(
+                    request_body=body_str,
+                    signature_header=signature_header,
+                    signature_key=SQUARE_WEBHOOK_SIGNATURE_KEY,
+                    notification_url=SQUARE_WEBHOOK_URL,
+                )
+
+                if not is_valid:
+                    print(
+                        f"[ERROR] Invalid webhook signature from {request.client.host}"
+                    )
+                    print(f"[ERROR] This usually means:")
+                    print(
+                        f"[ERROR]   1. SQUARE_WEBHOOK_URL doesn't match Square Dashboard exactly"
+                    )
+                    print(f"[ERROR]   2. SQUARE_WEBHOOK_SIGNATURE_KEY is incorrect")
+                    print(f"[ERROR]   3. Request body was modified in transit")
+                    return JSONResponse(
+                        status_code=status.HTTP_401_UNAUTHORIZED,
+                        content={"error": "Invalid signature"},
+                    )
+
+                print(f"[INFO] ✓ Webhook signature verified from {request.client.host}")
+            except Exception as e:
+                print(f"[ERROR] Signature verification exception: {e}")
+                return JSONResponse(
+                    status_code=status.HTTP_401_UNAUTHORIZED,
+                    content={"error": f"Signature verification failed: {str(e)}"},
+                )
+        else:
+            print(
+                f"[WARN] Webhook signature verification DISABLED - configure SQUARE_WEBHOOK_SIGNATURE_KEY"
+            )
+
+        # Parse JSON data
+        try:
+            data = json.loads(body_str)
+        except json.JSONDecodeError as e:
+            print(f"[ERROR] Invalid JSON from {request.client.host}: {e}")
+            return JSONResponse(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                content={"error": "Invalid JSON"},
+            )
+
+        # Check idempotency (event_id)
+        event_id = data.get("event_id")
+        if event_id:
+            if event_id in processed_event_ids:
+                print(
+                    f"[INFO] Duplicate event {event_id} - already processed (idempotency)"
+                )
+                return JSONResponse(
+                    status_code=status.HTTP_200_OK,
+                    content={
+                        "status": "success",
+                        "message": "Event already processed",
+                        "event_id": event_id,
+                    },
+                )
+
+            # Add to processed set
+            processed_event_ids.add(event_id)
+
+            # Prevent memory growth
+            if len(processed_event_ids) > MAX_STORED_EVENT_IDS:
+                processed_event_ids.pop()
+
+        # Get event info for quick response
+        webhook_type = data.get("type", "unknown")
+        event_id_val = data.get("event_id", "none")
+        merchant_id = data.get("merchant_id", "unknown")
+
+        # RESPOND IMMEDIATELY - Square requires fast response (< 2 seconds)
+        response_data = {
+            "status": "success",
+            "message": "Webhook received",
+            "event_id": event_id_val,
+        }
+
+        # Process webhook in background (async task)
+        asyncio.create_task(
+            process_webhook(
+                webhook_type, event_id_val, merchant_id, data, request.client.host
+            )
+        )
+
+        # Return immediate response
+        print(f"[INFO] 200 OK response sent for event {event_id_val}")
+        return JSONResponse(status_code=status.HTTP_200_OK, content=response_data)
+
+    except Exception as e:
+        # Catch-all for any unexpected errors - still respond quickly
+        print(f"[ERROR] Unexpected error in webhook handler: {e}")
+        import traceback
+
+        traceback.print_exc()
+        return JSONResponse(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            content={"error": "Internal server error"},
+        )
+
+    # Return immediate response
+    return JSONResponse(status_code=status.HTTP_200_OK, content=response_data)
+
+
+async def process_webhook(
+    webhook_type: str,
+    event_id: str,
+    merchant_id: str,
+    data: Dict[str, Any],
+    client_ip: str,
+):
+    """
+    Process webhook data asynchronously after responding to Square
+
+    This runs in the background and doesn't block the HTTP response
+    """
+    try:
+        print("\n" + "=" * 60)
+        print(f"[WEBHOOK] Received at {asyncio.get_event_loop().time()}")
+        print(f"[WEBHOOK] From: {client_ip}")
+        print(f"[WEBHOOK] Type: {webhook_type}")
+        print(f"[WEBHOOK] Event ID: {event_id}")
+        print(f"[WEBHOOK] Merchant: {merchant_id}")
+        print(f"[WEBHOOK] Full payload:")
+        print(json.dumps(data, indent=2))
+        print("=" * 60 + "\n")
+
+        # Process based on webhook type
+        if webhook_type == "inventory.count.updated":
+            print(f"[PROCESS] Processing inventory count update...")
+            inventory_counts = (
+                data.get("data", {}).get("object", {}).get("inventory_counts", [])
+            )
+
+            # Import here to avoid circular imports
+            import src.asquare as asquare
+            import src.glue as glue
+
+            for count in inventory_counts:
+                variation_id = count.get("catalog_object_id")
+                quantity = count.get("quantity")
+                state = count.get("state")
+                print(
+                    f"[PROCESS]   Catalog: {variation_id}, Qty: {quantity}, State: {state}"
+                )
+
+                try:
+                    # Get parent item from variation ID
+                    item = await asquare.get_item_by_variation_id(variation_id)
+                    item_id = item.get("id")
+                    item_name = item.get("name", "")
+                    category_id = item.get("category_id")
+
+                    print(f"[PROCESS]   Item: {item_id} - {item_name}")
+                    print(f"[PROCESS]   Category: {category_id}")
+
+                    # Only process LEGO category items
+                    if category_id == SQUARE_LEGO_CAT_ID:
+                        print(
+                            f"[PROCESS]   ✓ LEGO item detected - triggering enrichment"
+                        )
+                        # Trigger enrichment in background with item data to avoid redundant lookup
+                        asyncio.create_task(
+                            glue.enrich_single_item(item_id, item_data=item)
+                        )
+                    else:
+                        print(f"[PROCESS]   ✗ Not a LEGO item - skipping enrichment")
+
+                except Exception as e:
+                    print(f"[ERROR] Failed to process variation {variation_id}: {e}")
+
+        elif webhook_type == "catalog.version.updated":
+            print(f"[PROCESS] Processing catalog version update...")
+
+            # Import here to avoid circular imports
+            import src.asquare as asquare
+            import src.glue as glue
+
+            catalog_object = data.get("data", {}).get("object", {})
+            object_type = catalog_object.get("type")
+
+            if object_type == "ITEM":
+                item_id = catalog_object.get("id")
+                print(f"[PROCESS]   Item updated: {item_id}")
+
+                try:
+                    # Get item details to check category
+                    item = await asquare.get_item_by_id(item_id)
+                    item_name = item.get("name", "")
+                    category_id = item.get("category_id")
+
+                    print(f"[PROCESS]   Item: {item_id} - {item_name}")
+                    print(f"[PROCESS]   Category: {category_id}")
+
+                    # Only process LEGO category items
+                    if category_id == SQUARE_LEGO_CAT_ID:
+                        print(
+                            f"[PROCESS]   ✓ LEGO item detected - triggering enrichment"
+                        )
+                        # Trigger enrichment in background with item data to avoid redundant lookup
+                        asyncio.create_task(
+                            glue.enrich_single_item(item_id, item_data=item)
+                        )
+                    else:
+                        print(f"[PROCESS]   ✗ Not a LEGO item - skipping enrichment")
+
+                except Exception as e:
+                    print(f"[ERROR] Failed to process item {item_id}: {e}")
+            else:
+                print(f"[PROCESS]   Object type '{object_type}' - skipping")
+
+        else:
+            print(f"[PROCESS] Webhook type '{webhook_type}' - no handler configured")
+
+        print(f"[PROCESS] ✓ Webhook processing complete for {event_id}")
+
+    except Exception as e:
+        print(f"[ERROR] Failed to process webhook {event_id}: {e}")
+        import traceback
+
+        traceback.print_exc()
+
+
+if __name__ == "__main__":
+    # For development/testing - use uvicorn directly
+    import uvicorn
+
+    print("\n" + "=" * 60)
+    print("Studspider webhook boot dev")
+    print("=" * 60)
+    print(
+        f"Signature verification: {'ENABLED' if SQUARE_WEBHOOK_SIGNATURE_KEY else 'DISABLED'}"
+    )
+    print(f"Webhook URL: {SQUARE_WEBHOOK_URL or 'NOT CONFIGURED'}")
+    print("\nFor production, use Gunicorn:")
+    print(
+        "  gunicorn conf/studspider:app -w 4 -k uvicorn.workers.UvicornWorker --bind 0.0.0.0:7433"
+    )
+    print("=" * 60 + "\n")
+
+    uvicorn.run(app, host="0.0.0.0", port=7433, log_level="info")

tests/test.py

@@ -1,6 +1,6 @@
 import src.libsquare as sq
 import src.bricksetapi as lego
 
-oursq = sq.get_itm("71417")
-ourlego = lego.get_set(71417)
+oursq = sq.get_itm("10291")
+ourlego = lego.get_set(10291)
 print(f"{oursq}\n\n{ourlego}\n\n")

tests/test_server.py

@@ -15,9 +15,6 @@ import logging
 from logging.handlers import RotatingFileHandler
 from pathlib import Path
 
-print("Creating log directory if it doesn't exist...")
-os.makedirs("./logs/", exist_ok=True)
-
 import banner
 import get_sq_env
 from time import time
@@ -25,12 +22,17 @@ from time import time
 time = int(time())
 import asquare as sq
 
+# Square SDK webhook validation
+from square.utils.webhooks_helper import verify_signature
+
 # from asquareclass import AsyncSquareClient  # type: ignore
 from abricksetapi import AsyncBricksetAPI
 
 print("Loading environment variables...")
 dotenv.load_dotenv()
 SQUARE_LEGO_CAT_ID = os.environ.get("SQUARE_LEGO_CAT_ID")
+SQUARE_WEBHOOK_SIGNATURE_KEY = os.environ.get("SQUARE_WEBHOOK_SIGNATURE_KEY")
+SQUARE_WEBHOOK_URL = os.environ.get("SQUARE_WEBHOOK_URL")
 
 from asyncio_throttle.throttler import Throttler
 
@@ -52,29 +54,15 @@ UA = re.compile(r"^kopling\/?", re.IGNORECASE)
 
 
 async def run_update():
-    set_list = await sq.acat2id(SQUARE_LEGO_CAT_ID)  # type: ignore
-    # print(f"[@DEBUG]\t {set_list}")  # type: ignore
-    for l_set in set_list:
-        # print(f"[@DEBUG]{l_set}")
-        try:
-            l_setinfo = await lego.throttled_get_set(l_set["number"])
-            print(f"[@DEBUG] Found {l_setinfo["pw_name"]}")
-        except Exception as e:
-            print(f"Error fetching set\t: {l_set}: {str(e)}")
-            continue
+    """
+    DEPRECATED: Use glue.enrich_bulk() instead
 
-        # print(f"[@DEBUG]{l_setinfo}")
-        # await sq.update_itm(l_set, l_setinfo)
-    """for l_set in set_list:
-        print(f"[@DEBUG]{l_set}")
-        try:
-            l_setinfo = await lego.throttled_get_set(l_set["number"])
-        except Exception as e:
-            print(f"Error fetching set\t: {l_set}: {str(e)}")
-            continue
+    Legacy RUNUPDATE command handler - kept for backwards compatibility
+    but now delegates to the new glue.enrich_bulk() function
+    """
+    from src import glue
 
-        print(f"[@DEBUG]{l_setinfo}")"""
-    #    await sq.update_itm(l_set, l_setinfo)
+    await glue.enrich_bulk()
 
 
 def valid_uuid(val):
@@ -85,6 +73,11 @@ def valid_uuid(val):
         return False
 
 
+# In-memory store for processed event IDs (idempotency)
+processed_event_ids = set()
+MAX_STORED_EVENT_IDS = 10000  # Prevent memory growth
+
+
 async def hook_handler(request: web.Request) -> web.Response:
     """Handle incoming JSON webhook POSTs on /hook endpoint"""
     try:
@@ -98,21 +91,94 @@ async def hook_handler(request: web.Request) -> web.Response:
             )
             return web.Response(status=405, text="Method not allowed. Use POST.")
 
-        # Get JSON data from request
+        # Read raw body for signature verification
+        body = await request.read()
+        body_str = body.decode("utf-8")
+
+        # Verify Square webhook signature using Square SDK
+        signature_header = request.headers.get("x-square-hmacsha256-signature", "")
+
+        if SQUARE_WEBHOOK_SIGNATURE_KEY and SQUARE_WEBHOOK_URL:
+            if not signature_header:
+                logger.error(
+                    f"{current_time}\tMissing signature header from {request.remote}"
+                )
+                print(f"[@DEBUG] Missing x-square-hmacsha256-signature header")
+                return web.Response(status=401, text="Unauthorized: Missing signature")
+
+            # Use Square SDK's official validation function
+            is_valid = verify_signature(
+                request_body=body_str,
+                signature_header=signature_header,
+                signature_key=SQUARE_WEBHOOK_SIGNATURE_KEY,
+                notification_url=SQUARE_WEBHOOK_URL,
+            )
+
+            if not is_valid:
+                logger.error(f"{current_time}\tInvalid signature from {request.remote}")
+                print(f"[@DEBUG] Invalid webhook signature!")
+                return web.Response(status=401, text="Unauthorized: Invalid signature")
+
+            print(f"[@DEBUG] ✓ Webhook signature verified")
+        else:
+            print(
+                f"[@DEBUG] ⚠️  Webhook signature verification DISABLED (set SQUARE_WEBHOOK_SIGNATURE_KEY and SQUARE_WEBHOOK_URL in .env)"
+            )
+
+        # Parse JSON data
         try:
-            data = await request.json()
+            data = json.loads(body_str)
         except json.JSONDecodeError as e:
             print(f"[@DEBUG] Invalid JSON to /hook from {request.remote}: {str(e)}")
             logger.error(f"Invalid JSON to /hook from {request.remote}: {str(e)}")
             return web.Response(status=400, text="Invalid JSON in request body")
 
+        # Check for idempotency (event_id)
+        event_id = data.get("event_id")
+        if event_id:
+            if event_id in processed_event_ids:
+                print(
+                    f"[@DEBUG] Duplicate event {event_id} - already processed (idempotency)"
+                )
+                logger.info(
+                    f"{current_time}\tDuplicate event {event_id} from {request.remote}"
+                )
+                return web.json_response(
+                    {
+                        "status": "success",
+                        "message": "Event already processed (idempotency)",
+                        "event_id": event_id,
+                    }
+                )
+
+            # Add to processed set
+            processed_event_ids.add(event_id)
+
+            # Prevent memory growth - remove oldest if too many
+            if len(processed_event_ids) > MAX_STORED_EVENT_IDS:
+                processed_event_ids.pop()
+
+        # Get event info for quick response
+        webhook_type = data.get("type", "unknown")
+        event_id_val = data.get("event_id", "none")
+
+        # RESPOND IMMEDIATELY - Square requires fast response (< 2 seconds)
+        # Don't do any processing before responding!
+        response_data = {
+            "status": "success",
+            "message": "Webhook received",
+            "event_id": event_id_val,
+        }
+
+        # Log and process AFTER sending response (async background tasks)
+        async def log_and_process():
             # Log the received webhook with detailed output
             print(f"\n{'='*60}")
             print(f"[@DEBUG] WEBHOOK RECEIVED at {current_time}")
             print(f"[@DEBUG] From: {request.remote}")
             print(f"[@DEBUG] Headers: {dict(request.headers)}")
-        print(f"[@DEBUG] Data type: {data.get('type', 'unknown')}")
-        print(f"[@DEBUG] Event ID: {data.get('event_id', 'none')}")
+            print(f"[@DEBUG] Data type: {webhook_type}")
+            print(f"[@DEBUG] Event ID: {event_id_val}")
             print(f"[@DEBUG] Full payload:")
             print(json.dumps(data, indent=2))
             print(f"{'='*60}\n")
@@ -121,10 +187,7 @@ async def hook_handler(request: web.Request) -> web.Response:
                 f"{current_time}\tWebhook received from {request.remote}: {json.dumps(data)}"
             )
 
-        # Process the webhook data here
-        # TODO: Add your webhook processing logic
-        webhook_type = data.get("type", "unknown")
-
+            # Process the webhook data
             if webhook_type == "inventory.count.updated":
                 print(f"[@DEBUG] Processing inventory count update...")
                 # Extract inventory data
@@ -132,18 +195,16 @@ async def hook_handler(request: web.Request) -> web.Response:
                     data.get("data", {}).get("object", {}).get("inventory_counts", [])
                 )
                 for count in inventory_counts:
-                print(f"[@DEBUG]   Catalog Object: {count.get('catalog_object_id')}")
+                    print(
+                        f"[@DEBUG]   Catalog Object: {count.get('catalog_object_id')}"
+                    )
                     print(f"[@DEBUG]   Quantity: {count.get('quantity')}")
                     print(f"[@DEBUG]   State: {count.get('state')}")
 
-        response_data = {
-            "status": "success",
-            "message": f"Webhook received: {webhook_type}",
-            "timestamp": current_time,
-            "event_id": data.get("event_id"),
-            "data_received": data,
-        }
+        # Start background processing (don't wait for it)
+        asyncio.create_task(log_and_process())
 
+        # Return response immediately
         return web.json_response(response_data)
 
     except json.JSONDecodeError as e:
@@ -225,44 +286,75 @@ app = web.Application()
 app.router.add_post("/api", request_handler)
 app.router.add_post("/hook", hook_handler)
 
-parser = argparse.ArgumentParser(description="studspider")
+parser = argparse.ArgumentParser(
+    description="studspider - LEGO Inventory Sync Service for Square POS and Brickset",
+    epilog="""
+Examples:
+  # Basic HTTP server (recommended with nginx reverse proxy)
+  python src/test_server.py --host 0.0.0.0 --port 7432
+
+  # With separate webhook port
+  python src/test_server.py --port 7432 --hook-port 8080
+
+  # HTTPS using certificates from .env (set SSL_CERT_PATH and SSL_KEY_PATH)
+  python src/test_server.py --hook-port 8443 --hook-ssl-only
+
+  # HTTPS with command line override (self-signed cert for testing)
+  python src/test_server.py --ssl-cert cert.pem --ssl-key key.pem --hook-port 8443 --hook-ssl-only
+
+  # Full HTTPS (both endpoints)
+  python src/test_server.py --ssl-cert cert.pem --ssl-key key.pem --hook-port 8443
+
+  # Production behind nginx (no SSL needed in app)
+  python src/test_server.py --host 127.0.0.1 --port 7432
+
+Environment Variables (.env):
+  SSL_CERT_PATH       - Default SSL certificate path
+  SSL_KEY_PATH        - Default SSL key path
+
+For more information, see doc/ 
+    """,
+    formatter_class=argparse.RawDescriptionHelpFormatter,
+)
 parser.add_argument(
     "--host",
     type=str,
     default="localhost",
-    help="IP address to listen on. default: localhost",
+    help="IP address to listen on (default: localhost, use 0.0.0.0 for all interfaces)",
 )
 parser.add_argument(
-    "--port", type=int, default=7432, help="Port to listen on. default: 7432"
+    "--port", type=int, default=7432, help="Port for main API endpoint (default: 7432)"
 )
 parser.add_argument(
     "--hook-port",
     type=int,
-    default=8080,
-    help="Optional separate port for webhook endpoint. default: 8080",
+    default=None,
+    help="Separate port for webhook endpoint (default: None - uses same port as --port)",
 )
 parser.add_argument(
     "--ssl-cert",
     type=str,
-    default=None,
-    help="Path to SSL certificate file for HTTPS (PEM format)",
+    default=get_sq_env.SSL_CERT_PATH,
+    help="Path to SSL certificate file in PEM format (default: from .env SSL_CERT_PATH)",
 )
 parser.add_argument(
     "--ssl-key",
     type=str,
-    default=None,
-    help="Path to SSL private key file for HTTPS (PEM format)",
+    default=get_sq_env.SSL_KEY_PATH,
+    help="Path to SSL private key file in PEM format (default: from .env SSL_KEY_PATH)",
 )
 parser.add_argument(
     "--hook-ssl-only",
     action="store_true",
-    help="Enable HTTPS only for webhook endpoint (main server stays HTTP)",
+    help="Enable HTTPS only for webhook endpoint, main API stays HTTP (requires --ssl-cert and --ssl-key)",
 )
 args = parser.parse_args()
 
 if __name__ == "__main__":
+    print("Creating log directory if it doesn't exist...")
+    os.makedirs("./logs/", exist_ok=True)
     print(banner.generate("studspider v0.1"))
-    print("Built for PLAY-WELL TEKNOLOGIES by contact@traps.moe\n\n")
+    print("Built for PLAY-WELL TEKNOLOGIES by contact@studspider.sh\n\n")
 
     # Setup SSL context if certificates provided
     ssl_context = None
@@ -294,7 +386,6 @@ if __name__ == "__main__":
         except ssl.SSLError as e:
             print(f"ERROR: Invalid certificate or key file: {e}")
             print("\nMake sure you're using PEM format files.")
-            print("Generate certificates with: python generate_cert.py")
             exit(1)
     elif args.ssl_cert or args.ssl_key:
         print("ERROR: Both --ssl-cert and --ssl-key must be provided together")

tests/test_square_webhook.py

@@ -0,0 +1,51 @@
+"""
+Simple test script to verify Square webhook signature verification works correctly.
+
+This uses the same test data from Square's documentation to ensure our implementation
+matches their expected behavior.
+"""
+
+import sys
+
+sys.path.insert(0, "src")
+
+from square.utils.webhooks_helper import verify_signature
+
+# Test data from Square's documentation
+TEST_BODY = '{"hello":"world"}'
+TEST_SIGNATURE = "2kRE5qRU2tR+tBGlDwMEw2avJ7QM4ikPYD/PJ3bd9Og="
+TEST_SIGNATURE_KEY = "asdf1234"
+TEST_NOTIFICATION_URL = "https://example.com/webhook"
+
+
+def test_signature_validation():
+    """Test that signature validation works with Square SDK"""
+
+    print("Testing Square webhook signature validation...")
+    print(f"Body: {TEST_BODY}")
+    print(f"Signature: {TEST_SIGNATURE}")
+    print(f"Key: {TEST_SIGNATURE_KEY}")
+    print(f"URL: {TEST_NOTIFICATION_URL}")
+    print()
+
+    # This should return True with Square's test data
+    is_valid = verify_signature(
+        request_body=TEST_BODY,
+        signature_header=TEST_SIGNATURE,
+        signature_key=TEST_SIGNATURE_KEY,
+        notification_url=TEST_NOTIFICATION_URL,
+    )
+
+    if is_valid:
+        print("✅ SUCCESS: Signature validation passed!")
+        print("The webhook implementation is using Square SDK correctly.")
+        return True
+    else:
+        print("❌ FAILURE: Signature validation failed!")
+        print("Something is wrong with the signature verification.")
+        return False
+
+
+if __name__ == "__main__":
+    success = test_signature_validation()
+    sys.exit(0 if success else 1)

uv.lock

@@ -92,6 +92,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/4d/3f/3bc3f1d83f6e4a7fcb834d3720544ca597590425be5ba9db032b2bf322a2/altgraph-0.17.4-py2.py3-none-any.whl", hash = "sha256:642743b4750de17e655e6711601b077bc6598dbfa3ba5fa2b2a35ce12b508dff", size = 21212, upload-time = "2023-09-25T09:04:50.691Z" },
 ]
 
+[[package]]
+name = "annotated-doc"
+version = "0.0.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/57/ba/046ceea27344560984e26a590f90bc7f4a75b06701f653222458922b558c/annotated_doc-0.0.4.tar.gz", hash = "sha256:fbcda96e87e9c92ad167c2e53839e57503ecfda18804ea28102353485033faa4", size = 7288, upload-time = "2025-11-10T22:07:42.062Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1e/d3/26bf1008eb3d2daa8ef4cacc7f3bfdc11818d111f7e2d0201bc6e3b49d45/annotated_doc-0.0.4-py3-none-any.whl", hash = "sha256:571ac1dc6991c450b25a9c2d84a3705e2ae7a53467b5d111c24fa8baabbed320", size = 5303, upload-time = "2025-11-10T22:07:40.673Z" },
+]
+
 [[package]]
 name = "annotated-types"
 version = "0.7.0"
@@ -239,6 +248,21 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b2/b7/545d2c10c1fc15e48653c91efde329a790f2eecfbbf2bd16003b5db2bab0/dotenv-0.9.9-py2.py3-none-any.whl", hash = "sha256:29cf74a087b31dafdb5a446b6d7e11cbce8ed2741540e2339c69fbef92c94ce9", size = 1892, upload-time = "2025-02-19T22:15:01.647Z" },
 ]
 
+[[package]]
+name = "fastapi"
+version = "0.128.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "annotated-doc" },
+    { name = "pydantic" },
+    { name = "starlette" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/52/08/8c8508db6c7b9aae8f7175046af41baad690771c9bcde676419965e338c7/fastapi-0.128.0.tar.gz", hash = "sha256:1cc179e1cef10a6be60ffe429f79b829dce99d8de32d7acb7e6c8dfdf7f2645a", size = 365682, upload-time = "2025-12-27T15:21:13.714Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5c/05/5cbb59154b093548acd0f4c7c474a118eda06da25aa75c616b72d8fcd92a/fastapi-0.128.0-py3-none-any.whl", hash = "sha256:aebd93f9716ee3b4f4fcfe13ffb7cf308d99c9f3ab5622d8877441072561582d", size = 103094, upload-time = "2025-12-27T15:21:12.154Z" },
+]
+
 [[package]]
 name = "frozenlist"
 version = "1.7.0"
@@ -330,9 +354,23 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/ee/43/3cecdc0349359e1a527cbf2e3e28e5f8f06d3343aaf82ca13437a9aa290f/greenlet-3.2.4-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:23768528f2911bcd7e475210822ffb5254ed10d71f4028387e5a99b4c6699671", size = 610497, upload-time = "2025-08-07T13:18:31.636Z" },
     { url = "https://files.pythonhosted.org/packages/b8/19/06b6cf5d604e2c382a6f31cafafd6f33d5dea706f4db7bdab184bad2b21d/greenlet-3.2.4-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:00fadb3fedccc447f517ee0d3fd8fe49eae949e1cd0f6a611818f4f6fb7dc83b", size = 1121662, upload-time = "2025-08-07T13:42:41.117Z" },
     { url = "https://files.pythonhosted.org/packages/a2/15/0d5e4e1a66fab130d98168fe984c509249c833c1a3c16806b90f253ce7b9/greenlet-3.2.4-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:d25c5091190f2dc0eaa3f950252122edbbadbb682aa7b1ef2f8af0f8c0afefae", size = 1149210, upload-time = "2025-08-07T13:18:24.072Z" },
+    { url = "https://files.pythonhosted.org/packages/1c/53/f9c440463b3057485b8594d7a638bed53ba531165ef0ca0e6c364b5cc807/greenlet-3.2.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:6e343822feb58ac4d0a1211bd9399de2b3a04963ddeec21530fc426cc121f19b", size = 1564759, upload-time = "2025-11-04T12:42:19.395Z" },
+    { url = "https://files.pythonhosted.org/packages/47/e4/3bb4240abdd0a8d23f4f88adec746a3099f0d86bfedb623f063b2e3b4df0/greenlet-3.2.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:ca7f6f1f2649b89ce02f6f229d7c19f680a6238af656f61e0115b24857917929", size = 1634288, upload-time = "2025-11-04T12:42:21.174Z" },
     { url = "https://files.pythonhosted.org/packages/0b/55/2321e43595e6801e105fcfdee02b34c0f996eb71e6ddffca6b10b7e1d771/greenlet-3.2.4-cp313-cp313-win_amd64.whl", hash = "sha256:554b03b6e73aaabec3745364d6239e9e012d64c68ccd0b8430c64ccc14939a8b", size = 299685, upload-time = "2025-08-07T13:24:38.824Z" },
 ]
 
+[[package]]
+name = "gunicorn"
+version = "23.0.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "packaging" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/34/72/9614c465dc206155d93eff0ca20d42e1e35afc533971379482de953521a4/gunicorn-23.0.0.tar.gz", hash = "sha256:f014447a0101dc57e294f6c18ca6b40227a4c90e9bdb586042628030cba004ec", size = 375031, upload-time = "2024-08-10T20:25:27.378Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/cb/7d/6dac2a6e1eba33ee43f318edbed4ff29151a49b5d37f080aad1e6469bca4/gunicorn-23.0.0-py3-none-any.whl", hash = "sha256:ec400d38950de4dfd418cff8328b2c8faed0edb0d517d3394e457c317908ca4d", size = 85029, upload-time = "2024-08-10T20:25:24.996Z" },
+]
+
 [[package]]
 name = "h11"
 version = "0.16.0"
@@ -949,11 +987,14 @@ dependencies = [
     { name = "asyncio-throttle" },
     { name = "bs4" },
     { name = "dotenv" },
+    { name = "fastapi" },
+    { name = "gunicorn" },
     { name = "pyinstaller" },
     { name = "pytest" },
     { name = "reflex" },
     { name = "requests" },
     { name = "squareup" },
+    { name = "uvicorn" },
 ]
 
 [package.metadata]
@@ -964,11 +1005,14 @@ requires-dist = [
     { name = "asyncio-throttle", specifier = ">=1.0.2,<2.0.0" },
     { name = "bs4", specifier = ">=0.0.2" },
     { name = "dotenv", specifier = ">=0.9.9,<0.10.0" },
+    { name = "fastapi", specifier = ">=0.128.0" },
+    { name = "gunicorn", specifier = ">=23.0.0" },
     { name = "pyinstaller", specifier = ">=6.14.1,<7.0.0" },
     { name = "pytest", specifier = ">=8.4.2,<9.0.0" },
     { name = "reflex", specifier = ">=0.8.14.post1" },
     { name = "requests", specifier = ">=2.32.4,<3.0.0" },
     { name = "squareup", specifier = ">=43.0.0.20250618,<44.0.0.0" },
+    { name = "uvicorn", specifier = ">=0.40.0" },
 ]
 
 [[package]]
@@ -1022,6 +1066,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a7/c2/fe1e52489ae3122415c51f387e221dd0773709bad6c6cdaa599e8a2c5185/urllib3-2.5.0-py3-none-any.whl", hash = "sha256:e6b01673c0fa6a13e374b50871808eb3bf7046c4b125b216f6bf1cc604cff0dc", size = 129795, upload-time = "2025-06-18T14:07:40.39Z" },
 ]
 
+[[package]]
+name = "uvicorn"
+version = "0.40.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "click" },
+    { name = "h11" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/c3/d1/8f3c683c9561a4e6689dd3b1d345c815f10f86acd044ee1fb9a4dcd0b8c5/uvicorn-0.40.0.tar.gz", hash = "sha256:839676675e87e73694518b5574fd0f24c9d97b46bea16df7b8c05ea1a51071ea", size = 81761, upload-time = "2025-12-21T14:16:22.45Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3d/d8/2083a1daa7439a66f3a48589a57d576aa117726762618f6bb09fe3798796/uvicorn-0.40.0-py3-none-any.whl", hash = "sha256:c6c8f55bc8bf13eb6fa9ff87ad62308bbbc33d0b67f84293151efe87e0d5f2ee", size = 68502, upload-time = "2025-12-21T14:16:21.041Z" },
+]
+
 [[package]]
 name = "watchfiles"
 version = "1.1.1"