updated ai prompt

AI Prompt.txt

@@ -30,8 +30,9 @@ Long-term goal: evolve into a WMS, but right now focus on making this workflow r
 6) **Verify safety.** Warn me before destructive actions (delete/overwrite/migrations). Offer a safer alternative.
 7) **Evidence-based debugging.** Ask for exact error text/logs and versions before guessing.
 8) **CSS changes:** Ask which device(s) the change is for (desktop/mobile/scanner) before editing. Each has its own file.
-9) **Database changes:** The app auto-initializes the database if it doesn't exist. Schema is in /database/init_db.py.
-10) **Docker deployment:** Production runs in Docker on Linux (jisoo). Volume mounts only /app/database to preserve data between updates.
+9) **Docker deployment:** Production runs in Docker on Linux (PortainerVM). Volume mounts only /app/database to preserve data between updates.
+10) Database changes: Never tell user to "manually run SQL". Always add changes to migrations.py so they auto-apply on deployment.
+
 
 ## How you should respond
 - Start by confirming which mode we’re working on: Cycle Count or Physical Inventory.
@@ -43,10 +44,10 @@ Long-term goal: evolve into a WMS, but right now focus on making this workflow r
 ## Scanlook (current product summary)
 Scanlook is a web app for warehouse counting workflows built with Flask + SQLite.
 
-**Current Version:** 0.12.0
+**Current Version:** 0.13.0
 
 **Tech Stack:**
-- Backend: Python/Flask, raw SQL (no ORM)
+- Backend: Python/Flask, raw SQL (no ORM), openpyxl (Excel file generation)
 - Database: SQLite (located in /database/scanlook.db)
 - Frontend: Jinja2 templates, vanilla JS, custom CSS
 - CSS Architecture: Desktop-first with device-specific overrides
@@ -63,6 +64,7 @@ Scanlook is a web app for warehouse counting workflows built with Flask + SQLite
 - /database/ (scanlook.db, init_db.py)
 - db.py (database helper functions: query_db, execute_db)
 - utils.py (decorators: login_required, role_required)
+- migrations.py (database migration system)
 
 **Key Features (implemented):**
 - Count Sessions with archive/activate functionality
@@ -74,6 +76,8 @@ Scanlook is a web app for warehouse counting workflows built with Flask + SQLite
 - Session isolation (archived sessions blocked from access)
 - Role-based access: owner, admin, staff
 - Auto-initialize database on first run
+- Consumption Sheets module (production lot tracking with Excel export)
+- Database migration system (auto-applies schema changes on startup)
 
 **Two count types:**
 1. Cycle Count: shows Expected list for the BIN
@@ -81,7 +85,7 @@ Scanlook is a web app for warehouse counting workflows built with Flask + SQLite
 
 **Long-term goal:** Modular WMS with future modules for Shipping, Receiving, Transfers, Production.
 
-**Module System (v0.12.0):**
+**Module System (v0.13.0):**
 - Modules table defines available modules (module_key used for routing)
 - UserModules table tracks per-user access
 - Home page (/home) shows module cards based on user's access
@@ -90,6 +94,9 @@ Scanlook is a web app for warehouse counting workflows built with Flask + SQLite
   - __init__.py (blueprint registration)
   - routes.py (all routes)
   - templates/ (module-specific templates)
+- Current modules: 
+  - Inventory Counts (counting)
+  - Consumption Sheets (cons_sheets)
   
 
 ## Quick Reference