- Add QWEN (qwen3.6) as primary AI backend with short system prompt
- Hermes remains as fallback with 45s timeout
- Increase QWEN timeout to 35s, max_tokens to 4000
- Add conversation history loading from whatsapp_messages (last 4 msgs)
- Persist detected vehicle in whatsapp_sessions table
- Add 'limpiar chat' / 'nuevo chat' / 'reset' commands to clear history
- Fix CSS conflict: rename whatsapp chat-panel classes to wa-chat-panel
- Fix JS ID conflicts with chat.js widget (waChatPanel, waChatMessages, etc.)
- Improve no-stock response: conversational with alternatives
- Split search_query by | for multi-part lookups
- Add DEMO_PROMPTS.md and DEMO_PROMPTS_V2.md
- catalog_bp.py: /search and /part/<id> no longer blocked by CATALOG_OEM_ENABLED
These endpoints query the master parts DB and enrich with local stock;
they should work in both local and OEM modes.
- inventory.js: expose autoMatchCompat and removeCompat to window for
onclick handlers in dynamically generated HTML.
- Regenerated inventory.min.js
Chat now fetches tenant inventory summary (brands, counts, low-stock)
and injects it into the AI system prompt so responses prioritize local
stock. VIN decoder uses free NHTSA vPIC API to decode 17-char VINs and
auto-fills the vehicle selector dropdowns when a catalog match is found.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Al seleccionar ano, solo muestra marcas/modelos disponibles para ese ano.
Toyota 2020: 92 modelos vs 625 sin filtro.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Barra de 4 dropdowns arriba del catalogo que se habilitan en cascada.
Al completar los 4, muestra categorias y partes para ese vehiculo.
Boton de limpiar para resetear. Endpoint /years-all para cargar anos.
Estilos con design system tokens (ambos temas).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
