- 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
Proxy was using resp.raw.headers (urllib3) which could miss Content-Type;
switched to resp.headers. SW now skips /pos/api/auth/ to prevent stale
token caching, scopes fetch to /pos/ only, and bumps cache to v2.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>