Commit graph

3 commits

Author SHA1 Message Date
0120c904d7 feat(attendance): Multi-channel attendant config (email, phone, teams, google)
- Add email, teams, google columns to attendant.csv
- Add find_attendant_by_identifier() for multi-channel lookup
- Add find_attendants_by_channel() and find_attendants_by_department()
- Implement handle_status_command with database persistence
- Implement handle_transfer_command with actual transfer logic
- Update AttendantCSV struct with all new fields
2025-12-05 14:54:55 -03:00
5d93505012 feat(attendance): Add LLM-assisted attendant features
- Real-time tips when customer messages arrive
- Message polishing with one click
- Smart reply generation (3 contextual suggestions)
- Auto-summary when attendant takes conversation
- LLM-powered sentiment analysis with escalation warnings

WhatsApp Attendant Commands:
- /queue, /take, /status, /transfer, /resolve
- /tips, /polish, /replies, /summary, /help
- Portuguese versions: /fila, /pegar, /dicas, /polir, /respostas, /resumo

Config options (config.csv):
- attendant-llm-tips
- attendant-polish-message
- attendant-smart-replies
- attendant-auto-summary
- attendant-sentiment-analysis

API Endpoints:
- POST /api/attendance/llm/tips
- POST /api/attendance/llm/polish
- POST /api/attendance/llm/smart-replies
- GET /api/attendance/llm/summary/{session_id}
- POST /api/attendance/llm/sentiment
- GET /api/attendance/llm/config/{bot_id}

Uses bot's system prompt for consistency between bot and human-assisted responses.
2025-12-05 13:47:15 -03:00
53bac1f5ec - Refactor folder as features. 2025-11-22 22:55:35 -03:00