olsch01
5319bcd30b
- Created chatwoot-agent-bot/ with Node.js webhook server - Bot detects intent (greeting, billing, technical, features, account) - Auto-responds from FAQ knowledge base or escalates to human - FAQ-KB.md: Living knowledge base that grows with customer questions - CHATWOOT-SETUP.md: Complete deployment and configuration guide - Supports Telegram notifications on escalation - Bot runs on port 3001, ready for Chatwoot webhook integration
29 lines
744 B
Markdown
29 lines
744 B
Markdown
# Recovery Flow
|
|
|
|
When context gets long, interrupted, or stale, recover before asking the user to repeat work.
|
|
|
|
## Recovery Order
|
|
|
|
1. Read stable proactivity memory
|
|
2. Read session state
|
|
3. Read the working buffer if the task was long or tool-heavy
|
|
4. Reconstruct:
|
|
- current objective
|
|
- last confirmed decision
|
|
- blocker or missing input
|
|
- next useful move
|
|
|
|
## Good Recovery
|
|
|
|
- "Last agreed move was to draft the fix, and the blocker is missing deploy access. I can prepare the patch now."
|
|
|
|
## Bad Recovery
|
|
|
|
- "Can you remind me what we were doing?"
|
|
|
|
## When to Ask the User
|
|
|
|
- a required input is still missing after recovery
|
|
- local state conflicts with a newer instruction
|
|
- the task changed direction and old state is no longer trustworthy
|