feat: Add Chatwoot Agent Bot prototype and FAQ knowledge base

- 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
2026-04-01 16:26:05 -04:00
parent 7ba19752de
commit 5319bcd30b
1074 changed files with 456376 additions and 0 deletions
--- a/memory/2026-03-13-2328.md
+++ b/memory/2026-03-13-2328.md
@@ -0,0 +1,111 @@
+# Session: 2026-03-13 23:28:10 UTC
+
+- **Session Key**: agent:main:telegram:direct:8269921691
+- **Session ID**: fe0e2bf5-1199-4e42-8d11-354e8fc7a3f7
+- **Source**: telegram
+
+## Conversation Summary
+
+assistant:  I see the issue! The process is restarting every ~2.7 minutes even though it should sleep for 10 minutes. Something is killing
+assistant:  83 restarts today! There's definitely a crash. Let me run it directly
+assistant:  The script exits at `sleep 600`. Let me check if there's
+user: System: [2026-03-13 14:36:51 EDT] Exec completed (marine-b, code 0) :: unning after 5 seconds ✅ Process running after 15 seconds (stable) Current log: [2026-03-13 14:36:36] === Sales Prospector Started === [2026-03-13 14:36:36] Throttle: 10min busine…
+System: [2026-03-13 14:38:56 EDT] Exec completed (swift-pi, code 0) :: tro: Orlando FL [2026-03-13 14:09:39] === Sales Prospector Started === [2026-03-13 14:09:39] Metro: Orlando FL [2026-03-13 14:36:36] === Sales Prospector Started === [2026-03-13 1…
+
+Conversation info (untrusted metadata):
+```json
+{
+  "timestamp": "Fri 2026-03-13 14:41 EDT"
+}
+```
+
+go ahead and run it yourself. You are the main orchestrator/manager of all these subagents. you have full system control!
+user: System: [2026-03-13 14:42:23 EDT] Exec completed (tender-l, code 0) :: 4:39:16] === CYCLE 1: Orlando FL === [2026-03-13 14:39:16] SEARCH: Orlando FL HOA board [2026-03-13 14:39:16] THROTTLE: sleeping 600s [2026-03-13 14:41:58] === Sales Prospector St…
+System: [2026-03-13 14:45:23 EDT] Exec completed (neat-bre, code 0) :: === DIRECT TEST (with error capture) === PID: 87016 Waiting 10 seconds... ✅ Still running after 10s
+System: [2026-03-13 14:49:16 EDT] Exec completed (tidal-ot, code 0) :: 4:36:36] === CYCLE 1: Orlando FL === [2026-03-13 14:36:36] SEARCH: Orlando FL HOA board [2026-03-13 14:36:36] THROTTLE: sleeping 600s [2026-03-13 14:39:16] === Sales Prospector St…
+System: [2026-03-13 15:20:44 EDT] Exec failed (briny-cr, code 0) :: ] Sleeping 600s (throttle)... [2026-03-13 15:00:44] Cycle complete [2026-03-13 15:00:44] CYCLE 2: Phoenix AZ [2026-03-13 15:00:44] Searching: Phoenix AZ HOA board [2026-03-13 15:0…
+
+Conversation info (untrusted metadata):
+```json
+{
+  "timestamp": "Fri 2026-03-13 15:25 EDT"
+}
+```
+
+Last message didn’t come through
+assistant:  I'm here. Based on those logs, the prospector IS running now! Let me
+user: Conversation info (untrusted metadata):
+```json
+{
+  "timestamp": "Fri 2026-03-13 18:22 EDT"
+}
+```
+
+Can you give me a status update on the lead prospector? How many new leads created?
+assistant:  **Status Update:**
+
+**Process:** ❌ NOT RUNNING (died around 15:20)
+**Last Activity:** Cycle 3 - Charlotte NC at 15:10
+**Leads Created:** 0 (state shows `leads_found: 0`)
+
+**What happened:**
+- 14:50 - Started, completed 3 successful cycles
+- 15:10 - Started cycle for Charlotte NC, went to sleep for 600s
+- **Process died before waking up** - no log entries after 15:10
+
+**In CRM:** No new notes with 🎯 (prospected leads) found
+assistant:  ✅ **RESTARTED!** Running PID: 97829 **Current Status:** - **Metro:** Charlotte NC - **Throttle:** 300s (5 min - correct for off-hours 6:25 PM) - **Will sleep until:** ~18:30:56 **Next cycle:** Atlanta GA at ~18:31 **Issue:** The script ran for 3 cycles then died. The launcher didn't keep it alive. Looking at logs around 15:10-15:20, there's no error - it just stopped. **Leads count:** Still 0 (no web search results being found/processed)
+
+**Summary:**
+
+| Metric | Value |
+|--------|-------|
+| Process | ✅ Running (PID 97829) |
+| Last Cycle | Charlotte NC at 18:25 |
+| Cycles Today | 3 completed, 1 in progress |
+| Leads Found | 0 |
+| CRM Notes Created | 0 |
+| Issue | Process dies after ~3 cycles |
+
+**Next cycle:** Atlanta GA at ~18:31 Want me to monitor it or add auto-restart logic?
+user: Conversation info (untrusted metadata):
+```json
+{
+  "timestamp": "Fri 2026-03-13 18:29 EDT"
+}
+```
+
+Please do both
+user: Conversation info (untrusted metadata):
+```json
+{
+  "timestamp": "Fri 2026-03-13 18:37 EDT"
+}
+```
+
+Can you add this model as a fallback model using our existing nvidia api key? https://build.nvidia.com/nvidia/nemotron-3-super-120b-a12b/modelcard
+user: Conversation info (untrusted metadata):
+```json
+{
+  "timestamp": "Fri 2026-03-13 19:17 EDT"
+}
+```
+
+Were you able to add that fallback model?
+assistant:  ✅ **Fallback model added!** **NVIDIA provider now includes:** 1. Nemotron 3 Super 120B (NEW) 2. Qwen 3.5 3. Kimi K2.5 All using the same `nvapi-qfgSi0...` API key you already had configured. The model is available immediately for your sessions.
+user: Conversation info (untrusted metadata):
+```json
+{
+  "timestamp": "Fri 2026-03-13 19:22 EDT"
+}
+```
+
+It’s not showing - are you sure it’s added?
+assistant:  ✅ **Confirmed Added!** 
+
+**NVIDIA Models now:**
+1. **Nemotron 3 Super 120B** ← Added
+2. Qwen 3.5  
+3. Kimi K2.5
+
+The model is in the config file. If it's not showing in your interface, you may need to **restart your OpenClaw session** or run `openclaw restart` for it to pick up the new model configuration.