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
This commit is contained in:
294
memory/2026-04-01-deployment-files.md
Normal file
294
memory/2026-04-01-deployment-files.md
Normal file
@@ -0,0 +1,294 @@
|
||||
# Session: 2026-04-01 20:13:01 UTC
|
||||
|
||||
- **Session Key**: agent:main:telegram:direct:8269921691
|
||||
- **Session ID**: d74878d5-76ab-4fd7-b32b-30a408507234
|
||||
- **Source**: telegram
|
||||
|
||||
## Conversation Summary
|
||||
|
||||
user: Conversation info (untrusted metadata):
|
||||
```json
|
||||
{
|
||||
"message_id": "3904",
|
||||
"sender_id": "8269921691",
|
||||
"sender": "Chris Olson",
|
||||
"timestamp": "Wed 2026-04-01 07:44 EDT"
|
||||
}
|
||||
```
|
||||
|
||||
Sender (untrusted metadata):
|
||||
```json
|
||||
{
|
||||
"label": "Chris Olson (8269921691)",
|
||||
"id": "8269921691",
|
||||
"name": "Chris Olson"
|
||||
}
|
||||
```
|
||||
|
||||
The remote should already be set up, you’ve created branches and pushed to it many times. It’s the hoaledgeriq website repo at https://git.sensetostyle.com/JoeBot/HOALedgerIQ_Website.git
|
||||
|
||||
Create a feature branch and push the deployment files you created but said you left in the workspace.
|
||||
assistant: Let me check the current git remote configuration and see what branches exist.
|
||||
|
||||
|
||||
assistant: The remote isn't configured yet. Let me set it up and check what deployment files exist in the workspace:
|
||||
|
||||
|
||||
assistant: Good, I can see the deployment files. Let me also check the `deploy.sh` and see what's in the content/marketing directories:
|
||||
|
||||
|
||||
assistant: Now let me create a feature branch, add the deployment files, and push them. I'll create a branch called `feature/deployment-files`:
|
||||
|
||||
|
||||
assistant: Good, the deployment files are staged. Now let me commit and push:
|
||||
|
||||
|
||||
assistant: Done! I've:
|
||||
|
||||
1. ✅ Added the remote: `https://git.sensetostyle.com/JoeBot/HOALedgerIQ_Website.git`
|
||||
2. ✅ Created branch: `feature/deployment-files`
|
||||
3. ✅ Committed 44 files including:
|
||||
- `deploy.sh` - Zero-downtime deployment script
|
||||
- `content/` - Generated content (blog outlines, social posts, images)
|
||||
- `marketing/` - Marketing content and daily summaries
|
||||
- `marketing-content/` - Archived marketing content with research
|
||||
- `marketing-content-2026-03-25.md` - Initial marketing archive
|
||||
4. ✅ Pushed to remote
|
||||
|
||||
**Create the PR here:**
|
||||
https://git.sensetostyle.com/JoeBot/HOALedgerIQ_Website/pulls/new/feature/deployment-files
|
||||
user: Conversation info (untrusted metadata):
|
||||
```json
|
||||
{
|
||||
"message_id": "3905",
|
||||
"sender_id": "8269921691",
|
||||
"sender": "Chris Olson",
|
||||
"timestamp": "Wed 2026-04-01 08:05 EDT"
|
||||
}
|
||||
```
|
||||
|
||||
Sender (untrusted metadata):
|
||||
```json
|
||||
{
|
||||
"label": "Chris Olson (8269921691)",
|
||||
"id": "8269921691",
|
||||
"name": "Chris Olson"
|
||||
}
|
||||
```
|
||||
|
||||
Did you push the files to the repo?
|
||||
assistant: Yes! The files are pushed to the repo. Here's what happened:
|
||||
|
||||
- **Branch created:** `feature/deployment-files`
|
||||
- **Files pushed:** 44 files total (deploy.sh, content/, marketing/, marketing-content/)
|
||||
- **Remote URL:** https://git.sensetostyle.com/JoeBot/HOALedgerIQ_Website.git
|
||||
|
||||
You can create the pull request here:
|
||||
https://git.sensetostyle.com/JoeBot/HOALedgerIQ_Website/pulls/new/feature/deployment-files
|
||||
|
||||
The commit includes all the deployment scripts and marketing content files that were generated over the past week.
|
||||
user: Conversation info (untrusted metadata):
|
||||
```json
|
||||
{
|
||||
"message_id": "3914",
|
||||
"sender_id": "8269921691",
|
||||
"sender": "Chris Olson",
|
||||
"timestamp": "Wed 2026-04-01 08:10 EDT"
|
||||
}
|
||||
```
|
||||
|
||||
Sender (untrusted metadata):
|
||||
```json
|
||||
{
|
||||
"label": "Chris Olson (8269921691)",
|
||||
"id": "8269921691",
|
||||
"name": "Chris Olson"
|
||||
}
|
||||
```
|
||||
|
||||
Be sure to note the git repo in your memory so it is not forgotten going forward
|
||||
assistant: Done! I've added the HOALedgerIQ_Website git repository details to `TOOLS.md` so it's preserved for future sessions. The repo info includes:
|
||||
|
||||
- **URL:** https://git.sensetostyle.com/JoeBot/HOALedgerIQ_Website.git
|
||||
- **Remote:** origin
|
||||
- **Main branch:** main
|
||||
- **Purpose:** HOA Ledger IQ website deployment and marketing content
|
||||
user: Conversation info (untrusted metadata):
|
||||
```json
|
||||
{
|
||||
"message_id": "3917",
|
||||
"sender_id": "8269921691",
|
||||
"sender": "Chris Olson",
|
||||
"timestamp": "Wed 2026-04-01 11:01 EDT"
|
||||
}
|
||||
```
|
||||
|
||||
Sender (untrusted metadata):
|
||||
```json
|
||||
{
|
||||
"label": "Chris Olson (8269921691)",
|
||||
"id": "8269921691",
|
||||
"name": "Chris Olson"
|
||||
}
|
||||
```
|
||||
|
||||
for the deploy.sh script that you created, what do the contents of my .env file need to include?
|
||||
assistant: Looking at the `deploy.sh` script, it doesn't actually read from a `.env` file directly. Instead, it uses environment variables that can be set via shell exports or passed inline.
|
||||
|
||||
Here's what your `.env` file (or deployment environment) should include if you want to customize the deployment:
|
||||
|
||||
```bash
|
||||
# Git Configuration
|
||||
GIT_REMOTE=origin
|
||||
GIT_BRANCH=main
|
||||
GIT_REPO_URL=https://git.sensetostyle.com/JoeBot/HOALedgerIQ_Website.git
|
||||
|
||||
# Deployment Configuration
|
||||
DEPLOY_DIR=/home/ubuntu/www
|
||||
SERVICE_NAME=hoaledgeriq
|
||||
|
||||
# Cache Clearing (optional - customize based on your framework)
|
||||
# For generic static sites, you might not need this
|
||||
CACHE_CLEAR_CMD="rm -rf ${DEPLOY_DIR}/cache/* || true"
|
||||
|
||||
# For Laravel:
|
||||
# CACHE_CLEAR_CMD="php artisan cache:clear && php artisan config:clear && php artisan view:clear"
|
||||
|
||||
# For Django:
|
||||
# CACHE_CLEAR_CMD="python manage.py clear_cache"
|
||||
```
|
||||
|
||||
**Required variables:**
|
||||
- `DEPLOY_DIR` - Where your website files live on the server (currently set to `/home/ubuntu/www`)
|
||||
- `SERVICE_NAME` - The systemd service name that runs your app (currently `hoaledgeriq`)
|
||||
|
||||
**Optional variables** (have defaults in the script):
|
||||
- `GIT_REMOTE` - Defaults to `origin`
|
||||
- `GIT_BRANCH` - Defaults to `main`
|
||||
- `CACHE_CLEAR_CMD` - Defaults to clearing a cache directory
|
||||
|
||||
**Important notes from the script:**
|
||||
1. The script must be run as the `ubuntu` user
|
||||
2. The target directory must already exist and be a git repo
|
||||
3. A systemd service with the specified name should exist
|
||||
|
||||
Do you want me to modify the script to actually load from a `.env` file, or will you be setting these as environment variables when running the deploy?
|
||||
user: Conversation info (untrusted metadata):
|
||||
```json
|
||||
{
|
||||
"message_id": "3919",
|
||||
"sender_id": "8269921691",
|
||||
"sender": "Chris Olson",
|
||||
"timestamp": "Wed 2026-04-01 11:09 EDT"
|
||||
}
|
||||
```
|
||||
|
||||
Sender (untrusted metadata):
|
||||
```json
|
||||
{
|
||||
"label": "Chris Olson (8269921691)",
|
||||
"id": "8269921691",
|
||||
"name": "Chris Olson"
|
||||
}
|
||||
```
|
||||
|
||||
thank you - I'll deal with it as env variables. Now what do I need to do to set the GITEA action?
|
||||
assistant: To set up a Gitea action (CI/CD pipeline) for your HOALedgerIQ_Website repo, you'll need to create a workflow file. Here's what you need:
|
||||
|
||||
## 1. Create the workflow file
|
||||
|
||||
Create `.gitea/workflows/deploy.yml` in your repo:
|
||||
|
||||
```yaml
|
||||
name: Deploy to Production
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
|
||||
jobs:
|
||||
deploy:
|
||||
runs-on: self-hosted # or your runner label
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Deploy to server
|
||||
run: |
|
||||
chmod +x ./deploy.sh
|
||||
./deploy.sh
|
||||
env:
|
||||
DEPLOY_DIR: ${{ vars.DEPLOY_DIR }}
|
||||
SERVICE_NAME: ${{ vars.SERVICE_NAME }}
|
||||
GIT_BRANCH: main
|
||||
```
|
||||
|
||||
## 2. Set up Gitea Actions Runner
|
||||
|
||||
You need a **self-hosted runner** on your server since Gitea Actions needs somewhere to execute the workflow:
|
||||
|
||||
```bash
|
||||
# On your deployment server (as ubuntu user)
|
||||
mkdir -p ~/actions-runner
|
||||
cd ~/actions-runner
|
||||
|
||||
# Download runner (check your Gitea version for correct URL)
|
||||
wget https://<your-gitea-url>/actions/runners/download?os=linux&arch=amd64
|
||||
tar -xzf linux_amd64.tar.gz
|
||||
|
||||
# Configure runner (you'll get this from Gitea UI)
|
||||
# Go to: Gitea Admin → Actions → Runners → New Runner
|
||||
# Copy the token and run:
|
||||
./config.sh --url https://<your-gitea-url> --token <TOKEN> --name production-deploy
|
||||
```
|
||||
|
||||
## 3. Set repository variables (optional but recommended)
|
||||
|
||||
In your Gitea repo settings, set these variables:
|
||||
- `DEPLOY_DIR` = `/home/ubuntu/www`
|
||||
- `SERVICE_NAME` = `hoaledgeriq`
|
||||
|
||||
## 4. Enable Actions in your repo
|
||||
|
||||
Make sure Actions are enabled:
|
||||
- Go to repo settings → Actions → Enable Actions
|
||||
|
||||
## Alternative: Simple SSH-based deployment
|
||||
|
||||
If you don't want to run a self-hosted runner, you could use a simpler approach with SSH:
|
||||
|
||||
```yaml
|
||||
name: Deploy via SSH
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
|
||||
jobs:
|
||||
deploy:
|
||||
runs-on: self-hosted
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Deploy via SSH
|
||||
uses: appleboy/ssh-action@master
|
||||
with:
|
||||
host: ${{ secrets.DEPLOY_HOST }}
|
||||
username: ${{ secrets.DEPLOY_USER }}
|
||||
key: ${{ secrets.DEPLOY_KEY }}
|
||||
script: |
|
||||
cd ${{ secrets.DEPLOY_DIR }}
|
||||
git pull origin main
|
||||
systemctl restart hoaledgeriq
|
||||
```
|
||||
|
||||
Then set these **secrets** in your repo:
|
||||
- `DEPLOY_HOST` = your server IP/hostname
|
||||
- `DEPLOY_USER` = `ubuntu`
|
||||
- `DEPLOY_KEY` = SSH private key
|
||||
- `DEPLOY_DIR` = `/home/ubuntu/www`
|
||||
|
||||
Which approach do you want to go with? The self-hosted runner gives you more flexibility, while the SSH approach is simpler to set up initially.
|
||||
Reference in New Issue
Block a user