mirror of
https://github.com/qwibitai/nanoclaw.git
synced 2026-06-04 10:14:47 +08:00
v2: add Chat SDK channel adapters and skills for 11 platforms
Thin wrapper adapters + SKILL.md for Slack, Telegram, GitHub, Linear, Google Chat, Teams, WhatsApp Cloud API, Resend, Matrix, Webex, iMessage. All follow the same pattern as discord-v2.ts: readEnvFile → create*Adapter → createChatSdkBridge → registerChannelAdapter. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
gavrielc
@@ -0,0 +1,78 @@
|
||||
---
|
||||
name: add-gchat-v2
|
||||
description: Add Google Chat channel integration to NanoClaw v2 via Chat SDK.
|
||||
---
|
||||
|
||||
# Add Google Chat Channel (v2)
|
||||
|
||||
This skill adds Google Chat support to NanoClaw v2 using the Chat SDK bridge.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/gchat-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install @chat-adapter/gchat
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the Google Chat import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './gchat-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Create Google Chat App
|
||||
|
||||
> 1. Go to [Google Cloud Console](https://console.cloud.google.com)
|
||||
> 2. Create or select a project
|
||||
> 3. Enable the **Google Chat API**
|
||||
> 4. Go to **Google Chat API** > **Configuration**:
|
||||
> - App name and description
|
||||
> - Connection settings: select **HTTP endpoint URL** and set to `https://your-domain/webhook/gchat`
|
||||
> 5. Create a **Service Account**:
|
||||
> - Go to **IAM & Admin** > **Service Accounts** > **Create Service Account**
|
||||
> - Grant the Chat Bot role
|
||||
> - Create a JSON key and download it
|
||||
|
||||
### Configure environment
|
||||
|
||||
Add the service account JSON as a single-line string to `.env`:
|
||||
|
||||
```bash
|
||||
GCHAT_CREDENTIALS={"type":"service_account","project_id":"...","private_key":"...","client_email":"..."}
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# systemctl --user restart nanoclaw # Linux
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> Add the bot to a Google Chat space, then send a message or @mention the bot.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './gchat-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove `GCHAT_CREDENTIALS` from `.env`
|
||||
3. `npm uninstall @chat-adapter/gchat`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,80 @@
|
||||
---
|
||||
name: add-github-v2
|
||||
description: Add GitHub channel integration to NanoClaw v2 via Chat SDK. PR comment threads as conversations.
|
||||
---
|
||||
|
||||
# Add GitHub Channel (v2)
|
||||
|
||||
This skill adds GitHub support to NanoClaw v2 using the Chat SDK bridge. The agent can participate in PR comment threads.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/github-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install @chat-adapter/github
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the GitHub import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './github-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Create GitHub credentials
|
||||
|
||||
> 1. Go to [GitHub Settings > Developer Settings > Personal Access Tokens](https://github.com/settings/tokens)
|
||||
> 2. Create a **Fine-grained token** with:
|
||||
> - Repository access: select the repos you want the bot to monitor
|
||||
> - Permissions: **Pull requests** (Read & Write), **Issues** (Read & Write)
|
||||
> 3. Copy the token
|
||||
> 4. Set up a webhook on your repo(s):
|
||||
> - Go to **Settings** > **Webhooks** > **Add webhook**
|
||||
> - Payload URL: `https://your-domain/webhook/github`
|
||||
> - Content type: `application/json`
|
||||
> - Secret: generate a random string
|
||||
> - Events: select **Issue comments**, **Pull request review comments**
|
||||
|
||||
### Configure environment
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
GITHUB_TOKEN=github_pat_...
|
||||
GITHUB_WEBHOOK_SECRET=your-webhook-secret
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# systemctl --user restart nanoclaw # Linux
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> @mention the bot in a PR comment or issue comment. The bot should respond within a few seconds.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './github-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove `GITHUB_TOKEN` and `GITHUB_WEBHOOK_SECRET` from `.env`
|
||||
3. `npm uninstall @chat-adapter/github`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,86 @@
|
||||
---
|
||||
name: add-imessage-v2
|
||||
description: Add iMessage channel integration to NanoClaw v2 via Chat SDK. Local (macOS) or remote (Photon API) mode.
|
||||
---
|
||||
|
||||
# Add iMessage Channel (v2)
|
||||
|
||||
This skill adds iMessage support to NanoClaw v2 using the Chat SDK bridge. Supports local mode (macOS with Full Disk Access) and remote mode (via Photon API).
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/imessage-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install chat-adapter-imessage
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the iMessage import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './imessage-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Local Mode (macOS)
|
||||
|
||||
> **Requirements**: macOS with Full Disk Access granted to your terminal/Node.js process.
|
||||
>
|
||||
> 1. Go to **System Settings** > **Privacy & Security** > **Full Disk Access**
|
||||
> 2. Add your terminal app (Terminal, iTerm2, etc.) or the Node.js binary
|
||||
> 3. The adapter reads directly from the iMessage database on disk
|
||||
|
||||
### Remote Mode (Photon API)
|
||||
|
||||
> 1. Set up a [Photon](https://photon.im) account
|
||||
> 2. Get your server URL and API key
|
||||
|
||||
### Configure environment
|
||||
|
||||
**Local mode** — add to `.env`:
|
||||
|
||||
```bash
|
||||
IMESSAGE_ENABLED=true
|
||||
IMESSAGE_LOCAL=true
|
||||
```
|
||||
|
||||
**Remote mode** — add to `.env`:
|
||||
|
||||
```bash
|
||||
IMESSAGE_LOCAL=false
|
||||
IMESSAGE_SERVER_URL=https://your-photon-server.com
|
||||
IMESSAGE_API_KEY=your-api-key
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> Send an iMessage to the account running NanoClaw. The bot should respond within a few seconds.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './imessage-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove iMessage env vars from `.env`
|
||||
3. `npm uninstall chat-adapter-imessage`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,77 @@
|
||||
---
|
||||
name: add-linear-v2
|
||||
description: Add Linear channel integration to NanoClaw v2 via Chat SDK. Issue comment threads as conversations.
|
||||
---
|
||||
|
||||
# Add Linear Channel (v2)
|
||||
|
||||
This skill adds Linear support to NanoClaw v2 using the Chat SDK bridge. The agent can participate in issue comment threads.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/linear-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install @chat-adapter/linear
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the Linear import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './linear-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Create Linear credentials
|
||||
|
||||
> 1. Go to [Linear Settings > API](https://linear.app/settings/api)
|
||||
> 2. Create a **Personal API Key** (or use an OAuth application for team-wide access)
|
||||
> 3. Copy the API key
|
||||
> 4. Set up a webhook:
|
||||
> - Go to **Settings** > **API** > **Webhooks** > **New webhook**
|
||||
> - URL: `https://your-domain/webhook/linear`
|
||||
> - Select events: **Comment** (created, updated)
|
||||
> - Copy the signing secret
|
||||
|
||||
### Configure environment
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
LINEAR_API_KEY=lin_api_...
|
||||
LINEAR_WEBHOOK_SECRET=your-webhook-secret
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# systemctl --user restart nanoclaw # Linux
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> @mention the bot in a Linear issue comment. The bot should respond within a few seconds.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './linear-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove `LINEAR_API_KEY` and `LINEAR_WEBHOOK_SECRET` from `.env`
|
||||
3. `npm uninstall @chat-adapter/linear`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,77 @@
|
||||
---
|
||||
name: add-matrix-v2
|
||||
description: Add Matrix channel integration to NanoClaw v2 via Chat SDK. Works with any Matrix homeserver (Element, Beeper, etc.).
|
||||
---
|
||||
|
||||
# Add Matrix Channel (v2)
|
||||
|
||||
This skill adds Matrix support to NanoClaw v2 using the Chat SDK bridge. Works with any Matrix homeserver.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/matrix-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install @beeper/chat-adapter-matrix
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the Matrix import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './matrix-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Create Matrix bot account
|
||||
|
||||
> 1. Register a bot account on your Matrix homeserver (e.g., via Element)
|
||||
> 2. Get the homeserver URL (e.g., `https://matrix.org` or your self-hosted URL)
|
||||
> 3. Get an access token:
|
||||
> - In Element: **Settings** > **Help & About** > **Access Token** (advanced)
|
||||
> - Or via API: `curl -XPOST 'https://matrix.org/_matrix/client/r0/login' -d '{"type":"m.login.password","user":"botuser","password":"..."}'`
|
||||
> 4. Note the bot's user ID (e.g., `@botuser:matrix.org`)
|
||||
|
||||
### Configure environment
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
MATRIX_BASE_URL=https://matrix.org
|
||||
MATRIX_ACCESS_TOKEN=your-access-token
|
||||
MATRIX_USER_ID=@botuser:matrix.org
|
||||
MATRIX_BOT_USERNAME=botuser
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# systemctl --user restart nanoclaw # Linux
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> Invite the bot to a Matrix room and send a message. The bot should respond within a few seconds.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './matrix-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove `MATRIX_BASE_URL`, `MATRIX_ACCESS_TOKEN`, `MATRIX_USER_ID`, `MATRIX_BOT_USERNAME` from `.env`
|
||||
3. `npm uninstall @beeper/chat-adapter-matrix`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,79 @@
|
||||
---
|
||||
name: add-resend-v2
|
||||
description: Add Resend (email) channel integration to NanoClaw v2 via Chat SDK.
|
||||
---
|
||||
|
||||
# Add Resend Email Channel (v2)
|
||||
|
||||
This skill adds email support via Resend to NanoClaw v2 using the Chat SDK bridge.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/resend-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install @resend/chat-sdk-adapter
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the Resend import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './resend-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Create Resend credentials
|
||||
|
||||
> 1. Go to [resend.com](https://resend.com) and create an account
|
||||
> 2. Add and verify your sending domain
|
||||
> 3. Go to **API Keys** and create a new key
|
||||
> 4. Set up a webhook:
|
||||
> - Go to **Webhooks** > **Add webhook**
|
||||
> - URL: `https://your-domain/webhook/resend`
|
||||
> - Events: select **email.received** (for inbound email)
|
||||
> - Copy the signing secret
|
||||
|
||||
### Configure environment
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
RESEND_API_KEY=re_...
|
||||
RESEND_FROM_ADDRESS=bot@yourdomain.com
|
||||
RESEND_FROM_NAME=NanoClaw
|
||||
RESEND_WEBHOOK_SECRET=your-webhook-secret
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# systemctl --user restart nanoclaw # Linux
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> Send an email to the configured from address. The bot should respond via email within a few seconds.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './resend-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove `RESEND_API_KEY`, `RESEND_FROM_ADDRESS`, `RESEND_FROM_NAME`, `RESEND_WEBHOOK_SECRET` from `.env`
|
||||
3. `npm uninstall @resend/chat-sdk-adapter`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,81 @@
|
||||
---
|
||||
name: add-slack-v2
|
||||
description: Add Slack channel integration to NanoClaw v2 via Chat SDK.
|
||||
---
|
||||
|
||||
# Add Slack Channel (v2)
|
||||
|
||||
This skill adds Slack support to NanoClaw v2 using the Chat SDK bridge.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/slack-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install @chat-adapter/slack
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the Slack import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './slack-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Create Slack App (if needed)
|
||||
|
||||
If the user doesn't have a Slack app:
|
||||
|
||||
> 1. Go to [api.slack.com/apps](https://api.slack.com/apps) and click **Create New App** > **From scratch**
|
||||
> 2. Name it (e.g., "NanoClaw") and select your workspace
|
||||
> 3. Go to **OAuth & Permissions** and add Bot Token Scopes:
|
||||
> - `chat:write`, `channels:history`, `groups:history`, `im:history`, `channels:read`, `groups:read`, `users:read`, `reactions:write`
|
||||
> 4. Click **Install to Workspace** and copy the **Bot User OAuth Token** (`xoxb-...`)
|
||||
> 5. Go to **Basic Information** and copy the **Signing Secret**
|
||||
> 6. Go to **Event Subscriptions**, enable events, and subscribe to:
|
||||
> - `message.channels`, `message.groups`, `message.im`, `app_mention`
|
||||
> 7. Set the Request URL to your webhook endpoint (e.g., `https://your-domain/webhook/slack`)
|
||||
|
||||
### Configure environment
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
SLACK_BOT_TOKEN=xoxb-your-bot-token
|
||||
SLACK_SIGNING_SECRET=your-signing-secret
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# systemctl --user restart nanoclaw # Linux
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> Add the bot to a Slack channel, then send a message or @mention the bot.
|
||||
> The bot should respond within a few seconds.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './slack-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove `SLACK_BOT_TOKEN` and `SLACK_SIGNING_SECRET` from `.env`
|
||||
3. `npm uninstall @chat-adapter/slack`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,75 @@
|
||||
---
|
||||
name: add-teams-v2
|
||||
description: Add Microsoft Teams channel integration to NanoClaw v2 via Chat SDK.
|
||||
---
|
||||
|
||||
# Add Microsoft Teams Channel (v2)
|
||||
|
||||
This skill adds Microsoft Teams support to NanoClaw v2 using the Chat SDK bridge.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/teams-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install @chat-adapter/teams
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the Teams import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './teams-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Create Teams Bot
|
||||
|
||||
> 1. Go to [Azure Portal](https://portal.azure.com) > **Azure Bot** > **Create**
|
||||
> 2. Fill in the bot details and create
|
||||
> 3. Go to **Configuration**:
|
||||
> - Messaging endpoint: `https://your-domain/webhook/teams`
|
||||
> 4. Go to **Channels** > add **Microsoft Teams**
|
||||
> 5. Note the **Microsoft App ID** and **Password** (from the bot's Azure AD app registration)
|
||||
|
||||
### Configure environment
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
TEAMS_APP_ID=your-app-id
|
||||
TEAMS_APP_PASSWORD=your-app-password
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# systemctl --user restart nanoclaw # Linux
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> Add the bot to a Teams channel or send it a direct message. The bot should respond within a few seconds.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './teams-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove `TEAMS_APP_ID` and `TEAMS_APP_PASSWORD` from `.env`
|
||||
3. `npm uninstall @chat-adapter/teams`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,82 @@
|
||||
---
|
||||
name: add-telegram-v2
|
||||
description: Add Telegram channel integration to NanoClaw v2 via Chat SDK.
|
||||
---
|
||||
|
||||
# Add Telegram Channel (v2)
|
||||
|
||||
This skill adds Telegram support to NanoClaw v2 using the Chat SDK bridge.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/telegram-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install @chat-adapter/telegram
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the Telegram import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './telegram-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Create Telegram Bot (if needed)
|
||||
|
||||
> 1. Open Telegram and search for `@BotFather`
|
||||
> 2. Send `/newbot` and follow the prompts:
|
||||
> - Bot name: Something friendly (e.g., "NanoClaw Assistant")
|
||||
> - Bot username: Must end with "bot" (e.g., "nanoclaw_bot")
|
||||
> 3. Copy the bot token (looks like `123456:ABC-DEF1234ghIkl-zyx57W2v1u123ew11`)
|
||||
|
||||
### Disable Group Privacy (for group chats)
|
||||
|
||||
> **Important for group chats**: By default, Telegram bots only see @mentions and commands in groups. To let the bot see all messages:
|
||||
>
|
||||
> 1. Open `@BotFather` > `/mybots` > select your bot
|
||||
> 2. **Bot Settings** > **Group Privacy** > **Turn off**
|
||||
|
||||
### Configure environment
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
TELEGRAM_BOT_TOKEN=your-bot-token
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# systemctl --user restart nanoclaw # Linux
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> Send a message to your bot in Telegram (search for its username).
|
||||
> For groups: add the bot to a group and send a message.
|
||||
> The bot should respond within a few seconds.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './telegram-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove `TELEGRAM_BOT_TOKEN` from `.env`
|
||||
3. `npm uninstall @chat-adapter/telegram`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,75 @@
|
||||
---
|
||||
name: add-webex-v2
|
||||
description: Add Webex channel integration to NanoClaw v2 via Chat SDK.
|
||||
---
|
||||
|
||||
# Add Webex Channel (v2)
|
||||
|
||||
This skill adds Cisco Webex support to NanoClaw v2 using the Chat SDK bridge.
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/webex-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install @bitbasti/chat-adapter-webex
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the Webex import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './webex-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Create Webex Bot
|
||||
|
||||
> 1. Go to [developer.webex.com](https://developer.webex.com/my-apps/new/bot)
|
||||
> 2. Create a new bot and copy the **Bot Access Token**
|
||||
> 3. Set up a webhook:
|
||||
> - Use the Webex API to create a webhook pointing to `https://your-domain/webhook/webex`
|
||||
> - Or use the Webex Developer Portal
|
||||
> - Set a webhook secret for signature verification
|
||||
|
||||
### Configure environment
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
WEBEX_BOT_TOKEN=your-bot-token
|
||||
WEBEX_WEBHOOK_SECRET=your-webhook-secret
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# systemctl --user restart nanoclaw # Linux
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> Add the bot to a Webex space or send it a direct message. The bot should respond within a few seconds.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './webex-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove `WEBEX_BOT_TOKEN` and `WEBEX_WEBHOOK_SECRET` from `.env`
|
||||
3. `npm uninstall @bitbasti/chat-adapter-webex`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,82 @@
|
||||
---
|
||||
name: add-whatsapp-cloud-v2
|
||||
description: Add WhatsApp Business Cloud API channel to NanoClaw v2 via Chat SDK. Official Meta API (not Baileys).
|
||||
---
|
||||
|
||||
# Add WhatsApp Cloud API Channel (v2)
|
||||
|
||||
This skill adds WhatsApp support via the official Meta WhatsApp Business Cloud API. This is different from the Baileys-based WhatsApp adapter (which uses WhatsApp Web protocol).
|
||||
|
||||
## Phase 1: Pre-flight
|
||||
|
||||
Check if `src/channels/whatsapp-cloud-v2.ts` exists and the import is uncommented in `src/channels/index.ts`. If both are in place, skip to Phase 3.
|
||||
|
||||
## Phase 2: Apply Code Changes
|
||||
|
||||
### Install the adapter package
|
||||
|
||||
```bash
|
||||
npm install @chat-adapter/whatsapp
|
||||
```
|
||||
|
||||
### Enable the channel
|
||||
|
||||
Uncomment the WhatsApp Cloud API import in `src/channels/index.ts`:
|
||||
|
||||
```typescript
|
||||
import './whatsapp-cloud-v2.js';
|
||||
```
|
||||
|
||||
### Build
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
```
|
||||
|
||||
## Phase 3: Setup
|
||||
|
||||
### Create WhatsApp Business App
|
||||
|
||||
> 1. Go to [Meta for Developers](https://developers.facebook.com/apps/) and create an app (type: Business)
|
||||
> 2. Add the **WhatsApp** product
|
||||
> 3. Go to **WhatsApp** > **API Setup**:
|
||||
> - Note the **Phone Number ID** (not the phone number itself)
|
||||
> - Generate a **permanent System User access token** with `whatsapp_business_messaging` permission
|
||||
> 4. Go to **WhatsApp** > **Configuration**:
|
||||
> - Set webhook URL: `https://your-domain/webhook/whatsapp`
|
||||
> - Set a **Verify Token** (any random string you choose)
|
||||
> - Subscribe to webhook fields: `messages`
|
||||
> 5. Copy the **App Secret** from **Settings** > **Basic**
|
||||
|
||||
### Configure environment
|
||||
|
||||
Add to `.env`:
|
||||
|
||||
```bash
|
||||
WHATSAPP_ACCESS_TOKEN=your-system-user-access-token
|
||||
WHATSAPP_PHONE_NUMBER_ID=your-phone-number-id
|
||||
WHATSAPP_APP_SECRET=your-app-secret
|
||||
WHATSAPP_VERIFY_TOKEN=your-verify-token
|
||||
```
|
||||
|
||||
Sync to container: `mkdir -p data/env && cp .env data/env/env`
|
||||
|
||||
### Build and restart
|
||||
|
||||
```bash
|
||||
npm run build
|
||||
launchctl kickstart -k gui/$(id -u)/com.nanoclaw # macOS
|
||||
# systemctl --user restart nanoclaw # Linux
|
||||
```
|
||||
|
||||
## Phase 4: Verify
|
||||
|
||||
> Send a message to your WhatsApp Business number. The bot should respond within a few seconds.
|
||||
> Note: WhatsApp Cloud API only supports 1:1 DMs, not group chats.
|
||||
|
||||
## Removal
|
||||
|
||||
1. Comment out `import './whatsapp-cloud-v2.js'` in `src/channels/index.ts`
|
||||
2. Remove `WHATSAPP_ACCESS_TOKEN`, `WHATSAPP_PHONE_NUMBER_ID`, `WHATSAPP_APP_SECRET`, `WHATSAPP_VERIFY_TOKEN` from `.env`
|
||||
3. `npm uninstall @chat-adapter/whatsapp`
|
||||
4. Rebuild and restart
|
||||
@@ -0,0 +1,189 @@
|
||||
# NanoClaw v2 Checklist
|
||||
|
||||
Status: [x] done, [~] partial, [ ] not started
|
||||
|
||||
---
|
||||
|
||||
## Core Architecture
|
||||
|
||||
- [x] Session DB replaces IPC (messages_in / messages_out as sole IO)
|
||||
- [x] Central DB (agent groups, messaging groups, sessions, routing)
|
||||
- [x] Host sweep (stale detection, retry with backoff, recurrence scheduling)
|
||||
- [x] Active delivery polling (1s for running sessions)
|
||||
- [x] Sweep delivery polling (60s across all sessions)
|
||||
- [x] Container runner with session DB mounting
|
||||
- [x] Per-session container lifecycle and idle timeout
|
||||
- [x] Session resume (sessionId + resumeAt across queries)
|
||||
- [x] Graceful shutdown (SIGTERM/SIGINT handlers)
|
||||
- [x] Orphan container cleanup on startup
|
||||
|
||||
## Agent Runner (Container)
|
||||
|
||||
- [x] Poll loop (pending messages, status transitions, idle detection)
|
||||
- [x] Concurrent follow-up polling while agent is thinking
|
||||
- [x] Message formatter (chat, task, webhook, system kinds)
|
||||
- [x] Command categorization (admin, filtered, passthrough)
|
||||
- [x] Transcript archiving (pre-compact hook)
|
||||
- [x] XML message formatting with sender, timestamp
|
||||
- [~] Media handling inbound (formatter references attachments, no download-from-URL)
|
||||
|
||||
## Agent Providers
|
||||
|
||||
- [x] Claude provider (Agent SDK, tool allowlist, message stream, session resume)
|
||||
- [x] Mock provider (testing)
|
||||
- [x] Provider factory
|
||||
- [ ] Codex provider
|
||||
- [ ] OpenCode provider
|
||||
|
||||
## Channel Adapters
|
||||
|
||||
- [x] Channel adapter interface (setup, deliver, teardown, typing)
|
||||
- [x] Chat SDK bridge (generic, works with any Chat SDK adapter)
|
||||
- [x] Chat SDK SQLite state adapter (KV, subscriptions, locks, lists)
|
||||
- [x] Discord via Chat SDK
|
||||
- [~] Slack via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Telegram via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Microsoft Teams via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Google Chat via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Linear via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] GitHub via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] WhatsApp Cloud API via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Resend (email) via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Matrix via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] Webex via Chat SDK (adapter + skill written, not tested)
|
||||
- [~] iMessage via Chat SDK (adapter + skill written, not tested)
|
||||
- [x] Backward compatibility with native channels (old adapters still work)
|
||||
- [ ] Setup flow wired to v2 channels
|
||||
- [ ] Setup communicates each group is a different agent, distinct names
|
||||
- [ ] Setup vs production channel separation
|
||||
- [ ] Generate visual diagram of customized instance at end of setup
|
||||
|
||||
## Routing
|
||||
|
||||
- [x] Inbound routing (platform ID + thread ID -> agent group -> session)
|
||||
- [x] Auto-create messaging group on first message
|
||||
- [x] Session resolution (shared vs per-thread modes)
|
||||
- [x] Message writing to session DB with seq numbering
|
||||
- [x] Container waking on new message
|
||||
- [~] Trigger rule matching (router picks highest-priority agent, regex/mention matching TODO)
|
||||
|
||||
## Rich Messaging
|
||||
|
||||
- [x] Interactive cards with buttons (ask_user_question)
|
||||
- [x] Native platform rendering (Discord embeds, buttons)
|
||||
- [x] Message editing
|
||||
- [x] Emoji reactions
|
||||
- [x] File sending from agent (outbox -> delivery)
|
||||
- [x] File upload delivery (buffer-based via adapter)
|
||||
- [x] Markdown formatting
|
||||
- [~] Formatted /usage, /context, /cost output (commands pass through, no rich card formatting)
|
||||
- [ ] Context window visibility: show position in context, approaching compaction, when compaction happens, post-compaction state
|
||||
- [ ] Threading and replies support
|
||||
|
||||
## MCP Tools (Container)
|
||||
|
||||
- [x] send_message (text, optional cross-channel targeting)
|
||||
- [x] send_file (copy to outbox, write messages_out)
|
||||
- [x] edit_message
|
||||
- [x] add_reaction
|
||||
- [x] send_card
|
||||
- [x] ask_user_question (blocking poll for response)
|
||||
- [x] schedule_task (with process_after and recurrence)
|
||||
- [x] list_tasks
|
||||
- [x] cancel_task / pause_task / resume_task
|
||||
- [x] send_to_agent (writes message, routing incomplete)
|
||||
|
||||
## Scheduling
|
||||
|
||||
- [x] One-shot scheduled messages (process_after / deliver_after)
|
||||
- [x] Recurring tasks via cron expressions
|
||||
- [x] Host sweep picks up due messages and advances recurrence
|
||||
- [x] Scheduled outbound messages (no container wake needed)
|
||||
- [~] Pre-agent scripts (task kind with script field, documented but not verified)
|
||||
|
||||
## Permissions and Approval Flows
|
||||
|
||||
- [x] Admin user ID per group
|
||||
- [x] Admin-only command filtering in container
|
||||
- [ ] Approval flow (sensitive action -> card to admin -> approve/reject -> execute)
|
||||
- [ ] Role definitions beyond admin (custom roles, per-group permissions)
|
||||
- [ ] Configurable sensitive action list
|
||||
- [ ] Non-main groups requesting sensitive actions
|
||||
- [ ] Agent requests dependency/package install (persists via Dockerfile change, requires approval)
|
||||
- [ ] Agent self-modification flow:
|
||||
- [ ] Agent requests code changes by delegating to a builder agent
|
||||
- [ ] Builder agent has write access to the requesting agent's code and Dockerfile
|
||||
- [ ] Approval modes: approve per-edit as builder works, or approve full diff at the end
|
||||
- [ ] Diff review card sent to admin showing all proposed changes
|
||||
- [ ] On approval: apply edits, rebuild container image, restart agent
|
||||
- [ ] On rejection: discard changes, notify requesting agent
|
||||
|
||||
## Agent-to-Agent Communication
|
||||
|
||||
- [~] send_to_agent MCP tool (writes message, host-side routing TODO)
|
||||
- [ ] Host delivery to target agent's session DB
|
||||
- [ ] Agent spawning a new sub-agent
|
||||
- [ ] Internal-only agents (no channel attached)
|
||||
- [ ] Permission delegation from parent to child agent
|
||||
- [ ] Specialist sub-agents (browser agent, dev agent — user's agent delegates with request/approval)
|
||||
|
||||
## In-Chat Agent Management
|
||||
|
||||
- [x] /clear (resets session)
|
||||
- [x] /compact (triggers context compaction)
|
||||
- [~] /context (passes through, no rich formatting)
|
||||
- [~] /usage (passes through, no rich formatting)
|
||||
- [~] /cost (passes through, no rich formatting)
|
||||
- [ ] Smooth session transitions: load context into new sessions, solve cold start problem
|
||||
- [ ] MCP/package installation from chat
|
||||
- [ ] Browse MCP marketplace / skills repository from chat
|
||||
|
||||
## Webhook Ingestion
|
||||
|
||||
- [ ] Generic webhook endpoint for external events
|
||||
- [ ] GitHub webhook handling
|
||||
- [ ] CI/CD notification handling
|
||||
- [ ] Webhook -> messages_in routing
|
||||
|
||||
## System Actions
|
||||
|
||||
- [ ] register_group from inside agent (stub exists)
|
||||
- [ ] reset_session from inside agent (stub exists)
|
||||
|
||||
## Integrations
|
||||
|
||||
- [ ] Vercel CLI integration in setup process
|
||||
- [ ] Skills for deploying and managing Vercel websites from chat
|
||||
- [ ] Office 365 integration (create/edit documents with inline suggestions)
|
||||
|
||||
## Memory
|
||||
|
||||
- [ ] Shared memory with approval flow (write to global memory requires admin approval)
|
||||
|
||||
## Migration
|
||||
|
||||
- [ ] v1 -> v2 migration skill
|
||||
- [ ] Database migration (v1 SQLite -> v2 central DB + session DBs)
|
||||
- [ ] Channel credential preservation
|
||||
- [ ] Custom skill/code porting
|
||||
|
||||
## Testing
|
||||
|
||||
- [x] DB layer tests (agent groups, messaging groups, sessions, pending questions)
|
||||
- [x] Channel registry tests
|
||||
- [x] Poll loop / formatter tests
|
||||
- [x] Integration test (container agent-runner)
|
||||
- [x] Host core tests
|
||||
- [ ] End-to-end flow tests (message in -> agent -> message out -> delivery)
|
||||
- [ ] Delivery polling tests
|
||||
- [ ] Host sweep tests (stale detection, recurrence)
|
||||
- [ ] Multi-channel integration tests
|
||||
|
||||
## Rollout
|
||||
|
||||
- [ ] Internal testing across all channels
|
||||
- [ ] Migration skill built and tested
|
||||
- [ ] PR factory migrated as validation
|
||||
- [ ] Blog post / announcement
|
||||
- [ ] Video demos of key flows
|
||||
- [ ] Vercel coordination
|
||||
@@ -0,0 +1,20 @@
|
||||
/**
|
||||
* Google Chat channel adapter (v2) — uses Chat SDK bridge.
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createGoogleChatAdapter } from '@chat-adapter/gchat';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('gchat', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['GCHAT_CREDENTIALS']);
|
||||
if (!env.GCHAT_CREDENTIALS) return null;
|
||||
const gchatAdapter = createGoogleChatAdapter({
|
||||
credentials: JSON.parse(env.GCHAT_CREDENTIALS),
|
||||
});
|
||||
return createChatSdkBridge({ adapter: gchatAdapter, concurrency: 'concurrent' });
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,22 @@
|
||||
/**
|
||||
* GitHub channel adapter (v2) — uses Chat SDK bridge.
|
||||
* PR comment threads as conversations.
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createGitHubAdapter } from '@chat-adapter/github';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('github', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['GITHUB_TOKEN', 'GITHUB_WEBHOOK_SECRET']);
|
||||
if (!env.GITHUB_TOKEN) return null;
|
||||
const githubAdapter = createGitHubAdapter({
|
||||
token: env.GITHUB_TOKEN,
|
||||
webhookSecret: env.GITHUB_WEBHOOK_SECRET,
|
||||
});
|
||||
return createChatSdkBridge({ adapter: githubAdapter, concurrency: 'queue' });
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,25 @@
|
||||
/**
|
||||
* iMessage channel adapter (v2) — uses Chat SDK bridge.
|
||||
* Supports local mode (macOS Full Disk Access) and remote mode (Photon API).
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createiMessageAdapter } from 'chat-adapter-imessage';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('imessage', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['IMESSAGE_ENABLED', 'IMESSAGE_LOCAL', 'IMESSAGE_SERVER_URL', 'IMESSAGE_API_KEY']);
|
||||
const isLocal = env.IMESSAGE_LOCAL !== 'false';
|
||||
if (isLocal && !env.IMESSAGE_ENABLED) return null;
|
||||
if (!isLocal && !env.IMESSAGE_SERVER_URL) return null;
|
||||
const imessageAdapter = createiMessageAdapter({
|
||||
local: isLocal,
|
||||
serverUrl: env.IMESSAGE_SERVER_URL,
|
||||
apiKey: env.IMESSAGE_API_KEY,
|
||||
});
|
||||
return createChatSdkBridge({ adapter: imessageAdapter, concurrency: 'concurrent' });
|
||||
},
|
||||
});
|
||||
+34
-4
@@ -1,12 +1,42 @@
|
||||
// Channel self-registration barrel file.
|
||||
// Each import triggers the channel module's registerChannel() call.
|
||||
// Each import triggers the channel module's registerChannelAdapter() call.
|
||||
|
||||
// discord
|
||||
|
||||
// gmail
|
||||
// import './discord-v2.js';
|
||||
|
||||
// slack
|
||||
// import './slack-v2.js';
|
||||
|
||||
// telegram
|
||||
// import './telegram-v2.js';
|
||||
|
||||
// whatsapp
|
||||
// github
|
||||
// import './github-v2.js';
|
||||
|
||||
// linear
|
||||
// import './linear-v2.js';
|
||||
|
||||
// google chat
|
||||
// import './gchat-v2.js';
|
||||
|
||||
// microsoft teams
|
||||
// import './teams-v2.js';
|
||||
|
||||
// whatsapp cloud api
|
||||
// import './whatsapp-cloud-v2.js';
|
||||
|
||||
// resend (email)
|
||||
// import './resend-v2.js';
|
||||
|
||||
// matrix
|
||||
// import './matrix-v2.js';
|
||||
|
||||
// webex
|
||||
// import './webex-v2.js';
|
||||
|
||||
// imessage
|
||||
// import './imessage-v2.js';
|
||||
|
||||
// gmail (native, no Chat SDK)
|
||||
|
||||
// whatsapp baileys (native, no Chat SDK)
|
||||
|
||||
@@ -0,0 +1,22 @@
|
||||
/**
|
||||
* Linear channel adapter (v2) — uses Chat SDK bridge.
|
||||
* Issue comment threads as conversations.
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createLinearAdapter } from '@chat-adapter/linear';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('linear', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['LINEAR_API_KEY', 'LINEAR_WEBHOOK_SECRET']);
|
||||
if (!env.LINEAR_API_KEY) return null;
|
||||
const linearAdapter = createLinearAdapter({
|
||||
apiKey: env.LINEAR_API_KEY,
|
||||
webhookSecret: env.LINEAR_WEBHOOK_SECRET,
|
||||
});
|
||||
return createChatSdkBridge({ adapter: linearAdapter, concurrency: 'queue' });
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,23 @@
|
||||
/**
|
||||
* Matrix channel adapter (v2) — uses Chat SDK bridge.
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createMatrixAdapter } from '@beeper/chat-adapter-matrix';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('matrix', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['MATRIX_BASE_URL', 'MATRIX_ACCESS_TOKEN', 'MATRIX_USER_ID', 'MATRIX_BOT_USERNAME']);
|
||||
if (!env.MATRIX_BASE_URL) return null;
|
||||
// Matrix adapter reads from process.env directly
|
||||
process.env.MATRIX_BASE_URL = env.MATRIX_BASE_URL;
|
||||
if (env.MATRIX_ACCESS_TOKEN) process.env.MATRIX_ACCESS_TOKEN = env.MATRIX_ACCESS_TOKEN;
|
||||
if (env.MATRIX_USER_ID) process.env.MATRIX_USER_ID = env.MATRIX_USER_ID;
|
||||
if (env.MATRIX_BOT_USERNAME) process.env.MATRIX_BOT_USERNAME = env.MATRIX_BOT_USERNAME;
|
||||
const matrixAdapter = createMatrixAdapter();
|
||||
return createChatSdkBridge({ adapter: matrixAdapter, concurrency: 'concurrent' });
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,23 @@
|
||||
/**
|
||||
* Resend (email) channel adapter (v2) — uses Chat SDK bridge.
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createResendAdapter } from '@resend/chat-sdk-adapter';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('resend', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['RESEND_API_KEY', 'RESEND_FROM_ADDRESS', 'RESEND_FROM_NAME', 'RESEND_WEBHOOK_SECRET']);
|
||||
if (!env.RESEND_API_KEY) return null;
|
||||
const resendAdapter = createResendAdapter({
|
||||
apiKey: env.RESEND_API_KEY,
|
||||
fromAddress: env.RESEND_FROM_ADDRESS,
|
||||
fromName: env.RESEND_FROM_NAME,
|
||||
webhookSecret: env.RESEND_WEBHOOK_SECRET,
|
||||
});
|
||||
return createChatSdkBridge({ adapter: resendAdapter, concurrency: 'queue' });
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,21 @@
|
||||
/**
|
||||
* Slack channel adapter (v2) — uses Chat SDK bridge.
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createSlackAdapter } from '@chat-adapter/slack';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('slack', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['SLACK_BOT_TOKEN', 'SLACK_SIGNING_SECRET']);
|
||||
if (!env.SLACK_BOT_TOKEN) return null;
|
||||
const slackAdapter = createSlackAdapter({
|
||||
botToken: env.SLACK_BOT_TOKEN,
|
||||
signingSecret: env.SLACK_SIGNING_SECRET,
|
||||
});
|
||||
return createChatSdkBridge({ adapter: slackAdapter, concurrency: 'concurrent' });
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,21 @@
|
||||
/**
|
||||
* Microsoft Teams channel adapter (v2) — uses Chat SDK bridge.
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createTeamsAdapter } from '@chat-adapter/teams';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('teams', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['TEAMS_APP_ID', 'TEAMS_APP_PASSWORD']);
|
||||
if (!env.TEAMS_APP_ID) return null;
|
||||
const teamsAdapter = createTeamsAdapter({
|
||||
appId: env.TEAMS_APP_ID,
|
||||
appPassword: env.TEAMS_APP_PASSWORD,
|
||||
});
|
||||
return createChatSdkBridge({ adapter: teamsAdapter, concurrency: 'concurrent' });
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,21 @@
|
||||
/**
|
||||
* Telegram channel adapter (v2) — uses Chat SDK bridge.
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createTelegramAdapter } from '@chat-adapter/telegram';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('telegram', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['TELEGRAM_BOT_TOKEN']);
|
||||
if (!env.TELEGRAM_BOT_TOKEN) return null;
|
||||
const telegramAdapter = createTelegramAdapter({
|
||||
botToken: env.TELEGRAM_BOT_TOKEN,
|
||||
mode: 'polling',
|
||||
});
|
||||
return createChatSdkBridge({ adapter: telegramAdapter, concurrency: 'concurrent' });
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,21 @@
|
||||
/**
|
||||
* Webex channel adapter (v2) — uses Chat SDK bridge.
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createWebexAdapter } from '@bitbasti/chat-adapter-webex';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('webex', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['WEBEX_BOT_TOKEN', 'WEBEX_WEBHOOK_SECRET']);
|
||||
if (!env.WEBEX_BOT_TOKEN) return null;
|
||||
const webexAdapter = createWebexAdapter({
|
||||
botToken: env.WEBEX_BOT_TOKEN,
|
||||
webhookSecret: env.WEBEX_WEBHOOK_SECRET,
|
||||
});
|
||||
return createChatSdkBridge({ adapter: webexAdapter, concurrency: 'concurrent' });
|
||||
},
|
||||
});
|
||||
@@ -0,0 +1,24 @@
|
||||
/**
|
||||
* WhatsApp Cloud API channel adapter (v2) — uses Chat SDK bridge.
|
||||
* Uses the official Meta WhatsApp Business Cloud API (not Baileys).
|
||||
* Self-registers on import.
|
||||
*/
|
||||
import { createWhatsAppAdapter } from '@chat-adapter/whatsapp';
|
||||
|
||||
import { readEnvFile } from '../env.js';
|
||||
import { createChatSdkBridge } from './chat-sdk-bridge.js';
|
||||
import { registerChannelAdapter } from './channel-registry.js';
|
||||
|
||||
registerChannelAdapter('whatsapp-cloud', {
|
||||
factory: () => {
|
||||
const env = readEnvFile(['WHATSAPP_ACCESS_TOKEN', 'WHATSAPP_PHONE_NUMBER_ID', 'WHATSAPP_APP_SECRET', 'WHATSAPP_VERIFY_TOKEN']);
|
||||
if (!env.WHATSAPP_ACCESS_TOKEN) return null;
|
||||
const whatsappAdapter = createWhatsAppAdapter({
|
||||
accessToken: env.WHATSAPP_ACCESS_TOKEN,
|
||||
phoneNumberId: env.WHATSAPP_PHONE_NUMBER_ID,
|
||||
appSecret: env.WHATSAPP_APP_SECRET,
|
||||
verifyToken: env.WHATSAPP_VERIFY_TOKEN,
|
||||
});
|
||||
return createChatSdkBridge({ adapter: whatsappAdapter, concurrency: 'concurrent' });
|
||||
},
|
||||
});
|
||||
Reference in New Issue
Block a user