skills/lobehub__lobehub
1
0
Fork 0
mirror of https://github.com/lobehub/lobehub.git synced 2026-09-20 04:56:13 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
feat/quick-note
lobehub__lobehub/docs/usage/channels/overview.mdx
T
YuTengjing 191f3fe776 📝 docs: fix outdated content across the docs site (#16964) 
* 📝 docs: fix outdated content across the docs site

Audited docs/ against the current codebase and fixed stale content that
drifted after major refactors (Clerk/NextAuth → Better Auth, src/server →
apps/server, src/{config,envs,locales} → packages/*, model-bank updates).

- self-hosting/auth: mark removed NextAuth/Clerk pages with deprecation
  warnings; fix microsoft/zitadel alias claims and the Logto callback path
- environment-variables & advanced: correct wrong defaults (S3_SET_ACL,
  AI_IMAGE_DEFAULT_IMAGE_NUM, index/proxy URLs), drop non-existent env vars
  and fictional feature flags, fix OIDC config guidance
- development: update refactored paths, Better Auth, .mjs configs, remove
  the MSW section (msw is not a dependency)
- providers & model examples: replace retired model ids with in-bank ones;
  fix comfyui frontmatter corruption
- usage: rename Moderator→Orchestrator, GTD→Task, correct shortcut keys,
  channel capability tables, Feishu/Lark WebSocket mode
- platform/migration: fix dead links, docker service name, npx/npm → bun

EN and zh-CN pairs updated together.

* 📝 docs: fix Logto callback path and AUTH_SECRET deprecation guidance

- Revert Logto/Sealos callback URLs to /api/auth/callback/logto to match
  the runtime SSO redirectURI override
- Narrow legacy auth Callout: AUTH_SECRET remains required for Better Auth;
  mark NEXT_AUTH_SECRET as deprecated in zh-CN

* 📝 docs: refresh agent skills for locales, env, auth, and agentRun paths

Align OSS agent guidance with post-refactor layout:
- packages/locales/src/default + bun run i18n
- packages/env/src for env schemas (@/envs alias)
- spa-auth shell + src/routes/auth segments
- chat agentRun/transports/hetero instead of aiChat

* 📝 docs: document APP_URL as required for Better Auth base URL

Self-hosted auth uses appEnv.APP_URL as baseURL, not request-header
auto-detection. NEXT_PUBLIC_AUTH_URL remains deprecated.

* 📝 docs: note self-host search provider setup for web search

Built-in lobe-web-browsing needs no client plugin, but self-hosted
servers still require SEARCH_PROVIDERS / SEARXNG_URL (default SearXNG).

* 📝 docs: point feature guide welcome UI at AgentHome

Opening message/questions on the agent chat page live in
src/features/AgentHome, not Onboarding WelcomeMessage.
2026-07-10 17:50:03 +08:00

136 lines
11 KiB
Plaintext
Raw Permalink Blame History

---
title: Channels Overview
description: >-
Connect your LobeHub agents to external messaging platforms like Discord,
Slack, Telegram, LINE, QQ, WeChat, Feishu, and Lark, allowing users to
interact with AI assistants directly in their favorite chat apps.
tags:
- Channels
- Message Channels
- Integration
- Discord
- Slack
- Telegram
- LINE
- QQ
- WeChat
- Feishu
- Lark
---
# Channels
Channels allow you to connect your LobeHub agents to external messaging platforms. Once connected, users can interact with your AI assistant directly in the chat apps they already use — no need to visit LobeHub.
> \[!NOTE]
>
> WeChat currently requires an active subscription. If you are using the community edition without a subscription, the WeChat channel option may not appear in the Channels settings yet.
## Supported Platforms
| Platform | Description |
| ------------------------------------------ | --------------------------------------------------------------------------------------------- |
| [Discord](/docs/usage/channels/discord) | Connect to Discord servers for channel chat and direct messages |
| [Slack](/docs/usage/channels/slack) | Connect to Slack for channel and direct message conversations |
| [Telegram](/docs/usage/channels/telegram) | Connect to Telegram for private and group conversations |
| [LINE](/docs/usage/channels/line) | Connect to LINE Messaging API for direct and group chats |
| [iMessage](/docs/usage/channels/imessage) | Connect to iMessage through the local LobeHub Desktop BlueBubbles bridge (Labs) |
| [QQ](/docs/usage/channels/qq) | Connect to QQ for group chats and direct messages |
| [WeChat (微信)](/docs/usage/channels/wechat) | Connect to WeChat via iLink Bot for private and group chats (requires an active subscription) |
| [Feishu (飞书)](/docs/usage/channels/feishu) | Connect to Feishu for team collaboration (Chinese version) |
| [Lark](/docs/usage/channels/lark) | Connect to Lark for team collaboration (international version) |
## How It Works
Each channel integration works by linking a bot account on the target platform to a LobeHub agent. When a user sends a message to the bot, LobeHub processes it through the agent and sends the response back to the same conversation.
- **Per-agent configuration** — Each agent can have its own set of channel connections, so different agents can serve different platforms or communities.
- **Multiple channels simultaneously** — A single agent can be connected to Discord, Slack, Telegram, LINE, QQ, WeChat, Feishu, and Lark at the same time. LobeHub routes messages to the correct agent automatically.
- **Secure credential storage** — All bot tokens and app secrets are encrypted before being stored.
## Getting Started
1. Navigate to your agent's settings and select the **Channels** tab
2. Choose a platform and follow the setup guide:
- [Discord](/docs/usage/channels/discord)
- [Slack](/docs/usage/channels/slack)
- [Telegram](/docs/usage/channels/telegram)
- [LINE](/docs/usage/channels/line)
- [QQ](/docs/usage/channels/qq)
- [WeChat (微信)](/docs/usage/channels/wechat)
- [Feishu (飞书)](/docs/usage/channels/feishu)
- [Lark](/docs/usage/channels/lark)
If you do not see **WeChat** in the channel list, check that your account has an active subscription first.
## Feature Support
Text messages are supported across all platforms. Some features vary by platform:
| Feature | Discord | Slack | Telegram | LINE | QQ | WeChat | Feishu | Lark |
| ---------------------- | ------- | ----- | -------- | ------- | --- | ------ | ------- | ------- |
| Text messages | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Direct messages | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Group chats | Yes | Yes | Yes | Yes | Yes | Yes | Yes | Yes |
| Reactions | Yes | Yes | Yes | No | No | No | Partial | Partial |
| Image/file attachments | Yes | Yes | Yes | Inbound | Yes | Yes | Yes | Yes |
## Allowed Users (global)
The **Allowed Users** list at the top of **Advanced Settings** is a *global* user gate. When populated, only the listed users can interact with the bot — in DMs **and** in group `@mentions` — regardless of DM Policy or Group Policy mode. Leave it empty to disable user-level filtering and let per-scope policies decide on their own.
Behaviour when populated:
| Surface | Non-allowlisted sender |
| ---------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **DM** | Blocked. Sender receives a one-line "you aren't authorized to send direct messages" notice in the same DM. |
| **Group / channel @mention** | Blocked. A short "you aren't authorized to interact with this bot" notice is posted in the same thread the @-mention arrived on (on Discord this is the auto-created reply thread, not the parent channel). |
Add one entry per row. Each row holds a platform user ID (required) and an optional **Note** — a private label that's only ever shown back to you on the settings page. The note is what saves you from having to remember whether `U01ABCXYZ` was Alice or the on-call account six months from now; the runtime ignores it entirely.
> **Anti-lockout**: if you have **Your Platform User ID** set (the AI-tools field), that ID is implicitly trusted by the global allowlist. Forgetting to add yourself to **Allowed Users** when scoping the bot to friends won't lock you out.
## Direct Message Policy
DM Policy only governs DMs — group `@mentions` are gated independently by **Group Policy** below. The user-level filter from the global **Allowed Users** is also applied; per-scope policy stacks on top.
| Policy | Behavior |
| ------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Open** | Any user on the platform can DM the bot (subject to the global allowlist when set). Best for public-facing assistants. |
| **Allowlist** | DMs require the sender to be in **Allowed Users**. Distinct from `Open` only when the list is empty: `Allowlist` then **fails closed** (no DMs); `Open` still lets anyone DM. |
| **Pairing** | Same gate as `Allowlist`, but a non-listed sender receives a one-time pairing code instead of a flat rejection. The owner approves via `/approve <code>`, which appends the applicant to **Allowed Users** so future DMs flow normally. Requires **Your Platform User ID** and a configured Redis. |
| **Disabled** | The bot ignores all DMs entirely. Use this when the bot should only reply in shared channels via `@mention`. |
## Group Policy
For the same group-capable platforms, each channel has a **Group Policy** that controls where the bot responds to `@mentions`. This is independent of DM Policy: a `groupPolicy=disabled` bot still accepts DMs (subject to DM Policy), and vice versa.
| Policy | Behavior |
| ------------- | ---------------------------------------------------------------------------------------------------------------------- |
| **Open** | Respond to `@mentions` in any group, channel, or thread the bot can read. Default. |
| **Allowlist** | Respond only when the channel / group / chat ID is in **Allowed Channels**. Use to scope a bot to specific workspaces. |
| **Disabled** | Ignore all non-DM traffic. The bot becomes DM-only. |
When **Allowlist** is selected, **Allowed Channels** appears as a row editor — one entry per channel / group / chat ID, with an optional note (e.g. `#general`) shown only to you so you can recognise each ID later.
> **Discord parent channels**: an `@mention` in a Discord channel automatically spawns a reply thread, so the inbound thread ID is *not* what Discord's "Copy Channel ID" gives you. You can paste the **parent channel ID** here — the bot accepts any auto-created reply thread under it. Pasting a specific thread ID instead works too, in which case only that thread is allowed.
### Per-platform defaults
Every supported platform defaults to **Open** for both policies so the bot stays reachable out of the box. Tighten per-channel via **Allowlist** or **Disabled** when you want a private bot. WeChat does not expose these settings because the WeChat integration is DM-only by design.
### Finding a user's platform ID
- **Discord** — Enable Developer Mode in user settings, right-click the user, and choose **Copy User ID**.
- **Slack** — Open the user's profile → click the `⋮` menu → **Copy member ID** (starts with `U`).
- **Telegram** — Ask the user to message [@userinfobot](https://t.me/userinfobot), or read `from.id` from the bot's incoming update.
- **QQ** — Use the `openid` from the OpenAPI event payload — `user_openid` for private (C2C) messages, `member_openid` for group messages (the public-facing QQ number is not guaranteed to be the platform ID).
- **Feishu / Lark** — Use the `open_id` from the event payload, or the **User ID** displayed in the developer portal.
### Finding a channel / group ID
- **Discord** — Enable Developer Mode, right-click the channel, and choose **Copy Channel ID**.
- **Slack** — Open the channel's About panel and copy the channel ID at the bottom (starts with `C`).
- **Telegram** — Forward a message from the group to [@userinfobot](https://t.me/userinfobot), or read `chat.id` from the bot's incoming update (group IDs are negative).
- **Feishu / Lark** — Use the `chat_id` from the event payload.
Reference in New Issue View Git Blame Copy Permalink