> ## Documentation Index
> Fetch the complete documentation index at: https://docs.wolffi.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Telegram Channel

> Connect Wolffish to Telegram as a personal bot

# Your Personal Telegram Bot

The Telegram channel turns Wolffish into a personal bot that responds to your private messages. Same brain, same capabilities, accessible from any device with Telegram installed.

## Setup

<Tabs>
  <Tab title="Step 1: Create Bot">
    Open Telegram and message [@BotFather](https://t.me/BotFather):

    ```
    /newbot
    ```

    Follow the prompts to name your bot. BotFather will give you a token like:

    ```
    7123456789:AAHdqTcvCH1vGWJxfSeofSAs0K5PALDsaw
    ```

    Copy this token.
  </Tab>

  <Tab title="Step 2: Configure Wolffish">
    In Wolffish, open **Settings > Telegram** and paste your bot token. Click **Connect**.

    Wolffish will verify the token and confirm the connection. Your bot is now live.
  </Tab>

  <Tab title="Step 3: Start Chatting">
    Open your bot in Telegram (search for its username) and send any message. Wolffish will respond through the same brain pipeline as the desktop UI.
  </Tab>
</Tabs>

<Warning>
  Keep your bot token secret. Anyone with the token can receive messages sent to your bot. If compromised, revoke it via BotFather with `/revoke` and reconfigure in Wolffish.
</Warning>

## Commands

The bot recognizes these slash commands:

| Command    | Action                                      |
| ---------- | ------------------------------------------- |
| `/stop`    | Cancel the currently running task           |
| `/new`     | Start a fresh conversation                  |
| `/resume`  | Continue the previous conversation          |
| `/delete`  | Delete the current conversation             |
| `/current` | Show which conversation is active           |
| `/status`  | System report (model, memory usage, uptime) |
| `/local`   | Switch to local model (Ollama)              |
| `/cloud`   | Switch to cloud model (Claude/OpenAI)       |

## Approval Flow

When the amygdala flags a tool call as potentially dangerous, Wolffish sends an inline keyboard in Telegram:

```
Wolffish wants to execute:
  shell_exec: rm -rf ./build/

[Approve] [Deny]
```

Tap **Approve** to proceed or **Deny** to abort. The turn pauses until you respond — no timeout, no automatic approval.

<Info>
  Approval requests include the full tool name and arguments so you can make an informed decision. Dangerous commands (file deletion, network calls, system modifications) always require approval.
</Info>

## Conversation Management

Each Telegram chat maps to a Wolffish conversation. The mapping is:

* **Private chat with your bot** = one conversation thread
* Use `/new` to start fresh (previous conversation is preserved in memory)
* Use `/resume` to return to the last active conversation
* Use `/delete` to remove the current conversation from history

Conversations are shared across channels. A conversation started in Telegram appears in the Electron UI's conversation list, and vice versa.

## File Handling

The bot can receive and process:

* **Images** — screenshots, photos, diagrams (processed via vision capabilities)
* **Documents** — PDFs, text files, code files (content extracted and passed to the brain)
* **Voice notes** — transcribed via STT and processed as text input

Send a file with or without a caption. If you include a caption, it becomes the user message with the file as context. If no caption, Wolffish infers intent from the file content.

## Response Formatting

Wolffish formats responses using Telegram's HTML subset:

```html theme={null}
<b>bold</b>
<i>italic</i>
<code>inline code</code>
<pre>code block</pre>
<a href="url">link text</a>
```

Long responses are split at logical boundaries (paragraph breaks, list items) to stay within Telegram's message length limits. Code blocks are preserved intact where possible.

## Verbose Task Results

By default, Telegram receives a **clean feed** — the agent's replies, any files it produces, and errors. The step-by-step tool activity stays in the desktop UI so your chat doesn't fill up with internal steps.

Toggle this in **Settings → Channels → Telegram → Verbose task results**:

* **Off (default)** — agent messages, file-bearing results, and errors only.
* **On** — every tool call, result, and activity is relayed to the chat as it happens.

<Note>
  Verbose changes only what is **sent** to Telegram. The full turn — every tool call and result — is still saved to history and memory regardless of the setting.
</Note>

## Under the Hood

The Telegram channel is built on the [grammy](https://grammy.dev/) library — a modern, TypeScript-first framework for building Telegram bots. Grammy handles:

* Long polling for message updates
* Inline keyboard management for approvals
* File upload/download
* Message formatting and splitting
* Error recovery and reconnection

## Sensitive Data Filter

Wolffish includes an optional filter that discards messages containing credentials before they reach the agent. It is **off by default** — discussing secrets is a legitimate part of many workflows (setting up integrations, debugging auth, rotating keys).

**Enable it:** Settings → Wolffish → Block sensitive data in messages

When enabled, any incoming message matching a credential pattern is immediately discarded in its entirety. The turn does not process, nothing is stored, and the user receives a short notification. This applies equally to Desktop, Telegram, and WhatsApp.

**Patterns detected:** passwords (`password:`, `my password is...`), API keys (`api_key:`, `secret_key:`), access tokens (`access_token:`, `bearer_token:`), SSH/RSA/PGP private keys (`-----BEGIN PRIVATE KEY-----`), private key phrases (`private_key:`, `ssh_key:`).

<Note>
  When the filter is off (default), messages are processed normally regardless of content. If you work with credentials frequently, this is expected behavior — store secrets in Settings → Variables instead of pasting them in chat.
</Note>