Tab: Channels

The Channels tab connects an instance to messaging surfaces. Four channels are configurable here: Telegram, Slack, WhatsApp (via Twilio), and the in-process Agent channel. Each has its own card with sensitive fields hidden behind password-style inputs.

For step-by-step setup of each provider (BotFather, Slack app, Twilio sandbox), see Connect a Channel. This page is the field reference.

What you need

Open Telegram, message @BotFather, run /newbot. Follow prompts.
Save the bot token that BotFather hands back. It looks like 123456789:ABCdef....

Fields on the Channels tab

Bot Token (sensitive) — the BotFather token.
Allowed User IDs — a comma-separated list of Telegram numeric user ids. When set, the bot only replies to those users; everyone else is silently ignored. Leave blank to accept everyone.

Starting

Save, then click Start channel. Within seconds the engine logs “Telegram channel started for instance <slug>” and your bot is live. Test by messaging it from your own Telegram account.

Capabilities

Text, photos, documents, audio (transcribed by Deepgram if configured, otherwise ignored).
The fragmented-burst coordinator (see “The fragmented-burst coordinator” below) coalesces multiple quick messages into one pipeline run.

Slack

What you need

A Slack app with Socket Mode enabled. Required scopes:

chat:write
app_mentions:read
im:history
im:write
users:read

Socket Mode means the engine connects out to Slack — no public webhook required.

Fields on the Channels tab

Bot Token (sensitive) — starts with xoxb-.
App Token (sensitive) — starts with xapp-. Required for Socket Mode.
Signing Secret (sensitive) — the app’s signing secret. Required by the form schema (older drafts of the docs marked it optional — it is not). The secret is used to verify request signatures on Slack interactivity callbacks and to power DM/mention resolution (the adapter looks up users by id and opens DMs on demand).

Starting

Save, click Start channel. The engine opens a WebSocket to Slack. Test by @-mentioning the bot in any channel it has been invited to, or by DMing it directly.

Capabilities

Threaded replies in channels (@-mentions create or continue a thread).
DMs.
Text-only inbound (the Slack adapter ignores files[] payloads — uploaded images, documents, and voice clips are dropped). Attachments are supported only on Telegram and WhatsApp.
Tools like slackPostMessage can target specific channels (#general, channel id, or user id), and are not bound to the inbound channel — a conversation that started on WhatsApp, web, or a webhook trigger can fan out to Slack as long as the instance has Slack configured here. See Tool catalog → Messaging for the full contract, including the optional slack_allowed_channels allowlist.

WhatsApp (via Twilio)

What you need

A Twilio account with the WhatsApp sandbox or a production WhatsApp Business number, plus an inbound webhook configured to point at https://<your-base-url>/webhooks/twilio/<instanceSlug>/whatsapp (served by twilio-webhook.controller.ts).

Fields on the Channels tab

Account SID — Twilio account SID.
Auth Token (sensitive) — Twilio auth token.
WhatsApp Number — whatsapp:+14155238886 for the sandbox, or your production number.

Starting

Save and Start channel. WhatsApp does not “start” in the same sense as Telegram or Slack — there is no socket. What “start” actually does is register the instance to listen on its webhook route. Stopping the channel deregisters the route.

Capabilities

Text, images, audio (Deepgram transcription if configured), documents.
“Typing…” indicator (Twilio’s Indicators/Typing.json API): triggered ~1.5 s after the first fragment of a burst, expires after 25 s or on reply.
Pre-approved templates via send_whatsapp_template.

Agent (in-process)

The Agent channel is a virtual, in-process adapter (packages/engine/src/channels/adapters/agent.adapter.ts) that lets one instance invoke another from inside its own tool loop — no network hop, no external credentials.

What it does

When the Agent channel is enabled on an instance, that instance becomes reachable as a callee from every other instance via a synthetic tool named ask_<slug> (e.g. ask_support_bot). The caller passes a free-form question; the callee runs a full supervisor cycle on a fresh conversation scoped to the calling instance, and returns the final assistant message as the tool result.

Fields on the Channels tab

Enabled — master switch. There are no credentials: enabling it simply publishes the ask_<slug> synthetic tool to every other instance in the same engine.

Notes

Agent-to-agent calls inherit the caller’s auth context (Phase 2 RBAC will scope this).
Conversations spawned through the Agent channel use the conversation id pattern agent:<callerSlug>:<timestamp> and are visible in the Conversations screen like any other.
External agent-to-agent (over the network) is tracked separately in issue #114.

Stopping channels

Each channel card has a Stop channel button. Stopping unhooks the adapter; the next inbound message is dropped (Telegram, Slack) or returns a 404 (WhatsApp webhook). Conversation state is preserved — restarting the channel resumes where it left off.

Multi-channel behavior

A single instance can have all three channels running at once. Each conversation is scoped to a (instanceId, channel, externalUserId) triple, so the same end-user talking to the same bot via Telegram and via Slack has two independent conversations and two independent memories.

The fragmented-burst coordinator

WhatsApp and Telegram users often split a single thought across two or three quick messages:


hey
do you have time
to look at the spreadsheet?

Without coordination, the engine would launch three separate pipelines. Instead, the inbound message coordinator waits for a 2-second silence (the softDebounceMs default) before firing. Fragments that arrive after the pipeline has started abort the in-flight run and re-arm the timer, up to MESSAGE_MAX_RESTARTS (default 3) consecutive cancels. Beyond that, fragments accumulate and are flushed in a follow-up run.

The user sees one thoughtful answer instead of three scattered ones.

The coordinator is off for Slack and the OpenAI-compatible API (where messages are already complete units).