Overview
Let server members ask a Voiceflow agent questions with /ask question. This walkthrough uses signed HTTP interactions and private command replies; it does not read ordinary channel messages or direct-message text.
Before you begin
Collect the agent, account and host access.
The example provides public-policy text support. Keep private Voiceflow and platform credentials on the host; a customer’s messaging identity does not authorize access to orders or account records. Have the agent return text only and provide a support route in its instructions. Buttons, audio and Handoff traces need additional adapters; see Adapt agent replies.
Prepare the platform account
Create the exact app or account this relay will use.
Create the application
In the Discord Developer Portal, create an application. Copy its Application ID and Public Key from General Information. In Bot, generate the bot token and keep it private; it is used to register commands, while inbound verification uses the public key.
Install it in a test server
Configure a Guild Install with applications.commands and bot scopes, using the installation link from the portal. Have a server administrator authorize it. This command recipe needs no Message Content privileged intent and no passive message subscriptions. Retain the server ID from Discord’s developer mode for fast guild-command testing.
Run the relay
Configure and host the supplied executable example.
Use the configuration file for this platform. Every name below is read by the supplied artifact; IDs identify the resources prepared above. VF_ENVIRONMENT is the Environment alias, not a version label pasted from another project.
Download and configure the relay
On a Linux host you administer, create /opt/voiceflow-messaging and extract the relay archive there. Use Node.js 22.12 or later. Run node --test fixtures.test.mjs first: it generates signed synthetic events and mocks all remote calls, without credentials or live messages. Save the configuration above as .env, replacing every YOUR_ value; restrict it to the service account with chmod 600 .env. Set DATA_DIR to a private persistent directory that this account can write.
The archive includes core.mjs, platform adapters, HTTP/Teams entry points, local fixture tests and a package manifest. Run node --env-file=.env relay.mjs serve. The HTTP relay uses only Node built-ins; it does not need npm install.
Expose the HTTPS endpoint
Point your own DNS hostname to the host. Terminate HTTPS with a valid public certificate and proxy to 127.0.0.1:8080. For example, with Caddy installed:
Replace the example hostname, allow inbound 80/443 for certificate provisioning and keep the relay port private. Use a separate hostname and credentials for testing. Confirm https://YOUR_HOST/health returns ok before registering /webhook.
Keep one process running
After the foreground check, stop it and create a service using the unit below. Keep one process and one writable data directory per installation. Do not run this file store on ephemeral serverless storage or start multiple replicas.
Create the non-login relay service user, give it read access to the application and .env, and ownership of /var/lib/voiceflow-messaging. Confirm /usr/bin/node --version is 22.12 or later, or substitute your actual Node path. Then run sudo systemctl daemon-reload and sudo systemctl enable --now voiceflow-messaging. Expect the service to stay active; keep the HTTPS proxy running through its own service.
The file store is a small single-process starting point. Back it up privately and monitor disk space, queue age and failures. Higher traffic needs a transactional inbox/outbox and per-conversation workers before adding replicas. Session keys and customer text are stored in the data directory; apply your retention and access policy there as well as in Voiceflow.
Register incoming events
Connect the platform to your hosted endpoint.
With the relay running, save https://YOUR_HOST/webhook as the app’s Interactions Endpoint URL. Discord sends a signed PING; expect the URL to save successfully. The relay verifies Ed25519 over the timestamp plus raw body and returns type: 1 for that challenge.
Add DISCORD_BOT_TOKEN and DISCORD_GUILD_ID to .env, then register a guild command:
Expect an object with the command ID. This POST adds or updates this named command without replacing unrelated commands. Use Discord’s interaction contract for the request and response shapes.
Route conversations and replies
Keep the customer, agent session and reply destination aligned.
The relay hashes platform, destination account, customer/thread, project and Environment into a bounded Voiceflow userID. It creates a session with the private project key, stores the returned sessionKey, launches once, then sends { action: { type: "text", payload: text } } to /v4/interact. Text traces become platform replies. Follow-ups reuse the key; starting a session every message would reset the conversation.
Discord requires the initial acknowledgment within three seconds. The relay saves the event and immediately defers; it must edit the answer before the 15-minute interaction token expires. The sample uses a 14-minute deadline and 1900-character chunks, with automatic mentions disabled.
The answer is visible to the invoking user, but the /ask input and surrounding server context must still be treated according to that server’s privacy policy. This does not establish a private support inbox. App distribution, verification and command permissions remain separate from creating a test-server command.
Passive bot messages: Discord’s Gateway can deliver ordinary message events with the relevant intents. That is a different implementation with persistent socket and intent requirements; it is not included in this slash-command walkthrough.
Test a customer conversation
Verify the reply in the destination you installed.
Send a real platform message
In the test server, run /ask question: What is your return policy?. Expect a deferred private response followed by the answer visible to the invoking user.
Check continuity and isolation
Ask a related follow-up, then test with a second authorized customer. Confirm the intended Voiceflow project and exchange in Transcripts. Run node --env-file=.env relay.mjs inspect while the service is stopped to compare event IDs, conversation keys and completion states without printing session tokens.
Check this platform’s delivery behavior
Run another /ask in the same channel with a follow-up, then invoke it as a second member. Context must continue only for the first member. Do not test by posting plain channel text.
A saved callback, accepted API request or successful Voiceflow Run does not prove this platform conversation. Keep local signed-fixture tests separate from this authenticated customer test.
The callback saves but no reply arrives
Check platform access as well as endpoint connectivity.
If the endpoint will not save, check its public key, raw-body handling, PING response and certificate. “Unknown interaction” commonly means the initial three-second acknowledgment or reply-token deadline was missed.
A conversation is paused or a reply is duplicated
Reconcile remote effects before resuming the saved job.
Inspect the event’s phase, failedDuring, saved traces and accepted chunks in the private data file. A runtime timeout can occur after a tool action; a send timeout can occur after the platform accepted the message. The sample pauses that conversation and does not retry either effect automatically. Follow Recover failed messages, then repeat the platform test.
Release and maintain the connection
Promote the tested route and keep recovery available.
Approve the production destination
Register the same command as a global command by using /applications/{app-id}/commands instead of the guild path, then test it in the intended installed context. Complete any distribution/verification requirements for your app; remove the test guild command only after the global command is available.
Release the reviewed agent
Have the Voiceflow owner publish the tested agent to the intended Environment. Deploy that alias and production credentials to the relay, restart its service and repeat the customer test with a fresh customer/session. Existing session keys are not an automatic migration to a new release. Keep the previous deployment and state backup available for rollback.
Rotate, update or disconnect
Maintain both the provider registration and the relay state.
Stop the service before changing .env or running maintenance commands. Rotate the platform credentials using its administrator controls, update the secret file and restart. If a webhook secret changes, update both sides and check a real event. For a release change, drain or reconcile pending jobs first; do not erase the state file to resolve a delivery problem.
To disconnect, disable/remove this callback or uninstall this app in the provider, stop the relay and revoke its unused credentials. Confirm no new events arrive and retain/delete customer state according to your policy. Keep the registration details needed to reconnect. See Pause automated replies for a temporary conversation-specific pause.