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

# Deploy a Chat agent with Infobip SMS

> Host a text relay between Infobip and a Voiceflow Chat agent.

## Overview

This developer-led walkthrough connects **SMS API v3 with HTTP forwarding** to an existing Voiceflow Chat agent. Your server receives customer texts, selects the intended agent session, sends the text to Voiceflow, then delivers the answer through Infobip. You host and maintain the relay; a provider send action alone does not establish this conversation path.

**Note:** 

**Managed alternative:** [Voiceflow SMS](/docs/guides/channels/sms/voiceflow) hosts the two-way channel for connected Twilio numbers. This page teaches the Infobip relay.

<a id="prepare-provider"></a>

## Before you begin

Prepare the agent, provider account and relay host.

An Infobip long number or verified toll-free number with inbound SMS, access to **Channels and Numbers**, and an approved numeric sender. A shared trial sender such as InfoSMS cannot receive a customer reply for this route.

| Owner | Required input |
| --- | --- |
| Voiceflow owner | An existing [Chat agent](/docs/documentation/build/overview), a **published test Environment**, its alias, project ID and project runtime API key. Prepare approved text answers and a fallback. |
| Provider administrator | The number, account permissions and the SMS API v3 with HTTP forwarding configuration below. Verify country coverage and sender registration before testing. |
| Backend operator | A server with Docker Engine and Compose, a domain you control, DNS pointed at the server, inbound ports 80/443 and outbound HTTPS. Use one relay process and its persistent volume. |
| Tester | A separate phone that expects the messages, a known answer and a follow-up question. |

Examples use 🇺🇸 US `+14155550100` as the business number and `+12025550123` as the customer. Replace these fictional numbers with your controlled, eligible numbers. Use the provider’s required international representation at its boundary; the relay stores normalized E.164.

This sample handles incoming-first **text support**, one provider and one business number per deployment. It returns text traces, suppresses the launch greeting, and sends one answer of at most 640 UTF-16 units. It does not implement MMS, rich controls or human agent hand-off. Review [Chat agents](/docs/api-reference/agent-runtime/chat) before extending those behaviors.

<a id="host-relay"></a>

## Host the relay

Install the server and connect its persistent store and credentials.

### 1. Download the runnable relay

Download the [SMS relay archive](/docs/examples/sms-relay/sms-relay.zip) and unpack it on the host:

```sh
unzip sms-relay.zip -d sms-relay
cd sms-relay
cp .env.example .env
chmod 600 .env
```

The archive includes the server, provider adapters, SQLite worker, pinned dependency lock, Docker/HTTPS configuration and offline tests. The [README](/docs/examples/sms-relay/README.md) owns the shared operations and recovery commands.

### 2. Configure the agent and secrets

Edit `.env`: set `PROVIDER=infobip`, `SMS_DOMAIN` to your domain, `PUBLIC_ORIGIN` to its HTTPS origin without a trailing slash, and `SMS_FROM` to the owned E.164 business number. Set `VF_PROJECT_ID`, `VF_ENVIRONMENT` and `VF_API_KEY` to the published test Chat Environment and its runtime key. These are server secrets, never browser inputs.

Generate **two separate** random values with the following command, putting one in `IDENTITY_SECRET` and the other in `WEBHOOK_SECRET`. Set `ROUTE_GENERATION=1`.

```sh
openssl rand -hex 32
```

Keep `IDENTITY_SECRET` stable so sender identity and local opt-out records survive restarts. Add this provider’s variables:

| Variable | Value and source |
| --- | --- |
| `INFOBIP_HOST` | Your account’s base host, such as xxxxx.api.infobip.com, without https://. |
| `INFOBIP_API_KEY` | An account API key permitted to send SMS and read SMS logs. |

Remove the unused Telnyx entries from `.env.example` when selecting another provider. AWS SDK credentials, when needed, follow the credential-chain instructions in the provider setup below.

### 3. Start and check the HTTPS receiver

Point the domain’s DNS at the host, then run:

```sh
docker compose up -d --build
docker compose logs --tail=30 relay
curl --fail https://YOUR_SMS_DOMAIN/health
```

Replace `YOUR_SMS_DOMAIN` with `SMS_DOMAIN`. Caddy obtains TLS and proxies to the private relay port. Expect `{"ok":true}` from health. Keep the `sms-data` volume: it stores message IDs, session keys, pending replies and suppression records. Do not scale this SQLite example to several processes.

Your callback URLs are `https://YOUR_SMS_DOMAIN/inbound/WEBHOOK_SECRET` and `https://YOUR_SMS_DOMAIN/status/WEBHOOK_SECRET`, substituting the actual secret value. Call these **INBOUND_URL** and **STATUS_URL** below. Do not include the literal variable names in the provider settings or enable access logs containing the secret. Do not redirect either callback URL.

<a id="connect-provider"></a>

## Connect Infobip

Save the provider’s incoming route and prepare outgoing replies.

### 1. Configure the number’s forwarding action

In Infobip, open **Channels and Numbers → SMS**, select the controlled number and edit **Inbound configuration**. Select **Forward to HTTP** (or **Forward to URL** in the corresponding interface), set method **POST**, format **JSON**, and destination `INBOUND_URL`. Save.

### 2. Remove competing handlers

Inspect keyword rules and the default inbound configuration. Ensure your intended messages forward once to this relay; forwarding rules take precedence over subscriptions. Turn off any competing generic auto-response. Keep required STOP/HELP handling intact.

### 3. Check credentials and sender

Copy the account base URL and API key into the relay. The send request uses `Authorization: App ...` and `/sms/3/messages` with a numeric `sender`. Confirm this sender is the same reply-capable business number.

This HTTP-forwarding recipe authenticates the callback using the random token in `INBOUND_URL` over HTTPS, then checks the destination against `SMS_FROM`. It does not claim a signed Infobip event. Keep the URL out of logs; rotate its token in both systems if exposed. For an account requiring subscription signing, implement that subscription’s verified contract before changing the route.

<a id="map-conversations"></a>

## Map messages and sessions

Keep the sender, agent release and reply direction consistent.

| Boundary | Mapping |
| --- | --- |
| Event ID | `results[].messageId` |
| Customer → business / text | `results[].from` → `to`; `text` |
| Reply | `POST https://{account-host}/sms/3/messages`: `messages[].sender`, `destinations[].to`, `content.text` |
| Acceptance | Retain `messages[0].messageId` and its status group |

| Event | Relay behavior |
| --- | --- |
| First customer text | Commits the inbound ID, creates a v4 session in the explicit published Environment, launches it, then sends the customer’s text. |
| Follow-up | Reuses the stored session token for the provider/business/customer combination; the user ID is a keyed hash, not a raw phone number. |
| Duplicate / restart | Duplicate inbound IDs do not rerun the turn. Queued work survives restarts; interrupted turns/sends become `uncertain` and need operator review. |
| End / expiry | An `end` trace clears the local token. A definite session `404` creates a replacement once; a timeout never automatically replays a turn. |
| STOP / START / HELP | The relay bypasses the agent for these keywords and keeps a local suppression record. Configure the provider’s required keyword responses; the sample does not send its own compliance response. |
| Non-text / hand-off | No fabricated SMS reply: missing text, oversized answers or a hand-off trace hold the job for review. This sample does not deliver later help-desk messages. |

The server calls `POST /v4/project/{projectID}/environment/{alias}/session` with the runtime API key, then `POST /v4/interact` with the returned session token. The [session](/docs/api-reference/v4interact/start-session-specific-environment) and [interact](/docs/api-reference/v4interact/interact-non-stream) references own the full contracts. This route uses the Environment’s Published release; compiling a Draft alone does not release it. Transcripts identify these relay sessions as API conversations.

<a id="test-provider"></a>

## Test a customer conversation

Verify the real incoming text, agent session and delivered reply.

### 1. Run the offline checks

Before installing real provider credentials, run the archive’s tests with Node 22.13 or later:

```sh
npm ci --ignore-scripts
npm test
```

These tests use synthetic provider events and mocked agent/sender responses. They check mappings, signatures, duplicate handling and restart behavior without sending a message. They do not establish live provider acceptance.

### 2. Send the known question and follow-up

From your separate phone, text “What are your collection hours?” to the Infobip business number. Expect the prepared answer, for example “Northstar collection hours are 10 am to 6 pm.” Reply “Are you open at noon?” and check that the answer uses the same conversation. Inspect the intended project’s [Transcripts](/docs/documentation/measure/transcripts). Confirm no launch greeting is sent separately.

### 3. Compare ingestion, sending and receipt

Inspect `docker compose logs relay` for the hashed job ID and `phase:"accepted"`, then use the retained provider ID/reference to find the outgoing message. Confirm its sender is the business number, its recipient is the customer, and the phone receives one answer per turn.

The adapter requires a message ID and `status.groupName:"PENDING"`; inspect other responses as unresolved. Check the corresponding message in Infobip logs/reports and the actual handset for delivery. HTTP `200` can still contain an application-level failure.

### 4. Exercise continuity and recovery

Send a new question after restarting only the relay container; the stored session should continue. On a controlled recipient, test the configured STOP/START/HELP route and verify STOP prevents an agent send. Re-submit a captured **authorized synthetic fixture** only to a local/offline test receiver to check duplicate behavior; do not replay a production callback, which can trigger paid messages. Test a second customer to confirm their context remains separate.

### The provider has the text but the relay has no job

Check the saved incoming route, callback authorization and payload family.

Check the provider configuration against this manual, including number ownership, active subscription/application and exact URL. Inspect provider callback errors and relay container health. A `401` indicates callback authorization; a `400` indicates malformed incoming fields or the wrong schema; a temporary `503` means the local store could not commit. Other event types are acknowledged with `200` without creating a conversation, so verify an incoming job in the ledger as well as the callback status. Keep the provider’s event ID and timestamp. Fix the saved configuration before sending another controlled text.

### The relay records uncertain or held work

Resolve the original remote outcome before allowing another attempt.

Inspect the job with the README’s `inspect` command, the corresponding Transcript and provider log. An agent tool or send might have succeeded before its response was lost. The worker does not automatically retry this job and holds later messages for that conversation. Resolve the original outcome, then use the explicit recovery command; never clear the database to force a resend.

### The provider accepts the reply but the phone gets nothing

Check delivery evidence, sender eligibility and recipient suppression.

Find the exact outgoing ID/reference in the provider log, inspect final delivery status and errors, and confirm the destination, sender registration, balance, country permissions and opt-out state. An accepted request is not a delivery receipt. If the account rewrites the sender, correct its two-way routing before launch.

<a id="release-provider"></a>

## Release and maintain the channel

Cut over the provider number and the published agent together.

### 1. Release the reviewed agent and relay

[Publish](/docs/documentation/deploy/environments/publishing) the reviewed Chat Environment. Stop inbound routing temporarily or schedule the cutover, let queued work drain, and back up the persistent volume. Set the final `VF_PROJECT_ID`/`VF_ENVIRONMENT` and increase `ROUTE_GENERATION` to start fresh sessions on this deployment configuration. Recreate the relay container with `docker compose up -d`. The program refuses a route change while old queued jobs remain.

### 2. Verify the production route

Repeat the [known question and follow-up](#test-provider) through the final Infobip number. Check the Published instructions, provider sender, destination and final delivery evidence. Keep the earlier route ready until this acceptance succeeds.

### Update or disconnect the relay

Coordinate secrets, provider routing and the persistent message ledger.

Rotate a provider credential in `.env`, recreate the container and repeat the customer test. Rotate a webhook token/signing secret with the provider endpoint in the same change window. Keep `IDENTITY_SECRET` and the persistent volume stable; replacing them resets local sender identity and suppression history.

To stop this channel, disable the provider’s route/subscription first, then stop the worker after queued jobs drain. Restore the recorded prior provider route if required. Keep the volume/backup according to your data-retention policy; `docker compose down -v` deletes the message ledger and is not a recovery step. Number release and billing cancellation remain provider-account actions.
