Skip to main content

Documentation Index

Fetch the complete documentation index at: https://koreai.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

​
Channels

Channels connect your deployed agents to the platforms where your users interact — websites, messaging apps, and voice calls. Agent Platform provides channel adapters that handle the protocol-specific details so your agent definition works across all channels without modification. This guide covers deploying a web chat widget, connecting to Slack, WhatsApp, and voice, and using rich content and file attachments across channels.

​
Deploy on Web

Deploy your agent on a website using the ABL Web SDK to embed a chat widget that connects to your deployed agent.

​
Create an SDK Channel

Create a web SDK channel for your project. This generates the API key and configuration needed for the widget. 
curl -X POST https://your-platform/api/projects/$PROJECT_ID/sdk-channels \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Website Chat",
    "channelType": "web",
    "config": {
      "mode": "chat",
      "position": "bottom-right",
      "welcomeMessage": "Hi! How can I help you today?",
      "placeholderText": "Type a message...",
      "chatEnabled": true,
      "voiceEnabled": false,
      "theme": {
        "primaryColor": "#4F46E5",
        "fontFamily": "Inter, sans-serif"
      }
    }
  }'
The response includes a publicApiKeyId. Generate an embed token for the widget.

​
Generate an Embed Token

curl -X POST https://your-platform/api/projects/$PROJECT_ID/sdk-channels/$CHANNEL_ID/token \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "ttlSeconds": 2592000
  }'
The response includes the token and apiKey you embed in your website.

​
Add the Widget to Your Website

Add the SDK script tag and initialization code to your HTML page. 
<!doctype html>
<html>
  <head>
    <title>My Website</title>
  </head>
  <body>
    <!-- Your page content -->

    <!-- ABL Chat Widget -->
    <script src="https://your-platform/sdk/widget.js"></script>
    <script>
      ABL.init({
        apiKey: 'your-api-key',
        projectId: 'your-project-id',
        position: 'bottom-right',
        theme: {
          primaryColor: '#4F46E5',
        },
      });
    </script>
  </body>
</html>
The widget renders a chat button in the configured position. When clicked, it opens the chat interface connected to your deployed agent.

​
Voice-Enabled Widget

Enable voice input alongside chat. 
ABL.init({
  apiKey: 'your-api-key',
  projectId: 'your-project-id',
  chatEnabled: true,
  voiceEnabled: true,
  voiceConfig: {
    language: 'en-US',
    autoDetectLanguage: true,
  },
});

​
Restrict to Specific Domains

Lock the SDK key to specific origins to prevent unauthorized embedding. 
curl -X PATCH https://your-platform/api/projects/$PROJECT_ID/sdk-channels/$CHANNEL_ID \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "config": {
      "allowedOrigins": [
        "https://www.example.com",
        "https://app.example.com"
      ]
    }
  }'
Requests from origins not in the list receive a 403 Forbidden response.

​
Pass User Context

Identify authenticated users by passing context at initialization. 
ABL.init({
  apiKey: 'your-api-key',
  projectId: 'your-project-id',
  user: {
    id: 'user-123',
    name: 'Jane Smith',
    email: 'jane@example.com',
    metadata: {
      plan: 'premium',
      accountAge: 365,
    },
  },
});
User context is available to your agent via session variables and persistent memory lookups.

​
Target a Specific Deployment

Direct the SDK to use a specific deployment (e.g., staging vs. production). 
curl -X PATCH https://your-platform/api/projects/$PROJECT_ID/sdk-channels/$CHANNEL_ID \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "deploymentId": "deploy-abc123",
    "environment": "production"
  }'

​
Troubleshooting

  • Widget does not appear: Verify the script URL is correct and the apiKey is valid. Check the browser console for errors.
  • “Invalid or expired API key” error: The API key may have been rotated or the SDK channel deactivated. Generate a new token.
  • CORS errors: Add your website’s origin to the allowedOrigins list in the SDK channel configuration.
  • Widget loads but no response from agent: Verify that a deployment is active for the project. The SDK channel must be linked to an active deployment.

​
Set Up Slack

Connect your agent to Slack so users can interact with it directly in Slack channels and direct messages.

​
Create a Slack App

  1. Go to api.slack.com/apps and select Create New App > From scratch.
  2. Name your app and select the workspace.
  3. Under OAuth & Permissions, add these bot token scopes:
    • chat:write — send messages
    • app_mentions:read — respond to @mentions
    • im:read, im:write — direct messages
    • files:read — read file attachments (if your agent handles attachments)
  4. Install the app to your workspace. Copy the Bot User OAuth Token (xoxb-...).
  5. Under Basic Information, copy the Signing Secret.

​
Create a Channel Connection

Register the Slack app credentials with the Agent Platform. 
curl -X POST https://your-platform/api/projects/$PROJECT_ID/channel-connections \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "channelType": "slack",
    "name": "Production Slack",
    "credentials": {
      "bot_token": "xoxb-your-bot-token",
      "signing_secret": "your-signing-secret"
    },
    "environment": "production"
  }'
The response includes the webhookUrl. Copy it for the next step.

​
Configure the Slack Webhook

  1. In your Slack app settings, go to Event Subscriptions.
  2. Enable events and paste the webhookUrl from the channel connection response.
  3. Slack sends a verification challenge. The platform responds automatically.
  4. Under Subscribe to bot events, add:
    • message.im — direct messages to the bot
    • app_mention — @mentions in channels
  5. Save changes.

​
Slack with Threaded Replies

The platform supports threaded conversations in Slack. When a user mentions the bot in a channel, the agent responds in a thread to keep the channel clean. This is enabled by default for the Slack adapter.

​
Slack Slash Commands

Register a custom slash command that routes to your agent.
  1. In your Slack app settings, go to Slash Commands and create a new command (e.g., /ask).
  2. Set the Request URL to: https://your-platform/api/v1/channels/slack/slash/{connection-identifier}
  3. The connection identifier is the external identifier from your channel connection (format: team_id:app_id).

​
Slack with Interactive Components

If your agent uses actions (buttons, select menus), enable Interactivity in your Slack app:
  1. Go to Interactivity & Shortcuts and toggle on.
  2. Set the Request URL to the same webhook URL used for events.
  3. Interactive payloads (button clicks, menu selections) are automatically routed to your agent.

​
Multi-Workspace Slack App

For distributing your agent across multiple Slack workspaces, use the generic webhook URL (without a connection identifier). The platform extracts the workspace identifier from the event payload. 
Webhook URL: https://your-platform/api/v1/channels/slack/webhook
Create a separate channel connection for each workspace that installs the app.

​
Troubleshooting

  • “Channel not configured for this workspace” error: The channel connection’s external identifier does not match the Slack workspace. Verify the team_id:app_id matches your Slack app installation.
  • Bot does not respond to messages: Check that the Event Subscriptions URL verification succeeded (green checkmark in Slack). Verify the bot_token scope includes chat:write.
  • Signature verification fails: The signing_secret in the channel connection must match the Signing Secret from the Slack app’s Basic Information page. Secrets are case-sensitive.
  • Duplicate responses: Slack requires a response within 3 seconds. The platform queues messages and responds asynchronously. If your Slack app’s retry policy re-sends events, the platform deduplicates using event IDs.

​
Set Up WhatsApp

Connect your agent to WhatsApp so users can interact with it via WhatsApp messages.

​
Configure a WhatsApp Business API Account

Before connecting to the platform, you need a WhatsApp Business API provider account. The platform supports Meta’s Cloud API (direct) and third-party providers like Infobip and Twilio. Meta Cloud API setup:
  1. Go to developers.facebook.com and create a Meta App with WhatsApp product enabled.
  2. Under WhatsApp > Getting Started, note your Phone Number ID and WhatsApp Business Account ID.
  3. Generate a permanent System User Access Token with whatsapp_business_messaging permission.
  4. Under Configuration, note the App Secret for webhook signature verification.

​
Create a Channel Connection

Register the WhatsApp credentials with the Agent Platform. 
curl -X POST https://your-platform/api/projects/$PROJECT_ID/channel-connections \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "channelType": "whatsapp",
    "name": "Production WhatsApp",
    "credentials": {
      "access_token": "your-system-user-access-token",
      "app_secret": "your-app-secret",
      "verify_token": "a-random-string-you-choose"
    },
    "config": {
      "phoneNumberId": "your-phone-number-id"
    },
    "environment": "production"
  }'
The response includes the webhookUrl.

​
Configure the Meta Webhook

  1. In your Meta App settings, go to WhatsApp > Configuration.
  2. Under Webhook, click Edit and paste the webhookUrl.
  3. Enter the same verify_token you used when creating the channel connection.
  4. Click Verify and Save. Meta sends a GET request to verify the webhook.
  5. Under Webhook fields, subscribe to messages.

​
Infobip Provider

For WhatsApp via Infobip, use the provider-specific configuration. 
curl -X POST https://your-platform/api/projects/$PROJECT_ID/channel-connections \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "channelType": "whatsapp",
    "name": "Infobip WhatsApp",
    "credentials": {
      "access_token": "your-infobip-api-key",
      "app_secret": "your-webhook-secret",
      "verify_token": "unused-for-infobip"
    },
    "config": {
      "provider": "infobip",
      "phoneNumberId": "your-sender-number"
    }
  }'
Set the Infobip webhook URL to: 
https://your-platform/api/v1/channels/whatsapp/infobip/webhook

​
WhatsApp with Media Support

The WhatsApp adapter supports receiving images, documents, audio, and video from users. Media files are automatically downloaded and processed by the attachment pipeline. No additional configuration is needed — the adapter handles media extraction from the webhook payload.

​
WhatsApp Interactive Messages

Your agent can send interactive WhatsApp messages (buttons, lists) using the whatsapp field in rich content. 
FLOW:
  offer_options:
    REASONING: false
    RESPOND: "How can I help you today?"
      RICH_CONTENT:
        whatsapp: |
          {
            "type": "interactive",
            "interactive": {
              "type": "list",
              "body": {"text": "Choose a topic:"},
              "action": {
                "button": "Select",
                "sections": [
                  {
                    "title": "Support",
                    "rows": [
                      {"id": "billing", "title": "Billing"},
                      {"id": "technical", "title": "Technical Issue"}
                    ]
                  }
                ]
              }
            }
          }
    THEN: handle_selection

​
Troubleshooting

  • Webhook verification fails: The verify_token in the channel connection must match the value entered in the Meta webhook configuration. It is a plain string you choose, not a Meta-generated secret.
  • Messages not arriving: Verify that you subscribed to the messages webhook field in Meta’s configuration. Also check that the phone number is registered and has an active WhatsApp Business account.
  • Signature verification fails on inbound messages: The app_secret must be the Meta App Secret (from Basic Settings), not the system user access token.
  • Media messages not processed: Large media files may timeout during download. Check the attachment processing logs for the session.

​
Set Up Voice

Set up a voice channel so users can interact with your agent through phone calls, using speech-to-text and text-to-speech for natural voice conversations.

​
Jambonz Voice Setup

The platform supports voice through Jambonz (SIP gateway) and Twilio. Jambonz is the primary voice gateway. 
curl -X POST https://your-platform/api/projects/$PROJECT_ID/channel-connections \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "channelType": "jambonz",
    "name": "Voice Support Line",
    "config": {
      "provider": "jambonz",
      "welcomeMessage": "Hello! How can I help you today?",
      "voiceConfig": {
        "sttProvider": "deepgram",
        "sttLanguage": "en-US",
        "ttsProvider": "elevenlabs",
        "ttsVoice": "rachel"
      }
    },
    "environment": "production"
  }'
The response includes a SIP endpoint to point your phone number at.

​
Twilio Voice Setup

For Twilio-based voice, create a channel connection with Twilio credentials. 
curl -X POST https://your-platform/api/projects/$PROJECT_ID/channel-connections \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "channelType": "twilio_voice",
    "name": "Twilio Voice",
    "credentials": {
      "account_sid": "your-twilio-account-sid",
      "auth_token": "your-twilio-auth-token"
    },
    "config": {
      "phoneNumber": "+15551234567"
    },
    "environment": "production"
  }'
Configure the Twilio phone number’s webhook to point to the platform’s voice endpoint.

​
Add Voice-Specific Responses to Your Agent

Use VOICE blocks in your agent to provide voice-optimized output alongside text. 
FLOW:
  welcome:
    REASONING: false
    RESPOND: "Welcome to Acme Support. How can I help?"
      VOICE:
        INSTRUCTIONS: "Use a warm, professional tone. Speak at a moderate pace."

  confirm_booking:
    REASONING: false
    RESPOND: "Your booking is confirmed. Confirmation number: {{confirmation_id}}."
      VOICE:
        INSTRUCTIONS: "Read the confirmation number slowly and clearly, one character at a time."
        SSML: |
          <speak>
            Your booking is confirmed.
            Confirmation number: <say-as interpret-as="characters">{{confirmation_id}}</say-as>.
          </speak>

​
BYOC SIP (Bring Your Own Carrier)

Connect your existing SIP trunk to the platform. 
curl -X POST https://your-platform/api/projects/$PROJECT_ID/channel-connections \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "channelType": "jambonz",
    "name": "Enterprise SIP",
    "config": {
      "provider": "byoc_sip",
      "sipGateway": "192.168.1.100:5060",
      "voiceConfig": {
        "sttProvider": "deepgram",
        "ttsProvider": "elevenlabs",
        "ttsVoice": "rachel"
      }
    }
  }'

​
AudioCodes Voice Gateway

For AudioCodes VoiceAI Connect integration: 
curl -X POST https://your-platform/api/projects/$PROJECT_ID/channel-connections \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "channelType": "audiocodes",
    "name": "AudioCodes Voice",
    "config": {
      "botUrl": "https://your-platform/api/v1/channels/audiocodes/webhook"
    }
  }'

​
Browser-Based Voice (Twilio Client)

Generate a Twilio token for browser-based voice calls from your web application. 
curl -X POST https://your-platform/api/v1/voice/token \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "projectId": "your-project-id",
    "identity": "user-123"
  }'
Use the returned token with the Twilio Client SDK in your frontend: 
import { Device } from '@twilio/voice-sdk';

const device = new Device(token);
await device.register();

// Make a call
const call = await device.connect({
  params: { projectId: 'your-project-id' },
});

​
Voice with SSML

Use SSML for fine-grained control over speech output (pauses, emphasis, pronunciation). 
RESPOND: "Your account balance is ${{balance}}."
  VOICE:
    SSML: |
      <speak>
        Your account balance is
        <say-as interpret-as="currency">USD{{balance}}</say-as>.
        <break time="500ms"/>
        Is there anything else I can help with?
      </speak>

​
Troubleshooting

  • No audio in voice calls: Verify the STT and TTS providers are configured and their API keys are valid. Check the voice service health endpoint.
  • Webhook signature validation fails (Twilio): The auth_token must match the Twilio account’s Auth Token. The platform uses it to validate X-Twilio-Signature on incoming webhooks.
  • Voice responses cut off: Long text responses may exceed TTS limits. Keep voice responses concise or use SSML with <break> tags to create natural pauses.
  • SIP registration fails: For BYOC SIP, verify the SIP gateway IP and port are correct and that the gateway allows connections from the platform’s IP range.

​
Rich Content

Use rich content to send formatted responses — Markdown, Adaptive Cards, Slack blocks, carousels, and interactive elements — that adapt to each channel’s capabilities.

​
Add Rich Content to a Response

Use the RICH_CONTENT block alongside RESPOND to provide channel-specific formatting. 
FLOW:
  show_results:
    REASONING: false
    RESPOND: "Here are your search results"
      RICH_CONTENT:
        markdown: |
          ## Search Results

          | Hotel | Price | Rating |
          |-------|-------|--------|
          {{#each hotels}}
          | {{name}} | ${{price}} | {{rating}} stars |
          {{/each}}
The runtime selects the format that matches the connected channel. If a channel-specific format is not provided, it falls back to the plain text RESPOND message.

​
Adaptive Cards (Microsoft Teams)

Send rich interactive cards on Teams using the Microsoft Adaptive Cards format. 
RESPOND: "Your booking summary"
  RICH_CONTENT:
    adaptiveCard: |
      {
        "type": "AdaptiveCard",
        "version": "1.5",
        "body": [
          {"type": "TextBlock", "text": "Booking Confirmed", "size": "large", "weight": "bolder"},
          {"type": "FactSet", "facts": [
            {"title": "Hotel", "value": "{{hotel_name}}"},
            {"title": "Dates", "value": "{{checkin}} - {{checkout}}"},
            {"title": "Total", "value": "${{total}}"}
          ]}
        ]
      }

​
Slack Block Kit

Send formatted messages with Slack blocks. 
RESPOND: "Your order status"
  RICH_CONTENT:
    slack: |
      {
        "blocks": [
          {"type": "header", "text": {"type": "plain_text", "text": "Order Status"}},
          {"type": "section", "fields": [
            {"type": "mrkdwn", "text": "*Order:* #{{order_id}}"},
            {"type": "mrkdwn", "text": "*Status:* {{status}}"}
          ]},
          {"type": "divider"},
          {"type": "section", "text": {"type": "mrkdwn", "text": "Estimated delivery: {{delivery_date}}"}}
        ]
      }

​
WhatsApp Interactive Messages

Send interactive list or button messages on WhatsApp. 
RESPOND: "Select an option"
  RICH_CONTENT:
    whatsapp: |
      {
        "type": "interactive",
        "interactive": {
          "type": "button",
          "body": {"text": "How would you like to proceed?"},
          "action": {
            "buttons": [
              {"type": "reply", "reply": {"id": "modify", "title": "Modify Booking"}},
              {"type": "reply", "reply": {"id": "cancel", "title": "Cancel Booking"}},
              {"type": "reply", "reply": {"id": "info", "title": "More Info"}}
            ]
          }
        }
      }
Send a scrollable carousel of cards across supported channels. 
RESPOND: "Available hotels"
  RICH_CONTENT:
    carousel:
      cards:
        - title: "Grand Hotel"
          subtitle: "$200/night - 4.5 stars"
          imageUrl: "https://example.com/grand-hotel.jpg"
          buttons:
            - id: "book_grand"
              type: button
              label: "Book Now"
              value: "grand_hotel"
        - title: "City Lodge"
          subtitle: "$120/night - 4.0 stars"
          imageUrl: "https://example.com/city-lodge.jpg"
          buttons:
            - id: "book_city"
              type: button
              label: "Book Now"
              value: "city_lodge"

​
Interactive Actions (Buttons, Select, Input)

Attach interactive elements to any response. Handle user interactions with ON_ACTION. 
FLOW:
  offer_actions:
    REASONING: false
    RESPOND: "What would you like to do?"
      ACTIONS:
        - id: "view_details"
          type: button
          label: "View Details"
        - id: "select_category"
          type: select
          label: "Category"
          options:
            - id: "billing"
              label: "Billing"
            - id: "technical"
              label: "Technical"
            - id: "general"
              label: "General"

    ON_ACTION:
      - ACTION_ID: "view_details"
        RESPOND: "Here are the details..."
        THEN: show_details
      - ACTION_ID: "select_category"
        SET: selected_category = action.value
        THEN: route_to_category

​
Multi-Channel Templates

Use the TEMPLATES block to define reusable multi-format content. 
TEMPLATES:
  booking_summary:
    DEFAULT: |
      Booking Confirmed!
      Hotel: {{hotel_name}}
      Total: ${{total}}
    MARKDOWN: |
      ## Booking Confirmed

      | Detail | Value |
      |--------|-------|
      | **Hotel** | {{hotel_name}} |
      | **Total** | ${{total}} |
    HTML: |
      <div class="booking">
        <h2>Booking Confirmed</h2>
        <p>Hotel: {{hotel_name}}</p>
        <p>Total: ${{total}}</p>
      </div>
    VOICE INSTRUCTIONS: "Congratulate the user. Read the hotel name and total clearly."

FLOW:
  confirm:
    REASONING: false
    RESPOND: TEMPLATE(booking_summary)
    THEN: COMPLETE

​
Troubleshooting

  • Rich content not rendering: The connected channel may not support the format. Always provide a plain text RESPOND as fallback. The runtime uses it when no matching rich format exists.
  • Adaptive Card JSON parse error: Validate the JSON structure using the Adaptive Cards Designer. Template variables ({{...}}) are resolved before JSON parsing.
  • Slack blocks rejected by API: Slack has strict limits on block structure (max 50 blocks, max 3000 chars per text element). Validate against Slack’s Block Kit Builder.
  • Interactive action not handled: Ensure each button/select element has an id that matches an ACTION_ID in the ON_ACTION block.

​
File Attachments

Handle file attachments so your agent can accept, process, and respond to user-uploaded images, documents, audio, and video files.

​
Declare Attachment Fields

Use the ATTACHMENTS block in your agent to declare the types of files your agent accepts. 
AGENT: Document_Processor
GOAL: "Process uploaded documents and extract information"

ATTACHMENTS:
  id_document:
    prompt: "Please upload a photo of your ID"
    category: image
    required: true
    maxFileSizeMb: 10
    allowedMimeTypes: ["image/jpeg", "image/png", "image/webp"]
    ocrEnabled: true

  supporting_document:
    prompt: "Upload any supporting documents (optional)"
    category: document
    required: false
    maxFileSizeMb: 20
    allowedMimeTypes: ["application/pdf", "application/vnd.openxmlformats-officedocument.wordprocessingml.document"]
The runtime prompts the user for each required attachment and validates file type and size before processing.

​
Upload Attachments via the API

When building a custom integration, upload files through the attachments API. 
curl -X POST https://your-platform/api/projects/$PROJECT_ID/sessions/$SESSION_ID/attachments \
  -H "Authorization: Bearer $TOKEN" \
  -F "file=@document.pdf"
The response includes an attachmentId and processing status.

​
Check Attachment Processing Status

curl https://your-platform/api/projects/$PROJECT_ID/sessions/$SESSION_ID/attachments/$ATTACHMENT_ID/status \
  -H "Authorization: Bearer $TOKEN"
FieldDescription
scanStatusMalware scan result (pending, clean, infected).
processingStatusContent extraction (pending, processing, complete).
embeddingStatusEmbedding generation (pending, complete).

​
Image Attachments with OCR

Enable OCR to extract text from images. Useful for processing receipts, IDs, or handwritten notes. 
ATTACHMENTS:
  receipt:
    prompt: "Upload a photo of your receipt"
    category: image
    required: true
    ocrEnabled: true
The extracted text is available in the session as receipt.extractedText.

​
Audio Attachments with Transcription

Enable transcription for audio uploads. 
ATTACHMENTS:
  voicemail:
    prompt: "Upload the voicemail recording"
    category: audio
    required: true
    transcriptionEnabled: true
    allowedMimeTypes: ["audio/mpeg", "audio/wav", "audio/ogg"]
The transcribed text is available as voicemail.transcription.

​
Video Attachments with Key Frame Extraction

Extract key frames from video for visual analysis. 
ATTACHMENTS:
  product_video:
    prompt: "Upload a video of the defective product"
    category: video
    required: false
    maxFileSizeMb: 50
    keyFrameExtraction: true

​
Attachments in Flow Steps

Request attachments at specific points in a flow. 
FLOW:
  collect_documents:
    REASONING: false
    PROMPT: "I need to verify your identity. Please upload a photo of your ID."
    GATHER:
      FIELDS:
        - id_photo
          type: attachment
          category: image
          required: true
    THEN: verify_identity

  verify_identity:
    REASONING: true
    GOAL: "Verify the uploaded ID document"
    AVAILABLE_TOOLS: [verify_document, extract_id_data]
    EXIT_WHEN: identity_verified IS SET
    THEN: proceed

​
Channel-Specific Attachment Handling

Different channels handle attachments differently. The platform normalizes the experience:
ChannelAttachment support
Web SDKDrag-and-drop file upload in chat widget.
SlackNative file sharing, auto-downloaded.
WhatsAppImage, document, audio, video via media API.
TeamsFile attachments via Bot Framework.
EmailMIME attachments parsed from inbound email.
TelegramPhotos, documents, audio, video messages.
No agent-side configuration is needed for channel-specific handling — the platform’s channel adapters normalize all formats.

​
List and Retrieve Attachments

# List all attachments for a session
curl https://your-platform/api/projects/$PROJECT_ID/sessions/$SESSION_ID/attachments \
  -H "Authorization: Bearer $TOKEN"

# Get a download URL for a specific attachment
curl https://your-platform/api/projects/$PROJECT_ID/sessions/$SESSION_ID/attachments/$ATTACHMENT_ID/url \
  -H "Authorization: Bearer $TOKEN"
The download URL is time-limited (default: 1 hour) and scoped to the authenticated user.

​
Troubleshooting

  • Upload rejected with “PAYLOAD_TOO_LARGE”: The file exceeds the maximum size (20 MB by default for the upload endpoint, or the maxFileSizeMb declared in the attachment field). Reduce file size or adjust the limit.
  • Processing status stuck on “pending”: The multimodal processing service may be unavailable. Check service health.
  • OCR returns empty text: The image may be too low resolution or the text is not clearly visible. Recommend users upload high-quality images.
  • Attachment not available in session variables: Wait for the processingStatus to reach complete before accessing extracted content. Use the status endpoint to poll.

​
Further Reading