Conversation Creation + Management

This guide covers the complete lifecycle of conversations in the Amigo platform, from creation and interaction to monitoring agent actions and system integration.

Conversation Lifecycle Overview

Creation: Initialize a new conversation with a service
Interaction: Exchange messages between user and agent
Monitoring: Track agent actions and dynamic behaviors
Integration: Connect with external systems based on conversation events
Termination: End conversations automatically or manually

Creating a New Conversation

To initiate a new conversation with a user:

curl --request POST \
     --url 'https://api.amigo.ai/v1/<YOUR-ORG-ID>/conversation/?response_format=text' \
     --header 'Authorization: Bearer <AUTH-TOKEN-OF-USER>' \
     --header 'Accept: application/x-ndjson' \
     --header 'Content-Type: application/json' \
     --data '
{
  "service_version_set_name": "release",
  "service_id": "<SERVICE_ID>"
}'

Equivalent TypeScript / Node 18+ example (re‑uses the parseNdjsonStream helper defined later in this document):

import fetch from "node-fetch";  // remove if your environment already has global fetch
import { parseNdjsonStream } from "./parseNdjsonStream"; // or copy the helper from the example below

export async function createConversation() {
  const ORG_ID = "<YOUR‑ORG‑ID>";
  const AUTH_TOKEN = "<USER JWT>";
  const body = {
    service_version_set_name: "release",
    service_id: "<SERVICE_ID>",
  };

  const resp = await fetch(`https://api.amigo.ai/v1/${ORG_ID}/conversation/?response_format=text`, {
    method: "POST",
    headers: {
      Authorization: `Bearer ${AUTH_TOKEN}`,
      "Content-Type": "application/json",
      Accept: "application/x-ndjson",
    },
    body: JSON.stringify(body),
  });

  if (!resp.ok) throw new Error(`HTTP ${resp.status}`);

  for await (const evt of parseNdjsonStream(resp.body!)) {
    if (evt.type === "conversation-created") {
      return evt.conversation_id as string;
    }
    if (evt.type === "error") {
      throw new Error(evt.message ?? "server error");
    }
  }

  throw new Error("conversation-created event not received");
}

// example response stream

{"type":"conversation-created","conversation_id":"67d871c23eb91293ecfae8b0"}
{"type":"new-message","message":"","message_metadata":[],"transcript_alignment":null,"stop":false,"sequence_number":0,"message_id":"67d871c23eb91293ecfae8b2"}
{"type":"new-message","message":"Hi","message_metadata":[],"transcript_alignment":null,"stop":false,"sequence_number":1,"message_id":"67d871c23eb91293ecfae8b2"}

It will include several event types as denoted by the type field:

Event Type

Type field Value

Description

ConversationCreatedEvent

conversation-created

Provides the conversation_id and confirms successful creation

ErrorEvent

error

Indicates an internal error occurred. When this happens, none of the messages/artifacts in this interaction persist, and the entire API call is rolled back.

NewMessageEvent

new-message

Contains message chunks (text or voice based on parameters).

InteractionCompleteEvent

interaction-complete

Signals successful stream completion.

CurrentAgentActionEvent

current-agent-action

Only emitted if the emit_current_agent_action_event query parameter is set to True. Describes the action the agent's taking to produce the response.

Understanding the agent's actions:

You can use the CurrentAgentActionEvent to understand the agent's actions as it's generating the response. The event follows the schema below:

{
    "type": "current-agent-action",
    "action": <See action below>
}

Emitted when the agent enters a side-effect state with type emit-event during the state machine navigation. The action field will be a str equal to the event field in the state.

Emitted when a dynamic behavior is triggered. The action field will be an object containing the following field:

{
    "type": "dynamic-behavior-triggered",
    "dynamic_behavior_set_version_info": [str, int]
    """
    A 2-tuple describing the dynamic behavior that was triggered. The first element is the ID of the dynamic behavior set, and the second element is its version number.
    """
}

System Integration for Dynamic Events

Dynamic behaviors serve as powerful triggers for integrating the Amigo platform with your broader ecosystem of systems and agents. When specific conversation patterns are detected, dynamic behaviors provide a mechanism to seamlessly connect these systems while maintaining separation of business logic.

Integration Flow

Detect Dynamic Behavior: When you receive a dynamic-behavior-triggered event in the conversation stream, capture the dynamic_behavior_set_version_info tuple. This tuple contains the ID and version of the triggered dynamic behavior.
Map Behaviors to Metrics: In your integration layer, maintain a mapping between dynamic behavior IDs and the specific metrics you want to evaluate when that behavior triggers. This approach:
- Keeps your business logic separate from the Amigo platform
- Allows reconfiguration without code changes
- Enables A/B testing of different integration strategies
Evaluate Multiple Metrics: When a relevant dynamic behavior is detected, use the metric evaluation endpoint to extract structured data from the conversation:

curl -L \
  --request POST \
  --url 'https://api.amigo.ai/v1/{organization}/metric/evaluate' \
  --header 'Authorization: Bearer JWT' \
  --header 'Content-Type: application/json' \
  --data '{
    "metric_ids": [
      "metric_id_1", "metric_id_2"
    ],
    "conversation_id": "conversation_id",
    "evaluate_to_interaction_id": "interaction_id"  # Optional: evaluate up to a specific point
  }'

This endpoint returns structured data from each metric, including values, references to specific parts of the conversation, and justifications:

{
  "metrics": [
    {
      "metric_id": "metric_id_1",
      "name": "Risk Assessment Score",
      "value": "75",
      "references": [
        "User mentioned suicidal thoughts in message #3", 
        "User expressed severe depression in message #5"
      ],
      "justification": "The user has expressed concerning thoughts about self-harm with specific details about methods."
    }
  ]
}

Apply Business Logic: Based on the structured metric results, your systems can implement various actions:
- Route conversations to specialized AI agents with specific expertise
- Create tickets in support systems with detailed evidence and references
- Trigger automated workflows in business systems
- Hand off to human operators with contextual information
- Store structured conversation data for compliance and analytics

The key advantage of this architecture is the complete separation of concerns:

The Amigo platform handles conversation management and dynamic behavior detection
Your systems determine which metrics to evaluate for each behavior
Your business logic decides what actions to take based on metric results
The conversation continues naturally without interruption

This approach enables sophisticated, real-time integrations between conversational AI and your other systems while maintaining the flexibility to evolve your business processes independently of the conversation platform.

You can use the below endpoint to retrieve dynamic behavior set versions:

You can use the below endpoint to compute metrics:

Important Conversation Management Rules

A user cannot have multiple active conversations for the same service
The conversation_id must be stored and used for all subsequent interactions
The conversation object should be persisted for at least the duration of the active session

Interacting with a Conversation

After creating a conversation, you can send user messages:

curl --request POST \
     --url 'https://api.amigo.ai/v1/<YOUR-ORG-ID>/conversation/<CONVERSATION-ID>/interact?request_format=text&response_format=text' \
     --header 'Authorization: Bearer <AUTH-TOKEN-OF-USER>' \
     --header 'Accept: application/x-ndjson' \
     --header 'Content-Type: multipart/form-data' \
     --form 'recorded_message=<UTF-8 ENCODED USER MESSAGE>'

Request Format

The request body must use multipart/form-data format
Include a single form field named recorded_message containing UTF-8 encoded text
The body can be sent as a stream to reduce latency, as processing begins as soon as chunks are received

The response takes the form of a body stream:

// Example response stream

{"type":"user-message-available","message_id":"67d872693eb91293ecfae8b8","user_message":"I'm good"}
{"type":"new-message","message":"","message_metadata":[],"transcript_alignment":null,"stop":false,"sequence_number":0,"message_id":"67d8726b3eb91293ecfae8bd"}
{"type":"new-message","message":"Great","message_metadata":[],"transcript_alignment":null,"stop":false,"sequence_number":1,"message_id":"67d8726b3eb91293ecfae8bd"}

Response Stream Events

Event Type

Type Field Value

Description

UserMessageAvailableEvent

user-message-available

First event in response, includes the user message if sent as text.

ErrorEvent

error

Indicates an internal error occurred. When this happens, none of the messages/artifacts in this interaction persist, and the entire API call is rolled back.

InteractionCompleteEvent

interaction-complete

Signals the interaction is complete.

EndSessionEvent

end-session

Optional event if conversation automatically ends.

CurrentAgentActionEvent

current-agent-action

Only emitted if the emit_current_agent_action_event query parameter is set to True. Describes the action the agent's taking to produce the response.

How to Consume the `application/x‑ndjson` Stream

/conversation/{conversation_id}/interact returns an ND‑JSON stream (one JSON object per line, ‑separated). The server keeps the underlying HTTP/2 connection open after the last event of a turn so that you can immediately begin the next turn without paying the cost of a new TLS/TCP handshake. Do not wait for the socket to close—instead, decide in your client logic when you are done processing a turn.

The final event of every successful turn is always:

interaction-complete – the agent finished speaking/thinking for this user turn.

If the conversation is over (for example the agent decides to end‑session) you will also receive:

end-session

Once you have seen one of those events you can safely stop listening, cancel the stream, or start the next request on the same connection.

Below is a minimal Node 18+ example (TypeScript/JavaScript) that shows the correct pattern. The helper parseNdjsonStream() is reproduced in full below so you can copy‑paste without pulling in any external dependencies.

// Node 18+: run with  --experimental-fetch  OR upgrade to Node 20 (global fetch & FormData).
// If your runtime already provides these globals you can delete the two imports.
import fetch   from "node-fetch";  // npm i node-fetch@3   (ES modules only)
import FormData from "form-data";  // npm i form-data

const ORG_ID       = "<YOUR‑ORG‑ID>";
const CONVERSATION = "<CONVERSATION-ID>";
const AUTH_TOKEN   = "<USER JWT>";

/**
 * Async generator that yields parsed JSON objects from an ND‑JSON stream.
 */
async function* parseNdjsonStream(stream: NodeJS.ReadableStream) {
  const decoder = new TextDecoder();
  let buffer = "";

  for await (const chunk of stream as any) {
    buffer += decoder.decode(chunk, { stream: true });

    let nl;
    while ((nl = buffer.indexOf("\n")) !== -1) {
      const line = buffer.slice(0, nl).trim();
      buffer      = buffer.slice(nl + 1);
      if (!line) continue;
      yield JSON.parse(line);
    }
  }

  if (buffer.trim()) yield JSON.parse(buffer);
}

export async function sendMessage(text: string) {
  const form = new FormData();
  form.append("recorded_message", text);

  const url = `https://api.amigo.ai/v1/${ORG_ID}/conversation/${CONVERSATION}/interact` +
              "?request_format=text&response_format=text&emit_current_agent_action_event=true";

  const response = await fetch(url, {
    method: "POST",
    headers: {
      Authorization: `Bearer ${AUTH_TOKEN}`,
      Accept: "application/x-ndjson",
      ...form.getHeaders(),
    },
    body: form,
  });

  if (!response.ok) throw new Error(`HTTP ${response.status}`);

  for await (const evt of parseNdjsonStream(response.body!)) {
    console.log(`[event] ${evt.type}`, evt);

    switch (evt.type) {
      case "interaction-complete":
      case "end-session":
        response.body!.cancel();
        return;
      case "error":
        console.error("Server error", evt);
        response.body!.cancel();
        return;
    }
  }
}

// Run `node basic_interaction.ts` directly
if (import.meta.url === `file://${process.argv[1]}`) {
  await sendMessage("Hello there, June!");
}

Adding a Hard Timeout (Optional)

If you want to guarantee that your UI never waits more than N seconds for a turn to complete, wrap the fetch in an AbortController:

const ctrl   = new AbortController();
const timer  = setTimeout(() => ctrl.abort(), 15_000);   // 15‑second guard‑rail

const resp = await fetch(url, {
  method: "POST",
  body:   form,
  headers: { /* … */ },
  signal: ctrl.signal,
});

clearTimeout(timer);

If the controller aborts, fetch() rejects with DOMException: AbortError; show an appropriate error to the user and offer a retry.

Tips & Gotchas

Always set Accept: application/x-ndjson when you expect a text response stream. • If you set response_format=voice, use Accept: audio/mpeg (MP3) or Accept: audio/wav accordingly.
The connection staying open is not a timeout. It is normal HTTP/2 behaviour. Abort the request yourself (e.g. via AbortController) if you want a hard upper bound.
If you plan to send the next user message immediately, you can keep the connection open and reuse it – simply start another /interact request.

Voice‑Note (≠ Voice‑to‑Voice) Interactions

Amigo currently supports voice notes: you send audio, the agent responds with synthesised audio. It is not a full duplex "voice‑to‑voice" phone call. Treat each /interact turn as an async voice note exchange:

Encode the user's recording as a WAV or FLAC fragment.
POST it as the recorded_message form field with request_format=voice.
Set response_format=voice and choose an Accept header: • audio/mpeg → MP3, most efficient for mobile play‑back. • audio/wav → uncompressed PCM, lowest latency for small clips.
Parse the ND‑JSON events exactly as for text—new-message contains base‑64 audio chunks—and play them back in order.

Example (browser / React Native):

if (evt.type === "new-message" && typeof evt.message === "string" && evt.message) {
  const blob = Uint8Array.from(atob(evt.message), c => c.charCodeAt(0));
  playAudio(blob.buffer);  // your audio player
}

Because each request/response represents one voice note, you can easily build push‑to‑talk or walkie‑talkie style UX while re‑using the same streaming infrastructure described above.

Quick‑Start Checklist (Keep This Handy!)

🟢 Before You Hit Send

Have you set all three required headers? • Authorization: Bearer <JWT> • Accept: application/x-ndjson (or audio/*) • Content‑Type handled automatically by FormData, do not hard‑code multipart/form-data; boundary=... yourself.
Is the query‑string correct? request_format=text|voice and response_format=text|voice must match the formats you actually send/expect.
Are you waiting for interaction-complete, not for the socket to close? An open HTTP/2 connection ≠ timeout.
Did you remember that one user = one active conversation per service? Handle the "already started" error by resuming or finishing the existing conversation.

🟡 Troubleshooting

• error event received

{"type": "error", "code": 422, "message": "Request format mismatch"}

Log the full event. 2. Fix the request. 3. Retry the entire turn—the server has already rolled it back.

• HTTP 415 / 406 → Your Accept or Content‑Type is wrong.

• Stream seems silent → Are you parsing per‑line? The first bytes might be small; buffer until you hit .

🛑 Never

• Never assume the transport will close on success. • Never create a new conversation when one is still active—finish or resume instead.

Common Integration Patterns (Straight from amigo‑examples)

1. Fire‑and‑forget Notification

You only care about the agent's final reply; intermediate new-message chunks are ignored.

for await (const evt of parseNdjsonStream(resp.body!)) {
  if (evt.type === "interaction-complete") {
    console.log("assistant says:", evt.final_message);
    break;
  }
}

2. Real‑time "Type‑as‑you‑stream" UI

let current = "";
for await (const evt of parseNdjsonStream(resp.body!)) {
  if (evt.type === "new-message") {
    current += evt.message;
    redraw(current);   // e.g. setState in React
  }
  if (evt.type === "interaction-complete") break;
}

3. Server‑Side Relay (Backend collects, then pushes to client)

app.post("/amigo-proxy", async (req, res) => {
  const amigoResp = await fetch(/* … */);
  // Pipe raw ND‑JSON straight through:
  res.setHeader("Content-Type", "application/x-ndjson");
  amigoResp.body!.pipe(res);
});

Useful when the browser environment cannot (yet) consume streaming fetches—your backend remains the only component that needs the Amigo secret.

4. Finishing Idle Conversations Automatically

const INACTIVITY_MS = 30 * 60_000; // 30 min

setInterval(async () => {
  for (const convo of getActiveConversations()) {
    if (Date.now() - convo.lastUserActivity > INACTIVITY_MS) {
      await finishConversation(convo.id);
    }
  }
}, 5 * 60_000);

Keeps your database clean and avoids users hitting the "already in a conversation" error weeks later.

Conversation Lifecycle Management

Understanding Conversation States

Started: Conversation is active and can receive interactions
Finished: Conversation has ended and cannot receive further interactions

Automatic vs. Manual Finish

A conversation can finish in two ways:

Automatically: When the service determines the conversation should finish (based on user intent, service completion, etc.)
Manually: When explicitly ended via the finish conversation API (e.g. due to timeout or user action)

Finishing a Conversation

To manually finish a conversation:

curl --request POST \
     --url 'https://api.amigo.ai/v1/<YOUR-ORG-ID>/conversation/<CONVERSATION-ID>/finish/' \
     --header 'Authorization: Bearer <AUTH-TOKEN-OF-USER>' \
     --header 'accept: application/json' \
     --header 'content-type: application/json' \
     --data '{}'

Important: This endpoint should only be called:

On started, non-finished conversations
After previous conversation API calls have completed
When the conversation hasn't automatically finished during interaction

When a conversation finishes, post-conversation analysis is initiated asynchronously (memory generation, user model updates, etc.).

Managing "Dangling" Conversations

Conversations never time out automatically. You have several options for handling inactive conversations:

Timeout Approach: Track user's last interaction time and call the finish endpoint after a defined period
- Caution: This may terminate conversations users intend to continue
Resume Option (Recommended): When a user returns, offer options to:
- Resume the existing conversation
- Start a new conversation (which requires ending the current one)
Error Handling: If your application attempts to create a new conversation while one is active:
- Catch the error response
- Prompt the user to either resume or end the existing conversation

The Amigo system prevents users from having multiple ongoing conversations of the same service type, ensuring conversation integrity.

PreviousService Discovery + Management NextData Retrieval + User Model Management

Last updated 1 day ago

Was this helpful?

Conversation Creation + Management

This guide covers the complete lifecycle of conversations in the Amigo platform, from creation and interaction to monitoring agent actions and system integration.

Conversation Lifecycle Overview

Creation: Initialize a new conversation with a service
Interaction: Exchange messages between user and agent
Monitoring: Track agent actions and dynamic behaviors
Integration: Connect with external systems based on conversation events
Termination: End conversations automatically or manually

Creating a New Conversation

To initiate a new conversation with a user:

curl --request POST \
     --url 'https://api.amigo.ai/v1/<YOUR-ORG-ID>/conversation/?response_format=text' \
     --header 'Authorization: Bearer <AUTH-TOKEN-OF-USER>' \
     --header 'Accept: application/x-ndjson' \
     --header 'Content-Type: application/json' \
     --data '
{
  "service_version_set_name": "release",
  "service_id": "<SERVICE_ID>"
}'

Equivalent TypeScript / Node 18+ example (re‑uses the parseNdjsonStream helper defined later in this document):

import fetch from "node-fetch";  // remove if your environment already has global fetch
import { parseNdjsonStream } from "./parseNdjsonStream"; // or copy the helper from the example below

export async function createConversation() {
  const ORG_ID = "<YOUR‑ORG‑ID>";
  const AUTH_TOKEN = "<USER JWT>";
  const body = {
    service_version_set_name: "release",
    service_id: "<SERVICE_ID>",
  };

  const resp = await fetch(`https://api.amigo.ai/v1/${ORG_ID}/conversation/?response_format=text`, {
    method: "POST",
    headers: {
      Authorization: `Bearer ${AUTH_TOKEN}`,
      "Content-Type": "application/json",
      Accept: "application/x-ndjson",
    },
    body: JSON.stringify(body),
  });

  if (!resp.ok) throw new Error(`HTTP ${resp.status}`);

  for await (const evt of parseNdjsonStream(resp.body!)) {
    if (evt.type === "conversation-created") {
      return evt.conversation_id as string;
    }
    if (evt.type === "error") {
      throw new Error(evt.message ?? "server error");
    }
  }

  throw new Error("conversation-created event not received");
}

The response takes the form of a body stream () containing New line Delimited JSON ():

// example response stream

{"type":"conversation-created","conversation_id":"67d871c23eb91293ecfae8b0"}
{"type":"new-message","message":"","message_metadata":[],"transcript_alignment":null,"stop":false,"sequence_number":0,"message_id":"67d871c23eb91293ecfae8b2"}
{"type":"new-message","message":"Hi","message_metadata":[],"transcript_alignment":null,"stop":false,"sequence_number":1,"message_id":"67d871c23eb91293ecfae8b2"}

It will include several event types as denoted by the type field:

Event Type

Type field Value

Description

ConversationCreatedEvent

conversation-created

Provides the conversation_id and confirms successful creation

ErrorEvent

error

Indicates an internal error occurred. When this happens, none of the messages/artifacts in this interaction persist, and the entire API call is rolled back.

NewMessageEvent

new-message

Contains message chunks (text or voice based on parameters).

InteractionCompleteEvent

interaction-complete

Signals successful stream completion.

CurrentAgentActionEvent

current-agent-action

Only emitted if the emit_current_agent_action_event query parameter is set to True. Describes the action the agent's taking to produce the response.

Understanding the agent's actions:

You can use the CurrentAgentActionEvent to understand the agent's actions as it's generating the response. The event follows the schema below:

{
    "type": "current-agent-action",
    "action": <See action below>
}

Emitted when the agent enters a side-effect state with type emit-event during the state machine navigation. The action field will be a str equal to the event field in the state.

Emitted when a dynamic behavior is triggered. The action field will be an object containing the following field:

{
    "type": "dynamic-behavior-triggered",
    "dynamic_behavior_set_version_info": [str, int]
    """
    A 2-tuple describing the dynamic behavior that was triggered. The first element is the ID of the dynamic behavior set, and the second element is its version number.
    """
}

System Integration for Dynamic Events

Integration Flow

Detect Dynamic Behavior: When you receive a dynamic-behavior-triggered event in the conversation stream, capture the dynamic_behavior_set_version_info tuple. This tuple contains the ID and version of the triggered dynamic behavior.
Map Behaviors to Metrics: In your integration layer, maintain a mapping between dynamic behavior IDs and the specific metrics you want to evaluate when that behavior triggers. This approach:
- Keeps your business logic separate from the Amigo platform
- Allows reconfiguration without code changes
- Enables A/B testing of different integration strategies
Evaluate Multiple Metrics: When a relevant dynamic behavior is detected, use the metric evaluation endpoint to extract structured data from the conversation:

curl -L \
  --request POST \
  --url 'https://api.amigo.ai/v1/{organization}/metric/evaluate' \
  --header 'Authorization: Bearer JWT' \
  --header 'Content-Type: application/json' \
  --data '{
    "metric_ids": [
      "metric_id_1", "metric_id_2"
    ],
    "conversation_id": "conversation_id",
    "evaluate_to_interaction_id": "interaction_id"  # Optional: evaluate up to a specific point
  }'

This endpoint returns structured data from each metric, including values, references to specific parts of the conversation, and justifications:

{
  "metrics": [
    {
      "metric_id": "metric_id_1",
      "name": "Risk Assessment Score",
      "value": "75",
      "references": [
        "User mentioned suicidal thoughts in message #3", 
        "User expressed severe depression in message #5"
      ],
      "justification": "The user has expressed concerning thoughts about self-harm with specific details about methods."
    }
  ]
}

Apply Business Logic: Based on the structured metric results, your systems can implement various actions:
- Route conversations to specialized AI agents with specific expertise
- Create tickets in support systems with detailed evidence and references
- Trigger automated workflows in business systems
- Hand off to human operators with contextual information
- Store structured conversation data for compliance and analytics

The key advantage of this architecture is the complete separation of concerns:

The Amigo platform handles conversation management and dynamic behavior detection
Your systems determine which metrics to evaluate for each behavior
Your business logic decides what actions to take based on metric results
The conversation continues naturally without interruption

You can use the below endpoint to retrieve dynamic behavior set versions:

You can use the below endpoint to compute metrics:

Important Conversation Management Rules

A user cannot have multiple active conversations for the same service
The conversation_id must be stored and used for all subsequent interactions
The conversation object should be persisted for at least the duration of the active session

Interacting with a Conversation

After creating a conversation, you can send user messages:

curl --request POST \
     --url 'https://api.amigo.ai/v1/<YOUR-ORG-ID>/conversation/<CONVERSATION-ID>/interact?request_format=text&response_format=text' \
     --header 'Authorization: Bearer <AUTH-TOKEN-OF-USER>' \
     --header 'Accept: application/x-ndjson' \
     --header 'Content-Type: multipart/form-data' \
     --form 'recorded_message=<UTF-8 ENCODED USER MESSAGE>'

Request Format

The request body must use multipart/form-data format
Include a single form field named recorded_message containing UTF-8 encoded text
The body can be sent as a stream to reduce latency, as processing begins as soon as chunks are received

The response takes the form of a body stream:

// Example response stream

{"type":"user-message-available","message_id":"67d872693eb91293ecfae8b8","user_message":"I'm good"}
{"type":"new-message","message":"","message_metadata":[],"transcript_alignment":null,"stop":false,"sequence_number":0,"message_id":"67d8726b3eb91293ecfae8bd"}
{"type":"new-message","message":"Great","message_metadata":[],"transcript_alignment":null,"stop":false,"sequence_number":1,"message_id":"67d8726b3eb91293ecfae8bd"}

Response Stream Events

Event Type

Type Field Value

Description

UserMessageAvailableEvent

user-message-available

First event in response, includes the user message if sent as text.

ErrorEvent

error

Indicates an internal error occurred. When this happens, none of the messages/artifacts in this interaction persist, and the entire API call is rolled back.

InteractionCompleteEvent

interaction-complete

Signals the interaction is complete.

EndSessionEvent

end-session

Optional event if conversation automatically ends.

CurrentAgentActionEvent

current-agent-action

Only emitted if the emit_current_agent_action_event query parameter is set to True. Describes the action the agent's taking to produce the response.

How to Consume the `application/x‑ndjson` Stream

The final event of every successful turn is always:

interaction-complete – the agent finished speaking/thinking for this user turn.

If the conversation is over (for example the agent decides to end‑session) you will also receive:

end-session

Once you have seen one of those events you can safely stop listening, cancel the stream, or start the next request on the same connection.

// Node 18+: run with  --experimental-fetch  OR upgrade to Node 20 (global fetch & FormData).
// If your runtime already provides these globals you can delete the two imports.
import fetch   from "node-fetch";  // npm i node-fetch@3   (ES modules only)
import FormData from "form-data";  // npm i form-data

const ORG_ID       = "<YOUR‑ORG‑ID>";
const CONVERSATION = "<CONVERSATION-ID>";
const AUTH_TOKEN   = "<USER JWT>";

/**
 * Async generator that yields parsed JSON objects from an ND‑JSON stream.
 */
async function* parseNdjsonStream(stream: NodeJS.ReadableStream) {
  const decoder = new TextDecoder();
  let buffer = "";

  for await (const chunk of stream as any) {
    buffer += decoder.decode(chunk, { stream: true });

    let nl;
    while ((nl = buffer.indexOf("\n")) !== -1) {
      const line = buffer.slice(0, nl).trim();
      buffer      = buffer.slice(nl + 1);
      if (!line) continue;
      yield JSON.parse(line);
    }
  }

  if (buffer.trim()) yield JSON.parse(buffer);
}

export async function sendMessage(text: string) {
  const form = new FormData();
  form.append("recorded_message", text);

  const url = `https://api.amigo.ai/v1/${ORG_ID}/conversation/${CONVERSATION}/interact` +
              "?request_format=text&response_format=text&emit_current_agent_action_event=true";

  const response = await fetch(url, {
    method: "POST",
    headers: {
      Authorization: `Bearer ${AUTH_TOKEN}`,
      Accept: "application/x-ndjson",
      ...form.getHeaders(),
    },
    body: form,
  });

  if (!response.ok) throw new Error(`HTTP ${response.status}`);

  for await (const evt of parseNdjsonStream(response.body!)) {
    console.log(`[event] ${evt.type}`, evt);

    switch (evt.type) {
      case "interaction-complete":
      case "end-session":
        response.body!.cancel();
        return;
      case "error":
        console.error("Server error", evt);
        response.body!.cancel();
        return;
    }
  }
}

// Run `node basic_interaction.ts` directly
if (import.meta.url === `file://${process.argv[1]}`) {
  await sendMessage("Hello there, June!");
}

Adding a Hard Timeout (Optional)

If you want to guarantee that your UI never waits more than N seconds for a turn to complete, wrap the fetch in an AbortController:

const ctrl   = new AbortController();
const timer  = setTimeout(() => ctrl.abort(), 15_000);   // 15‑second guard‑rail

const resp = await fetch(url, {
  method: "POST",
  body:   form,
  headers: { /* … */ },
  signal: ctrl.signal,
});

clearTimeout(timer);

If the controller aborts, fetch() rejects with DOMException: AbortError; show an appropriate error to the user and offer a retry.

Tips & Gotchas

Always set Accept: application/x-ndjson when you expect a text response stream. • If you set response_format=voice, use Accept: audio/mpeg (MP3) or Accept: audio/wav accordingly.
The connection staying open is not a timeout. It is normal HTTP/2 behaviour. Abort the request yourself (e.g. via AbortController) if you want a hard upper bound.
If you plan to send the next user message immediately, you can keep the connection open and reuse it – simply start another /interact request.

Voice‑Note (≠ Voice‑to‑Voice) Interactions

Encode the user's recording as a WAV or FLAC fragment.
POST it as the recorded_message form field with request_format=voice.
Set response_format=voice and choose an Accept header: • audio/mpeg → MP3, most efficient for mobile play‑back. • audio/wav → uncompressed PCM, lowest latency for small clips.
Parse the ND‑JSON events exactly as for text—new-message contains base‑64 audio chunks—and play them back in order.

Example (browser / React Native):

if (evt.type === "new-message" && typeof evt.message === "string" && evt.message) {
  const blob = Uint8Array.from(atob(evt.message), c => c.charCodeAt(0));
  playAudio(blob.buffer);  // your audio player
}

Because each request/response represents one voice note, you can easily build push‑to‑talk or walkie‑talkie style UX while re‑using the same streaming infrastructure described above.

Quick‑Start Checklist (Keep This Handy!)

🟢 Before You Hit Send

Have you set all three required headers? • Authorization: Bearer <JWT> • Accept: application/x-ndjson (or audio/*) • Content‑Type handled automatically by FormData, do not hard‑code multipart/form-data; boundary=... yourself.
Is the query‑string correct? request_format=text|voice and response_format=text|voice must match the formats you actually send/expect.
Are you waiting for interaction-complete, not for the socket to close? An open HTTP/2 connection ≠ timeout.
Did you remember that one user = one active conversation per service? Handle the "already started" error by resuming or finishing the existing conversation.

🟡 Troubleshooting

• error event received

{"type": "error", "code": 422, "message": "Request format mismatch"}

Log the full event. 2. Fix the request. 3. Retry the entire turn—the server has already rolled it back.

• HTTP 415 / 406 → Your Accept or Content‑Type is wrong.

• Stream seems silent → Are you parsing per‑line? The first bytes might be small; buffer until you hit .

🛑 Never

• Never assume the transport will close on success. • Never create a new conversation when one is still active—finish or resume instead.

Common Integration Patterns (Straight from amigo‑examples)

1. Fire‑and‑forget Notification

You only care about the agent's final reply; intermediate new-message chunks are ignored.

for await (const evt of parseNdjsonStream(resp.body!)) {
  if (evt.type === "interaction-complete") {
    console.log("assistant says:", evt.final_message);
    break;
  }
}

2. Real‑time "Type‑as‑you‑stream" UI

let current = "";
for await (const evt of parseNdjsonStream(resp.body!)) {
  if (evt.type === "new-message") {
    current += evt.message;
    redraw(current);   // e.g. setState in React
  }
  if (evt.type === "interaction-complete") break;
}

3. Server‑Side Relay (Backend collects, then pushes to client)

app.post("/amigo-proxy", async (req, res) => {
  const amigoResp = await fetch(/* … */);
  // Pipe raw ND‑JSON straight through:
  res.setHeader("Content-Type", "application/x-ndjson");
  amigoResp.body!.pipe(res);
});

Useful when the browser environment cannot (yet) consume streaming fetches—your backend remains the only component that needs the Amigo secret.

4. Finishing Idle Conversations Automatically

const INACTIVITY_MS = 30 * 60_000; // 30 min

setInterval(async () => {
  for (const convo of getActiveConversations()) {
    if (Date.now() - convo.lastUserActivity > INACTIVITY_MS) {
      await finishConversation(convo.id);
    }
  }
}, 5 * 60_000);

Keeps your database clean and avoids users hitting the "already in a conversation" error weeks later.

Conversation Lifecycle Management

Understanding Conversation States

Started: Conversation is active and can receive interactions
Finished: Conversation has ended and cannot receive further interactions

Automatic vs. Manual Finish

A conversation can finish in two ways:

Automatically: When the service determines the conversation should finish (based on user intent, service completion, etc.)
Manually: When explicitly ended via the finish conversation API (e.g. due to timeout or user action)

Finishing a Conversation

To manually finish a conversation:

curl --request POST \
     --url 'https://api.amigo.ai/v1/<YOUR-ORG-ID>/conversation/<CONVERSATION-ID>/finish/' \
     --header 'Authorization: Bearer <AUTH-TOKEN-OF-USER>' \
     --header 'accept: application/json' \
     --header 'content-type: application/json' \
     --data '{}'

Important: This endpoint should only be called:

On started, non-finished conversations
After previous conversation API calls have completed
When the conversation hasn't automatically finished during interaction

When a conversation finishes, post-conversation analysis is initiated asynchronously (memory generation, user model updates, etc.).

Managing "Dangling" Conversations

Conversations never time out automatically. You have several options for handling inactive conversations:

Timeout Approach: Track user's last interaction time and call the finish endpoint after a defined period
- Caution: This may terminate conversations users intend to continue
Resume Option (Recommended): When a user returns, offer options to:
- Resume the existing conversation
- Start a new conversation (which requires ending the current one)
Error Handling: If your application attempts to create a new conversation while one is active:
- Catch the error response
- Prompt the user to either resume or end the existing conversation

The Amigo system prevents users from having multiple ongoing conversations of the same service type, ensuring conversation integrity.

PreviousService Discovery + Management NextData Retrieval + User Model Management

Last updated 1 day ago

Was this helpful?

Conversation Lifecycle Overview

Creating a New Conversation

Understanding the agent's actions:

Important Conversation Management Rules

Interacting with a Conversation

Request Format

Response Stream Events

How to Consume the application/x‑ndjson Stream

Tips & Gotchas

Voice‑Note (≠ Voice‑to‑Voice) Interactions

Quick‑Start Checklist (Keep This Handy!)

Common Integration Patterns (Straight from amigo‑examples)

1. Fire‑and‑forget Notification

2. Real‑time "Type‑as‑you‑stream" UI

3. Server‑Side Relay (Backend collects, then pushes to client)

4. Finishing Idle Conversations Automatically

Conversation Lifecycle Management

Understanding Conversation States

Automatic vs. Manual Finish

Finishing a Conversation

Managing "Dangling" Conversations

Conversation Lifecycle Overview

Creating a New Conversation

Understanding the agent's actions:

Important Conversation Management Rules

Interacting with a Conversation

Request Format

Response Stream Events

How to Consume the application/x‑ndjson Stream

Tips & Gotchas

Voice‑Note (≠ Voice‑to‑Voice) Interactions

Quick‑Start Checklist (Keep This Handy!)

Common Integration Patterns (Straight from amigo‑examples)

1. Fire‑and‑forget Notification

2. Real‑time "Type‑as‑you‑stream" UI

3. Server‑Side Relay (Backend collects, then pushes to client)

4. Finishing Idle Conversations Automatically

Conversation Lifecycle Management

Understanding Conversation States

Automatic vs. Manual Finish

Finishing a Conversation

Managing "Dangling" Conversations

Get dynamic behavior set versions

Permissions

Interact with a conversation

Permissions

Finish a conversation

Permissions

Evaluate metrics

Permissions

Create a conversation

Permissions

How to Consume the `application/x‑ndjson` Stream

How to Consume the `application/x‑ndjson` Stream