> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developers.deepgram.com/docs/voice-agent-history/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.deepgram.com/_mcp/server.

# History

Voice Agent

When starting a new conversation session with the Voice Agent, you can provide historical context about previous conversations and function calls using the `agent.context` parameter. This allows the agent to maintain awareness of prior interactions, enabling more coherent and contextual conversations.

## Purpose

History is particularly useful when:

* Resuming a conversation from a previous session
* Providing context about what has already been discussed
* Maintaining personality and conversation style consistency
* Enabling the agent to reference previous statements, topics, or function results
* Providing background context about function calls already executed
* Maintaining continuity in multi-session interactions

> **Info**
>
> History can be disabled by setting `settings.flags.history` to `false` in the agent configuration. History is enabled by default.

## Conversation Context History

| Field     | Type   | Description                                                       |
| --------- | ------ | ----------------------------------------------------------------- |
| `type`    | String | Must be "History" to identify this as a history message           |
| `role`    | String | Either "user" (human statements) or "assistant" (agent responses) |
| `content` | String | The actual text content of what was said                          |

### Example Payload

**`Conversation History`**

```json Conversation History
{
  "type": "Settings",
  "settings": {
    "flags": {
      "history": true // true by default, set to false to disable
    }
  },
  "agent": {
    "context": {
      "messages": [
        {
          "type": "History",
          "role": "user",
          "content": "Hello, I'm looking for help with my account."
        },
        {
          "type": "History",
          "role": "assistant",
          "content": "Hello! I'd be happy to help you with your account. What specific issue are you experiencing?"
        },
        {
          "type": "History",
          "role": "user",
          "content": "I can't remember my username."
        },
        {
          "type": "History",
          "role": "assistant",
          "content": "I can help you recover your username. I'll need to verify a few details first. Could you provide the email address associated with your account?"
        }
      ]
    },
    "think": {
      "provider": {
        "type": "open_ai",
        "model": "gpt-4o-mini"
      }
    }
  }
}
```

## Function Call Context History

| Field            | Type   | Description                                             |
| ---------------- | ------ | ------------------------------------------------------- |
| `type`           | String | Must be "History" to identify this as a history message |
| `function_calls` | Array  | Array of function call objects with execution details   |

Each function call in the history includes:

| Field         | Type    | Description                                                       |
| ------------- | ------- | ----------------------------------------------------------------- |
| `id`          | String  | A unique identifier for the function call                         |
| `name`        | String  | The name of the function that was called                          |
| `client_side` | Boolean | Indicates if the function was executed client-side or server-side |
| `arguments`   | String  | JSON string containing the arguments passed to the function       |
| `response`    | String  | The response/result returned by the function                      |

### Example Payload

**`Function Call History`**

```json Function Call History
{
  "type": "Settings",
  "settings": {
    "flags": {
      "history": true // true by default, set to false to disable
    }
  },
  "agent": {
    "context": {
      "messages": [
        {
          "type": "History",
          "role": "user",
          "content": "What's the weather like in New York?"
        },
        {
          "type": "History",
          "function_calls": [
            {
              "id": "fc_weather_12345",
              "name": "get_weather",
              "client_side": true,
              "arguments": "{\"location\": \"New York\"}",
              "response": "The current weather in New York is partly cloudy with a temperature of 295.15°K."
            }
          ]
        },
        {
          "type": "History",
          "role": "assistant",
          "content": "The weather in New York is partly cloudy with a temperature of about 72°F (295.15°K)."
        }
      ]
    },
    "think": {
      "provider": {
        "type": "open_ai",
        "model": "gpt-4o-mini"
      },
      "functions": [
        {
          "name": "get_weather",
          "description": "Get the current weather for a specific location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city or location to get weather for"
              }
            },
            "required": ["location"]
          }
        }
      ]
    }
  }
}
```

> Provide conversation and function call history when starting a new Voice Agent session.