---
title: prompt.active_agent
description: A model prompt request made through ActiveAgent.
url: https://docs.honeybadger.io/insights/event-types/ruby/prompt.active_agent/
---

A model prompt request made through ActiveAgent.

Source **Active Agent** Category **LLM** Fields **24** [honeybadger-ruby](https://docs.honeybadger.io/lib/ruby/)

## Fields

| Field                 | Type    | Description                                                                                                               |
| --------------------- | ------- | ------------------------------------------------------------------------------------------------------------------------- |
| `event_type`          | string  | Allowed value: `prompt.active_agent`.                                                                                     |
| `provider`            | string  | Model provider name, e.g. "openai", "anthropic".                                                                          |
| `provider_module`     | string  | ActiveAgent provider module class name.                                                                                   |
| `model`               | string  | Model identifier, e.g. "gpt-4o", "claude-3-opus".                                                                         |
| `trace_id`            | string  | Trace ID for correlating events within a single agent run.                                                                |
| `message_count`       | integer | Number of messages in the prompt context.                                                                                 |
| `stream`              | boolean | Whether the response was streamed.                                                                                        |
| `finish_reason`       | string  | Stop reason returned by the provider, e.g. "stop", "length".                                                              |
| `response_model`      | string  | Model identifier as returned by the provider response.                                                                    |
| `response_id`         | string  | Provider-assigned response ID.                                                                                            |
| `temperature`         | number  | Sampling temperature used.                                                                                                |
| `max_tokens`          | integer | Max tokens parameter.                                                                                                     |
| `top_p`               | number  | Top-p nucleus sampling parameter.                                                                                         |
| `tool_count`          | integer | Number of tools available to the model.                                                                                   |
| `has_instructions`    | boolean | Whether a system instructions block was included.                                                                         |
| `usage`               | object  | Token usage reported by the provider.                                                                                     |
| `usage.input_tokens`  | integer |                                                                                                                           |
| `usage.output_tokens` | integer |                                                                                                                           |
| `usage.total_tokens`  | integer |                                                                                                                           |
| `duration`            | number  | Duration in milliseconds.                                                                                                 |
| `instrumenter_id`     | string  | ActiveSupport::Notifications instrumenter UUID, added by the Honeybadger notification subscriber.                         |
| `request_id`          | string  | Rails request UUID, present on any event fired during a web request context. Set by the Honeybadger agent when available. |
| `hostname`            | string  | Server hostname. Attached to every event by default (events.attach\_hostname).                                            |
| `environment`         | string  | Application environment, e.g. "production". Attached to every event by default (events.attach\_environment).              |

## Example

```json
{
  "event_type": "prompt.active_agent",
  "provider": "openai",
  "provider_module": "ActiveAgent::GenerationProvider::OpenAIProvider",
  "model": "gpt-4o",
  "trace_id": "7c9e6679-7425-40de-944b-e07fc1f90ae7",
  "message_count": 4,
  "stream": false,
  "finish_reason": "stop",
  "response_model": "gpt-4o-2024-08-06",
  "response_id": "chatcmpl-Bx7Qk2T9fJ3aV1mN5pR8sLwY",
  "temperature": 0.7,
  "max_tokens": 1024,
  "top_p": 1,
  "tool_count": 3,
  "has_instructions": true,
  "usage": {
    "input_tokens": 412,
    "output_tokens": 186,
    "total_tokens": 598
  },
  "duration": 1820.43,
  "instrumenter_id": "d6a5b3f4c2e1908a7b6c",
  "request_id": "0f5e4bb2-3c46-4b1c-91d5-2f4e8a6b9c01",
  "hostname": "web-1.example.com",
  "environment": "production"
}
```

---

## Try Honeybadger for FREE

Intelligent logging, error tracking, and Just Enough APM™ in one dev-friendly platform. Find and fix problems before users notice.

[Start free trial](https://app.honeybadger.io/users/sign_up)

[See plans and pricing](https://www.honeybadger.io/plans/)