# Codex

## Overview

The OpenAI Codex input receives OTel telemetry data emitted by [Codex](https://openai.com/codex), OpenAI's agentic coding tool, for observability and telemetry.

## Requirements

There is no configuration needed at the input level in Monad. Simply create a Codex input and attach it to a pipeline.

All configuration is done on the Codex side, where you point its OTel exporter to the Monad endpoint with the appropriate authentication headers.

## Codex Configuration

To send telemetry from Codex to Monad, configure the OpenTelemetry exporter in your Codex settings. You will need:

1. A Monad **organization API key** with the `pipeline:data:write` permission
2. The **pipeline ID** of the pipeline with your Codex input

### Required Headers

| Header | Value | Description |
|--------|-------|-------------|
| `Authorization` | `ApiKey <your-api-key>` | Monad organization API key |
| `Monad-Pipeline-Id` | `<your-pipeline-id>` | The pipeline ID containing the Codex input |

### Example Configuration

Add the following to your Codex TOML configuration file:

```toml
[otel]
exporter = { otlp-grpc = {
  endpoint = "https://app.monad.com:4317",
  headers = { "Authorization" = "ApiKey <your-api-key>", "Monad-Pipeline-Id" = "<your-pipeline-id>" }
}}
```

For full details on enabling and configuring telemetry in Codex, see the [Codex Advanced Configuration - Observability and Telemetry guide](https://developers.openai.com/codex/config-advanced#observability-and-telemetry).

## Related Articles

- [Codex Advanced Configuration - Observability and Telemetry](https://developers.openai.com/codex/config-advanced#observability-and-telemetry)
- [Monad OpenTelemetry Input](../monad/monad-otel.mdx)
- [OpenTelemetry OTLP Exporter Configuration](https://opentelemetry.io/docs/languages/sdk-configuration/otlp-exporter/)