# Request Format

**Headers**

```
Content-Type: application/json
Authorization: Bearer YOUR API_TOKEN
```

**Request body**

```
{
    "messages": [
        {
            "role": "user",
            "content": "Your question here"
        }
    ]
}
```

**Message roles**

* **user** - Messages from the end user
* **assistant** - Previous responses from the AI (for conversation history)

**Multi-turn Conversations**

To maintain conversation context, include the full conversation history:

<pre><code>{
    "messages": [
        {
            "role": "user",
            "content": "How does authentication work in this project?"
        },
        {
            "role": "assistant",
            "content": "The project uses Spring Security with..."
        },
        {
<strong>            "role": "user",
</strong>            "content": "Can you show me the code for that?"
        }
    ]
}
</code></pre>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.kodesage.ai/api/request-format.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.