> For the complete documentation index, see [llms.txt](https://docs.workflowgen.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.workflowgen.com/admin-fr/applications-de-workflow/openai/openaiaddmessage.md).

# OPENAIADDMESSAGE

## Aperçu

L'application de workflow **OPENAIADDMESSAGE** vous permet de mettre à jour l'historique des messages d'une conversation pour y ajouter des interactions utilisateurs ou d'outils. Il est aussi possible de mettre à jour l'historique directement depuis un sous-processus.

## Paramètres requis

<table data-full-width="true"><thead><tr><th width="202" valign="top">Paramètre</th><th width="76" valign="top">Type</th><th width="125" valign="top">Direction</th><th valign="top">Description</th></tr></thead><tbody><tr><td valign="top"><code>CONTENT</code></td><td valign="top">TEXT</td><td valign="top">IN</td><td valign="top">L'historique des messages au format JSON. La structure de référence est celle de la documentation d'OpenAI pour l'objet <code>messages</code> <a href="https://platform.openai.com/docs/api-reference/chat/create#chat-create-messages">https://platform.openai.com/docs/api-reference/chat/create#chat-create-messages</a></td></tr><tr><td valign="top"><code>ROLE</code></td><td valign="top">TEXT</td><td valign="top">IN</td><td valign="top">Le rôle à associer au message; les valeurs possibles sont <code>user</code>, <code>system</code>, <code>assistant</code> ou <code>tool</code></td></tr></tbody></table>

## Paramètres facultatifs

<table data-full-width="true"><thead><tr><th width="302" valign="top">Paramètre</th><th width="118" valign="top">Type</th><th width="125" valign="top">Direction</th><th valign="top">Description</th></tr></thead><tbody><tr><td valign="top"><code>MESSAGE_HISTORY</code></td><td valign="top">TEXT</td><td valign="top">INOUT</td><td valign="top">L'historique des messages à mettre à jour</td></tr><tr><td valign="top"><code>TOOL_CALL_ID</code></td><td valign="top">TEXT</td><td valign="top">IN</td><td valign="top">Dans le cas où le <code>ROLE</code> est <code>tool</code>, il s'agit de l'identifiant de l'outil</td></tr><tr><td valign="top"><code>ASSISTANT_TOOL_CALL</code></td><td valign="top">TEXT</td><td valign="top">IN</td><td valign="top">Dans le cas où le <code>ROLE</code> est <code>assistant</code> et que vous souhaitez ajouter une liste d'outil à appeler, il s'agit de la liste des outils</td></tr><tr><td valign="top"><code>REQUEST_ID</code></td><td valign="top">NUMERIC</td><td valign="top">IN</td><td valign="top">Dans le cas où l'historique est mis à jour depuis un autre processus, il s'agit du numéro de la demande à mettre à jour</td></tr><tr><td valign="top"><code>REQUEST_DATA_NAME</code></td><td valign="top">TEXT</td><td valign="top">IN</td><td valign="top">Dans le cas où l'historique est mis à jour depuis un autre processus, il s'agit du nom de la donnée à mettre à jour</td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

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

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.workflowgen.com/admin-fr/applications-de-workflow/openai/openaiaddmessage.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
