# I think discourse-ai API needs a regression

**URL:** https://meta.discourse.org/t/i-think-discourse-ai-api-needs-a-regression/387355
**Category:** Development
**Tags:** ai
**Created:** [November 1, 2025, 4:57pm UTC](https://meta.discourse.org/t/i-think-discourse-ai-api-needs-a-regression/387355 "2025-11-01T16:57:25Z")
**Posts on this page:** 1
**Showing post:** 3

<div class="post-metadata">

### Author: ![MoRanYue](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/moranyue/32/523065_2.png) [@MoRanYue](https://meta.discourse.org/u/MoRanYue)
#### Post date: [November 1, 2025, 6:04pm UTC](https://meta.discourse.org/t/i-think-discourse-ai-api-needs-a-regression/387355/3 "2025-11-01T18:04:20Z")

</div>

> [@Falco](#):
>
> I’d be open for a PR that adds a checkbox for disabling Structured Outputs from the API request on the OpenAI provider.

That would be nice, I am not and can not demand Discourse team, so just giving some suggestions.

Using old “separators” solution for robuster parsing, a XML-like raw content like this:

```plaintext
<SUMMARY_START>
Summary contnet.
<SUMMARY_END>

<SUGGESTIONS_START>
<SUGGESTION_START>
Suggestion 1
<SUGGESTION_END>
<SUGGESTION_START>
Suggestion 2
<SUGGESTION_END>
...
<SUGGESTIONS_END>

```

Then not caring about anything outside of `<START>` and `<END>`, I believe that the most foolish productional AI model can process labels correctly.

And asking AI not to add extra discription; then warning admins possible problems if opening that checkbox.

I do not know what Discourse AI generated request body looks like. But if not, just putting system prompts in first message said by role `system`, vector database query result in the next `system` role message with a prefix anything like `Past important content:\n`, and putting post content or other actual data in `user` role’s messages.

---

_[View the full topic](https://meta.discourse.org/t/i-think-discourse-ai-api-needs-a-regression/387355)._