# TypeSafe Jev와 다른 System One 의사결정 모델

**URL:** <https://meta.discourse.org/t/typesafe-jev-and-other-system-one-decision-models/414738>\
**Category:** Announcements\
**Tags:** ai, workflows\
**Created:** [10월 15, 2026, 5:27오전 UTC](https://meta.discourse.org/t/typesafe-jev-and-other-system-one-decision-models/414738 "2026-10-15T05:27:05Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![Falco](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/falco/32/179432_2.png) [@Falco](https://meta.discourse.org/u/Falco)\
**Post date:** [11월 4, 2026, 6:08오후 UTC](https://meta.discourse.org/t/typesafe-jev-and-other-system-one-decision-models/414738/7 "2026-11-04T18:08:14Z")

</div>

> [@putty](#):
>
> 이 기능과 관련된 아주 사소한 버그를 발견했습니다: 통합 AI 도구를 사용하여 이 기능을 만들었으나, CDCK Hosted Decisions 모델을 인식하지 못했습니다. 또한 모델 페이지에서 ID 번호를 확인할 방법이 없습니다(상세 정보를 보기 위한 수정 버튼이 없습니다). 수동으로 업데이트해야 할 것을 알면서도 일부러 잘못된 ID 번호를 입력했습니다.

훌륭한 보고 감사합니다!

> <https://github.com/discourse/discourse/pull/45575>
>
> When admins drafted workflows with AI, the authoring agent never used the classi…fy node, even on sites with a decision model (for example, a hosted site's seeded model). It used an AI agent node for classification instead. There were three reasons:
> 
> \- The agent had no way to find a \`decision\_model\_id\`. There is a lookup tool for AI agents but none for decision models, and the prompt tells it not to invent IDs.
> \- Every AI-related rule in the prompt pointed at \`action:ai\_agent\`. Its only example was "Classify the trigger post with an existing agent".
> \- The classify node had no examples or notes, so the agent didn't know its output shape or how to branch on it.
> 
> \### Changes
> 
> \- \`workflow\_node\_catalog\` now returns \`load\_options\`: the current choices for picker parameters that don't depend on other parameters. A list is included only when it has 25 entries or fewer. Longer lists are left out, so the agent never mistakes a partial list for every value; it uses \`workflow\_resolve\_entity\` for those instead.
> \- The options preloading moves from \`NodeTypeSerializer\` to \`DiscourseWorkflows::PreloadedOptions\`, so the editor and the catalog share it. The serializer output doesn't change.
> \- The classify node gets a catalog example and notes. They cover when to prefer it over an agent, its output fields, threshold branching with \`condition:if\`, the rules for questions, choices, and levels, and refused answers.
> \- The system prompt now prefers \`action:classify\` for judging, labelling, routing, and gating items whenever it's in the node menu. It keeps \`action:ai\_agent\` for generated text, tool use, and open-ended reasoning.

---

_[View the full topic](https://meta.discourse.org/t/typesafe-jev-and-other-system-one-decision-models/414738)._