> For the complete documentation index, see [llms.txt](https://docs.struct.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.struct.com/changelog/july-2026/july-6th.md).

# July 6th

**Changelog released on 2026-07-06**

Welcome to our latest release, featuring importer auto mapping by attribute alias, a migration step for custom file templates, and Business Rules cache preservation during attribute or global list updates. We’ve fixed foreign key, KeyNotFound and deadlock errors, ensured empty global list references, and added AI-powered image manipulation, a native provider with credit controls, plus AI Assistant support for Google Gemini and Claude.ai.

## New Feature

1. **Add native AI provider with credit system to control spending:** Added a native AI provider system. (SP-2303)
2. **Add support for image manipulation with AI:** Added support for manipulating images with AI. (SP-2393)

## Enhancement

1. **AI Assistant should support Claude.ai:** The AI Assistant now support Claude.ai. (SP-1930)
2. **Deleting products that are in the progress of being updated can cause deadlocks:** Fixed an issue where deleting products currently being updated would cause a deadlock. (SP-2713)
3. **Requesting entities in the API that is being deleted during the request can cause KeyNotFoundException:** Fixed an issue where requesting an entity that is being deleted through the API would throw an exception. (SP-2716)
4. **Support auto mapping by attribute alias in importer:** Added support for auto mapping by attribute. (SP-2720)

## Bug

1. **Global list reference attribute is not empty when left empty in Copy Wizard flow:** Global list reference attributes that is left empty in the copy wizard will now also be empty on the new copied product. (SP-2622)

## Task

1. **AI Assistant shall support Google Gemini models:** The AI Assistant now supports Google Gemini models. (SP-2011)


---

# 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 dynamically by asking a question.

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

```
GET https://docs.struct.com/changelog/july-2026/july-6th.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.