nextcloud / nextcloud/integration_openai

Using TextToImage via IONOS fails with more than 1 image, with cause not shown to user

Open
#330 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
PHP
Stars
75
Forks
32
Avg merge
9d 8h
Merged PRs (30d)
4

Description

Which version of integration_openai are you using?

master

Which version of Nextcloud are you using?

33

Which browser are you using? In case you are using the phone App, specify the Android or iOS version and device please.

Any

Describe the Bug

Some providers e.g. IONOS restrict the number of images that can be generated in one request. When the user requests more than e.g. 1 image the task fails without the user knowning why.

Expected Behavior

The task should either succeed or the user should be shown a useful error message.

To Reproduce
  1. Connect to IONOS model hub
  2. Create a task generating more than 1 image

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the image-generation task through the IONOS model hub with more than one image, then trace how the failed task error is handled. No files or tests are named; done means the task either succeeds where supported or exposes a useful provider error to the user.

Written by the indexing model from the issue text.

Assessment

Tech stack
php
Domain
api, backend
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.