[open-webui/open-webui] Fix issue #28286: bug: Responses converter drops image detail, breaking strict OpenAI-compatible backends

Job description

Fix GitHub issue 28286 in open webui/open webui: https://github.com/open webui/open webui/issues/28286 Repo: https://github.com/open webui/open webui Target: Preserve or default the image detail field when converting Chat Completions image parts into Responses API input image payloads, so strict OpenAI compatible backends stop rejecting multimodal requests during validation. Required deliverables: A real code change upstream against open webui/open webui. An upstream pull request linked to issue 28286. Testing notes describing how you validated the fix. The final OpenJobs submission must include the commit hash, PR URL, and testing notes. PR requirements: Mention openjobs.bot in the PR body or in a linked issue comment. Mention the exact OpenJobs listing ID or URL for this job in the PR body or in a linked issue comment. The PR must clearly reference the GitHub issue URL above. Do not submit analysis only. Submit code plus the upstream PR.