Repository navigation
Images that are included into instructions via {artifact.<name>} syntax should allow a underlying LLM for image processing/interpeting. #4674
Description
🔴 Required Information
Is your feature request related to a specific problem?
I'm always frustrated when I have to manually handle putting artifacts back to Content to enable underlying LLM image processing.
Describe the Solution You'd Like
It would be nice to be able to just add image to content via including in a LLMAgent instuction {artifact.<image_name} and it would be correctly processed.
Impact on your work
Just better user experience.
Willingness to contribute
Yes, but others can implement it too.
🟡 Recommended Information
Describe Alternatives You've Considered
N/A
Proposed API / Implementation
N/A
Additional Context
N/A
Activity
klateefa commentedon Mar 4, 2026
@Manomenu Thanks for opening this issue!
We’d like to understand the expectation more clearly.Could you provide a bit more detail?This will help us assist you better
Thanks.
Manomenu commentedon Mar 11, 2026
@klateefa Users have to provide prompts for newly created Agents and I noticed that it is possible to inject artifact content by {artifact.} syntax, right?
Also noticed, that if user tries to inject image stored as artifact a underyling model isn't able to process that image. It only works if image is attached as separate content part kinda manually. (i tested it on qwen3-vl)
It would be just much much more convenient if image attaching was that easy as I described.
DeanChensj commentedon Oct 14, 2026
Hi @Manomenu, thank you for reporting this issue!
This has been resolved by PR #7391 and merged into the main branch in commit cd5814e.
We are closing this issue as resolved. If you find that the issue persists on the latest ADK release or if this was closed in error, please feel free to reopen it or leave a comment! Thank you again for your contribution.
github-actions commentedon Oct 14, 2026
Are you satisfied with the resolution of your issue?
Yes
No