-
Notifications
You must be signed in to change notification settings - Fork 2.7k
Open
Labels
answered[Status] This issue has been answered by the maintainer[Status] This issue has been answered by the maintainerlive[Component] This issue is related to live, voice and video chat[Component] This issue is related to live, voice and video chatrequest clarification[Status] The maintainer need clarification or more information from the author[Status] The maintainer need clarification or more information from the author
Description
I am replicating bidirectional streaming for my multi-agent system. When a user asks for an image, the root agent should route the query to one of the sub-agents, which successfully returns the image as part of its response. However, this image output is not being surfaced in the final UI response.
I have tested this multiple times. Text and audio responses work perfectly, but when the user requests an image, there is no response. While checking the run_config, I noticed that response_modalities only lists text and audio; there is no mention of image support.
Expected behavior:
Input: text or audio
Output: text, audio, and image
Metadata
Metadata
Assignees
Labels
answered[Status] This issue has been answered by the maintainer[Status] This issue has been answered by the maintainerlive[Component] This issue is related to live, voice and video chat[Component] This issue is related to live, voice and video chatrequest clarification[Status] The maintainer need clarification or more information from the author[Status] The maintainer need clarification or more information from the author