FCE-2759 Add support for agent image capture#228
Merged
Conversation
There was a problem hiding this comment.
Pull request overview
This PR adds support for agent image capture functionality, enabling agents to request and receive captured images from video tracks. The implementation includes new protobuf message types, SDK methods for image capture requests, and a multimodal example demonstrating audio+video interactions with the Gemini Live API.
Changes:
- Added
captureImagemethod toFishjamAgentfor requesting track images - Extended protobuf definitions with
AgentRequest_CaptureImageandAgentResponse_TrackImagemessages - Implemented periodic image capture in a new multimodal example that integrates Fishjam with Gemini Live API
Reviewed changes
Copilot reviewed 14 out of 16 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| packages/js-server-sdk/src/agent.ts | Added captureImage method and trackImage event support |
| packages/js-server-sdk/src/integrations/gemini.ts | Added metadata field to audio codec parameters |
| packages/fishjam-proto/src/fishjam/agent_notifications.ts | Added protobuf message types for image capture requests and responses |
| packages/fishjam-proto/src/fishjam/server_notifications.ts | Added channel management notifications and fixed typos in comments |
| examples/multimodal/* | New example demonstrating multimodal interactions with Gemini |
| .gitmodules | Updated protos submodule branch reference |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Qizot
force-pushed
the
agent-image-capture
branch
from
c576d44 to
87216be
Compare
AHGIJMKLKKZNPJKQR
approved these changes
Feb 9, 2026
PiotrWodecki
added a commit
that referenced
this pull request
Feb 9, 2026
PiotrWodecki
added a commit
that referenced
this pull request
Feb 9, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
This PR adds support for agent image capture.
Motivation and Context
Why is this change required? What problem does it solve? If it fixes an open
issue, please link to the issue here.
Documentation impact
Types of changes
not work as expected)