Skip to content

FEAT: add support for image_path data type in WebSocketCopilotTarget#1345

Open
paulinek13 wants to merge 11 commits intoAzure:mainfrom
paulinek13:feat/30jan26/images_support_for_websocket_copilot_target
Open

FEAT: add support for image_path data type in WebSocketCopilotTarget#1345
paulinek13 wants to merge 11 commits intoAzure:mainfrom
paulinek13:feat/30jan26/images_support_for_websocket_copilot_target

Conversation

@paulinek13
Copy link
Contributor

Description

Enabling multimodal input in WebSocketCopilotTarget by adding support for image_path data type.

The implementation follows the exact browser behavior discovered through network traffic analysis: images are uploaded to /m365Copilot/UploadFile --> the response contains a docId field --> docId is used as the annotation id in WebSocket messageAnnotations.

Tests and Documentation

  • Added tests for new functionality
  • Updated existing tests a little
  • Added multimodal usage example in 10_3_websocket_copilot_target.py

(Also, I've made a very small fix, not related to this PR, in pyrit/common/data_url_converter.py)

@paulinek13 paulinek13 marked this pull request as ready for review February 1, 2026 21:04
@paulinek13 paulinek13 changed the title feat: add support for image_path data type in WebSocketCopilotTarget FEAT: add support for image_path data type in WebSocketCopilotTarget Feb 1, 2026
Copy link
Contributor

@romanlutz romanlutz left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks great but we should have a maintainer validate.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants