Enable File Upload/Paste as Task in AGS

[victordibia]

Why are these changes needed?

imagetaskags.mp4

Enable file upload/paste as a task in AGS. Enables tasks like

• Can you research and fact check the ideas in this screenshot?
• Summarize this file

Only text and images supported for now
Underneath, it constructs TextMessage and Multimodal messages as the task.

Related issue number

Closes #5773

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 76.96%. Comparing base (7487687) to head (2996fdd).

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #6091   +/-   ##
=======================================
  Coverage   76.96%   76.96%           
=======================================
  Files         192      192           
  Lines       13438    13438           
=======================================
  Hits        10342    10342           
  Misses       3096     3096           

Flag	Coverage Δ
unittests	76.96% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[husseinmozannar]

Thank you Victor!

Let me make sure I understand the flow:

in chat_input, user uploads a file (or multiple), it gets appended to FileList (upload supported on paste events and the upload button). I noticed the 5b file size limit, is this just for convenience or is there limits due to the webapp?

once a user submits, we send the file alongside the task string to the websocket

in start_stream, we take the files uploaded, and construct a task from them, which can be a MultiModal message if the uploaded file was an image. This is then uses for the run_stream method of the team, and the rest of the code is as usual.

[victordibia]

in start_stream, we take the files uploaded, and construct a task from them, which can be a MultiModal message if the uploaded file was an image. This is then uses for the run_stream method of the team, and the rest of the code is as usual.

Yes, that is correct.

[KanikaChoudhary1312]

You havent added the changes to runview, Now the task is saved as an object in RUN table.
and In UI user message still reads from - run.task

[victordibia]

@KanikaChoudhary1312 , that is correct.
Will push that (and a few other fixes shortly)