Skip to content

Getting image to generate#957

Open
TravisHilbert wants to merge 204 commits into
microsoft:feature/TAS27from
TravisHilbert:th-congen-updates
Open

Getting image to generate#957
TravisHilbert wants to merge 204 commits into
microsoft:feature/TAS27from
TravisHilbert:th-congen-updates

Conversation

@TravisHilbert
Copy link
Copy Markdown
Collaborator

Co-authored-by: Copilot copilot@github.com

Purpose

  • ...

Does this introduce a breaking change?

  • Yes
  • No

How to Test

  • Get the code
git clone [repo-address]
cd [repo-name]
git checkout [branch-name]
npm install
  • Test the code

What to Check

Verify that the following are valid

  • ...

Other Information

Abdul-Microsoft and others added 30 commits February 4, 2026 18:28
…on with deployment name fallback"

This reverts commit c513f4b.
…team objects and streamline AzureAIClient initialization
refactor: replace avm module with bicep module for search service for initial provisioning
Roopan-Microsoft and others added 20 commits April 9, 2026 22:01
fix: Filter the files path for pipeline run
Added notes about tenant security restrictions and Azure OpenAI quota availability.
Added note about security restrictions and WAF-supported version deployment.
docs: Added content in Readme and deploymentguide for SFI issue
fix: updated the local deployment changes
fix: added the env variable in backend to run it locally
fix: Downmerge from main to dev-v4
fix: update cd ./src/frontend to cd ./src/App in setupEnv File
- Add content_gen.json team config (7-agent marketing content gen team)
- Add ImageAgent backend class: calls gpt-image-1 directly, pushes image
  to user via WebSocket to avoid base64 flooding the agent conversation
- Add image_agent.py and wire into magentic_agent_factory.py (type=image bypass)
- Add AZURE_OPENAI_IMAGE_DEPLOYMENT_NAME to app_config.py
- Add gpt-image-1 (GlobalStandard) model deployment to main.bicep
- Add eastus to allowed AI service locations in main.bicep
- Wire team_config.plan into HumanApprovalMagenticManager planning prompts
  so manager LLM follows the declared workflow sequence
- Increase max_rounds from 20 to 30 for longer multi-agent workflows
- Add upload_images_to_cosmos.py: uploads product images to CosmosDB
- Add content gen data upload to Selecting-Team-Config-And-Data.ps1 (option 6)
- Add azure-cosmos to requirements.txt
Co-authored-by: Copilot <copilot@github.com>
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.