Purpose

This pull request updates the default image generation model throughout the codebase and documentation from gpt-image-1 to gpt-image-1-mini. This change affects deployment workflows, environment configuration, documentation, and troubleshooting guides to ensure consistency and reflect the new default model. The update also clarifies supported models and quotas for Azure OpenAI image generation.

Deployment workflow and configuration updates:

• Changed the default image model from gpt-image-1 to gpt-image-1-mini in all relevant GitHub Actions workflows, including deploy-orchestrator.yml, deploy-v2.yml, and job-deploy.yml, as well as their input validation and environment variable handling. [1] [2] [3] [4] [5] [6]
• Updated the sample environment configuration (content-gen/.env.sample) to use gpt-image-1-mini as the default for both Azure AI Foundry and Azure OpenAI image models, and clarified supported models in comments. [1] [2]

Documentation and usage instructions:

• Revised all documentation—including deployment guides, parameter tables, quick start instructions, and environment variable references—to use gpt-image-1-mini as the default and to list it as the primary supported model. [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12]
• Updated the README and cost/pricing documentation to reflect the new default image model.

Troubleshooting and quota guidance:

• Amended troubleshooting steps and quota request documentation to reference gpt-image-1-mini instead of gpt-image-1, including instructions for requesting model access.

These updates ensure the project consistently uses gpt-image-1-mini as the default image generation model and provides clear guidance for users and maintainers.

Does this introduce a breaking change?

• Yes
• No

Golden Path Validation

• I have tested the primary workflows (the "golden path") to ensure they function correctly without errors.

Deployment Validation

• I have validated the deployment process successfully and all services are running as expected with this change.