feat: Update scenario-based agent setup and model references to GPT-5.1

[Avijit-Microsoft]

Purpose

This pull request introduces several important updates to support Azure OpenAI GPT-5.1 as the default language model, improve scenario-based agent configuration, and enhance Azure role assignments for AI Foundry integration. The changes also streamline environment setup and add dynamic tool selection for agents based on scenario data types.

Model Upgrade and Documentation Updates:

• Default model for chat and agent features is upgraded from GPT-4o to GPT-5.1 throughout the codebase, infrastructure, and documentation, ensuring the latest model is used for all deployments and user guidance. [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12]

Agent Creation and Scenario Configuration:

• The agent creation script (scripts/create_agent.py) now loads scenario-specific prompts and tool configurations, regenerating the agent prompt for the selected scenario and dynamically enabling SQL analytics tools for structured data scenarios. [1] [2] [3]
• The agent creation script determines SQL tool availability from scenarios.json, enabling SQL analytics only for relevant scenarios (e.g., JSON, CSV, WAV) and defaulting to search-only otherwise. [1] [2]

Infrastructure and Role Assignment Enhancements:

• Azure Bicep templates and role modules are updated to pass and assign a managed identity for the AI Foundry project, granting it appropriate search index reader and contributor roles for seamless agent integration. [1] [2] [3]

Environment Setup Improvements:

• Python virtual environment directory is standardized to .venv (from venv) in both PowerShell and Bash setup scripts, and the agent setup step is removed from the default deployment flow for clarity. [1] [2]

File Path Consistency:

• Configuration directory references in agent scripts are updated to use data/config instead of Sample_Data/config for consistency.

These changes collectively modernize the platform to use the latest Azure OpenAI model, make agent capabilities scenario-aware, and improve deployment reliability and maintainability.

Does this introduce a breaking change?

• Yes
• [x ] 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.

What to Check

Verify that the following are valid

• ...

Other Information