[BlueRaddish]

Motivation & Context

The multimodal guide currently tells readers to configure Azure OpenAI variables, but both Azure-named scripts construct FoundryChatClient and require the Foundry project endpoint and model variables. Following the documented configuration raises ValueError: Model is required before either example can run.

Description & Review Guide

• What are the major changes? Replace the obsolete Azure OpenAI variable list with FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL, including a full project-scoped endpoint example.
• What is the impact of these changes? Readers configure the variables the existing samples actually consume. The obsolete API-version and API-key options are removed from that list; sample code and runtime behavior stay unchanged. These Foundry variables are already present in the consolidated sample inventory.
• What do you want reviewers to focus on? The setup instructions match both azure_chat_multimodal.py and azure_responses_multimodal.py. Both unchanged complete main() paths were exercised with real Foundry client construction and an offline response boundary: the original instructions fail twice, two explicit-configuration controls pass, and all four cases pass with the guide corrected. Normal scoped and native hooks pass, including whole-samples checks; nine hooks are nonapplicable. No live Azure credentials, network/model responses, full workspace unit suite or distribution build are claimed.

Related Issue

N/A - trivial change. This is an obvious documentation correction to the environment variable names already required by the two adjacent sample scripts; the intended configuration is not in dispute.

AI Assistance

• No material AI assistance was used.
• This is an AI-assisted contribution. I reviewed, understood, and verified all submitted content and accept responsibility for it.

AI assistance details: OpenAI Codex assisted with identifying the documentation mismatch, the focused documentation change, offline verification and this description.

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR links to an agreed issue with no competing open PR, or the Related Issue section documents a trivial-change or repository-automation exception.
• This is not a breaking change. If it is a breaking change, add the breaking change label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has insufficient remaining quota.

[Eduard van Valkenburg (eavanvalkenburg)]

/review

[github-actions]

MAF Automated Review — Iteration 1

Result: No findings
Scope: full PR (1 commit(s)): 37971e90165c
Model: gpt-5.6-sol

Overview

This documentation-only change aligns the multimodal samples with the environment variables that FoundryChatClient actually resolves. The full project-scoped endpoint follows the repository's sample guidance, and constructor checks plus settings tests confirm that both documented variables are required. No publishable risk was established.

Reviewed the supplied pull-request change set across correctness, security/reliability, architecture, and failure behavior.
No publishable findings remained after source verification for this scope.

[Eduard van Valkenburg (eavanvalkenburg)]

BlueRaddish The authentication guidance still recommends passing an api_key to FoundryChatClient, but the public constructor accepts neither that parameter nor arbitrary **kwargs; readers following this alternative get TypeError before either multimodal sample can start. Please remove the API-key alternative from the authentication section and execution comments, and document Azure CLI login or another supported token credential instead.