Python: Add load_dotenv to get-started samples and fix chat_response_…

[Amit Dhawan (amit12cool)]

Motivation & Context

05_functional_workflow_with_agents.py calls FoundryChatClient(credential=AzureCliCredential()) without explicit project_endpoint/model arguments, relying on FOUNDRY_PROJECT_ENDPOINT and FOUNDRY_MODEL environment variables. However, the sample never calls load_dotenv(), so users storing credentials in a .env file get a cryptic ValueError at runtime (Model is required. Set via 'model' parameter or 'FOUNDRY_MODEL' environment variable).

Additionally, chat_response_cancellation.py had an outdated docstring referencing OPENAI_MODEL/OPENAI_API_KEY even though the sample uses FoundryChatClient with AzureCliCredential — which requires Foundry env vars, not OpenAI ones.

Description & Review Guide

• What are the major changes? Added from dotenv import load_dotenv and load_dotenv() to 05_functional_workflow_with_agents.py. Fixed the configuration docstring in chat_response_cancellation.py to reference FOUNDRY_PROJECT_ENDPOINT, FOUNDRY_MODEL, and az login instead of the incorrect OpenAI env vars.

• What is the impact of these changes? Sample 05 now works out of the box for users with a .env file, consistent with how chat_response_cancellation.py and other env-var-based samples already behave. The cancellation sample no longer misleads users about which credentials to set.

• What do you want reviewers to focus on? Placement of load_dotenv() relative to imports in sample 05.

Related Issue

Fixes # 6689

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 is linked to an issue and there is no other open PR for this issue (see Related Issue above).
• 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.

[Amit Dhawan (amit12cool)]

@microsoft-github-policy-service agree

@microsoft-github-policy-service agree

[Copilot]

Pull request overview

This PR improves the Python samples’ “zero-config via env vars” experience for Azure AI Foundry by ensuring .env files are actually loaded in the get-started workflow sample, and by correcting configuration guidance in the cancellation sample to match the Foundry-based client it uses (Fixes #6689).

Changes:

• Add python-dotenv loading (load_dotenv()) to 05_functional_workflow_with_agents.py so FOUNDRY_PROJECT_ENDPOINT / FOUNDRY_MODEL can be supplied via a .env file.
• Update chat_response_cancellation.py docstring configuration instructions to reference Foundry env vars and Azure CLI auth instead of OpenAI env vars.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
python/samples/02-agents/chat_client/chat_response_cancellation.py	Updates configuration docs to correctly describe Foundry env vars + az login for AzureCliCredential.
python/samples/01-get-started/05_functional_workflow_with_agents.py	Loads .env at startup so Foundry client can pick up FOUNDRY_* settings without explicit constructor args.