Python: Failed to chat on Agent Playground — message stuck loading (no response).

[Menghua1]

Description:
After the deployment completes, navigate to the agent playground link shown in the post-deploy output and try out some test inputs. The Agent Playground remains stuck in a loading/spinning state and no response is returned. Details are as follows:

In addition, pytest also fails due to request timeouts. Details are as follows:

Steps to Reproduce:

1. Initialize the project: azd init --template Azure-Samples/ai-foundry-starter-basic.
2. Initialize AI agent: azd ai agent init -m https://github.com/microsoft-foundry/foundry-samples/blob/main/samples/python/hosted-agents/agent-framework/echo-agent/agent.yaml and select location southcentralus.
3. Run azd up.
4. Navigate to the agent playground link.
5. Enter a test message, such as: "Hello world!"

Environment:

• Azd version: azd version 1.24.0-beta.1-daily.5998626 (commit dbbb97c88a1679b8f3a4cdc74a36792c0e057864).
• AI Agent Extension version: 0.1.14-preview
• OS: Windows
• Location: southcentralus.
• Agent: agents-in-workflow, agent-with-text-search-rag, agent-with-foundry-tools, echo-agent, web-search-agent, AgentsInWorkflows, AgentWithTextSearchRag.

Expected Behavior:
The Agent Playground chat works correctly, and pytest also passes successfully.

@JeffreyCA and @rajeshkamal5050 for notification.

[Menghua1]

@JeffreyCA and @rajeshkamal5050 Based on testing with the latest azure.ai.agents 0.1.16-preview, this issue can still be reproduced.

Environment:

• Azd version: azd version 1.24.0-beta.1-daily.6038384 (commit 26ca32ee9b29c23cca87a69e731920ff48841f89)
• AI Agent Extension version: 0.1.16-preview
• OS: Windows
• Agent: agents-in-workflow, agent-with-text-search-rag, agent-with-foundry-tools, echo-agent, web-search-agent, AgentsInWorkflows, AgentWithTextSearchRag.
• OS: Windows
• Location: southcentralus.