[Naveen Chatlapalli (1aifanatic)]

Motivation & Context

samples/03-workflows/orchestrations/group_chat_philosophical_debate.py passes intermediate_output_from=["all"]. In a list, each entry is a participant name or instance, so build() fails:

ValueError: Unknown intermediate participant 'all'. Known participants: ...

The sample's comment says to mark every participant's responses as intermediate output. The GroupChatBuilder docstring documents the string "all_other" for that.

Description & Review Guide

• What are the major changes? The sample passes intermediate_output_from="all_other".
• What is the impact of these changes? The sample builds and streams each participant's turn as intermediate output, as its comment describes.
• What do you want reviewers to focus on? Nothing in particular.

I ran the sample with the Foundry client replaced by a stub whose moderator returns valid AgentOrchestrationOutput JSON. The workflow builds, streams the participants' turns and ends on the moderator's final message. On main it raises the ValueError above at build(). Ruff and the repo's sample pyright config are clean.

Related Issue

N/A - trivial change: a sample argument is corrected to the documented value.

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: Claude Code helped find the build failure by running the sample against a stub client, make the change, verify the run, and draft 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.

🤖 Generated with Claude Code

[Copilot]

🟢 Approval recommended

No active review issues are reported for the change to the debate sample’s intermediate-output selector.

No open issues 🎉

What changed in this PR

Fixes the philosophical debate sample’s group-chat configuration so the workflow builds and streams participant turns as intended.

Changes:

• Replaces intermediate_output_from=["all"] with the documented "all_other" selector, avoiding the unknown-participant error.

File	Description
python/​samples/​03-workflows/​orchestrations/​group_chat_philosophical_debate.py	Corrects the selector used to emit participant responses as intermediate output.

_{Review effort: Balanced}