[kylin (JennyMa11)]

Motivation & Context

The group-chat selector sample builds its agent instructions from adjacent string
literals, and the first literal has no trailing space, so the model receives
"practically dangerous.If there is nothing woth pointing out". Two other samples
carry wording mistakes: "gracefull" in the tool-recovery sample and a doubled
"with" in the message it prints, plus "messsages ... nor load" in a comment in the
Foundry memory sample.

Description & Review Guide

• What are the major changes? Correct the missing space and the typo in the
  selector prompt; fix "gracefull" and "Tool failed: with error" in the tool
  recovery sample and update its Expected Output block to match; fix the wording
  and spelling of a comment in the Foundry memory sample.
• What is the impact of these changes? Samples only. No library code, no API,
  no behavior change. The only non-cosmetic element is the missing space inside
  the concatenated prompt string.
• What do you want reviewers to focus on? Whether the reworded prompt clause in
  the selector sample is acceptable as written.

Related Issue

N/A - trivial change: spelling and grammar fixes in samples. The one-character
prompt fix restores the intended sentence boundary; nothing else changes behavior.

AI Assistance

• This is an AI-assisted contribution. I reviewed, understood, and verified all submitted content and accept responsibility for it.

AI assistance details: A coding agent located the misspellings with a spell checker
and flagged the missing space while reviewing the diff. I reviewed each change and
verified the files compile and pass the repository's spell and lint checks. No
library code was generated.

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.

[Copilot]

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

[kylin (JennyMa11)]

@microsoft-github-policy-service agree

[Eduard van Valkenburg (eavanvalkenburg)]

/review

[github-actions]

MAF Automated Review — Iteration 1

Result: No findings
Scope: full PR (1 commit(s)): 776c73e22e31
Model: gpt-5.6-sol

Overview

This sample-only change corrects spelling and output text while restoring the missing sentence boundary in the verifier prompt. The tool exception behavior and expected-output example remain synchronized, and the changed code introduces no API, persistence, authorization, or resource-lifecycle surface. No Critical, High, or Medium defect 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.

[agent-framework-automation]

kylin (@JennyMa11), this pull request is waiting on your response. If there is no further activity within 4 days, it will be closed automatically. (This is an automated message.)