pull-requests

Anleitung zum Erstellen von Pull Requests und zum Umgang mit PR-Review-Kommentaren im Agent Framework Repository. Verwenden Sie dies beim Verfassen einer PR-Beschreibung (Ausfüllen der…)

npx skills add https://github.com/microsoft/agent-framework --skill pull-requests

Pull Request Workflow

This skill covers two tasks: (1) writing a high-quality PR description, and (2) handling review comments on an existing PR.

1. Writing the PR description

Always follow the repository PR template at .github/pull_request_template.md. Keep its exact structure and headings. Fill every section:

### Motivation & Context

Explain why the change is needed: the problem it solves and the scenario it contributes to. Describe the net change relative to main — this is implied, so do not spell out "vs main" explicitly.

### Description & Review Guide

Describe the changes, the overall approach, and the design. Answer the three prompts:

  • What are the major changes?
  • What is the impact of these changes?
  • What do you want reviewers to focus on? — This item is for human reviewers only. Automated/AI reviewers must ignore it and review the entire change rather than narrowing scope to it.

### Related Issue

Link the issue the PR fixes using a GitHub closing keyword (Fixes #123 / Closes #123) so it closes automatically on merge. A PR with no linked issue may be closed regardless of how valid the change is. Before opening, confirm there is no other open PR for the same issue; if there is, explain how this PR differs.

### Contribution Checklist

Check every item that applies. For the breaking-change item:

  • Leave "This is not a breaking change." checked for the common case.
  • If the change is breaking, add the breaking change label or put [BREAKING] in the title prefix, before or after a language prefix such as Python: or .NET: — workflows keep the label and the title prefix in sync automatically (see .github/workflows/label-title-prefix.yml and .github/workflows/label-pr.yml).

Do not

  • Do not add ad-hoc sections such as "Validation" or "Tests run"; CI/CD and the checklist already cover validation status.
  • Do not remove or reorder the template's headings.

Stable specifications

For Python function-calling loop changes, read docs/specs/004-python-function-calling-loop.md and validate the PR against it. Do not edit that specification by default. It is a stable cross-package contract, not a per-PR changelog. A specification change is warranted only when the PR intentionally changes normative behavior, the scenario inventory, an acknowledged coverage gap, or the authoritative scenario-to-test mapping; keep any such edit to the smallest affected sections.

Creating the PR

Open new PRs as drafts until they are ready for review. Example:

gh pr create --repo microsoft/agent-framework --base main \
  --head <your-fork-owner>:<branch> --draft \
  --title "<concise title>" --body "<body following the template>"

2. Handling review comments

When a PR receives review comments, follow this sequence — do not start editing code before the user has reviewed the plan:

  1. Review the comments. Read every review comment and thread on the PR, including inline code comments and general review summaries.
  2. Make a plan. Produce a concrete plan describing how each comment will be addressed (or why it should not be, with reasoning).
  3. Let the user review the plan. Present the plan and wait for the user's approval or adjustments before implementing anything.
  4. Implement. Make the agreed changes.
  5. Reply to every comment. Add a reply to all comments explaining how it was addressed, preferably citing the commit containing the change. If the feedback was not addressed, explain why. Leave no comment unanswered.
  6. Resolve completed threads yourself. After replying and completing any necessary discussion, resolve the review thread. Do not wait for the reviewer or a maintainer to resolve it. Leave a thread open only while it has an unanswered question or active discussion.

Useful commands

List review comments and threads:

# Inline review comments
gh api repos/{owner}/{repo}/pulls/{pr}/comments

# Review threads with resolution state (GraphQL)
gh api graphql -f query='
  query($owner:String!,$repo:String!,$pr:Int!){
    repository(owner:$owner,name:$repo){
      pullRequest(number:$pr){
        reviewThreads(first:100){
          nodes{ id isResolved comments(first:50){ nodes{ id body author{login} } } }
        }
      }
    }
  }' -F owner={owner} -F repo={repo} -F pr={pr}

Reply to an inline review comment:

gh api repos/{owner}/{repo}/pulls/{pr}/comments/{comment_id}/replies \
  -f body="Addressed in <commit>: <explanation>"

Resolve a review thread (needs the thread node id from the GraphQL query above):

gh api graphql -f query='
  mutation($threadId:ID!){
    resolveReviewThread(input:{threadId:$threadId}){ thread{ isResolved } }
  }' -F threadId={thread_id}

Mehr Skills von microsoft

oss-growth
microsoft
OSS-Wachstums-Hacker-Persona
agent-framework-azure-ai-py
microsoft
Erstellen Sie Azure AI Foundry-Agents mit dem Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Verwenden Sie dies beim Erstellen persistenter Agents mit AzureAIAgentsProvider, bei der Nutzung gehosteter Tools (Code-Interpreter, Dateisuche, Websuche), bei der Integration von MCP-Servern, bei der Verwaltung von Konversationsthreads oder bei der Implementierung von Streaming-Antworten. Umfasst Funktionstools, strukturierte Ausgaben und Multi-Tool-Agents.
development
airunway-aks-setup
microsoft
Richte AI Runway auf AKS ein – vom leeren Cluster bis zum laufenden Modell. Umfasst Cluster-Überprüfung, Controller-Installation, GPU-Bewertung, Provider-Einrichtung und erste Bereitstellung. WANN: „AI Runway einrichten“, „AKS-Cluster onboarden“, „AI Runway installieren“, „airunway setup“, „Modell auf AKS bereitstellen“, „GPU-Inferenz auf AKS“, „KAITO-Setup auf AKS“, „LLM auf AKS ausführen“, „vLLM auf AKS“, „Modell-Serving auf AKS einrichten“, „AI Runway-Controller“.
devops
appinsights-instrumentation
microsoft
Leitfaden zur Instrumentierung von Webanwendungen mit Azure Application Insights. Bietet Telemetriemuster, SDK-Einrichtung und Konfigurationsreferenzen. WANN: wie man eine App instrumentiert, App Insights SDK, Telemetriemuster, was ist App Insights, Application Insights-Anleitung, Instrumentierungsbeispiele, APM-Best Practices.
devops
applicationinsights-web-ts
microsoft
Instrumentieren Sie Browser-/Web-Apps mit dem Application Insights JavaScript SDK (@microsoft/applicationinsights-web). Verwenden Sie es für Real User Monitoring (RUM) – Seitenaufrufe, Klicks, AJAX/Fetch-Abhängigkeiten, Ausnahmen, benutzerdefinierte Ereignisse und browser-seitige GenAI-Agent-Traces, die mit Backend-OpenTelemetry-Traces korreliert werden. Umfasst SDK-Loader-Skript und npm-Setup, Framework-Erweiterungen (React, React Native, Angular), Click Analytics, Telemetrie-Initialisierer und OTel-GenAI-Semantik-Konventionen für Agent-/Tool-/Modell-Spans, die vom Browser ausgegeben werden.
devops
azure-ai-anomalydetector-java
microsoft
Erstellen Sie Anomalieerkennungsanwendungen mit dem Azure AI Anomaly Detector SDK für Java. Verwenden Sie dies bei der Implementierung von univariater/multivariater Anomalieerkennung, Zeitreihenanalyse oder KI-gestützter Überwachung.
development
azure-ai-language-conversations-py
microsoft
Implementieren Sie Conversational Language Understanding (CLU) mit dem azure-ai-language-conversations Python SDK. Verwenden Sie dies, wenn Sie mit ConversationAnalysisClient arbeiten, um Gesprächsabsichten und Entitäten zu analysieren, NLP-Funktionen zu erstellen oder Sprachverständnis in Anwendungen zu integrieren.
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 für Python. Verwenden für ML-Workspaces, Jobs, Modelle, Datensätze, Compute und Pipelines. Auslöser: „azure-ai-ml“, „MLClient“, „Workspace“, „Modell-Registry“, „Trainings-Jobs“, „Datensätze“.
development