Merged
Conversation
jsuarezruiz
suggested changes
Nov 3, 2025
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR adds comprehensive documentation for PR review processes, test validation procedures, and instrumentation guidelines for the .NET MAUI repository. It introduces three new documentation files and updates the copilot instructions to reference them.
Key changes:
- Adds a detailed PR Test Validation Guide for ensuring UI tests properly validate fixes
- Introduces an Instrumentation Guide for debugging and testing MAUI code
- Creates a PR Reviewer agent definition with three review modes (Quick, Thorough, Deep)
- Adds quick reference prompts for using the PR reviewer agent
Reviewed Changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| docs/PR-Test-Validation-Guide.md | New comprehensive guide for validating that UI tests in PRs actually test what they claim to test, including revert testing procedures |
| .github/prompts/pr-reviewer.prompt.md | New quick reference guide for using the pr-reviewer agent with example prompts |
| .github/instructions/instrumentation.instructions.md | New detailed guide for instrumenting .NET MAUI source code for debugging and testing |
| .github/copilot-instructions.md | Updates Additional Resources section to reference the three new guides |
| .github/agents/pr-reviewer.md | New agent definition for conducting thorough PR reviews with three review modes and comprehensive guidelines |
Comments suppressed due to low confidence (1)
.github/instructions/instrumentation.instructions.md:1
- The code uses
platformViewwhich is undefined in this scope. It should beplatformViewfrom the null-check on line 104. This appears to be correct, but ensure the example is clear that this code should be inside the if statement block whereplatformViewis defined.
---
- Remove broken link to RTL-Testing-Guide.md (file doesn't exist) - Update instrumentation guide example to use Task.Delay instead of Dispatcher.DispatchDelayed for better clarity Addresses: #32340 (comment) Addresses: #32340 (comment)
- Add dedicated Security section to code review checklist covering: - Hardcoded secrets detection - External endpoint usage in tests - Input validation - Secure data handling - Dependency security - Platform permissions - Expand PR splitting guidance with specific scenarios: - Separate refactoring from bug fixes - Split unrelated documentation updates - Separate new features from fixes - Split multi-platform changes - Break up large API additions Addresses: #32340 (comment) Addresses: #32340 (comment)
PureWeen
requested review from
jonathanpeppers,
jsuarezruiz,
mattleibow and
rolfbjarne
- Change default mode from Quick (code-only) to Thorough (with testing) - Expand trigger words to include 'thorough', 'validation', 'review', 'check' - Add 'Core Philosophy' section emphasizing hands-on testing over code review - Add 'Edge Case Discovery' section with comprehensive test scenarios - Add explicit 'Default Mode Selection Logic' decision tree - Update mode examples to show reasoning for mode selection - Mark Quick Mode as 'NOT RECOMMENDED' and requiring explicit user request - Add warnings in output format section about default behavior Fixes issue where 'thorough review and validation' incorrectly triggered Quick Mode instead of Thorough Mode with actual device testing.
- Add new 'Handling Build Errors' section after 'Build and Deploy' - Update Thorough Mode to reference build error handling (step 5) - Add explicit instructions to STOP and ask for help after 1-2 failed fix attempts - Provide template message for reporting build errors to user - Add 'What NOT to do' list to prevent silent mode switching - Clarify that incomplete testing means incomplete review
- Update Quick Mode examples to require explicit 'quick' keyword - Add 'Please review PR #XXXXX' to Thorough Mode (it's the default) - Add 'Important: Default Behavior' section explaining mode selection - Add 'What Happens If Build Fails?' section documenting error handling - Mark Quick Mode as NOT RECOMMENDED to align with agent instructions - Clarify that simple 'review this PR' defaults to Thorough Mode (with testing) This ensures the prompt guide is consistent with the agent instructions where Thorough Mode (with testing) is the default for all PR reviews.
Member
Author
|
@copilot can you create a pr reviewing this pr? Make sure to evaluate best practices with custom agents and prompts This will be a custom agent that will be ran locally using cli, vscode and eventually github copilot |
Contributor
- Add clear section explaining when to use each app - Sandbox app: For PR validation and testing (99% of reviews) - TestCases.HostApp: Only for writing/validating UI tests (1%, explicit request only) - Emphasize Sandbox builds in ~2min vs HostApp ~20min - Add decision tree and examples to prevent confusion - Update Core Philosophy and Thorough Mode sections to reinforce this
rmarinho
approved these changes
Nov 7, 2025
PureWeen
added
area-infrastructure
kubaflo
added
area-ai-agents
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.