Fix TestResults-IO review-set structure and add IOTests.cs subsystem test suite

[Copilot]

Pull Request

Description

Corrects the structure of the .reviewmark.yaml review-sets to follow the required pattern where each review-set contains exactly three items: requirements, design, and test suite.

TestResults-IO subsystem review-set was over-populated with all unit-level files. It has been trimmed to the correct three subsystem-level items:

• docs/reqstream/test-results/io/io.yaml — subsystem requirements
• docs/design/test-results/io/io.md — subsystem design
• test/DemaConsulting.TestResults.Tests/IO/IOTests.cs — subsystem test suite

IOTests.cs has been created as the IO subsystem test suite. It exercises the subsystem's public API (Serializer.Identify and Serializer.Deserialize) end-to-end for both TRX and JUnit formats, proving the subsystem works without diving into individual unit internals.

Unit review-sets (TestResults-IO-Serializer, TestResults-IO-TrxSerializer) have had TestHelpers.cs added since those units' test suites use it:

• TestResults-IO-Serializer: added TestHelpers.cs (used by SerializerTests.cs)
• TestResults-IO-TrxSerializer: added TestHelpers.cs (used by TrxExampleTests.cs)
• TestResults-IO-JUnitSerializer: unchanged — JUnitSerializerTests.cs does not use TestHelpers.cs

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Code quality improvement

Related Issues

Pre-Submission Checklist

Before submitting this pull request, ensure you have completed the following:

Build and Test

• Code builds successfully: dotnet build --configuration Release
• All unit tests pass: dotnet test --configuration Release
• Code produces zero warnings

Code Quality

• Code formatting is correct: dotnet format --verify-no-changes
• New code has appropriate XML documentation comments
• Static analyzer warnings have been addressed

Quality Checks

Please run the following checks before submitting:

• All linters pass: ./lint.sh (Unix/macOS) or cmd /c lint.bat / ./lint.bat (Windows)

Testing

• Added unit tests for new functionality
• Updated existing tests if behavior changed
• All tests follow the AAA (Arrange, Act, Assert) pattern
• Test coverage is maintained or improved

Documentation

• Updated README.md (if applicable)
• Updated ARCHITECTURE.md (if applicable)
• Added code examples for new features (if applicable)
• Updated requirements.yaml (if applicable)

Additional Notes

Changes to .reviewmark.yaml and the addition of IOTests.cs. No source library or documentation changes.

[Malcolmnixon]

@copilot Hold on - the TestResults-IO review-set is ENORMOUS.

I gave you clear instructions on what's supposed to be in a review-set:

• System-Architecture review-set MUST have ONLY [system-requirements, design-introduction, system-design, system-test-suite (IntegrationTests.cs, Runner.cs, AssemblyInfo.cs]
• Subsystem review-sets MUST have ONLY [subsystem-requirements, subsystem-design, subsystem-test-suite]
• Unit review-sets MUST have ONLY [unit-requirements, unit-design, unit-test-suite]

TestResults-IO is a subsystem so it's only supposed to have THREE items:

• docs/reqstream/test-results/io/io.yaml - the subsystem requirements
• docs/design/test-results/io/io.md - the subsystem design
• test/DemaConsulting.TestResults.Tests/IO/IOTests.cs - the subsystem test suite (which I notice doesn't exist)

Every subsystem is supposed to have a test suite - a specific subsyste test-suite whose job is to have tests proving the subsystem works - that's separate from the unit test-suites - and those tests will end up utilizing one or more of the units and possibly having tests that look similar to unit tests, but that's how it's supposed to work.

A subsystem is supposed to be reviewable to show it works without having to dive in to all its units. This is a mitigation for agent LLM context windows.

[Copilot]

@copilot Hold on - the TestResults-IO review-set is ENORMOUS.

I gave you clear instructions on what's supposed to be in a review-set:
...

Fixed in 6988e61. TestResults-IO now contains only the three subsystem-level items: io.yaml, io.md, and a new IOTests.cs. The subsystem test suite exercises the IO subsystem's public API (Serializer.Identify and Serializer.Deserialize) end-to-end for both TRX and JUnit formats.

[Copilot]

Pull request overview

Updates the repository’s ReviewMark configuration for the TestResults-IO subsystem to align review-set grouping with the intended subsystem/unit boundaries, and introduces a new end-to-end IO subsystem test suite.

Changes:

• Trimmed TestResults-IO review-set to subsystem-level artifacts (reqs/design/test suite) and removed unit-level files from that subsystem review-set.
• Added test/DemaConsulting.TestResults.Tests/IO/IOTests.cs as the IO subsystem end-to-end test suite (Identify + Deserialize for TRX and JUnit).
• Added TestHelpers.cs into the relevant unit review-sets that depend on it.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
test/DemaConsulting.TestResults.Tests/IO/IOTests.cs	Adds subsystem-level end-to-end tests covering format identification and deserialization for TRX and JUnit.
.reviewmark.yaml	Restructures TestResults-IO to subsystem scope and updates unit review-sets to include shared TestHelpers.cs where used.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.