Agent update

[Malcolmnixon]

Pull Request

Description

This PR updates the agents and applies corrections for design back-feeding into requirements and then improvements from formal-reviews

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

Closes #

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
• Self-validation tests pass:
  dotnet run --project src/DemaConsulting.ReviewMark --configuration Release --framework net10.0
--no-build -- --validate
• 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:

• Spell checker passes: cspell "**/*.{md,cs}"
• Markdown linter passes: markdownlint "**/*.md"
• YAML linter passes: yamllint .

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

[Malcolmnixon]

@copilot Please use the lint-fix agent to fix lint issues

[Copilot]

Pull request overview

This PR updates ReviewMark’s agent/standards documentation and back-feeds design clarifications into ReqStream requirements, alongside a set of targeted test additions and small correctness/consistency improvements in configuration/indexing.

Changes:

• Expand/clarify requirements + design docs (ReqStream + design markdown) for CLI, configuration, indexing, and self-test behavior.
• Add/strengthen MSTest coverage for validation/self-test, glob matching, configuration linting, indexing load/scan, and --enforce exit-code behavior.
• Minor code adjustments to enforce whitespace-only paths linting and update GlobMatcher documentation reference.

Reviewed changes

Copilot reviewed 46 out of 46 changed files in this pull request and generated 4 comments.

Show a summary per file

File	Description
test/DemaConsulting.ReviewMark.Tests/SelfTest/ValidationTests.cs	Adds assertion strictness + new unsupported-results-extension test.
test/DemaConsulting.ReviewMark.Tests/SelfTest/SelfTestTests.cs	Adds console-summary assertions, TRX XML parsing, and a new non-zero-exit scenario.
test/DemaConsulting.ReviewMark.Tests/ProgramTests.cs	Adds tests for --enforce exit-code vs warning behavior.
test/DemaConsulting.ReviewMark.Tests/Indexing/IndexingTests.cs	Adds tests for none/url evidence source loading and PDF keyword parsing scan path.
test/DemaConsulting.ReviewMark.Tests/Configuration/ReviewMarkConfigurationTests.cs	Adds lint test for whitespace-only review-set paths.
test/DemaConsulting.ReviewMark.Tests/Configuration/GlobMatcherTests.cs	Adds whitespace baseDirectory rejection + forward-slash normalization test.
test/DemaConsulting.ReviewMark.Tests/Configuration/ConfigurationTests.cs	Strengthens elaboration assertions; adds unknown-ID + rename-invariant fingerprint tests.
test/DemaConsulting.ReviewMark.Tests/Cli/ContextTests.cs	Adds invalid --log path test expecting InvalidOperationException.
test/DemaConsulting.ReviewMark.Tests/Cli/CliTests.cs	Improves test naming and invokes real Program.Main via reflection for invalid-args exit code.
src/DemaConsulting.ReviewMark/Indexing/ReviewIndex.cs	Simplifies Save exception handling (removes redundant catch).
src/DemaConsulting.ReviewMark/Configuration/ReviewMarkConfiguration.cs	Treats whitespace-only paths as missing during lint validation.
src/DemaConsulting.ReviewMark/Configuration/GlobMatcher.cs	Updates internal comment to point to the new glob-matcher design doc location.
docs/user_guide/introduction.md	Clarifies --depth description wording.
docs/reqstream/review-mark/self-test/self-test.yaml	Refines self-test requirements; adds exit-code and console-summary requirements.
docs/reqstream/review-mark/program.yaml	Clarifies Program entry-point requirement; adds enforce/issue-handling requirement.
docs/reqstream/review-mark/indexing/review-index.yaml	Refines ReviewIndex requirements text (load/scan/save/query behaviors).
docs/reqstream/review-mark/indexing/path-helpers.yaml	Tightens PathHelpers requirements wording (less algorithm detail).
docs/reqstream/review-mark/indexing/indexing.yaml	Adds requirement coverage for load none/url tests and scan valid PDF scenario.
docs/reqstream/review-mark/configuration/review-mark-configuration.yaml	Restructures configuration requirements (linting/null-on-error/depth requirements).
docs/reqstream/review-mark/configuration/glob-matcher.yaml	Splits/clarifies glob-matcher requirements (null/empty handling + normalization).
docs/reqstream/review-mark/configuration/configuration.yaml	Clarifies fingerprinting requirement, adds malformed-yaml and unknown-id requirements.
docs/reqstream/review-mark/cli/context.yaml	Clarifies context responsibilities; adds log-file-open failure requirement.
docs/reqstream/review-mark/cli/cli.yaml	Clarifies CLI subsystem requirements and updates referenced test names.
docs/design/review-mark/self-test/validation.md	Adds depth-flag scenario to self-validation design coverage list.
docs/design/review-mark/review-mark.md	Expands system design: enforce semantics + operational modes + exit code behavior.
docs/design/review-mark/program.md	Clarifies lint/index/definition flows and HandleIssues behavior in design doc.
docs/design/review-mark/indexing/review-index.md	Expands Load/Scan error behavior and HttpClient-injected overload documentation.
docs/design/review-mark/indexing/path-helpers.md	Documents passthrough platform exceptions behavior.
docs/design/review-mark/indexing/indexing.md	Adds subsystem data-flow description and API summary.
docs/design/review-mark/configuration/review-mark-configuration.md	Updates duplicate-id validation description to match implementation.
docs/design/review-mark/configuration/configuration.md	Updates ElaborateReviewSet signature documentation.
docs/design/review-mark/cli/context.md	Expands argument parsing design details + depth and IDisposable contracts.
docs/design/review-mark/cli/cli.md	Clarifies CLI unit description and adds dependency note.
docs/design/introduction.md	Fixes guide link target to user guide.
README.md	Clarifies --dir behavior description.
AGENTS.md	Updates docs folder tree + standards selection matrix for Requirements principles.
.reviewmark.yaml	Updates Purpose review-set title/comment and coverage paths to include user guide.
.github/standards/testing-principles.md	Clarifies requirements-vs-tests expectations (requirements need tests; tests may be unlinked).
.github/standards/technical-documentation.md	Tightens Pandoc collection mandatory file list and creation guidance.
.github/standards/software-items.md	Adds “Software Package” category and expands artifact model guidance.
.github/standards/requirements-principles.md	New: defines requirement unidirectionality + test linkage expectations.
.github/standards/reqstream-usage.md	Refactors ReqStream standards to align with new requirements principles and improves examples.
.github/agents/software-architect.agent.md	New: architecture interview agent definition and deliverable template.
.github/agents/quality.agent.md	Updates agent guidance to reflect “tests may be unlinked” and new-feature vs test-only changes.
.github/agents/formal-review.agent.md	Adds required standards references for formal review agent.
.github/agents/developer.agent.md	Adds build/test expectations for code changes and shifts step numbering.

---

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

[Malcolmnixon]

@copilot The lint-fix agent can't fix the long tables - no amount of folding will make them fit. Please run lint.ps1 then identify the tables that are too long. Examine them, and consider converting them to bullet lists (which are friendly for compiling to PDF) or failing that if it really has to be a table then fall back to grid-tables.

[Copilot]

@copilot The lint-fix agent can't fix the long tables - no amount of folding will make them fit. Please run lint.ps1 then identify the tables that are too long. Examine them, and consider converting t...

Fixed in d8b3dfb. Ran lint.ps1 to identify all issues, then converted the offending tables to bullet lists across the design docs (cli.md, context.md, configuration.md, indexing.md, review-index.md) and fixed the alignment issue in user_guide/introduction.md. Also wrapped the long title: lines in the reqstream YAML files. All lint checks now pass.

[Malcolmnixon]

@copilot apply changes based on the comments in this thread

[Copilot]

@copilot apply changes based on the comments in this thread

Applied all three review changes in 6351b70:

1. review-index.md — Removed the duplicate "selects a loading strategy" sentence; the source type list now follows the single introduction directly.
2. SelfTestTests.cs — Renamed SelfTest_Run_ValidationTestFails_ExitCodeIsNonZero → SelfTest_Run_UnsupportedResultsFormat_ExitCodeIsNonZero to accurately reflect the unsupported-results-format scenario.
3. self-test.yaml — Broadened the requirement title/justification to cover any validation error (including results output errors) and updated the tests: link to the renamed method.

[Copilot]

Pull request overview

Copilot reviewed 46 out of 46 changed files in this pull request and generated 1 comment.

---

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

[Malcolmnixon]

@copilot apply changes based on the comments in this thread

[Copilot]

@copilot apply changes based on the comments in this thread

Fixed in 12440a6. Validation_Run_WithUnsupportedResultsFileExtension_WritesError now saves/restores both Console.Out and Console.Error, redirecting stderr to a StringWriter to prevent leakage into test output logs. Also added an assertion that the captured error output is non-empty.