feat(rpi): refine RPI and HVE artifact workflows

[Allen Greaves (agreaves-ms)]

Pull Request

Description

This PR refines the RPI and HVE artifact workflows around explicit operating modes, durable
task-centered evidence, bounded delegation, and terminal review or testing decisions. It also
migrates pull request preparation from a prompt and broad instruction set to a dedicated skill with
focused local preflight checks.

RPI lifecycle

• The RPI Agent and phase skills now distinguish manual and confirmed automatic operation, preserve
  stable task identity, and record user-owned, agent-owned, or retained decisions with provenance.
• Research and planning use dated task-centered artifacts, explicit readiness gates, bounded lane or
  phase delegation, and task-local requirements and implementation detail.
• Review construction moves to the new RPI Review Builder, while the parent retains final outcomes,
  route decisions, and user conversation.
• RPI guidance and generated references now describe standard review depth, explicit deep review,
  stranded-run recovery, and distinct routing for defects, decision gaps, evidence gaps, and residual
  work.

HVE artifact lifecycle

• HVE Builder now composes creation, improvement, refactoring, review, replacement, validation, and
  workflow-extension modes while keeping detailed criteria in on-demand references.
• HVE Builder Tester is the one-shot black-box behavior gate for a frozen candidate. It records
  fidelity and independent grading, and a non-Pass result ends the run instead of starting a same-run
  edit and retest loop.
• Compatibility aliases for prompt creation, analysis, and refactoring remain available, while current
  guidance routes new work through HVE Builder and HVE Builder Tester.

Pull request workflow and distribution

• Pull request preparation is now a dedicated skill with Bash and PowerShell context collectors,
  repository-template preservation, committed-diff analysis, focused changed-area validation, and one
  approval before push or GitHub write.
• Plugin membership adds the RPI Review Builder agent and pull-request skill, and removes the former
  pull-request prompt and package-scoped instruction.
• Generated reference documentation, RPI agent expectations, and behavior-conformance evals are
  synchronized with the new workflow contracts.

Related Issue(s)

None identified in the branch or commit history.

Type of Change

Select all that apply:

Code & Documentation:

• Bug fix (non-breaking change fixing an issue)
• New feature (non-breaking change adding functionality)
• Breaking change (fix or feature causing existing functionality to change)
• Documentation update

Infrastructure & Configuration:

• GitHub Actions workflow
• Linting configuration (markdown, PowerShell, etc.)
• Security configuration
• DevContainer configuration
• Dependency update

AI Artifacts:

• Reviewed contribution with hve-builder and addressed all actionable findings
• Copilot instructions (.github/instructions/*.instructions.md)
• Copilot prompt (.github/prompts/*.prompt.md)
• Copilot agent (.github/agents/*.agent.md)
• Copilot skill (.github/skills/*/SKILL.md)
• Copilot hook (.github/hooks/*/*.json)
• Eval spec added/updated for changed AI artifacts (evals/)

Note for AI Artifact Contributors:

• Agents: Research, indexing/referencing other project (using standard VS Code GitHub Copilot/MCP tools), planning, and general implementation agents likely already exist. Review .github/agents/ before creating new ones.
• Skills: Must include both bash and PowerShell scripts. See Skills.
• Model Versions: Contributions MUST target models listed in the model catalog (scripts/linting/model-catalog.json) whose provider appears in providerAllowlist and whose status is ga or preview. Run npm run lint:models to validate references.
• See Agents Not Accepted and Model Version Requirements.

Other:

• Script/automation (.ps1, .sh, .py)
• Other (please describe):

Sample Prompts (for AI Artifact Contributions)

User Request:

Take this repository change through RPI automatically with standard review depth, then prepare a pull
request using focused changed-area checks.

Execution Flow:

RPI routes the work through Research, Plan, Implement, and Review while persisting phase evidence and
parent decisions. The pull-request skill then collects committed branch context, preserves this
repository template, runs changed-area checks, and requests approval before any GitHub write.

Output Artifacts:

• Dated research, plan, changes, critique, and review records under .copilot-tracking/
• One review record with parent decisions and explicit next routes
• A template-backed pull request body at .copilot-tracking/pr/pr.md

Success Indicators:

Each phase reports its durable artifact and decision state, the review records a bounded verdict, and
the prepared pull request matches the committed diff without pushing or writing to GitHub before
approval.

For detailed contribution requirements, see:

• Common Standards: docs/contributing/ai-artifacts-common.md - Shared standards for XML blocks, markdown quality, RFC 2119, validation, and testing
• Agents: docs/contributing/custom-agents.md - Agent configurations with tools and behavior patterns
• Prompts: docs/contributing/prompts.md - Workflow-specific guidance with template variables
• Instructions: docs/contributing/instructions.md - Technology-specific standards with glob patterns
• Skills: docs/contributing/skills.md - Task execution utilities with cross-platform scripts

Testing

• Passed git diff --check 52abb388bc76da960005ef60dc1c81b768b9b3ed..HEAD
• Passed npm run plugin:validate
• Passed npm run docs:generate:check
• Passed npm run validate:skills (78 skills, zero errors and warnings)
• Passed npm run lint:ai-artifacts
• Passed npm run lint:asset-docs with zero errors and repository-wide advisory warnings
• Passed npm run lint:md
• Passed npm run lint:tables after repair commit cd68fcb6e
• Passed npm run lint:frontmatter
• Passed npm run lint:ps
• Passed shellcheck .github/skills/hve-core/pull-request/scripts/collect-context.sh
• Passed npm run lint:yaml
• Passed npm run spell-check with zero issues
• Passed changed-area link validation with Markdown-Link-Check.ps1 -ChangedFilesOnly

The broad npm run lint:md-links command also ran and reported three unchanged external-link failures
outside this branch. Hosted CI and model-backed behavior execution remain pending.

Checklist

Required Checks

• Documentation is updated (if applicable)
• Files follow existing naming conventions
• Changes are backwards compatible (if applicable)
• Tests added for new functionality (if applicable)

AI Artifact Contributions

• Used hve-builder review mode to review contribution
• Addressed all actionable findings from the hve-builder review
• Verified contribution follows common standards and type-specific requirements

Required Local Checks

The following local-safe validation commands must pass before merging:

• Local validation aggregate: npm run validate:local
• Documentation validation (if docs changed): npm run validate:docs
• Spell checking: npm run spell-check
• Link validation: npm run lint:md-links

Security Considerations

• This PR does not contain any sensitive or NDA information
• Any new dependencies have been reviewed for security issues
• Security-related scripts follow the principle of least privilege

GHCP Membership Changes

• Added .github/agents/hve-core/subagents/rpi-review-builder.agent.md
• Added .github/skills/hve-core/pull-request
• Removed .github/prompts/hve-core/pull-request.prompt.md
• Removed .github/instructions/hve-core/pull-request.instructions.md

Additional Notes

The full validation and documentation aggregates, hosted CI, browser suites, service-dependent tests,
security scans, and model-backed eval execution were not run as part of targeted local preflight.

[Codecov Comments Bot (codecov-commenter)]

Codecov Report

❌ Patch coverage is 0% with 106 lines in your changes missing coverage. Please review.
✅ Project coverage is 83.02%. Comparing base (52abb38) to head (2ded864).
⚠️ Report is 2 commits behind head on main.

Files with missing lines	Patch %	Lines
.../hve-core/pull-request/scripts/Collect-Context.ps1	0.00%	106 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2843      +/-   ##
==========================================
- Coverage   83.14%   83.02%   -0.12%     
==========================================
  Files         183      185       +2     
  Lines       34029    34616     +587     
  Branches       25       27       +2     
==========================================
+ Hits        28292    28740     +448     
- Misses       5734     5873     +139     
  Partials        3        3              

Flag	Coverage Δ
docusaurus	90.60% <ø> (+0.67%)	⬆️
pester	83.41% <0.00%> (-0.43%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
.../hve-core/pull-request/scripts/Collect-Context.ps1	0.00% <0.00%> (ø)

... and 10 files with indirect coverage changes

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[github-actions]

Eval Execution

⚠️ No eval summary was produced.