feat(rpi): consolidate lifecycle around reusable skills#2474
Open
agreaves-ms wants to merge 23 commits into
Open
feat(rpi): consolidate lifecycle around reusable skills#2474agreaves-ms wants to merge 23 commits into
agreaves-ms wants to merge 23 commits into
Conversation
- implement rpi-researcher to execute delegated research lanes - update documentation to reflect new agent and its purpose - enhance existing rpi collection with improved descriptions and structure 🔍 - Generated by Copilot
- delete hve-artifact-author, hve-artifact-explorer, hve-artifact-reviewer, hve-artifact-test-designer, hve-artifact-test-reviewer, and hve-artifact-validator agents - introduce hve-builder agent for managing the HVE Builder lifecycle - update README to reflect changes in available agents 🔧 - Generated by Copilot
…er agent - Consolidate agent responsibilities by removing hve-builder agent - Introduce rpi-researcher agent for handling RPI research lanes - Update documentation and references to reflect the changes 🔄 - Generated by Copilot
- add rpi-research playbook to handle research artifacts - update workflow to utilize rpi-research for decision-critical exploration - enhance stage dispatch documentation for clarity on research processes - adjust artifact types documentation to reflect new research capabilities 🔍 - Generated by Copilot
…lugin.json - delete implementation-validator, phase-implementor, plan-validator, and rpi-validator markdown files - add rpi-planner and rpi-plan-critique agent definitions - update project-planning README to reflect new agent features - revise rpi plugin description for clarity 🔒 - Generated by Copilot
- update research.md to clarify template usage - modify research.md template for artifact path formatting - add rpi-researcher agent to project planning collection - update various documentation files to reflect new links and context management practices 🔒 - Generated by Copilot
- delete task-challenger agent definition and expectations - update agent behavior suite to reflect removal - adjust baseline equivalence stimuli to exclude task-challenger - introduce rpi-challenger for adaptive questioning 🔄 - Generated by Copilot
- replace task-plan with sample-prompt in tests - update agent references from task-research to sample-agent - ensure coverage checks for new agent and prompt names 🔍 - Generated by Copilot
…tail - specify reasoning profile and fallback options for phase implementation subagent - improve guidance on task execution and evidence provision 🔧 - Generated by Copilot
🔒 - Generated by Copilot
- change ms.date to 2026-07-15 in multiple files - update keywords for clarity and relevance - refine task descriptions for better guidance 🔖 - Generated by Copilot
…larity - refine fidelity descriptions in test methodology - clarify capability-bearing frontmatter preservation rules - enhance artifact types and extending HVE Builder documentation - adjust review rubric for non-tool capability preservation - improve workflow contract to emphasize non-tool boundaries 📚 - Generated by Copilot
- route behavior gates and research through canonical skills - return tester artifacts for lead-owned persistence - refresh generated references and remove retired asset docs - safely reconcile orphaned asset documentation - expand conformance and generator validation coverage 🔧 - Generated by Copilot
- separate functional, non-functional, and acceptance requirements - delegate ADR research activation to shared instructions 🛠️ - Generated by Copilot
- separate local-safe checks from CI-owned commands - update RPI planning summaries and walkthrough ledgers - rename CI evaluation and browser test scripts 🧭 - Generated by Copilot
- sync RPI prompt packaging and generated references - exclude browser reports from frontmatter validation - correct documentation metadata and eval spell annotations 🛠️ - Generated by Copilot
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #2474 +/- ##
=======================================
Coverage ? 82.71%
=======================================
Files ? 154
Lines ? 20785
Branches ? 13
=======================================
Hits ? 17193
Misses ? 3590
Partials ? 2
Flags with carried forward coverage won't be shown. Click here to find out more.
🚀 New features to boost your workflow:
|
Contributor
Eval Execution✅ Status: Passed — no merge-blocking failures (147 advisory assertion failure(s) present)
|
Contributor
Dependency Review SummaryThe full dependency review summary was too large to display here (12251KB, limit is 1024KB). Please download the artifact named "dependency-review-summary" to view the complete report. |
- replace Docusaurus-escaping links with public repository URLs - add conformance coverage for five changed AI artifacts - regenerate agent eval inventory and aggregate spec 🛠️ - Generated by Copilot
rezatnoMsirhC
approved these changes
Jul 17, 2026
Contributor
There was a problem hiding this comment.
Noting the behavioral differences from task-challenger for anyone migrating from the old surface.
Scope: Both operate across lifecycle stages. Neither was limited to completed implementations; the previous CUSTOM-AGENTS.md description was an inaccurate summary of the actual agent.
Question strategy: task-challenger imposed a mandatory What→How→Why grammar per topic, in that fixed sequence, with a hard rule of two probes maximum per point before marking it unresolved and moving on. rpi-challenger reads the supplied artifacts first and selects angles from what it finds there. What/Why/How are permitted but not required, and probing depth follows the evidence and user answers rather than a fixed count.
Leading questions: Prohibited in both.
Handoff model: task-challenger had explicit handoff buttons wired to Task Researcher, Task Planner, and Task Implementor. rpi-challenger is advisory only: it names the relevant rpi-* skill when an unresolved item warrants follow-up but does not dispatch automatically.
Session artifact path: Both produce a persistent challenge record. The path changed from .copilot-tracking/challenges/{{YYYY-MM-DD}}-{{topic}}-challenge.md (flat) to .copilot-tracking/challenges/{{YYYY-MM-DD}}/{{task_slug}}-challenge.md (subdirectory per date).
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Dependency Review — All Checks Passed ✅
This PR does not introduce version bumps or new dependencies. The dependency-adjacent changes are limited to build script taxonomy and workflow command references. All safety checks passed.
Changes Reviewed
| File | Change Type | Classification |
|---|---|---|
package.json |
Script renaming (eval:* → ci:eval:*, lint:all → validate:local) |
No dependency change |
docs/docusaurus/package.json |
Script renaming (test:e2e → ci:test:e2e) |
No dependency change |
.github/workflows/docusaurus-tests.yml |
Quote normalization, test:e2e → ci:test:e2e command reference |
No action version change |
.github/workflows/eval-validation.yml |
eval:* → ci:eval:* npm command references |
No action version change |
.github/workflows/issue-implement.lock.yml |
Auto-generated lock file refresh (agent import removed) | All actions SHA-pinned |
Safety Check Results
- New dependencies: None introduced. ✅
- Dependency version bumps: None. ✅
- License compatibility: N/A — no new or changed packages. ✅
- SHA pinning (GitHub Actions): All references in changed workflow files use SHA + version comment. ✅
actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0- All actions in
issue-implement.lock.ymlmanifest are SHA-pinned.
- Environment synchronization (
.devcontainer/↔copilot-setup-steps.yml): Neither file was modified — no synchronization gap. ✅ - Known vulnerabilities: No dependency changes to assess. ✅
No action required from a dependency-review perspective. Human merge gate applies as usual.
Generated by Dependabot PR Review for #2474 · 74.4 AIC · ⌖ 6.1 AIC · ⊞ 8.4K
♿ - Generated by Copilot
🧪 - Generated by Copilot
- replace stale scenarios with one current bootstrap contract - regenerate the agent behavior aggregate 🧪 - Generated by Copilot
🧪 - Generated by Copilot
🔒 - Generated by Copilot
🧪 - Generated by Copilot
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 join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
feat(rpi): consolidate lifecycle around reusable skills
Description
This PR consolidated the Research, Plan, Implement, Review, and Follow-up lifecycle around reusable
rpi-*skills, a thin RPI Agent wrapper, and bounded research and planning workers. It removed superseded Task agents, fixed lifecycle workers, Memory and checkpoint surfaces, and dedicated Prompt Builder entry points while retaining the three prompt-engineering compatibility skills.RPI lifecycle and evidence
PxxandPxx-Txxmarkers, and stage-specific amendment, change, divergence, critique, and review records.rpi-challengerfor adaptive scope challenges andrpi-plan-critiquefor independent read-only plan assessment.RPI ResearcherandRPI Plannerworkers and routed demonstrated evidence gaps from planning, documentation, Design Thinking, code review, accessibility, privacy, RAI, security, SSSC, and PowerPoint workflows throughrpi-research.HVE Builder and validation
validate:*commands from CI-owned browser, model, moderation, and evaluation lanes underci:*.Packaging, documentation, and evaluations
/rpientry prompt with RPI Agent in the Design Thinking and Project Planning collections.Related Issue(s)
None
Type of Change
Select all that apply:
Code & Documentation:
Infrastructure & Configuration:
AI Artifacts:
hve-builderand addressed all actionable findings.github/instructions/*.instructions.md).github/prompts/*.prompt.md).github/agents/*.agent.md).github/skills/*/SKILL.md).github/hooks/*/*.json)evals/)Other:
.ps1,.sh,.py)Sample Prompts (for AI Artifact Contributions)
User Request:
Execution Flow:
rpi-researchonly for demonstrated evidence gaps.rpi-plancreated the plan and matching phase details, then activatedrpi-plan-critiquefor an independent disposition.rpi-implementexecuted approvedPxxorPxx-Txxscope and recorded changes, validation evidence, amendments, and material divergences.rpi-reviewreconciled the plan and implementation evidence, recorded separate execution and outcome states, and routed defects, decision gaps, evidence gaps, or residual work.Output Artifacts:
Success Indicators:
DIV-xxxchanges toAM-xxxamendments and fresh critique evidence.For detailed contribution requirements, see:
Testing
npm run validate:localpassed on the final tree. Asset-doc validation reported the existing human-authored stub baseline as non-blocking warnings with zero errors.npm run validate:docspassed 10 Jest suites and 116 tests, along with Docusaurus linting, label-registry validation, and TypeScript checking.npm run ci:docs:test:e2ecompleted the production build and passed 176 Playwright tests with 2 intentional skips, including all normal and forced-colors axe scans.npm run spell-checkpassed 1,249 files with zero issues.npm run lint:md-linkscompleted successfully.git diff --check origin/main...HEADpassed, and all 18 commit subjects followed conventional commit syntax.Note
Add manual testing descriptions when applicable.
Checklist
Required Checks
AI Artifact Contributions
hve-builderreview mode to review contributionhve-builderreviewRequired Local Checks
The following local-safe validation commands must pass before merging:
npm run validate:localnpm run validate:docsnpm run spell-checknpm run lint:md-linksSecurity Considerations
GHCP Artifact Maturity
Warning
This PR includes experimental GHCP artifacts that may have breaking changes.
.github/agents/accessibility/accessibility-planner.agent.md.github/agents/coding-standards/code-review.agent.md.github/agents/coding-standards/subagents/code-review-walkback.agent.md.github/agents/hve-core/task-challenger.agent.md(removed).github/agents/privacy/privacy-planner.agent.md.github/agents/privacy/privacy-reviewer.agent.md.github/agents/project-planning/network-isa95-planner.agent.md.github/agents/rai-planning/rai-planner.agent.md.github/agents/security/security-planner.agent.md.github/agents/security/sssc-planner.agent.md.github/instructions/accessibility/accessibility-identity.instructions.md.github/instructions/project-planning/adr-handoff.instructions.md.github/instructions/project-planning/adr-standards.instructions.md.github/instructions/rai-planning/rai-identity.instructions.md.github/instructions/security/identity.instructions.md.github/instructions/security/sssc-planner.instructions.md.github/instructions/security/standards-mapping.instructions.md.github/prompts/experimental/graph-research.prompt.md.github/prompts/hve-core/evals-import.prompt.md.github/prompts/hve-core/task-challenge.prompt.md(removed).github/prompts/hve-core/vally-test-write.prompt.md.github/skills/hve-core/vally-tests/SKILL.md.github/agents/design-thinking/dt-coach.agent.md.github/prompts/design-thinking/dt-handoff-*-space.prompt.md.github/skills/design-thinking/dt-rpi-integration/SKILL.md.github/agents/accessibility/accessibility-planner.agent.md.github/agents/coding-standards/code-review.agent.md.github/agents/coding-standards/subagents/code-review-walkback.agent.md.github/agents/hve-core/task-challenger.agent.md.github/agents/privacy/*.agent.md.github/agents/project-planning/network-isa95-planner.agent.md.github/agents/rai-planning/rai-planner.agent.md.github/agents/security/{security-planner,sssc-planner}.agent.md.github/instructions/accessibility/accessibility-identity.instructions.md.github/instructions/project-planning/{adr-handoff,adr-standards}.instructions.md.github/instructions/rai-planning/rai-identity.instructions.md.github/instructions/security/{identity,sssc-planner,standards-mapping}.instructions.md.github/prompts/experimental/graph-research.prompt.md.github/prompts/hve-core/{evals-import,vally-test-write}.prompt.md.github/prompts/hve-core/task-challenge.prompt.md.github/skills/hve-core/vally-tests/SKILL.md.agent.mdfiles.prompt.mdfiles.instructions.mdfilesSKILL.mdfilesGHCP Maturity Acknowledgment
Additional Notes
pr-validation-successmerge gate remains the final merge-readiness signal after all required CI jobs complete.