Repository navigation
Broaden review criteria for multimodal workflows - #5961
aaronpowell wants to merge 1 commit into
Conversation
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> Copilot-Session: a6823cbb-5734-459d-bd6b-f80d2c864943
🚦 Submission status: 👀 Ready for reviewRisk tier: Why this tier
Automated checks
Review
Commands
Updated for |
|
🟡 Contributor Reputation Check: MEDIUM risk
Maintainers: please review this contributor before merging. |
There was a problem hiding this comment.
🔵 Needs a closer look
A maintainer should confirm the broadened submission scope before changes to the canonical code-review policy and both boards’ repository-fit criteria are merged.
No open issues 🎉
What changed in this PR
Broadens both review boards’ guidance to assess Copilot-supported multimodal workflows while preserving independent quality checks. Also improves handling of GitHub HTTP 422 decision failures.
Changes:
- Clarifies that non-coding use or modality alone does not justify rejection.
- Retains checks for user value, provenance, duplication, vendor funnels, responsible use, and appropriate validation.
- Adds actionable HTTP 422 notices and regression tests for the updated behavior and guidance.
| File | Description |
|---|---|
eng/open-pr-board.test.mjs |
Tests multimodal guidance and HTTP 422 notice behavior. |
eng/external-plugin-review-board.test.mjs |
Tests multimodal criteria in prompts and guidance. |
.github/skills/code-review/SKILL.md |
Broadens repository-fit criteria while retaining quality checks. |
.github/extensions/open-pr-board/review-guidance.md |
Removes non-coding use as a standalone rejection reason. |
.github/extensions/open-pr-board/lib/review-prompt.mjs |
Updates review prompts and repository-fit field guidance. |
.github/extensions/open-pr-board/lib/decisions.mjs |
Converts HTTP 422 failures into actionable notices without agent handoff. |
.github/extensions/external-plugin-review-board/review-guidance.md |
Adds workflow-inclusive value and validation criteria. |
.github/extensions/external-plugin-review-board/lib/review-prompt.mjs |
Applies multimodal criteria to initial and repeat reviews. |
Review effort: Balanced (auto)
| " - `gh pr checks <number> -R " + repo + "` when checks are failing, to see which ones and why.", | ||
| " - `gh pr list -R " + repo + " --author <login> --state all` to find the author's sibling PRs. If siblings were closed for a reason, apply it consistently and cite them; flag any open sibling recorded more leniently in `checkNext`.", | ||
| "Judge the submitted result, not assumptions about the tool that produced it. A title ending in 🤖🤖🤖 is a disclosure, not a defect.", | ||
| "Do not limit repository fit to coding or text-based developer tasks. Evaluate Copilot-supported workflows across modalities, including image, video, audio, other media generation, and creative work where applicable. Modality or non-coding use alone is not a rejection reason; assess concrete Copilot relevance, specific standalone user value, knowledge uplift, provenance, product/vendor-funnel evidence, responsible use, and validation appropriate to the workflow.", |
| Recent maintainer decisions (calibrate against these as well as the guidance): | ||
| ${formatHistory(history)} | ||
|
|
||
| Evaluate concrete Copilot relevance and specific standalone user value across supported workflows, not only coding or text-based developer tasks. Image, video, audio, other media-generation, and creative work may be in scope where applicable; modality or non-coding use alone is not a rejection reason. Assess knowledge uplift, provenance, product/vendor-funnel evidence, responsible use, and validation appropriate to the workflow. Preserve rejection of marketing-only funnels, paid or credit-based acquisition paths without standalone user value, duplicates of native Copilot features, and generic content with no meaningful uplift. |
Pull Request Checklist
npm startand verified thatREADME.mdis up to date.mainbranch for this pull request.Description
Broaden the Open PR Board and External Plugin Review Board guidance so reviewers assess Copilot workflows across coding and non-coding modalities, including image, video, audio, and creative work. Clarify that modality alone is not grounds for rejection, while retaining independent checks for user value, knowledge uplift, vendor funnels, provenance, native-feature duplication, responsible use, and workflow-appropriate validation.
Also show an actionable notice for GitHub CLI HTTP 422 decision failures rather than offering an opaque error for agent handoff.
Type of Contribution
Additional Notes
Focused validation passed:
node --test --test-reporter=spec eng/open-pr-board.test.mjs eng/external-plugin-review-board.test.mjs(60 passed, 0 failed).git diff --checkpassed.npm startwas not run; this change does not add resource entries or generated README content. No GitHub Copilot session test was performed.By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.