Conversation
Co-authored-by: mikeharder <9459391+mikeharder@users.noreply.github.com>
Co-authored-by: mikeharder <9459391+mikeharder@users.noreply.github.com>
mikeharder
left a comment
mikeharder
left a comment
There was a problem hiding this comment.
These auto-gen instructions look good enough to me as a starting point, future updates can be made manually, or by asking copilot to update its own instructions.
mikeharder
requested review from
AkhilaIlla,
raosuhas,
tejaswiMinnu and
weshaggard
as code owners
|
@copilot: disable formatting on agent instructions, by adding |
Co-authored-by: mikeharder <9459391+mikeharder@users.noreply.github.com>
Co-authored-by: mikeharder <9459391+mikeharder@users.noreply.github.com>
There was a problem hiding this comment.
Pull request overview
Adds repository-specific GitHub Copilot guidance and updates formatting ignores so instruction files aren’t auto-formatted.
Changes:
- Added
.github/copilot-instructions.mddocumenting repo architecture, build/test commands, and key conventions. - Updated
.github/.prettierignoreto exclude*instructions.mdfiles from Prettier formatting.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| .github/copilot-instructions.md | Introduces Copilot agent instructions for working effectively in this Rush monorepo. |
| .github/.prettierignore | Excludes instruction markdown files from Prettier formatting runs under .github/. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: mikeharder <9459391+mikeharder@users.noreply.github.com>
Co-authored-by: mikeharder <9459391+mikeharder@users.noreply.github.com>
.github/copilot-instructions.md
Outdated
|
|
||
| ### Adding New Linter Rules | ||
| 1. Add rule to staging pipeline first (set to run only in staging) | ||
| 2. Wait for at least 10 PRs to verify no false positives |
There was a problem hiding this comment.
isnt this an iterative development? How will it know to analyze production PR's and move to prod?
Also, I dont think the stagingOnly has any significance now as there isnt a staging pipeline.
Instead we can ask it to add the label to trigger the staging-lint check pipeline. Wish it can also validate the errors generated.
.github/copilot-instructions.md
Outdated
| 5. For significant changes, manually update `changelog.md` | ||
|
|
||
| ### Adding New Linter Rules | ||
| 1. Add rule to staging pipeline first (set to run only in staging) |
There was a problem hiding this comment.
@copilot
There is no staging pipeline and hence the stagingOnly option doesnt really have any significance.
Instead update this to have the rule name added as a label which will trigger the staging-lint check pipeline.
Also, is there a way you can validate if the errors generated are accurate
There was a problem hiding this comment.
Updated the instructions to reflect the current workflow using test-<RuleName> labels to trigger the staging-lint check pipeline. Added a new section explaining how to test rules with the staging-lint check workflow, and clarified that stagingOnly is now legacy. (7f931c7)
Regarding validation of errors: The staging-lint check workflow generates a linter-findings.txt artifact that you can download to review the violations found. Manual review is currently needed to validate accuracy.
Co-authored-by: AkhilaIlla <36493984+AkhilaIlla@users.noreply.github.com>
.github/copilot-instructions.md
Outdated
| 1. Add the new rule with appropriate severity and documentation | ||
| 2. Add a label to your PR in the format `test-<RuleName>` to trigger the staging-lint check pipeline | ||
| 3. Verify the rule works correctly by checking the staging-lint check results | ||
| 4. Wait for at least 10 PRs in azure-rest-api-specs to validate no false positives |
There was a problem hiding this comment.
@copilot how are you planning to implement these 2 instructions
There was a problem hiding this comment.
These instructions are written for human developers, not for automated implementation. Steps 4-5 describe a validation and release process:
Step 4 (Wait for 10 PRs): This is a manual monitoring step where developers review staging-lint results across multiple PRs to ensure the rule doesn't produce false positives. This requires human judgment and cannot be automated.
Step 5 (Create release PR): This follows the release process in CONTRIBUTING.md, which involves running rush change, updating changelogs, and coordinating deployment. While I can help create the PR, the deployment coordination requires human oversight.
If you'd like to clarify that these are manual steps, I can update the wording to make it more explicit.
There was a problem hiding this comment.
There is no release PR process.
the author validates the rule using the staging lint check and then the rule is released.
@copilot update based on this context
There was a problem hiding this comment.
Updated the instructions to reflect the actual workflow. Removed references to waiting for 10 PRs and creating a separate release PR. The new steps show that after validation with the staging-lint check, the rule is automatically deployed when the PR is merged. (a25e910)
Co-authored-by: AkhilaIlla <36493984+AkhilaIlla@users.noreply.github.com>
.github/copilot-instructions.mdwith comprehensive instructionsWorkspace.resolveRef(enhancedSchema, inventory)matching actual APIEnhancedSchema | undefined)test-<RuleName>labels for staging-lint checkstagingOnlyis legacy and staging-lint check is the current approach**/*instructions.mdto.github/.prettierignoreOriginal prompt
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.