STAR copilot reviews #762
Draft
STAR copilot reviews #762
Conversation
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
…which couldn't possibly cause any side effects, but lets be safe about it shall we?)
…oken count while preserving its meaning.
…ving the AI's understanding of the document.
Apply STAR coding standards in copilot-based reviews
Minor code cleanups
Co-authored-by: Copilot <[email protected]>
Co-authored-by: Copilot <[email protected]>
Co-authored-by: Copilot <[email protected]>
Co-authored-by: Copilot <[email protected]>
Co-authored-by: Copilot <[email protected]>
Co-authored-by: Copilot <[email protected]>
… into STAR-REPO-AI
More minor cleanups...
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
This PR provides a copilot instructions file including a set of coding standards based on the STAR c++ coding standards adopted in 2015 link. The goal is to enable copilot reviews of pull requests to make suggestions which will better align incoming codes with out standards.
The instructions file provides some initial prompts, intended to direct the LLM utilized by copilot to better analyze the codes presented to it, and to not propose changes which turn around and violate the standards.
The coding standards in this document are derived from our 2015 standards document. Changes have been made aimed at reducing the number of tokens the document presents to the LLMs, and making the standards more imperative. In that effort I employed LLM to ensure that changes from one iteration to the next did not significantly alter the meaning of the standards (as understood by the LLM). I have reviewed the end product against the original, and believe them to be consistent. Reviewers are kindly asked to point out where my AI friend and I have it wrong ;)