You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This file contains 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
Introduced a GitHub Actions workflow named ai-review.yml to automate PR reviews and respond to user comments.
The workflow triggers on various pull request events (opened, reopened, ready for review, review requested) and issue comment events (created, edited).
Utilizes Codium-ai/pr-agent@main to perform automated actions, requiring OPENAI_KEY and GITHUB_TOKEN for operation.
Changes walkthrough
Relevant files
Enhancement
ai-review.yml
Integrate PR Agent GitHub Action for Automated Reviews
.github/workflows/ai-review.yml
Added a new GitHub Actions workflow to trigger on pull request events and issue comment events.
Configured the workflow to run on ubuntu-latest.
Set permissions for issues, pull-requests, and contents to write.
Included a step to use Codium-ai/pr-agent@main with environment variables for OPENAI_KEY and GITHUB_TOKEN.
2, because the PR introduces a new GitHub Actions workflow which is relatively straightforward to review. The workflow configuration is simple and focuses on automating PR reviews and responding to user comments, which doesn't involve complex logic.
🧪 Relevant tests
No
🔍 Possible issues
The workflow triggers on both pull request and issue comment events but does not specify any conditions for when the automated actions should run. This could potentially lead to unnecessary runs, consuming GitHub Actions minutes and possibly reaching rate limits.
🔒 Security concerns
Yes, because the workflow uses secrets (OPENAI_KEY and GITHUB_TOKEN) which are sensitive. It's important to ensure that the Codium-ai/pr-agent@main action is from a trusted source to prevent any potential misuse of these secrets.
Code feedback:
relevant file
.github/workflows/ai-review.yml
suggestion
Consider adding conditions to limit when the automated actions should run, especially for issue comment events, to avoid unnecessary workflow runs. For example, you could check the content of the comment and only trigger the workflow for specific commands. [important]
Ensure that the Codium-ai/pr-agent@main action is from a trusted source and regularly maintained. Using actions from untrusted sources can pose a security risk, especially when handling secrets. [important]
Overview:
The review tool scans the PR code changes, and generates a PR review. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on any PR.
When commenting, to edit configurations related to the review tool (pr_reviewer section), use the following template:
The review tool can be configured with extra instructions, which can be used to guide the model to a feedback tailored to the needs of your project.
Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify the relevant sub-tool, and the relevant aspects of the PR that you want to emphasize.
Examples for extra instructions:
[pr_reviewer] # /review #
extra_instructions="""
In the 'possible issues' section, emphasize the following:
- Does the code logic cover relevant edge cases?
- Is the code logic clear and easy to understand?
- Is the code logic efficient?
...
"""
Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
How to enable\disable automation
When you first install PR-Agent app, the default mode for the review tool is:
pr_commands = ["/review", ...]
meaning the review tool will run automatically on every PR, with the default configuration.
Edit this field to enable/disable the tool, or to change the used configurations
Auto-labels
The review tool can auto-generate two specific types of labels for a PR:
a possible security issue label, that detects possible security issues (enable_review_labels_security flag)
a Review effort [1-5]: x label, where x is the estimated effort to review the PR (enable_review_labels_effort flag)
Extra sub-tools
The review tool provides a collection of possible feedbacks about a PR.
It is recommended to review the possible options, and choose the ones relevant for your use case.
Some of the feature that are disabled by default are quite useful, and should be considered for enabling. For example: require_score_review, require_soc2_ticket, and more.
Auto-approve PRs
By invoking:
/review auto_approve
The tool will automatically approve the PR, and add a comment with the approval.
To ensure safety, the auto-approval feature is disabled by default. To enable auto-approval, you need to actively set in a pre-defined configuration file the following:
[pr_reviewer]
enable_auto_approval = true
(this specific flag cannot be set with a command line argument, only in the configuration file, committed to the repository)
You can also enable auto-approval only if the PR meets certain requirements, such as that the estimated_review_effort is equal or below a certain threshold, by adjusting the flag:
[pr_reviewer]
maximal_review_effort = 5
More PR-Agent commands
To invoke the PR-Agent, add a comment using one of the following commands:
/review: Request a review of your Pull Request.
/describe: Update the PR title and description based on the contents of the PR.
Limit workflow permissions to the minimum required.
It's recommended to limit the permissions to the minimum required for the workflow to function. This enhances security by following the principle of least privilege. For instance, if the workflow does not need to write to issues, consider setting issues: read or removing the permission if not needed at all.
Use a specific version for GitHub Actions to ensure stability.
Consider specifying a version for the Codium-ai/pr-agent@main action to ensure stability and predictability of your workflow. Using a specific version or commit hash instead of main can prevent unexpected changes from affecting your workflow.
Add names to all steps for better readability and maintainability.
To improve the maintainability and readability of the workflow, consider adding a name attribute to each step. This will make it easier to identify and troubleshoot steps within the GitHub Actions logs.
Overview:
The improve tool scans the PR code changes, and automatically generates suggestions for improving the PR code. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on a PR.
When commenting, to edit configurations related to the improve tool (pr_code_suggestions section), use the following template:
meaning the improve tool will run automatically on every PR, with summarization enabled. Delete this line to disable the tool from running automatically.
Utilizing extra instructions
Extra instructions are very important for the improve tool, since they enable to guide the model to suggestions that are more relevant to the specific needs of the project.
Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on.
Examples for extra instructions:
[pr_code_suggestions] # /improve #
extra_instructions="""
Emphasize the following aspects:
- Does the code logic cover relevant edge cases?
- Is the code logic clear and easy to understand?
- Is the code logic efficient?
...
"""
Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
A note on code suggestions quality
While the current AI for code is getting better and better (GPT-4), it's not flawless. Not all the suggestions will be perfect, and a user should not accept all of them automatically.
Suggestions are not meant to be simplistic. Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base.
Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project, or use the custom suggestions 💎 tool
With large PRs, best quality will be obtained by using 'improve --extended' mode.
More PR-Agent commands
To invoke the PR-Agent, add a comment using one of the following commands:
/review: Request a review of your Pull Request.
/describe: Update the PR title and description based on the contents of the PR.
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.
Type
enhancement
Description
ai-review.ymlto automate PR reviews and respond to user comments.Codium-ai/pr-agent@mainto perform automated actions, requiringOPENAI_KEYandGITHUB_TOKENfor operation.Changes walkthrough
ai-review.yml
Integrate PR Agent GitHub Action for Automated Reviews.github/workflows/ai-review.yml
and issue comment events.
ubuntu-latest.Codium-ai/pr-agent@mainwith environmentvariables for
OPENAI_KEYandGITHUB_TOKEN.