auto approval feature

[mrT23]

Type

Enhancement

---

Description

• This PR introduces an auto-approval feature to the PR-Agent. This feature allows PRs to be automatically approved if they meet certain conditions.
• The auto-approval feature is disabled by default and can be enabled through the configuration file.
• The PR adds a new method auto_approve to the GitProvider class and its implementation in the GithubProvider class.
• The PRAgent class now includes a list of forbidden CLI arguments and checks to prevent these arguments from being used.
• The PRReviewer class has been updated to check for the 'auto_approve' argument and run the auto-approval logic if it is present.
• The documentation for the auto-approval feature has been added to the help.py file, REVIEW.md, and README.md.

---

Changes walkthrough

	Relevant files
Error handling	pr_agent.py Added forbidden CLI arguments handling in PRAgent                            pr_agent/agent/pr_agent.py Added a list of forbidden CLI arguments in the PRAgent class. Implemented a check in the handle_request method to prevent forbidden arguments from being used. +8/-0
Enhancement	git_provider.py Added auto_approve method to GitProvider                                              pr_agent/git_providers/git_provider.py Added a placeholder auto_approve method in the base GitProvider class. +5/-1      github_provider.py Implemented auto_approve in GithubProvider                                          pr_agent/git_providers/github_provider.py Implemented the auto_approve method to automatically approve a PR. +10/-0    pr_reviewer.py Implemented auto-approval logic in PRReviewer                                    pr_agent/tools/pr_reviewer.py Added a check for 'auto_approve' argument in the run method. Implemented auto_approve_logic method to handle the auto-approval process. +33/-0
Documentation	help.py Added auto-approval guide to help.py                                                      pr_agent/servers/help.py Added a detailed guide on how to use the auto-approval feature. +26/-0    README.md Updated README with auto-approval feature note                                  README.md Added a note about the new auto-approval feature in the News and Updates section. +3/-0      REVIEW.md Added auto-approval documentation to REVIEW.md                                  docs/REVIEW.md Added a detailed explanation of the auto-approval feature. +29/-0
Configuration changes	configuration.toml Added auto-approval settings to configuration.toml                          pr_agent/settings/configuration.toml Added configuration options for the auto-approval feature. +4/-0

---

✨ Usage guide:

---

Overview:
The describe tool scans the PR code changes, and generates a description for the PR - title, type, summary, walkthrough and labels. 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 describe tool (pr_description section), use the following template:

/describe --pr_description.some_config1=... --pr_description.some_config2=...

With a configuration file, use the following template:

[pr_description]
some_config1=...
some_config2=...

Enabling\disabling automation When you first install the app, the default mode for the describe tool is: pr_commands = ["/describe --pr_description.add_original_user_description=true" "--pr_description.keep_original_user_title=true", ...] meaning the describe tool will run automatically on every PR, will keep the original title, and will add the original user description above the generated description. Markers are an alternative way to control the generated description, to give maximal control to the user. If you set: pr_commands = ["/describe --pr_description.use_description_markers=true", ...] the tool will replace every marker of the form pr_agent:marker_name in the PR description with the relevant content, where marker_name is one of the following: type: the PR type. summary: the PR summary. walkthrough: the PR walkthrough. Note that when markers are enabled, if the original PR description does not contain any markers, the tool will not alter the description at all.

Custom labels The default labels of the describe tool are quite generic: [Bug fix, Tests, Enhancement, Documentation, Other]. If you specify custom labels in the repo's labels page or via configuration file, you can get tailored labels for your use cases. Examples for custom labels: Main topic:performance - pr_agent:The main topic of this PR is performance New endpoint - pr_agent:A new endpoint was added in this PR SQL query - pr_agent:A new SQL query was added in this PR Dockerfile changes - pr_agent:The PR contains changes in the Dockerfile ... The list above is eclectic, and aims to give an idea of different possibilities. Define custom labels that are relevant for your repo and use cases. Note that Labels are not mutually exclusive, so you can add multiple label categories. Make sure to provide proper title, and a detailed and well-phrased description for each label, so the tool will know when to suggest it.

Inline File Walkthrough 💎 For enhanced user experience, the describe tool can add file summaries directly to the "Files changed" tab in the PR page. This will enable you to quickly understand the changes in each file, while reviewing the code changes (diffs). To enable inline file summary, set pr_description.inline_file_summary in the configuration file, possible values are: 'table': File changes walkthrough table will be displayed on the top of the "Files changed" tab, in addition to the "Conversation" tab. true: A collapsable file comment with changes title and a changes summary for each file in the PR. false (default): File changes walkthrough will be added only to the "Conversation" tab.

Utilizing extra instructions The describe tool can be configured with extra instructions, 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. Notice that the general structure of the description is fixed, and cannot be changed. Extra instructions can change the content or style of each sub-section of the PR description. Examples for extra instructions: [pr_description] extra_instructions=""" - The PR title should be in the format: '<PR type>: <title>' - The title should be short and concise (up to 10 words) - ... """ Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.

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. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the describe usage page for a comprehensive guide on using this tool.

[codiumai-pr-agent-pro]

PR Description updated to latest commit (b190b18)

[codiumai-pr-agent-pro]

PR Analysis

• 🎯 Main theme: Implementing auto-approval feature
• 📝 PR summary: This PR introduces an auto-approval feature that allows PRs to be automatically approved if they meet certain criteria. It includes changes in the PRAgent, GitProvider, GithubProvider, PRReviewer classes, and updates to the documentation and configuration files.
• 📌 Type of PR: Enhancement
• 🧪 Relevant tests added: No
• ⏱️ Estimated effort to review [1-5]: 4, because the PR introduces a new feature across multiple classes and files, and the logic needs to be carefully reviewed to ensure it works as expected and doesn't introduce any security issues.
• 🔒 Security concerns: No

PR Feedback

💡 General suggestions: The code changes are well-structured and the logic seems sound. However, it would be beneficial to add some tests to ensure the new feature works as expected. Also, consider handling the case where the 'auto_approve' argument is passed but the feature is not enabled in the configuration. Currently, it seems like the PR would just return without any action or feedback to the user.

---

✨ Usage guide:

---

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:

/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...

With a configuration file, use the following template:

[pr_reviewer]
some_config1=...
some_config2=...

Utilizing extra instructions 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 'general suggestions' 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.

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. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the review usage page for a comprehensive guide on using this tool.

[codiumai-pr-agent-pro]

PR Code Suggestions

	Suggestions
performance	Use a set for faster CLI argument lookups.                                    Consider using a set for forbidden_cli_args for faster lookups, especially if this list might grow in the future. pr_agent/agent/pr_agent.py [48] -self.forbidden_cli_args = ['enable_auto_approval'] +self.forbidden_cli_args = {'enable_auto_approval'} Optimize forbidden argument check with set intersection.                      Optimize the loop by checking if any forbidden argument is in args using set intersection, to avoid nested loops. pr_agent/agent/pr_agent.py [63-68] -if args: - for forbidden_arg in self.forbidden_cli_args: - for arg in args: - if forbidden_arg in arg: - get_logger().error(f"CLI argument '{forbidden_arg}' is forbidden") - return False +if args and set(args).intersection(self.forbidden_cli_args): + forbidden_arg = set(args).intersection(self.forbidden_cli_args).pop() + get_logger().error(f"CLI argument '{forbidden_arg}' is forbidden") + return False
maintainability	Ensure self.args is always a list for consistency.               Instead of checking isinstance(self.args, list) every time, ensure self.args is always a list during initialization. pr_agent/tools/pr_reviewer.py [106-109] -if isinstance(self.args, list) and self.args and self.args[0] == 'auto_approve': +if self.args and self.args[0] == 'auto_approve': get_logger().info(f'Auto approve flow PR: {self.pr_url} ...') self.auto_approve_logic() return None
enhancement	Use regex for extracting effort value from labels.                            Use a more Pythonic way to extract the effort value from the label using regex, improving readability and reliability. pr_agent/tools/pr_reviewer.py [409-413] +import re for label in current_labels: - if label.lower().startswith('review effort [1-5]:'): - effort = int(label.split(':')[1].strip()) + match = re.search(r'review effort \[1-5\]:\s*(\d)', label, re.IGNORECASE) + if match: + effort = int(match.group(1))
best practice	Improve error handling by catching specific exceptions.                       Handle specific exceptions for better error handling and logging, instead of catching a generic exception. pr_agent/git_providers/github_provider.py [647-655] +from github.GithubException import GithubException try: res = self.pr.create_review(event="APPROVE") if res.state == "APPROVED": return True return False -except Exception as e: - get_logger().exception(f"Failed to auto-approve, error: {e}") +except GithubException as e: + get_logger().exception(f"Failed to auto-approve, GitHub API error: {e}") return False

---

✨ Usage guide:

---

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:

/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...

With a configuration file, use the following template:

[pr_code_suggestions]
some_config1=...
some_config2=...

Enabling\disabling automation When you first install the app, the default mode for the improve tool is: pr_commands = ["/improve --pr_code_suggestions.summarize=true", ...] 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. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the improve usage page for a more comprehensive guide on using this tool.

[mrT23]

/describe

[codiumai-pr-agent-pro]

PR Description updated to latest commit (8a04a4f)

• Copy walkthrough table to "Files Changed" Tab