pr-agent/docs/docs/tools/improve.md

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 it can be invoked manually by commenting on any PR:

/improve

Example usage

Manual triggering

Invoke the tool manually by commenting /improve on any PR. The code suggestions by default are presented as a single comment:

{width=512}

To edit configurations related to the improve tool, use the following template:

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

For example, you can choose to present the suggestions as commitable code comments, by running the following command:

/improve --pr_code_suggestions.commitable_code_suggestions=true

{width=512}

Note that a single comment has a significantly smaller PR footprint. We recommend this mode for most cases. Also note that collapsible are not supported in Bitbucket. Hence, the suggestions are presented there as code comments.

Automatic triggering

To run the improve automatically when a PR is opened, define in a configuration file:

[github_app]
pr_commands = [
    "/improve",
    ...
]

[pr_code_suggestions]
num_code_suggestions_per_chunk = ...
...

• The pr_commands lists commands that will be executed automatically when a PR is opened.
• The [pr_code_suggestions] section contains the configurations for the improve tool you want to edit (if any)

Usage Tips

Self-review

If you set in a configuration file:

[pr_code_suggestions]
demand_code_suggestions_self_review = true

The improve tool will add a checkbox below the suggestions, prompting user to acknowledge that they have reviewed the suggestions. You can set the content of the checkbox text via:

[pr_code_suggestions]
code_suggestions_self_review_text = "... (your text here) ..."

{width=512}

💎 In addition, by setting:

[pr_code_suggestions]
approve_pr_on_self_review = true

the tool can automatically approve the PR when the user checks the self-review checkbox.

!!! tip "Tip - demanding self-review from the PR author" If you set the number of required reviewers for a PR to 2, this effectively means that the PR author must click the self-review checkbox before the PR can be merged (in addition to a human reviewer).

![self_review_2](https://codium.ai/images/pr_agent/self_review_2.png){width=512}

Extra instructions and best practices

Extra instructions

You can use the extra_instructions configuration option to give the AI model additional instructions for the improve tool. 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 possible instructions:

[pr_code_suggestions]
extra_instructions="""\
(1) Answer in japanese
(2) Don't suggest to add try-excpet block
(3) Ignore changes in toml files
...
"""

Use triple quotes to write multi-line instructions. Use bullet points or numbers to make the instructions more readable.

Best practices 💎

Another option to give additional guidance to the AI model is by creating a dedicated wiki page called best_practices.md. This page can contain a list of best practices, coding standards, and guidelines that are specific to your repo/organization (up to 800 lines are allowed)

The AI model will use this page as a reference, and in case the PR code violates any of the guidelines, it will suggest improvements accordingly. Examples for possible best practices:

## Here are the organization's best practices for writing code:
- avoid nested loops
- avoid typos
- use meaningful variable names
- follow the DRY principle
- keep functions short and simple, typically within 10-30 lines of code.
...

When a PR code violates any of the guidelines, the AI model will suggest improvements accordingly, with a dedicated label: Organization best practice.

Example results:

{width=512}

Note that while the extra instructions are more related to the way the improve tool behaves, the best_practices.md file is a general guideline for the way code should be written in the repo. Using a combination of both can help the AI model to provide relevant and tailored suggestions.

Configuration options

!!! example "General options"

num_code_suggestions	Number of code suggestions provided by the 'improve' tool. Default is 4 for CLI, 0 for auto tools.
extra_instructions	Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
rank_suggestions	If set to true, the tool will rank the suggestions, based on importance. Default is false.
commitable_code_suggestions	If set to true, the tool will display the suggestions as commitable code comments. Default is false.
persistent_comment	If set to true, the improve comment will be persistent, meaning that every new improve request will edit the previous one. Default is false.
self_reflect_on_suggestions	If set to true, the improve tool will calculate an importance score for each suggestion [1-10], and sort the suggestion labels group based on this score. Default is true.
suggestions_score_threshold	Any suggestion with importance score less than this threshold will be removed. Default is 0. Highly recommend not to set this value above 7-8, since above it may clip relevant suggestions that can be useful.
apply_suggestions_checkbox	Enable the checkbox to create a committable suggestion. Default is true.
enable_help_text	If set to true, the tool will display a help text in the comment. Default is true.

!!! example "params for 'extended' mode"

auto_extended_mode	Enable extended mode automatically (no need for the --extended option). Default is true.
num_code_suggestions_per_chunk	Number of code suggestions provided by the 'improve' tool, per chunk. Default is 5.
rank_extended_suggestions	If set to true, the tool will rank the suggestions, based on importance. Default is true.
max_number_of_calls	Maximum number of chunks. Default is 5.
final_clip_factor	Factor to remove suggestions with low confidence. Default is 0.9.

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. Critical reading and judgment are required.

• While mistakes of the AI are rare but can happen, a real benefit from the suggestions of the improve (and review) tool is to catch, with high probability, mistakes or bugs done by the PR author, when they happen. So, it's a good practice to spend the needed ~30-60 seconds to review the suggestions, even if not all of them are always relevant.

• The hierarchical structure of the suggestions is designed to help the user to quickly understand them, and to decide which ones are relevant and which are not:

  • Only if the Category header is relevant, the user should move to the summarized suggestion description
  • Only if the summarized suggestion description is relevant, the user should click on the collapsible, to read the full suggestion description with a code preview example.

In addition, we recommend to use the extra_instructions field to guide the model to suggestions that are more relevant to the specific needs of the project.
Consider also trying the Custom Prompt Tool 💎, that will only propose code suggestions that follow specific guidelines defined by user.