Improve

Overview

The improve tool scans the PR code changes, and automatically generates meaningful 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

How it looks

Suggestions OverviewSelecting a specific suggestion

---

The following features are available only for Qodo Merge 💎 users:

• The Apply / Chat checkbox, which interactively converts a suggestion into a committable code comment
• The More checkbox to generate additional suggestions
• On Bitbucket (Cloud & Data Center) and GitLab Server (v16 and earlier), you can invoke More Suggestions manually

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:

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 all the suggestions as committable code comments, by running the following command:

/improve --pr_code_suggestions.commitable_code_suggestions=true

As can be seen, a single table 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 can only be presented in Bitbucket as code comments.

Manual more suggestions

To generate more suggestions (distinct from the ones already generated), for git-providers that don't support interactive checkbox option, you can manually run:

/improve --more_suggestions=true

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)

Assessing Impact

💎 feature

Qodo Merge tracks two types of implementations for tracking implemented suggestions:

• Direct implementation - when the user directly applies the suggestion by clicking the Apply checkbox.
• Indirect implementation - when the user implements the suggestion in their IDE environment. In this case, Qodo Merge will utilize, after each commit, a dedicated logic to identify if a suggestion was implemented, and will mark it as implemented.

In post-process, Qodo Merge counts the number of suggestions that were implemented, and provides general statistics and insights about the suggestions' impact on the PR process.

Suggestion tracking

💎 feature. Platforms supported: GitHub, GitLab

Qodo Merge employs a novel detection system to automatically identify AI code suggestions that PR authors have accepted and implemented.

Accepted suggestions are also automatically documented in a dedicated wiki page called .pr_agent_accepted_suggestions, allowing users to track historical changes, assess the tool's effectiveness, and learn from previously implemented recommendations in the repository. An example result:

This dedicated wiki page will also serve as a foundation for future AI model improvements, allowing it to learn from historically implemented suggestions and generate more targeted, contextually relevant recommendations.

This feature is controlled by a boolean configuration parameter: pr_code_suggestions.wiki_page_accepted_suggestions (default is true).

Wiki must be enabled

While the aggregation process is automatic, GitHub repositories require a one-time manual wiki setup.

To initialize the wiki: navigate to Wiki, select Create the first page, then click Save page.

Once a wiki repo is created, the tool will automatically use this wiki for tracking suggestions.

Why a wiki page?

Your code belongs to you, and we respect your privacy. Hence, we won't store any code suggestions in an external database.

Instead, we leverage a dedicated private page, within your repository wiki, to track suggestions. This approach offers convenient secure suggestion tracking while avoiding pull requests or any noise to the main repository.

Extra instructions and best practices

The improve tool can be further customized by providing additional instructions and best practices to the AI model.

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.

Examples for possible instructions:

[pr_code_suggestions]
extra_instructions="""\
(1) Answer in Japanese
(2) Don't suggest to add try-except 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

💎 feature. Platforms supported: GitHub, GitLab, Bitbucket

Qodo Merge supports both simple and hierarchical best practices configurations to provide guidance to the AI model for generating relevant code suggestions.

Writing effective best practices files

The following guidelines apply to all best practices files:

• Write clearly and concisely
• Include brief code examples when helpful with before/after patterns
• Focus on project-specific guidelines that will result in relevant suggestions you actually want to get
• Keep each file relatively short, under 800 lines, since:
  • AI models may not process effectively very long documents
  • Long files tend to contain generic guidelines already known to AI
• Use pattern-based structure rather than simple bullet points for better clarity

Example of a best practices file

Pattern 1: Add proper error handling with try-except blocks around external function calls.

Example code before:

# Some code that might raise an exception
return process_pr_data(data)

Example code after:

try:
    # Some code that might raise an exception
    return process_pr_data(data)
except Exception as e:
    logger.exception("Failed to process request", extra={"error": e})

Pattern 2: Add defensive null/empty checks before accessing object properties or performing operations on potentially null variables to prevent runtime errors.

Example code before:

def get_pr_code(pr_data):
    if "changed_code" in pr_data:
        return pr_data.get("changed_code", "")
    return ""

Example code after:

def get_pr_code(pr_data):
    if pr_data is None:
        return ""
    if "changed_code" in pr_data:
        return pr_data.get("changed_code", "")
    return ""

Local best practices

For basic usage, create a best_practices.md file in your repository's root directory containing a list of best practices, coding standards, and guidelines specific to your repository.

The AI model will use this best_practices.md file as a reference, and in case the PR code violates any of the guidelines, it will create additional suggestions, with a dedicated label: Organization best practice.

Global hierarchical best practices

For organizations managing multiple repositories with different requirements, Qodo Merge supports a hierarchical best practices system using a dedicated global configuration repository.

Supported scenarios:

1. Standalone repositories: Individual repositories can have their own specific best practices tailored to their unique requirements
2. Groups of repositories: Repositories can be mapped to shared group-level best practices for consistent standards across similar projects
3. Monorepos with subprojects: Large monorepos can have both repository-level and subproject-level best practices, with automatic path-based matching

Setting up global hierarchical best practices

1. Create a new repository named pr-agent-settings in your organization/workspace.

2. Build the folder hierarchy in your pr-agent-settings repository, for example:

pr-agent-settings/
├── metadata.yaml                     # Maps repos/folders to best practice paths
└── codebase_standards/               # Root for all best practice definitions
    ├── global/                       # Global rules, inherited widely
    │   └── best_practices.md
    ├── groups/                       # For groups of repositories
    │   ├── frontend_repos/
    │   │   └── best_practices.md
    │   ├── backend_repos/
    │   │   └── best_practices.md
    │   └── ...
    ├── qodo-merge/                   # For standalone repositories
    │   └── best_practices.md
    ├── qodo-monorepo/                # For monorepo-specific rules 
    │   ├── best_practices.md         # Root level monorepo rules
    │   ├── qodo-github/              # Subproject best practices
    │   │   └── best_practices.md
    │   └── qodo-gitlab/              # Another subproject
    │       └── best_practices.md
    └── ...                           # More repositories

3. Define the metadata file metadata.yaml that maps your repositories to their relevant best practices paths, for example:

# Standalone repos
qodo-merge:
  best_practices_paths:
    - "qodo-merge"

# Group-associated repos
repo_b:
  best_practices_paths:
    - "groups/backend_repos"

# Multi-group repos
repo_c:
  best_practices_paths:
    - "groups/frontend_repos"
    - "groups/backend_repos"

# Monorepo with subprojects
qodo-monorepo:
  best_practices_paths:
    - "qodo-monorepo"
  monorepo_subprojects:
    qodo-github:
      best_practices_paths:
        - "qodo-monorepo/qodo-github"
    qodo-gitlab:
      best_practices_paths:
        - "qodo-monorepo/qodo-gitlab"

4. Set the following configuration in your global configuration file:

[best_practices]
enable_global_best_practices = true

Best practices priority and fallback behavior

When global best practices are enabled, Qodo Merge follows this priority order:

1. Primary: Global hierarchical best practices from pr-agent-settings repository:

1.1 If the repository is mapped in `metadata.yaml`, it uses the specified paths

1.2 For monorepos, it automatically collects best practices matching PR file paths

1.3 If no mapping exists, it falls back to the global best practices

2. Fallback: Local repository best_practices.md file:

2.1 Used when global best practices are not found or configured

2.2 Acts as a safety net for repositories not yet configured in the global system

2.3 Local best practices are completely ignored when global best practices are successfully loaded

Edge cases and behavior

• Missing paths: If specified paths in metadata.yaml don't exist in the file system, those paths are skipped
• Monorepo subproject matching: For monorepos, Qodo Merge automatically matches PR file paths against subproject paths to apply relevant best practices
• Multiple group inheritance: Repositories can inherit from multiple groups, and all applicable best practices are combined

Dedicated label for best practices suggestions

Best practice suggestions are labeled as Organization best practice by default. To customize this label, modify it in your configuration file:

[best_practices]
organization_name = "..."

And the label will be: {organization_name} best practice.

Example results

Auto best practices

💎 feature. Platforms supported: GitHub.

Auto best practices is a novel Qodo Merge capability that:

1. Identifies recurring patterns from accepted suggestions
2. Automatically generates best practices page based on what your team consistently values
3. Applies these learned patterns to future code reviews

This creates an automatic feedback loop where the system continuously learns from your team's choices to provide increasingly relevant suggestions. The system maintains two analysis phases:

• Open exploration for new issues
• Targeted checking against established best practices

Note that when a custom best practices exist, Qodo Merge will still generate an 'auto best practices' wiki file, though it won't use it in the improve tool. Learn more about utilizing 'auto best practices' in our detailed guide.

Relevant configurations

[auto_best_practices]
# Disable all auto best practices usage or generation
enable_auto_best_practices = true  

# Disable usage of auto best practices file in the 'improve' tool
utilize_auto_best_practices = true 

# Extra instructions to the auto best practices generation prompt
extra_instructions = ""            

# Max number of patterns to be detected
max_patterns = 5                   

Multiple best practices sources

The improve tool will combine best practices from all available sources - global configuration, local configuration, and auto-generated files - to provide you with comprehensive recommendations.

Combining 'extra instructions' and 'best practices'

💎 feature

The extra instructions configuration is more related to the improve tool prompt. It can be used, for example, to avoid specific suggestions ("Don't suggest to add try-except block", "Ignore changes in toml files", ...) or to emphasize specific aspects or formats ("Answer in Japanese", "Give only short suggestions", ...)

In contrast, 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.

Usage Tips

Implementing the proposed code suggestions

Each generated suggestion consists of three key elements:

1. A single-line summary of the proposed change
2. An expandable section containing a comprehensive description of the suggestion
3. A diff snippet showing the recommended code modification (before and after)

We advise users to apply critical analysis and judgment when implementing the proposed suggestions. In addition to mistakes (which may happen, but are rare), sometimes the presented code modification may serve more as an illustrative example than a directly applicable solution. In such cases, we recommend prioritizing the suggestion's detailed description, using the diff snippet primarily as a supporting reference.

Dual publishing mode

Our recommended approach for presenting code suggestions is through a table (--pr_code_suggestions.commitable_code_suggestions=false). This method significantly reduces the PR footprint and allows for quick and easy digestion of multiple suggestions.

We also offer a complementary dual publishing mode. When enabled, suggestions exceeding a certain score threshold are not only displayed in the table, but also presented as committable PR comments. This mode helps highlight suggestions deemed more critical.

To activate dual publishing mode, use the following setting:

[pr_code_suggestions]
dual_publishing_score_threshold = x

Where x represents the minimum score threshold (>=) for suggestions to be presented as committable PR comments in addition to the table. Default is -1 (disabled).

Self-review

💎 feature Platforms supported: GitHub, GitLab

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) ..."

Tip - Reducing visual footprint after self-review 💎

The configuration parameter pr_code_suggestions.fold_suggestions_on_self_review (default is True) can be used to automatically fold the suggestions after the user clicks the self-review checkbox.

This reduces the visual footprint of the suggestions, and also indicates to the PR reviewer that the suggestions have been reviewed by the PR author, and don't require further attention.

Tip - Demanding self-review from the PR author 💎

By setting:

[pr_code_suggestions]
approve_pr_on_self_review = true

the tool can automatically add an approval when the PR author clicks the self-review checkbox.

• 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).

• If you keep the number of required reviewers for a PR to 1 and enable this configuration, this effectively means that the PR author can approve the PR by actively clicking the self-review checkbox.

  To prevent unauthorized approvals, this configuration defaults to false, and cannot be altered through online comments; enabling requires a direct update to the configuration file and a commit to the repository. This ensures that utilizing the feature demands a deliberate documented decision by the repository owner.

Auto-approval

💎 feature. Platforms supported: GitHub, GitLab, Bitbucket

Under specific conditions, Qodo Merge can auto-approve a PR when a specific comment is invoked, or when the PR meets certain criteria.

To ensure safety, the auto-approval feature is disabled by default. To enable auto-approval features, you need to actively set one or both of the following options in a pre-defined configuration file:

[config]
enable_comment_approval = true # For approval via comments
enable_auto_approval = true   # For criteria-based auto-approval

Notes

• Note that this specific flag cannot be set with a command line argument, only in the configuration file, committed to the repository.
• Enabling auto-approval must be a deliberate decision by the repository owner.

1. Auto-approval by commenting

To enable auto-approval by commenting, set in the configuration file:

[config]
enable_comment_approval = true

After enabling, by commenting on a PR:

/review auto_approve

Qodo Merge will automatically approve the PR, and add a comment with the approval.

2. Auto-approval when the PR meets certain criteria

To enable auto-approval based on specific criteria, first, you need to enable the top-level flag:

[config]
enable_auto_approval = true

There are several criteria that can be set for auto-approval:

• Review effort score

[config]
enable_auto_approval = true
auto_approve_for_low_review_effort = X # X is a number between 1 to 5

When the review effort score is lower or equal to X, the PR will be auto-approved.

---

• No code suggestions

[config]
enable_auto_approval = true
auto_approve_for_no_suggestions = true

When no code suggestions were found for the PR, the PR will be auto-approved.

---

• Ticket Compliance

[config]
enable_auto_approval = true
ensure_ticket_compliance = true # Default is false

If ensure_ticket_compliance is set to true, auto-approval will be disabled if a ticket is linked to the PR and the ticket is not compliant (e.g., the review tool did not mark the PR as fully compliant with the ticket). This ensures that PRs are only auto-approved if their associated tickets are properly resolved.

How many code suggestions are generated?

Qodo Merge uses a dynamic strategy to generate code suggestions based on the size of the pull request (PR). Here's how it works:

1. Chunking large PRs

• Qodo Merge divides large PRs into 'chunks'.
• Each chunk contains up to pr_code_suggestions.max_context_tokens tokens (default: 24,000).

2. Generating suggestions

• For each chunk, Qodo Merge generates up to pr_code_suggestions.num_code_suggestions_per_chunk suggestions (default: 4).

This approach has two main benefits:

• Scalability: The number of suggestions scales with the PR size, rather than being fixed.
• Quality: By processing smaller chunks, the AI can maintain higher quality suggestions, as larger contexts tend to decrease AI performance.

Note: Chunking is primarily relevant for large PRs. For most PRs (up to 600 lines of code), Qodo Merge will be able to process the entire code in a single call.

Configuration options

General options

extra_instructions	Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
commitable_code_suggestions	If set to true, the tool will display the suggestions as committable code comments. Default is false.
enable_chat_in_code_suggestions	If set to true, QM bot will interact with comments made on code changes it has proposed. Default is true.
dual_publishing_score_threshold	Minimum score threshold for suggestions to be presented as committable PR comments in addition to the table. Default is -1 (disabled).
focus_only_on_problems	If set to true, suggestions will focus primarily on identifying and fixing code problems, and less on style considerations like best practices, maintainability, or readability. Default is true.
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 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_more_suggestions_checkbox	Enable the checkbox to generate more suggestions. Default is true.
enable_help_text	If set to true, the tool will display a help text in the comment. Default is true.
enable_chat_text	If set to true, the tool will display a reference to the PR chat in the comment. Default is true.
publish_output_no_suggestions	If set to true, the tool will publish a comment even if no suggestions were found. Default is true.
wiki_page_accepted_suggestions	If set to true, the tool will automatically track accepted suggestions in a dedicated wiki page called .pr_agent_accepted_suggestions. Default is true.
allow_thumbs_up_down	If set to true, all code suggestions will have thumbs up and thumbs down buttons, to encourage users to provide feedback on the suggestions. Default is false. Note that this feature is for statistics tracking. It will not affect future feedback from the AI model.

Params for number of suggestions and AI calls

auto_extended_mode	Enable chunking the PR code and running the tool on each chunk. Default is true.
num_code_suggestions_per_chunk	Number of code suggestions provided by the 'improve' tool, per chunk. Default is 3.
max_number_of_calls	Maximum number of chunks. Default is 3.

Understanding AI Code Suggestions

• AI Limitations: AI models for code are getting better and better, but they are 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. Mistakes of the AI are rare but can happen, and it is usually quite easy for a human to spot them.
• Purpose of Suggestions:
  • Self-reflection: The suggestions aim to enable developers to self-reflect and improve their pull requests. This process can help to identify blind spots, uncover missed edge cases, and enhance code readability and coherency. Even when a specific code suggestion isn't suitable, the underlying issue it highlights often reveals something important that might deserve attention.
  • Bug detection: The suggestions also alert on any critical bugs that may have been identified during the analysis. This provides an additional safety net to catch potential issues before they make it into production. It's perfectly acceptable to implement only the suggestions you find valuable for your specific context.
• Hierarchy: Presenting the suggestions in a structured hierarchical table enables the user to quickly understand them, and to decide which ones are relevant and which are not.
• Customization: To guide the model to suggestions that are more relevant to the specific needs of your project, we recommend using the extra_instructions and best practices fields.
• Model Selection: SaaS users can also choose between different models. For specific programming languages or use cases, some models may perform better than others.
• Interactive usage: The interactive PR chat also provides an easy way to get more tailored suggestions and feedback from the AI model.