xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-16 02:30:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into gerrit

Browse Source
This commit is contained in:
Nikolay Telepenin
2023-09-05 09:04:32 +01:00
parent 53ce609266 958ecf333a
commit 0dbe64e401
9 changed files with 383 additions and 224 deletions
Download Patch File Download Diff File Expand all files Collapse all files

98
CONFIGURATION.md
View File

@ -1,98 +0,0 @@
## Configuration
The different tools and sub-tools used by CodiumAI PR-Agent are adjustable via the **[configuration file](pr_agent/settings/configuration.toml)**
### Working from CLI
When running from source (CLI), your local configuration file will be initially used.
Example for invoking the 'review' tools via the CLI:
```
python cli.py --pr-url=<pr_url> review
```
In addition to general configurations, the 'review' tool will use parameters from the `[pr_reviewer]` section (every tool has a dedicated section in the configuration file).
Note that you can print results locally, without publishing them, by setting in `configuration.toml`:
```
[config]
publish_output=true
verbosity_level=2
```
This is useful for debugging or experimenting with the different tools.
### Working from GitHub App (pre-built repo)
When running PR-Agent from GitHub App, the default configuration file (`configuration.toml`) will be loaded.
#### GitHub app default tools
The `[github_app]` section of the configuration file defines GitHub app specific configurations.
The important parameter is `pr_commands`, which is a list of tools that will be run automatically when a new PR is opened:
```
[github_app]
pr_commands = [
"/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
"/auto_review",
]
```
This means that when a new PR is opened, PR-Agent will run the `describe` and `auto_review` tools.
For the describe tool, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.
However, you can override the default tool parameters by uploading a local configuration file called `.pr_agent.toml` to the root of your repo.
For example, if your local `.pr_agent.toml` file contains:
```
[pr_description]
add_original_user_description = false
keep_original_user_title = false
```
Then when a new PR is opened, PR-Agent will run the `describe` tool with the above parameters.
Note that a local `.pr_agent.toml` file enables you to edit and customize the default parameters of any tool, not just the ones that are run automatically.
#### Editing the prompts
The prompts for the various PR-Agent tools are defined in the `pr_agent/settings` folder.
In practice, the prompts are loaded and stored as a standard setting object. Hence,
editing them is similar to editing any other configuration value - just place the relevant key in `.pr_agent.toml`file, and override the default value.
For example, if you want to edit the prompts of the [describe](./pr_agent/settings/pr_description_prompts.toml) tool, you can add the following to your `.pr_agent.toml` file:
```
[pr_description_prompt]
system="""
...
"""
user="""
...
"""
```
Note that the new prompt will need to generate an output compatible with the relevant [post-process function](./pr_agent/tools/pr_description.py#L137).
#### Online usage
For online usage (calling tools by comments on a PR like `/ask ...`), just add `--config_path=<value>` to any command, to edit a specific configuration value.
For example if you want to edit `pr_reviewer` configurations, you can run:
```
/review --pr_reviewer.extra_instructions="..." --pr_reviewer.require_score_review=false ...
```
Any configuration value in `configuration.toml` file can be similarly edited.
### General configuration walkthrough
#### Changing a model
See [here](pr_agent/algo/__init__.py) for the list of available models.
To use Llama2 model, for example, set:
```
[config]
model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
[replicate]
key = ...
```
(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
Also review the [AiHandler](pr_agent/algo/ai_handler.py) file for instruction how to set keys for other models.
#### Extra instructions
All PR-Agent tools have a parameter called `extra_instructions`, that enables to add free-text extra instructions. Example usage:
```
/update_changelog --pr_update_changelog.extra_instructions="Make sure to update also the version ..."
```

78
INSTALL.md
View File

@ -9,8 +9,8 @@ To get started with PR-Agent quickly, you first need to acquire two tokens:
There are several ways to use PR-Agent:
- [Method 1: Use Docker image (no installation required)](INSTALL.md#method-1-use-docker-image-no-installation-required)
- [Method 2: Run as a GitHub Action](INSTALL.md#method-2-run-as-a-github-action)
- [Method 3: Run from source](INSTALL.md#method-3-run-from-source)
- [Method 2: Run from source](INSTALL.md#method-2-run-from-source)
- [Method 3: Run as a GitHub Action](INSTALL.md#method-3-run-as-a-github-action)
- [Method 4: Run as a polling server](INSTALL.md#method-4-run-as-a-polling-server)
- [Method 5: Run as a GitHub App](INSTALL.md#method-5-run-as-a-github-app)
- [Method 6: Deploy as a Lambda Function](INSTALL.md#method-6---deploy-as-a-lambda-function)
@ -55,7 +55,41 @@ Possible questions you can ask include:
---
### Method 2: Run as a GitHub Action
### Method 2: Run from source
1. Clone this repository:
```
git clone https://github.com/Codium-ai/pr-agent.git
```
2. Install the requirements in your favorite virtual environment:
```
pip install -r requirements.txt
```
3. Copy the secrets template file and fill in your OpenAI key and your GitHub user token:
```
cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
chmod 600 pr_agent/settings/.secrets.toml
# Edit .secrets.toml file
```
4. Add the pr_agent folder to your PYTHONPATH, then run the cli.py script:
```
export PYTHONPATH=[$PYTHONPATH:]<PATH to pr_agent folder>
python pr_agent/cli.py --pr_url <pr_url> /review
python pr_agent/cli.py --pr_url <pr_url> /ask <your question>
python pr_agent/cli.py --pr_url <pr_url> /describe
python pr_agent/cli.py --pr_url <pr_url> /improve
```
---
### Method 3: Run as a GitHub Action
You can use our pre-built Github Action Docker image to run PR-Agent as a Github Action.
@ -114,7 +148,7 @@ The GITHUB_TOKEN secret is automatically created by GitHub.
3. Merge this change to your main branch.
When you open your next PR, you should see a comment from `github-actions` bot with a review of your PR, and instructions on how to use the rest of the tools.
4. You may configure PR-Agent by adding environment variables under the env section corresponding to any configurable property in the [configuration](./CONFIGURATION.md) file. Some examples:
4. You may configure PR-Agent by adding environment variables under the env section corresponding to any configurable property in the [configuration](./Usage.md) file. Some examples:
```yaml
env:
# ... previous environment values
@ -125,40 +159,6 @@ When you open your next PR, you should see a comment from `github-actions` bot w
---
### Method 3: Run from source
1. Clone this repository:
```
git clone https://github.com/Codium-ai/pr-agent.git
```
2. Install the requirements in your favorite virtual environment:
```
pip install -r requirements.txt
```
3. Copy the secrets template file and fill in your OpenAI key and your GitHub user token:
```
cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
chmod 600 pr_agent/settings/.secrets.toml
# Edit .secrets.toml file
```
4. Add the pr_agent folder to your PYTHONPATH, then run the cli.py script:
```
export PYTHONPATH=[$PYTHONPATH:]<PATH to pr_agent folder>
python pr_agent/cli.py --pr_url <pr_url> review
python pr_agent/cli.py --pr_url <pr_url> ask <your question>
python pr_agent/cli.py --pr_url <pr_url> describe
python pr_agent/cli.py --pr_url <pr_url> improve
```
---
### Method 4: Run as a polling server
Request reviews by tagging your Github user on a PR
@ -253,7 +253,7 @@ docker push codiumai/pr-agent:github_app # Push to your Docker repository
> **Note:** When running PR-Agent from GitHub App, the default configuration file (configuration.toml) will be loaded.<br>
> However, you can override the default tool parameters by uploading a local configuration file<br>
> For more information please check out [CONFIGURATION.md](CONFIGURATION.md#working-from-github-app-pre-built-repo)
> For more information please check out [CONFIGURATION.md](Usage.md#working-from-github-app-pre-built-repo)
---
### Method 6 - Deploy as a Lambda Function

148
README.md
View File

@ -17,17 +17,20 @@ Making pull requests less painful with an AI agent
CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull requests faster and more efficiently. It automatically analyzes the pull request and can provide several types of PR feedback:
**Auto-Description**: Automatically generating [PR description](https://github.com/Codium-ai/pr-agent/pull/229#issue-1860711415) - title, type, summary, code walkthrough and labels.
**Auto Description (/describe)**: Automatically generating [PR description](https://github.com/Codium-ai/pr-agent/pull/229#issue-1860711415) - title, type, summary, code walkthrough and labels.
\
**Auto Review**: [Adjustable feedback](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695022908) about the PR main theme, type, relevant tests, security issues, score, and various suggestions for the PR content.
**Auto Review (/review)**: [Adjustable feedback](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695022908) about the PR main theme, type, relevant tests, security issues, score, and various suggestions for the PR content.
\
**Question Answering**: Answering [free-text questions](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021332) about the PR.
**Question Answering (/ask ...)**: Answering [free-text questions](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021332) about the PR.
\
**Code Suggestions**: [Committable code suggestions](https://github.com/Codium-ai/pr-agent/pull/229#discussion_r1306919276) for improving the PR.
**Code Suggestions (/improve)**: [Committable code suggestions](https://github.com/Codium-ai/pr-agent/pull/229#discussion_r1306919276) for improving the PR.
\
**Update Changelog**: Automatically updating the CHANGELOG.md file with the [PR changes](https://github.com/Codium-ai/pr-agent/pull/168#discussion_r1282077645).
**Update Changelog (/update_changelog)**: Automatically updating the CHANGELOG.md file with the [PR changes](https://github.com/Codium-ai/pr-agent/pull/168#discussion_r1282077645).
<h3>Example results:</h2>
See the [usage guide](./Usage.md) for instructions how to run the different tools from [CLI](./Usage.md#working-from-a-local-repo-cli), or by [online usage](./Usage.md#online-usage).
<h3>Example results:</h3>
</div>
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1687561986">/describe:</a></h4>
<div align="center">
@ -35,91 +38,100 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
<img src="https://www.codium.ai/images/describe-2.gif" width="800">
</p>
</div>
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901">/review:</a></h4>
<div align="center">
<p float="center">
<img src="https://www.codium.ai/images/review-2.gif" width="800">
</p>
</div>
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/78#issuecomment-1639739496">/reflect_and_review:</a></h4>
<div align="center">
<p float="center">
<img src="https://www.codium.ai/images/reflect_and_review.gif" width="800">
</p>
</div>
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695020538">/ask:</a></h4>
<div align="center">
<p float="center">
<img src="https://www.codium.ai/images/ask-2.gif" width="800">
</p>
</div>
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695024952">/improve:</a></h4>
<div align="center">
<p float="center">
<img src="https://www.codium.ai/images/improve-2.gif" width="800">
</p>
</div>
[//]: # (<h4><a href="https://github.com/Codium-ai/pr-agent/pull/78#issuecomment-1639739496">/reflect_and_review:</a></h4>)
[//]: # (<div align="center">)
[//]: # (<p float="center">)
[//]: # (<img src="https://www.codium.ai/images/reflect_and_review.gif" width="800">)
[//]: # (</p>)
[//]: # (</div>)
[//]: # (<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695020538">/ask:</a></h4>)
[//]: # (<div align="center">)
[//]: # (<p float="center">)
[//]: # (<img src="https://www.codium.ai/images/ask-2.gif" width="800">)
[//]: # (</p>)
[//]: # (</div>)
[//]: # (<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695024952">/improve:</a></h4>)
[//]: # (<div align="center">)
[//]: # (<p float="center">)
[//]: # (<img src="https://www.codium.ai/images/improve-2.gif" width="800">)
[//]: # (</p>)
[//]: # (</div>)
<div align="left">
## Table of Contents
- [Overview](#overview)
- [Try it now](#try-it-now)
- [Installation](#installation)
- [Configuration](./CONFIGURATION.md)
- [Usage guide](./Usage.md)
- [How it works](#how-it-works)
- [Why use PR-Agent](#why-use-pr-agent)
- [Roadmap](#roadmap)
- [Similar projects](#similar-projects)
</div>
## Overview
`PR-Agent` offers extensive pull request functionalities across various git providers:
| | | GitHub | Gitlab | Bitbucket | CodeCommit | Gerrit |
| | | GitHub | Gitlab | Bitbucket | CodeCommit | Azure DevOps |
|-------|---------------------------------------------|:------:|:------:|:---------:|:----------:|:----------:|
| TOOLS | Review | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | ⮑ Inline review | :white_check_mark: | :white_check_mark: | | |
| | Ask | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | Auto-Description | :white_check_mark: | :white_check_mark: | | :white_check_mark: | :white_check_mark: |
| | Improve Code | :white_check_mark: | :white_check_mark: | | | :white_check_mark: |
| | ⮑ Extended | :white_check_mark: | :white_check_mark: | | | :white_check_mark: |
| | Reflect and Review | :white_check_mark: | | | | :white_check_mark: |
| | Update CHANGELOG.md | :white_check_mark: | | | |
| | | | | | |
| USAGE | CLI | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | App / webhook | :white_check_mark: | :white_check_mark: | | | |
| | Tagging bot | :white_check_mark: | | | | |
| | Actions | :white_check_mark: | | | | |
| | HTTP Server | | | | | :white_check_mark:|
| | | | | | |
| CORE | PR compression | :white_check_mark: | :white_check_mark: | :white_check_mark: | | :white_check_mark: |
| | Repo language prioritization | :white_check_mark: | :white_check_mark: | :white_check_mark: | | :white_check_mark: |
| | Adaptive and token-aware<br />file patch fitting | :white_check_mark: | :white_check_mark: | :white_check_mark: | | :white_check_mark: |
| | Multiple models support | :white_check_mark: | :white_check_mark: | :white_check_mark: | | :white_check_mark: |
| | Incremental PR Review | :white_check_mark: | | | | |
| TOOLS | Review | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | Ask | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark:
| | Auto-Description | :white_check_mark: | :white_check_mark: | | :white_check_mark: | :white_check_mark: |
| | Improve Code | :white_check_mark: | :white_check_mark: | | :white_check_mark: | |
| | ⮑ Extended | :white_check_mark: | :white_check_mark: | | :white_check_mark: | |
| | Reflect and Review | :white_check_mark: | | | | :white_check_mark: |
| | Update CHANGELOG.md | :white_check_mark: | | | | |
| | | | | | | |
| USAGE | CLI | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | App / webhook | :white_check_mark: | :white_check_mark: | | | |
| | Tagging bot | :white_check_mark: | | | | |
| | Actions | :white_check_mark: | | | | |
| | | | | | | |
| CORE | PR compression | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | Repo language prioritization | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | Adaptive and token-aware<br />file patch fitting | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | Multiple models support | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | Incremental PR Review | :white_check_mark: | | | | |
Examples for invoking the different tools via the CLI:
- **Review**: python cli.py --pr_url=<pr_url> review
- **Describe**: python cli.py --pr_url=<pr_url> describe
- **Improve**: python cli.py --pr_url=<pr_url> improve
- **Ask**: python cli.py --pr_url=<pr_url> ask "Write me a poem about this PR"
- **Reflect**: python cli.py --pr_url=<pr_url> reflect
- **Update Changelog**: python cli.py --pr_url=<pr_url> update_changelog
"<pr_url>" is the url of the relevant PR (for example: https://github.com/Codium-ai/pr-agent/pull/50).
In the [configuration](./CONFIGURATION.md) file you can select your git provider (GitHub, Gitlab, Bitbucket), and further configure the different tools.
Options that are available in the configuration file can be specified at run time when calling actions. Two examples:
- /review --pr_reviewer.extra_instructions="focus on the file: ..."
- /describe --pr_description.add_original_user_description=false -pr_description.extra_instructions="make sure to mention: ..."
Review the **[usage guide](./Usage.md)** section for detailed instructions how to use the different tools, select the relevant git provider (GitHub, Gitlab, Bitbucket,...), and adjust the configuration file to your needs.
## Try it now
Try GPT-4 powered PR-Agent on your public GitHub repository for free. Just mention `@CodiumAI-Agent` and add the desired command in any PR comment! The agent will generate a response based on your command.
You can try GPT-4 powered PR-Agent, on your public GitHub repository, instantly. Just mention `@CodiumAI-Agent` and add the desired command in any PR comment. The agent will generate a response based on your command.
For example, add a comment to any pull request with the following text:
```
@CodiumAI-Agent /review
```
and the agent will respond with a review of your PR
![Review generation process](https://www.codium.ai/images/demo-2.gif)
To set up your own PR-Agent, see the [Installation](#installation) section
To set up your own PR-Agent, see the [Installation](#installation) section below.
---
@ -133,8 +145,8 @@ To get started with PR-Agent quickly, you first need to acquire two tokens:
There are several ways to use PR-Agent:
- [Method 1: Use Docker image (no installation required)](INSTALL.md#method-1-use-docker-image-no-installation-required)
- [Method 2: Run as a GitHub Action](INSTALL.md#method-2-run-as-a-github-action)
- [Method 3: Run from source](INSTALL.md#method-3-run-from-source)
- [Method 2: Run from source](INSTALL.md#method-2-run-from-source)
- [Method 3: Run as a GitHub Action](INSTALL.md#method-3-run-as-a-github-action)
- [Method 4: Run as a polling server](INSTALL.md#method-4-run-as-a-polling-server)
- Request reviews by tagging your GitHub user on a PR
- [Method 5: Run as a GitHub App](INSTALL.md#method-5-run-as-a-github-app)
@ -158,7 +170,7 @@ Here are some advantages of PR-Agent:
- We emphasize **real-life practical usage**. Each tool (review, improve, ask, ...) has a single GPT-4 call, no more. We feel that this is critical for realistic team usage - obtaining an answer quickly (~30 seconds) and affordably.
- Our [PR Compression strategy](./PR_COMPRESSION.md) is a core ability that enables to effectively tackle both short and long PRs.
- Our JSON prompting strategy enables to have **modular, customizable tools**. For example, the '/review' tool categories can be controlled via the [configuration](./CONFIGURATION.md) file. Adding additional categories is easy and accessible.
- Our JSON prompting strategy enables to have **modular, customizable tools**. For example, the '/review' tool categories can be controlled via the [configuration](pr_agent/settings/configuration.toml) file. Adding additional categories is easy and accessible.
- We support **multiple git providers** (GitHub, Gitlab, Bitbucket, CodeCommit), **multiple ways** to use the tool (CLI, GitHub Action, GitHub App, Docker, ...), and **multiple models** (GPT-4, GPT-3.5, Anthropic, Cohere, Llama2).
- We are open-source, and welcome contributions from the community.
@ -185,4 +197,4 @@ Here are some advantages of PR-Agent:
- [Aider - GPT powered coding in your terminal](https://github.com/paul-gauthier/aider)
- [openai-pr-reviewer](https://github.com/coderabbitai/openai-pr-reviewer)
- [CodeReview BOT](https://github.com/anc95/ChatGPT-CodeReview)
- [AI-Maintainer](https://github.com/merwanehamadi/AI-Maintainer)
- [AI-Maintainer](https://github.com/merwanehamadi/AI-Maintainer)

182
Usage.md Normal file
View File

@ -0,0 +1,182 @@
## Usage guide
### Table of Contents
- [Introduction](#introduction)
- [Working from a local repo (CLI)](#working-from-a-local-repo-cli)
- [Online usage](#online-usage)
- [Working with GitHub App](#working-with-github-app)
- [Working with GitHub Action](#working-with-github-action)
- [Appendix - additional configurations walkthrough](#appendix---additional-configurations-walkthrough)
### Introduction
There are 3 basic ways to invoke CodiumAI PR-Agent:
1. Locally running a CLI command
2. Online usage - by [commenting](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901) on a PR
3. Enabling PR-Agent tools to run automatically when a new PR is opened
See the [installation guide](/INSTALL.md) for instructions on how to setup your own PR-Agent.
Specifically, CLI commands can be issued by invoking a pre-built [docker image](/INSTALL.md#running-from-source), or by invoking a [locally cloned repo](INSTALL.md#method-2-run-from-source).
For online usage, you will need to setup either a [GitHub App](INSTALL.md#method-5-run-as-a-github-app), or a [GitHub Action](INSTALL.md#method-3-run-as-a-github-action).
GitHub App and GitHub Action also enable to run PR-Agent specific tool automatically when a new PR is opened.
#### The configuration file
The different tools and sub-tools used by CodiumAI PR-Agent are adjustable via the **[configuration file](pr_agent/settings/configuration.toml)**.
In addition to general configuration options, each tool has its own configurations. For example, the `review` tool will use parameters from the [pr_reviewer](/pr_agent/settings/configuration.toml#L16) section in the configuration file.
**git provider:**
The [git_provider](pr_agent/settings/configuration.toml#L4) field in the configuration file determines the GIT provider that will be used by PR-Agent. Currently, the following providers are supported:
`
"github", "gitlab", "azure", "codecommit", "local"
`
[//]: # (** online usage:**)
[//]: # (Options that are available in the configuration file can be specified at run time when calling actions. Two examples:)
[//]: # (```)
[//]: # (- /review --pr_reviewer.extra_instructions="focus on the file: ...")
[//]: # (- /describe --pr_description.add_original_user_description=false -pr_description.extra_instructions="make sure to mention: ...")
[//]: # (```)
### Working from a local repo (CLI)
When running from your local repo (CLI), your local configuration file will be used.
Examples for invoking the different tools via the CLI:
- **Review**: `python cli.py --pr_url=<pr_url> /review`
- **Describe**: `python cli.py --pr_url=<pr_url> /describe`
- **Improve**: `python cli.py --pr_url=<pr_url> /improve`
- **Ask**: `python cli.py --pr_url=<pr_url> /ask "Write me a poem about this PR"`
- **Reflect**: `python cli.py --pr_url=<pr_url> /reflect`
- **Update Changelog**: `python cli.py --pr_url=<pr_url> /update_changelog`
`<pr_url>` is the url of the relevant PR (for example: https://github.com/Codium-ai/pr-agent/pull/50).
**Notes:**
(1) in addition to editing your local configuration file, you can also change any configuration value by adding it to the command line:
```
python cli.py --pr_url=<pr_url> /review --pr_reviewer.extra_instructions="focus on the file: ..."
```
(2) You can print results locally, without publishing them, by setting in `configuration.toml`:
```
[config]
publish_output=true
verbosity_level=2
```
This is useful for debugging or experimenting with the different tools.
### Online usage
Online usage means invoking PR-Agent tools by [comments](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901) on a PR.
Commands for invoking the different tools via comments:
- **Review**: `/review`
- **Describe**: `/describe`
- **Improve**: `/improve`
- **Ask**: `/ask "..."`
- **Reflect**: `/reflect`
- **Update Changelog**: `/update_changelog`
To edit a specific configuration value, just add `--config_path=<value>` to any command.
For example if you want to edit the `review` tool configurations, you can run:
```
/review --pr_reviewer.extra_instructions="..." --pr_reviewer.require_score_review=false
```
Any configuration value in [configuration file](pr_agent/settings/configuration.toml) file can be similarly edited.
### Working with GitHub App
When running PR-Agent from [GitHub App](INSTALL.md#method-5-run-as-a-github-app), the default configurations from a pre-built repo will be initially loaded.
#### GitHub app automatic tools
The [github_app](pr_agent/settings/configuration.toml#L56) section defines GitHub app specific configurations.
An important parameter is `pr_commands`, which is a list of tools that will be **run automatically when a new PR is opened**:
```
[github_app]
pr_commands = [
"/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
"/auto_review",
]
```
This means that when a new PR is opened, PR-Agent will run the `describe` and `auto_review` tools.
For the describe tool, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.
However, you can override the default tool parameters by uploading a local configuration file called `.pr_agent.toml` to the root of your repo.
For example, if your local `.pr_agent.toml` file contains:
```
[pr_description]
add_original_user_description = false
keep_original_user_title = false
```
When a new PR is opened, PR-Agent will run the `describe` tool with the above parameters.
Note that a local `.pr_agent.toml` file enables you to edit and customize the default parameters of any tool, not just the ones that are run automatically.
#### Editing the prompts
The prompts for the various PR-Agent tools are defined in the `pr_agent/settings` folder.
In practice, the prompts are loaded and stored as a standard setting object.
Hence, editing them is similar to editing any other configuration value - just place the relevant key in `.pr_agent.toml`file, and override the default value.
For example, if you want to edit the prompts of the [describe](./pr_agent/settings/pr_description_prompts.toml) tool, you can add the following to your `.pr_agent.toml` file:
```
[pr_description_prompt]
system="""
...
"""
user="""
...
"""
```
Note that the new prompt will need to generate an output compatible with the relevant [post-process function](./pr_agent/tools/pr_description.py#L137).
### Working with GitHub Action
TBD
### Appendix - additional configurations walkthrough
#### Changing a model
See [here](pr_agent/algo/__init__.py) for the list of available models.
To use Llama2 model, for example, set:
```
[config]
model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
[replicate]
key = ...
```
(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
Also review the [AiHandler](pr_agent/algo/ai_handler.py) file for instruction how to set keys for other models.
#### Extra instructions
All PR-Agent tools have a parameter called `extra_instructions`, that enables to add free-text extra instructions. Example usage:
```
/update_changelog --pr_update_changelog.extra_instructions="Make sure to update also the version ..."
```
#### Azure DevOps provider
To use Azure DevOps provider use the following settings in configuration.toml:
```
[config]
git_provider="azure"
use_repo_settings_file=false
```
And use the following settings (you have to replace the values) in .secrets.toml:
```
[azure_devops]
org = "https://dev.azure.com/YOUR_ORGANIZATION/"
pat = "YOUR_PAT_TOKEN"
```

54
pr_agent/git_providers/codecommit_client.py
View File

@ -90,7 +90,11 @@ class CodeCommitClient:
):
differences.extend(page.get("differences", []))
except botocore.exceptions.ClientError as e:
raise ValueError(f"Failed to retrieve differences from CodeCommit PR #{self.pr_num}") from e
if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
raise ValueError(f"CodeCommit cannot retrieve differences: Repository does not exist: {repo_name}") from e
raise ValueError(f"CodeCommit cannot retrieve differences for {source_commit}..{destination_commit}") from e
except Exception as e:
raise ValueError(f"CodeCommit cannot retrieve differences for {source_commit}..{destination_commit}") from e
output = []
for json in differences:
@ -122,6 +126,8 @@ class CodeCommitClient:
try:
response = self.boto_client.get_file(repositoryName=repo_name, commitSpecifier=sha_hash, filePath=file_path)
except botocore.exceptions.ClientError as e:
if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
raise ValueError(f"CodeCommit cannot retrieve PR: Repository does not exist: {repo_name}") from e
# if the file does not exist, but is flagged as optional, then return an empty string
if optional and e.response["Error"]["Code"] == 'FileDoesNotExistException':
return ""
@ -133,11 +139,12 @@ class CodeCommitClient:
return response.get("fileContent", "")
def get_pr(self, pr_number: int):
def get_pr(self, repo_name: str, pr_number: int):
"""
Get a information about a CodeCommit PR.
Args:
- repo_name: Name of the repository
- pr_number: The PR number you are requesting
Returns:
@ -155,6 +162,8 @@ class CodeCommitClient:
except botocore.exceptions.ClientError as e:
if e.response["Error"]["Code"] == 'PullRequestDoesNotExistException':
raise ValueError(f"CodeCommit cannot retrieve PR: PR number does not exist: {pr_number}") from e
if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
raise ValueError(f"CodeCommit cannot retrieve PR: Repository does not exist: {repo_name}") from e
raise ValueError(f"CodeCommit cannot retrieve PR: {pr_number}: boto client error") from e
except Exception as e:
raise ValueError(f"CodeCommit cannot retrieve PR: {pr_number}") from e
@ -201,7 +210,7 @@ class CodeCommitClient:
except Exception as e:
raise ValueError(f"Error calling publish_description") from e
def publish_comment(self, repo_name: str, pr_number: int, destination_commit: str, source_commit: str, comment: str):
def publish_comment(self, repo_name: str, pr_number: int, destination_commit: str, source_commit: str, comment: str, annotation_file: str = None, annotation_line: int = None):
"""
Publish a comment to a pull request
@ -210,7 +219,13 @@ class CodeCommitClient:
- pr_number: number of the pull request
- destination_commit: The commit hash you want to merge into (the "before" hash) (usually on the main or master branch)
- source_commit: The commit hash of the code you are adding (the "after" branch)
- pr_comment: comment
- comment: The comment you want to publish
- annotation_file: The file you want to annotate (optional)
- annotation_line: The line number you want to annotate (optional)
Comment annotations for CodeCommit are different than GitHub.
CodeCommit only designates the starting line number for the comment.
It does not support the ending line number to highlight a range of lines.
Returns:
- None
@ -223,13 +238,30 @@ class CodeCommitClient:
self._connect_boto_client()
try:
self.boto_client.post_comment_for_pull_request(
pullRequestId=str(pr_number),
repositoryName=repo_name,
beforeCommitId=destination_commit,
afterCommitId=source_commit,
content=comment,
)
# If the comment has code annotations,
# then set the file path and line number in the location dictionary
if annotation_file and annotation_line:
self.boto_client.post_comment_for_pull_request(
pullRequestId=str(pr_number),
repositoryName=repo_name,
beforeCommitId=destination_commit,
afterCommitId=source_commit,
content=comment,
location={
"filePath": annotation_file,
"filePosition": annotation_line,
"relativeFileVersion": "AFTER",
},
)
else:
# The comment does not have code annotations
self.boto_client.post_comment_for_pull_request(
pullRequestId=str(pr_number),
repositoryName=repo_name,
beforeCommitId=destination_commit,
afterCommitId=source_commit,
content=comment,
)
except botocore.exceptions.ClientError as e:
if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
raise ValueError(f"Repository does not exist: {repo_name}") from e

42
pr_agent/git_providers/codecommit_provider.py
View File

@ -180,10 +180,37 @@ class CodeCommitProvider(GitProvider):
comment=pr_comment,
)
except Exception as e:
raise ValueError(f"CodeCommit Cannot post comment for PR: {self.pr_num}") from e
raise ValueError(f"CodeCommit Cannot publish comment for PR: {self.pr_num}") from e
def publish_code_suggestions(self, code_suggestions: list) -> bool:
return [""] # not implemented yet
counter = 1
for suggestion in code_suggestions:
# Verify that each suggestion has the required keys
if not all(key in suggestion for key in ["body", "relevant_file", "relevant_lines_start"]):
logging.warning(f"Skipping code suggestion #{counter}: Each suggestion must have 'body', 'relevant_file', 'relevant_lines_start' keys")
continue
# Publish the code suggestion to CodeCommit
try:
logging.debug(f"Code Suggestion #{counter} in file: {suggestion['relevant_file']}: {suggestion['relevant_lines_start']}")
self.codecommit_client.publish_comment(
repo_name=self.repo_name,
pr_number=self.pr_num,
destination_commit=self.pr.destination_commit,
source_commit=self.pr.source_commit,
comment=suggestion["body"],
annotation_file=suggestion["relevant_file"],
annotation_line=suggestion["relevant_lines_start"],
)
except Exception as e:
raise ValueError(f"CodeCommit Cannot publish code suggestions for PR: {self.pr_num}") from e
counter += 1
# The calling function passes in a list of code suggestions, and this function publishes each suggestion one at a time.
# If we were to return False here, the calling function will attempt to publish the same list of code suggestions again, one at a time.
# Since this function publishes the suggestions one at a time anyway, we always return True here to avoid the retry.
return True
def publish_labels(self, labels):
return [""] # not implemented yet
@ -195,6 +222,7 @@ class CodeCommitProvider(GitProvider):
return "" # not implemented yet
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
# https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_compared_commit.html
raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
@ -255,9 +283,11 @@ class CodeCommitProvider(GitProvider):
return self.codecommit_client.get_file(self.repo_name, settings_filename, self.pr.source_commit, optional=True)
def add_eyes_reaction(self, issue_comment_id: int) -> Optional[int]:
logging.info("CodeCommit provider does not support eyes reaction yet")
return True
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
logging.info("CodeCommit provider does not support removing reactions yet")
return True
@staticmethod
@ -315,16 +345,16 @@ class CodeCommitProvider(GitProvider):
return re.match(r"^[a-z]{2}-(gov-)?[a-z]+-\d\.console\.aws\.amazon\.com$", hostname) is not None
def _get_pr(self):
response = self.codecommit_client.get_pr(self.pr_num)
response = self.codecommit_client.get_pr(self.repo_name, self.pr_num)
if len(response.targets) == 0:
raise ValueError(f"No files found in CodeCommit PR: {self.pr_num}")
# TODO: implement support for multiple commits in one CodeCommit PR
# for now, we are only using the first commit in the PR
# TODO: implement support for multiple targets in one CodeCommit PR
# for now, we are only using the first target in the PR
if len(response.targets) > 1:
logging.warning(
"Multiple commits in one PR is not supported for CodeCommit yet. Continuing, using the first commit only..."
"Multiple targets in one PR is not supported for CodeCommit yet. Continuing, using the first target only..."
)
# Return our object that mimics PullRequest class from the PyGithub library

1
pr_agent/git_providers/git_provider.py
View File

@ -161,7 +161,6 @@ def get_main_pr_language(languages, files) -> str:
most_common_extension == 'scala' and top_language == 'scala' or \
most_common_extension == 'kt' and top_language == 'kotlin' or \
most_common_extension == 'pl' and top_language == 'perl' or \
most_common_extension == 'swift' and top_language == 'swift' or \
most_common_extension == top_language:
main_language_str = top_language

2
requirements.txt
View File

@ -17,3 +17,5 @@ litellm~=0.1.504
boto3~=1.28.25
google-cloud-storage==2.10.0
ujson==5.8.0
azure-devops==7.1.0b3
msrest==0.7.1

2
tests/unittest/test_codecommit_client.py
View File

@ -125,7 +125,7 @@ class TestCodeCommitProvider:
}
}
pr = api.get_pr(321)
pr = api.get_pr("my_test_repo", 321)
assert pr.title == "My PR"
assert pr.description == "My PR description"