mirror of
https://github.com/qodo-ai/pr-agent.git
synced 2025-07-04 04:40:38 +08:00
Compare commits
3 Commits
test-PR-ne
...
ok/gitlab_
| Author | SHA1 | Date | |
|---|---|---|---|
| e41247c473 | |||
| 5704070834 | |||
| 98fe376add |
@ -1,5 +1,3 @@
|
||||
venv/
|
||||
pr_agent/settings/.secrets.toml
|
||||
pics/
|
||||
pr_agent.egg-info/
|
||||
build/
|
||||
pics/
|
||||
41
.github/workflows/build-and-test.yaml
vendored
41
.github/workflows/build-and-test.yaml
vendored
@ -1,41 +0,0 @@
|
||||
name: Build-and-test
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
pull_request:
|
||||
branches:
|
||||
- main
|
||||
|
||||
jobs:
|
||||
build-and-test:
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
- id: checkout
|
||||
uses: actions/checkout@v2
|
||||
|
||||
- id: dockerx
|
||||
name: Setup Docker Buildx
|
||||
uses: docker/setup-buildx-action@v2
|
||||
|
||||
- id: build
|
||||
name: Build dev docker
|
||||
uses: docker/build-push-action@v2
|
||||
with:
|
||||
context: .
|
||||
file: ./docker/Dockerfile
|
||||
push: false
|
||||
load: true
|
||||
tags: codiumai/pr-agent:test
|
||||
cache-from: type=gha,scope=dev
|
||||
cache-to: type=gha,mode=max,scope=dev
|
||||
target: test
|
||||
|
||||
- id: test
|
||||
name: Test dev docker
|
||||
run: |
|
||||
docker run --rm codiumai/pr-agent:test pytest -v
|
||||
|
||||
|
||||
33
.github/workflows/docs-ci.yaml
vendored
33
.github/workflows/docs-ci.yaml
vendored
@ -1,33 +0,0 @@
|
||||
name: docs-ci
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
- add-docs-portal
|
||||
paths:
|
||||
- docs/**
|
||||
permissions:
|
||||
contents: write
|
||||
jobs:
|
||||
deploy:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Configure Git Credentials
|
||||
run: |
|
||||
git config user.name github-actions[bot]
|
||||
git config user.email 41898282+github-actions[bot]@users.noreply.github.com
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: 3.x
|
||||
- run: echo "cache_id=$(date --utc '+%V')" >> $GITHUB_ENV
|
||||
- uses: actions/cache@v4
|
||||
with:
|
||||
key: mkdocs-material-${{ env.cache_id }}
|
||||
path: .cache
|
||||
restore-keys: |
|
||||
mkdocs-material-
|
||||
- run: pip install mkdocs-material
|
||||
- run: pip install "mkdocs-material[imaging]"
|
||||
- run: pip install mkdocs-glightbox
|
||||
- run: mkdocs gh-deploy -f docs/mkdocs.yml --force
|
||||
35
.github/workflows/pr-agent-review.yaml
vendored
35
.github/workflows/pr-agent-review.yaml
vendored
@ -1,35 +0,0 @@
|
||||
# This workflow enables developers to call PR-Agents `/[actions]` in PR's comments and upon PR creation.
|
||||
# Learn more at https://www.codium.ai/pr-agent/
|
||||
# This is v0.2 of this workflow file
|
||||
|
||||
name: PR-Agent
|
||||
|
||||
on:
|
||||
# pull_request:
|
||||
# issue_comment:
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
issues: write
|
||||
pull-requests: write
|
||||
|
||||
jobs:
|
||||
pr_agent_job:
|
||||
runs-on: ubuntu-latest
|
||||
name: Run pr agent on every pull request
|
||||
steps:
|
||||
- name: PR Agent action step
|
||||
id: pragent
|
||||
uses: Codium-ai/pr-agent@main
|
||||
env:
|
||||
OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
|
||||
OPENAI_ORG: ${{ secrets.OPENAI_ORG }} # optional
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
PINECONE.API_KEY: ${{ secrets.PINECONE_API_KEY }}
|
||||
PINECONE.ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
|
||||
GITHUB_ACTION_CONFIG.AUTO_DESCRIBE: true
|
||||
GITHUB_ACTION_CONFIG.AUTO_REVIEW: true
|
||||
GITHUB_ACTION_CONFIG.AUTO_IMPROVE: true
|
||||
|
||||
|
||||
|
||||
16
.github/workflows/review.yaml
vendored
Normal file
16
.github/workflows/review.yaml
vendored
Normal file
@ -0,0 +1,16 @@
|
||||
on:
|
||||
pull_request:
|
||||
issue_comment:
|
||||
jobs:
|
||||
pr_agent_job:
|
||||
runs-on: ubuntu-latest
|
||||
name: Run pr agent on every pull request
|
||||
steps:
|
||||
- name: PR Agent action step
|
||||
id: pragent
|
||||
uses: Codium-ai/pr-agent@main
|
||||
env:
|
||||
OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
|
||||
OPENAI_ORG: ${{ secrets.OPENAI_ORG }} # optional
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
7
.gitignore
vendored
7
.gitignore
vendored
@ -1,9 +1,4 @@
|
||||
.idea/
|
||||
venv/
|
||||
pr_agent/settings/.secrets.toml
|
||||
__pycache__
|
||||
dist/
|
||||
*.egg-info/
|
||||
build/
|
||||
.DS_Store
|
||||
docs/.cache/
|
||||
__pycache__
|
||||
11
.gitlab-ci.yml
Normal file
11
.gitlab-ci.yml
Normal file
@ -0,0 +1,11 @@
|
||||
bot-review:
|
||||
stage: test
|
||||
variables:
|
||||
MR_URL: ${CI_MERGE_REQUEST_PROJECT_URL}/-/merge_requests/${CI_MERGE_REQUEST_IID}
|
||||
image: docker:latest
|
||||
services:
|
||||
- docker:19-dind
|
||||
script:
|
||||
- docker run --rm -e OPENAI.KEY=${OPEN_API_KEY} -e OPENAI.ORG=${OPEN_API_ORG} -e GITLAB.PERSONAL_ACCESS_TOKEN=${GITLAB_PAT} -e CONFIG.GIT_PROVIDER=gitlab codiumai/pr-agent --pr_url ${MR_URL} describe
|
||||
rules:
|
||||
- if: $CI_COMMIT_BRANCH != $CI_DEFAULT_BRANCH
|
||||
@ -1,7 +0,0 @@
|
||||
[pr_reviewer]
|
||||
enable_review_labels_effort = true
|
||||
enable_auto_approval = true
|
||||
|
||||
|
||||
[pr_code_suggestions]
|
||||
commitable_code_suggestions=false
|
||||
45
CHANGELOG.md
45
CHANGELOG.md
@ -1,45 +0,0 @@
|
||||
## 2023-08-03
|
||||
|
||||
### Optimized
|
||||
- Optimized PR diff processing by introducing caching for diff files, reducing the number of API calls.
|
||||
- Refactored `load_large_diff` function to generate a patch only when necessary.
|
||||
- Fixed a bug in the GitLab provider where the new file was not retrieved correctly.
|
||||
|
||||
## 2023-08-02
|
||||
|
||||
### Enhanced
|
||||
- Updated several tools in the `pr_agent` package to use commit messages in their functionality.
|
||||
- Commit messages are now retrieved and stored in the `vars` dictionary for each tool.
|
||||
- Added a section to display the commit messages in the prompts of various tools.
|
||||
|
||||
## 2023-08-01
|
||||
|
||||
### Enhanced
|
||||
- Introduced the ability to retrieve commit messages from pull requests across different git providers.
|
||||
- Implemented commit messages retrieval for GitHub and GitLab providers.
|
||||
- Updated the PR description template to include a section for commit messages if they exist.
|
||||
- Added support for repository-specific configuration files (.pr_agent.yaml) for the PR Agent.
|
||||
- Implemented this feature for both GitHub and GitLab providers.
|
||||
- Added a new configuration option 'use_repo_settings_file' to enable or disable the use of a repo-specific settings file.
|
||||
|
||||
|
||||
## 2023-07-30
|
||||
|
||||
### Enhanced
|
||||
- Added the ability to modify any configuration parameter from 'configuration.toml' on-the-fly.
|
||||
- Updated the command line interface and bot commands to accept configuration changes as arguments.
|
||||
- Improved the PR agent to handle additional arguments for each action.
|
||||
|
||||
## 2023-07-28
|
||||
|
||||
### Improved
|
||||
- Enhanced error handling and logging in the GitLab provider.
|
||||
- Improved handling of inline comments and code suggestions in GitLab.
|
||||
- Fixed a bug where an additional unneeded line was added to code suggestions in GitLab.
|
||||
|
||||
## 2023-07-26
|
||||
|
||||
### Added
|
||||
- New feature for updating the CHANGELOG.md based on the contents of a PR.
|
||||
- Added support for this feature for the Github provider.
|
||||
- New configuration settings and prompts for the changelog update feature.
|
||||
19
CONFIGURATION.md
Normal file
19
CONFIGURATION.md
Normal file
@ -0,0 +1,19 @@
|
||||
## Configuration
|
||||
|
||||
The different tools and sub-tools used by CodiumAI pr-agent are easily configurable via the configuration file: `/pr-agent/settings/configuration.toml`.
|
||||
##### Git Provider:
|
||||
You can select your git_provider with the flag `git_provider` in the `config` section
|
||||
|
||||
##### PR Reviewer:
|
||||
|
||||
You can enable/disable the different PR Reviewer abilities with the following flags (`pr_reviewer` section):
|
||||
```
|
||||
require_focused_review=true
|
||||
require_score_review=true
|
||||
require_tests_review=true
|
||||
require_security_review=true
|
||||
```
|
||||
You can contol the number of suggestions returned by the PR Reviewer with the following flag:
|
||||
```inline_code_comments=3```
|
||||
And enable/disable the inline code suggestions with the following flag:
|
||||
```inline_code_comments=true```
|
||||
@ -1,9 +1,8 @@
|
||||
FROM python:3.10 as base
|
||||
|
||||
WORKDIR /app
|
||||
ADD pyproject.toml .
|
||||
ADD requirements.txt .
|
||||
RUN pip install . && rm pyproject.toml requirements.txt
|
||||
RUN pip install -r requirements.txt && rm requirements.txt
|
||||
ENV PYTHONPATH=/app
|
||||
ADD pr_agent pr_agent
|
||||
ADD github_action/entrypoint.sh /
|
||||
|
||||
218
INSTALL.md
Normal file
218
INSTALL.md
Normal file
@ -0,0 +1,218 @@
|
||||
|
||||
## Installation
|
||||
|
||||
---
|
||||
|
||||
#### Method 1: Use Docker image (no installation required)
|
||||
|
||||
To request a review for a PR, or ask a question about a PR, you can run directly from the Docker image. Here's how:
|
||||
|
||||
1. To request a review for a PR, run the following command:
|
||||
|
||||
```
|
||||
docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> review
|
||||
```
|
||||
|
||||
2. To ask a question about a PR, run the following command:
|
||||
|
||||
```
|
||||
docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> ask "<your question>"
|
||||
```
|
||||
|
||||
Possible questions you can ask include:
|
||||
|
||||
- What is the main theme of this PR?
|
||||
- Is the PR ready for merge?
|
||||
- What are the main changes in this PR?
|
||||
- Should this PR be split into smaller parts?
|
||||
- Can you compose a rhymed song about this PR?
|
||||
|
||||
---
|
||||
|
||||
#### Method 2: Run as a GitHub Action
|
||||
|
||||
You can use our pre-built Github Action Docker image to run PR-Agent as a Github Action.
|
||||
|
||||
1. Add the following file to your repository under `.github/workflows/pr_agent.yml`:
|
||||
|
||||
```yaml
|
||||
on:
|
||||
pull_request:
|
||||
issue_comment:
|
||||
jobs:
|
||||
pr_agent_job:
|
||||
runs-on: ubuntu-latest
|
||||
name: Run pr agent on every pull request, respond to user comments
|
||||
steps:
|
||||
- name: PR Agent action step
|
||||
id: pragent
|
||||
uses: Codium-ai/pr-agent@main
|
||||
env:
|
||||
OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
```
|
||||
|
||||
2. Add the following secret to your repository under `Settings > Secrets`:
|
||||
|
||||
```
|
||||
OPENAI_KEY: <your key>
|
||||
```
|
||||
|
||||
The GITHUB_TOKEN secret is automatically created by GitHub.
|
||||
|
||||
3. Merge this change to your main branch.
|
||||
When you open your next PR, you should see a comment from `github-actions` bot with a review of your PR, and instructions on how to use the rest of the tools.
|
||||
|
||||
4. You may configure PR-Agent by adding environment variables under the env section corresponding to any configurable property in the [configuration](./CONFIGURATION.md) file. Some examples:
|
||||
```yaml
|
||||
env:
|
||||
# ... previous environment values
|
||||
OPENAI.ORG: "<Your organization name under your OpenAI account>"
|
||||
PR_REVIEWER.REQUIRE_TESTS_REVIEW: "false" # Disable tests review
|
||||
PR_CODE_SUGGESTIONS.NUM_CODE_SUGGESTIONS: 6 # Increase number of code suggestions
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
#### Method 3: Run from source
|
||||
|
||||
1. Clone this repository:
|
||||
|
||||
```
|
||||
git clone https://github.com/Codium-ai/pr-agent.git
|
||||
```
|
||||
|
||||
2. Install the requirements in your favorite virtual environment:
|
||||
|
||||
```
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
|
||||
3. Copy the secrets template file and fill in your OpenAI key and your GitHub user token:
|
||||
|
||||
```
|
||||
cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
|
||||
# Edit .secrets.toml file
|
||||
```
|
||||
|
||||
4. Add the pr_agent folder to your PYTHONPATH, then run the cli.py script:
|
||||
|
||||
```
|
||||
export PYTHONPATH=[$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
|
||||
|
||||
Follow steps 1-3 of method 2.
|
||||
Run the following command to start the server:
|
||||
|
||||
```
|
||||
python pr_agent/servers/github_polling.py
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
#### Method 5: Run as a GitHub App
|
||||
Allowing you to automate the review process on your private or public repositories.
|
||||
|
||||
1. Create a GitHub App from the [Github Developer Portal](https://docs.github.com/en/developers/apps/creating-a-github-app).
|
||||
|
||||
- Set the following permissions:
|
||||
- Pull requests: Read & write
|
||||
- Issue comment: Read & write
|
||||
- Metadata: Read-only
|
||||
- Set the following events:
|
||||
- Issue comment
|
||||
- Pull request
|
||||
|
||||
2. Generate a random secret for your app, and save it for later. For example, you can use:
|
||||
|
||||
```
|
||||
WEBHOOK_SECRET=$(python -c "import secrets; print(secrets.token_hex(10))")
|
||||
```
|
||||
|
||||
3. Acquire the following pieces of information from your app's settings page:
|
||||
|
||||
- App private key (click "Generate a private key" and save the file)
|
||||
- App ID
|
||||
|
||||
4. Clone this repository:
|
||||
|
||||
```
|
||||
git clone https://github.com/Codium-ai/pr-agent.git
|
||||
```
|
||||
|
||||
5. Copy the secrets template file and fill in the following:
|
||||
```
|
||||
cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
|
||||
# Edit .secrets.toml file
|
||||
```
|
||||
- Your OpenAI key.
|
||||
- Copy your app's private key to the private_key field.
|
||||
- Copy your app's ID to the app_id field.
|
||||
- Copy your app's webhook secret to the webhook_secret field.
|
||||
- Set deployment_type to 'app' in [configuration.toml](./pr_agent/settings/configuration.toml)
|
||||
|
||||
> The .secrets.toml file is not copied to the Docker image by default, and is only used for local development.
|
||||
> If you want to use the .secrets.toml file in your Docker image, you can add remove it from the .dockerignore file.
|
||||
> In most production environments, you would inject the secrets file as environment variables or as mounted volumes.
|
||||
> For example, in order to inject a secrets file as a volume in a Kubernetes environment you can update your pod spec to include the following,
|
||||
> assuming you have a secret named `pr-agent-settings` with a key named `.secrets.toml`:
|
||||
```
|
||||
volumes:
|
||||
- name: settings-volume
|
||||
secret:
|
||||
secretName: pr-agent-settings
|
||||
// ...
|
||||
containers:
|
||||
// ...
|
||||
volumeMounts:
|
||||
- mountPath: /app/pr_agent/settings_prod
|
||||
name: settings-volume
|
||||
```
|
||||
|
||||
> Another option is to set the secrets as environment variables in your deployment environment, for example `OPENAI.KEY` and `GITHUB.USER_TOKEN`.
|
||||
|
||||
6. Build a Docker image for the app and optionally push it to a Docker repository. We'll use Dockerhub as an example:
|
||||
|
||||
```
|
||||
docker build . -t codiumai/pr-agent:github_app --target github_app -f docker/Dockerfile
|
||||
docker push codiumai/pr-agent:github_app # Push to your Docker repository
|
||||
```
|
||||
|
||||
7. Host the app using a server, serverless function, or container environment. Alternatively, for development and
|
||||
debugging, you may use tools like smee.io to forward webhooks to your local machine.
|
||||
You can check [Deploy as a Lambda Function](#deploy-as-a-lambda-function)
|
||||
|
||||
8. Go back to your app's settings, and set the following:
|
||||
|
||||
- Webhook URL: The URL of your app's server or the URL of the smee.io channel.
|
||||
- Webhook secret: The secret you generated earlier.
|
||||
|
||||
9. Install the app by navigating to the "Install App" tab and selecting your desired repositories.
|
||||
|
||||
---
|
||||
|
||||
#### Deploy as a Lambda Function
|
||||
|
||||
1. Follow steps 1-5 of [Method 5](#method-5-run-as-a-github-app).
|
||||
2. Build a docker image that can be used as a lambda function
|
||||
```shell
|
||||
docker buildx build --platform=linux/amd64 . -t codiumai/pr-agent:serverless -f docker/Dockerfile.lambda
|
||||
```
|
||||
3. Push image to ECR
|
||||
```shell
|
||||
docker tag codiumai/pr-agent:serverless <AWS_ACCOUNT>.dkr.ecr.<AWS_REGION>.amazonaws.com/codiumai/pr-agent:serverless
|
||||
docker push <AWS_ACCOUNT>.dkr.ecr.<AWS_REGION>.amazonaws.com/codiumai/pr-agent:serverless
|
||||
```
|
||||
4. Create a lambda function that uses the uploaded image. Set the lambda timeout to be at least 3m.
|
||||
5. Configure the lambda function to have a Function URL.
|
||||
6. Go back to steps 8-9 of [Method 5](#method-5-run-as-a-github-app) with the function url as your Webhook URL.
|
||||
The Webhook URL would look like `https://<LAMBDA_FUNCTION_URL>/api/v1/github_webhooks`
|
||||
@ -1,2 +0,0 @@
|
||||
recursive-include pr_agent *.toml
|
||||
recursive-exclude pr_agent *.secrets.toml
|
||||
@ -1,52 +1,42 @@
|
||||
## PR Compression Strategy
|
||||
# Git Patch Logic
|
||||
There are two scenarios:
|
||||
|
||||
1. The PR is small enough to fit in a single prompt (including system and user prompt)
|
||||
2. The PR is too large to fit in a single prompt (including system and user prompt)
|
||||
|
||||
For both scenarios, we first use the following strategy
|
||||
|
||||
#### Repo language prioritization strategy
|
||||
We prioritize the languages of the repo based on the following criteria:
|
||||
|
||||
We prioritize the languages of the repo based on the following criteria:
|
||||
1. Exclude binary files and non code files (e.g. images, pdfs, etc)
|
||||
2. Given the main languages used in the repo
|
||||
3. We sort the PR files by the most common languages in the repo (in descending order):
|
||||
2. We sort the PR files by the most common languages in the repo (in descending order):
|
||||
* ```[[file.py, file2.py],[file3.js, file4.jsx],[readme.md]]```
|
||||
|
||||
|
||||
### Small PR
|
||||
## Small PR
|
||||
In this case, we can fit the entire PR in a single prompt:
|
||||
1. Exclude binary files and non code files (e.g. images, pdfs, etc)
|
||||
2. We Expand the surrounding context of each patch to 3 lines above and below the patch
|
||||
2. We Expand the surrounding context of each patch to 6 lines above and below the patch
|
||||
## Large PR
|
||||
|
||||
### Large PR
|
||||
|
||||
#### Motivation
|
||||
### Motivation
|
||||
Pull Requests can be very long and contain a lot of information with varying degree of relevance to the pr-agent.
|
||||
We want to be able to pack as much information as possible in a single LMM prompt, while keeping the information relevant to the pr-agent.
|
||||
|
||||
#### Compression strategy
|
||||
|
||||
|
||||
#### PR compression strategy
|
||||
We prioritize additions over deletions:
|
||||
- Combine all deleted files into a single list (`deleted files`)
|
||||
- File patches are a list of hunks, remove all hunks of type deletion-only from the hunks in the file patch
|
||||
|
||||
#### Adaptive and token-aware file patch fitting
|
||||
We use [tiktoken](https://github.com/openai/tiktoken) to tokenize the patches after the modifications described above, and we use the following strategy to fit the patches into the prompt:
|
||||
|
||||
1. Within each language we sort the files by the number of tokens in the file (in descending order):
|
||||
- ```[[file2.py, file.py],[file4.jsx, file3.js],[readme.md]]```
|
||||
1. Withing each language we sort the files by the number of tokens in the file (in descending order):
|
||||
* ```[[file2.py, file.py],[file4.jsx, file3.js],[readme.md]]```
|
||||
2. Iterate through the patches in the order described above
|
||||
3. Add the patches to the prompt until the prompt reaches a certain buffer from the max token length
|
||||
4. If there are still patches left, add the remaining patches as a list called `other modified files` to the prompt until the prompt reaches the max token length (hard stop), skip the rest of the patches.
|
||||
5. If we haven't reached the max token length, add the `deleted files` to the prompt until the prompt reaches the max token length (hard stop), skip the rest of the patches.
|
||||
2. Add the patches to the prompt until the prompt reaches a certain buffer from the max token length
|
||||
3. If there are still patches left, add the remaining patches as a list called `other modified files` to the prompt until the prompt reaches the max token length (hard stop), skip the rest of the patches.
|
||||
4. If we haven't reached the max token length, add the `deleted files` to the prompt until the prompt reaches the max token length (hard stop), skip the rest of the patches.
|
||||
|
||||
#### Example
|
||||
|
||||
{width=768}
|
||||
|
||||
## YAML Prompting
|
||||
TBD
|
||||
|
||||
## Static Code Analysis 💎
|
||||
TBD
|
||||
### Example
|
||||
|
||||
384
README.md
384
README.md
@ -2,337 +2,169 @@
|
||||
|
||||
<div align="center">
|
||||
|
||||
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" srcset="https://codium.ai/images/pr_agent/logo-dark.png" width="330">
|
||||
<source media="(prefers-color-scheme: light)" srcset="https://codium.ai/images/pr_agent/logo-light.png" width="330">
|
||||
<img src="https://codium.ai/images/pr_agent/logo-light.png" alt="logo" width="330">
|
||||
|
||||
</picture>
|
||||
<br/>
|
||||
CodiumAI PR-Agent aims to help efficiently review and handle pull requests, by providing AI feedbacks and suggestions
|
||||
<img src="./pics/logo-dark.png#gh-dark-mode-only" width="330"/>
|
||||
<img src="./pics/logo-light.png#gh-light-mode-only" width="330"/><br/>
|
||||
Making pull requests less painful with an AI agent
|
||||
</div>
|
||||
|
||||
[](https://github.com/Codium-ai/pr-agent/blob/main/LICENSE)
|
||||
[](https://discord.com/channels/1057273017547378788/1126104260430528613)
|
||||
[](https://twitter.com/codiumai)
|
||||
<a href="https://github.com/Codium-ai/pr-agent/commits/main">
|
||||
<img alt="GitHub" src="https://img.shields.io/github/last-commit/Codium-ai/pr-agent/main?style=for-the-badge" height="20">
|
||||
</a>
|
||||
</div>
|
||||
|
||||
### [Documentation](https://pr-agent-docs.codium.ai/)
|
||||
- See the [Installation Guide](https://pr-agent-docs.codium.ai/installation/) for instructions on installing PR-Agent on different platforms.
|
||||
|
||||
- See the [Usage Guide](https://pr-agent-docs.codium.ai/usage-guide/) for instructions on running PR-Agent tools via different interfaces, such as CLI, PR Comments, or by automatically triggering them when a new PR is opened.
|
||||
|
||||
- See the [Tools Guide](https://pr-agent-docs.codium.ai/tools/) for a detailed description of the different tools, and the available configurations for each tool.
|
||||
|
||||
|
||||
## Table of Contents
|
||||
- [News and Updates](#news-and-updates)
|
||||
- [Overview](#overview)
|
||||
- [Example results](#example-results)
|
||||
- [Try it now](#try-it-now)
|
||||
- [PR-Agent Pro 💎](#pr-agent-pro-)
|
||||
- [How it works](#how-it-works)
|
||||
- [Why use PR-Agent?](#why-use-pr-agent)
|
||||
|
||||
## News and Updates
|
||||
|
||||
### May 2, 2024
|
||||
Check out the new [PR-Agent Chrome Extension](https://chromewebstore.google.com/detail/pr-agent-chrome-extension/ephlnjeghhogofkifjloamocljapahnl) 🚀🚀🚀
|
||||
|
||||
This toolbar integrates seamlessly with your GitHub environment, allowing you to access PR-Agent tools [directly from the GitHub interface](https://www.youtube.com/watch?v=gT5tli7X4H4).
|
||||
You can also easily export your chosen configuration, and use it for the automatic commands.
|
||||
|
||||
<kbd><img src="https://codium.ai/images/pr_agent/toolbar1.png" width="512"></kbd>
|
||||
|
||||
<kbd><img src="https://codium.ai/images/pr_agent/toolbar2.png" width="512"></kbd>
|
||||
|
||||
|
||||
### April 14, 2024
|
||||
You can now ask questions about images that appear in the comment, where the entire PR is considered as the context.
|
||||
see [here](https://pr-agent-docs.codium.ai/tools/ask/#ask-on-images) for more details.
|
||||
|
||||
<kbd><img src="https://codium.ai/images/pr_agent/ask_images5.png" width="512"></kbd>
|
||||
|
||||
### March 24, 2024
|
||||
PR-Agent is now available for easy installation via [pip](https://pr-agent-docs.codium.ai/installation/locally/#using-pip-package).
|
||||
|
||||
### March 17, 2024
|
||||
- A new feature is now available for the review tool: [`require_can_be_split_review`](https://pr-agent-docs.codium.ai/tools/review/#enabledisable-features).
|
||||
If set to true, the tool will add a section that checks if the PR contains several themes, and can be split into smaller PRs.
|
||||
|
||||
<kbd><img src="https://codium.ai/images/pr_agent/multiple_pr_themes.png" width="512"></kbd>
|
||||
|
||||
### March 10, 2024
|
||||
- A new [knowledge-base website](https://pr-agent-docs.codium.ai/) for PR-Agent is now available. It includes detailed information about the different tools, usage guides and more, in an accessible and organized format.
|
||||
|
||||
### March 8, 2024
|
||||
|
||||
- A new tool, [Find Similar Code](https://pr-agent-docs.codium.ai/tools/similar_code/) 💎 is now available.
|
||||
<br>This tool retrieves the most similar code components from inside the organization's codebase, or from open-source code:
|
||||
|
||||
<kbd><a href="https://codium.ai/images/pr_agent/similar_code.mp4"><img src="https://codium.ai/images/pr_agent/similar_code_global2.png" width="512"></a></kbd>
|
||||
|
||||
(click on the image to see an instructional video)
|
||||
|
||||
### Feb 29, 2024
|
||||
- You can now use the repo's [wiki page](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/) to set configurations for PR-Agent 💎
|
||||
|
||||
<kbd><img src="https://codium.ai/images/pr_agent/wiki_configuration.png" width="512"></kbd>
|
||||
|
||||
|
||||
## Overview
|
||||
<div style="text-align:left;">
|
||||
|
||||
Supported commands per platform:
|
||||
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 feedback:
|
||||
|
||||
| | | GitHub | Gitlab | Bitbucket | Azure DevOps |
|
||||
|-------|-------------------------------------------------------------------------------------------------------------------|:--------------------:|:--------------------:|:--------------------:|:--------------------:|
|
||||
| TOOLS | Review | ✅ | ✅ | ✅ | ✅ |
|
||||
| | ⮑ Incremental | ✅ | | | |
|
||||
| | ⮑ [SOC2 Compliance](https://pr-agent-docs.codium.ai/tools/review/#soc2-ticket-compliance) 💎 | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Describe | ✅ | ✅ | ✅ | ✅ |
|
||||
| | ⮑ [Inline File Summary](https://pr-agent-docs.codium.ai/tools/describe#inline-file-summary) 💎 | ✅ | | | |
|
||||
| | Improve | ✅ | ✅ | ✅ | ✅ |
|
||||
| | ⮑ Extended | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Ask | ✅ | ✅ | ✅ | ✅ |
|
||||
| | ⮑ [Ask on code lines](https://pr-agent-docs.codium.ai/tools/ask#ask-lines) | ✅ | ✅ | | |
|
||||
| | [Custom Suggestions](https://pr-agent-docs.codium.ai/tools/custom_suggestions/) 💎 | ✅ | ✅ | ✅ | ✅ |
|
||||
| | [Test](https://pr-agent-docs.codium.ai/tools/test/) 💎 | ✅ | ✅ | | ✅ |
|
||||
| | Reflect and Review | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Update CHANGELOG.md | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Find Similar Issue | ✅ | | | |
|
||||
| | [Add PR Documentation](https://pr-agent-docs.codium.ai/tools/documentation/) 💎 | ✅ | ✅ | | ✅ |
|
||||
| | [Custom Labels](https://pr-agent-docs.codium.ai/tools/custom_labels/) 💎 | ✅ | ✅ | | ✅ |
|
||||
| | [Analyze](https://pr-agent-docs.codium.ai/tools/analyze/) 💎 | ✅ | ✅ | | ✅ |
|
||||
| | [CI Feedback](https://pr-agent-docs.codium.ai/tools/ci_feedback/) 💎 | ✅ | | | |
|
||||
| | [Similar Code](https://pr-agent-docs.codium.ai/tools/similar_code/) 💎 | ✅ | | | |
|
||||
| | | | | | |
|
||||
| USAGE | CLI | ✅ | ✅ | ✅ | ✅ |
|
||||
| | App / webhook | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Tagging bot | ✅ | | | |
|
||||
| | Actions | ✅ | | ✅ | |
|
||||
| | | | | | |
|
||||
| CORE | PR compression | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Repo language prioritization | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Adaptive and token-aware file patch fitting | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Multiple models support | ✅ | ✅ | ✅ | ✅ |
|
||||
| | [Static code analysis](https://pr-agent-docs.codium.ai/core-abilities/#static-code-analysis) 💎 | ✅ | ✅ | ✅ | ✅ |
|
||||
| | [Global and wiki configurations](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/) 💎 | ✅ | ✅ | ✅ | ✅ |
|
||||
| | [PR interactive actions](https://www.codium.ai/images/pr_agent/pr-actions.mp4) 💎 | ✅ | | | |
|
||||
- 💎 means this feature is available only in [PR-Agent Pro](https://www.codium.ai/pricing/)
|
||||
**Auto-Description**: Automatically generating PR description - title, type, summary, code walkthrough and PR labels.
|
||||
\
|
||||
**PR Review**: Adjustable feedback about the PR main theme, type, relevant tests, security issues, focus, score, and various suggestions for the PR content.
|
||||
\
|
||||
**Question Answering**: Answering free-text questions about the PR.
|
||||
\
|
||||
**Code Suggestion**: Committable code suggestions for improving the PR.
|
||||
|
||||
[//]: # (- Support for additional git providers is described in [here](./docs/Full_environments.md))
|
||||
___
|
||||
|
||||
‣ **Auto Description ([`/describe`](https://pr-agent-docs.codium.ai/tools/describe/))**: Automatically generating PR description - title, type, summary, code walkthrough and labels.
|
||||
\
|
||||
‣ **Auto Review ([`/review`](https://pr-agent-docs.codium.ai/tools/review/))**: Adjustable feedback about the PR, possible issues, security concerns, review effort and more.
|
||||
\
|
||||
‣ **Code Suggestions ([`/improve`](https://pr-agent-docs.codium.ai/tools/improve/))**: Code suggestions for improving the PR.
|
||||
\
|
||||
‣ **Question Answering ([`/ask ...`](https://pr-agent-docs.codium.ai/tools/ask/))**: Answering free-text questions about the PR.
|
||||
\
|
||||
‣ **Update Changelog ([`/update_changelog`](https://pr-agent-docs.codium.ai/tools/update_changelog/))**: Automatically updating the CHANGELOG.md file with the PR changes.
|
||||
\
|
||||
‣ **Find Similar Issue ([`/similar_issue`](https://pr-agent-docs.codium.ai/tools/similar_issues/))**: Automatically retrieves and presents similar issues.
|
||||
\
|
||||
‣ **Add Documentation 💎 ([`/add_docs`](https://pr-agent-docs.codium.ai/tools/documentation/))**: Generates documentation to methods/functions/classes that changed in the PR.
|
||||
\
|
||||
‣ **Generate Custom Labels 💎 ([`/generate_labels`](https://pr-agent-docs.codium.ai/tools/custom_labels/))**: Generates custom labels for the PR, based on specific guidelines defined by the user.
|
||||
\
|
||||
‣ **Analyze 💎 ([`/analyze`](https://pr-agent-docs.codium.ai/tools/analyze/))**: Identify code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component.
|
||||
\
|
||||
‣ **Custom Suggestions 💎 ([`/custom_suggestions`](https://pr-agent-docs.codium.ai/tools/custom_suggestions/))**: Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user.
|
||||
\
|
||||
‣ **Generate Tests 💎 ([`/test component_name`](https://pr-agent-docs.codium.ai/tools/test/))**: Generates unit tests for a selected component, based on the PR code changes.
|
||||
\
|
||||
‣ **CI Feedback 💎 ([`/checks ci_job`](https://pr-agent-docs.codium.ai/tools/ci_feedback/))**: Automatically generates feedback and analysis for a failed CI job.
|
||||
\
|
||||
‣ **Similar Code 💎 ([`/find_similar_component`](https://pr-agent-docs.codium.ai/tools/similar_code/))**: Retrieves the most similar code components from inside the organization's codebase, or from open-source code.
|
||||
___
|
||||
|
||||
## Example results
|
||||
<h3>Example results:</h2>
|
||||
</div>
|
||||
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/530">/describe</a></h4>
|
||||
<h4>/describe:</h4>
|
||||
<div align="center">
|
||||
<p float="center">
|
||||
<img src="https://www.codium.ai/images/pr_agent/describe_new_short_main.png" width="512">
|
||||
<img src="https://www.codium.ai/images/describe-2.gif" width="800">
|
||||
</p>
|
||||
</div>
|
||||
<hr>
|
||||
|
||||
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/732#issuecomment-1975099151">/review</a></h4>
|
||||
<h4>/review:</h4>
|
||||
<div align="center">
|
||||
<p float="center">
|
||||
<kbd>
|
||||
<img src="https://www.codium.ai/images/pr_agent/review_new_short_main.png" width="512">
|
||||
</kbd>
|
||||
<img src="https://www.codium.ai/images/review-2.gif" width="800">
|
||||
</p>
|
||||
</div>
|
||||
<hr>
|
||||
|
||||
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/732#issuecomment-1975099159">/improve</a></h4>
|
||||
<h4>/reflect_and_review:</h4>
|
||||
<div align="center">
|
||||
<p float="center">
|
||||
<kbd>
|
||||
<img src="https://www.codium.ai/images/pr_agent/improve_new_short_main.png" width="512">
|
||||
</kbd>
|
||||
<img src="https://www.codium.ai/images/reflect_and_review.gif" width="800">
|
||||
</p>
|
||||
</div>
|
||||
<hr>
|
||||
|
||||
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/530">/generate_labels</a></h4>
|
||||
<h4>/ask:</h4>
|
||||
<div align="center">
|
||||
<p float="center">
|
||||
<kbd><img src="https://www.codium.ai/images/pr_agent/geneare_custom_labels_main_short.png" width="300"></kbd>
|
||||
<img src="https://www.codium.ai/images/ask-2.gif" width="800">
|
||||
</p>
|
||||
</div>
|
||||
<h4>/improve:</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">
|
||||
|
||||
|
||||
- [Overview](#overview)
|
||||
- [Try it now](#try-it-now)
|
||||
- [Installation](#installation)
|
||||
- [Usage and tools](#usage-and-tools)
|
||||
- [Configuration](./CONFIGURATION.md)
|
||||
- [How it works](#how-it-works)
|
||||
- [Roadmap](#roadmap)
|
||||
- [Similar projects](#similar-projects)
|
||||
</div>
|
||||
<hr>
|
||||
|
||||
|
||||
## Overview
|
||||
`PR-Agent` offers extensive pull request functionalities across various git providers:
|
||||
| | | GitHub | Gitlab | Bitbucket |
|
||||
|-------|---------------------------------------------|:------:|:------:|:---------:|
|
||||
| TOOLS | Review | :white_check_mark: | :white_check_mark: | :white_check_mark: |
|
||||
| | ⮑ Inline review | :white_check_mark: | :white_check_mark: | |
|
||||
| | Ask | :white_check_mark: | :white_check_mark: | |
|
||||
| | Auto-Description | :white_check_mark: | :white_check_mark: | |
|
||||
| | Improve Code | :white_check_mark: | :white_check_mark: | |
|
||||
| | Reflect and Review | :white_check_mark: | | |
|
||||
| | | | | |
|
||||
| USAGE | CLI | :white_check_mark: | :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: |
|
||||
| | Repo language prioritization | :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: |
|
||||
| | 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
|
||||
|
||||
"<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.
|
||||
|
||||
## Try it now
|
||||
|
||||
Try the GPT-4 powered PR-Agent instantly on _your public GitHub repository_. 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
|
||||
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.
|
||||
|
||||
|
||||
|
||||
|
||||
To set up your own PR-Agent, see the [Installation](https://pr-agent-docs.codium.ai/installation/) section below.
|
||||
Note that when you set your own PR-Agent or use CodiumAI hosted PR-Agent, there is no need to mention `@CodiumAI-Agent ...`. Instead, directly start with the command, e.g., `/ask ...`.
|
||||
To set up your own PR-Agent, see the [Installation](#installation) section
|
||||
|
||||
---
|
||||
|
||||
[//]: # (## Installation)
|
||||
## Installation
|
||||
|
||||
[//]: # (To use your own version of PR-Agent, you first need to acquire two tokens:)
|
||||
To get started with PR-Agent quickly, you first need to acquire two tokens:
|
||||
|
||||
[//]: # ()
|
||||
[//]: # (1. An OpenAI key from [here](https://platform.openai.com/), with access to GPT-4.)
|
||||
1. An OpenAI key from [here](https://platform.openai.com/), with access to GPT-4.
|
||||
2. A GitHub personal access token (classic) with the repo scope.
|
||||
|
||||
[//]: # (2. A GitHub personal access token (classic) with the repo scope.)
|
||||
There are several ways to use PR-Agent:
|
||||
|
||||
[//]: # ()
|
||||
[//]: # (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 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)
|
||||
- Allowing you to automate the review process on your private or public repositories
|
||||
|
||||
[//]: # ()
|
||||
[//]: # (**Locally**)
|
||||
|
||||
[//]: # (- [Using pip package](https://pr-agent-docs.codium.ai/installation/locally/#using-pip-package))
|
||||
|
||||
[//]: # (- [Using Docker image](https://pr-agent-docs.codium.ai/installation/locally/#using-docker-image))
|
||||
|
||||
[//]: # (- [Run from source](https://pr-agent-docs.codium.ai/installation/locally/#run-from-source))
|
||||
|
||||
[//]: # ()
|
||||
[//]: # (**GitHub specific methods**)
|
||||
|
||||
[//]: # (- [Run as a GitHub Action](https://pr-agent-docs.codium.ai/installation/github/#run-as-a-github-action))
|
||||
|
||||
[//]: # (- [Run as a GitHub App](https://pr-agent-docs.codium.ai/installation/github/#run-as-a-github-app))
|
||||
|
||||
[//]: # ()
|
||||
[//]: # (**GitLab specific methods**)
|
||||
|
||||
[//]: # (- [Run a GitLab webhook server](https://pr-agent-docs.codium.ai/installation/gitlab/))
|
||||
|
||||
[//]: # ()
|
||||
[//]: # (**BitBucket specific methods**)
|
||||
|
||||
[//]: # (- [Run as a Bitbucket Pipeline](https://pr-agent-docs.codium.ai/installation/bitbucket/))
|
||||
|
||||
## PR-Agent Pro 💎
|
||||
[PR-Agent Pro](https://www.codium.ai/pricing/) is a hosted version of PR-Agent, provided by CodiumAI. It is available for a monthly fee, and provides the following benefits:
|
||||
1. **Fully managed** - We take care of everything for you - hosting, models, regular updates, and more. Installation is as simple as signing up and adding the PR-Agent app to your GitHub\GitLab\BitBucket repo.
|
||||
2. **Improved privacy** - No data will be stored or used to train models. PR-Agent Pro will employ zero data retention, and will use an OpenAI account with zero data retention.
|
||||
3. **Improved support** - PR-Agent Pro users will receive priority support, and will be able to request new features and capabilities.
|
||||
4. **Extra features** -In addition to the benefits listed above, PR-Agent Pro will emphasize more customization, and the usage of static code analysis, in addition to LLM logic, to improve results.
|
||||
See [here](https://pr-agent-docs.codium.ai/#pr-agent-pro) for a list of features available in PR-Agent Pro.
|
||||
## Usage and Tools
|
||||
|
||||
**PR-Agent** provides five types of interactions ("tools"): `"PR Reviewer"`, `"PR Q&A"`, `"PR Description"`, `"PR Code Sueggestions"` and `"PR Reflect and Review"`.
|
||||
|
||||
- The "PR Reviewer" tool automatically analyzes PRs, and provides various types of feedback.
|
||||
- The "PR Q&A" tool answers free-text questions about the PR.
|
||||
- The "PR Description" tool automatically sets the PR Title and body.
|
||||
- The "PR Code Suggestion" tool provide inline code suggestions for the PR that can be applied and committed.
|
||||
- The "PR Reflect and Review" tool initiates a dialog with the user, asks them to reflect on the PR, and then provides a more focused review.
|
||||
|
||||
## How it works
|
||||
|
||||
The following diagram illustrates PR-Agent tools and their flow:
|
||||
|
||||
|
||||
|
||||
Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more details on how we convert a code diff to a manageable LLM prompt
|
||||
|
||||
Check out the [PR Compression strategy](https://pr-agent-docs.codium.ai/core-abilities/#pr-compression-strategy) page for more details on how we convert a code diff to a manageable LLM prompt
|
||||
## Roadmap
|
||||
|
||||
## Why use PR-Agent?
|
||||
- [ ] Support open-source models, as a replacement for OpenAI models. (Note - a minimal requirement for each open-source model is to have 8k+ context, and good support for generating JSON as an output)
|
||||
- [x] Support other Git providers, such as Gitlab and Bitbucket.
|
||||
- [ ] Develop additional logic for handling large PRs, and compressing git patches
|
||||
- [ ] Add additional context to the prompt. For example, repo (or relevant files) summarization, with tools such a [ctags](https://github.com/universal-ctags/ctags)
|
||||
- [ ] Adding more tools. Possible directions:
|
||||
- [x] PR description
|
||||
- [x] Inline code suggestions
|
||||
- [x] Reflect and review
|
||||
- [ ] Enforcing CONTRIBUTING.md guidelines
|
||||
- [ ] Performance (are there any performance issues)
|
||||
- [ ] Documentation (is the PR properly documented)
|
||||
- [ ] Rank the PR importance
|
||||
- [ ] ...
|
||||
|
||||
A reasonable question that can be asked is: `"Why use PR-Agent? What makes it stand out from existing tools?"`
|
||||
## Similar Projects
|
||||
|
||||
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](https://pr-agent-docs.codium.ai/core-abilities/#pr-compression-strategy) 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](pr_agent/settings/configuration.toml) file. Adding additional categories is easy and accessible.
|
||||
- We support **multiple git providers** (GitHub, Gitlab, Bitbucket), **multiple ways** to use the tool (CLI, GitHub Action, GitHub App, Docker, ...), and **multiple models** (GPT-4, GPT-3.5, Anthropic, Cohere, Llama2).
|
||||
|
||||
|
||||
## Data privacy
|
||||
|
||||
If you host PR-Agent with your OpenAI API key, it is between you and OpenAI. You can read their API data privacy policy here:
|
||||
https://openai.com/enterprise-privacy
|
||||
|
||||
When using PR-Agent Pro 💎, hosted by CodiumAI, we will not store any of your data, nor will we use it for training.
|
||||
You will also benefit from an OpenAI account with zero data retention.
|
||||
|
||||
## Links
|
||||
|
||||
[](https://discord.gg/kG35uSHDBc)
|
||||
|
||||
- Discord community: https://discord.gg/kG35uSHDBc
|
||||
- CodiumAI site: https://codium.ai
|
||||
- Blog: https://www.codium.ai/blog/
|
||||
- Troubleshooting: https://www.codium.ai/blog/technical-faq-and-troubleshooting/
|
||||
- Support: support@codium.ai
|
||||
- [CodiumAI - Meaningful tests for busy devs](https://github.com/Codium-ai/codiumai-vscode-release)
|
||||
- [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)
|
||||
|
||||
103
RELEASE_NOTES.md
103
RELEASE_NOTES.md
@ -1,103 +0,0 @@
|
||||
## [Version 0.11] - 2023-12-07
|
||||
- codiumai/pr-agent:0.11
|
||||
- codiumai/pr-agent:0.11-github_app
|
||||
- codiumai/pr-agent:0.11-bitbucket-app
|
||||
- codiumai/pr-agent:0.11-gitlab_webhook
|
||||
- codiumai/pr-agent:0.11-github_polling
|
||||
- codiumai/pr-agent:0.11-github_action
|
||||
|
||||
### Added::Algo
|
||||
- New section in `/describe` tool - [PR changes walkthrough](https://github.com/Codium-ai/pr-agent/pull/509)
|
||||
- Improving PR Agent [prompts](https://github.com/Codium-ai/pr-agent/pull/501)
|
||||
- Persistent tools (`/review`, `/describe`) now send an [update message](https://github.com/Codium-ai/pr-agent/pull/499) after finishing
|
||||
- Add Amazon Bedrock [support](https://github.com/Codium-ai/pr-agent/pull/483)
|
||||
|
||||
### Fixed
|
||||
- Update [dependencies](https://github.com/Codium-ai/pr-agent/pull/503) in requirements.txt for Python 3.12
|
||||
|
||||
|
||||
## [Version 0.10] - 2023-11-15
|
||||
- codiumai/pr-agent:0.10
|
||||
- codiumai/pr-agent:0.10-github_app
|
||||
- codiumai/pr-agent:0.10-bitbucket-app
|
||||
- codiumai/pr-agent:0.10-gitlab_webhook
|
||||
- codiumai/pr-agent:0.10-github_polling
|
||||
- codiumai/pr-agent:0.10-github_action
|
||||
|
||||
### Added::Algo
|
||||
- Review tool now works with [persistent comments](https://github.com/Codium-ai/pr-agent/pull/451) by default
|
||||
- Bitbucket now publishes review suggestions with [code links](https://github.com/Codium-ai/pr-agent/pull/428)
|
||||
- Enabling to limit [max number of tokens](https://github.com/Codium-ai/pr-agent/pull/437/files)
|
||||
- Support ['gpt-4-1106-preview'](https://github.com/Codium-ai/pr-agent/pull/437/files) model
|
||||
- Support for Google's [Vertex AI](https://github.com/Codium-ai/pr-agent/pull/436)
|
||||
- Implementing [thresholds](https://github.com/Codium-ai/pr-agent/pull/423) for incremental PR reviews
|
||||
- Decoupled custom labels from [PR type](https://github.com/Codium-ai/pr-agent/pull/431)
|
||||
|
||||
### Fixed
|
||||
- Fixed bug in [parsing quotes](https://github.com/Codium-ai/pr-agent/pull/446) in CLI
|
||||
- Preserve [user-added labels](https://github.com/Codium-ai/pr-agent/pull/433) in pull requests
|
||||
- Bug fixes in GitLab and BitBucket
|
||||
|
||||
## [Version 0.9] - 2023-10-29
|
||||
- codiumai/pr-agent:0.9
|
||||
- codiumai/pr-agent:0.9-github_app
|
||||
- codiumai/pr-agent:0.9-bitbucket-app
|
||||
- codiumai/pr-agent:0.9-gitlab_webhook
|
||||
- codiumai/pr-agent:0.9-github_polling
|
||||
- codiumai/pr-agent:0.9-github_action
|
||||
|
||||
### Added::Algo
|
||||
- New tool - [generate_labels](https://github.com/Codium-ai/pr-agent/blob/main/docs/GENERATE_CUSTOM_LABELS.md)
|
||||
- New ability to use [customize labels](https://github.com/Codium-ai/pr-agent/blob/main/docs/GENERATE_CUSTOM_LABELS.md#how-to-enable-custom-labels) on the `review` and `describe` tools.
|
||||
- New tool - [add_docs](https://github.com/Codium-ai/pr-agent/blob/main/docs/ADD_DOCUMENTATION.md)
|
||||
- GitHub Action: Can now use a `.pr_agent.toml` file to control configuration parameters (see [Usage Guide](./Usage.md#working-with-github-action)).
|
||||
- GitHub App: Added ability to trigger tools on [push events](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools-for-new-code-pr-push)
|
||||
- Support custom domain URLs for Azure devops integration (see [link](https://github.com/Codium-ai/pr-agent/pull/381)).
|
||||
- PR Description default mode is now in [bullet points](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L35).
|
||||
|
||||
### Added::Documentation
|
||||
Significant documentation updates (see [Installation Guide](https://github.com/Codium-ai/pr-agent/blob/main/INSTALL.md), [Usage Guide](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md), and [Tools Guide](https://github.com/Codium-ai/pr-agent/blob/main/docs/TOOLS_GUIDE.md))
|
||||
|
||||
### Fixed
|
||||
- Fixed support for BitBucket pipeline (see [link](https://github.com/Codium-ai/pr-agent/pull/386))
|
||||
- Fixed a bug in `review -i` tool
|
||||
- Added blacklist for specific file extensions in `add_docs` tool (see [link](https://github.com/Codium-ai/pr-agent/pull/385/))
|
||||
|
||||
## [Version 0.8] - 2023-09-27
|
||||
- codiumai/pr-agent:0.8
|
||||
- codiumai/pr-agent:0.8-github_app
|
||||
- codiumai/pr-agent:0.8-bitbucket-app
|
||||
- codiumai/pr-agent:0.8-gitlab_webhook
|
||||
- codiumai/pr-agent:0.8-github_polling
|
||||
- codiumai/pr-agent:0.8-github_action
|
||||
|
||||
### Added::Algo
|
||||
- GitHub Action: Can control which tools will run automatically when a new PR is created. (see usage guide: https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-action)
|
||||
- Code suggestion tool: Will try to avoid an 'add comments' suggestion (see https://github.com/Codium-ai/pr-agent/pull/327)
|
||||
|
||||
### Fixed
|
||||
- Gitlab: Fixed a bug of improper usage of pr_id
|
||||
|
||||
|
||||
## [Version 0.7] - 2023-09-20
|
||||
|
||||
### Docker Tags
|
||||
- codiumai/pr-agent:0.7
|
||||
- codiumai/pr-agent:0.7-github_app
|
||||
- codiumai/pr-agent:0.7-bitbucket-app
|
||||
- codiumai/pr-agent:0.7-gitlab_webhook
|
||||
- codiumai/pr-agent:0.7-github_polling
|
||||
- codiumai/pr-agent:0.7-github_action
|
||||
|
||||
### Added::Algo
|
||||
- New tool /similar_issue - Currently on GitHub app and CLI: indexes the issues in the repo, find the most similar issues to the target issue.
|
||||
- Describe markers: Empower the /describe tool with a templating capability (see more details in https://github.com/Codium-ai/pr-agent/pull/273).
|
||||
- New feature in the /review tool - added an estimated effort estimation to the review (https://github.com/Codium-ai/pr-agent/pull/306).
|
||||
|
||||
### Added::Infrastructure
|
||||
- Implementation of a GitLab webhook.
|
||||
- Implementation of a BitBucket app.
|
||||
|
||||
### Fixed
|
||||
- Protection against no code suggestions generated.
|
||||
- Resilience to repositories where the languages cannot be automatically detected.
|
||||
@ -1,41 +1,20 @@
|
||||
FROM python:3.10 as base
|
||||
|
||||
WORKDIR /app
|
||||
ADD pyproject.toml .
|
||||
ADD requirements.txt .
|
||||
RUN pip install . && rm pyproject.toml requirements.txt
|
||||
RUN pip install -r requirements.txt && rm requirements.txt
|
||||
ENV PYTHONPATH=/app
|
||||
ADD pr_agent pr_agent
|
||||
|
||||
FROM base as github_app
|
||||
ADD pr_agent pr_agent
|
||||
CMD ["python", "pr_agent/servers/github_app.py"]
|
||||
|
||||
FROM base as bitbucket_app
|
||||
ADD pr_agent pr_agent
|
||||
CMD ["python", "pr_agent/servers/bitbucket_app.py"]
|
||||
|
||||
FROM base as bitbucket_server_webhook
|
||||
ADD pr_agent pr_agent
|
||||
CMD ["python", "pr_agent/servers/bitbucket_server_webhook.py"]
|
||||
|
||||
FROM base as github_polling
|
||||
ADD pr_agent pr_agent
|
||||
CMD ["python", "pr_agent/servers/github_polling.py"]
|
||||
|
||||
FROM base as gitlab_webhook
|
||||
ADD pr_agent pr_agent
|
||||
CMD ["python", "pr_agent/servers/gitlab_webhook.py"]
|
||||
|
||||
FROM base as azure_devops_webhook
|
||||
ADD pr_agent pr_agent
|
||||
CMD ["python", "pr_agent/servers/azuredevops_server_webhook.py"]
|
||||
|
||||
FROM base as test
|
||||
ADD requirements-dev.txt .
|
||||
RUN pip install -r requirements-dev.txt && rm requirements-dev.txt
|
||||
ADD pr_agent pr_agent
|
||||
ADD tests tests
|
||||
|
||||
FROM base as cli
|
||||
ADD pr_agent pr_agent
|
||||
ENTRYPOINT ["python", "pr_agent/cli.py"]
|
||||
|
||||
@ -1,12 +1,12 @@
|
||||
FROM public.ecr.aws/lambda/python:3.10
|
||||
|
||||
RUN yum update -y && \
|
||||
yum install -y gcc python3-devel git && \
|
||||
yum install -y gcc python3-devel && \
|
||||
yum clean all
|
||||
|
||||
ADD pyproject.toml requirements.txt .
|
||||
RUN pip install . && rm pyproject.toml
|
||||
RUN pip install mangum==0.17.0
|
||||
ADD requirements.txt .
|
||||
RUN pip install -r requirements.txt && rm requirements.txt
|
||||
RUN pip install mangum==16.0.0
|
||||
COPY pr_agent/ ${LAMBDA_TASK_ROOT}/pr_agent/
|
||||
|
||||
CMD ["pr_agent.servers.serverless.serverless"]
|
||||
|
||||
@ -1 +0,0 @@
|
||||
# [Visit Our Docs Portal](https://pr-agent-docs.codium.ai/)
|
||||
@ -1 +0,0 @@
|
||||
pr-agent-docs.codium.ai
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 15 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 263 KiB |
@ -1,140 +0,0 @@
|
||||
<?xml version="1.0" encoding="utf-8"?>
|
||||
<!-- Generator: Adobe Illustrator 28.1.0, SVG Export Plug-In . SVG Version: 6.00 Build 0) -->
|
||||
<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
|
||||
width="64px" height="64px" viewBox="0 0 64 64" enable-background="new 0 0 64 64" xml:space="preserve">
|
||||
<g>
|
||||
<defs>
|
||||
<rect id="SVGID_1_" x="0.4" y="0.1" width="63.4" height="63.4"/>
|
||||
</defs>
|
||||
<clipPath id="SVGID_00000008836131916906499950000015813697852011234749_">
|
||||
<use xlink:href="#SVGID_1_" overflow="visible"/>
|
||||
</clipPath>
|
||||
<g clip-path="url(#SVGID_00000008836131916906499950000015813697852011234749_)">
|
||||
<path fill="#05E5AD" d="M21.4,9.8c3,0,5.9,0.7,8.5,1.9c-5.7,3.4-9.8,11.1-9.8,20.1c0,9,4,16.7,9.8,20.1c-2.6,1.2-5.5,1.9-8.5,1.9
|
||||
c-11.6,0-21-9.8-21-22S9.8,9.8,21.4,9.8z"/>
|
||||
|
||||
<radialGradient id="SVGID_00000150822754378345238340000008985053211526864828_" cx="-140.0905" cy="350.1757" r="4.8781" gradientTransform="matrix(-4.7708 -6.961580e-02 -0.1061 7.2704 -601.3099 -2523.8489)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#6447FF"/>
|
||||
<stop offset="6.666670e-02" style="stop-color:#6348FE"/>
|
||||
<stop offset="0.1333" style="stop-color:#614DFC"/>
|
||||
<stop offset="0.2" style="stop-color:#5C54F8"/>
|
||||
<stop offset="0.2667" style="stop-color:#565EF3"/>
|
||||
<stop offset="0.3333" style="stop-color:#4E6CEC"/>
|
||||
<stop offset="0.4" style="stop-color:#447BE4"/>
|
||||
<stop offset="0.4667" style="stop-color:#3A8DDB"/>
|
||||
<stop offset="0.5333" style="stop-color:#2F9FD1"/>
|
||||
<stop offset="0.6" style="stop-color:#25B1C8"/>
|
||||
<stop offset="0.6667" style="stop-color:#1BC0C0"/>
|
||||
<stop offset="0.7333" style="stop-color:#13CEB9"/>
|
||||
<stop offset="0.8" style="stop-color:#0DD8B4"/>
|
||||
<stop offset="0.8667" style="stop-color:#08DFB0"/>
|
||||
<stop offset="0.9333" style="stop-color:#06E4AE"/>
|
||||
<stop offset="1" style="stop-color:#05E5AD"/>
|
||||
</radialGradient>
|
||||
<path fill="url(#SVGID_00000150822754378345238340000008985053211526864828_)" d="M21.4,9.8c3,0,5.9,0.7,8.5,1.9
|
||||
c-5.7,3.4-9.8,11.1-9.8,20.1c0,9,4,16.7,9.8,20.1c-2.6,1.2-5.5,1.9-8.5,1.9c-11.6,0-21-9.8-21-22S9.8,9.8,21.4,9.8z"/>
|
||||
|
||||
<radialGradient id="SVGID_00000022560571240417802950000012439139323268113305_" cx="-191.7649" cy="385.7387" r="4.8781" gradientTransform="matrix(-2.5514 -0.7616 -0.8125 2.7217 -130.733 -1180.2209)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#6447FF"/>
|
||||
<stop offset="6.666670e-02" style="stop-color:#6348FE"/>
|
||||
<stop offset="0.1333" style="stop-color:#614DFC"/>
|
||||
<stop offset="0.2" style="stop-color:#5C54F8"/>
|
||||
<stop offset="0.2667" style="stop-color:#565EF3"/>
|
||||
<stop offset="0.3333" style="stop-color:#4E6CEC"/>
|
||||
<stop offset="0.4" style="stop-color:#447BE4"/>
|
||||
<stop offset="0.4667" style="stop-color:#3A8DDB"/>
|
||||
<stop offset="0.5333" style="stop-color:#2F9FD1"/>
|
||||
<stop offset="0.6" style="stop-color:#25B1C8"/>
|
||||
<stop offset="0.6667" style="stop-color:#1BC0C0"/>
|
||||
<stop offset="0.7333" style="stop-color:#13CEB9"/>
|
||||
<stop offset="0.8" style="stop-color:#0DD8B4"/>
|
||||
<stop offset="0.8667" style="stop-color:#08DFB0"/>
|
||||
<stop offset="0.9333" style="stop-color:#06E4AE"/>
|
||||
<stop offset="1" style="stop-color:#05E5AD"/>
|
||||
</radialGradient>
|
||||
<path fill="url(#SVGID_00000022560571240417802950000012439139323268113305_)" d="M38,18.3c-2.1-2.8-4.9-5.1-8.1-6.6
|
||||
c2-1.2,4.2-1.9,6.6-1.9c2.2,0,4.3,0.6,6.2,1.7C40.8,12.9,39.2,15.3,38,18.3L38,18.3z"/>
|
||||
|
||||
<radialGradient id="SVGID_00000143611122169386473660000017673587931016751800_" cx="-194.7918" cy="395.2442" r="4.8781" gradientTransform="matrix(-2.5514 -0.7616 -0.8125 2.7217 -130.733 -1172.9556)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#6447FF"/>
|
||||
<stop offset="6.666670e-02" style="stop-color:#6348FE"/>
|
||||
<stop offset="0.1333" style="stop-color:#614DFC"/>
|
||||
<stop offset="0.2" style="stop-color:#5C54F8"/>
|
||||
<stop offset="0.2667" style="stop-color:#565EF3"/>
|
||||
<stop offset="0.3333" style="stop-color:#4E6CEC"/>
|
||||
<stop offset="0.4" style="stop-color:#447BE4"/>
|
||||
<stop offset="0.4667" style="stop-color:#3A8DDB"/>
|
||||
<stop offset="0.5333" style="stop-color:#2F9FD1"/>
|
||||
<stop offset="0.6" style="stop-color:#25B1C8"/>
|
||||
<stop offset="0.6667" style="stop-color:#1BC0C0"/>
|
||||
<stop offset="0.7333" style="stop-color:#13CEB9"/>
|
||||
<stop offset="0.8" style="stop-color:#0DD8B4"/>
|
||||
<stop offset="0.8667" style="stop-color:#08DFB0"/>
|
||||
<stop offset="0.9333" style="stop-color:#06E4AE"/>
|
||||
<stop offset="1" style="stop-color:#05E5AD"/>
|
||||
</radialGradient>
|
||||
<path fill="url(#SVGID_00000143611122169386473660000017673587931016751800_)" d="M38,45.2c1.2,3,2.9,5.3,4.7,6.8
|
||||
c-1.9,1.1-4,1.7-6.2,1.7c-2.3,0-4.6-0.7-6.6-1.9C33.1,50.4,35.8,48.1,38,45.2L38,45.2z"/>
|
||||
<path fill="#684BFE" d="M20.1,31.8c0-9,4-16.7,9.8-20.1c3.2,1.5,6,3.8,8.1,6.6c-1.5,3.7-2.5,8.4-2.5,13.5s0.9,9.8,2.5,13.5
|
||||
c-2.1,2.8-4.9,5.1-8.1,6.6C24.1,48.4,20.1,40.7,20.1,31.8z"/>
|
||||
|
||||
<radialGradient id="SVGID_00000147942998054305738810000004710078864578628519_" cx="-212.7358" cy="363.2475" r="4.8781" gradientTransform="matrix(-2.3342 -1.063 -1.623 3.5638 149.3813 -1470.1027)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#6447FF"/>
|
||||
<stop offset="6.666670e-02" style="stop-color:#6348FE"/>
|
||||
<stop offset="0.1333" style="stop-color:#614DFC"/>
|
||||
<stop offset="0.2" style="stop-color:#5C54F8"/>
|
||||
<stop offset="0.2667" style="stop-color:#565EF3"/>
|
||||
<stop offset="0.3333" style="stop-color:#4E6CEC"/>
|
||||
<stop offset="0.4" style="stop-color:#447BE4"/>
|
||||
<stop offset="0.4667" style="stop-color:#3A8DDB"/>
|
||||
<stop offset="0.5333" style="stop-color:#2F9FD1"/>
|
||||
<stop offset="0.6" style="stop-color:#25B1C8"/>
|
||||
<stop offset="0.6667" style="stop-color:#1BC0C0"/>
|
||||
<stop offset="0.7333" style="stop-color:#13CEB9"/>
|
||||
<stop offset="0.8" style="stop-color:#0DD8B4"/>
|
||||
<stop offset="0.8667" style="stop-color:#08DFB0"/>
|
||||
<stop offset="0.9333" style="stop-color:#06E4AE"/>
|
||||
<stop offset="1" style="stop-color:#05E5AD"/>
|
||||
</radialGradient>
|
||||
<path fill="url(#SVGID_00000147942998054305738810000004710078864578628519_)" d="M50.7,42.5c0.6,3.3,1.5,6.1,2.5,8
|
||||
c-1.8,2-3.8,3.1-6,3.1c-1.6,0-3.1-0.6-4.5-1.7C46.1,50.2,48.9,46.8,50.7,42.5L50.7,42.5z"/>
|
||||
|
||||
<radialGradient id="SVGID_00000083770737908230256670000016126156495859285174_" cx="-208.5327" cy="357.2025" r="4.8781" gradientTransform="matrix(-2.3342 -1.063 -1.623 3.5638 149.3813 -1476.8097)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#6447FF"/>
|
||||
<stop offset="6.666670e-02" style="stop-color:#6348FE"/>
|
||||
<stop offset="0.1333" style="stop-color:#614DFC"/>
|
||||
<stop offset="0.2" style="stop-color:#5C54F8"/>
|
||||
<stop offset="0.2667" style="stop-color:#565EF3"/>
|
||||
<stop offset="0.3333" style="stop-color:#4E6CEC"/>
|
||||
<stop offset="0.4" style="stop-color:#447BE4"/>
|
||||
<stop offset="0.4667" style="stop-color:#3A8DDB"/>
|
||||
<stop offset="0.5333" style="stop-color:#2F9FD1"/>
|
||||
<stop offset="0.6" style="stop-color:#25B1C8"/>
|
||||
<stop offset="0.6667" style="stop-color:#1BC0C0"/>
|
||||
<stop offset="0.7333" style="stop-color:#13CEB9"/>
|
||||
<stop offset="0.8" style="stop-color:#0DD8B4"/>
|
||||
<stop offset="0.8667" style="stop-color:#08DFB0"/>
|
||||
<stop offset="0.9333" style="stop-color:#06E4AE"/>
|
||||
<stop offset="1" style="stop-color:#05E5AD"/>
|
||||
</radialGradient>
|
||||
<path fill="url(#SVGID_00000083770737908230256670000016126156495859285174_)" d="M42.7,11.5c1.4-1.1,2.9-1.7,4.5-1.7
|
||||
c2.2,0,4.3,1.1,6,3.1c-1,2-1.9,4.7-2.5,8C48.9,16.7,46.1,13.4,42.7,11.5L42.7,11.5z"/>
|
||||
<path fill="#684BFE" d="M38,45.2c2.8-3.7,4.4-8.4,4.4-13.5c0-5.1-1.7-9.8-4.4-13.5c1.2-3,2.9-5.3,4.7-6.8c3.4,1.9,6.2,5.3,8,9.5
|
||||
c-0.6,3.2-0.9,6.9-0.9,10.8s0.3,7.6,0.9,10.8c-1.8,4.3-4.6,7.6-8,9.5C40.8,50.6,39.2,48.2,38,45.2L38,45.2z"/>
|
||||
<path fill="#321BB2" d="M38,45.2c-1.5-3.7-2.5-8.4-2.5-13.5S36.4,22,38,18.3c2.8,3.7,4.4,8.4,4.4,13.5S40.8,41.5,38,45.2z"/>
|
||||
<path fill="#05E6AD" d="M53.2,12.9c1.1-2,2.3-3.1,3.6-3.1c3.9,0,7,9.8,7,22s-3.1,22-7,22c-1.3,0-2.6-1.1-3.6-3.1
|
||||
c3.4-3.8,5.7-10.8,5.7-18.8C58.8,23.8,56.6,16.8,53.2,12.9z"/>
|
||||
|
||||
<radialGradient id="SVGID_00000009565123575973598080000009335550354766300606_" cx="-7.8671" cy="278.2442" r="4.8781" gradientTransform="matrix(1.5187 0 0 -7.8271 69.237 2209.3281)" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0" style="stop-color:#05E5AD"/>
|
||||
<stop offset="0.32" style="stop-color:#05E5AD;stop-opacity:0"/>
|
||||
<stop offset="0.9028" style="stop-color:#6447FF"/>
|
||||
</radialGradient>
|
||||
<path fill="url(#SVGID_00000009565123575973598080000009335550354766300606_)" d="M53.2,12.9c1.1-2,2.3-3.1,3.6-3.1
|
||||
c3.9,0,7,9.8,7,22s-3.1,22-7,22c-1.3,0-2.6-1.1-3.6-3.1c3.4-3.8,5.7-10.8,5.7-18.8C58.8,23.8,56.6,16.8,53.2,12.9z"/>
|
||||
<path fill="#684BFE" d="M52.8,31.8c0-3.9-0.8-7.6-2.1-10.8c0.6-3.3,1.5-6.1,2.5-8c3.4,3.8,5.7,10.8,5.7,18.8c0,8-2.3,15-5.7,18.8
|
||||
c-1-2-1.9-4.7-2.5-8C52,39.3,52.8,35.7,52.8,31.8z"/>
|
||||
<path fill="#321BB2" d="M50.7,42.5c-0.6-3.2-0.9-6.9-0.9-10.8s0.3-7.6,0.9-10.8c1.3,3.2,2.1,6.9,2.1,10.8S52,39.3,50.7,42.5z"/>
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 9.0 KiB |
@ -1,27 +0,0 @@
|
||||
|
||||
|
||||
:root {
|
||||
--md-primary-fg-color: #765bfa;
|
||||
--md-accent-fg-color: #AEA1F1;
|
||||
}
|
||||
.md-nav__title, .md-nav__link {
|
||||
font-size: 16px;
|
||||
}
|
||||
|
||||
.md-tabs__link {
|
||||
font-size: 16px;
|
||||
}
|
||||
|
||||
.md-header__title {
|
||||
font-size: 20px;
|
||||
margin-left: 0px !important;
|
||||
}
|
||||
|
||||
.md-content img {
|
||||
border-width: 1px;
|
||||
border-style: solid;
|
||||
border-color: black;
|
||||
outline-width: 1px;
|
||||
outline-style: solid;
|
||||
outline-color: darkgray;
|
||||
}
|
||||
@ -1,113 +0,0 @@
|
||||
# Overview
|
||||
|
||||
CodiumAI PR-Agent is an open-source tool to help efficiently review and handle pull requests.
|
||||
|
||||
- See the [Installation Guide](./installation/index.md) for instructions on installing and running the tool on different git platforms.
|
||||
|
||||
- See the [Usage Guide](./usage-guide/index.md) for instructions on running the PR-Agent commands via different interfaces, including _CLI_, _online usage_, or by _automatically triggering_ them when a new PR is opened.
|
||||
|
||||
- See the [Tools Guide](./tools/index.md) for a detailed description of the different tools.
|
||||
|
||||
|
||||
## PR-Agent Features
|
||||
PR-Agent offers extensive pull request functionalities across various git providers.
|
||||
|
||||
| | | GitHub | Gitlab | Bitbucket | Azure DevOps |
|
||||
|-------|---------------------------------------------------------------------------------------------------------------------|:------:|:------:|:---------:|:------------:|
|
||||
| TOOLS | Review | ✅ | ✅ | ✅ | ✅ |
|
||||
| | ⮑ Incremental | ✅ | | | |
|
||||
| | ⮑ [SOC2 Compliance](https://pr-agent-docs.codium.ai/tools/review/#soc2-ticket-compliance){:target="_blank"} 💎 | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Ask | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Describe | ✅ | ✅ | ✅ | ✅ |
|
||||
| | ⮑ [Inline file summary](https://pr-agent-docs.codium.ai/tools/describe/#inline-file-summary){:target="_blank"} 💎 | ✅ | ✅ | | ✅ |
|
||||
| | Improve | ✅ | ✅ | ✅ | ✅ |
|
||||
| | ⮑ Extended | ✅ | ✅ | ✅ | ✅ |
|
||||
| | [Custom Suggestions](./tools/custom_suggestions.md){:target="_blank"} 💎 | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Reflect and Review | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Update CHANGELOG.md | ✅ | ✅ | ✅ | ️ |
|
||||
| | Find Similar Issue | ✅ | | | ️ |
|
||||
| | [Add PR Documentation](./tools/documentation.md){:target="_blank"} 💎 | ✅ | ✅ | | ✅ |
|
||||
| | [Generate Custom Labels](./tools/describe.md#handle-custom-labels-from-the-repos-labels-page-💎){:target="_blank"} 💎 | ✅ | ✅ | | ✅ |
|
||||
| | [Analyze PR Components](./tools/analyze.md){:target="_blank"} 💎 | ✅ | ✅ | | ✅ |
|
||||
| | | | | | ️ |
|
||||
| USAGE | CLI | ✅ | ✅ | ✅ | ✅ |
|
||||
| | App / webhook | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Actions | ✅ | | | ️ |
|
||||
| | | | | |
|
||||
| CORE | PR compression | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Repo language prioritization | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Adaptive and token-aware file patch fitting | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Multiple models support | ✅ | ✅ | ✅ | ✅ |
|
||||
| | Incremental PR review | ✅ | | | |
|
||||
| | [Static code analysis](./tools/analyze.md/){:target="_blank"} 💎 | ✅ | ✅ | ✅ | ✅ |
|
||||
| | [Multiple configuration options](./usage-guide/configuration_options.md){:target="_blank"} 💎 | ✅ | ✅ | ✅ | ✅ |
|
||||
|
||||
💎 marks a feature available only in [PR-Agent Pro](https://www.codium.ai/pricing/){:target="_blank"}
|
||||
|
||||
|
||||
## Example Results
|
||||
<hr>
|
||||
|
||||
#### [/describe](https://github.com/Codium-ai/pr-agent/pull/530)
|
||||
<figure markdown="1">
|
||||
{width=512}
|
||||
</figure>
|
||||
<hr>
|
||||
|
||||
#### [/review](https://github.com/Codium-ai/pr-agent/pull/732#issuecomment-1975099151)
|
||||
<figure markdown="1">
|
||||
{width=512}
|
||||
</figure>
|
||||
<hr>
|
||||
|
||||
#### [/improve](https://github.com/Codium-ai/pr-agent/pull/732#issuecomment-1975099159)
|
||||
<figure markdown="1">
|
||||
{width=512}
|
||||
</figure>
|
||||
<hr>
|
||||
|
||||
#### [/generate_labels](https://github.com/Codium-ai/pr-agent/pull/530)
|
||||
<figure markdown="1">
|
||||
{width=300}
|
||||
</figure>
|
||||
<hr>
|
||||
|
||||
## How it Works
|
||||
|
||||
The following diagram illustrates PR-Agent tools and their flow:
|
||||
|
||||
|
||||
|
||||
Check out the [PR Compression strategy](core-abilities/index.md) page for more details on how we convert a code diff to a manageable LLM prompt
|
||||
|
||||
|
||||
|
||||
## PR-Agent Pro 💎
|
||||
|
||||
[PR-Agent Pro](https://www.codium.ai/pricing/) is a hosted version of PR-Agent, provided by CodiumAI. It is available for a monthly fee, and provides the following benefits:
|
||||
|
||||
1. **Fully managed** - We take care of everything for you - hosting, models, regular updates, and more. Installation is as simple as signing up and adding the PR-Agent app to your GitHub\GitLab\BitBucket repo.
|
||||
2. **Improved privacy** - No data will be stored or used to train models. PR-Agent Pro will employ zero data retention, and will use an OpenAI account with zero data retention.
|
||||
3. **Improved support** - PR-Agent Pro users will receive priority support, and will be able to request new features and capabilities.
|
||||
4. **Extra features** -In addition to the benefits listed above, PR-Agent Pro will emphasize more customization, and the usage of static code analysis, in addition to LLM logic, to improve results. It has the following additional tools and features:
|
||||
- (Tool): [**Analyze PR components**](./tools/analyze.md/)
|
||||
- (Tool): [**Custom Code Suggestions**](./tools/custom_suggestions.md/)
|
||||
- (Tool): [**Tests**](./tools/test.md/)
|
||||
- (Tool): [**PR documentation**](./tools/documentation.md/)
|
||||
- (Tool): [**Improve Component**](https://pr-agent-docs.codium.ai/tools/improve_component/)
|
||||
- (Tool): [**Similar code search**](https://pr-agent-docs.codium.ai/tools/similar_code/)
|
||||
- (Tool): [**CI feedback**](./tools/ci_feedback.md/)
|
||||
- (Feature): [**Interactive triggering**](./usage-guide/automations_and_usage.md/#interactive-triggering)
|
||||
- (Feature): [**SOC2 compliance check**](./tools/review.md/#soc2-ticket-compliance)
|
||||
- (Feature): [**Custom labels**](./tools/describe.md/#handle-custom-labels-from-the-repos-labels-page)
|
||||
- (Feature): [**Global and wiki configuration**](./usage-guide/configuration_options.md/#wiki-configuration-file)
|
||||
- (Feature): [**Inline file summary**](https://pr-agent-docs.codium.ai/tools/describe/#inline-file-summary)
|
||||
|
||||
|
||||
## Data Privacy
|
||||
|
||||
If you host PR-Agent with your OpenAI API key, it is between you and OpenAI. You can read their API data privacy policy here:
|
||||
https://openai.com/enterprise-privacy
|
||||
|
||||
When using PR-Agent Pro 💎, hosted by CodiumAI, we will not store any of your data, nor will we use it for training.
|
||||
You will also benefit from an OpenAI account with zero data retention.
|
||||
@ -1,35 +0,0 @@
|
||||
## Azure DevOps provider
|
||||
|
||||
To use Azure DevOps provider use the following settings in configuration.toml:
|
||||
```
|
||||
[config]
|
||||
git_provider="azure"
|
||||
```
|
||||
|
||||
Azure DevOps provider supports [PAT token](https://learn.microsoft.com/en-us/azure/devops/organizations/accounts/use-personal-access-tokens-to-authenticate?view=azure-devops&tabs=Windows) or [DefaultAzureCredential](https://learn.microsoft.com/en-us/azure/developer/python/sdk/authentication-overview#authentication-in-server-environments) authentication.
|
||||
PAT is faster to create, but has build in expiration date, and will use the user identity for API calls.
|
||||
Using DefaultAzureCredential you can use managed identity or Service principle, which are more secure and will create separate ADO user identity (via AAD) to the agent.
|
||||
|
||||
If PAT was chosen, you can assign the value in .secrets.toml.
|
||||
If DefaultAzureCredential was chosen, you can assigned the additional env vars like AZURE_CLIENT_SECRET directly,
|
||||
or use managed identity/az cli (for local development) without any additional configuration.
|
||||
in any case, 'org' value must be assigned in .secrets.toml:
|
||||
```
|
||||
[azure_devops]
|
||||
org = "https://dev.azure.com/YOUR_ORGANIZATION/"
|
||||
# pat = "YOUR_PAT_TOKEN" needed only if using PAT for authentication
|
||||
```
|
||||
|
||||
### Azure DevOps Webhook
|
||||
|
||||
To trigger from an Azure webhook, you need to manually [add a webhook](https://learn.microsoft.com/en-us/azure/devops/service-hooks/services/webhooks?view=azure-devops).
|
||||
Use the "Pull request created" type to trigger a review, or "Pull request commented on" to trigger any supported comment with /<command> <args> comment on the relevant PR. Note that for the "Pull request commented on" trigger, only API v2.0 is supported.
|
||||
|
||||
|
||||
For webhook security, create a sporadic username/password pair and configure the webhook username and password on both the server and Azure DevOps webhook. These will be sent as basic Auth data by the webhook with each request:
|
||||
```
|
||||
[azure_devops_server]
|
||||
webhook_username = "<basic auth user>"
|
||||
webhook_password = "<basic auth password>"
|
||||
```
|
||||
> :warning: **Ensure that the webhook endpoint is only accessible over HTTPS** to mitigate the risk of credential interception when using basic authentication.
|
||||
@ -1,70 +0,0 @@
|
||||
## Run as a Bitbucket Pipeline
|
||||
|
||||
|
||||
You can use the Bitbucket Pipeline system to run PR-Agent on every pull request open or update.
|
||||
|
||||
1. Add the following file in your repository bitbucket_pipelines.yml
|
||||
|
||||
```yaml
|
||||
pipelines:
|
||||
pull-requests:
|
||||
'**':
|
||||
- step:
|
||||
name: PR Agent Review
|
||||
image: python:3.10
|
||||
services:
|
||||
- docker
|
||||
script:
|
||||
- docker run -e CONFIG.GIT_PROVIDER=bitbucket -e OPENAI.KEY=$OPENAI_API_KEY -e BITBUCKET.BEARER_TOKEN=$BITBUCKET_BEARER_TOKEN codiumai/pr-agent:latest --pr_url=https://bitbucket.org/$BITBUCKET_WORKSPACE/$BITBUCKET_REPO_SLUG/pull-requests/$BITBUCKET_PR_ID review
|
||||
```
|
||||
|
||||
2. Add the following secure variables to your repository under Repository settings > Pipelines > Repository variables.
|
||||
OPENAI_API_KEY: `<your key>`
|
||||
BITBUCKET_BEARER_TOKEN: `<your token>`
|
||||
|
||||
You can get a Bitbucket token for your repository by following Repository Settings -> Security -> Access Tokens.
|
||||
|
||||
Note that comments on a PR are not supported in Bitbucket Pipeline.
|
||||
|
||||
|
||||
## Run using CodiumAI-hosted Bitbucket app
|
||||
|
||||
Please contact [support@codium.ai](mailto:support@codium.ai) or visit [CodiumAI pricing page](https://www.codium.ai/pricing/) if you're interested in a hosted BitBucket app solution that provides full functionality including PR reviews and comment handling. It's based on the [bitbucket_app.py](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/git_providers/bitbucket_provider.py) implementation.
|
||||
|
||||
|
||||
## Bitbucket Server and Data Center
|
||||
|
||||
Login into your on-prem instance of Bitbucket with your service account username and password.
|
||||
Navigate to `Manage account`, `HTTP Access tokens`, `Create Token`.
|
||||
Generate the token and add it to .secret.toml under `bitbucket_server` section
|
||||
|
||||
```toml
|
||||
[bitbucket_server]
|
||||
bearer_token = "<your key>"
|
||||
```
|
||||
|
||||
### Run it as CLI
|
||||
|
||||
Modify `configuration.toml`:
|
||||
|
||||
```toml
|
||||
git_provider="bitbucket_server"
|
||||
```
|
||||
|
||||
and pass the Pull request URL:
|
||||
```shell
|
||||
python cli.py --pr_url https://git.onpreminstanceofbitbucket.com/projects/PROJECT/repos/REPO/pull-requests/1 review
|
||||
```
|
||||
|
||||
### Run it as service
|
||||
|
||||
To run pr-agent as webhook, build the docker image:
|
||||
```
|
||||
docker build . -t codiumai/pr-agent:bitbucket_server_webhook --target bitbucket_server_webhook -f docker/Dockerfile
|
||||
docker push codiumai/pr-agent:bitbucket_server_webhook # Push to your Docker repository
|
||||
```
|
||||
|
||||
Navigate to `Projects` or `Repositories`, `Settings`, `Webhooks`, `Create Webhook`.
|
||||
Fill the name and URL, Authentication None select the Pull Request Opened checkbox to receive that event as webhook.
|
||||
|
||||
The URL should end with `/webhook`, for example: https://domain.com/webhook
|
||||
@ -1,242 +0,0 @@
|
||||
## Run as a GitHub Action
|
||||
|
||||
You can use our pre-built Github Action Docker image to run PR-Agent as a Github Action.
|
||||
|
||||
1) Add the following file to your repository under `.github/workflows/pr_agent.yml`:
|
||||
|
||||
```yaml
|
||||
on:
|
||||
pull_request:
|
||||
types: [opened, reopened, ready_for_review]
|
||||
issue_comment:
|
||||
jobs:
|
||||
pr_agent_job:
|
||||
if: ${{ github.event.sender.type != 'Bot' }}
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
issues: write
|
||||
pull-requests: write
|
||||
contents: write
|
||||
name: Run pr agent on every pull request, respond to user comments
|
||||
steps:
|
||||
- name: PR Agent action step
|
||||
id: pragent
|
||||
uses: Codium-ai/pr-agent@main
|
||||
env:
|
||||
OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
```
|
||||
** if you want to pin your action to a specific release (v2.0 for example) for stability reasons, use:
|
||||
```yaml
|
||||
...
|
||||
steps:
|
||||
- name: PR Agent action step
|
||||
id: pragent
|
||||
uses: Codium-ai/pr-agent@v2.0
|
||||
...
|
||||
```
|
||||
2) Add the following secret to your repository under `Settings > Secrets and variables > Actions > New repository secret > Add secret`:
|
||||
|
||||
```
|
||||
Name = OPENAI_KEY
|
||||
Secret = <your key>
|
||||
```
|
||||
|
||||
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](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml) file. Some examples:
|
||||
```yaml
|
||||
env:
|
||||
# ... previous environment values
|
||||
OPENAI.ORG: "<Your organization name under your OpenAI account>"
|
||||
PR_REVIEWER.REQUIRE_TESTS_REVIEW: "false" # Disable tests review
|
||||
PR_CODE_SUGGESTIONS.NUM_CODE_SUGGESTIONS: 6 # Increase number of code suggestions
|
||||
```
|
||||
See detailed usage instructions in the [USAGE GUIDE](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#github-action)
|
||||
|
||||
---
|
||||
|
||||
## Run as a GitHub App
|
||||
Allowing you to automate the review process on your private or public repositories.
|
||||
|
||||
1) Create a GitHub App from the [Github Developer Portal](https://docs.github.com/en/developers/apps/creating-a-github-app).
|
||||
|
||||
- Set the following permissions:
|
||||
- Pull requests: Read & write
|
||||
- Issue comment: Read & write
|
||||
- Metadata: Read-only
|
||||
- Contents: Read-only
|
||||
- Set the following events:
|
||||
- Issue comment
|
||||
- Pull request
|
||||
- Push (if you need to enable triggering on PR update)
|
||||
|
||||
2) Generate a random secret for your app, and save it for later. For example, you can use:
|
||||
|
||||
```
|
||||
WEBHOOK_SECRET=$(python -c "import secrets; print(secrets.token_hex(10))")
|
||||
```
|
||||
|
||||
3) Acquire the following pieces of information from your app's settings page:
|
||||
|
||||
- App private key (click "Generate a private key" and save the file)
|
||||
- App ID
|
||||
|
||||
4) Clone this repository:
|
||||
|
||||
```
|
||||
git clone https://github.com/Codium-ai/pr-agent.git
|
||||
```
|
||||
|
||||
5) Copy the secrets template file and fill in the following:
|
||||
|
||||
```
|
||||
cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
|
||||
# Edit .secrets.toml file
|
||||
```
|
||||
|
||||
- Your OpenAI key.
|
||||
- Copy your app's private key to the private_key field.
|
||||
- Copy your app's ID to the app_id field.
|
||||
- Copy your app's webhook secret to the webhook_secret field.
|
||||
- Set deployment_type to 'app' in [configuration.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml)
|
||||
|
||||
> The .secrets.toml file is not copied to the Docker image by default, and is only used for local development.
|
||||
> If you want to use the .secrets.toml file in your Docker image, you can add remove it from the .dockerignore file.
|
||||
> In most production environments, you would inject the secrets file as environment variables or as mounted volumes.
|
||||
> For example, in order to inject a secrets file as a volume in a Kubernetes environment you can update your pod spec to include the following,
|
||||
> assuming you have a secret named `pr-agent-settings` with a key named `.secrets.toml`:
|
||||
```
|
||||
volumes:
|
||||
- name: settings-volume
|
||||
secret:
|
||||
secretName: pr-agent-settings
|
||||
// ...
|
||||
containers:
|
||||
// ...
|
||||
volumeMounts:
|
||||
- mountPath: /app/pr_agent/settings_prod
|
||||
name: settings-volume
|
||||
```
|
||||
|
||||
> Another option is to set the secrets as environment variables in your deployment environment, for example `OPENAI.KEY` and `GITHUB.USER_TOKEN`.
|
||||
|
||||
6) Build a Docker image for the app and optionally push it to a Docker repository. We'll use Dockerhub as an example:
|
||||
|
||||
```
|
||||
docker build . -t codiumai/pr-agent:github_app --target github_app -f docker/Dockerfile
|
||||
docker push codiumai/pr-agent:github_app # Push to your Docker repository
|
||||
```
|
||||
|
||||
7. Host the app using a server, serverless function, or container environment. Alternatively, for development and
|
||||
debugging, you may use tools like smee.io to forward webhooks to your local machine.
|
||||
You can check [Deploy as a Lambda Function](#deploy-as-a-lambda-function)
|
||||
|
||||
8. Go back to your app's settings, and set the following:
|
||||
|
||||
- Webhook URL: The URL of your app's server or the URL of the smee.io channel.
|
||||
- Webhook secret: The secret you generated earlier.
|
||||
|
||||
9. Install the app by navigating to the "Install App" tab and selecting your desired repositories.
|
||||
|
||||
> **Note:** When running PR-Agent from GitHub App, the default configuration file (configuration.toml) will be loaded.
|
||||
> However, you can override the default tool parameters by uploading a local configuration file `.pr_agent.toml`
|
||||
> For more information please check out the [USAGE GUIDE](../usage-guide/automations_and_usage.md#github-app)
|
||||
---
|
||||
|
||||
## Deploy as a Lambda Function
|
||||
|
||||
Note that since AWS Lambda env vars cannot have "." in the name, you can replace each "." in an env variable with "__".<br>
|
||||
For example: `GITHUB.WEBHOOK_SECRET` --> `GITHUB__WEBHOOK_SECRET`
|
||||
|
||||
1. Follow steps 1-5 from [here](#run-as-a-github-app).
|
||||
2. Build a docker image that can be used as a lambda function
|
||||
```shell
|
||||
docker buildx build --platform=linux/amd64 . -t codiumai/pr-agent:serverless -f docker/Dockerfile.lambda
|
||||
```
|
||||
3. Push image to ECR
|
||||
```shell
|
||||
docker tag codiumai/pr-agent:serverless <AWS_ACCOUNT>.dkr.ecr.<AWS_REGION>.amazonaws.com/codiumai/pr-agent:serverless
|
||||
docker push <AWS_ACCOUNT>.dkr.ecr.<AWS_REGION>.amazonaws.com/codiumai/pr-agent:serverless
|
||||
```
|
||||
4. Create a lambda function that uses the uploaded image. Set the lambda timeout to be at least 3m.
|
||||
5. Configure the lambda function to have a Function URL.
|
||||
6. In the environment variables of the Lambda function, specify `AZURE_DEVOPS_CACHE_DIR` to a writable location such as /tmp. (see [link](https://github.com/Codium-ai/pr-agent/pull/450#issuecomment-1840242269))
|
||||
7. Go back to steps 8-9 of [Method 5](#run-as-a-github-app) with the function url as your Webhook URL.
|
||||
The Webhook URL would look like `https://<LAMBDA_FUNCTION_URL>/api/v1/github_webhooks`
|
||||
|
||||
---
|
||||
|
||||
## AWS CodeCommit Setup
|
||||
|
||||
Not all features have been added to CodeCommit yet. As of right now, CodeCommit has been implemented to run the pr-agent CLI on the command line, using AWS credentials stored in environment variables. (More features will be added in the future.) The following is a set of instructions to have pr-agent do a review of your CodeCommit pull request from the command line:
|
||||
|
||||
1. Create an IAM user that you will use to read CodeCommit pull requests and post comments
|
||||
* Note: That user should have CLI access only, not Console access
|
||||
2. Add IAM permissions to that user, to allow access to CodeCommit (see IAM Role example below)
|
||||
3. Generate an Access Key for your IAM user
|
||||
4. Set the Access Key and Secret using environment variables (see Access Key example below)
|
||||
5. Set the `git_provider` value to `codecommit` in the `pr_agent/settings/configuration.toml` settings file
|
||||
6. Set the `PYTHONPATH` to include your `pr-agent` project directory
|
||||
* Option A: Add `PYTHONPATH="/PATH/TO/PROJECTS/pr-agent` to your `.env` file
|
||||
* Option B: Set `PYTHONPATH` and run the CLI in one command, for example:
|
||||
* `PYTHONPATH="/PATH/TO/PROJECTS/pr-agent python pr_agent/cli.py [--ARGS]`
|
||||
|
||||
---
|
||||
|
||||
|
||||
#### AWS CodeCommit IAM Role Example
|
||||
|
||||
Example IAM permissions to that user to allow access to CodeCommit:
|
||||
|
||||
* Note: The following is a working example of IAM permissions that has read access to the repositories and write access to allow posting comments
|
||||
* Note: If you only want pr-agent to review your pull requests, you can tighten the IAM permissions further, however this IAM example will work, and allow the pr-agent to post comments to the PR
|
||||
* Note: You may want to replace the `"Resource": "*"` with your list of repos, to limit access to only those repos
|
||||
|
||||
```
|
||||
{
|
||||
"Version": "2012-10-17",
|
||||
"Statement": [
|
||||
{
|
||||
"Effect": "Allow",
|
||||
"Action": [
|
||||
"codecommit:BatchDescribe*",
|
||||
"codecommit:BatchGet*",
|
||||
"codecommit:Describe*",
|
||||
"codecommit:EvaluatePullRequestApprovalRules",
|
||||
"codecommit:Get*",
|
||||
"codecommit:List*",
|
||||
"codecommit:PostComment*",
|
||||
"codecommit:PutCommentReaction",
|
||||
"codecommit:UpdatePullRequestDescription",
|
||||
"codecommit:UpdatePullRequestTitle"
|
||||
],
|
||||
"Resource": "*"
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
#### AWS CodeCommit Access Key and Secret
|
||||
|
||||
Example setting the Access Key and Secret using environment variables
|
||||
|
||||
```sh
|
||||
export AWS_ACCESS_KEY_ID="XXXXXXXXXXXXXXXX"
|
||||
export AWS_SECRET_ACCESS_KEY="XXXXXXXXXXXXXXXX"
|
||||
export AWS_DEFAULT_REGION="us-east-1"
|
||||
```
|
||||
|
||||
#### AWS CodeCommit CLI Example
|
||||
|
||||
After you set up AWS CodeCommit using the instructions above, here is an example CLI run that tells pr-agent to **review** a given pull request.
|
||||
(Replace your specific PYTHONPATH and PR URL in the example)
|
||||
|
||||
```sh
|
||||
PYTHONPATH="/PATH/TO/PROJECTS/pr-agent" python pr_agent/cli.py \
|
||||
--pr_url https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/MY_REPO_NAME/pull-requests/321 \
|
||||
review
|
||||
```
|
||||
@ -1,20 +0,0 @@
|
||||
## Run a GitLab webhook server
|
||||
|
||||
1. From the GitLab workspace or group, create an access token. Enable the "api" scope only.
|
||||
|
||||
2. Generate a random secret for your app, and save it for later. For example, you can use:
|
||||
|
||||
```
|
||||
WEBHOOK_SECRET=$(python -c "import secrets; print(secrets.token_hex(10))")
|
||||
```
|
||||
3. Follow the instructions to build the Docker image, setup a secrets file and deploy on your own server from [here](https://pr-agent-docs.codium.ai/installation/github/#run-as-a-github-app) steps 4-7.
|
||||
|
||||
4. In the secrets file, fill in the following:
|
||||
- Your OpenAI key.
|
||||
- In the [gitlab] section, fill in personal_access_token and shared_secret. The access token can be a personal access token, or a group or project access token.
|
||||
- Set deployment_type to 'gitlab' in [configuration.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml)
|
||||
|
||||
5. Create a webhook in GitLab. Set the URL to the URL of your app's server. Set the secret token to the generated secret from step 2.
|
||||
In the "Trigger" section, check the ‘comments’ and ‘merge request events’ boxes.
|
||||
|
||||
6. Test your installation by opening a merge request or commenting or a merge request using one of CodiumAI's commands.
|
||||
@ -1,22 +0,0 @@
|
||||
# Installation
|
||||
|
||||
## Self-hosted PR-Agent
|
||||
If you choose to host you own PR-Agent, you first need to acquire two tokens:
|
||||
|
||||
1. An OpenAI key from [here](https://platform.openai.com/api-keys), with access to GPT-4 (or a key for [other models](../usage-guide/additional_configurations.md/#changing-a-model), if you prefer).
|
||||
2. A GitHub\GitLab\BitBucket personal access token (classic), with the repo scope. [GitHub from [here](https://github.com/settings/tokens)]
|
||||
|
||||
There are several ways to use self-hosted PR-Agent:
|
||||
|
||||
- [Locally](./locally.md)
|
||||
- [GitHub](./github.md)
|
||||
- [GitLab](./gitlab.md)
|
||||
- [BitBucket](./bitbucket.md)
|
||||
- [Azure DevOps](./azure.md)
|
||||
|
||||
## PR-Agent Pro 💎
|
||||
PR-Agent Pro, an app for GitHub\GitLab\BitBucket hosted by CodiumAI, is also available.
|
||||
<br>
|
||||
With PR-Agent Pro Installation is as simple as signing up and adding the PR-Agent app to your relevant repo.
|
||||
<br>
|
||||
See [here](./pr_agent_pro.md) for more details.
|
||||
@ -1,121 +0,0 @@
|
||||
## Using pip package
|
||||
|
||||
Install the package:
|
||||
|
||||
```
|
||||
pip install pr-agent
|
||||
```
|
||||
|
||||
Then run the relevant tool with the script below.
|
||||
<br>
|
||||
Make sure to fill in the required parameters (`user_token`, `openai_key`, `pr_url`, `command`):
|
||||
|
||||
```python
|
||||
from pr_agent import cli
|
||||
from pr_agent.config_loader import get_settings
|
||||
|
||||
def main():
|
||||
# Fill in the following values
|
||||
provider = "github" # GitHub provider
|
||||
user_token = "..." # GitHub user token
|
||||
openai_key = "..." # OpenAI key
|
||||
pr_url = "..." # PR URL, for example 'https://github.com/Codium-ai/pr-agent/pull/809'
|
||||
command = "/review" # Command to run (e.g. '/review', '/describe', '/ask="What is the purpose of this PR?"', ...)
|
||||
|
||||
# Setting the configurations
|
||||
get_settings().set("CONFIG.git_provider", provider)
|
||||
get_settings().set("openai.key", openai_key)
|
||||
get_settings().set("github.user_token", user_token)
|
||||
|
||||
# Run the command. Feedback will appear in GitHub PR comments
|
||||
cli.run_command(pr_url, command)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
```
|
||||
|
||||
## Using Docker image
|
||||
|
||||
A list of the relevant tools can be found in the [tools guide](../tools/ask.md).
|
||||
|
||||
To invoke a tool (for example `review`), you can run directly from the Docker image. Here's how:
|
||||
|
||||
- For GitHub:
|
||||
```
|
||||
docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent:latest --pr_url <pr_url> review
|
||||
```
|
||||
|
||||
- For GitLab:
|
||||
```
|
||||
docker run --rm -it -e OPENAI.KEY=<your key> -e CONFIG.GIT_PROVIDER=gitlab -e GITLAB.PERSONAL_ACCESS_TOKEN=<your token> codiumai/pr-agent:latest --pr_url <pr_url> review
|
||||
```
|
||||
|
||||
Note: If you have a dedicated GitLab instance, you need to specify the custom url as variable:
|
||||
```
|
||||
docker run --rm -it -e OPENAI.KEY=<your key> -e CONFIG.GIT_PROVIDER=gitlab -e GITLAB.PERSONAL_ACCESS_TOKEN=<your token> -e GITLAB.URL=<your gitlab instance url> codiumai/pr-agent:latest --pr_url <pr_url> review
|
||||
```
|
||||
|
||||
- For BitBucket:
|
||||
```
|
||||
docker run --rm -it -e CONFIG.GIT_PROVIDER=bitbucket -e OPENAI.KEY=$OPENAI_API_KEY -e BITBUCKET.BEARER_TOKEN=$BITBUCKET_BEARER_TOKEN codiumai/pr-agent:latest --pr_url=<pr_url> review
|
||||
```
|
||||
|
||||
For other git providers, update CONFIG.GIT_PROVIDER accordingly, and check the `pr_agent/settings/.secrets_template.toml` file for the environment variables expected names and values.
|
||||
|
||||
---
|
||||
|
||||
|
||||
If you want to ensure you're running a specific version of the Docker image, consider using the image's digest:
|
||||
```bash
|
||||
docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent@sha256:71b5ee15df59c745d352d84752d01561ba64b6d51327f97d46152f0c58a5f678 --pr_url <pr_url> review
|
||||
```
|
||||
|
||||
Or you can run a [specific released versions](https://github.com/Codium-ai/pr-agent/blob/main/RELEASE_NOTES.md) of pr-agent, for example:
|
||||
```
|
||||
codiumai/pr-agent@v0.9
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Run from source
|
||||
|
||||
1. Clone this repository:
|
||||
|
||||
```
|
||||
git clone https://github.com/Codium-ai/pr-agent.git
|
||||
```
|
||||
|
||||
2. Navigate to the `/pr-agent` folder and install the requirements in your favorite virtual environment:
|
||||
|
||||
```
|
||||
pip install -e .
|
||||
```
|
||||
|
||||
*Note: If you get an error related to Rust in the dependency installation then make sure Rust is installed and in your `PATH`, instructions: https://rustup.rs*
|
||||
|
||||
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. Run the cli.py script:
|
||||
|
||||
```
|
||||
python3 -m pr_agent.cli --pr_url <pr_url> review
|
||||
python3 -m pr_agent.cli --pr_url <pr_url> ask <your question>
|
||||
python3 -m pr_agent.cli --pr_url <pr_url> describe
|
||||
python3 -m pr_agent.cli --pr_url <pr_url> improve
|
||||
python3 -m pr_agent.cli --pr_url <pr_url> add_docs
|
||||
python3 -m pr_agent.cli --pr_url <pr_url> generate_labels
|
||||
python3 -m pr_agent.cli --issue_url <issue_url> similar_issue
|
||||
...
|
||||
```
|
||||
|
||||
[Optional] Add the pr_agent folder to your PYTHONPATH
|
||||
```
|
||||
export PYTHONPATH=$PYTHONPATH:<PATH to pr_agent folder>
|
||||
```
|
||||
@ -1,64 +0,0 @@
|
||||
|
||||
## Getting Started with PR-Agent Pro
|
||||
|
||||
PR-Agent Pro is a versatile application compatible with GitHub, GitLab, and BitBucket, hosted by CodiumAI.
|
||||
See [here](https://pr-agent-docs.codium.ai/#pr-agent-pro) for more details about the benefits of using PR-Agent Pro.
|
||||
|
||||
Interested parties can subscribe to PR-Agent Pro through the following [link](https://www.codium.ai/pricing/).
|
||||
After subscribing, you are granted the ability to easily install the application across any of your repositories.
|
||||
|
||||
{width=468}
|
||||
|
||||
Each user who wants to use PR-Agent pro needs to buy a seat.
|
||||
Initially, CodiumAI offers a two-week trial period at no cost, after which continued access requires each user to secure a personal seat.
|
||||
Once a user acquires a seat, they gain the flexibility to use PR-Agent Pro across any repository where it was enabled.
|
||||
|
||||
Users without a purchased seat who interact with a repository featuring PR-Agent Pro are entitled to receive up to five complimentary feedbacks.
|
||||
Beyond this limit, PR-Agent Pro will cease to respond to their inquiries unless a seat is purchased.
|
||||
|
||||
|
||||
## Install PR-Agent Pro for GitLab (Teams & Enterprise)
|
||||
|
||||
Since GitLab platform does not support apps, installing PR-Agent Pro for GitLab is a bit more involved, and requires the following steps:
|
||||
|
||||
### Step 1
|
||||
|
||||
Acquire a personal, project or group level access token. Enable the “api” scope in order to allow PR-Agent to read pull requests, comment and respond to requests.
|
||||
|
||||
<figure markdown="1">
|
||||
{width=750}
|
||||
</figure>
|
||||
|
||||
Store the token in a safe place, you won’t be able to access it again after it was generated.
|
||||
|
||||
### Step 2
|
||||
|
||||
Generate a shared secret and link it to the access token. Browse to [https://register.gitlab.pr-agent.codium.ai](https://register.gitlab.pr-agent.codium.ai).
|
||||
Fill in your generated GitLab token and your company or personal name in the appropriate fields and click "Submit".
|
||||
|
||||
You should see "Success!" displayed above the Submit button, and a shared secret will be generated. Store it in a safe place, you won’t be able to access it again after it was generated.
|
||||
|
||||
### Step 3
|
||||
|
||||
Install a webhook for your repository or groups, by clicking “webhooks” on the settings menu. Click the “Add new webhook” button.
|
||||
|
||||
<figure markdown="1">
|
||||
|
||||
</figure>
|
||||
|
||||
In the webhook definition form, fill in the following fields:
|
||||
URL: https://pro.gitlab.pr-agent.codium.ai/webhook
|
||||
|
||||
Secret token: Your CodiumAI key
|
||||
Trigger: Check the ‘comments’ and ‘merge request events’ boxes.
|
||||
Enable SSL verification: Check the box.
|
||||
|
||||
<figure markdown="1">
|
||||
{width=750}
|
||||
</figure>
|
||||
|
||||
### Step 4
|
||||
|
||||
You’re all set!
|
||||
|
||||
Open a new merge request or add a MR comment with one of PR-Agent’s commands such as /review, /describe or /improve.
|
||||
@ -1,19 +0,0 @@
|
||||
## Overview
|
||||
The `analyze` tool combines advanced static code analysis with LLM capabilities to provide a comprehensive analysis of the PR code changes.
|
||||
|
||||
The tool scans the PR code changes, find the code components (methods, functions, classes) that changed, and enables to interactively generate tests, docs, code suggestions and similar code search for each component.
|
||||
|
||||
It can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/analyze
|
||||
```
|
||||
|
||||
## Example usage
|
||||
|
||||
An example result:
|
||||
|
||||
{width=750}
|
||||
|
||||
**Notes**
|
||||
|
||||
- Language that are currently supported: Python, Java, C++, JavaScript, TypeScript, C#.
|
||||
@ -1,59 +0,0 @@
|
||||
## Overview
|
||||
|
||||
The `ask` tool answers questions about the PR, based on the PR code changes. Make sure to be specific and clear in your questions.
|
||||
It can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/ask "..."
|
||||
```
|
||||
|
||||
## Example usage
|
||||
|
||||
{width=512}
|
||||
|
||||
{width=512}
|
||||
|
||||
## Ask lines
|
||||
|
||||
You can run `/ask` on specific lines of code in the PR from the PR's diff view. The tool will answer questions based on the code changes in the selected lines.
|
||||
- Click on the '+' sign next to the line number to select the line.
|
||||
- To select multiple lines, click on the '+' sign of the first line and then hold and drag to select the rest of the lines.
|
||||
- write `/ask "..."` in the comment box and press `Add single comment` button.
|
||||
|
||||
{width=512}
|
||||
|
||||
Note that the tool does not have "memory" of previous questions, and answers each question independently.
|
||||
|
||||
## Ask on images
|
||||
|
||||
You can also ask questions about images that appear in the comment, where the entire PR code will be used as context.
|
||||
<br>
|
||||
The basic syntax is:
|
||||
```
|
||||
/ask "..."
|
||||
|
||||
[Image](https://real_link_to_image)
|
||||
```
|
||||
where `https://real_link_to_image` is the direct link to the image.
|
||||
|
||||
Note that GitHub has a built-in mechanism of pasting images in comments. However, pasted image does not provide a direct link.
|
||||
To get a direct link to an image, we recommend using the following scheme:
|
||||
|
||||
1) First, post a comment that contains **only** the image:
|
||||
|
||||
{width=512}
|
||||
|
||||
2) Quote reply to that comment:
|
||||
|
||||
{width=512}
|
||||
|
||||
3) In the screen opened, type the question below the image:
|
||||
|
||||
{width=512}
|
||||
{width=512}
|
||||
|
||||
4) Post the comment, and receive the answer:
|
||||
|
||||
{width=512}
|
||||
|
||||
|
||||
See a full video tutorial [here](https://codium.ai/images/pr_agent/ask_image_video.mov)
|
||||
@ -1,39 +0,0 @@
|
||||
## Overview
|
||||
|
||||
The CI feedback tool (`/checks)` automatically triggers when a PR has a failed check.
|
||||
The tool analyzes the failed checks and provides several feedbacks:
|
||||
|
||||
- Failed stage
|
||||
- Failed test name
|
||||
- Failure summary
|
||||
- Relevant error logs
|
||||
|
||||
## Example usage
|
||||
|
||||
{width=768}
|
||||
|
||||
→
|
||||
{width=768}
|
||||
|
||||
___
|
||||
|
||||
In addition to being automatically triggered, the tool can also be invoked manually by commenting on a PR:
|
||||
```
|
||||
/checks "https://github.com/{repo_name}/actions/runs/{run_number}/job/{job_number}"
|
||||
```
|
||||
where `{repo_name}` is the name of the repository, `{run_number}` is the run number of the failed check, and `{job_number}` is the job number of the failed check.
|
||||
|
||||
## Disabling the tool from running automatically
|
||||
|
||||
If you wish to disable the tool from running automatically, you can do so by adding the following configuration to the configuration file:
|
||||
```
|
||||
[checks]
|
||||
enable_auto_checks_feedback = false
|
||||
```
|
||||
|
||||
## Configuration options
|
||||
- `enable_auto_checks_feedback` - if set to true, the tool will automatically provide feedback when a check is failed. Default is true.
|
||||
- `excluded_checks_list` - a list of checks to exclude from the feedback, for example: ["check1", "check2"]. Default is an empty list.
|
||||
- `persistent_comment` - if set to true, the tool will overwrite a previous checks comment with the new feedback. Default is true.
|
||||
- `enable_help_text=true` - if set to true, the tool will provide a help message when a user comments "/checks" on a PR. Default is true.
|
||||
- `final_update_message` - if `persistent_comment` is true and updating a previous checks message, the tool will also create a new message: "Persistent checks updated to latest commit". Default is true.
|
||||
@ -1,60 +0,0 @@
|
||||
## Overview
|
||||
The `generate_labels` tool scans the PR code changes, and given a list of labels and their descriptions, it automatically suggests labels that match the PR code changes.
|
||||
|
||||
It can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/generate_labels
|
||||
```
|
||||
|
||||
## Example usage
|
||||
|
||||
If we wish to add detect changes to SQL queries in a given PR, we can add the following custom label along with its description:
|
||||
|
||||
{width=768}
|
||||
|
||||
When running the `generate_labels` tool on a PR that includes changes in SQL queries, it will automatically suggest the custom label:
|
||||
|
||||
{width=768}
|
||||
|
||||
Note that in addition to the dedicated tool `generate_labels`, the custom labels will also be used by the `describe` tool.
|
||||
|
||||
### How to enable custom labels
|
||||
There are 3 ways to enable custom labels:
|
||||
|
||||
#### 1. CLI (local configuration file)
|
||||
When working from CLI, you need to apply the [configuration changes](#configuration-options) to the [custom_labels file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/custom_labels.toml):
|
||||
|
||||
#### 2. Repo configuration file
|
||||
To enable custom labels, you need to apply the [configuration changes](#configuration-options) to the local `.pr_agent.toml` file in you repository.
|
||||
|
||||
#### 3. Handle custom labels from the Repo's labels page 💎
|
||||
> This feature is available only in PR-Agent Pro
|
||||
|
||||
* GitHub : `https://github.com/{owner}/{repo}/labels`, or click on the "Labels" tab in the issues or PRs page.
|
||||
* GitLab : `https://gitlab.com/{owner}/{repo}/-/labels`, or click on "Manage" -> "Labels" on the left menu.
|
||||
|
||||
b. Add/edit the custom labels. It should be formatted as follows:
|
||||
* Label name: The name of the custom label.
|
||||
* Description: Start the description of with prefix `pr_agent:`, for example: `pr_agent: Description of when AI should suggest this label`.<br>
|
||||
The description should be comprehensive and detailed, indicating when to add the desired label.
|
||||
|
||||
{width=880}
|
||||
|
||||
c. Now the custom labels will be included in the `generate_labels` tool.
|
||||
|
||||
> This feature is supported in GitHub and GitLab.
|
||||
|
||||
## Configuration options
|
||||
- Change `enable_custom_labels` to True: This will turn off the default labels and enable the custom labels provided in the custom_labels.toml file.
|
||||
- Add the custom labels. It should be formatted as follows:
|
||||
|
||||
```
|
||||
[config]
|
||||
enable_custom_labels=true
|
||||
|
||||
[custom_labels."Custom Label Name"]
|
||||
description = "Description of when AI should suggest this label"
|
||||
|
||||
[custom_labels."Custom Label 2"]
|
||||
description = "Description of when AI should suggest this label 2"
|
||||
```
|
||||
@ -1,61 +0,0 @@
|
||||
## Overview
|
||||
The `custom_suggestions` tool scans the PR code changes, and automatically generates suggestions for improving the PR code.
|
||||
It shares similarities with the `improve` tool, but with one main difference: the `custom_suggestions` tool will **only propose suggestions that follow specific guidelines defined by the prompt** in: `pr_custom_suggestions.prompt` configuration.
|
||||
|
||||
The tool can be triggered [automatically](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-a-new-pr-is-opened) every time a new PR is opened, or can be invoked manually by commenting on a PR.
|
||||
|
||||
When commenting, use the following template:
|
||||
|
||||
```
|
||||
/custom_suggestions --pr_custom_suggestions.prompt="
|
||||
The suggestions should focus only on the following:
|
||||
- ...
|
||||
- ...
|
||||
|
||||
"
|
||||
```
|
||||
|
||||
With a [configuration file](../usage-guide/automations_and_usage.md#github-app), use the following template:
|
||||
|
||||
```
|
||||
[pr_custom_suggestions]
|
||||
prompt="""\
|
||||
The suggestions should focus only on the following:
|
||||
-...
|
||||
-...
|
||||
|
||||
"""
|
||||
```
|
||||
|
||||
Remember - with this tool, you are the prompter. Be specific, clear, and concise in the instructions. Specify relevant aspects that you want the model to focus on. \
|
||||
You might benefit from several trial-and-error iterations, until you get the correct prompt for your use case.
|
||||
|
||||
## Example usage
|
||||
|
||||
Here is an example of a possible prompt, defined in the configuration file:
|
||||
```
|
||||
[pr_custom_suggestions]
|
||||
prompt="""\
|
||||
The suggestions should focus only on the following:
|
||||
- look for edge cases when implementing a new function
|
||||
- make sure every variable has a meaningful name
|
||||
- make sure the code is efficient
|
||||
"""
|
||||
```
|
||||
|
||||
(The instructions above are just an example. We want to emphasize that the prompt should be specific and clear, and be tailored to the needs of your project)
|
||||
|
||||
Results obtained with the prompt above:
|
||||
|
||||
[//]: # ({width=512})
|
||||
|
||||
[//]: # (→)
|
||||
{width=768}
|
||||
|
||||
## Configuration options
|
||||
|
||||
`prompt`: the prompt for the tool. It should be a multi-line string.
|
||||
|
||||
`num_code_suggestions`: number of code suggestions provided by the 'custom_suggestions' tool. Default is 4.
|
||||
|
||||
`enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
|
||||
@ -1,185 +0,0 @@
|
||||
## 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](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-a-new-pr-is-opened), or it can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/describe
|
||||
```
|
||||
|
||||
## Example usage
|
||||
|
||||
### Manual triggering
|
||||
|
||||
Invoke the tool manually by commenting `/describe` on any PR:
|
||||
|
||||
{width=512}
|
||||
|
||||
After ~30 seconds, the tool will generate a description for the PR:
|
||||
|
||||
{width=512}
|
||||
|
||||
If you want to edit [configurations](#configuration-options), add the relevant ones to the command:
|
||||
```
|
||||
/describe --pr_description.some_config1=... --pr_description.some_config2=...
|
||||
```
|
||||
|
||||
### Automatic triggering
|
||||
|
||||
To run the `describe` automatically when a PR is opened, define in a [configuration file](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/#wiki-configuration-file):
|
||||
```
|
||||
[github_app]
|
||||
pr_commands = [
|
||||
"/describe",
|
||||
...
|
||||
]
|
||||
|
||||
[pr_description]
|
||||
publish_labels = ...
|
||||
...
|
||||
```
|
||||
|
||||
- The `pr_commands` lists commands that will be executed automatically when a PR is opened.
|
||||
- The `[pr_description]` section contains the configurations for the `describe` tool you want to edit (if any).
|
||||
|
||||
|
||||
## Configuration options
|
||||
|
||||
### General configurations
|
||||
|
||||
!!! example "Possible configurations"
|
||||
|
||||
- `publish_labels`: if set to true, the tool will publish the labels to the PR. Default is true.
|
||||
|
||||
- `publish_description_as_comment`: if set to true, the tool will publish the description as a comment to the PR. If false, it will overwrite the original description. Default is false.
|
||||
|
||||
- `publish_description_as_comment_persistent`: if set to true and `publish_description_as_comment` is true, the tool will publish the description as a persistent comment to the PR. Default is true.
|
||||
|
||||
- `add_original_user_description`: if set to true, the tool will add the original user description to the generated description. Default is true.
|
||||
|
||||
- `generate_ai_title`: if set to true, the tool will also generate an AI title for the PR. Default is false.
|
||||
|
||||
- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
|
||||
|
||||
- To enable `custom labels`, apply the configuration changes described [here](./custom_labels.md#configuration-options)
|
||||
|
||||
- `enable_pr_type`: if set to false, it will not show the `PR type` as a text value in the description content. Default is true.
|
||||
|
||||
- `final_update_message`: if set to true, it will add a comment message [`PR Description updated to latest commit...`](https://github.com/Codium-ai/pr-agent/pull/499#issuecomment-1837412176) after finishing calling `/describe`. Default is true.
|
||||
|
||||
- `enable_semantic_files_types`: if set to true, "Changes walkthrough" section will be generated. Default is true.
|
||||
- `collapsible_file_list`: if set to true, the file list in the "Changes walkthrough" section will be collapsible. If set to "adaptive", the file list will be collapsible only if there are more than 8 files. Default is "adaptive".
|
||||
- `enable_help_text`: if set to true, the tool will display a help text in the comment. Default is false.
|
||||
|
||||
### Inline file summary 💎
|
||||
|
||||
This feature enables you to copy the `changes walkthrough` table to the "Files changed" tab, so you can quickly understand the changes in each file while reviewing the code changes (diff view).
|
||||
|
||||
To copy the `changes walkthrough` table to the "Files changed" tab, you can click on the checkbox that appears PR Description status message below the main PR Description:
|
||||
|
||||
{width=512}
|
||||
|
||||
If you prefer to have the file summaries appear in the "Files changed" tab on every PR, change the `pr_description.inline_file_summary` parameter 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.
|
||||
|
||||
{width=512}
|
||||
|
||||
- `true`: A collapsable file comment with changes title and a changes summary for each file in the PR.
|
||||
|
||||
{width=512}
|
||||
|
||||
- `false` (`default`): File changes walkthrough will be added only to the "Conversation" tab.
|
||||
|
||||
**Note**: that this feature is currently available only for GitHub.
|
||||
|
||||
|
||||
### Markers template
|
||||
|
||||
To enable markers, set `pr_description.use_description_markers=true`.
|
||||
Markers enable to easily integrate user's content and auto-generated content, with a template-like mechanism.
|
||||
|
||||
For example, if the PR original description was:
|
||||
```
|
||||
User content...
|
||||
|
||||
## PR Type:
|
||||
pr_agent:type
|
||||
|
||||
## PR Description:
|
||||
pr_agent:summary
|
||||
|
||||
## PR Walkthrough:
|
||||
pr_agent:walkthrough
|
||||
```
|
||||
The marker `pr_agent:type` will be replaced with the PR type, `pr_agent:summary` will be replaced with the PR summary, and `pr_agent:walkthrough` will be replaced with the PR walkthrough.
|
||||
|
||||
{width=512}
|
||||
|
||||
→
|
||||
|
||||
{width=512}
|
||||
|
||||
|
||||
**Configuration params**:
|
||||
|
||||
- `use_description_markers`: if set to true, the tool will use markers template. It replaces every marker of the form `pr_agent:marker_name` with the relevant content. Default is false.
|
||||
- `include_generated_by_header`: if set to true, the tool will add a dedicated header: 'Generated by PR Agent at ...' to any automatic content. Default is true.
|
||||
|
||||
## Custom labels
|
||||
|
||||
The default labels of the describe tool are quite generic, since they are meant to be used in any repo: [`Bug fix`, `Tests`, `Enhancement`, `Documentation`, `Other`].
|
||||
|
||||
You can define custom labels that are relevant for your repo and use cases.
|
||||
Custom labels can be defined in a [configuration file](https://pr-agent-docs.codium.ai/tools/custom_labels/#configuration-options), or directly in the repo's [labels page](#handle-custom-labels-from-the-repos-labels-page).
|
||||
|
||||
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.
|
||||
<br>
|
||||
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.
|
||||
Each label description should be a **conditional statement**, that indicates if to add the label to the PR or not, according to the PR content.
|
||||
|
||||
|
||||
### Handle custom labels from the Repo's labels page 💎
|
||||
|
||||
You can control the custom labels that will be suggested by the `describe` tool, from the repo's labels page:
|
||||
|
||||
* GitHub : go to `https://github.com/{owner}/{repo}/labels` (or click on the "Labels" tab in the issues or PRs page)
|
||||
* GitLab : go to `https://gitlab.com/{owner}/{repo}/-/labels` (or click on "Manage" -> "Labels" on the left menu)
|
||||
|
||||
Now add/edit the custom labels. they should be formatted as follows:
|
||||
|
||||
* Label name: The name of the custom label.
|
||||
* Description: Start the description of with prefix `pr_agent:`, for example: `pr_agent: Description of when AI should suggest this label`.<br>
|
||||
|
||||
The description should be comprehensive and detailed, indicating when to add the desired label. For example:
|
||||
{width=768}
|
||||
|
||||
|
||||
## Usage Tips
|
||||
|
||||
!!! tip "Automation"
|
||||
- When you first install PR-Agent app, the [default mode](../usage-guide/automations_and_usage.md#github-app) for the describe tool is:
|
||||
```
|
||||
pr_commands = ["/describe", ...]
|
||||
```
|
||||
meaning the `describe` tool will run automatically on every PR, with the default configurations.
|
||||
|
||||
|
||||
- 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.
|
||||
@ -1,33 +0,0 @@
|
||||
## Overview
|
||||
The `add_docs` tool scans the PR code changes, and automatically suggests documentation for any code components that changed in the PR (functions, classes, etc.).
|
||||
|
||||
It can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/add_docs
|
||||
```
|
||||
|
||||
## Example usage
|
||||
|
||||
Invoke the tool manually by commenting `/add_docs` on any PR:
|
||||
|
||||
{width=768}
|
||||
|
||||
The tool will generate documentation for all the components that changed in the PR:
|
||||
|
||||
{width=768}
|
||||
|
||||
{width=768}
|
||||
|
||||
You can state a name of a specific component in the PR to get documentation only for that component:
|
||||
```
|
||||
/add_docs component_name
|
||||
```
|
||||
|
||||
## Configuration options
|
||||
- `docs_style`: The exact style of the documentation (for python docstring). you can choose between: `google`, `numpy`, `sphinx`, `restructuredtext`, `plain`. Default is `sphinx`.
|
||||
- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
|
||||
|
||||
**Notes**
|
||||
|
||||
- Language that are currently fully supported: Python, Java, C++, JavaScript, TypeScript, C#.
|
||||
- This tool can also be triggered interactively by using the [`analyze`](./analyze.md) tool.
|
||||
@ -1,17 +0,0 @@
|
||||
## Overview
|
||||
The `help` tool provides a list of all the available tools and their descriptions.
|
||||
For PR-Agent Pro users, it also enables to trigger each tool by checking the relevant box.
|
||||
|
||||
It can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/help
|
||||
```
|
||||
|
||||
## Example usage
|
||||
An example [result](https://github.com/Codium-ai/pr-agent/pull/546#issuecomment-1868524805):
|
||||
|
||||
{width=750}
|
||||
|
||||
→
|
||||
|
||||
{width=750}
|
||||
@ -1,129 +0,0 @@
|
||||
## 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](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-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](#configuration-options) 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](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/#wiki-configuration-file):
|
||||
```
|
||||
[github_app]
|
||||
pr_commands = [
|
||||
"/improve",
|
||||
...
|
||||
]
|
||||
|
||||
[pr_code_suggestions]
|
||||
num_code_suggestions = ...
|
||||
...
|
||||
```
|
||||
|
||||
- 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)
|
||||
|
||||
|
||||
|
||||
## 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.
|
||||
- `enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
|
||||
|
||||
!!! example "params for '/improve --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.;
|
||||
|
||||
## Extended mode
|
||||
|
||||
An extended mode, which does not involve PR Compression and provides more comprehensive suggestions, can be invoked by commenting on any PR:
|
||||
```
|
||||
/improve --extended
|
||||
```
|
||||
|
||||
or by setting:
|
||||
```
|
||||
[pr_code_suggestions]
|
||||
auto_extended_mode=true
|
||||
```
|
||||
(True by default).
|
||||
|
||||
Note that the extended mode divides the PR code changes into chunks, up to the token limits, where each chunk is handled separately (might use multiple calls to GPT-4 for large PRs).
|
||||
Hence, the total number of suggestions is proportional to the number of chunks, i.e., the size of the PR.
|
||||
|
||||
|
||||
|
||||
## Usage Tips
|
||||
|
||||
!!! tip "Extra instructions"
|
||||
|
||||
Extra instructions are very important for the `imrpove` tool, since they enable you 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.
|
||||
|
||||
!!! tip "Review vs. Improve tools comparison"
|
||||
|
||||
- The [`review`](https://pr-agent-docs.codium.ai/tools/review/) tool includes a section called 'Possible issues', that also provide feedback on the PR Code.
|
||||
In this section, the model is instructed to focus **only** on [major bugs and issues](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/pr_reviewer_prompts.toml#L71).
|
||||
- The `improve` tool, on the other hand, has a broader mandate, and in addition to bugs and issues, it can also give suggestions for improving code quality and making the code more efficient, readable, and maintainable (see [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/pr_code_suggestions_prompts.toml#L34)).
|
||||
- Hence, if you are interested only in feedback about clear bugs, the `review` tool might suffice. If you want a more detailed feedback, including broader suggestions for improving the PR code, also enable the `improve` tool to run on each PR.
|
||||
|
||||
## 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`](https://pr-agent-docs.codium.ai/tools/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 `exra_instructions` field to guide the model to suggestions that are more relevant to the specific needs of the project.
|
||||
<br>
|
||||
Consider also trying the [Custom Suggestions Tool](./custom_suggestions.md) 💎, that will **only** propose suggestions that follow specific guidelines defined by user.
|
||||
@ -1,29 +0,0 @@
|
||||
## Overview
|
||||
The `improve_component` tool generates code suggestions for a specific code component that changed in the PR.
|
||||
it can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/improve_component component_name
|
||||
```
|
||||
|
||||
To get a list of the components that changed in the PR and choose the relevant component interactively, use the [`analyze`](./analyze.md) tool.
|
||||
|
||||
|
||||
## Example usage
|
||||
|
||||
Invoke the tool manually by commenting `/improve_component` on any PR:
|
||||
|
||||
{width=768}
|
||||
|
||||
The tool will generate code suggestions for the selected component (if no component is stated, it will generate code suggestions for the largest component):
|
||||
|
||||
{width=768}
|
||||
|
||||
**Notes**
|
||||
- Language that are currently supported by the tool: Python, Java, C++, JavaScript, TypeScript, C#.
|
||||
- This tool can also be triggered interactively by using the [`analyze`](./analyze.md) tool.
|
||||
|
||||
## Configuration options
|
||||
- `num_code_suggestions`: number of code suggestions to provide. Default is 4
|
||||
- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on ...".
|
||||
- `file`: in case there are several components with the same name, you can specify the relevant file.
|
||||
- `class_name`: in case there are several methods with the same name in the same file, you can specify the relevant class name.
|
||||
@ -1,22 +0,0 @@
|
||||
# Tools
|
||||
|
||||
Here is a list of PR-Agent tools, each with a dedicated page that explains how to use it:
|
||||
|
||||
| Tool | Description |
|
||||
|------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------|
|
||||
| **[PR Description (`/describe`](./describe.md))** | Automatically generating PR description - title, type, summary, code walkthrough and labels |
|
||||
| **[PR Review (`/review`](./review.md))** | Adjustable feedback about the PR, possible issues, security concerns, review effort and more |
|
||||
| **[Code Suggestions (`/improve`](./improve.md))** | Code suggestions for improving the PR |
|
||||
| **[Question Answering (`/ask ...`](./ask.md))** | Answering free-text questions about the PR, or on specific code lines |
|
||||
| **[Update Changelog (`/update_changelog`](./update_changelog.md))** | Automatically updating the CHANGELOG.md file with the PR changes |
|
||||
| **[Find Similar Issue (`/similar_issue`](./similar_issues.md))** | Automatically retrieves and presents similar issues |
|
||||
| **[Help (`/help`](./help.md))** | Provides a list of all the available tools. Also enables to trigger them interactively (💎) |
|
||||
| **💎 [Add Documentation (`/add_docs`](./documentation.md))** | Generates documentation to methods/functions/classes that changed in the PR |
|
||||
| **💎 [Generate Custom Labels (`/generate_labels`](./custom_labels.md))** | Generates custom labels for the PR, based on specific guidelines defined by the user |
|
||||
| **💎 [Analyze (`/analyze`](./analyze.md))** | Identify code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component |
|
||||
| **💎 [Custom Suggestions (`/custom_suggestions`](./custom_suggestions.md))** | Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user |
|
||||
| **💎 [Generate Tests (`/test component_name`](./test.md))** | Automatically generates unit tests for a selected component, based on the PR code changes |
|
||||
| **💎 [Improve Component (`/improve_component component_name`](./improve_component.md))** | Generates code suggestions for a specific code component that changed in the PR |
|
||||
| **💎 [CI Feedback (`/checks ci_job`](./ci_feedback.md))** | Automatically generates feedback and analysis for a failed CI job |
|
||||
|
||||
Note that the tools marked with 💎 are available only for PR-Agent Pro users.
|
||||
@ -1,187 +0,0 @@
|
||||
## Overview
|
||||
The `review` tool scans the PR code changes, and automatically generates a PR review.
|
||||
The tool can be triggered automatically every time a new PR is [opened](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-a-new-pr-is-opened), or can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/review
|
||||
```
|
||||
|
||||
## Example usage
|
||||
|
||||
### Manual triggering
|
||||
|
||||
Invoke the tool manually by commenting `/review` on any PR:
|
||||
|
||||
{width=512}
|
||||
|
||||
After ~30 seconds, the tool will generate a review for the PR:
|
||||
|
||||
{width=512}
|
||||
|
||||
If you want to edit [configurations](#configuration-options), add the relevant ones to the command:
|
||||
```
|
||||
/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...
|
||||
```
|
||||
|
||||
### Automatic triggering
|
||||
|
||||
To run the `review` automatically when a PR is opened, define in a [configuration file](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/#wiki-configuration-file):
|
||||
```
|
||||
[github_app]
|
||||
pr_commands = [
|
||||
"/review",
|
||||
...
|
||||
]
|
||||
|
||||
[pr_reviewer]
|
||||
num_code_suggestions = ...
|
||||
...
|
||||
```
|
||||
|
||||
- The `pr_commands` lists commands that will be executed automatically when a PR is opened.
|
||||
- The `[pr_reviewer]` section contains the configurations for the `review` tool you want to edit (if any).
|
||||
|
||||
|
||||
## Configuration options
|
||||
|
||||
### General configurations
|
||||
|
||||
!!! example "General options"
|
||||
- <a name="num_code_suggestions"></a>`num_code_suggestions`: number of code suggestions provided by the 'review' tool. For manual comments, default is 4. For [PR-Agent app](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L142) auto tools, default is 0, meaning no code suggestions will be provided by the review tool, unless you manually edit `pr_commands`.
|
||||
- <a name="inline_code_comments"></a>`inline_code_comments`: if set to true, the tool will publish the code suggestions as comments on the code diff. Default is false.
|
||||
- <a name="persistent_comment"></a>`persistent_comment`: if set to true, the review comment will be persistent, meaning that every new review request will edit the previous one. Default is true.
|
||||
- <a name="extra_instructions"></a>`extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
|
||||
- <a name="enable_help_text"></a>`enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
|
||||
|
||||
!!! example "Enable\\disable sub-sections"
|
||||
You can enable or disable specific sub-sections of the review tool:
|
||||
|
||||
- <a name="require_score_review"></a>`require_score_review`: if set to true, the tool will add a section that scores the PR. Default is false.
|
||||
- <a name="require_tests_review"></a>`require_tests_review`: if set to true, the tool will add a section that checks if the PR contains tests. Default is true.
|
||||
- <a name="require_estimate_effort_to_review"></a>`require_estimate_effort_to_review`: if set to true, the tool will add a section that estimates the effort needed to review the PR. Default is true.
|
||||
- <a name="require_can_be_split_review"></a>`require_can_be_split_review`: if set to true, the tool will add a section that checks if the PR contains several themes, and can be split into smaller PRs. Default is false.
|
||||
|
||||
!!! example "SOC2 ticket compliance 💎"
|
||||
|
||||
This sub-tool checks if the PR description properly contains a ticket to a project management system (e.g., Jira, Asana, Trello, etc.), as required by SOC2 compliance. If not, it will add a label to the PR: "Missing SOC2 ticket".
|
||||
|
||||
- <a name="require_soc2_ticket"></a>`require_soc2_ticket`: If set to true, the SOC2 ticket checker sub-tool will be enabled. Default is false.
|
||||
- <a name="soc2_ticket_prompt"></a>`soc2_ticket_prompt`: The prompt for the SOC2 ticket review. Default is: `Does the PR description include a link to ticket in a project management system (e.g., Jira, Asana, Trello, etc.) ?`. Edit this field if your compliance requirements are different.
|
||||
|
||||
!!! example "Adding PR labels"
|
||||
You can enable the tool to add specific labels to the PR:
|
||||
|
||||
- <a name="enable_review_labels_security"></a>`enable_review_labels_security`: if set to true, the tool will publish a 'possible security issue' label if it detects a security issue. Default is true.
|
||||
- <a name="enable_review_labels_effort"></a>`enable_review_labels_effort`: if set to true, the tool will publish a 'Review effort [1-5]: x' label. Default is true.
|
||||
|
||||
!!! example "Auto-approval"
|
||||
The review tool can approve a PR when a specific comment, `/review auto_approve` is invoked.
|
||||
|
||||
- <a name="enable_auto_approval"></a>`enable_auto_approval`: if set to true, the tool will approve the PR when invoked with the 'auto_approve' command. Default is false. This flag can be changed only from configuration file.
|
||||
- <a name="maximal_review_effort"></a>`maximal_review_effort`: maximal effort level for auto-approval. If the PR's estimated review effort is above this threshold, the auto-approval will not run. Default is 5.
|
||||
|
||||
### Incremental Mode
|
||||
Incremental review only considers changes since the last PR-Agent review. This can be useful when working on the PR in an iterative manner, and you want to focus on the changes since the last review instead of reviewing the entire PR again.
|
||||
For invoking the incremental mode, the following command can be used:
|
||||
```
|
||||
/review -i
|
||||
```
|
||||
Note that the incremental mode is only available for GitHub.
|
||||
|
||||
{width=512}
|
||||
|
||||
### PR Reflection
|
||||
|
||||
By invoking:
|
||||
```
|
||||
/reflect_and_review
|
||||
```
|
||||
The tool will first ask the author questions about the PR, and will guide the review based on their answers.
|
||||
|
||||
{width=512}
|
||||
|
||||
{width=512}
|
||||
|
||||
{width=512}
|
||||
|
||||
|
||||
## Usage Tips
|
||||
|
||||
!!! tip "General guidelines"
|
||||
|
||||
The `review` tool provides a collection of possible feedbacks about a PR.
|
||||
It is recommended to review the [Configuration options](#configuration-options) section, and choose the relevant options for your use case.
|
||||
|
||||
Some of the features that are disabled by default are quite useful, and should be considered for enabling. For example:
|
||||
`require_score_review`, `require_soc2_ticket`, and more.
|
||||
|
||||
On the other hand, if you find one of the enabled features to be irrelevant for your use case, disable it. No default configuration can fit all use cases.
|
||||
|
||||
!!! tip "Automation"
|
||||
When you first install PR-Agent app, the [default mode](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-a-new-pr-is-opened) for the `review` tool is:
|
||||
```
|
||||
pr_commands = ["/review --pr_reviewer.num_code_suggestions=0", ...]
|
||||
```
|
||||
Meaning the `review` tool will run automatically on every PR, without providing code suggestions.
|
||||
Edit this field to enable/disable the tool, or to change the used configurations.
|
||||
|
||||
!!! tip "Code suggestions"
|
||||
|
||||
If you set `num_code_suggestions`>0 , the `review` tool will also provide code suggestions.
|
||||
|
||||
Notice If you are interested **only** in the code suggestions, it is recommended to use the [`improve`](./improve.md) feature instead, since it is a dedicated only to code suggestions, and usually gives better results.
|
||||
Use the `review` tool if you want to get more comprehensive feedback, which includes code suggestions as well.
|
||||
|
||||
!!! tip "Possible labels from the review tool"
|
||||
|
||||
The `review` tool can auto-generate two specific types of labels for a PR:
|
||||
|
||||
- a `possible security issue` label that detects if a possible [security issue](https://github.com/Codium-ai/pr-agent/blob/tr/user_description/pr_agent/settings/pr_reviewer_prompts.toml#L136) exists in the PR code (`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)
|
||||
|
||||
Both modes are useful, and we recommended to enable them.
|
||||
|
||||
!!! tip "Extra instructions"
|
||||
|
||||
Extra instructions are important.
|
||||
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]
|
||||
extra_instructions="""\
|
||||
In the code feedback 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.
|
||||
|
||||
|
||||
!!! tip "Auto-approval"
|
||||
|
||||
PR-Agent can approve a PR when a specific comment is invoked.
|
||||
|
||||
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)
|
||||
|
||||
|
||||
After enabling, by commenting on a PR:
|
||||
```
|
||||
/review auto_approve
|
||||
```
|
||||
PR-Agent will automatically approve the PR, and add a comment with the approval.
|
||||
|
||||
|
||||
You can also enable auto-approval only if the PR meets certain requirements, such as that the `estimated_review_effort` label is equal or below a certain threshold, by adjusting the flag:
|
||||
```
|
||||
[pr_reviewer]
|
||||
maximal_review_effort = 5
|
||||
```
|
||||
@ -1,63 +0,0 @@
|
||||
## Overview
|
||||
The similar code tool retrieves the most similar code components from inside the organization's codebase, or from open-source code.
|
||||
|
||||
For example:
|
||||
|
||||
`Global Search` for a method called `chat_completion`:
|
||||
|
||||
{width=768}
|
||||
|
||||
|
||||
PR-Agent will examine the code component and will extract the most relevant keywords to search for similar code:
|
||||
|
||||
- `extracted keywords`: the keywords that were extracted from the code by PR-Agent. the link will open a search page with the extracted keywords, to allow the user to modify the search if needed.
|
||||
- `search context`: the context in which the search will be performed, organization's codebase or open-source code (Global).
|
||||
- `similar code`: the most similar code components found. the link will open the code component in the relevant file.
|
||||
- `relevant repositories`: the open-source repositories in which that are relevant to the searched code component and it's keywords.
|
||||
|
||||
Search result link example:
|
||||
|
||||
{width=768}
|
||||
|
||||
|
||||
`Organization Search`:
|
||||
|
||||
{width=768}
|
||||
|
||||
|
||||
## How to use
|
||||
### Manually
|
||||
To invoke the `similar code` tool manually, comment on the PR:
|
||||
```
|
||||
/find_similar_component COMPONENT_NAME
|
||||
```
|
||||
Where `COMPONENT_NAME` should be the name of a code component in the PR (class, method, function).
|
||||
|
||||
If there is a name ambiguity, there are two configurations that will help the tool to find the correct component:
|
||||
|
||||
- `--pr_find_similar_component.file`: in case there are several components with the same name, you can specify the relevant file.
|
||||
- `--pr_find_similar_component.class_name`: in case there are several methods with the same name in the same file, you can specify the relevant class name.
|
||||
|
||||
example:
|
||||
```
|
||||
/find_similar_component COMPONENT_NAME --pr_find_similar_component.file=FILE_NAME
|
||||
```
|
||||
|
||||
### Automatically (via Analyze table)
|
||||
It can be invoked automatically from the analyze table, can be accessed by:
|
||||
```
|
||||
/analyze
|
||||
```
|
||||
Choose the components you want to find similar code for, and click on the `similar` checkbox.
|
||||
{width=768}
|
||||
|
||||
If you are looking to search for similar code in the organization's codebase, you can click on the `Organization` checkbox, and it will invoke a new search command just for the organization's codebase.
|
||||
|
||||
{width=768}
|
||||
|
||||
|
||||
## Configuration options
|
||||
|
||||
- `search_from_org`: if set to true, the tool will search for similar code in the organization's codebase. Default is false.
|
||||
- `number_of_keywords`: number of keywords to use for the search. Default is 5.
|
||||
- `number_of_results`: the maximum number of results to present. Default is 5.
|
||||
@ -1,43 +0,0 @@
|
||||
## Overview
|
||||
The similar issue tool retrieves the most similar issues to the current issue.
|
||||
It can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/similar_issue
|
||||
```
|
||||
|
||||
|
||||
## Example usage
|
||||
|
||||
{width=768}
|
||||
|
||||
{width=768}
|
||||
|
||||
{width=768}
|
||||
|
||||
Note that to perform retrieval, the `similar_issue` tool indexes all the repo previous issues (once).
|
||||
|
||||
|
||||
**Select VectorDBs** by changing `pr_similar_issue` parameter in `configuration.toml` file
|
||||
|
||||
2 VectorDBs are available to switch in
|
||||
1. LanceDB
|
||||
2. Pinecone
|
||||
|
||||
To enable usage of the '**similar issue**' tool for Pinecone, you need to set the following keys in `.secrets.toml` (or in the relevant environment variables):
|
||||
|
||||
```
|
||||
[pinecone]
|
||||
api_key = "..."
|
||||
environment = "..."
|
||||
```
|
||||
These parameters can be obtained by registering to [Pinecone](https://app.pinecone.io/?sessionType=signup/).
|
||||
|
||||
|
||||
## How to use:
|
||||
- To invoke the 'similar issue' tool from **CLI**, run:
|
||||
`python3 cli.py --issue_url=... similar_issue`
|
||||
|
||||
- To invoke the 'similar' issue tool via online usage, [comment](https://github.com/Codium-ai/pr-agent/issues/178#issuecomment-1716934893) on a PR:
|
||||
`/similar_issue`
|
||||
|
||||
- You can also enable the 'similar issue' tool to run automatically when a new issue is opened, by adding it to the [pr_commands list in the github_app section](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L66)
|
||||
@ -1,36 +0,0 @@
|
||||
## Overview
|
||||
By combining LLM abilities with static code analysis, the `test` tool generate tests for a selected component, based on the PR code changes.
|
||||
It can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/test component_name
|
||||
```
|
||||
where 'component_name' is the name of a specific component in the PR.
|
||||
To get a list of the components that changed in the PR and choose the relevant component interactively, use the [`analyze`](./analyze.md) tool.
|
||||
|
||||
## Example usage
|
||||
|
||||
Invoke the tool manually by commenting `/test` on any PR:
|
||||
|
||||
{width=704}
|
||||
|
||||
The tool will generate tests for the selected component (if no component is stated, it will generate tests for largest component):
|
||||
|
||||
{width=768}
|
||||
|
||||
{width=768}
|
||||
|
||||
(Example taken from [here](https://github.com/Codium-ai/pr-agent/pull/598#issuecomment-1913679429)):
|
||||
|
||||
**Notes**
|
||||
- Language that are currently supported by the tool: Python, Java, C++, JavaScript, TypeScript, C#.
|
||||
- This tool can also be triggered interactively by using the [`analyze`](./analyze.md) tool.
|
||||
|
||||
|
||||
## Configuration options
|
||||
- `num_tests`: number of tests to generate. Default is 3.
|
||||
- `testing_framework`: the testing framework to use. If not set, for Python it will use `pytest`, for Java it will use `JUnit`, for C++ it will use `Catch2`, and for JavaScript and TypeScript it will use `jest`.
|
||||
- `avoid_mocks`: if set to true, the tool will try to avoid using mocks in the generated tests. Note that even if this option is set to true, the tool might still use mocks if it cannot generate a test without them. Default is true.
|
||||
- `extra_instructions`: Optional extra instructions to the tool. For example: "use the following mock injection scheme: ...".
|
||||
- `file`: in case there are several components with the same name, you can specify the relevant file.
|
||||
- `class_name`: in case there are several methods with the same name in the same file, you can specify the relevant class name.
|
||||
- `enable_help_text`: if set to true, the tool will add a help text to the PR comment. Default is true.
|
||||
@ -1,19 +0,0 @@
|
||||
## Overview
|
||||
The `update_changelog` tool automatically updates the CHANGELOG.md file with the PR changes.
|
||||
It can be invoked manually by commenting on any PR:
|
||||
```
|
||||
/update_changelog
|
||||
```
|
||||
|
||||
## Example usage
|
||||
|
||||
{width=768}
|
||||
|
||||
{width=768}
|
||||
|
||||
## Configuration options
|
||||
|
||||
Under the section `pr_update_changelog`, the [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L50) contains options to customize the 'update changelog' tool:
|
||||
|
||||
- `push_changelog_changes`: whether to push the changes to CHANGELOG.md, or just print them. Default is false (print only).
|
||||
- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...
|
||||
@ -1,242 +0,0 @@
|
||||
## Ignoring files from analysis
|
||||
|
||||
In some cases, you may want to exclude specific files or directories from the analysis performed by CodiumAI PR-Agent. This can be useful, for example, when you have files that are generated automatically or files that shouldn't be reviewed, like vendored code.
|
||||
|
||||
To ignore files or directories, edit the **[ignore.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/ignore.toml)** configuration file. This setting also exposes the following environment variables:
|
||||
|
||||
- `IGNORE.GLOB`
|
||||
- `IGNORE.REGEX`
|
||||
|
||||
For example, to ignore Python files in a PR with online usage, comment on a PR:
|
||||
`/review --ignore.glob=['*.py']`
|
||||
|
||||
To ignore Python files in all PRs, set in a configuration file:
|
||||
```
|
||||
[ignore]
|
||||
glob = ['*.py']
|
||||
```
|
||||
|
||||
## 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 ..."
|
||||
```
|
||||
|
||||
## Working with large PRs
|
||||
|
||||
The default mode of CodiumAI is to have a single call per tool, using GPT-4, which has a token limit of 8000 tokens.
|
||||
This mode provides a very good speed-quality-cost tradeoff, and can handle most PRs successfully.
|
||||
When the PR is above the token limit, it employs a [PR Compression strategy](../core-abilities/index.md).
|
||||
|
||||
However, for very large PRs, or in case you want to emphasize quality over speed and cost, there are two possible solutions:
|
||||
1) [Use a model](https://codium-ai.github.io/Docs-PR-Agent/usage-guide/#changing-a-model) with larger context, like GPT-32K, or claude-100K. This solution will be applicable for all the tools.
|
||||
2) For the `/improve` tool, there is an ['extended' mode](https://codium-ai.github.io/Docs-PR-Agent/tools/#improve) (`/improve --extended`),
|
||||
which divides the PR to chunks, and processes each chunk separately. With this mode, regardless of the model, no compression will be done (but for large PRs, multiple model calls may occur)
|
||||
|
||||
|
||||
## Changing a model
|
||||
|
||||
See [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/__init__.py) for the list of available models.
|
||||
To use a different model than the default (GPT-4), you need to edit [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L2).
|
||||
For models and environments not from OPENAI, you might need to provide additional keys and other parameters. See below for instructions.
|
||||
|
||||
### Azure
|
||||
|
||||
To use Azure, set in your `.secrets.toml` (working from CLI), or in the GitHub `Settings > Secrets and variables` (working from GitHub App or GitHub Action):
|
||||
```
|
||||
[openai]
|
||||
key = "" # your azure api key
|
||||
api_type = "azure"
|
||||
api_version = '2023-05-15' # Check Azure documentation for the current API version
|
||||
api_base = "" # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
|
||||
deployment_id = "" # The deployment name you chose when you deployed the engine
|
||||
```
|
||||
|
||||
and set in your configuration file:
|
||||
```
|
||||
[config]
|
||||
model="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
|
||||
```
|
||||
|
||||
### Huggingface
|
||||
|
||||
**Local**
|
||||
You can run Huggingface models locally through either [VLLM](https://docs.litellm.ai/docs/providers/vllm) or [Ollama](https://docs.litellm.ai/docs/providers/ollama)
|
||||
|
||||
E.g. to use a new Huggingface model locally via Ollama, set:
|
||||
```
|
||||
[__init__.py]
|
||||
MAX_TOKENS = {
|
||||
"model-name-on-ollama": <max_tokens>
|
||||
}
|
||||
e.g.
|
||||
MAX_TOKENS={
|
||||
...,
|
||||
"ollama/llama2": 4096
|
||||
}
|
||||
|
||||
|
||||
[config] # in configuration.toml
|
||||
model = "ollama/llama2"
|
||||
model_turbo = "ollama/llama2"
|
||||
|
||||
[ollama] # in .secrets.toml
|
||||
api_base = ... # the base url for your huggingface inference endpoint
|
||||
# e.g. if running Ollama locally, you may use:
|
||||
api_base = "http://localhost:11434/"
|
||||
```
|
||||
|
||||
### Inference Endpoints
|
||||
|
||||
To use a new model with Huggingface Inference Endpoints, for example, set:
|
||||
```
|
||||
[__init__.py]
|
||||
MAX_TOKENS = {
|
||||
"model-name-on-huggingface": <max_tokens>
|
||||
}
|
||||
e.g.
|
||||
MAX_TOKENS={
|
||||
...,
|
||||
"meta-llama/Llama-2-7b-chat-hf": 4096
|
||||
}
|
||||
[config] # in configuration.toml
|
||||
model = "huggingface/meta-llama/Llama-2-7b-chat-hf"
|
||||
model_turbo = "huggingface/meta-llama/Llama-2-7b-chat-hf"
|
||||
|
||||
[huggingface] # in .secrets.toml
|
||||
key = ... # your huggingface api key
|
||||
api_base = ... # the base url for your huggingface inference endpoint
|
||||
```
|
||||
(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
|
||||
|
||||
### Replicate
|
||||
|
||||
To use Llama2 model with Replicate, for example, set:
|
||||
```
|
||||
[config] # in configuration.toml
|
||||
model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
|
||||
model_turbo = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
|
||||
[replicate] # in .secrets.toml
|
||||
key = ...
|
||||
```
|
||||
(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
|
||||
|
||||
|
||||
Also, review the [AiHandler](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/ai_handler.py) file for instructions on how to set keys for other models.
|
||||
|
||||
### Groq
|
||||
|
||||
To use Llama3 model with Groq, for example, set:
|
||||
```
|
||||
[config] # in configuration.toml
|
||||
model = "llama3-70b-8192"
|
||||
model_turbo = "llama3-70b-8192"
|
||||
fallback_models = ["groq/llama3-70b-8192"]
|
||||
[groq] # in .secrets.toml
|
||||
key = ... # your Groq api key
|
||||
```
|
||||
(you can obtain a Groq key from [here](https://console.groq.com/keys))
|
||||
|
||||
### Vertex AI
|
||||
|
||||
To use Google's Vertex AI platform and its associated models (chat-bison/codechat-bison) set:
|
||||
|
||||
```
|
||||
[config] # in configuration.toml
|
||||
model = "vertex_ai/codechat-bison"
|
||||
model_turbo = "vertex_ai/codechat-bison"
|
||||
fallback_models="vertex_ai/codechat-bison"
|
||||
|
||||
[vertexai] # in .secrets.toml
|
||||
vertex_project = "my-google-cloud-project"
|
||||
vertex_location = ""
|
||||
```
|
||||
|
||||
Your [application default credentials](https://cloud.google.com/docs/authentication/application-default-credentials) will be used for authentication so there is no need to set explicit credentials in most environments.
|
||||
|
||||
If you do want to set explicit credentials then you can use the `GOOGLE_APPLICATION_CREDENTIALS` environment variable set to a path to a json credentials file.
|
||||
|
||||
### Anthropic
|
||||
|
||||
To use Anthropic models, set the relevant models in the configuration section of the configuration file:
|
||||
```
|
||||
[config]
|
||||
model="anthropic/claude-3-opus-20240229"
|
||||
model_turbo="anthropic/claude-3-opus-20240229"
|
||||
fallback_models=["anthropic/claude-3-opus-20240229"]
|
||||
```
|
||||
|
||||
And also set the api key in the .secrets.toml file:
|
||||
```
|
||||
[anthropic]
|
||||
KEY = "..."
|
||||
```
|
||||
|
||||
### Amazon Bedrock
|
||||
|
||||
To use Amazon Bedrock and its foundational models, add the below configuration:
|
||||
|
||||
```
|
||||
[config] # in configuration.toml
|
||||
model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
|
||||
model_turbo="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
|
||||
fallback_models=["bedrock/anthropic.claude-v2:1"]
|
||||
|
||||
[aws] # in .secrets.toml
|
||||
bedrock_region = "us-east-1"
|
||||
```
|
||||
|
||||
Note that you have to add access to foundational models before using them. Please refer to [this document](https://docs.aws.amazon.com/bedrock/latest/userguide/setting-up.html) for more details.
|
||||
|
||||
If you are using the claude-3 model, please configure the following settings as there are parameters incompatible with claude-3.
|
||||
```
|
||||
[litellm]
|
||||
drop_params = true
|
||||
```
|
||||
|
||||
AWS session is automatically authenticated from your environment, but you can also explicitly set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` environment variables.
|
||||
|
||||
|
||||
## Patch Extra Lines
|
||||
|
||||
By default, around any change in your PR, git patch provides three lines of context above and below the change.
|
||||
```
|
||||
@@ -12,5 +12,5 @@ def func1():
|
||||
code line that already existed in the file...
|
||||
code line that already existed in the file...
|
||||
code line that already existed in the file....
|
||||
-code line that was removed in the PR
|
||||
+new code line added in the PR
|
||||
code line that already existed in the file...
|
||||
code line that already existed in the file...
|
||||
code line that already existed in the file...
|
||||
```
|
||||
|
||||
For the `review`, `describe`, `ask` and `add_docs` tools, if the token budget allows, PR-Agent tries to increase the number of lines of context, via the parameter:
|
||||
```
|
||||
[config]
|
||||
patch_extra_lines=3
|
||||
```
|
||||
|
||||
Increasing this number provides more context to the model, but will also increase the token budget.
|
||||
If the PR is too large (see [PR Compression strategy](https://github.com/Codium-ai/pr-agent/blob/main/PR_COMPRESSION.md)), PR-Agent automatically sets this number to 0, using the original git patch.
|
||||
|
||||
|
||||
## 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](https://github.com/Codium-ai/pr-agent/blob/main/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](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/tools/pr_description.py#L137).
|
||||
@ -1,208 +0,0 @@
|
||||
## Local repo (CLI)
|
||||
When running from your locally cloned PR-Agent repo (CLI), your local configuration file will be used.
|
||||
Examples of invoking the different tools via the CLI:
|
||||
|
||||
- **Review**: `python -m pr_agent.cli --pr_url=<pr_url> review`
|
||||
- **Describe**: `python -m pr_agent.cli --pr_url=<pr_url> describe`
|
||||
- **Improve**: `python -m pr_agent.cli --pr_url=<pr_url> improve`
|
||||
- **Ask**: `python -m pr_agent.cli --pr_url=<pr_url> ask "Write me a poem about this PR"`
|
||||
- **Reflect**: `python -m pr_agent.cli --pr_url=<pr_url> reflect`
|
||||
- **Update Changelog**: `python -m pr_agent.cli --pr_url=<pr_url> update_changelog`
|
||||
|
||||
`<pr_url>` is the url of the relevant PR (for example: [#50](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 -m pr_agent.cli --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=false
|
||||
verbosity_level=2
|
||||
```
|
||||
This is useful for debugging or experimenting with 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](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml) file can be similarly edited. Comment `/config` to see the list of available configurations.
|
||||
|
||||
|
||||
## GitHub App
|
||||
|
||||
!!! note "Configurations for PR-Agent Pro"
|
||||
PR-Agent Pro for GitHub is an App, hosted by CodiumAI. So all the instructions below are relevant also for PR-Agent Pro users.
|
||||
Same goes for [GitLab webhook](#gitlab-webhook) and [BitBucket App](#bitbucket-app) sections.
|
||||
|
||||
### GitHub app automatic tools when a new PR is opened
|
||||
|
||||
The [github_app](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L108) section defines GitHub app specific configurations.
|
||||
|
||||
The configuration parameter `pr_commands` defines the list of tools that will be **run automatically** when a new PR is opened.
|
||||
```
|
||||
[github_app]
|
||||
pr_commands = [
|
||||
"/describe --pr_description.final_update_message=false",
|
||||
"/review --pr_reviewer.num_code_suggestions=0",
|
||||
"/improve",
|
||||
]
|
||||
```
|
||||
This means that when a new PR is opened/reopened or marked as ready for review, PR-Agent will run the `describe`, `review` and `improve` tools.
|
||||
For the `review` tool, for example, the `num_code_suggestions` parameter will be set to 0.
|
||||
|
||||
You can override the default tool parameters by using one the three options for a [configuration file](https://codium-ai.github.io/Docs-PR-Agent/usage-guide/#configuration-options): **wiki**, **local**, or **global**.
|
||||
For example, if your local `.pr_agent.toml` file contains:
|
||||
```
|
||||
[pr_description]
|
||||
generate_ai_title = true
|
||||
```
|
||||
Every time you run the `describe` tool, including automatic runs, the PR title will be generated by the AI.
|
||||
|
||||
To cancel the automatic run of all the tools, set:
|
||||
```
|
||||
[github_app]
|
||||
handle_pr_actions = []
|
||||
```
|
||||
|
||||
You can also disable automatic runs for PRs with specific titles, by setting the `ignore_pr_titles` parameter with the relevant regex. For example:
|
||||
```
|
||||
[github_app]
|
||||
ignore_pr_title = ["^[Auto]", ".*ignore.*"]
|
||||
```
|
||||
will ignore PRs with titles that start with "Auto" or contain the word "ignore".
|
||||
|
||||
### GitHub app automatic tools for push actions (commits to an open PR)
|
||||
|
||||
In addition to running automatic tools when a PR is opened, the GitHub app can also respond to new code that is pushed to an open PR.
|
||||
|
||||
The configuration toggle `handle_push_trigger` can be used to enable this feature.
|
||||
The configuration parameter `push_commands` defines the list of tools that will be **run automatically** when new code is pushed to the PR.
|
||||
```
|
||||
[github_app]
|
||||
handle_push_trigger = true
|
||||
push_commands = [
|
||||
"/describe",
|
||||
"/review --pr_reviewer.num_code_suggestions=0 --pr_reviewer.final_update_message=false",
|
||||
]
|
||||
```
|
||||
This means that when new code is pushed to the PR, the PR-Agent will run the `describe` and `review` tools, with the specified parameters.
|
||||
|
||||
## GitHub Action
|
||||
`GitHub Action` is a different way to trigger PR-Agent tools, and uses a different configuration mechanism than `GitHub App`.<br>
|
||||
You can configure settings for `GitHub Action` by adding environment variables under the env section in `.github/workflows/pr_agent.yml` file.
|
||||
Specifically, start by setting the following environment variables:
|
||||
```yaml
|
||||
env:
|
||||
OPENAI_KEY: ${{ secrets.OPENAI_KEY }} # Make sure to add your OpenAI key to your repo secrets
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # Make sure to add your GitHub token to your repo secrets
|
||||
github_action_config.auto_review: "true" # enable\disable auto review
|
||||
github_action_config.auto_describe: "true" # enable\disable auto describe
|
||||
github_action_config.auto_improve: "true" # enable\disable auto improve
|
||||
github_action_config.enable_output: "true" # enable\disable github actions output parameter
|
||||
```
|
||||
`github_action_config.auto_review`, `github_action_config.auto_describe` and `github_action_config.auto_improve` are used to enable/disable automatic tools that run when a new PR is opened.
|
||||
If not set, the default configuration is for all three tools to run automatically when a new PR is opened.
|
||||
|
||||
`github_action_config.enable_output` are used to enable/disable github actions [output parameter](https://docs.github.com/en/actions/creating-actions/metadata-syntax-for-github-actions#outputs-for-docker-container-and-javascript-actions) (default is `true`).
|
||||
Review result is output as JSON to `steps.{step-id}.outputs.review` property.
|
||||
The JSON structure is equivalent to the yaml data structure defined in [pr_reviewer_prompts.toml](https://github.com/idubnori/pr-agent/blob/main/pr_agent/settings/pr_reviewer_prompts.toml).
|
||||
|
||||
Note that you can give additional config parameters by adding environment variables to `.github/workflows/pr_agent.yml`, or by using a `.pr_agent.toml` [configuration file](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/#global-configuration-file) in the root of your repo
|
||||
|
||||
For example, you can set an environment variable: `pr_description.publish_labels=false`, or add a `.pr_agent.toml` file with the following content:
|
||||
```
|
||||
[pr_description]
|
||||
publish_labels = false
|
||||
```
|
||||
to prevent PR-Agent from publishing labels when running the `describe` tool.
|
||||
|
||||
## GitLab Webhook
|
||||
After setting up a GitLab webhook, to control which commands will run automatically when a new PR is opened, you can set the `pr_commands` parameter in the configuration file, similar to the GitHub App:
|
||||
```
|
||||
[gitlab]
|
||||
pr_commands = [
|
||||
"/describe",
|
||||
"/review --pr_reviewer.num_code_suggestions=0",
|
||||
"/improve",
|
||||
]
|
||||
```
|
||||
|
||||
## BitBucket App
|
||||
Similar to GitHub app, when running PR-Agent from BitBucket App, the default [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml) from a pre-built docker will be initially loaded.
|
||||
|
||||
By uploading a local `.pr_agent.toml` file to the root of the repo's main branch, you can edit and customize any configuration parameter. Note that you need to upload `.pr_agent.toml` prior to creating a PR, in order for the configuration to take effect.
|
||||
|
||||
For example, if your local `.pr_agent.toml` file contains:
|
||||
```
|
||||
[pr_reviewer]
|
||||
inline_code_comments = true
|
||||
```
|
||||
|
||||
Each time you invoke a `/review` tool, it will use inline code comments.
|
||||
|
||||
### BitBucket Self-Hosted App automatic tools
|
||||
|
||||
To control which commands will run automatically when a new PR is opened, you can set the `pr_commands` parameter in the configuration file:
|
||||
Specifically, set the following values:
|
||||
|
||||
```
|
||||
[bitbucket_app]
|
||||
pr_commands = [
|
||||
"/review --pr_reviewer.num_code_suggestions=0",
|
||||
"/improve --pr_code_suggestions.commitable_code_suggestions=true",
|
||||
]
|
||||
```
|
||||
|
||||
## Azure DevOps provider
|
||||
|
||||
To use Azure DevOps provider use the following settings in configuration.toml:
|
||||
```
|
||||
[config]
|
||||
git_provider="azure"
|
||||
```
|
||||
|
||||
Azure DevOps provider supports [PAT token](https://learn.microsoft.com/en-us/azure/devops/organizations/accounts/use-personal-access-tokens-to-authenticate?view=azure-devops&tabs=Windows) or [DefaultAzureCredential](https://learn.microsoft.com/en-us/azure/developer/python/sdk/authentication-overview#authentication-in-server-environments) authentication.
|
||||
PAT is faster to create, but has build in expiration date, and will use the user identity for API calls.
|
||||
Using DefaultAzureCredential you can use managed identity or Service principle, which are more secure and will create separate ADO user identity (via AAD) to the agent.
|
||||
|
||||
If PAT was chosen, you can assign the value in .secrets.toml.
|
||||
If DefaultAzureCredential was chosen, you can assigned the additional env vars like AZURE_CLIENT_SECRET directly,
|
||||
or use managed identity/az cli (for local development) without any additional configuration.
|
||||
in any case, 'org' value must be assigned in .secrets.toml:
|
||||
```
|
||||
[azure_devops]
|
||||
org = "https://dev.azure.com/YOUR_ORGANIZATION/"
|
||||
# pat = "YOUR_PAT_TOKEN" needed only if using PAT for authentication
|
||||
```
|
||||
|
||||
### Azure DevOps Webhook
|
||||
|
||||
To control which commands will run automatically when a new PR is opened, you can set the `pr_commands` parameter in the configuration file, similar to the GitHub App:
|
||||
```
|
||||
[azure_devops_server]
|
||||
pr_commands = [
|
||||
"/describe",
|
||||
"/review --pr_reviewer.num_code_suggestions=0",
|
||||
"/improve",
|
||||
]
|
||||
```
|
||||
@ -1,56 +0,0 @@
|
||||
The different tools and sub-tools used by CodiumAI PR-Agent are adjustable via the **[configuration file](https://github.com/Codium-ai/pr-agent/blob/main/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](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L16) section in the configuration file.
|
||||
See the [Tools Guide](https://codium-ai.github.io/Docs-PR-Agent/tools/) for a detailed description of the different tools and their configurations.
|
||||
|
||||
There are three ways to set persistent configurations:
|
||||
|
||||
1. Wiki configuration page 💎
|
||||
2. Local configuration file
|
||||
3. Global configuration file 💎
|
||||
|
||||
In terms of precedence, wiki configurations will override local configurations, and local configurations will override global configurations.
|
||||
|
||||
## Wiki configuration file 💎
|
||||
|
||||
Specifically for GitHub, with PR-Agent-Pro you can set configurations by creating a page called `.pr_agent.toml` in the [wiki](https://github.com/Codium-ai/pr-agent/wiki/pr_agent.toml) of the repo.
|
||||
The advantage of this method is that it allows to set configurations without needing to commit new content to the repo - just edit the wiki page and **save**.
|
||||
|
||||
{width=512}
|
||||
|
||||
Click [here](https://codium.ai/images/pr_agent/wiki_configuration_pr_agent.mp4) to see a short instructional video. We recommend surrounding the configuration content with triple-quotes, to allow better presentation when displayed in the wiki as markdown.
|
||||
An example content:
|
||||
|
||||
```
|
||||
[pr_description]
|
||||
generate_ai_title=true
|
||||
```
|
||||
|
||||
PR-Agent will know to remove the triple-quotes when reading the configuration content.
|
||||
|
||||
## Local configuration file
|
||||
|
||||
By uploading a local `.pr_agent.toml` file to the root of the repo's main branch, you can edit and customize any configuration parameter. Note that you need to upload `.pr_agent.toml` prior to creating a PR, in order for the configuration to take effect.
|
||||
|
||||
For example, if you set in `.pr_agent.toml`:
|
||||
|
||||
```
|
||||
[pr_reviewer]
|
||||
extra_instructions="""\
|
||||
- instruction a
|
||||
- instruction b
|
||||
...
|
||||
"""
|
||||
```
|
||||
|
||||
Then you can give a list of extra instructions to the `review` tool.
|
||||
|
||||
|
||||
## Global configuration file 💎
|
||||
|
||||
If you create a repo called `pr-agent-settings` in your **organization**, it's configuration file `.pr_agent.toml` will be used as a global configuration file for any other repo that belongs to the same organization.
|
||||
Parameters from a local `.pr_agent.toml` file, in a specific repo, will override the global configuration parameters.
|
||||
|
||||
For example, in the GitHub organization `Codium-ai`:
|
||||
- The repo [`https://github.com/Codium-ai/pr-agent-settings`](https://github.com/Codium-ai/pr-agent-settings/blob/main/.pr_agent.toml) contains a `.pr_agent.toml` file that serves as a global configuration file for all the repos in the GitHub organization `Codium-ai`.
|
||||
- The repo [`https://github.com/Codium-ai/pr-agent`](https://github.com/Codium-ai/pr-agent/blob/main/.pr_agent.toml) inherits the global configuration file from `pr-agent-settings`.
|
||||
@ -1,23 +0,0 @@
|
||||
# Usage guide
|
||||
|
||||
This page provides a detailed guide on how to use PR-Agent. It includes information on how to adjust PR-Agent configurations, define which tools will run automatically, manage mail notifications, and other advanced configurations.
|
||||
|
||||
|
||||
- [Introduction](./introduction.md)
|
||||
- [Configuration Options](./configuration_options.md)
|
||||
- [Usage and Automation](./automations_and_usage.md)
|
||||
- [Local Repo (CLI)](./automations_and_usage.md#local-repo-cli)
|
||||
- [Online Usage](./automations_and_usage.md#online-usage)
|
||||
- [GitHub App](./automations_and_usage.md#github-app)
|
||||
- [GitHub Action](./automations_and_usage.md#github-action)
|
||||
- [GitLab Webhook](./automations_and_usage.md#gitlab-webhook)
|
||||
- [BitBucket App](./automations_and_usage.md#bitbucket-app)
|
||||
- [Azure DevOps Provider](./automations_and_usage.md#azure-devops-provider)
|
||||
- [Managing Mail Notifications](./mail_notifications.md)
|
||||
- [Additional Configurations Walkthrough](./additional_configurations.md)
|
||||
- [Ignoring files from analysis](./additional_configurations.md#ignoring-files-from-analysis)
|
||||
- [Extra instructions](./additional_configurations.md#extra-instructions)
|
||||
- [Working with large PRs](./additional_configurations.md#working-with-large-prs)
|
||||
- [Changing a model](./additional_configurations.md#changing-a-model)
|
||||
- [Patch Extra Lines](./additional_configurations.md#patch-extra-lines)
|
||||
- [Editing the prompts](./additional_configurations.md#editing-the-prompts)
|
||||
@ -1,18 +0,0 @@
|
||||
|
||||
After [installation](https://codium-ai.github.io/Docs-PR-Agent/installation/), there are three 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
|
||||
|
||||
|
||||
Specifically, CLI commands can be issued by invoking a pre-built [docker image](https://codium-ai.github.io/Docs-PR-Agent/installation/#run-from-source), or by invoking a [locally cloned repo](https://codium-ai.github.io/Docs-PR-Agent/installation/#locally).
|
||||
For online usage, you will need to setup either a [GitHub App](https://codium-ai.github.io/Docs-PR-Agent/installation/#run-as-a-github-app), or a [GitHub Action](https://codium-ai.github.io/Docs-PR-Agent/installation/#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.
|
||||
|
||||
|
||||
**git provider**: The [git_provider](https://github.com/Codium-ai/pr-agent/blob/main/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", "bitbucket", "azure", "codecommit", "local", "gerrit"
|
||||
`
|
||||
|
||||
@ -1,18 +0,0 @@
|
||||
|
||||
Unfortunately, it is not possible in GitHub to disable mail notifications from a specific user.
|
||||
If you are subscribed to notifications for a repo with PR-Agent, we recommend turning off notifications for PR comments, to avoid lengthy emails:
|
||||
|
||||
{width=512}
|
||||
|
||||
As an alternative, you can filter in your mail provider the notifications specifically from the PR-Agent bot, [see how](https://www.quora.com/How-can-you-filter-emails-for-specific-people-in-Gmail#:~:text=On%20the%20Filters%20and%20Blocked,the%20body%20of%20the%20email).
|
||||
|
||||
{width=512}
|
||||
|
||||
|
||||
Another option to reduce the mail overload, yet still receive notifications on PR-Agent tools, is to disable the help collapsible section in PR-Agent bot comments.
|
||||
This can done by setting `enable_help_text=false` for the relevant tool in the configuration file.
|
||||
For example, to disable the help text for the `pr_reviewer` tool, set:
|
||||
```
|
||||
[pr_reviewer]
|
||||
enable_help_text = false
|
||||
```
|
||||
133
docs/mkdocs.yml
133
docs/mkdocs.yml
@ -1,133 +0,0 @@
|
||||
site_name: PR-Agent Documentation
|
||||
repo_url: https://github.com/Codium-ai/pr-agent
|
||||
repo_name: Codium-ai/pr-agent
|
||||
|
||||
nav:
|
||||
- Overview: 'index.md'
|
||||
- Installation:
|
||||
- 'installation/index.md'
|
||||
- Locally: 'installation/locally.md'
|
||||
- GitHub: 'installation/github.md'
|
||||
- GitLab: 'installation/gitlab.md'
|
||||
- BitBucket: 'installation/bitbucket.md'
|
||||
- Azure DevOps: 'installation/azure.md'
|
||||
- 💎 PR-Agent Pro: 'installation/pr_agent_pro.md'
|
||||
- Usage Guide:
|
||||
- 'usage-guide/index.md'
|
||||
- Introduction: 'usage-guide/introduction.md'
|
||||
- Configuration Options: 'usage-guide/configuration_options.md'
|
||||
- Managing Mail Notifications: 'usage-guide/mail_notifications.md'
|
||||
- Usage and Automation: 'usage-guide/automations_and_usage.md'
|
||||
- Additional Configurations: 'usage-guide/additional_configurations.md'
|
||||
- Tools:
|
||||
- 'tools/index.md'
|
||||
- Describe: 'tools/describe.md'
|
||||
- Review: 'tools/review.md'
|
||||
- Improve: 'tools/improve.md'
|
||||
- Ask: 'tools/ask.md'
|
||||
- Update Changelog: 'tools/update_changelog.md'
|
||||
- Similar Issues: 'tools/similar_issues.md'
|
||||
- Help: 'tools/help.md'
|
||||
- 💎 Analyze: 'tools/analyze.md'
|
||||
- 💎 Test: 'tools/test.md'
|
||||
- 💎 Improve Component: 'tools/improve_component.md'
|
||||
- 💎 Documentation: 'tools/documentation.md'
|
||||
- 💎 Custom Labels: 'tools/custom_labels.md'
|
||||
- 💎 Custom Suggestions: 'tools/custom_suggestions.md'
|
||||
- 💎 CI Feedback: 'tools/ci_feedback.md'
|
||||
- 💎 Similar Code: 'tools/similar_code.md'
|
||||
- Core Abilities: 'core-abilities/index.md'
|
||||
|
||||
theme:
|
||||
logo: assets/logo.svg
|
||||
favicon: assets/favicon.ico
|
||||
name: material
|
||||
icon:
|
||||
repo: fontawesome/brands/github
|
||||
features:
|
||||
- navigation.tabs
|
||||
- navigation.expand
|
||||
- navigation.path
|
||||
- navigation.top
|
||||
- navigation.tracking
|
||||
- navigation.indexes
|
||||
- search.suggest
|
||||
- search.highlight
|
||||
- content.tabs.link
|
||||
- content.code.annotation
|
||||
- content.code.copy
|
||||
- toc.integrate
|
||||
language: en
|
||||
custom_dir: overrides
|
||||
|
||||
palette:
|
||||
- media: "(prefers-color-scheme)"
|
||||
toggle:
|
||||
icon: material/brightness-auto
|
||||
name: Switch to light mode
|
||||
- media: "(prefers-color-scheme: light)"
|
||||
scheme: default
|
||||
toggle:
|
||||
icon: material/toggle-switch-off-outline
|
||||
name: Switch to dark mode
|
||||
primary: custom
|
||||
accent: custom
|
||||
- media: "(prefers-color-scheme: dark)"
|
||||
scheme: slate
|
||||
toggle:
|
||||
icon: material/toggle-switch
|
||||
name: Switch to light mode
|
||||
primary: custom
|
||||
accent: custom
|
||||
|
||||
plugins:
|
||||
- social
|
||||
- search
|
||||
- glightbox
|
||||
|
||||
extra:
|
||||
generator: false
|
||||
social:
|
||||
- icon: fontawesome/brands/github
|
||||
link: https://github.com/Codium-ai
|
||||
- icon: fontawesome/brands/discord
|
||||
link: https://discord.com/invite/SgSxuQ65GF
|
||||
- icon: fontawesome/brands/youtube
|
||||
link: https://www.youtube.com/@Codium-AI
|
||||
- icon: fontawesome/brands/linkedin
|
||||
link: https://www.linkedin.com/company/codiumai
|
||||
- icon: fontawesome/brands/twitter
|
||||
link: https://twitter.com/CodiumAI
|
||||
- icon: fontawesome/brands/instagram
|
||||
link: https://www.instagram.com/codiumai/
|
||||
analytics:
|
||||
provider: custom
|
||||
property: ${{ secrets.GOOGLE_ANALYTICS_ID }}
|
||||
|
||||
extra_css:
|
||||
- css/custom.css
|
||||
|
||||
markdown_extensions:
|
||||
- pymdownx.highlight:
|
||||
anchor_linenums: true
|
||||
- pymdownx.inlinehilite
|
||||
- pymdownx.snippets
|
||||
- admonition
|
||||
- pymdownx.arithmatex:
|
||||
generic: true
|
||||
- footnotes
|
||||
- pymdownx.details
|
||||
- pymdownx.superfences
|
||||
- pymdownx.mark
|
||||
- md_in_html
|
||||
- attr_list
|
||||
- pymdownx.emoji:
|
||||
emoji_index: !!python/name:material.extensions.emoji.twemoji
|
||||
emoji_generator: !!python/name:material.extensions.emoji.to_svg
|
||||
- toc:
|
||||
title: On this page
|
||||
toc_depth: 3
|
||||
permalink: true
|
||||
|
||||
copyright: |
|
||||
© 2024 <a href="https://www.codium.ai/" target="_blank" rel="noopener">CodiumAI</a>
|
||||
@ -1,10 +0,0 @@
|
||||
{% extends "base.html" %}
|
||||
|
||||
{% block scripts %}
|
||||
{{ super() }}
|
||||
|
||||
<!-- Google Tag Manager (noscript) -->
|
||||
<noscript><iframe src="https://www.googletagmanager.com/ns.html?id=GTM-5C9KZBM3"
|
||||
height="0" width="0" style="display:none;visibility:hidden"></iframe></noscript>
|
||||
<!-- End Google Tag Manager (noscript) -->
|
||||
{% endblock %}
|
||||
@ -1,115 +0,0 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Footer</title>
|
||||
<style>
|
||||
body {
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
font-family: Arial, sans-serif;
|
||||
font-size: 16px;
|
||||
}
|
||||
|
||||
.wrapper {
|
||||
background-color: #171518;
|
||||
}
|
||||
|
||||
.container {
|
||||
display: flex;
|
||||
flex-direction: row;
|
||||
align-items: center;
|
||||
justify-content: space-between;
|
||||
color: white;
|
||||
padding: 20px;
|
||||
max-width: 61rem;
|
||||
margin-left: auto;
|
||||
margin-right: auto;
|
||||
}
|
||||
|
||||
.footer-links, .social-icons {
|
||||
padding: 0;
|
||||
list-style-type: none;
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
gap: 20px;
|
||||
align-items: center;
|
||||
}
|
||||
|
||||
.footer-links a:hover, .social-icons a:hover {
|
||||
color: #AEA1F1;
|
||||
}
|
||||
|
||||
.social-icons svg {
|
||||
width: 24px;
|
||||
height: auto;
|
||||
fill: white;
|
||||
}
|
||||
|
||||
.footer-text {
|
||||
width: 240px;
|
||||
}
|
||||
|
||||
@media (max-width: 768px) {
|
||||
.container {
|
||||
flex-direction: column;
|
||||
align-items: center;
|
||||
text-align: center;
|
||||
}
|
||||
|
||||
.footer-links, .social-icons, .footer-text {
|
||||
width: 100%;
|
||||
justify-content: center;
|
||||
margin: 10px 0;
|
||||
}
|
||||
|
||||
.footer-links {
|
||||
order: 1;
|
||||
}
|
||||
|
||||
.social-icons {
|
||||
order: 2;
|
||||
}
|
||||
|
||||
.footer-text {
|
||||
order: 3;
|
||||
}
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
|
||||
<footer class="wrapper">
|
||||
<div class="container">
|
||||
<p class="footer-text">© 2024 <a href="https://www.codium.ai/" target="_blank" rel="noopener">CodiumAI</a></p>
|
||||
<div class="footer-links">
|
||||
<a href="https://codiumate-docs.codium.ai/">Codiumate</a>
|
||||
<p>|</p>
|
||||
<a href="https://alpha-codium-docs.codium.ai/">AlphaCodium</a>
|
||||
</div>
|
||||
<div class="social-icons">
|
||||
<a href="https://github.com/Codium-ai" target="_blank" rel="noopener" title="github.com" class="social-link">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6zm-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3zm44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9zM244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8zM97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1zm-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7zm32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1zm-11.4-14.7c-1.6 1-1.6 3.6 0 5.9 1.6 2.3 4.3 3.3 5.6 2.3 1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2z"></path></svg>
|
||||
</a>
|
||||
<a href="https://discord.com/invite/SgSxuQ65GF" target="_blank" rel="noopener" title="discord.com" class="social-link">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 640 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M524.531 69.836a1.5 1.5 0 0 0-.764-.7A485.065 485.065 0 0 0 404.081 32.03a1.816 1.816 0 0 0-1.923.91 337.461 337.461 0 0 0-14.9 30.6 447.848 447.848 0 0 0-134.426 0 309.541 309.541 0 0 0-15.135-30.6 1.89 1.89 0 0 0-1.924-.91 483.689 483.689 0 0 0-119.688 37.107 1.712 1.712 0 0 0-.788.676C39.068 183.651 18.186 294.69 28.43 404.354a2.016 2.016 0 0 0 .765 1.375 487.666 487.666 0 0 0 146.825 74.189 1.9 1.9 0 0 0 2.063-.676A348.2 348.2 0 0 0 208.12 430.4a1.86 1.86 0 0 0-1.019-2.588 321.173 321.173 0 0 1-45.868-21.853 1.885 1.885 0 0 1-.185-3.126 251.047 251.047 0 0 0 9.109-7.137 1.819 1.819 0 0 1 1.9-.256c96.229 43.917 200.41 43.917 295.5 0a1.812 1.812 0 0 1 1.924.233 234.533 234.533 0 0 0 9.132 7.16 1.884 1.884 0 0 1-.162 3.126 301.407 301.407 0 0 1-45.89 21.83 1.875 1.875 0 0 0-1 2.611 391.055 391.055 0 0 0 30.014 48.815 1.864 1.864 0 0 0 2.063.7A486.048 486.048 0 0 0 610.7 405.729a1.882 1.882 0 0 0 .765-1.352c12.264-126.783-20.532-236.912-86.934-334.541ZM222.491 337.58c-28.972 0-52.844-26.587-52.844-59.239s23.409-59.241 52.844-59.241c29.665 0 53.306 26.82 52.843 59.239 0 32.654-23.41 59.241-52.843 59.241Zm195.38 0c-28.971 0-52.843-26.587-52.843-59.239s23.409-59.241 52.843-59.241c29.667 0 53.307 26.82 52.844 59.239 0 32.654-23.177 59.241-52.844 59.241Z"></path></svg>
|
||||
</a>
|
||||
<a href="https://www.youtube.com/@Codium-AI" target="_blank" rel="noopener" title="www.youtube.com" class="social-link">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M549.655 124.083c-6.281-23.65-24.787-42.276-48.284-48.597C458.781 64 288 64 288 64S117.22 64 74.629 75.486c-23.497 6.322-42.003 24.947-48.284 48.597-11.412 42.867-11.412 132.305-11.412 132.305s0 89.438 11.412 132.305c6.281 23.65 24.787 41.5 48.284 47.821C117.22 448 288 448 288 448s170.78 0 213.371-11.486c23.497-6.321 42.003-24.171 48.284-47.821 11.412-42.867 11.412-132.305 11.412-132.305s0-89.438-11.412-132.305zm-317.51 213.508V175.185l142.739 81.205-142.739 81.201z"></path></svg>
|
||||
</a>
|
||||
<a href="https://www.linkedin.com/company/codiumai" target="_blank" rel="noopener" title="www.linkedin.com" class="social-link">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M416 32H31.9C14.3 32 0 46.5 0 64.3v383.4C0 465.5 14.3 480 31.9 480H416c17.6 0 32-14.5 32-32.3V64.3c0-17.8-14.4-32.3-32-32.3zM135.4 416H69V202.2h66.5V416zm-33.2-243c-21.3 0-38.5-17.3-38.5-38.5S80.9 96 102.2 96c21.2 0 38.5 17.3 38.5 38.5 0 21.3-17.2 38.5-38.5 38.5zm282.1 243h-66.4V312c0-24.8-.5-56.7-34.5-56.7-34.6 0-39.9 27-39.9 54.9V416h-66.4V202.2h63.7v29.2h.9c8.9-16.8 30.6-34.5 62.9-34.5 67.2 0 79.7 44.3 79.7 101.9V416z"></path></svg>
|
||||
</a>
|
||||
<a href="https://twitter.com/CodiumAI" target="_blank" rel="noopener" title="twitter.com" class="social-link">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M459.37 151.716c.325 4.548.325 9.097.325 13.645 0 138.72-105.583 298.558-298.558 298.558-59.452 0-114.68-17.219-161.137-47.106 8.447.974 16.568 1.299 25.34 1.299 49.055 0 94.213-16.568 130.274-44.832-46.132-.975-84.792-31.188-98.112-72.772 6.498.974 12.995 1.624 19.818 1.624 9.421 0 18.843-1.3 27.614-3.573-48.081-9.747-84.143-51.98-84.143-102.985v-1.299c13.969 7.797 30.214 12.67 47.431 13.319-28.264-18.843-46.781-51.005-46.781-87.391 0-19.492 5.197-37.36 14.294-52.954 51.655 63.675 129.3 105.258 216.365 109.807-1.624-7.797-2.599-15.918-2.599-24.04 0-57.828 46.782-104.934 104.934-104.934 30.213 0 57.502 12.67 76.67 33.137 23.715-4.548 46.456-13.32 66.599-25.34-7.798 24.366-24.366 44.833-46.132 57.827 21.117-2.273 41.584-8.122 60.426-16.243-14.292 20.791-32.161 39.308-52.628 54.253z"></path></svg>
|
||||
</a>
|
||||
<a href="https://www.instagram.com/codiumai/" target="_blank" rel="noopener" title="www.instagram.com" class="social-link">
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.5.1 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2023 Fonticons, Inc.--><path d="M224.1 141c-63.6 0-114.9 51.3-114.9 114.9s51.3 114.9 114.9 114.9S339 319.5 339 255.9 287.7 141 224.1 141zm0 189.6c-41.1 0-74.7-33.5-74.7-74.7s33.5-74.7 74.7-74.7 74.7 33.5 74.7 74.7-33.6 74.7-74.7 74.7zm146.4-194.3c0 14.9-12 26.8-26.8 26.8-14.9 0-26.8-12-26.8-26.8s12-26.8 26.8-26.8 26.8 12 26.8 26.8zm76.1 27.2c-1.7-35.9-9.9-67.7-36.2-93.9-26.2-26.2-58-34.4-93.9-36.2-37-2.1-147.9-2.1-184.9 0-35.8 1.7-67.6 9.9-93.9 36.1s-34.4 58-36.2 93.9c-2.1 37-2.1 147.9 0 184.9 1.7 35.9 9.9 67.7 36.2 93.9s58 34.4 93.9 36.2c37 2.1 147.9 2.1 184.9 0 35.9-1.7 67.7-9.9 93.9-36.2 26.2-26.2 34.4-58 36.2-93.9 2.1-37 2.1-147.8 0-184.8zM398.8 388c-7.8 19.6-22.9 34.7-42.6 42.6-29.5 11.7-99.5 9-132.1 9s-102.7 2.6-132.1-9c-19.6-7.8-34.7-22.9-42.6-42.6-11.7-29.5-9-99.5-9-132.1s-2.6-102.7 9-132.1c7.8-19.6 22.9-34.7 42.6-42.6 29.5-11.7 99.5-9 132.1-9s102.7-2.6 132.1 9c19.6 7.8 34.7 22.9 42.6 42.6 11.7 29.5 9 99.5 9 132.1s2.7 102.7-9 132.1z"></path></svg>
|
||||
</a>
|
||||
</div>
|
||||
</div>
|
||||
</footer>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
@ -1,7 +0,0 @@
|
||||
<!-- Google Tag Manager -->
|
||||
<script>(function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':
|
||||
new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],
|
||||
j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src=
|
||||
'https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);
|
||||
})(window,document,'script','dataLayer','GTM-5C9KZBM3');</script>
|
||||
<!-- End Google Tag Manager -->
|
||||
BIN
pics/logo-dark.png
Normal file
BIN
pics/logo-dark.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 22 KiB |
BIN
pics/logo-light.png
Normal file
BIN
pics/logo-light.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 25 KiB |
@ -1,97 +1,33 @@
|
||||
import shlex
|
||||
from functools import partial
|
||||
import re
|
||||
|
||||
from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
|
||||
from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
|
||||
|
||||
from pr_agent.algo.utils import update_settings_from_args
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.git_providers.utils import apply_repo_settings
|
||||
from pr_agent.log import get_logger
|
||||
from pr_agent.tools.pr_add_docs import PRAddDocs
|
||||
from pr_agent.config_loader import settings
|
||||
from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
|
||||
from pr_agent.tools.pr_config import PRConfig
|
||||
from pr_agent.tools.pr_description import PRDescription
|
||||
from pr_agent.tools.pr_generate_labels import PRGenerateLabels
|
||||
from pr_agent.tools.pr_help_message import PRHelpMessage
|
||||
from pr_agent.tools.pr_information_from_user import PRInformationFromUser
|
||||
from pr_agent.tools.pr_line_questions import PR_LineQuestions
|
||||
from pr_agent.tools.pr_questions import PRQuestions
|
||||
from pr_agent.tools.pr_reviewer import PRReviewer
|
||||
from pr_agent.tools.pr_similar_issue import PRSimilarIssue
|
||||
from pr_agent.tools.pr_update_changelog import PRUpdateChangelog
|
||||
|
||||
command2class = {
|
||||
"auto_review": PRReviewer,
|
||||
"answer": PRReviewer,
|
||||
"review": PRReviewer,
|
||||
"review_pr": PRReviewer,
|
||||
"reflect": PRInformationFromUser,
|
||||
"reflect_and_review": PRInformationFromUser,
|
||||
"describe": PRDescription,
|
||||
"describe_pr": PRDescription,
|
||||
"improve": PRCodeSuggestions,
|
||||
"improve_code": PRCodeSuggestions,
|
||||
"ask": PRQuestions,
|
||||
"ask_question": PRQuestions,
|
||||
"ask_line": PR_LineQuestions,
|
||||
"update_changelog": PRUpdateChangelog,
|
||||
"config": PRConfig,
|
||||
"settings": PRConfig,
|
||||
"help": PRHelpMessage,
|
||||
"similar_issue": PRSimilarIssue,
|
||||
"add_docs": PRAddDocs,
|
||||
"generate_labels": PRGenerateLabels,
|
||||
}
|
||||
|
||||
commands = list(command2class.keys())
|
||||
|
||||
class PRAgent:
|
||||
def __init__(self, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
|
||||
self.ai_handler = ai_handler # will be initialized in run_action
|
||||
self.forbidden_cli_args = ['enable_auto_approval']
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
async def handle_request(self, pr_url, request, notify=None) -> bool:
|
||||
# First, apply repo specific settings if exists
|
||||
apply_repo_settings(pr_url)
|
||||
|
||||
# Then, apply user specific settings if exists
|
||||
if isinstance(request, str):
|
||||
request = request.replace("'", "\\'")
|
||||
lexer = shlex.shlex(request, posix=True)
|
||||
lexer.whitespace_split = True
|
||||
action, *args = list(lexer)
|
||||
else:
|
||||
action, *args = request
|
||||
|
||||
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 for param '{forbidden_arg}' is forbidden. Use instead a configuration file.")
|
||||
return False
|
||||
args = update_settings_from_args(args)
|
||||
|
||||
action = action.lstrip("/").lower()
|
||||
if action not in command2class:
|
||||
get_logger().debug(f"Unknown command: {action}")
|
||||
return False
|
||||
with get_logger().contextualize(command=action):
|
||||
get_logger().info("PR-Agent request handler started", analytics=True)
|
||||
if action == "reflect_and_review":
|
||||
get_settings().pr_reviewer.ask_and_reflect = True
|
||||
if action == "answer":
|
||||
if notify:
|
||||
notify()
|
||||
await PRReviewer(pr_url, is_answer=True, args=args, ai_handler=self.ai_handler).run()
|
||||
elif action == "auto_review":
|
||||
await PRReviewer(pr_url, is_auto=True, args=args, ai_handler=self.ai_handler).run()
|
||||
elif action in command2class:
|
||||
if notify:
|
||||
notify()
|
||||
|
||||
await command2class[action](pr_url, ai_handler=self.ai_handler, args=args).run()
|
||||
async def handle_request(self, pr_url, request) -> bool:
|
||||
action, *args = request.strip().split()
|
||||
if any(cmd == action for cmd in ["/answer"]):
|
||||
await PRReviewer(pr_url, is_answer=True).review()
|
||||
elif any(cmd == action for cmd in ["/review", "/review_pr", "/reflect_and_review"]):
|
||||
if settings.pr_reviewer.ask_and_reflect or "/reflect_and_review" in request:
|
||||
await PRInformationFromUser(pr_url).generate_questions()
|
||||
else:
|
||||
return False
|
||||
return True
|
||||
await PRReviewer(pr_url, args=args).review()
|
||||
elif any(cmd == action for cmd in ["/describe", "/describe_pr"]):
|
||||
await PRDescription(pr_url).describe()
|
||||
elif any(cmd == action for cmd in ["/improve", "/improve_code"]):
|
||||
await PRCodeSuggestions(pr_url).suggest()
|
||||
elif any(cmd == action for cmd in ["/ask", "/ask_question"]):
|
||||
await PRQuestions(pr_url, args).answer()
|
||||
else:
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
@ -1,37 +1,10 @@
|
||||
MAX_TOKENS = {
|
||||
'text-embedding-ada-002': 8000,
|
||||
'gpt-3.5-turbo': 16000,
|
||||
'gpt-3.5-turbo-0125': 16000,
|
||||
'gpt-3.5-turbo': 4000,
|
||||
'gpt-3.5-turbo-0613': 4000,
|
||||
'gpt-3.5-turbo-1106': 16000,
|
||||
'gpt-3.5-turbo-0301': 4000,
|
||||
'gpt-3.5-turbo-16k': 16000,
|
||||
'gpt-3.5-turbo-16k-0613': 16000,
|
||||
'gpt-4': 8000,
|
||||
'gpt-4-0613': 8000,
|
||||
'gpt-4-32k': 32000,
|
||||
'gpt-4-1106-preview': 128000, # 128K, but may be limited by config.max_model_tokens
|
||||
'gpt-4-0125-preview': 128000, # 128K, but may be limited by config.max_model_tokens
|
||||
'gpt-4-turbo-preview': 128000, # 128K, but may be limited by config.max_model_tokens
|
||||
'gpt-4-turbo-2024-04-09': 128000, # 128K, but may be limited by config.max_model_tokens
|
||||
'gpt-4-turbo': 128000, # 128K, but may be limited by config.max_model_tokens
|
||||
'claude-instant-1': 100000,
|
||||
'claude-2': 100000,
|
||||
'command-nightly': 4096,
|
||||
'replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1': 4096,
|
||||
'meta-llama/Llama-2-7b-chat-hf': 4096,
|
||||
'vertex_ai/codechat-bison': 6144,
|
||||
'vertex_ai/codechat-bison-32k': 32000,
|
||||
'codechat-bison': 6144,
|
||||
'codechat-bison-32k': 32000,
|
||||
'anthropic.claude-instant-v1': 100000,
|
||||
'anthropic.claude-v1': 100000,
|
||||
'anthropic.claude-v2': 100000,
|
||||
'anthropic/claude-3-opus-20240229': 100000,
|
||||
'bedrock/anthropic.claude-instant-v1': 100000,
|
||||
'bedrock/anthropic.claude-v2': 100000,
|
||||
'bedrock/anthropic.claude-v2:1': 100000,
|
||||
'bedrock/anthropic.claude-3-sonnet-20240229-v1:0': 100000,
|
||||
'bedrock/anthropic.claude-3-haiku-20240307-v1:0': 100000,
|
||||
'groq/llama3-8b-8192': 8192,
|
||||
'groq/llama3-70b-8192': 8192,
|
||||
}
|
||||
|
||||
82
pr_agent/algo/ai_handler.py
Normal file
82
pr_agent/algo/ai_handler.py
Normal file
@ -0,0 +1,82 @@
|
||||
import logging
|
||||
|
||||
import openai
|
||||
from openai.error import APIError, Timeout, TryAgain, RateLimitError
|
||||
from retry import retry
|
||||
|
||||
from pr_agent.config_loader import settings
|
||||
|
||||
OPENAI_RETRIES=5
|
||||
|
||||
class AiHandler:
|
||||
"""
|
||||
This class handles interactions with the OpenAI API for chat completions.
|
||||
It initializes the API key and other settings from a configuration file,
|
||||
and provides a method for performing chat completions using the OpenAI ChatCompletion API.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""
|
||||
Initializes the OpenAI API key and other settings from a configuration file.
|
||||
Raises a ValueError if the OpenAI key is missing.
|
||||
"""
|
||||
try:
|
||||
openai.api_key = settings.openai.key
|
||||
if settings.get("OPENAI.ORG", None):
|
||||
openai.organization = settings.openai.org
|
||||
self.deployment_id = settings.get("OPENAI.DEPLOYMENT_ID", None)
|
||||
if settings.get("OPENAI.API_TYPE", None):
|
||||
openai.api_type = settings.openai.api_type
|
||||
if settings.get("OPENAI.API_VERSION", None):
|
||||
openai.api_version = settings.openai.api_version
|
||||
if settings.get("OPENAI.API_BASE", None):
|
||||
openai.api_base = settings.openai.api_base
|
||||
except AttributeError as e:
|
||||
raise ValueError("OpenAI key is required") from e
|
||||
|
||||
@retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
|
||||
tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
|
||||
async def chat_completion(self, model: str, temperature: float, system: str, user: str):
|
||||
"""
|
||||
Performs a chat completion using the OpenAI ChatCompletion API.
|
||||
Retries in case of API errors or timeouts.
|
||||
|
||||
Args:
|
||||
model (str): The model to use for chat completion.
|
||||
temperature (float): The temperature parameter for chat completion.
|
||||
system (str): The system message for chat completion.
|
||||
user (str): The user message for chat completion.
|
||||
|
||||
Returns:
|
||||
tuple: A tuple containing the response and finish reason from the API.
|
||||
|
||||
Raises:
|
||||
TryAgain: If the API response is empty or there are no choices in the response.
|
||||
APIError: If there is an error during OpenAI inference.
|
||||
Timeout: If there is a timeout during OpenAI inference.
|
||||
TryAgain: If there is an attribute error during OpenAI inference.
|
||||
"""
|
||||
try:
|
||||
response = await openai.ChatCompletion.acreate(
|
||||
model=model,
|
||||
deployment_id=self.deployment_id,
|
||||
messages=[
|
||||
{"role": "system", "content": system},
|
||||
{"role": "user", "content": user}
|
||||
],
|
||||
temperature=temperature,
|
||||
)
|
||||
except (APIError, Timeout, TryAgain) as e:
|
||||
logging.error("Error during OpenAI inference: ", e)
|
||||
raise
|
||||
except (RateLimitError) as e:
|
||||
logging.error("Rate limit error during OpenAI inference: ", e)
|
||||
raise
|
||||
except (Exception) as e:
|
||||
logging.error("Unknown error during OpenAI inference: ", e)
|
||||
raise TryAgain from e
|
||||
if response is None or len(response.choices) == 0:
|
||||
raise TryAgain
|
||||
resp = response.choices[0]['message']['content']
|
||||
finish_reason = response.choices[0].finish_reason
|
||||
return resp, finish_reason
|
||||
@ -1,28 +0,0 @@
|
||||
from abc import ABC, abstractmethod
|
||||
|
||||
class BaseAiHandler(ABC):
|
||||
"""
|
||||
This class defines the interface for an AI handler to be used by the PR Agents.
|
||||
"""
|
||||
|
||||
@abstractmethod
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
@property
|
||||
@abstractmethod
|
||||
def deployment_id(self):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2, img_path: str = None):
|
||||
"""
|
||||
This method should be implemented to return a chat completion from the AI model.
|
||||
Args:
|
||||
model (str): the name of the model to use for the chat completion
|
||||
system (str): the system message string to use for the chat completion
|
||||
user (str): the user message string to use for the chat completion
|
||||
temperature (float): the temperature to use for the chat completion
|
||||
"""
|
||||
pass
|
||||
|
||||
@ -1,67 +0,0 @@
|
||||
try:
|
||||
from langchain.chat_models import ChatOpenAI, AzureChatOpenAI
|
||||
from langchain.schema import SystemMessage, HumanMessage
|
||||
except: # we don't enforce langchain as a dependency, so if it's not installed, just move on
|
||||
pass
|
||||
|
||||
from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.log import get_logger
|
||||
|
||||
from openai.error import APIError, RateLimitError, Timeout, TryAgain
|
||||
from retry import retry
|
||||
import functools
|
||||
|
||||
OPENAI_RETRIES = 5
|
||||
|
||||
class LangChainOpenAIHandler(BaseAiHandler):
|
||||
def __init__(self):
|
||||
# Initialize OpenAIHandler specific attributes here
|
||||
super().__init__()
|
||||
self.azure = get_settings().get("OPENAI.API_TYPE", "").lower() == "azure"
|
||||
try:
|
||||
if self.azure:
|
||||
# using a partial function so we can set the deployment_id later to support fallback_deployments
|
||||
# but still need to access the other settings now so we can raise a proper exception if they're missing
|
||||
self._chat = functools.partial(
|
||||
lambda **kwargs: AzureChatOpenAI(**kwargs),
|
||||
openai_api_key=get_settings().openai.key,
|
||||
openai_api_base=get_settings().openai.api_base,
|
||||
openai_api_version=get_settings().openai.api_version,
|
||||
)
|
||||
else:
|
||||
self._chat = ChatOpenAI(openai_api_key=get_settings().openai.key)
|
||||
except AttributeError as e:
|
||||
if getattr(e, "name"):
|
||||
raise ValueError(f"OpenAI {e.name} is required") from e
|
||||
else:
|
||||
raise e
|
||||
|
||||
@property
|
||||
def chat(self):
|
||||
if self.azure:
|
||||
# we must set the deployment_id only here (instead of the __init__ method) to support fallback_deployments
|
||||
return self._chat(deployment_name=self.deployment_id)
|
||||
else:
|
||||
return self._chat
|
||||
|
||||
@property
|
||||
def deployment_id(self):
|
||||
"""
|
||||
Returns the deployment ID for the OpenAI API.
|
||||
"""
|
||||
return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
|
||||
@retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
|
||||
tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
|
||||
async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
|
||||
try:
|
||||
messages=[SystemMessage(content=system), HumanMessage(content=user)]
|
||||
|
||||
# get a chat completion from the formatted messages
|
||||
resp = self.chat(messages, model=model, temperature=temperature)
|
||||
finish_reason="completed"
|
||||
return resp.content, finish_reason
|
||||
|
||||
except (Exception) as e:
|
||||
get_logger().error("Unknown error during OpenAI inference: ", e)
|
||||
raise e
|
||||
@ -1,170 +0,0 @@
|
||||
import os
|
||||
import requests
|
||||
import boto3
|
||||
import litellm
|
||||
import openai
|
||||
from litellm import acompletion
|
||||
from tenacity import retry, retry_if_exception_type, stop_after_attempt
|
||||
from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.log import get_logger
|
||||
|
||||
OPENAI_RETRIES = 5
|
||||
|
||||
|
||||
class LiteLLMAIHandler(BaseAiHandler):
|
||||
"""
|
||||
This class handles interactions with the OpenAI API for chat completions.
|
||||
It initializes the API key and other settings from a configuration file,
|
||||
and provides a method for performing chat completions using the OpenAI ChatCompletion API.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
"""
|
||||
Initializes the OpenAI API key and other settings from a configuration file.
|
||||
Raises a ValueError if the OpenAI key is missing.
|
||||
"""
|
||||
self.azure = False
|
||||
self.aws_bedrock_client = None
|
||||
self.api_base = None
|
||||
self.repetition_penalty = None
|
||||
if get_settings().get("OPENAI.KEY", None):
|
||||
openai.api_key = get_settings().openai.key
|
||||
litellm.openai_key = get_settings().openai.key
|
||||
if get_settings().get("litellm.use_client"):
|
||||
litellm_token = get_settings().get("litellm.LITELLM_TOKEN")
|
||||
assert litellm_token, "LITELLM_TOKEN is required"
|
||||
os.environ["LITELLM_TOKEN"] = litellm_token
|
||||
litellm.use_client = True
|
||||
if get_settings().get("LITELLM.DROP_PARAMS", None):
|
||||
litellm.drop_params = get_settings().litellm.drop_params
|
||||
if get_settings().get("OPENAI.ORG", None):
|
||||
litellm.organization = get_settings().openai.org
|
||||
if get_settings().get("OPENAI.API_TYPE", None):
|
||||
if get_settings().openai.api_type == "azure":
|
||||
self.azure = True
|
||||
litellm.azure_key = get_settings().openai.key
|
||||
if get_settings().get("OPENAI.API_VERSION", None):
|
||||
litellm.api_version = get_settings().openai.api_version
|
||||
if get_settings().get("OPENAI.API_BASE", None):
|
||||
litellm.api_base = get_settings().openai.api_base
|
||||
if get_settings().get("ANTHROPIC.KEY", None):
|
||||
litellm.anthropic_key = get_settings().anthropic.key
|
||||
if get_settings().get("COHERE.KEY", None):
|
||||
litellm.cohere_key = get_settings().cohere.key
|
||||
if get_settings().get("GROQ.KEY", None):
|
||||
litellm.api_key = get_settings().groq.key
|
||||
if get_settings().get("REPLICATE.KEY", None):
|
||||
litellm.replicate_key = get_settings().replicate.key
|
||||
if get_settings().get("HUGGINGFACE.KEY", None):
|
||||
litellm.huggingface_key = get_settings().huggingface.key
|
||||
if get_settings().get("HUGGINGFACE.API_BASE", None) and 'huggingface' in get_settings().config.model:
|
||||
litellm.api_base = get_settings().huggingface.api_base
|
||||
self.api_base = get_settings().huggingface.api_base
|
||||
if get_settings().get("OLLAMA.API_BASE", None) :
|
||||
litellm.api_base = get_settings().ollama.api_base
|
||||
self.api_base = get_settings().ollama.api_base
|
||||
if get_settings().get("HUGGINGFACE.REPITITION_PENALTY", None):
|
||||
self.repetition_penalty = float(get_settings().huggingface.repetition_penalty)
|
||||
if get_settings().get("VERTEXAI.VERTEX_PROJECT", None):
|
||||
litellm.vertex_project = get_settings().vertexai.vertex_project
|
||||
litellm.vertex_location = get_settings().get(
|
||||
"VERTEXAI.VERTEX_LOCATION", None
|
||||
)
|
||||
if get_settings().get("AWS.BEDROCK_REGION", None):
|
||||
litellm.AmazonAnthropicConfig.max_tokens_to_sample = 2000
|
||||
litellm.AmazonAnthropicClaude3Config.max_tokens = 2000
|
||||
self.aws_bedrock_client = boto3.client(
|
||||
service_name="bedrock-runtime",
|
||||
region_name=get_settings().aws.bedrock_region,
|
||||
)
|
||||
|
||||
def prepare_logs(self, response, system, user, resp, finish_reason):
|
||||
response_log = response.dict().copy()
|
||||
response_log['system'] = system
|
||||
response_log['user'] = user
|
||||
response_log['output'] = resp
|
||||
response_log['finish_reason'] = finish_reason
|
||||
if hasattr(self, 'main_pr_language'):
|
||||
response_log['main_pr_language'] = self.main_pr_language
|
||||
else:
|
||||
response_log['main_pr_language'] = 'unknown'
|
||||
return response_log
|
||||
|
||||
@property
|
||||
def deployment_id(self):
|
||||
"""
|
||||
Returns the deployment ID for the OpenAI API.
|
||||
"""
|
||||
return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
|
||||
|
||||
@retry(
|
||||
retry=retry_if_exception_type((openai.APIError, openai.APIConnectionError, openai.Timeout)), # No retry on RateLimitError
|
||||
stop=stop_after_attempt(OPENAI_RETRIES)
|
||||
)
|
||||
async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2, img_path: str = None):
|
||||
try:
|
||||
resp, finish_reason = None, None
|
||||
deployment_id = self.deployment_id
|
||||
if self.azure:
|
||||
model = 'azure/' + model
|
||||
messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
|
||||
if img_path:
|
||||
try:
|
||||
# check if the image link is alive
|
||||
r = requests.head(img_path, allow_redirects=True)
|
||||
if r.status_code == 404:
|
||||
error_msg = f"The image link is not [alive](img_path).\nPlease repost the original image as a comment, and send the question again with 'quote reply' (see [instructions](https://pr-agent-docs.codium.ai/tools/ask/#ask-on-images-using-the-pr-code-as-context))."
|
||||
get_logger().error(error_msg)
|
||||
return f"{error_msg}", "error"
|
||||
except Exception as e:
|
||||
get_logger().error(f"Error fetching image: {img_path}", e)
|
||||
return f"Error fetching image: {img_path}", "error"
|
||||
messages[1]["content"] = [{"type": "text", "text": messages[1]["content"]},
|
||||
{"type": "image_url", "image_url": {"url": img_path}}]
|
||||
|
||||
kwargs = {
|
||||
"model": model,
|
||||
"deployment_id": deployment_id,
|
||||
"messages": messages,
|
||||
"temperature": temperature,
|
||||
"force_timeout": get_settings().config.ai_timeout,
|
||||
"api_base" : self.api_base,
|
||||
}
|
||||
if self.aws_bedrock_client:
|
||||
kwargs["aws_bedrock_client"] = self.aws_bedrock_client
|
||||
if self.repetition_penalty:
|
||||
kwargs["repetition_penalty"] = self.repetition_penalty
|
||||
|
||||
get_logger().debug("Prompts", artifact={"system": system, "user": user})
|
||||
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"\nSystem prompt:\n{system}")
|
||||
get_logger().info(f"\nUser prompt:\n{user}")
|
||||
|
||||
response = await acompletion(**kwargs)
|
||||
except (openai.APIError, openai.Timeout) as e:
|
||||
get_logger().error("Error during OpenAI inference: ", e)
|
||||
raise
|
||||
except (openai.RateLimitError) as e:
|
||||
get_logger().error("Rate limit error during OpenAI inference: ", e)
|
||||
raise
|
||||
except (Exception) as e:
|
||||
get_logger().error("Unknown error during OpenAI inference: ", e)
|
||||
raise openai.APIError from e
|
||||
if response is None or len(response["choices"]) == 0:
|
||||
raise openai.APIError
|
||||
else:
|
||||
resp = response["choices"][0]['message']['content']
|
||||
finish_reason = response["choices"][0]["finish_reason"]
|
||||
get_logger().debug(f"\nAI response:\n{resp}")
|
||||
|
||||
# log the full response for debugging
|
||||
response_log = self.prepare_logs(response, system, user, resp, finish_reason)
|
||||
get_logger().debug("Full_response", artifact=response_log)
|
||||
|
||||
# for CLI debugging
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"\nAI response:\n{resp}")
|
||||
|
||||
return resp, finish_reason
|
||||
@ -1,67 +0,0 @@
|
||||
from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
|
||||
import openai
|
||||
from openai.error import APIError, RateLimitError, Timeout, TryAgain
|
||||
from retry import retry
|
||||
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.log import get_logger
|
||||
|
||||
OPENAI_RETRIES = 5
|
||||
|
||||
|
||||
class OpenAIHandler(BaseAiHandler):
|
||||
def __init__(self):
|
||||
# Initialize OpenAIHandler specific attributes here
|
||||
try:
|
||||
super().__init__()
|
||||
openai.api_key = get_settings().openai.key
|
||||
if get_settings().get("OPENAI.ORG", None):
|
||||
openai.organization = get_settings().openai.org
|
||||
if get_settings().get("OPENAI.API_TYPE", None):
|
||||
if get_settings().openai.api_type == "azure":
|
||||
self.azure = True
|
||||
openai.azure_key = get_settings().openai.key
|
||||
if get_settings().get("OPENAI.API_VERSION", None):
|
||||
openai.api_version = get_settings().openai.api_version
|
||||
if get_settings().get("OPENAI.API_BASE", None):
|
||||
openai.api_base = get_settings().openai.api_base
|
||||
|
||||
except AttributeError as e:
|
||||
raise ValueError("OpenAI key is required") from e
|
||||
@property
|
||||
def deployment_id(self):
|
||||
"""
|
||||
Returns the deployment ID for the OpenAI API.
|
||||
"""
|
||||
return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
|
||||
|
||||
@retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
|
||||
tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
|
||||
async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
|
||||
try:
|
||||
deployment_id = self.deployment_id
|
||||
get_logger().info("System: ", system)
|
||||
get_logger().info("User: ", user)
|
||||
messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
|
||||
|
||||
chat_completion = await openai.ChatCompletion.acreate(
|
||||
model=model,
|
||||
deployment_id=deployment_id,
|
||||
messages=messages,
|
||||
temperature=temperature,
|
||||
)
|
||||
resp = chat_completion["choices"][0]['message']['content']
|
||||
finish_reason = chat_completion["choices"][0]["finish_reason"]
|
||||
usage = chat_completion.get("usage")
|
||||
get_logger().info("AI response", response=resp, messages=messages, finish_reason=finish_reason,
|
||||
model=model, usage=usage)
|
||||
return resp, finish_reason
|
||||
except (APIError, Timeout, TryAgain) as e:
|
||||
get_logger().error("Error during OpenAI inference: ", e)
|
||||
raise
|
||||
except (RateLimitError) as e:
|
||||
get_logger().error("Rate limit error during OpenAI inference: ", e)
|
||||
raise
|
||||
except (Exception) as e:
|
||||
get_logger().error("Unknown error during OpenAI inference: ", e)
|
||||
raise TryAgain from e
|
||||
@ -1,36 +0,0 @@
|
||||
import fnmatch
|
||||
import re
|
||||
|
||||
from pr_agent.config_loader import get_settings
|
||||
|
||||
def filter_ignored(files):
|
||||
"""
|
||||
Filter out files that match the ignore patterns.
|
||||
"""
|
||||
|
||||
try:
|
||||
# load regex patterns, and translate glob patterns to regex
|
||||
patterns = get_settings().ignore.regex
|
||||
if isinstance(patterns, str):
|
||||
patterns = [patterns]
|
||||
glob_setting = get_settings().ignore.glob
|
||||
if isinstance(glob_setting, str): # --ignore.glob=[.*utils.py], --ignore.glob=.*utils.py
|
||||
glob_setting = glob_setting.strip('[]').split(",")
|
||||
patterns += [fnmatch.translate(glob) for glob in glob_setting]
|
||||
|
||||
# compile all valid patterns
|
||||
compiled_patterns = []
|
||||
for r in patterns:
|
||||
try:
|
||||
compiled_patterns.append(re.compile(r))
|
||||
except re.error:
|
||||
pass
|
||||
|
||||
# keep filenames that _don't_ match the ignore regex
|
||||
for r in compiled_patterns:
|
||||
files = [f for f in files if (f.filename and not r.match(f.filename))]
|
||||
|
||||
except Exception as e:
|
||||
print(f"Could not filter file list: {e}")
|
||||
|
||||
return files
|
||||
@ -1,10 +1,9 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import re
|
||||
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
|
||||
from pr_agent.log import get_logger
|
||||
from pr_agent.config_loader import settings
|
||||
|
||||
|
||||
def extend_patch(original_file_str, patch_str, num_lines) -> str:
|
||||
@ -42,16 +41,8 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
|
||||
extended_patch_lines.extend(
|
||||
original_lines[start1 + size1 - 1:start1 + size1 - 1 + num_lines])
|
||||
|
||||
res = list(match.groups())
|
||||
for i in range(len(res)):
|
||||
if res[i] is None:
|
||||
res[i] = 0
|
||||
try:
|
||||
start1, size1, start2, size2 = map(int, res[:4])
|
||||
except: # '@@ -0,0 +1 @@' case
|
||||
start1, size1, size2 = map(int, res[:3])
|
||||
start2 = 0
|
||||
section_header = res[4]
|
||||
start1, size1, start2, size2 = map(int, match.groups()[:4])
|
||||
section_header = match.groups()[4]
|
||||
extended_start1 = max(1, start1 - num_lines)
|
||||
extended_size1 = size1 + (start1 - extended_start1) + num_lines
|
||||
extended_start2 = max(1, start2 - num_lines)
|
||||
@ -64,8 +55,8 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
|
||||
continue
|
||||
extended_patch_lines.append(line)
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to extend patch: {e}")
|
||||
if settings.config.verbosity_level >= 2:
|
||||
logging.error(f"Failed to extend patch: {e}")
|
||||
return patch_str
|
||||
|
||||
# finish previous hunk
|
||||
@ -116,7 +107,7 @@ def omit_deletion_hunks(patch_lines) -> str:
|
||||
|
||||
|
||||
def handle_patch_deletions(patch: str, original_file_content_str: str,
|
||||
new_file_content_str: str, file_name: str, edit_type: EDIT_TYPE = EDIT_TYPE.UNKNOWN) -> str:
|
||||
new_file_content_str: str, file_name: str) -> str:
|
||||
"""
|
||||
Handle entire file or deletion patches.
|
||||
|
||||
@ -133,25 +124,24 @@ def handle_patch_deletions(patch: str, original_file_content_str: str,
|
||||
str: The modified patch with deletion hunks omitted.
|
||||
|
||||
"""
|
||||
if not new_file_content_str and edit_type != EDIT_TYPE.ADDED:
|
||||
if not new_file_content_str:
|
||||
# logic for handling deleted files - don't show patch, just show that the file was deleted
|
||||
if get_settings().config.verbosity_level > 0:
|
||||
get_logger().info(f"Processing file: {file_name}, minimizing deletion file")
|
||||
if settings.config.verbosity_level > 0:
|
||||
logging.info(f"Processing file: {file_name}, minimizing deletion file")
|
||||
patch = None # file was deleted
|
||||
else:
|
||||
patch_lines = patch.splitlines()
|
||||
patch_new = omit_deletion_hunks(patch_lines)
|
||||
if patch != patch_new:
|
||||
if get_settings().config.verbosity_level > 0:
|
||||
get_logger().info(f"Processing file: {file_name}, hunks were deleted")
|
||||
if settings.config.verbosity_level > 0:
|
||||
logging.info(f"Processing file: {file_name}, hunks were deleted")
|
||||
patch = patch_new
|
||||
return patch
|
||||
|
||||
|
||||
def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
|
||||
"""
|
||||
Convert a given patch string into a string with line numbers for each hunk, indicating the new and old content of
|
||||
the file.
|
||||
Convert a given patch string into a string with line numbers for each hunk, indicating the new and old content of the file.
|
||||
|
||||
Args:
|
||||
patch (str): The patch string to be converted.
|
||||
@ -162,7 +152,7 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
|
||||
|
||||
example output:
|
||||
## src/file.ts
|
||||
__new hunk__
|
||||
--new hunk--
|
||||
881 line1
|
||||
882 line2
|
||||
883 line3
|
||||
@ -171,7 +161,7 @@ __new hunk__
|
||||
889 line6
|
||||
890 line7
|
||||
...
|
||||
__old hunk__
|
||||
--old hunk--
|
||||
line1
|
||||
line2
|
||||
- line3
|
||||
@ -181,7 +171,8 @@ __old hunk__
|
||||
...
|
||||
"""
|
||||
|
||||
patch_with_lines_str = f"\n\n## file: '{file.filename.strip()}'\n"
|
||||
patch_with_lines_str = f"## {file.filename}\n"
|
||||
import re
|
||||
patch_lines = patch.splitlines()
|
||||
RE_HUNK_HEADER = re.compile(
|
||||
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
|
||||
@ -189,41 +180,24 @@ __old hunk__
|
||||
old_content_lines = []
|
||||
match = None
|
||||
start1, size1, start2, size2 = -1, -1, -1, -1
|
||||
prev_header_line = []
|
||||
header_line =[]
|
||||
for line in patch_lines:
|
||||
if 'no newline at end of file' in line.lower():
|
||||
continue
|
||||
|
||||
if line.startswith('@@'):
|
||||
header_line = line
|
||||
match = RE_HUNK_HEADER.match(line)
|
||||
if match and new_content_lines: # found a new hunk, split the previous lines
|
||||
if new_content_lines:
|
||||
if prev_header_line:
|
||||
patch_with_lines_str += f'\n{prev_header_line}\n'
|
||||
patch_with_lines_str = patch_with_lines_str.rstrip()+'\n__new hunk__\n'
|
||||
patch_with_lines_str += '\n--new hunk--\n'
|
||||
for i, line_new in enumerate(new_content_lines):
|
||||
patch_with_lines_str += f"{start2 + i} {line_new}\n"
|
||||
if old_content_lines:
|
||||
patch_with_lines_str = patch_with_lines_str.rstrip()+'\n__old hunk__\n'
|
||||
patch_with_lines_str += '--old hunk--\n'
|
||||
for line_old in old_content_lines:
|
||||
patch_with_lines_str += f"{line_old}\n"
|
||||
new_content_lines = []
|
||||
old_content_lines = []
|
||||
if match:
|
||||
prev_header_line = header_line
|
||||
|
||||
res = list(match.groups())
|
||||
for i in range(len(res)):
|
||||
if res[i] is None:
|
||||
res[i] = 0
|
||||
try:
|
||||
start1, size1, start2, size2 = map(int, res[:4])
|
||||
except: # '@@ -0,0 +1 @@' case
|
||||
start1, size1, size2 = map(int, res[:3])
|
||||
start2 = 0
|
||||
|
||||
start1, size1, start2, size2 = map(int, match.groups()[:4])
|
||||
elif line.startswith('+'):
|
||||
new_content_lines.append(line)
|
||||
elif line.startswith('-'):
|
||||
@ -235,69 +209,12 @@ __old hunk__
|
||||
# finishing last hunk
|
||||
if match and new_content_lines:
|
||||
if new_content_lines:
|
||||
patch_with_lines_str += f'\n{header_line}\n'
|
||||
patch_with_lines_str = patch_with_lines_str.rstrip()+ '\n__new hunk__\n'
|
||||
patch_with_lines_str += '\n--new hunk--\n'
|
||||
for i, line_new in enumerate(new_content_lines):
|
||||
patch_with_lines_str += f"{start2 + i} {line_new}\n"
|
||||
if old_content_lines:
|
||||
patch_with_lines_str = patch_with_lines_str.rstrip() + '\n__old hunk__\n'
|
||||
patch_with_lines_str += '\n--old hunk--\n'
|
||||
for line_old in old_content_lines:
|
||||
patch_with_lines_str += f"{line_old}\n"
|
||||
|
||||
return patch_with_lines_str.rstrip()
|
||||
|
||||
|
||||
def extract_hunk_lines_from_patch(patch: str, file_name, line_start, line_end, side) -> tuple[str, str]:
|
||||
|
||||
patch_with_lines_str = f"\n\n## file: '{file_name.strip()}'\n\n"
|
||||
selected_lines = ""
|
||||
patch_lines = patch.splitlines()
|
||||
RE_HUNK_HEADER = re.compile(
|
||||
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
|
||||
match = None
|
||||
start1, size1, start2, size2 = -1, -1, -1, -1
|
||||
skip_hunk = False
|
||||
selected_lines_num = 0
|
||||
for line in patch_lines:
|
||||
if 'no newline at end of file' in line.lower():
|
||||
continue
|
||||
|
||||
if line.startswith('@@'):
|
||||
skip_hunk = False
|
||||
selected_lines_num = 0
|
||||
header_line = line
|
||||
|
||||
match = RE_HUNK_HEADER.match(line)
|
||||
|
||||
res = list(match.groups())
|
||||
for i in range(len(res)):
|
||||
if res[i] is None:
|
||||
res[i] = 0
|
||||
try:
|
||||
start1, size1, start2, size2 = map(int, res[:4])
|
||||
except: # '@@ -0,0 +1 @@' case
|
||||
start1, size1, size2 = map(int, res[:3])
|
||||
start2 = 0
|
||||
|
||||
# check if line range is in this hunk
|
||||
if side.lower() == 'left':
|
||||
# check if line range is in this hunk
|
||||
if not (start1 <= line_start <= start1 + size1):
|
||||
skip_hunk = True
|
||||
continue
|
||||
elif side.lower() == 'right':
|
||||
if not (start2 <= line_start <= start2 + size2):
|
||||
skip_hunk = True
|
||||
continue
|
||||
patch_with_lines_str += f'\n{header_line}\n'
|
||||
|
||||
elif not skip_hunk:
|
||||
if side.lower() == 'right' and line_start <= start2 + selected_lines_num <= line_end:
|
||||
selected_lines += line + '\n'
|
||||
if side.lower() == 'left' and start1 <= selected_lines_num + start1 <= line_end:
|
||||
selected_lines += line + '\n'
|
||||
patch_with_lines_str += line + '\n'
|
||||
if not line.startswith('-'): # currently we don't support /ask line for deleted lines
|
||||
selected_lines_num += 1
|
||||
|
||||
return patch_with_lines_str.rstrip(), selected_lines.rstrip()
|
||||
return patch_with_lines_str.strip()
|
||||
|
||||
@ -1,18 +1,19 @@
|
||||
# Language Selection, source: https://github.com/bigcode-project/bigcode-dataset/blob/main/language_selection/programming-languages-to-file-extensions.json # noqa E501
|
||||
from typing import Dict
|
||||
|
||||
from pr_agent.config_loader import get_settings
|
||||
|
||||
from pr_agent.config_loader import settings
|
||||
|
||||
language_extension_map_org = settings.language_extension_map_org
|
||||
language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
|
||||
|
||||
# Bad Extensions, source: https://github.com/EleutherAI/github-downloader/blob/345e7c4cbb9e0dc8a0615fd995a08bf9d73b3fe6/download_repo_text.py # noqa: E501
|
||||
bad_extensions = get_settings().bad_extensions.default
|
||||
if get_settings().config.use_extra_bad_extensions:
|
||||
bad_extensions += get_settings().bad_extensions.extra
|
||||
bad_extensions = settings.bad_extensions.default
|
||||
if settings.config.use_extra_bad_extensions:
|
||||
bad_extensions += settings.bad_extensions.extra
|
||||
|
||||
|
||||
def filter_bad_extensions(files):
|
||||
return [f for f in files if f.filename is not None and is_valid_file(f.filename)]
|
||||
return [f for f in files if is_valid_file(f.filename)]
|
||||
|
||||
|
||||
def is_valid_file(filename):
|
||||
@ -28,8 +29,6 @@ def sort_files_by_main_languages(languages: Dict, files: list):
|
||||
# languages_sorted = sorted(languages, key=lambda x: x[1], reverse=True)
|
||||
# get all extensions for the languages
|
||||
main_extensions = []
|
||||
language_extension_map_org = get_settings().language_extension_map_org
|
||||
language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
|
||||
for language in languages_sorted_list:
|
||||
if language.lower() in language_extension_map:
|
||||
main_extensions.append(language_extension_map[language.lower()])
|
||||
@ -43,11 +42,6 @@ def sort_files_by_main_languages(languages: Dict, files: list):
|
||||
files_sorted = []
|
||||
rest_files = {}
|
||||
|
||||
# if no languages detected, put all files in the "Other" category
|
||||
if not languages:
|
||||
files_sorted = [({"language": "Other", "files": list(files_filtered)})]
|
||||
return files_sorted
|
||||
|
||||
main_extensions_flat = []
|
||||
for ext in main_extensions:
|
||||
main_extensions_flat.extend(ext)
|
||||
|
||||
@ -1,28 +1,24 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import traceback
|
||||
from typing import Callable, List, Tuple
|
||||
|
||||
from github import RateLimitExceededException
|
||||
import logging
|
||||
from typing import Tuple, Union, Callable, List
|
||||
|
||||
from pr_agent.algo import MAX_TOKENS
|
||||
from pr_agent.algo.git_patch_processing import convert_to_hunks_with_lines_numbers, extend_patch, handle_patch_deletions
|
||||
from pr_agent.algo.language_handler import sort_files_by_main_languages
|
||||
from pr_agent.algo.file_filter import filter_ignored
|
||||
from pr_agent.algo.token_handler import TokenHandler
|
||||
from pr_agent.algo.utils import get_max_tokens, clip_tokens, ModelType
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.algo.utils import load_large_diff
|
||||
from pr_agent.config_loader import settings
|
||||
from pr_agent.git_providers.git_provider import GitProvider
|
||||
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
|
||||
from pr_agent.log import get_logger
|
||||
|
||||
DELETED_FILES_ = "Deleted files:\n"
|
||||
|
||||
MORE_MODIFIED_FILES_ = "Additional modified files (insufficient token budget to process):\n"
|
||||
|
||||
ADDED_FILES_ = "Additional added files (insufficient token budget to process):\n"
|
||||
MORE_MODIFIED_FILES_ = "More modified files:\n"
|
||||
|
||||
OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD = 1000
|
||||
OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD = 600
|
||||
PATCH_EXTRA_LINES = 3
|
||||
|
||||
|
||||
def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: str,
|
||||
add_line_numbers_to_hunks: bool = False, disable_extra_lines: bool = False) -> str:
|
||||
@ -30,123 +26,79 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
|
||||
Returns a string with the diff of the pull request, applying diff minimization techniques if needed.
|
||||
|
||||
Args:
|
||||
git_provider (GitProvider): An object of the GitProvider class representing the Git provider used for the pull
|
||||
request.
|
||||
token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the
|
||||
pull request.
|
||||
git_provider (GitProvider): An object of the GitProvider class representing the Git provider used for the pull request.
|
||||
token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the pull request.
|
||||
model (str): The name of the model used for tokenization.
|
||||
add_line_numbers_to_hunks (bool, optional): A boolean indicating whether to add line numbers to the hunks in the
|
||||
diff. Defaults to False.
|
||||
disable_extra_lines (bool, optional): A boolean indicating whether to disable the extension of each patch with
|
||||
extra lines of context. Defaults to False.
|
||||
add_line_numbers_to_hunks (bool, optional): A boolean indicating whether to add line numbers to the hunks in the diff. Defaults to False.
|
||||
disable_extra_lines (bool, optional): A boolean indicating whether to disable the extension of each patch with extra lines of context. Defaults to False.
|
||||
|
||||
Returns:
|
||||
str: A string with the diff of the pull request, applying diff minimization techniques if needed.
|
||||
"""
|
||||
|
||||
if disable_extra_lines:
|
||||
global PATCH_EXTRA_LINES
|
||||
PATCH_EXTRA_LINES = 0
|
||||
else:
|
||||
PATCH_EXTRA_LINES = get_settings().config.patch_extra_lines
|
||||
|
||||
try:
|
||||
diff_files_original = git_provider.get_diff_files()
|
||||
except RateLimitExceededException as e:
|
||||
get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
|
||||
raise
|
||||
|
||||
diff_files = filter_ignored(diff_files_original)
|
||||
if diff_files != diff_files_original:
|
||||
try:
|
||||
get_logger().info(f"Filtered out {len(diff_files_original) - len(diff_files)} files")
|
||||
new_names = set([a.filename for a in diff_files])
|
||||
orig_names = set([a.filename for a in diff_files_original])
|
||||
get_logger().info(f"Filtered out files: {orig_names - new_names}")
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
diff_files = list(git_provider.get_diff_files())
|
||||
|
||||
# get pr languages
|
||||
pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
|
||||
if pr_languages:
|
||||
try:
|
||||
get_logger().info(f"PR main language: {pr_languages[0]['language']}")
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
# generate a standard diff string, with patch extension
|
||||
patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
|
||||
pr_languages, token_handler, add_line_numbers_to_hunks, patch_extra_lines=PATCH_EXTRA_LINES)
|
||||
patches_extended, total_tokens = pr_generate_extended_diff(pr_languages, token_handler,
|
||||
add_line_numbers_to_hunks)
|
||||
|
||||
# if we are under the limit, return the full diff
|
||||
if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < get_max_tokens(model):
|
||||
get_logger().info(f"Tokens: {total_tokens}, total tokens under limit: {get_max_tokens(model)}, "
|
||||
f"returning full diff.")
|
||||
if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < MAX_TOKENS[model]:
|
||||
return "\n".join(patches_extended)
|
||||
|
||||
# if we are over the limit, start pruning
|
||||
get_logger().info(f"Tokens: {total_tokens}, total tokens over limit: {get_max_tokens(model)}, "
|
||||
f"pruning diff.")
|
||||
patches_compressed, modified_file_names, deleted_file_names, added_file_names, total_tokens_new = \
|
||||
pr_generate_compressed_diff(pr_languages, token_handler, model, add_line_numbers_to_hunks)
|
||||
patches_compressed, modified_file_names, deleted_file_names = \
|
||||
pr_generate_compressed_diff(pr_languages, token_handler, add_line_numbers_to_hunks)
|
||||
|
||||
# Insert additional information about added, modified, and deleted files if there is enough space
|
||||
max_tokens = get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD
|
||||
curr_token = total_tokens_new # == token_handler.count_tokens(final_diff)+token_handler.prompt_tokens
|
||||
final_diff = "\n".join(patches_compressed)
|
||||
delta_tokens = 10
|
||||
if added_file_names and (max_tokens - curr_token) > delta_tokens:
|
||||
added_list_str = ADDED_FILES_ + "\n".join(added_file_names)
|
||||
added_list_str = clip_tokens(added_list_str, max_tokens - curr_token)
|
||||
if added_list_str:
|
||||
final_diff = final_diff + "\n\n" + added_list_str
|
||||
curr_token += token_handler.count_tokens(added_list_str) + 2
|
||||
if modified_file_names and (max_tokens - curr_token) > delta_tokens:
|
||||
if modified_file_names:
|
||||
modified_list_str = MORE_MODIFIED_FILES_ + "\n".join(modified_file_names)
|
||||
modified_list_str = clip_tokens(modified_list_str, max_tokens - curr_token)
|
||||
if modified_list_str:
|
||||
final_diff = final_diff + "\n\n" + modified_list_str
|
||||
curr_token += token_handler.count_tokens(modified_list_str) + 2
|
||||
if deleted_file_names and (max_tokens - curr_token) > delta_tokens:
|
||||
final_diff = final_diff + "\n\n" + modified_list_str
|
||||
if deleted_file_names:
|
||||
deleted_list_str = DELETED_FILES_ + "\n".join(deleted_file_names)
|
||||
deleted_list_str = clip_tokens(deleted_list_str, max_tokens - curr_token)
|
||||
if deleted_list_str:
|
||||
final_diff = final_diff + "\n\n" + deleted_list_str
|
||||
try:
|
||||
get_logger().debug(f"After pruning, added_list_str: {added_list_str}, modified_list_str: {modified_list_str}, "
|
||||
f"deleted_list_str: {deleted_list_str}")
|
||||
except Exception as e:
|
||||
pass
|
||||
final_diff = final_diff + "\n\n" + deleted_list_str
|
||||
return final_diff
|
||||
|
||||
|
||||
def pr_generate_extended_diff(pr_languages: list,
|
||||
token_handler: TokenHandler,
|
||||
add_line_numbers_to_hunks: bool,
|
||||
patch_extra_lines: int = 0) -> Tuple[list, int, list]:
|
||||
def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
|
||||
add_line_numbers_to_hunks: bool) -> \
|
||||
Tuple[list, int]:
|
||||
"""
|
||||
Generate a standard diff string with patch extension, while counting the number of tokens used and applying diff
|
||||
minimization techniques if needed.
|
||||
Generate a standard diff string with patch extension, while counting the number of tokens used and applying diff minimization techniques if needed.
|
||||
|
||||
Args:
|
||||
- pr_languages: A list of dictionaries representing the languages used in the pull request and their corresponding
|
||||
files.
|
||||
- pr_languages: A list of dictionaries representing the languages used in the pull request and their corresponding files.
|
||||
- token_handler: An object of the TokenHandler class used for handling tokens in the context of the pull request.
|
||||
- add_line_numbers_to_hunks: A boolean indicating whether to add line numbers to the hunks in the diff.
|
||||
|
||||
Returns:
|
||||
- patches_extended: A list of extended patches for each file in the pull request.
|
||||
- total_tokens: The total number of tokens used in the extended patches.
|
||||
"""
|
||||
total_tokens = token_handler.prompt_tokens # initial tokens
|
||||
patches_extended = []
|
||||
patches_extended_tokens = []
|
||||
for lang in pr_languages:
|
||||
for file in lang['files']:
|
||||
original_file_content_str = file.base_file
|
||||
new_file_content_str = file.head_file
|
||||
patch = file.patch
|
||||
|
||||
# handle the case of large patch, that initially was not loaded
|
||||
patch = load_large_diff(file, new_file_content_str, original_file_content_str, patch)
|
||||
|
||||
if not patch:
|
||||
continue
|
||||
|
||||
# extend each patch with extra lines of context
|
||||
extended_patch = extend_patch(original_file_content_str, patch, num_lines=patch_extra_lines)
|
||||
full_extended_patch = f"\n\n## {file.filename}\n\n{extended_patch}\n"
|
||||
extended_patch = extend_patch(original_file_content_str, patch, num_lines=PATCH_EXTRA_LINES)
|
||||
full_extended_patch = f"## {file.filename}\n\n{extended_patch}\n"
|
||||
|
||||
if add_line_numbers_to_hunks:
|
||||
full_extended_patch = convert_to_hunks_with_lines_numbers(extended_patch, file)
|
||||
@ -154,22 +106,18 @@ def pr_generate_extended_diff(pr_languages: list,
|
||||
patch_tokens = token_handler.count_tokens(full_extended_patch)
|
||||
file.tokens = patch_tokens
|
||||
total_tokens += patch_tokens
|
||||
patches_extended_tokens.append(patch_tokens)
|
||||
patches_extended.append(full_extended_patch)
|
||||
|
||||
return patches_extended, total_tokens, patches_extended_tokens
|
||||
return patches_extended, total_tokens
|
||||
|
||||
|
||||
def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, model: str,
|
||||
convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list, list, int]:
|
||||
convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list]:
|
||||
"""
|
||||
Generate a compressed diff string for a pull request, using diff minimization techniques to reduce the number of
|
||||
tokens used.
|
||||
Generate a compressed diff string for a pull request, using diff minimization techniques to reduce the number of tokens used.
|
||||
Args:
|
||||
top_langs (list): A list of dictionaries representing the languages used in the pull request and their
|
||||
corresponding files.
|
||||
token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the
|
||||
pull request.
|
||||
top_langs (list): A list of dictionaries representing the languages used in the pull request and their corresponding files.
|
||||
token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the pull request.
|
||||
model (str): The model used for tokenization.
|
||||
convert_hunks_to_line_numbers (bool): A boolean indicating whether to convert hunks to line numbers in the diff.
|
||||
Returns:
|
||||
@ -187,7 +135,6 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
|
||||
"""
|
||||
|
||||
patches = []
|
||||
added_files_list = []
|
||||
modified_files_list = []
|
||||
deleted_files_list = []
|
||||
# sort each one of the languages in top_langs by the number of tokens in the diff
|
||||
@ -200,18 +147,18 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
|
||||
original_file_content_str = file.base_file
|
||||
new_file_content_str = file.head_file
|
||||
patch = file.patch
|
||||
patch = load_large_diff(file, new_file_content_str, original_file_content_str, patch)
|
||||
if not patch:
|
||||
continue
|
||||
|
||||
# removing delete-only hunks
|
||||
patch = handle_patch_deletions(patch, original_file_content_str,
|
||||
new_file_content_str, file.filename, file.edit_type)
|
||||
new_file_content_str, file.filename)
|
||||
if patch is None:
|
||||
# if not deleted_files_list:
|
||||
# total_tokens += token_handler.count_tokens(DELETED_FILES_)
|
||||
if file.filename not in deleted_files_list:
|
||||
deleted_files_list.append(file.filename)
|
||||
# total_tokens += token_handler.count_tokens(file.filename) + 1
|
||||
if not deleted_files_list:
|
||||
total_tokens += token_handler.count_tokens(DELETED_FILES_)
|
||||
deleted_files_list.append(file.filename)
|
||||
total_tokens += token_handler.count_tokens(file.filename) + 1
|
||||
continue
|
||||
|
||||
if convert_hunks_to_line_numbers:
|
||||
@ -220,182 +167,46 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
|
||||
new_patch_tokens = token_handler.count_tokens(patch)
|
||||
|
||||
# Hard Stop, no more tokens
|
||||
if total_tokens > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
|
||||
get_logger().warning(f"File was fully skipped, no more tokens: {file.filename}.")
|
||||
if total_tokens > MAX_TOKENS[model] - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
|
||||
logging.warning(f"File was fully skipped, no more tokens: {file.filename}.")
|
||||
continue
|
||||
|
||||
# If the patch is too large, just show the file name
|
||||
if total_tokens + new_patch_tokens > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
|
||||
if total_tokens + new_patch_tokens > MAX_TOKENS[model] - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
|
||||
# Current logic is to skip the patch if it's too large
|
||||
# TODO: Option for alternative logic to remove hunks from the patch to reduce the number of tokens
|
||||
# until we meet the requirements
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().warning(f"Patch too large, minimizing it, {file.filename}")
|
||||
if file.edit_type == EDIT_TYPE.ADDED:
|
||||
# if not added_files_list:
|
||||
# total_tokens += token_handler.count_tokens(ADDED_FILES_)
|
||||
if file.filename not in added_files_list:
|
||||
added_files_list.append(file.filename)
|
||||
# total_tokens += token_handler.count_tokens(file.filename) + 1
|
||||
else:
|
||||
# if not modified_files_list:
|
||||
# total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
|
||||
if file.filename not in modified_files_list:
|
||||
modified_files_list.append(file.filename)
|
||||
# total_tokens += token_handler.count_tokens(file.filename) + 1
|
||||
if settings.config.verbosity_level >= 2:
|
||||
logging.warning(f"Patch too large, minimizing it, {file.filename}")
|
||||
if not modified_files_list:
|
||||
total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
|
||||
modified_files_list.append(file.filename)
|
||||
total_tokens += token_handler.count_tokens(file.filename) + 1
|
||||
continue
|
||||
|
||||
if patch:
|
||||
if not convert_hunks_to_line_numbers:
|
||||
patch_final = f"\n\n## file: '{file.filename.strip()}\n\n{patch.strip()}\n'"
|
||||
patch_final = f"## {file.filename}\n\n{patch}\n"
|
||||
else:
|
||||
patch_final = "\n\n" + patch.strip()
|
||||
patch_final = patch
|
||||
patches.append(patch_final)
|
||||
total_tokens += token_handler.count_tokens(patch_final)
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
|
||||
if settings.config.verbosity_level >= 2:
|
||||
logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
|
||||
|
||||
return patches, modified_files_list, deleted_files_list, added_files_list, total_tokens
|
||||
return patches, modified_files_list, deleted_files_list
|
||||
|
||||
|
||||
async def retry_with_fallback_models(f: Callable, model_type: ModelType = ModelType.REGULAR):
|
||||
all_models = _get_all_models(model_type)
|
||||
all_deployments = _get_all_deployments(all_models)
|
||||
# try each (model, deployment_id) pair until one is successful, otherwise raise exception
|
||||
for i, (model, deployment_id) in enumerate(zip(all_models, all_deployments)):
|
||||
async def retry_with_fallback_models(f: Callable):
|
||||
model = settings.config.model
|
||||
fallback_models = settings.config.fallback_models
|
||||
if not isinstance(fallback_models, list):
|
||||
fallback_models = [fallback_models]
|
||||
all_models = [model] + fallback_models
|
||||
for i, model in enumerate(all_models):
|
||||
try:
|
||||
get_logger().debug(
|
||||
f"Generating prediction with {model}"
|
||||
f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
|
||||
)
|
||||
get_settings().set("openai.deployment_id", deployment_id)
|
||||
return await f(model)
|
||||
except:
|
||||
get_logger().warning(
|
||||
f"Failed to generate prediction with {model}"
|
||||
f"{(' from deployment ' + deployment_id) if deployment_id else ''}: "
|
||||
f"{traceback.format_exc()}"
|
||||
)
|
||||
except Exception as e:
|
||||
logging.warning(f"Failed to generate prediction with {model}: {e}")
|
||||
if i == len(all_models) - 1: # If it's the last iteration
|
||||
raise # Re-raise the last exception
|
||||
|
||||
|
||||
def _get_all_models(model_type: ModelType = ModelType.REGULAR) -> List[str]:
|
||||
if model_type == ModelType.TURBO:
|
||||
model = get_settings().config.model_turbo
|
||||
else:
|
||||
model = get_settings().config.model
|
||||
fallback_models = get_settings().config.fallback_models
|
||||
if not isinstance(fallback_models, list):
|
||||
fallback_models = [m.strip() for m in fallback_models.split(",")]
|
||||
all_models = [model] + fallback_models
|
||||
return all_models
|
||||
|
||||
|
||||
def _get_all_deployments(all_models: List[str]) -> List[str]:
|
||||
deployment_id = get_settings().get("openai.deployment_id", None)
|
||||
fallback_deployments = get_settings().get("openai.fallback_deployments", [])
|
||||
if not isinstance(fallback_deployments, list) and fallback_deployments:
|
||||
fallback_deployments = [d.strip() for d in fallback_deployments.split(",")]
|
||||
if fallback_deployments:
|
||||
all_deployments = [deployment_id] + fallback_deployments
|
||||
if len(all_deployments) < len(all_models):
|
||||
raise ValueError(f"The number of deployments ({len(all_deployments)}) "
|
||||
f"is less than the number of models ({len(all_models)})")
|
||||
else:
|
||||
all_deployments = [deployment_id] * len(all_models)
|
||||
return all_deployments
|
||||
|
||||
|
||||
def get_pr_multi_diffs(git_provider: GitProvider,
|
||||
token_handler: TokenHandler,
|
||||
model: str,
|
||||
max_calls: int = 5) -> List[str]:
|
||||
"""
|
||||
Retrieves the diff files from a Git provider, sorts them by main language, and generates patches for each file.
|
||||
The patches are split into multiple groups based on the maximum number of tokens allowed for the given model.
|
||||
|
||||
Args:
|
||||
git_provider (GitProvider): An object that provides access to Git provider APIs.
|
||||
token_handler (TokenHandler): An object that handles tokens in the context of a pull request.
|
||||
model (str): The name of the model.
|
||||
max_calls (int, optional): The maximum number of calls to retrieve diff files. Defaults to 5.
|
||||
|
||||
Returns:
|
||||
List[str]: A list of final diff strings, split into multiple groups based on the maximum number of tokens allowed for the given model.
|
||||
|
||||
Raises:
|
||||
RateLimitExceededException: If the rate limit for the Git provider API is exceeded.
|
||||
"""
|
||||
try:
|
||||
diff_files = git_provider.get_diff_files()
|
||||
except RateLimitExceededException as e:
|
||||
get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
|
||||
raise
|
||||
|
||||
diff_files = filter_ignored(diff_files)
|
||||
|
||||
# Sort files by main language
|
||||
pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
|
||||
|
||||
# Sort files within each language group by tokens in descending order
|
||||
sorted_files = []
|
||||
for lang in pr_languages:
|
||||
sorted_files.extend(sorted(lang['files'], key=lambda x: x.tokens, reverse=True))
|
||||
|
||||
|
||||
# try first a single run with standard diff string, with patch extension, and no deletions
|
||||
patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
|
||||
pr_languages, token_handler, add_line_numbers_to_hunks=True)
|
||||
if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < get_max_tokens(model):
|
||||
return ["\n".join(patches_extended)]
|
||||
|
||||
patches = []
|
||||
final_diff_list = []
|
||||
total_tokens = token_handler.prompt_tokens
|
||||
call_number = 1
|
||||
for file in sorted_files:
|
||||
if call_number > max_calls:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Reached max calls ({max_calls})")
|
||||
break
|
||||
|
||||
original_file_content_str = file.base_file
|
||||
new_file_content_str = file.head_file
|
||||
patch = file.patch
|
||||
if not patch:
|
||||
continue
|
||||
|
||||
# Remove delete-only hunks
|
||||
patch = handle_patch_deletions(patch, original_file_content_str, new_file_content_str, file.filename, file.edit_type)
|
||||
if patch is None:
|
||||
continue
|
||||
|
||||
patch = convert_to_hunks_with_lines_numbers(patch, file)
|
||||
new_patch_tokens = token_handler.count_tokens(patch)
|
||||
|
||||
if patch and (token_handler.prompt_tokens + new_patch_tokens) > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
|
||||
get_logger().warning(f"Patch too large, skipping: {file.filename}")
|
||||
continue
|
||||
|
||||
if patch and (total_tokens + new_patch_tokens > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD):
|
||||
final_diff = "\n".join(patches)
|
||||
final_diff_list.append(final_diff)
|
||||
patches = []
|
||||
total_tokens = token_handler.prompt_tokens
|
||||
call_number += 1
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Call number: {call_number}")
|
||||
|
||||
if patch:
|
||||
patches.append(patch)
|
||||
total_tokens += new_patch_tokens
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
|
||||
|
||||
# Add the last chunk
|
||||
if patches:
|
||||
final_diff = "\n".join(patches)
|
||||
final_diff_list.append(final_diff)
|
||||
|
||||
return final_diff_list
|
||||
@ -1,24 +1,8 @@
|
||||
from jinja2 import Environment, StrictUndefined
|
||||
from tiktoken import encoding_for_model, get_encoding
|
||||
from pr_agent.config_loader import get_settings
|
||||
from threading import Lock
|
||||
from tiktoken import encoding_for_model
|
||||
|
||||
|
||||
class TokenEncoder:
|
||||
_encoder_instance = None
|
||||
_model = None
|
||||
_lock = Lock() # Create a lock object
|
||||
|
||||
@classmethod
|
||||
def get_token_encoder(cls):
|
||||
model = get_settings().config.model
|
||||
if cls._encoder_instance is None or model != cls._model: # Check without acquiring the lock for performance
|
||||
with cls._lock: # Lock acquisition to ensure thread safety
|
||||
if cls._encoder_instance is None or model != cls._model:
|
||||
cls._model = model
|
||||
cls._encoder_instance = encoding_for_model(cls._model) if "gpt" in cls._model else get_encoding(
|
||||
"cl100k_base")
|
||||
return cls._encoder_instance
|
||||
from pr_agent.algo import MAX_TOKENS
|
||||
from pr_agent.config_loader import settings
|
||||
|
||||
|
||||
class TokenHandler:
|
||||
@ -26,15 +10,12 @@ class TokenHandler:
|
||||
A class for handling tokens in the context of a pull request.
|
||||
|
||||
Attributes:
|
||||
- encoder: An object of the encoding_for_model class from the tiktoken module. Used to encode strings and count the
|
||||
number of tokens in them.
|
||||
- limit: The maximum number of tokens allowed for the given model, as defined in the MAX_TOKENS dictionary in the
|
||||
pr_agent.algo module.
|
||||
- prompt_tokens: The number of tokens in the system and user strings, as calculated by the _get_system_user_tokens
|
||||
method.
|
||||
- encoder: An object of the encoding_for_model class from the tiktoken module. Used to encode strings and count the number of tokens in them.
|
||||
- limit: The maximum number of tokens allowed for the given model, as defined in the MAX_TOKENS dictionary in the pr_agent.algo module.
|
||||
- prompt_tokens: The number of tokens in the system and user strings, as calculated by the _get_system_user_tokens method.
|
||||
"""
|
||||
|
||||
def __init__(self, pr=None, vars: dict = {}, system="", user=""):
|
||||
def __init__(self, pr, vars: dict, system, user):
|
||||
"""
|
||||
Initializes the TokenHandler object.
|
||||
|
||||
@ -44,9 +25,8 @@ class TokenHandler:
|
||||
- system: The system string.
|
||||
- user: The user string.
|
||||
"""
|
||||
self.encoder = TokenEncoder.get_token_encoder()
|
||||
if pr is not None:
|
||||
self.prompt_tokens = self._get_system_user_tokens(pr, self.encoder, vars, system, user)
|
||||
self.encoder = encoding_for_model(settings.config.model)
|
||||
self.prompt_tokens = self._get_system_user_tokens(pr, self.encoder, vars, system, user)
|
||||
|
||||
def _get_system_user_tokens(self, pr, encoder, vars: dict, system, user):
|
||||
"""
|
||||
@ -65,6 +45,7 @@ class TokenHandler:
|
||||
environment = Environment(undefined=StrictUndefined)
|
||||
system_prompt = environment.from_string(system).render(vars)
|
||||
user_prompt = environment.from_string(user).render(vars)
|
||||
|
||||
system_prompt_tokens = len(encoder.encode(system_prompt))
|
||||
user_prompt_tokens = len(encoder.encode(user_prompt))
|
||||
return system_prompt_tokens + user_prompt_tokens
|
||||
|
||||
@ -1,23 +0,0 @@
|
||||
from dataclasses import dataclass
|
||||
from enum import Enum
|
||||
|
||||
|
||||
class EDIT_TYPE(Enum):
|
||||
ADDED = 1
|
||||
DELETED = 2
|
||||
MODIFIED = 3
|
||||
RENAMED = 4
|
||||
UNKNOWN = 5
|
||||
|
||||
|
||||
@dataclass
|
||||
class FilePatchInfo:
|
||||
base_file: str
|
||||
head_file: str
|
||||
patch: str
|
||||
filename: str
|
||||
tokens: int = -1
|
||||
edit_type: EDIT_TYPE = EDIT_TYPE.UNKNOWN
|
||||
old_filename: str = None
|
||||
num_plus_lines: int = -1
|
||||
num_minus_lines: int = -1
|
||||
@ -1,255 +1,85 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import difflib
|
||||
from datetime import datetime
|
||||
import json
|
||||
import os
|
||||
import logging
|
||||
import re
|
||||
import textwrap
|
||||
from datetime import datetime
|
||||
from enum import Enum
|
||||
from typing import Any, List, Tuple
|
||||
|
||||
import yaml
|
||||
from starlette_context import context
|
||||
|
||||
from pr_agent.algo import MAX_TOKENS
|
||||
from pr_agent.algo.token_handler import TokenEncoder
|
||||
from pr_agent.config_loader import get_settings, global_settings
|
||||
from pr_agent.algo.types import FilePatchInfo
|
||||
from pr_agent.log import get_logger
|
||||
|
||||
class ModelType(str, Enum):
|
||||
REGULAR = "regular"
|
||||
TURBO = "turbo"
|
||||
|
||||
def get_setting(key: str) -> Any:
|
||||
try:
|
||||
key = key.upper()
|
||||
return context.get("settings", global_settings).get(key, global_settings.get(key, None))
|
||||
except Exception:
|
||||
return global_settings.get(key, None)
|
||||
from pr_agent.config_loader import settings
|
||||
|
||||
|
||||
def emphasize_header(text: str) -> str:
|
||||
try:
|
||||
# Finding the position of the first occurrence of ": "
|
||||
colon_position = text.find(": ")
|
||||
|
||||
# Splitting the string and wrapping the first part in <strong> tags
|
||||
if colon_position != -1:
|
||||
# Everything before the colon (inclusive) is wrapped in <strong> tags
|
||||
transformed_string = "<strong>" + text[:colon_position + 1] + "</strong>" + text[colon_position + 1:]
|
||||
else:
|
||||
# If there's no ": ", return the original string
|
||||
transformed_string = text
|
||||
|
||||
return transformed_string
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to emphasize header: {e}")
|
||||
return text
|
||||
|
||||
|
||||
def unique_strings(input_list: List[str]) -> List[str]:
|
||||
if not input_list or not isinstance(input_list, list):
|
||||
return input_list
|
||||
seen = set()
|
||||
unique_list = []
|
||||
for item in input_list:
|
||||
if item not in seen:
|
||||
unique_list.append(item)
|
||||
seen.add(item)
|
||||
return unique_list
|
||||
|
||||
|
||||
def convert_to_markdown(output_data: dict, gfm_supported: bool = True, incremental_review=None) -> str:
|
||||
def convert_to_markdown(output_data: dict) -> str:
|
||||
"""
|
||||
Convert a dictionary of data into markdown format.
|
||||
Args:
|
||||
output_data (dict): A dictionary containing data to be converted to markdown format.
|
||||
Returns:
|
||||
str: The markdown formatted text generated from the input dictionary.
|
||||
"""
|
||||
"""
|
||||
markdown_text = ""
|
||||
|
||||
emojis = {
|
||||
"Can be split": "🔀",
|
||||
"Possible issues": "⚡",
|
||||
"Main theme": "🎯",
|
||||
"Type of PR": "📌",
|
||||
"Score": "🏅",
|
||||
"Relevant tests": "🧪",
|
||||
"Relevant tests added": "🧪",
|
||||
"Unrelated changes": "⚠️",
|
||||
"Focused PR": "✨",
|
||||
"Security concerns": "🔒",
|
||||
"General PR suggestions": "💡",
|
||||
"Insights from user's answers": "📝",
|
||||
"Code feedback": "🤖",
|
||||
"Estimated effort to review [1-5]": "⏱️",
|
||||
"Code suggestions": "🤖",
|
||||
}
|
||||
markdown_text = ""
|
||||
if not incremental_review:
|
||||
markdown_text += f"## PR Review 🔍\n\n"
|
||||
else:
|
||||
markdown_text += f"## Incremental PR Review 🔍 \n\n"
|
||||
markdown_text += f"⏮️ Review for commits since previous PR-Agent review {incremental_review}.\n\n"
|
||||
if gfm_supported:
|
||||
markdown_text += "<table>\n<tr>\n"
|
||||
# markdown_text += """<td> Feedback </td> <td></td></tr>"""
|
||||
|
||||
if not output_data or not output_data.get('review', {}):
|
||||
return ""
|
||||
|
||||
for key, value in output_data['review'].items():
|
||||
if value is None or value == '' or value == {} or value == []:
|
||||
if key.lower() != 'can_be_split':
|
||||
continue
|
||||
key_nice = key.replace('_', ' ').capitalize()
|
||||
emoji = emojis.get(key_nice, "")
|
||||
if gfm_supported:
|
||||
if 'Estimated effort to review' in key_nice:
|
||||
key_nice = 'Estimated effort to review [1-5]'
|
||||
if 'security concerns' in key_nice.lower():
|
||||
value = emphasize_header(value.strip())
|
||||
markdown_text += f"<tr><td> {emoji} <strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
|
||||
elif 'can be split' in key_nice.lower():
|
||||
markdown_text += process_can_be_split(emoji, value)
|
||||
elif 'possible issues' in key_nice.lower():
|
||||
value = value.strip()
|
||||
issues = value.split('\n- ')
|
||||
for i, _ in enumerate(issues):
|
||||
issues[i] = issues[i].strip().strip('-').strip()
|
||||
issues = unique_strings(issues) # remove duplicates
|
||||
number_of_issues = len(issues)
|
||||
if number_of_issues > 1:
|
||||
markdown_text += f"<tr><td rowspan={number_of_issues}> {emoji} <strong>{key_nice}</strong></td>\n"
|
||||
for i, issue in enumerate(issues):
|
||||
if not issue:
|
||||
continue
|
||||
issue = emphasize_header(issue)
|
||||
if i == 0:
|
||||
markdown_text += f"<td>\n\n{issue}</td></tr>\n"
|
||||
else:
|
||||
markdown_text += f"<tr>\n<td>\n\n{issue}</td></tr>\n"
|
||||
else:
|
||||
value = emphasize_header(value.strip('-').strip())
|
||||
markdown_text += f"<tr><td> {emoji} <strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
|
||||
else:
|
||||
markdown_text += f"<tr><td> {emoji} <strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
|
||||
else:
|
||||
if len(value.split()) > 1:
|
||||
markdown_text += f"{emoji} **{key_nice}:**\n\n {value}\n\n"
|
||||
else:
|
||||
markdown_text += f"{emoji} **{key_nice}:** {value}\n\n"
|
||||
if gfm_supported:
|
||||
markdown_text += "</table>\n"
|
||||
|
||||
if 'code_feedback' in output_data:
|
||||
if gfm_supported:
|
||||
markdown_text += f"\n\n"
|
||||
markdown_text += f"<details><summary> <strong>Code feedback:</strong></summary>\n\n"
|
||||
markdown_text += "<hr>"
|
||||
else:
|
||||
markdown_text += f"\n\n** Code feedback:**\n\n"
|
||||
for i, value in enumerate(output_data['code_feedback']):
|
||||
if value is None or value == '' or value == {} or value == []:
|
||||
continue
|
||||
markdown_text += parse_code_suggestion(value, i, gfm_supported)+"\n\n"
|
||||
if markdown_text.endswith('<hr>'):
|
||||
markdown_text = markdown_text[:-4]
|
||||
if gfm_supported:
|
||||
markdown_text += f"</details>"
|
||||
#print(markdown_text)
|
||||
|
||||
|
||||
for key, value in output_data.items():
|
||||
if not value:
|
||||
continue
|
||||
if isinstance(value, dict):
|
||||
markdown_text += f"## {key}\n\n"
|
||||
markdown_text += convert_to_markdown(value)
|
||||
elif isinstance(value, list):
|
||||
if key.lower() == 'code suggestions':
|
||||
markdown_text += "\n" # just looks nicer with additional line breaks
|
||||
emoji = emojis.get(key, "")
|
||||
markdown_text += f"- {emoji} **{key}:**\n\n"
|
||||
for item in value:
|
||||
if isinstance(item, dict) and key.lower() == 'code suggestions':
|
||||
markdown_text += parse_code_suggestion(item)
|
||||
elif item:
|
||||
markdown_text += f" - {item}\n"
|
||||
elif value != 'n/a':
|
||||
emoji = emojis.get(key, "")
|
||||
markdown_text += f"- {emoji} **{key}:** {value}\n"
|
||||
return markdown_text
|
||||
|
||||
|
||||
def process_can_be_split(emoji, value):
|
||||
# key_nice = "Can this PR be split?"
|
||||
key_nice = "Multiple PR themes"
|
||||
markdown_text = ""
|
||||
if not value or isinstance(value, list) and len(value) == 1:
|
||||
value = "No"
|
||||
markdown_text += f"<tr><td> {emoji} <strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
|
||||
else:
|
||||
number_of_splits = len(value)
|
||||
markdown_text += f"<tr><td rowspan={number_of_splits}> {emoji} <strong>{key_nice}</strong></td>\n"
|
||||
for i, split in enumerate(value):
|
||||
title = split.get('title', '')
|
||||
relevant_files = split.get('relevant_files', [])
|
||||
if i == 0:
|
||||
markdown_text += f"<td><details><summary>\nSub-PR theme: <strong>{title}</strong></summary>\n\n"
|
||||
markdown_text += f"<hr>\n"
|
||||
markdown_text += f"Relevant files:\n"
|
||||
markdown_text += f"<ul>\n"
|
||||
for file in relevant_files:
|
||||
markdown_text += f"<li>{file}</li>\n"
|
||||
markdown_text += f"</ul>\n\n</details></td></tr>\n"
|
||||
else:
|
||||
markdown_text += f"<tr>\n<td><details><summary>\nSub-PR theme: <strong>{title}</strong></summary>\n\n"
|
||||
markdown_text += f"<hr>\n"
|
||||
markdown_text += f"Relevant files:\n"
|
||||
markdown_text += f"<ul>\n"
|
||||
for file in relevant_files:
|
||||
markdown_text += f"<li>{file}</li>\n"
|
||||
markdown_text += f"</ul>\n\n</details></td></tr>\n"
|
||||
return markdown_text
|
||||
|
||||
|
||||
def parse_code_suggestion(code_suggestion: dict, i: int = 0, gfm_supported: bool = True) -> str:
|
||||
def parse_code_suggestion(code_suggestions: dict) -> str:
|
||||
"""
|
||||
Convert a dictionary of data into markdown format.
|
||||
|
||||
Args:
|
||||
code_suggestion (dict): A dictionary containing data to be converted to markdown format.
|
||||
code_suggestions (dict): A dictionary containing data to be converted to markdown format.
|
||||
|
||||
Returns:
|
||||
str: A string containing the markdown formatted text generated from the input dictionary.
|
||||
"""
|
||||
markdown_text = ""
|
||||
if gfm_supported and 'relevant_line' in code_suggestion:
|
||||
markdown_text += '<table>'
|
||||
for sub_key, sub_value in code_suggestion.items():
|
||||
try:
|
||||
if sub_key.lower() == 'relevant_file':
|
||||
relevant_file = sub_value.strip('`').strip('"').strip("'")
|
||||
markdown_text += f"<tr><td>relevant file</td><td>{relevant_file}</td></tr>"
|
||||
# continue
|
||||
elif sub_key.lower() == 'suggestion':
|
||||
markdown_text += (f"<tr><td>{sub_key} </td>"
|
||||
f"<td>\n\n<strong>\n\n{sub_value.strip()}\n\n</strong>\n</td></tr>")
|
||||
elif sub_key.lower() == 'relevant_line':
|
||||
markdown_text += f"<tr><td>relevant line</td>"
|
||||
sub_value_list = sub_value.split('](')
|
||||
relevant_line = sub_value_list[0].lstrip('`').lstrip('[')
|
||||
if len(sub_value_list) > 1:
|
||||
link = sub_value_list[1].rstrip(')').strip('`')
|
||||
markdown_text += f"<td><a href='{link}'>{relevant_line}</a></td>"
|
||||
else:
|
||||
markdown_text += f"<td>{relevant_line}</td>"
|
||||
markdown_text += "</tr>"
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to parse code suggestion: {e}")
|
||||
pass
|
||||
markdown_text += '</table>'
|
||||
markdown_text += "<hr>"
|
||||
else:
|
||||
for sub_key, sub_value in code_suggestion.items():
|
||||
if isinstance(sub_key, str):
|
||||
sub_key = sub_key.rstrip()
|
||||
if isinstance(sub_value,str):
|
||||
sub_value = sub_value.rstrip()
|
||||
if isinstance(sub_value, dict): # "code example"
|
||||
markdown_text += f" - **{sub_key}:**\n"
|
||||
for code_key, code_value in sub_value.items(): # 'before' and 'after' code
|
||||
code_str = f"```\n{code_value}\n```"
|
||||
code_str_indented = textwrap.indent(code_str, ' ')
|
||||
markdown_text += f" - **{code_key}:**\n{code_str_indented}\n"
|
||||
for sub_key, sub_value in code_suggestions.items():
|
||||
if isinstance(sub_value, dict): # "code example"
|
||||
markdown_text += f" - **{sub_key}:**\n"
|
||||
for code_key, code_value in sub_value.items(): # 'before' and 'after' code
|
||||
code_str = f"```\n{code_value}\n```"
|
||||
code_str_indented = textwrap.indent(code_str, ' ')
|
||||
markdown_text += f" - **{code_key}:**\n{code_str_indented}\n"
|
||||
else:
|
||||
if "relevant file" in sub_key.lower():
|
||||
markdown_text += f"\n - **{sub_key}:** {sub_value}\n"
|
||||
else:
|
||||
if "relevant_file" in sub_key.lower():
|
||||
markdown_text += f"\n - **{sub_key}:** {sub_value} \n"
|
||||
else:
|
||||
markdown_text += f" **{sub_key}:** {sub_value} \n"
|
||||
if "relevant_line" not in sub_key.lower(): # nicer presentation
|
||||
# markdown_text = markdown_text.rstrip('\n') + "\\\n" # works for gitlab
|
||||
markdown_text = markdown_text.rstrip('\n') + " \n" # works for gitlab and bitbucker
|
||||
markdown_text += f" **{sub_key}:** {sub_value}\n"
|
||||
|
||||
markdown_text += "\n"
|
||||
markdown_text += "\n"
|
||||
return markdown_text
|
||||
|
||||
|
||||
@ -260,22 +90,18 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
|
||||
Args:
|
||||
- review: A string containing the JSON message to be fixed.
|
||||
- max_iter: An integer representing the maximum number of iterations to try and fix the JSON message.
|
||||
- code_suggestions: A boolean indicating whether to try and fix JSON messages with code feedback.
|
||||
- code_suggestions: A boolean indicating whether to try and fix JSON messages with code suggestions.
|
||||
|
||||
Returns:
|
||||
- data: A dictionary containing the parsed JSON data.
|
||||
|
||||
The function attempts to fix broken or incomplete JSON messages by parsing until the last valid code suggestion.
|
||||
If the JSON message ends with a closing bracket, the function calls the fix_json_escape_char function to fix the
|
||||
message.
|
||||
If code_suggestions is True and the JSON message contains code feedback, the function tries to fix the JSON
|
||||
message by parsing until the last valid code suggestion.
|
||||
The function uses regular expressions to find the last occurrence of "}," with any number of whitespaces or
|
||||
newlines.
|
||||
If the JSON message ends with a closing bracket, the function calls the fix_json_escape_char function to fix the message.
|
||||
If code_suggestions is True and the JSON message contains code suggestions, the function tries to fix the JSON message by parsing until the last valid code suggestion.
|
||||
The function uses regular expressions to find the last occurrence of "}," with any number of whitespaces or newlines.
|
||||
It tries to parse the JSON message with the closing bracket and checks if it is valid.
|
||||
If the JSON message is valid, the parsed JSON data is returned.
|
||||
If the JSON message is not valid, the last code suggestion is removed and the process is repeated until a valid JSON
|
||||
message is obtained or the maximum number of iterations is reached.
|
||||
If the JSON message is not valid, the last code suggestion is removed and the process is repeated until a valid JSON message is obtained or the maximum number of iterations is reached.
|
||||
If a valid JSON message is not obtained, an error is logged and an empty dictionary is returned.
|
||||
"""
|
||||
|
||||
@ -288,8 +114,7 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
|
||||
else:
|
||||
closing_bracket = "]}}"
|
||||
|
||||
if (review.rfind("'Code feedback': [") > 0 or review.rfind('"Code feedback": [') > 0) or \
|
||||
(review.rfind("'Code suggestions': [") > 0 or review.rfind('"Code suggestions": [') > 0) :
|
||||
if review.rfind("'Code suggestions': [") > 0 or review.rfind('"Code suggestions": [') > 0:
|
||||
last_code_suggestion_ind = [m.end() for m in re.finditer(r"\}\s*,", review)][-1] - 1
|
||||
valid_json = False
|
||||
iter_count = 0
|
||||
@ -305,7 +130,7 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
|
||||
iter_count += 1
|
||||
|
||||
if not valid_json:
|
||||
get_logger().error("Unable to decode JSON response from AI")
|
||||
logging.error("Unable to decode JSON response from AI")
|
||||
data = {}
|
||||
|
||||
return data
|
||||
@ -324,7 +149,7 @@ def fix_json_escape_char(json_message=None):
|
||||
Raises:
|
||||
None
|
||||
|
||||
"""
|
||||
"""
|
||||
try:
|
||||
result = json.loads(json_message)
|
||||
except Exception as e:
|
||||
@ -351,326 +176,38 @@ def convert_str_to_datetime(date_str):
|
||||
Example:
|
||||
>>> convert_str_to_datetime('Mon, 01 Jan 2022 12:00:00 UTC')
|
||||
datetime.datetime(2022, 1, 1, 12, 0, 0)
|
||||
"""
|
||||
"""
|
||||
datetime_format = '%a, %d %b %Y %H:%M:%S %Z'
|
||||
return datetime.strptime(date_str, datetime_format)
|
||||
|
||||
|
||||
def load_large_diff(filename, new_file_content_str: str, original_file_content_str: str) -> str:
|
||||
def load_large_diff(file, new_file_content_str: str, original_file_content_str: str, patch: str) -> str:
|
||||
"""
|
||||
Generate a patch for a modified file by comparing the original content of the file with the new content provided as
|
||||
input.
|
||||
Generate a patch for a modified file by comparing the original content of the file with the new content provided as input.
|
||||
|
||||
Args:
|
||||
file: The file object for which the patch needs to be generated.
|
||||
new_file_content_str: The new content of the file as a string.
|
||||
original_file_content_str: The original content of the file as a string.
|
||||
patch: An optional patch string that can be provided as input.
|
||||
|
||||
Returns:
|
||||
The generated or provided patch string.
|
||||
|
||||
Raises:
|
||||
None.
|
||||
|
||||
Additional Information:
|
||||
- If 'patch' is not provided as input, the function generates a patch using the 'difflib' library and returns it as output.
|
||||
- If the 'settings.config.verbosity_level' is greater than or equal to 2, a warning message is logged indicating that the file was modified but no patch was found, and a patch is manually created.
|
||||
"""
|
||||
patch = ""
|
||||
try:
|
||||
diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
|
||||
new_file_content_str.splitlines(keepends=True))
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
|
||||
patch = ''.join(diff)
|
||||
except Exception:
|
||||
pass
|
||||
if not patch: # to Do - also add condition for file extension
|
||||
try:
|
||||
diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
|
||||
new_file_content_str.splitlines(keepends=True))
|
||||
if settings.config.verbosity_level >= 2:
|
||||
logging.warning(f"File was modified, but no patch was found. Manually creating patch: {file.filename}.")
|
||||
patch = ''.join(diff)
|
||||
except Exception:
|
||||
pass
|
||||
return patch
|
||||
|
||||
|
||||
def update_settings_from_args(args: List[str]) -> List[str]:
|
||||
"""
|
||||
Update the settings of the Dynaconf object based on the arguments passed to the function.
|
||||
|
||||
Args:
|
||||
args: A list of arguments passed to the function.
|
||||
Example args: ['--pr_code_suggestions.extra_instructions="be funny',
|
||||
'--pr_code_suggestions.num_code_suggestions=3']
|
||||
|
||||
Returns:
|
||||
None
|
||||
|
||||
Raises:
|
||||
ValueError: If the argument is not in the correct format.
|
||||
|
||||
"""
|
||||
other_args = []
|
||||
if args:
|
||||
for arg in args:
|
||||
arg = arg.strip()
|
||||
if arg.startswith('--'):
|
||||
arg = arg.strip('-').strip()
|
||||
vals = arg.split('=', 1)
|
||||
if len(vals) != 2:
|
||||
if len(vals) > 2: # --extended is a valid argument
|
||||
get_logger().error(f'Invalid argument format: {arg}')
|
||||
other_args.append(arg)
|
||||
continue
|
||||
key, value = _fix_key_value(*vals)
|
||||
get_settings().set(key, value)
|
||||
get_logger().info(f'Updated setting {key} to: "{value}"')
|
||||
else:
|
||||
other_args.append(arg)
|
||||
return other_args
|
||||
|
||||
|
||||
def _fix_key_value(key: str, value: str):
|
||||
key = key.strip().upper()
|
||||
value = value.strip()
|
||||
try:
|
||||
value = yaml.safe_load(value)
|
||||
except Exception as e:
|
||||
get_logger().debug(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
|
||||
return key, value
|
||||
|
||||
|
||||
def load_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
|
||||
response_text = response_text.removeprefix('```yaml').rstrip('`')
|
||||
try:
|
||||
data = yaml.safe_load(response_text)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to parse AI prediction: {e}")
|
||||
data = try_fix_yaml(response_text, keys_fix_yaml=keys_fix_yaml)
|
||||
return data
|
||||
|
||||
|
||||
def try_fix_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
|
||||
response_text_lines = response_text.split('\n')
|
||||
|
||||
keys = ['relevant line:', 'suggestion content:', 'relevant file:', 'existing code:', 'improved code:']
|
||||
keys = keys + keys_fix_yaml
|
||||
# first fallback - try to convert 'relevant line: ...' to relevant line: |-\n ...'
|
||||
response_text_lines_copy = response_text_lines.copy()
|
||||
for i in range(0, len(response_text_lines_copy)):
|
||||
for key in keys:
|
||||
if key in response_text_lines_copy[i] and not '|-' in response_text_lines_copy[i]:
|
||||
response_text_lines_copy[i] = response_text_lines_copy[i].replace(f'{key}',
|
||||
f'{key} |-\n ')
|
||||
try:
|
||||
data = yaml.safe_load('\n'.join(response_text_lines_copy))
|
||||
get_logger().info(f"Successfully parsed AI prediction after adding |-\n")
|
||||
return data
|
||||
except:
|
||||
get_logger().info(f"Failed to parse AI prediction after adding |-\n")
|
||||
|
||||
# second fallback - try to extract only range from first ```yaml to ````
|
||||
snippet_pattern = r'```(yaml)?[\s\S]*?```'
|
||||
snippet = re.search(snippet_pattern, '\n'.join(response_text_lines_copy))
|
||||
if snippet:
|
||||
snippet_text = snippet.group()
|
||||
try:
|
||||
data = yaml.safe_load(snippet_text.removeprefix('```yaml').rstrip('`'))
|
||||
get_logger().info(f"Successfully parsed AI prediction after extracting yaml snippet")
|
||||
return data
|
||||
except:
|
||||
pass
|
||||
|
||||
# third fallback - try to remove leading and trailing curly brackets
|
||||
response_text_copy = response_text.strip().rstrip().removeprefix('{').removesuffix('}').rstrip(':\n')
|
||||
try:
|
||||
data = yaml.safe_load(response_text_copy)
|
||||
get_logger().info(f"Successfully parsed AI prediction after removing curly brackets")
|
||||
return data
|
||||
except:
|
||||
pass
|
||||
|
||||
# fourth fallback - try to remove last lines
|
||||
data = {}
|
||||
for i in range(1, len(response_text_lines)):
|
||||
response_text_lines_tmp = '\n'.join(response_text_lines[:-i])
|
||||
try:
|
||||
data = yaml.safe_load(response_text_lines_tmp)
|
||||
get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
|
||||
return data
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
def set_custom_labels(variables, git_provider=None):
|
||||
if not get_settings().config.enable_custom_labels:
|
||||
return
|
||||
|
||||
labels = get_settings().custom_labels
|
||||
if not labels:
|
||||
# set default labels
|
||||
labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']
|
||||
labels_list = "\n - ".join(labels) if labels else ""
|
||||
labels_list = f" - {labels_list}" if labels_list else ""
|
||||
variables["custom_labels"] = labels_list
|
||||
return
|
||||
|
||||
# Set custom labels
|
||||
variables["custom_labels_class"] = "class Label(str, Enum):"
|
||||
counter = 0
|
||||
labels_minimal_to_labels_dict = {}
|
||||
for k, v in labels.items():
|
||||
description = "'" + v['description'].strip('\n').replace('\n', '\\n') + "'"
|
||||
# variables["custom_labels_class"] += f"\n {k.lower().replace(' ', '_')} = '{k}' # {description}"
|
||||
variables["custom_labels_class"] += f"\n {k.lower().replace(' ', '_')} = {description}"
|
||||
labels_minimal_to_labels_dict[k.lower().replace(' ', '_')] = k
|
||||
counter += 1
|
||||
variables["labels_minimal_to_labels_dict"] = labels_minimal_to_labels_dict
|
||||
|
||||
def get_user_labels(current_labels: List[str] = None):
|
||||
"""
|
||||
Only keep labels that has been added by the user
|
||||
"""
|
||||
try:
|
||||
if current_labels is None:
|
||||
current_labels = []
|
||||
user_labels = []
|
||||
for label in current_labels:
|
||||
if label.lower() in ['bug fix', 'tests', 'enhancement', 'documentation', 'other']:
|
||||
continue
|
||||
if get_settings().config.enable_custom_labels:
|
||||
if label in get_settings().custom_labels:
|
||||
continue
|
||||
user_labels.append(label)
|
||||
if user_labels:
|
||||
get_logger().debug(f"Keeping user labels: {user_labels}")
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to get user labels: {e}")
|
||||
return current_labels
|
||||
return user_labels
|
||||
|
||||
|
||||
def get_max_tokens(model):
|
||||
settings = get_settings()
|
||||
if model in MAX_TOKENS:
|
||||
max_tokens_model = MAX_TOKENS[model]
|
||||
else:
|
||||
raise Exception(f"MAX_TOKENS must be set for model {model} in ./pr_agent/algo/__init__.py")
|
||||
|
||||
if settings.config.max_model_tokens:
|
||||
max_tokens_model = min(settings.config.max_model_tokens, max_tokens_model)
|
||||
# get_logger().debug(f"limiting max tokens to {max_tokens_model}")
|
||||
return max_tokens_model
|
||||
|
||||
|
||||
def clip_tokens(text: str, max_tokens: int, add_three_dots=True) -> str:
|
||||
"""
|
||||
Clip the number of tokens in a string to a maximum number of tokens.
|
||||
|
||||
Args:
|
||||
text (str): The string to clip.
|
||||
max_tokens (int): The maximum number of tokens allowed in the string.
|
||||
add_three_dots (bool, optional): A boolean indicating whether to add three dots at the end of the clipped
|
||||
Returns:
|
||||
str: The clipped string.
|
||||
"""
|
||||
if not text:
|
||||
return text
|
||||
|
||||
try:
|
||||
encoder = TokenEncoder.get_token_encoder()
|
||||
num_input_tokens = len(encoder.encode(text))
|
||||
if num_input_tokens <= max_tokens:
|
||||
return text
|
||||
num_chars = len(text)
|
||||
chars_per_token = num_chars / num_input_tokens
|
||||
num_output_chars = int(chars_per_token * max_tokens)
|
||||
clipped_text = text[:num_output_chars]
|
||||
if add_three_dots:
|
||||
clipped_text += "\n...(truncated)"
|
||||
return clipped_text
|
||||
except Exception as e:
|
||||
get_logger().warning(f"Failed to clip tokens: {e}")
|
||||
return text
|
||||
|
||||
def replace_code_tags(text):
|
||||
"""
|
||||
Replace odd instances of ` with <code> and even instances of ` with </code>
|
||||
"""
|
||||
parts = text.split('`')
|
||||
for i in range(1, len(parts), 2):
|
||||
parts[i] = '<code>' + parts[i] + '</code>'
|
||||
return ''.join(parts)
|
||||
|
||||
|
||||
def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
|
||||
relevant_file: str,
|
||||
relevant_line_in_file: str,
|
||||
absolute_position: int = None) -> Tuple[int, int]:
|
||||
position = -1
|
||||
if absolute_position is None:
|
||||
absolute_position = -1
|
||||
re_hunk_header = re.compile(
|
||||
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
|
||||
|
||||
for file in diff_files:
|
||||
if file.filename and (file.filename.strip() == relevant_file):
|
||||
patch = file.patch
|
||||
patch_lines = patch.splitlines()
|
||||
delta = 0
|
||||
start1, size1, start2, size2 = 0, 0, 0, 0
|
||||
if absolute_position != -1: # matching absolute to relative
|
||||
for i, line in enumerate(patch_lines):
|
||||
# new hunk
|
||||
if line.startswith('@@'):
|
||||
delta = 0
|
||||
match = re_hunk_header.match(line)
|
||||
start1, size1, start2, size2 = map(int, match.groups()[:4])
|
||||
elif not line.startswith('-'):
|
||||
delta += 1
|
||||
|
||||
#
|
||||
absolute_position_curr = start2 + delta - 1
|
||||
|
||||
if absolute_position_curr == absolute_position:
|
||||
position = i
|
||||
break
|
||||
else:
|
||||
# try to find the line in the patch using difflib, with some margin of error
|
||||
matches_difflib: list[str | Any] = difflib.get_close_matches(relevant_line_in_file,
|
||||
patch_lines, n=3, cutoff=0.93)
|
||||
if len(matches_difflib) == 1 and matches_difflib[0].startswith('+'):
|
||||
relevant_line_in_file = matches_difflib[0]
|
||||
|
||||
|
||||
for i, line in enumerate(patch_lines):
|
||||
if line.startswith('@@'):
|
||||
delta = 0
|
||||
match = re_hunk_header.match(line)
|
||||
start1, size1, start2, size2 = map(int, match.groups()[:4])
|
||||
elif not line.startswith('-'):
|
||||
delta += 1
|
||||
|
||||
if relevant_line_in_file in line and line[0] != '-':
|
||||
position = i
|
||||
absolute_position = start2 + delta - 1
|
||||
break
|
||||
|
||||
if position == -1 and relevant_line_in_file[0] == '+':
|
||||
no_plus_line = relevant_line_in_file[1:].lstrip()
|
||||
for i, line in enumerate(patch_lines):
|
||||
if line.startswith('@@'):
|
||||
delta = 0
|
||||
match = re_hunk_header.match(line)
|
||||
start1, size1, start2, size2 = map(int, match.groups()[:4])
|
||||
elif not line.startswith('-'):
|
||||
delta += 1
|
||||
|
||||
if no_plus_line in line and line[0] != '-':
|
||||
# The model might add a '+' to the beginning of the relevant_line_in_file even if originally
|
||||
# it's a context line
|
||||
position = i
|
||||
absolute_position = start2 + delta - 1
|
||||
break
|
||||
return position, absolute_position
|
||||
|
||||
def github_action_output(output_data: dict, key_name: str):
|
||||
try:
|
||||
if not get_settings().get('github_action_config.enable_output', False):
|
||||
return
|
||||
|
||||
key_data = output_data.get(key_name, {})
|
||||
with open(os.environ['GITHUB_OUTPUT'], 'a') as fh:
|
||||
print(f"{key_name}={json.dumps(key_data, indent=None, ensure_ascii=False)}", file=fh)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to write to GitHub Action output: {e}")
|
||||
return
|
||||
149
pr_agent/cli.py
149
pr_agent/cli.py
@ -1,80 +1,101 @@
|
||||
import argparse
|
||||
import asyncio
|
||||
import logging
|
||||
import os
|
||||
|
||||
from pr_agent.agent.pr_agent import PRAgent, commands
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.log import setup_logger
|
||||
from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
|
||||
from pr_agent.tools.pr_description import PRDescription
|
||||
from pr_agent.tools.pr_information_from_user import PRInformationFromUser
|
||||
from pr_agent.tools.pr_questions import PRQuestions
|
||||
from pr_agent.tools.pr_reviewer import PRReviewer
|
||||
|
||||
log_level = os.environ.get("LOG_LEVEL", "INFO")
|
||||
setup_logger(log_level)
|
||||
|
||||
def set_parser():
|
||||
def run(args=None):
|
||||
parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage=
|
||||
"""\
|
||||
Usage: cli.py --pr-url=<URL on supported git hosting service> <command> [<args>].
|
||||
For example:
|
||||
- cli.py --pr_url=... review
|
||||
- cli.py --pr_url=... describe
|
||||
- cli.py --pr_url=... improve
|
||||
- cli.py --pr_url=... ask "write me a poem about this PR"
|
||||
- cli.py --pr_url=... reflect
|
||||
- cli.py --issue_url=... similar_issue
|
||||
"""\
|
||||
Usage: cli.py --pr-url <URL on supported git hosting service> <command> [<args>].
|
||||
For example:
|
||||
- cli.py --pr-url=... review
|
||||
- cli.py --pr-url=... describe
|
||||
- cli.py --pr-url=... improve
|
||||
- cli.py --pr-url=... ask "write me a poem about this PR"
|
||||
- cli.py --pr-url=... reflect
|
||||
|
||||
Supported commands:
|
||||
- review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
|
||||
|
||||
- ask / ask_question [question] - Ask a question about the PR.
|
||||
|
||||
- describe / describe_pr - Modify the PR title and description based on the PR's contents.
|
||||
|
||||
- improve / improve_code - Suggest improvements to the code in the PR as pull request comments ready to commit.
|
||||
Extended mode ('improve --extended') employs several calls, and provides a more thorough feedback
|
||||
|
||||
- reflect - Ask the PR author questions about the PR.
|
||||
|
||||
- update_changelog - Update the changelog based on the PR's contents.
|
||||
|
||||
- add_docs
|
||||
|
||||
- generate_labels
|
||||
|
||||
|
||||
Configuration:
|
||||
To edit any configuration parameter from 'configuration.toml', just add -config_path=<value>.
|
||||
For example: 'python cli.py --pr_url=... review --pr_reviewer.extra_instructions="focus on the file: ..."'
|
||||
""")
|
||||
parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', default=None)
|
||||
parser.add_argument('--issue_url', type=str, help='The URL of the Issue to review', default=None)
|
||||
parser.add_argument('command', type=str, help='The', choices=commands, default='review')
|
||||
Supported commands:
|
||||
review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
|
||||
ask / ask_question [question] - Ask a question about the PR.
|
||||
describe / describe_pr - Modify the PR title and description based on the PR's contents.
|
||||
improve / improve_code - Suggest improvements to the code in the PR as pull request comments ready to commit.
|
||||
reflect - Ask the PR author questions about the PR.
|
||||
""")
|
||||
parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', required=True)
|
||||
parser.add_argument('command', type=str, help='The', choices=['review', 'review_pr',
|
||||
'ask', 'ask_question',
|
||||
'describe', 'describe_pr',
|
||||
'improve', 'improve_code',
|
||||
'reflect', 'review_after_reflect'],
|
||||
default='review')
|
||||
parser.add_argument('rest', nargs=argparse.REMAINDER, default=[])
|
||||
return parser
|
||||
|
||||
def run_command(pr_url, command):
|
||||
# Preparing the command
|
||||
run_command_str = f"--pr_url={pr_url} {command.lstrip('/')}"
|
||||
args = set_parser().parse_args(run_command_str.split())
|
||||
|
||||
# Run the command. Feedback will appear in GitHub PR comments
|
||||
run(args=args)
|
||||
|
||||
def run(inargs=None, args=None):
|
||||
parser = set_parser()
|
||||
if not args:
|
||||
args = parser.parse_args(inargs)
|
||||
if not args.pr_url and not args.issue_url:
|
||||
parser.print_help()
|
||||
return
|
||||
|
||||
args = parser.parse_args(args)
|
||||
logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
|
||||
command = args.command.lower()
|
||||
get_settings().set("CONFIG.CLI_MODE", True)
|
||||
if args.issue_url:
|
||||
result = asyncio.run(PRAgent().handle_request(args.issue_url, [command] + args.rest))
|
||||
commands = {
|
||||
'ask': _handle_ask_command,
|
||||
'ask_question': _handle_ask_command,
|
||||
'describe': _handle_describe_command,
|
||||
'describe_pr': _handle_describe_command,
|
||||
'improve': _handle_improve_command,
|
||||
'improve_code': _handle_improve_command,
|
||||
'review': _handle_review_command,
|
||||
'review_pr': _handle_review_command,
|
||||
'reflect': _handle_reflect_command,
|
||||
'review_after_reflect': _handle_review_after_reflect_command
|
||||
}
|
||||
if command in commands:
|
||||
commands[command](args.pr_url, args.rest)
|
||||
else:
|
||||
result = asyncio.run(PRAgent().handle_request(args.pr_url, [command] + args.rest))
|
||||
if not result:
|
||||
print(f"Unknown command: {command}")
|
||||
parser.print_help()
|
||||
|
||||
|
||||
def _handle_ask_command(pr_url: str, rest: list):
|
||||
if len(rest) == 0:
|
||||
print("Please specify a question")
|
||||
return
|
||||
print(f"Question: {' '.join(rest)} about PR {pr_url}")
|
||||
reviewer = PRQuestions(pr_url, rest)
|
||||
asyncio.run(reviewer.answer())
|
||||
|
||||
|
||||
def _handle_describe_command(pr_url: str, rest: list):
|
||||
print(f"PR description: {pr_url}")
|
||||
reviewer = PRDescription(pr_url)
|
||||
asyncio.run(reviewer.describe())
|
||||
|
||||
|
||||
def _handle_improve_command(pr_url: str, rest: list):
|
||||
print(f"PR code suggestions: {pr_url}")
|
||||
reviewer = PRCodeSuggestions(pr_url)
|
||||
asyncio.run(reviewer.suggest())
|
||||
|
||||
|
||||
def _handle_review_command(pr_url: str, rest: list):
|
||||
print(f"Reviewing PR: {pr_url}")
|
||||
reviewer = PRReviewer(pr_url, cli_mode=True, args=rest)
|
||||
asyncio.run(reviewer.review())
|
||||
|
||||
|
||||
def _handle_reflect_command(pr_url: str, rest: list):
|
||||
print(f"Asking the PR author questions: {pr_url}")
|
||||
reviewer = PRInformationFromUser(pr_url)
|
||||
asyncio.run(reviewer.generate_questions())
|
||||
|
||||
|
||||
def _handle_review_after_reflect_command(pr_url: str, rest: list):
|
||||
print(f"Processing author's answers and sending review: {pr_url}")
|
||||
reviewer = PRReviewer(pr_url, cli_mode=True, is_answer=True)
|
||||
asyncio.run(reviewer.review())
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
run()
|
||||
|
||||
@ -1,23 +0,0 @@
|
||||
from pr_agent import cli
|
||||
from pr_agent.config_loader import get_settings
|
||||
|
||||
|
||||
def main():
|
||||
# Fill in the following values
|
||||
provider = "github" # GitHub provider
|
||||
user_token = "..." # GitHub user token
|
||||
openai_key = "..." # OpenAI key
|
||||
pr_url = "..." # PR URL, for example 'https://github.com/Codium-ai/pr-agent/pull/809'
|
||||
command = "/review" # Command to run (e.g. '/review', '/describe', '/ask="What is the purpose of this PR?"')
|
||||
|
||||
# Setting the configurations
|
||||
get_settings().set("CONFIG.git_provider", provider)
|
||||
get_settings().set("openai.key", openai_key)
|
||||
get_settings().set("github.user_token", user_token)
|
||||
|
||||
# Run the command. Feedback will appear in GitHub PR comments
|
||||
cli.run_command(pr_url, command)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@ -1,71 +1,20 @@
|
||||
from os.path import abspath, dirname, join
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
from dynaconf import Dynaconf
|
||||
from starlette_context import context
|
||||
|
||||
PR_AGENT_TOML_KEY = 'pr-agent'
|
||||
|
||||
current_dir = dirname(abspath(__file__))
|
||||
global_settings = Dynaconf(
|
||||
settings = Dynaconf(
|
||||
envvar_prefix=False,
|
||||
merge_enabled=True,
|
||||
settings_files=[join(current_dir, f) for f in [
|
||||
"settings/.secrets.toml",
|
||||
"settings/configuration.toml",
|
||||
"settings/ignore.toml",
|
||||
"settings/language_extensions.toml",
|
||||
"settings/pr_reviewer_prompts.toml",
|
||||
"settings/pr_questions_prompts.toml",
|
||||
"settings/pr_line_questions_prompts.toml",
|
||||
"settings/pr_description_prompts.toml",
|
||||
"settings/pr_code_suggestions_prompts.toml",
|
||||
"settings/pr_sort_code_suggestions_prompts.toml",
|
||||
"settings/pr_information_from_user_prompts.toml",
|
||||
"settings/pr_update_changelog_prompts.toml",
|
||||
"settings/pr_custom_labels.toml",
|
||||
"settings/pr_add_docs.toml",
|
||||
"settings_prod/.secrets.toml",
|
||||
"settings/custom_labels.toml"
|
||||
]]
|
||||
"settings/.secrets.toml",
|
||||
"settings/configuration.toml",
|
||||
"settings/language_extensions.toml",
|
||||
"settings/pr_reviewer_prompts.toml",
|
||||
"settings/pr_questions_prompts.toml",
|
||||
"settings/pr_description_prompts.toml",
|
||||
"settings/pr_code_suggestions_prompts.toml",
|
||||
"settings/pr_information_from_user_prompts.toml",
|
||||
"settings_prod/.secrets.toml"
|
||||
]]
|
||||
)
|
||||
|
||||
|
||||
def get_settings():
|
||||
try:
|
||||
return context["settings"]
|
||||
except Exception:
|
||||
print("error")
|
||||
return global_settings
|
||||
|
||||
|
||||
# Add local configuration from pyproject.toml of the project being reviewed
|
||||
def _find_repository_root() -> Path:
|
||||
"""
|
||||
Identify project root directory by recursively searching for the .git directory in the parent directories.
|
||||
"""
|
||||
cwd = Path.cwd().resolve()
|
||||
no_way_up = False
|
||||
while not no_way_up:
|
||||
no_way_up = cwd == cwd.parent
|
||||
if (cwd / ".git").is_dir():
|
||||
return cwd
|
||||
cwd = cwd.parent
|
||||
return None
|
||||
|
||||
|
||||
def _find_pyproject() -> Optional[Path]:
|
||||
"""
|
||||
Search for file pyproject.toml in the repository root.
|
||||
"""
|
||||
repo_root = _find_repository_root()
|
||||
if repo_root:
|
||||
pyproject = _find_repository_root() / "pyproject.toml"
|
||||
return pyproject if pyproject.is_file() else None
|
||||
return None
|
||||
|
||||
|
||||
pyproject_path = _find_pyproject()
|
||||
if pyproject_path is not None:
|
||||
get_settings().load_file(pyproject_path, env=f'tool.{PR_AGENT_TOML_KEY}')
|
||||
|
||||
@ -1,28 +1,17 @@
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.config_loader import settings
|
||||
from pr_agent.git_providers.bitbucket_provider import BitbucketProvider
|
||||
from pr_agent.git_providers.bitbucket_server_provider import BitbucketServerProvider
|
||||
from pr_agent.git_providers.codecommit_provider import CodeCommitProvider
|
||||
from pr_agent.git_providers.github_provider import GithubProvider
|
||||
from pr_agent.git_providers.gitlab_provider import GitLabProvider
|
||||
from pr_agent.git_providers.local_git_provider import LocalGitProvider
|
||||
from pr_agent.git_providers.azuredevops_provider import AzureDevopsProvider
|
||||
from pr_agent.git_providers.gerrit_provider import GerritProvider
|
||||
|
||||
|
||||
_GIT_PROVIDERS = {
|
||||
'github': GithubProvider,
|
||||
'gitlab': GitLabProvider,
|
||||
'bitbucket': BitbucketProvider,
|
||||
'bitbucket_server': BitbucketServerProvider,
|
||||
'azure': AzureDevopsProvider,
|
||||
'codecommit': CodeCommitProvider,
|
||||
'local' : LocalGitProvider,
|
||||
'gerrit': GerritProvider,
|
||||
}
|
||||
|
||||
def get_git_provider():
|
||||
try:
|
||||
provider_id = get_settings().config.git_provider
|
||||
provider_id = settings.config.git_provider
|
||||
except AttributeError as e:
|
||||
raise ValueError("git_provider is a required attribute in the configuration file") from e
|
||||
if provider_id not in _GIT_PROVIDERS:
|
||||
|
||||
@ -1,566 +0,0 @@
|
||||
import os
|
||||
from typing import Optional, Tuple
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from ..log import get_logger
|
||||
from ..algo.language_handler import is_valid_file
|
||||
from ..algo.utils import clip_tokens, find_line_number_of_relevant_line_in_file, load_large_diff
|
||||
from ..config_loader import get_settings
|
||||
from .git_provider import GitProvider
|
||||
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
|
||||
|
||||
AZURE_DEVOPS_AVAILABLE = True
|
||||
ADO_APP_CLIENT_DEFAULT_ID = "499b84ac-1321-427f-aa17-267ca6975798/.default"
|
||||
MAX_PR_DESCRIPTION_AZURE_LENGTH = 4000-1
|
||||
|
||||
try:
|
||||
# noinspection PyUnresolvedReferences
|
||||
from msrest.authentication import BasicAuthentication
|
||||
# noinspection PyUnresolvedReferences
|
||||
from azure.devops.connection import Connection
|
||||
# noinspection PyUnresolvedReferences
|
||||
from azure.identity import DefaultAzureCredential
|
||||
# noinspection PyUnresolvedReferences
|
||||
from azure.devops.v7_1.git.models import (
|
||||
Comment,
|
||||
CommentThread,
|
||||
GitVersionDescriptor,
|
||||
GitPullRequest,
|
||||
)
|
||||
except ImportError:
|
||||
AZURE_DEVOPS_AVAILABLE = False
|
||||
|
||||
|
||||
class AzureDevopsProvider(GitProvider):
|
||||
|
||||
def __init__(
|
||||
self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
|
||||
):
|
||||
if not AZURE_DEVOPS_AVAILABLE:
|
||||
raise ImportError(
|
||||
"Azure DevOps provider is not available. Please install the required dependencies."
|
||||
)
|
||||
|
||||
self.azure_devops_client = self._get_azure_devops_client()
|
||||
self.diff_files = None
|
||||
self.workspace_slug = None
|
||||
self.repo_slug = None
|
||||
self.repo = None
|
||||
self.pr_num = None
|
||||
self.pr = None
|
||||
self.temp_comments = []
|
||||
self.incremental = incremental
|
||||
if pr_url:
|
||||
self.set_pr(pr_url)
|
||||
|
||||
def publish_code_suggestions(self, code_suggestions: list) -> bool:
|
||||
"""
|
||||
Publishes code suggestions as comments on the PR.
|
||||
"""
|
||||
post_parameters_list = []
|
||||
for suggestion in code_suggestions:
|
||||
body = suggestion['body']
|
||||
relevant_file = suggestion['relevant_file']
|
||||
relevant_lines_start = suggestion['relevant_lines_start']
|
||||
relevant_lines_end = suggestion['relevant_lines_end']
|
||||
|
||||
if not relevant_lines_start or relevant_lines_start == -1:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().exception(
|
||||
f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
|
||||
continue
|
||||
|
||||
if relevant_lines_end < relevant_lines_start:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().exception(f"Failed to publish code suggestion, "
|
||||
f"relevant_lines_end is {relevant_lines_end} and "
|
||||
f"relevant_lines_start is {relevant_lines_start}")
|
||||
continue
|
||||
|
||||
if relevant_lines_end > relevant_lines_start:
|
||||
post_parameters = {
|
||||
"body": body,
|
||||
"path": relevant_file,
|
||||
"line": relevant_lines_end,
|
||||
"start_line": relevant_lines_start,
|
||||
"start_side": "RIGHT",
|
||||
}
|
||||
else: # API is different for single line comments
|
||||
post_parameters = {
|
||||
"body": body,
|
||||
"path": relevant_file,
|
||||
"line": relevant_lines_start,
|
||||
"side": "RIGHT",
|
||||
}
|
||||
post_parameters_list.append(post_parameters)
|
||||
|
||||
try:
|
||||
for post_parameters in post_parameters_list:
|
||||
comment = Comment(content=post_parameters["body"], comment_type=1)
|
||||
thread = CommentThread(comments=[comment],
|
||||
thread_context={
|
||||
"filePath": post_parameters["path"],
|
||||
"rightFileStart": {
|
||||
"line": post_parameters["start_line"],
|
||||
"offset": 1,
|
||||
},
|
||||
"rightFileEnd": {
|
||||
"line": post_parameters["line"],
|
||||
"offset": 1,
|
||||
},
|
||||
})
|
||||
self.azure_devops_client.create_thread(
|
||||
comment_thread=thread,
|
||||
project=self.workspace_slug,
|
||||
repository_id=self.repo_slug,
|
||||
pull_request_id=self.pr_num
|
||||
)
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(
|
||||
f"Published code suggestion on {self.pr_num} at {post_parameters['path']}"
|
||||
)
|
||||
return True
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to publish code suggestion, error: {e}")
|
||||
return False
|
||||
|
||||
def get_pr_description_full(self) -> str:
|
||||
return self.pr.description
|
||||
|
||||
def edit_comment(self, comment, body: str):
|
||||
try:
|
||||
self.azure_devops_client.update_comment(
|
||||
repository_id=self.repo_slug,
|
||||
pull_request_id=self.pr_num,
|
||||
thread_id=comment["thread_id"],
|
||||
comment_id=comment["comment_id"],
|
||||
comment=Comment(content=body),
|
||||
project=self.workspace_slug,
|
||||
)
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to edit comment, error: {e}")
|
||||
|
||||
def remove_comment(self, comment):
|
||||
try:
|
||||
self.azure_devops_client.delete_comment(
|
||||
repository_id=self.repo_slug,
|
||||
pull_request_id=self.pr_num,
|
||||
thread_id=comment["thread_id"],
|
||||
comment_id=comment["comment_id"],
|
||||
project=self.workspace_slug,
|
||||
)
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to remove comment, error: {e}")
|
||||
|
||||
def publish_labels(self, pr_types):
|
||||
try:
|
||||
for pr_type in pr_types:
|
||||
self.azure_devops_client.create_pull_request_label(
|
||||
label={"name": pr_type},
|
||||
project=self.workspace_slug,
|
||||
repository_id=self.repo_slug,
|
||||
pull_request_id=self.pr_num,
|
||||
)
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to publish labels, error: {e}")
|
||||
|
||||
def get_pr_labels(self, update=False):
|
||||
try:
|
||||
labels = self.azure_devops_client.get_pull_request_labels(
|
||||
project=self.workspace_slug,
|
||||
repository_id=self.repo_slug,
|
||||
pull_request_id=self.pr_num,
|
||||
)
|
||||
return [label.name for label in labels]
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to get labels, error: {e}")
|
||||
return []
|
||||
|
||||
def is_supported(self, capability: str) -> bool:
|
||||
if capability in [
|
||||
"get_issue_comments",
|
||||
]:
|
||||
return False
|
||||
return True
|
||||
|
||||
def set_pr(self, pr_url: str):
|
||||
self.workspace_slug, self.repo_slug, self.pr_num = self._parse_pr_url(pr_url)
|
||||
self.pr = self._get_pr()
|
||||
|
||||
def get_repo_settings(self):
|
||||
try:
|
||||
contents = self.azure_devops_client.get_item_content(
|
||||
repository_id=self.repo_slug,
|
||||
project=self.workspace_slug,
|
||||
download=False,
|
||||
include_content_metadata=False,
|
||||
include_content=True,
|
||||
path=".pr_agent.toml",
|
||||
)
|
||||
return list(contents)[0]
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to get repo settings, error: {e}")
|
||||
return ""
|
||||
|
||||
def get_files(self):
|
||||
files = []
|
||||
for i in self.azure_devops_client.get_pull_request_commits(
|
||||
project=self.workspace_slug,
|
||||
repository_id=self.repo_slug,
|
||||
pull_request_id=self.pr_num,
|
||||
):
|
||||
changes_obj = self.azure_devops_client.get_changes(
|
||||
project=self.workspace_slug,
|
||||
repository_id=self.repo_slug,
|
||||
commit_id=i.commit_id,
|
||||
)
|
||||
|
||||
for c in changes_obj.changes:
|
||||
files.append(c["item"]["path"])
|
||||
return list(set(files))
|
||||
|
||||
def get_diff_files(self) -> list[FilePatchInfo]:
|
||||
try:
|
||||
|
||||
if self.diff_files:
|
||||
return self.diff_files
|
||||
|
||||
base_sha = self.pr.last_merge_target_commit
|
||||
head_sha = self.pr.last_merge_source_commit
|
||||
|
||||
commits = self.azure_devops_client.get_pull_request_commits(
|
||||
project=self.workspace_slug,
|
||||
repository_id=self.repo_slug,
|
||||
pull_request_id=self.pr_num,
|
||||
)
|
||||
|
||||
diff_files = []
|
||||
diffs = []
|
||||
diff_types = {}
|
||||
|
||||
for c in commits:
|
||||
changes_obj = self.azure_devops_client.get_changes(
|
||||
project=self.workspace_slug,
|
||||
repository_id=self.repo_slug,
|
||||
commit_id=c.commit_id,
|
||||
)
|
||||
for i in changes_obj.changes:
|
||||
if i["item"]["gitObjectType"] == "tree":
|
||||
continue
|
||||
diffs.append(i["item"]["path"])
|
||||
diff_types[i["item"]["path"]] = i["changeType"]
|
||||
|
||||
diffs = list(set(diffs))
|
||||
|
||||
for file in diffs:
|
||||
if not is_valid_file(file):
|
||||
continue
|
||||
|
||||
version = GitVersionDescriptor(
|
||||
version=head_sha.commit_id, version_type="commit"
|
||||
)
|
||||
try:
|
||||
new_file_content_str = self.azure_devops_client.get_item(
|
||||
repository_id=self.repo_slug,
|
||||
path=file,
|
||||
project=self.workspace_slug,
|
||||
version_descriptor=version,
|
||||
download=False,
|
||||
include_content=True,
|
||||
)
|
||||
|
||||
new_file_content_str = new_file_content_str.content
|
||||
except Exception as error:
|
||||
get_logger().error(
|
||||
"Failed to retrieve new file content of %s at version %s. Error: %s",
|
||||
file,
|
||||
version,
|
||||
str(error),
|
||||
)
|
||||
new_file_content_str = ""
|
||||
|
||||
edit_type = EDIT_TYPE.MODIFIED
|
||||
if diff_types[file] == "add":
|
||||
edit_type = EDIT_TYPE.ADDED
|
||||
elif diff_types[file] == "delete":
|
||||
edit_type = EDIT_TYPE.DELETED
|
||||
elif diff_types[file] == "rename":
|
||||
edit_type = EDIT_TYPE.RENAMED
|
||||
|
||||
version = GitVersionDescriptor(
|
||||
version=base_sha.commit_id, version_type="commit"
|
||||
)
|
||||
try:
|
||||
original_file_content_str = self.azure_devops_client.get_item(
|
||||
repository_id=self.repo_slug,
|
||||
path=file,
|
||||
project=self.workspace_slug,
|
||||
version_descriptor=version,
|
||||
download=False,
|
||||
include_content=True,
|
||||
)
|
||||
original_file_content_str = original_file_content_str.content
|
||||
except Exception as error:
|
||||
get_logger().error(
|
||||
"Failed to retrieve original file content of %s at version %s. Error: %s",
|
||||
file,
|
||||
version,
|
||||
str(error),
|
||||
)
|
||||
original_file_content_str = ""
|
||||
|
||||
patch = load_large_diff(
|
||||
file, new_file_content_str, original_file_content_str
|
||||
)
|
||||
|
||||
diff_files.append(
|
||||
FilePatchInfo(
|
||||
original_file_content_str,
|
||||
new_file_content_str,
|
||||
patch=patch,
|
||||
filename=file,
|
||||
edit_type=edit_type,
|
||||
)
|
||||
)
|
||||
self.diff_files = diff_files
|
||||
return diff_files
|
||||
except Exception as e:
|
||||
print(f"Error: {str(e)}")
|
||||
return []
|
||||
|
||||
def publish_comment(self, pr_comment: str, is_temporary: bool = False, thread_context=None):
|
||||
comment = Comment(content=pr_comment)
|
||||
thread = CommentThread(comments=[comment], thread_context=thread_context, status=1)
|
||||
thread_response = self.azure_devops_client.create_thread(
|
||||
comment_thread=thread,
|
||||
project=self.workspace_slug,
|
||||
repository_id=self.repo_slug,
|
||||
pull_request_id=self.pr_num,
|
||||
)
|
||||
response = {"thread_id": thread_response.id, "comment_id": thread_response.comments[0].id}
|
||||
if is_temporary:
|
||||
self.temp_comments.append(response)
|
||||
return response
|
||||
|
||||
def publish_description(self, pr_title: str, pr_body: str):
|
||||
if len(pr_body) > MAX_PR_DESCRIPTION_AZURE_LENGTH:
|
||||
|
||||
usage_guide_text='<details> <summary><strong>✨ Describe tool usage guide:</strong></summary><hr>'
|
||||
ind = pr_body.find(usage_guide_text)
|
||||
if ind != -1:
|
||||
pr_body = pr_body[:ind]
|
||||
|
||||
if len(pr_body) > MAX_PR_DESCRIPTION_AZURE_LENGTH:
|
||||
changes_walkthrough_text = '## **Changes walkthrough**'
|
||||
ind = pr_body.find(changes_walkthrough_text)
|
||||
if ind != -1:
|
||||
pr_body = pr_body[:ind]
|
||||
|
||||
if len(pr_body) > MAX_PR_DESCRIPTION_AZURE_LENGTH:
|
||||
trunction_message = " ... (description truncated due to length limit)"
|
||||
pr_body = pr_body[:MAX_PR_DESCRIPTION_AZURE_LENGTH - len(trunction_message)] + trunction_message
|
||||
get_logger().warning("PR description was truncated due to length limit")
|
||||
try:
|
||||
updated_pr = GitPullRequest()
|
||||
updated_pr.title = pr_title
|
||||
updated_pr.description = pr_body
|
||||
self.azure_devops_client.update_pull_request(
|
||||
project=self.workspace_slug,
|
||||
repository_id=self.repo_slug,
|
||||
pull_request_id=self.pr_num,
|
||||
git_pull_request_to_update=updated_pr,
|
||||
)
|
||||
except Exception as e:
|
||||
get_logger().exception(
|
||||
f"Could not update pull request {self.pr_num} description: {e}"
|
||||
)
|
||||
|
||||
def remove_initial_comment(self):
|
||||
try:
|
||||
for comment in self.temp_comments:
|
||||
self.remove_comment(comment)
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to remove temp comments, error: {e}")
|
||||
|
||||
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
self.publish_inline_comments([self.create_inline_comment(body, relevant_file, relevant_line_in_file)])
|
||||
|
||||
|
||||
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
|
||||
absolute_position: int = None):
|
||||
position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(),
|
||||
relevant_file.strip('`'),
|
||||
relevant_line_in_file,
|
||||
absolute_position)
|
||||
if position == -1:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
|
||||
subject_type = "FILE"
|
||||
else:
|
||||
subject_type = "LINE"
|
||||
path = relevant_file.strip()
|
||||
return dict(body=body, path=path, position=position, absolute_position=absolute_position) if subject_type == "LINE" else {}
|
||||
|
||||
def publish_inline_comments(self, comments: list[dict], disable_fallback: bool = False):
|
||||
overall_sucess = True
|
||||
for comment in comments:
|
||||
try:
|
||||
self.publish_comment(comment["body"],
|
||||
thread_context={
|
||||
"filePath": comment["path"],
|
||||
"rightFileStart": {
|
||||
"line": comment["absolute_position"],
|
||||
"offset": comment["position"],
|
||||
},
|
||||
"rightFileEnd": {
|
||||
"line": comment["absolute_position"],
|
||||
"offset": comment["position"],
|
||||
},
|
||||
})
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(
|
||||
f"Published code suggestion on {self.pr_num} at {comment['path']}"
|
||||
)
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to publish code suggestion, error: {e}")
|
||||
overall_sucess = False
|
||||
return overall_sucess
|
||||
|
||||
def get_title(self):
|
||||
return self.pr.title
|
||||
|
||||
def get_languages(self):
|
||||
languages = []
|
||||
files = self.azure_devops_client.get_items(
|
||||
project=self.workspace_slug,
|
||||
repository_id=self.repo_slug,
|
||||
recursion_level="Full",
|
||||
include_content_metadata=True,
|
||||
include_links=False,
|
||||
download=False,
|
||||
)
|
||||
for f in files:
|
||||
if f.git_object_type == "blob":
|
||||
file_name, file_extension = os.path.splitext(f.path)
|
||||
languages.append(file_extension[1:])
|
||||
|
||||
extension_counts = {}
|
||||
for ext in languages:
|
||||
if ext != "":
|
||||
extension_counts[ext] = extension_counts.get(ext, 0) + 1
|
||||
|
||||
total_extensions = sum(extension_counts.values())
|
||||
|
||||
extension_percentages = {
|
||||
ext: (count / total_extensions) * 100
|
||||
for ext, count in extension_counts.items()
|
||||
}
|
||||
|
||||
return extension_percentages
|
||||
|
||||
def get_pr_branch(self):
|
||||
pr_info = self.azure_devops_client.get_pull_request_by_id(
|
||||
project=self.workspace_slug, pull_request_id=self.pr_num
|
||||
)
|
||||
source_branch = pr_info.source_ref_name.split("/")[-1]
|
||||
return source_branch
|
||||
|
||||
def get_pr_description(self, *, full: bool = True) -> str:
|
||||
max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
|
||||
if max_tokens:
|
||||
return clip_tokens(self.pr.description, max_tokens)
|
||||
return self.pr.description
|
||||
|
||||
def get_user_id(self):
|
||||
return 0
|
||||
|
||||
def get_issue_comments(self):
|
||||
raise NotImplementedError(
|
||||
"Azure DevOps provider does not support issue comments yet"
|
||||
)
|
||||
|
||||
def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
|
||||
return True
|
||||
|
||||
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
|
||||
return True
|
||||
|
||||
@staticmethod
|
||||
def _parse_pr_url(pr_url: str) -> Tuple[str, str, int]:
|
||||
parsed_url = urlparse(pr_url)
|
||||
|
||||
path_parts = parsed_url.path.strip("/").split("/")
|
||||
|
||||
if len(path_parts) < 6 or path_parts[4] != "pullrequest":
|
||||
raise ValueError(
|
||||
"The provided URL does not appear to be a Azure DevOps PR URL"
|
||||
)
|
||||
|
||||
workspace_slug = path_parts[1]
|
||||
repo_slug = path_parts[3]
|
||||
try:
|
||||
pr_number = int(path_parts[5])
|
||||
except ValueError as e:
|
||||
raise ValueError("Unable to convert PR number to integer") from e
|
||||
|
||||
return workspace_slug, repo_slug, pr_number
|
||||
|
||||
@staticmethod
|
||||
def _get_azure_devops_client():
|
||||
org = get_settings().azure_devops.get("org", None)
|
||||
pat = get_settings().azure_devops.get("pat", None)
|
||||
|
||||
if not org:
|
||||
raise ValueError("Azure DevOps organization is required")
|
||||
|
||||
if pat:
|
||||
auth_token = pat
|
||||
else:
|
||||
try:
|
||||
# try to use azure default credentials
|
||||
# see https://learn.microsoft.com/en-us/python/api/overview/azure/identity-readme?view=azure-python
|
||||
# for usage and env var configuration of user-assigned managed identity, local machine auth etc.
|
||||
get_logger().info("No PAT found in settings, trying to use Azure Default Credentials.")
|
||||
credentials = DefaultAzureCredential()
|
||||
accessToken = credentials.get_token(ADO_APP_CLIENT_DEFAULT_ID)
|
||||
auth_token = accessToken.token
|
||||
except Exception as e:
|
||||
get_logger().error(f"No PAT found in settings, and Azure Default Authentication failed, error: {e}")
|
||||
raise
|
||||
|
||||
credentials = BasicAuthentication("", auth_token)
|
||||
|
||||
credentials = BasicAuthentication("", auth_token)
|
||||
azure_devops_connection = Connection(base_url=org, creds=credentials)
|
||||
azure_devops_client = azure_devops_connection.clients.get_git_client()
|
||||
|
||||
return azure_devops_client
|
||||
|
||||
def _get_repo(self):
|
||||
if self.repo is None:
|
||||
self.repo = self.azure_devops_client.get_repository(
|
||||
project=self.workspace_slug, repository_id=self.repo_slug
|
||||
)
|
||||
return self.repo
|
||||
|
||||
def _get_pr(self):
|
||||
self.pr = self.azure_devops_client.get_pull_request_by_id(
|
||||
pull_request_id=self.pr_num, project=self.workspace_slug
|
||||
)
|
||||
return self.pr
|
||||
|
||||
def get_commit_messages(self):
|
||||
return "" # not implemented yet
|
||||
|
||||
def get_pr_id(self):
|
||||
try:
|
||||
pr_id = f"{self.workspace_slug}/{self.repo_slug}/{self.pr_num}"
|
||||
return pr_id
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to get pr id, error: {e}")
|
||||
return ""
|
||||
|
||||
@ -1,113 +1,33 @@
|
||||
import json
|
||||
import logging
|
||||
from typing import Optional, Tuple
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import requests
|
||||
from atlassian.bitbucket import Cloud
|
||||
from starlette_context import context
|
||||
|
||||
from pr_agent.algo.types import FilePatchInfo, EDIT_TYPE
|
||||
from ..algo.utils import find_line_number_of_relevant_line_in_file
|
||||
from ..config_loader import get_settings
|
||||
from ..log import get_logger
|
||||
from .git_provider import GitProvider
|
||||
from pr_agent.config_loader import settings
|
||||
|
||||
from .git_provider import FilePatchInfo
|
||||
|
||||
|
||||
class BitbucketProvider(GitProvider):
|
||||
def __init__(
|
||||
self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
|
||||
):
|
||||
class BitbucketProvider:
|
||||
def __init__(self, pr_url: Optional[str] = None, incremental: Optional[bool] = False):
|
||||
s = requests.Session()
|
||||
try:
|
||||
bearer = context.get("bitbucket_bearer_token", None)
|
||||
s.headers["Authorization"] = f"Bearer {bearer}"
|
||||
except Exception:
|
||||
s.headers[
|
||||
"Authorization"
|
||||
] = f'Bearer {get_settings().get("BITBUCKET.BEARER_TOKEN", None)}'
|
||||
s.headers["Content-Type"] = "application/json"
|
||||
self.headers = s.headers
|
||||
s.headers['Authorization'] = f'Bearer {settings.get("BITBUCKET.BEARER_TOKEN", None)}'
|
||||
self.bitbucket_client = Cloud(session=s)
|
||||
|
||||
self.workspace_slug = None
|
||||
self.repo_slug = None
|
||||
self.repo = None
|
||||
self.pr_num = None
|
||||
self.pr = None
|
||||
self.pr_url = pr_url
|
||||
self.temp_comments = []
|
||||
self.incremental = incremental
|
||||
self.diff_files = None
|
||||
if pr_url:
|
||||
self.set_pr(pr_url)
|
||||
self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"]["comments"]["href"]
|
||||
self.bitbucket_pull_request_api_url = self.pr._BitbucketBase__data["links"]['self']['href']
|
||||
|
||||
def get_repo_settings(self):
|
||||
try:
|
||||
url = (f"https://api.bitbucket.org/2.0/repositories/{self.workspace_slug}/{self.repo_slug}/src/"
|
||||
f"{self.pr.destination_branch}/.pr_agent.toml")
|
||||
response = requests.request("GET", url, headers=self.headers)
|
||||
if response.status_code == 404: # not found
|
||||
return ""
|
||||
contents = response.text.encode('utf-8')
|
||||
return contents
|
||||
except Exception:
|
||||
return ""
|
||||
|
||||
def publish_code_suggestions(self, code_suggestions: list) -> bool:
|
||||
"""
|
||||
Publishes code suggestions as comments on the PR.
|
||||
"""
|
||||
post_parameters_list = []
|
||||
for suggestion in code_suggestions:
|
||||
body = suggestion["body"]
|
||||
relevant_file = suggestion["relevant_file"]
|
||||
relevant_lines_start = suggestion["relevant_lines_start"]
|
||||
relevant_lines_end = suggestion["relevant_lines_end"]
|
||||
|
||||
if not relevant_lines_start or relevant_lines_start == -1:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().exception(
|
||||
f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
|
||||
)
|
||||
continue
|
||||
|
||||
if relevant_lines_end < relevant_lines_start:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().exception(
|
||||
f"Failed to publish code suggestion, "
|
||||
f"relevant_lines_end is {relevant_lines_end} and "
|
||||
f"relevant_lines_start is {relevant_lines_start}"
|
||||
)
|
||||
continue
|
||||
|
||||
if relevant_lines_end > relevant_lines_start:
|
||||
post_parameters = {
|
||||
"body": body,
|
||||
"path": relevant_file,
|
||||
"line": relevant_lines_end,
|
||||
"start_line": relevant_lines_start,
|
||||
"start_side": "RIGHT",
|
||||
}
|
||||
else: # API is different for single line comments
|
||||
post_parameters = {
|
||||
"body": body,
|
||||
"path": relevant_file,
|
||||
"line": relevant_lines_start,
|
||||
"side": "RIGHT",
|
||||
}
|
||||
post_parameters_list.append(post_parameters)
|
||||
|
||||
try:
|
||||
self.publish_inline_comments(post_parameters_list)
|
||||
return True
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to publish code suggestion, error: {e}")
|
||||
return False
|
||||
|
||||
def is_supported(self, capability: str) -> bool:
|
||||
if capability in ['get_issue_comments', 'publish_inline_comments', 'get_labels', 'gfm_markdown']:
|
||||
if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments']:
|
||||
return False
|
||||
return True
|
||||
|
||||
@ -119,209 +39,68 @@ class BitbucketProvider(GitProvider):
|
||||
return [diff.new.path for diff in self.pr.diffstat()]
|
||||
|
||||
def get_diff_files(self) -> list[FilePatchInfo]:
|
||||
if self.diff_files:
|
||||
return self.diff_files
|
||||
|
||||
diffs = self.pr.diffstat()
|
||||
diff_split = [
|
||||
"diff --git%s" % x for x in self.pr.diff().split("diff --git") if x.strip()
|
||||
]
|
||||
|
||||
diff_split = ['diff --git%s' % x for x in self.pr.diff().split('diff --git') if x.strip()]
|
||||
|
||||
diff_files = []
|
||||
for index, diff in enumerate(diffs):
|
||||
original_file_content_str = self._get_pr_file_content(
|
||||
diff.old.get_data("links")
|
||||
)
|
||||
new_file_content_str = self._get_pr_file_content(diff.new.get_data("links"))
|
||||
file_patch_canonic_structure = FilePatchInfo(
|
||||
original_file_content_str,
|
||||
new_file_content_str,
|
||||
diff_split[index],
|
||||
diff.new.path,
|
||||
)
|
||||
|
||||
if diff.data['status'] == 'added':
|
||||
file_patch_canonic_structure.edit_type = EDIT_TYPE.ADDED
|
||||
elif diff.data['status'] == 'removed':
|
||||
file_patch_canonic_structure.edit_type = EDIT_TYPE.DELETED
|
||||
elif diff.data['status'] == 'modified':
|
||||
file_patch_canonic_structure.edit_type = EDIT_TYPE.MODIFIED
|
||||
elif diff.data['status'] == 'renamed':
|
||||
file_patch_canonic_structure.edit_type = EDIT_TYPE.RENAMED
|
||||
diff_files.append(file_patch_canonic_structure)
|
||||
|
||||
|
||||
self.diff_files = diff_files
|
||||
original_file_content_str = self._get_pr_file_content(diff.old.get_data('links'))
|
||||
new_file_content_str = self._get_pr_file_content(diff.new.get_data('links'))
|
||||
diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str,
|
||||
diff_split[index], diff.new.path))
|
||||
return diff_files
|
||||
|
||||
def get_latest_commit_url(self):
|
||||
return self.pr.data['source']['commit']['links']['html']['href']
|
||||
|
||||
def get_comment_url(self, comment):
|
||||
return comment.data['links']['html']['href']
|
||||
|
||||
def publish_persistent_comment(self, pr_comment: str,
|
||||
initial_header: str,
|
||||
update_header: bool = True,
|
||||
name='review',
|
||||
final_update_message=True):
|
||||
try:
|
||||
for comment in self.pr.comments():
|
||||
body = comment.raw
|
||||
if initial_header in body:
|
||||
latest_commit_url = self.get_latest_commit_url()
|
||||
comment_url = self.get_comment_url(comment)
|
||||
if update_header:
|
||||
updated_header = f"{initial_header}\n\n### ({name.capitalize()} updated until commit {latest_commit_url})\n"
|
||||
pr_comment_updated = pr_comment.replace(initial_header, updated_header)
|
||||
else:
|
||||
pr_comment_updated = pr_comment
|
||||
get_logger().info(f"Persistent mode - updating comment {comment_url} to latest {name} message")
|
||||
d = {"content": {"raw": pr_comment_updated}}
|
||||
response = comment._update_data(comment.put(None, data=d))
|
||||
if final_update_message:
|
||||
self.publish_comment(
|
||||
f"**[Persistent {name}]({comment_url})** updated to latest commit {latest_commit_url}")
|
||||
return
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to update persistent review, error: {e}")
|
||||
pass
|
||||
self.publish_comment(pr_comment)
|
||||
|
||||
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
|
||||
comment = self.pr.comment(pr_comment)
|
||||
if is_temporary:
|
||||
self.temp_comments.append(comment["id"])
|
||||
return comment
|
||||
|
||||
def edit_comment(self, comment, body: str):
|
||||
try:
|
||||
comment.update(body)
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to update comment, error: {e}")
|
||||
self.temp_comments.append(comment['id'])
|
||||
|
||||
def remove_initial_comment(self):
|
||||
try:
|
||||
for comment in self.temp_comments:
|
||||
self.remove_comment(comment)
|
||||
self.pr.delete(f'comments/{comment}')
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to remove temp comments, error: {e}")
|
||||
logging.exception(f"Failed to remove temp comments, error: {e}")
|
||||
|
||||
def remove_comment(self, comment):
|
||||
try:
|
||||
self.pr.delete(f"comments/{comment}")
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to remove comment, error: {e}")
|
||||
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
pass
|
||||
|
||||
# funtion to create_inline_comment
|
||||
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
|
||||
position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(),
|
||||
relevant_file.strip('`'),
|
||||
relevant_line_in_file, absolute_position)
|
||||
if position == -1:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
|
||||
subject_type = "FILE"
|
||||
else:
|
||||
subject_type = "LINE"
|
||||
path = relevant_file.strip()
|
||||
return dict(body=body, path=path, position=absolute_position) if subject_type == "LINE" else {}
|
||||
|
||||
|
||||
def publish_inline_comment(self, comment: str, from_line: int, file: str):
|
||||
payload = json.dumps( {
|
||||
"content": {
|
||||
"raw": comment,
|
||||
},
|
||||
"inline": {
|
||||
"to": from_line,
|
||||
"path": file
|
||||
},
|
||||
})
|
||||
response = requests.request(
|
||||
"POST", self.bitbucket_comment_api_url, data=payload, headers=self.headers
|
||||
)
|
||||
return response
|
||||
|
||||
def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
|
||||
if relevant_line_start == -1:
|
||||
link = f"{self.pr_url}/#L{relevant_file}"
|
||||
else:
|
||||
link = f"{self.pr_url}/#L{relevant_file}T{relevant_line_start}"
|
||||
return link
|
||||
|
||||
def generate_link_to_relevant_line_number(self, suggestion) -> str:
|
||||
try:
|
||||
relevant_file = suggestion['relevant_file'].strip('`').strip("'").rstrip()
|
||||
relevant_line_str = suggestion['relevant_line'].rstrip()
|
||||
if not relevant_line_str:
|
||||
return ""
|
||||
|
||||
diff_files = self.get_diff_files()
|
||||
position, absolute_position = find_line_number_of_relevant_line_in_file \
|
||||
(diff_files, relevant_file, relevant_line_str)
|
||||
|
||||
if absolute_position != -1 and self.pr_url:
|
||||
link = f"{self.pr_url}/#L{relevant_file}T{absolute_position}"
|
||||
return link
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Failed adding line link, error: {e}")
|
||||
|
||||
return ""
|
||||
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
raise NotImplementedError("Bitbucket provider does not support creating inline comments yet")
|
||||
|
||||
def publish_inline_comments(self, comments: list[dict]):
|
||||
for comment in comments:
|
||||
if 'position' in comment:
|
||||
self.publish_inline_comment(comment['body'], comment['position'], comment['path'])
|
||||
elif 'start_line' in comment: # multi-line comment
|
||||
# note that bitbucket does not seem to support range - only a comment on a single line - https://community.developer.atlassian.com/t/api-post-endpoint-for-inline-pull-request-comments/60452
|
||||
self.publish_inline_comment(comment['body'], comment['start_line'], comment['path'])
|
||||
elif 'line' in comment: # single-line comment
|
||||
self.publish_inline_comment(comment['body'], comment['line'], comment['path'])
|
||||
else:
|
||||
get_logger().error(f"Could not publish inline comment {comment}")
|
||||
raise NotImplementedError("Bitbucket provider does not support publishing inline comments yet")
|
||||
|
||||
def get_title(self):
|
||||
return self.pr.title
|
||||
|
||||
def get_languages(self):
|
||||
languages = {self._get_repo().get_data("language"): 0}
|
||||
languages = {self._get_repo().get_data('language'): 0}
|
||||
return languages
|
||||
|
||||
def get_pr_branch(self):
|
||||
return self.pr.source_branch
|
||||
|
||||
def get_pr_description_full(self):
|
||||
def get_pr_description(self):
|
||||
return self.pr.description
|
||||
|
||||
def get_user_id(self):
|
||||
return 0
|
||||
|
||||
def get_issue_comments(self):
|
||||
raise NotImplementedError(
|
||||
"Bitbucket provider does not support issue comments yet"
|
||||
)
|
||||
|
||||
def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
|
||||
return True
|
||||
|
||||
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
|
||||
return True
|
||||
raise NotImplementedError("Bitbucket provider does not support issue comments yet")
|
||||
|
||||
@staticmethod
|
||||
def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
|
||||
parsed_url = urlparse(pr_url)
|
||||
|
||||
if 'bitbucket.org' not in parsed_url.netloc:
|
||||
raise ValueError("The provided URL is not a valid GitHub URL")
|
||||
|
||||
if "bitbucket.org" not in parsed_url.netloc:
|
||||
raise ValueError("The provided URL is not a valid Bitbucket URL")
|
||||
|
||||
path_parts = parsed_url.path.strip("/").split("/")
|
||||
|
||||
if len(path_parts) < 4 or path_parts[2] != "pull-requests":
|
||||
raise ValueError(
|
||||
"The provided URL does not appear to be a Bitbucket PR URL"
|
||||
)
|
||||
path_parts = parsed_url.path.strip('/').split('/')
|
||||
|
||||
if len(path_parts) < 4 or path_parts[2] != 'pull-requests':
|
||||
raise ValueError("The provided URL does not appear to be a Bitbucket PR URL")
|
||||
|
||||
workspace_slug = path_parts[0]
|
||||
repo_slug = path_parts[1]
|
||||
@ -334,75 +113,11 @@ class BitbucketProvider(GitProvider):
|
||||
|
||||
def _get_repo(self):
|
||||
if self.repo is None:
|
||||
self.repo = self.bitbucket_client.workspaces.get(
|
||||
self.workspace_slug
|
||||
).repositories.get(self.repo_slug)
|
||||
self.repo = self.bitbucket_client.workspaces.get(self.workspace_slug).repositories.get(self.repo_slug)
|
||||
return self.repo
|
||||
|
||||
def _get_pr(self):
|
||||
return self._get_repo().pullrequests.get(self.pr_num)
|
||||
|
||||
def get_pr_file_content(self, file_path: str, branch: str) -> str:
|
||||
try:
|
||||
if branch == self.pr.source_branch:
|
||||
branch = self.pr.data["source"]["commit"]["hash"]
|
||||
elif branch == self.pr.destination_branch:
|
||||
branch = self.pr.data["destination"]["commit"]["hash"]
|
||||
url = (f"https://api.bitbucket.org/2.0/repositories/{self.workspace_slug}/{self.repo_slug}/src/"
|
||||
f"{branch}/{file_path}")
|
||||
response = requests.request("GET", url, headers=self.headers)
|
||||
if response.status_code == 404: # not found
|
||||
return ""
|
||||
contents = response.text
|
||||
return contents
|
||||
except Exception:
|
||||
return ""
|
||||
|
||||
|
||||
def create_or_update_pr_file(self, file_path: str, branch: str, contents="", message="") -> None:
|
||||
url = (f"https://api.bitbucket.org/2.0/repositories/{self.workspace_slug}/{self.repo_slug}/src/")
|
||||
if not message:
|
||||
if contents:
|
||||
message = f"Update {file_path}"
|
||||
else:
|
||||
message = f"Create {file_path}"
|
||||
files={file_path: contents}
|
||||
data={
|
||||
"message": message,
|
||||
"branch": branch
|
||||
}
|
||||
headers = {'Authorization':self.headers['Authorization']} if 'Authorization' in self.headers else {}
|
||||
try:
|
||||
requests.request("POST", url, headers=headers, data=data, files=files)
|
||||
except Exception:
|
||||
get_logger().exception(f"Failed to create empty file {file_path} in branch {branch}")
|
||||
|
||||
def _get_pr_file_content(self, remote_link: str):
|
||||
return ""
|
||||
|
||||
def get_commit_messages(self):
|
||||
return "" # not implemented yet
|
||||
|
||||
# bitbucket does not support labels
|
||||
def publish_description(self, pr_title: str, description: str):
|
||||
payload = json.dumps({
|
||||
"description": description,
|
||||
"title": pr_title
|
||||
|
||||
})
|
||||
|
||||
response = requests.request("PUT", self.bitbucket_pull_request_api_url, headers=self.headers, data=payload)
|
||||
try:
|
||||
if response.status_code != 200:
|
||||
get_logger().info(f"Failed to update description, error code: {response.status_code}")
|
||||
except:
|
||||
pass
|
||||
return response
|
||||
|
||||
# bitbucket does not support labels
|
||||
def publish_labels(self, pr_types: list):
|
||||
pass
|
||||
|
||||
# bitbucket does not support labels
|
||||
def get_pr_labels(self, update=False):
|
||||
pass
|
||||
|
||||
@ -1,354 +0,0 @@
|
||||
import json
|
||||
from typing import Optional, Tuple
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import requests
|
||||
from atlassian.bitbucket import Bitbucket
|
||||
from starlette_context import context
|
||||
|
||||
from .git_provider import GitProvider
|
||||
from pr_agent.algo.types import FilePatchInfo
|
||||
from ..algo.utils import load_large_diff, find_line_number_of_relevant_line_in_file
|
||||
from ..config_loader import get_settings
|
||||
from ..log import get_logger
|
||||
|
||||
|
||||
class BitbucketServerProvider(GitProvider):
|
||||
def __init__(
|
||||
self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
|
||||
):
|
||||
s = requests.Session()
|
||||
try:
|
||||
bearer = context.get("bitbucket_bearer_token", None)
|
||||
s.headers["Authorization"] = f"Bearer {bearer}"
|
||||
except Exception:
|
||||
s.headers[
|
||||
"Authorization"
|
||||
] = f'Bearer {get_settings().get("BITBUCKET_SERVER.BEARER_TOKEN", None)}'
|
||||
|
||||
s.headers["Content-Type"] = "application/json"
|
||||
self.headers = s.headers
|
||||
self.bitbucket_server_url = None
|
||||
self.workspace_slug = None
|
||||
self.repo_slug = None
|
||||
self.repo = None
|
||||
self.pr_num = None
|
||||
self.pr = None
|
||||
self.pr_url = pr_url
|
||||
self.temp_comments = []
|
||||
self.incremental = incremental
|
||||
self.diff_files = None
|
||||
self.bitbucket_pull_request_api_url = pr_url
|
||||
|
||||
self.bitbucket_server_url = self._parse_bitbucket_server(url=pr_url)
|
||||
self.bitbucket_client = Bitbucket(url=self.bitbucket_server_url,
|
||||
token=get_settings().get("BITBUCKET_SERVER.BEARER_TOKEN", None))
|
||||
|
||||
if pr_url:
|
||||
self.set_pr(pr_url)
|
||||
|
||||
def get_repo_settings(self):
|
||||
try:
|
||||
url = (f"{self.bitbucket_server_url}/projects/{self.workspace_slug}/repos/{self.repo_slug}/src/"
|
||||
f"{self.pr.destination_branch}/.pr_agent.toml")
|
||||
response = requests.request("GET", url, headers=self.headers)
|
||||
if response.status_code == 404: # not found
|
||||
return ""
|
||||
contents = response.text.encode('utf-8')
|
||||
return contents
|
||||
except Exception:
|
||||
return ""
|
||||
|
||||
def publish_code_suggestions(self, code_suggestions: list) -> bool:
|
||||
"""
|
||||
Publishes code suggestions as comments on the PR.
|
||||
"""
|
||||
post_parameters_list = []
|
||||
for suggestion in code_suggestions:
|
||||
body = suggestion["body"]
|
||||
relevant_file = suggestion["relevant_file"]
|
||||
relevant_lines_start = suggestion["relevant_lines_start"]
|
||||
relevant_lines_end = suggestion["relevant_lines_end"]
|
||||
|
||||
if not relevant_lines_start or relevant_lines_start == -1:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().exception(
|
||||
f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
|
||||
)
|
||||
continue
|
||||
|
||||
if relevant_lines_end < relevant_lines_start:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().exception(
|
||||
f"Failed to publish code suggestion, "
|
||||
f"relevant_lines_end is {relevant_lines_end} and "
|
||||
f"relevant_lines_start is {relevant_lines_start}"
|
||||
)
|
||||
continue
|
||||
|
||||
if relevant_lines_end > relevant_lines_start:
|
||||
post_parameters = {
|
||||
"body": body,
|
||||
"path": relevant_file,
|
||||
"line": relevant_lines_end,
|
||||
"start_line": relevant_lines_start,
|
||||
"start_side": "RIGHT",
|
||||
}
|
||||
else: # API is different for single line comments
|
||||
post_parameters = {
|
||||
"body": body,
|
||||
"path": relevant_file,
|
||||
"line": relevant_lines_start,
|
||||
"side": "RIGHT",
|
||||
}
|
||||
post_parameters_list.append(post_parameters)
|
||||
|
||||
try:
|
||||
self.publish_inline_comments(post_parameters_list)
|
||||
return True
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to publish code suggestion, error: {e}")
|
||||
return False
|
||||
|
||||
def is_supported(self, capability: str) -> bool:
|
||||
if capability in ['get_issue_comments', 'get_labels', 'gfm_markdown']:
|
||||
return False
|
||||
return True
|
||||
|
||||
def set_pr(self, pr_url: str):
|
||||
self.workspace_slug, self.repo_slug, self.pr_num = self._parse_pr_url(pr_url)
|
||||
self.pr = self._get_pr()
|
||||
|
||||
def get_file(self, path: str, commit_id: str):
|
||||
file_content = ""
|
||||
try:
|
||||
file_content = self.bitbucket_client.get_content_of_file(self.workspace_slug,
|
||||
self.repo_slug,
|
||||
path,
|
||||
commit_id)
|
||||
except requests.HTTPError as e:
|
||||
get_logger().debug(f"File {path} not found at commit id: {commit_id}")
|
||||
return file_content
|
||||
|
||||
def get_files(self):
|
||||
changes = self.bitbucket_client.get_pull_requests_changes(self.workspace_slug, self.repo_slug, self.pr_num)
|
||||
diffstat = [change["path"]['toString'] for change in changes]
|
||||
return diffstat
|
||||
|
||||
def get_diff_files(self) -> list[FilePatchInfo]:
|
||||
if self.diff_files:
|
||||
return self.diff_files
|
||||
|
||||
commits_in_pr = self.bitbucket_client.get_pull_requests_commits(
|
||||
self.workspace_slug,
|
||||
self.repo_slug,
|
||||
self.pr_num
|
||||
)
|
||||
|
||||
commit_list = list(commits_in_pr)
|
||||
base_sha, head_sha = commit_list[0]['parents'][0]['id'], commit_list[-1]['id']
|
||||
|
||||
diff_files = []
|
||||
original_file_content_str = ""
|
||||
new_file_content_str = ""
|
||||
|
||||
changes = self.bitbucket_client.get_pull_requests_changes(self.workspace_slug, self.repo_slug, self.pr_num)
|
||||
for change in changes:
|
||||
file_path = change['path']['toString']
|
||||
match change['type']:
|
||||
case 'ADD':
|
||||
edit_type = EDIT_TYPE.ADDED
|
||||
new_file_content_str = self.get_file(file_path, head_sha)
|
||||
if isinstance(new_file_content_str, (bytes, bytearray)):
|
||||
new_file_content_str = new_file_content_str.decode("utf-8")
|
||||
original_file_content_str = ""
|
||||
case 'DELETE':
|
||||
edit_type = EDIT_TYPE.DELETED
|
||||
new_file_content_str = ""
|
||||
original_file_content_str = self.get_file(file_path, base_sha)
|
||||
if isinstance(original_file_content_str, (bytes, bytearray)):
|
||||
original_file_content_str = original_file_content_str.decode("utf-8")
|
||||
case 'RENAME':
|
||||
edit_type = EDIT_TYPE.RENAMED
|
||||
case _:
|
||||
edit_type = EDIT_TYPE.MODIFIED
|
||||
original_file_content_str = self.get_file(file_path, base_sha)
|
||||
if isinstance(original_file_content_str, (bytes, bytearray)):
|
||||
original_file_content_str = original_file_content_str.decode("utf-8")
|
||||
new_file_content_str = self.get_file(file_path, head_sha)
|
||||
if isinstance(new_file_content_str, (bytes, bytearray)):
|
||||
new_file_content_str = new_file_content_str.decode("utf-8")
|
||||
|
||||
patch = load_large_diff(file_path, new_file_content_str, original_file_content_str)
|
||||
|
||||
diff_files.append(
|
||||
FilePatchInfo(
|
||||
original_file_content_str,
|
||||
new_file_content_str,
|
||||
patch,
|
||||
file_path,
|
||||
edit_type=edit_type,
|
||||
)
|
||||
)
|
||||
|
||||
self.diff_files = diff_files
|
||||
return diff_files
|
||||
|
||||
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
|
||||
if not is_temporary:
|
||||
self.bitbucket_client.add_pull_request_comment(self.workspace_slug, self.repo_slug, self.pr_num, pr_comment)
|
||||
|
||||
def remove_initial_comment(self):
|
||||
try:
|
||||
for comment in self.temp_comments:
|
||||
self.remove_comment(comment)
|
||||
except ValueError as e:
|
||||
get_logger().exception(f"Failed to remove temp comments, error: {e}")
|
||||
|
||||
def remove_comment(self, comment):
|
||||
pass
|
||||
|
||||
# funtion to create_inline_comment
|
||||
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
|
||||
absolute_position: int = None):
|
||||
|
||||
position, absolute_position = find_line_number_of_relevant_line_in_file(
|
||||
self.get_diff_files(),
|
||||
relevant_file.strip('`'),
|
||||
relevant_line_in_file,
|
||||
absolute_position
|
||||
)
|
||||
if position == -1:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
|
||||
subject_type = "FILE"
|
||||
else:
|
||||
subject_type = "LINE"
|
||||
path = relevant_file.strip()
|
||||
return dict(body=body, path=path, position=absolute_position) if subject_type == "LINE" else {}
|
||||
|
||||
def publish_inline_comment(self, comment: str, from_line: int, file: str):
|
||||
payload = {
|
||||
"text": comment,
|
||||
"severity": "NORMAL",
|
||||
"anchor": {
|
||||
"diffType": "EFFECTIVE",
|
||||
"path": file,
|
||||
"lineType": "ADDED",
|
||||
"line": from_line,
|
||||
"fileType": "TO"
|
||||
}
|
||||
}
|
||||
|
||||
response = requests.post(url=self._get_pr_comments_url(), json=payload, headers=self.headers)
|
||||
return response
|
||||
|
||||
def generate_link_to_relevant_line_number(self, suggestion) -> str:
|
||||
try:
|
||||
relevant_file = suggestion['relevant_file'].strip('`').strip("'").rstrip()
|
||||
relevant_line_str = suggestion['relevant_line'].rstrip()
|
||||
if not relevant_line_str:
|
||||
return ""
|
||||
|
||||
diff_files = self.get_diff_files()
|
||||
position, absolute_position = find_line_number_of_relevant_line_in_file \
|
||||
(diff_files, relevant_file, relevant_line_str)
|
||||
|
||||
if absolute_position != -1 and self.pr_url:
|
||||
link = f"{self.pr_url}/#L{relevant_file}T{absolute_position}"
|
||||
return link
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Failed adding line link, error: {e}")
|
||||
|
||||
return ""
|
||||
|
||||
def publish_inline_comments(self, comments: list[dict]):
|
||||
for comment in comments:
|
||||
self.publish_inline_comment(comment['body'], comment['position'], comment['path'])
|
||||
|
||||
def get_title(self):
|
||||
return self.pr.title
|
||||
|
||||
def get_languages(self):
|
||||
return {"yaml": 0} # devops LOL
|
||||
|
||||
def get_pr_branch(self):
|
||||
return self.pr.fromRef['displayId']
|
||||
|
||||
def get_pr_description_full(self):
|
||||
return self.pr.description
|
||||
|
||||
def get_user_id(self):
|
||||
return 0
|
||||
|
||||
def get_issue_comments(self):
|
||||
raise NotImplementedError(
|
||||
"Bitbucket provider does not support issue comments yet"
|
||||
)
|
||||
|
||||
def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
|
||||
return True
|
||||
|
||||
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
|
||||
return True
|
||||
|
||||
@staticmethod
|
||||
def _parse_bitbucket_server(url: str) -> str:
|
||||
parsed_url = urlparse(url)
|
||||
return f"{parsed_url.scheme}://{parsed_url.netloc}"
|
||||
|
||||
@staticmethod
|
||||
def _parse_pr_url(pr_url: str) -> Tuple[str, str, int]:
|
||||
parsed_url = urlparse(pr_url)
|
||||
path_parts = parsed_url.path.strip("/").split("/")
|
||||
if len(path_parts) < 6 or path_parts[4] != "pull-requests":
|
||||
raise ValueError(
|
||||
"The provided URL does not appear to be a Bitbucket PR URL"
|
||||
)
|
||||
|
||||
workspace_slug = path_parts[1]
|
||||
repo_slug = path_parts[3]
|
||||
try:
|
||||
pr_number = int(path_parts[5])
|
||||
except ValueError as e:
|
||||
raise ValueError("Unable to convert PR number to integer") from e
|
||||
|
||||
return workspace_slug, repo_slug, pr_number
|
||||
|
||||
def _get_repo(self):
|
||||
if self.repo is None:
|
||||
self.repo = self.bitbucket_client.get_repo(self.workspace_slug, self.repo_slug)
|
||||
return self.repo
|
||||
|
||||
def _get_pr(self):
|
||||
pr = self.bitbucket_client.get_pull_request(self.workspace_slug, self.repo_slug, pull_request_id=self.pr_num)
|
||||
return type('new_dict', (object,), pr)
|
||||
|
||||
def _get_pr_file_content(self, remote_link: str):
|
||||
return ""
|
||||
|
||||
def get_commit_messages(self):
|
||||
def get_commit_messages(self):
|
||||
raise NotImplementedError("Get commit messages function not implemented yet.")
|
||||
# bitbucket does not support labels
|
||||
def publish_description(self, pr_title: str, description: str):
|
||||
payload = json.dumps({
|
||||
"description": description,
|
||||
"title": pr_title
|
||||
})
|
||||
|
||||
response = requests.put(url=self.bitbucket_pull_request_api_url, headers=self.headers, data=payload)
|
||||
return response
|
||||
|
||||
# bitbucket does not support labels
|
||||
def publish_labels(self, pr_types: list):
|
||||
pass
|
||||
|
||||
# bitbucket does not support labels
|
||||
def get_pr_labels(self, update=False):
|
||||
pass
|
||||
|
||||
def _get_pr_comments_url(self):
|
||||
return f"{self.bitbucket_server_url}/rest/api/latest/projects/{self.workspace_slug}/repos/{self.repo_slug}/pull-requests/{self.pr_num}/comments"
|
||||
@ -1,277 +0,0 @@
|
||||
import boto3
|
||||
import botocore
|
||||
|
||||
|
||||
class CodeCommitDifferencesResponse:
|
||||
"""
|
||||
CodeCommitDifferencesResponse is the response object returned from our get_differences() function.
|
||||
It maps the JSON response to member variables of this class.
|
||||
"""
|
||||
|
||||
def __init__(self, json: dict):
|
||||
before_blob = json.get("beforeBlob", {})
|
||||
after_blob = json.get("afterBlob", {})
|
||||
|
||||
self.before_blob_id = before_blob.get("blobId", "")
|
||||
self.before_blob_path = before_blob.get("path", "")
|
||||
self.after_blob_id = after_blob.get("blobId", "")
|
||||
self.after_blob_path = after_blob.get("path", "")
|
||||
self.change_type = json.get("changeType", "")
|
||||
|
||||
|
||||
class CodeCommitPullRequestResponse:
|
||||
"""
|
||||
CodeCommitPullRequestResponse is the response object returned from our get_pr() function.
|
||||
It maps the JSON response to member variables of this class.
|
||||
"""
|
||||
|
||||
def __init__(self, json: dict):
|
||||
self.title = json.get("title", "")
|
||||
self.description = json.get("description", "")
|
||||
|
||||
self.targets = []
|
||||
for target in json.get("pullRequestTargets", []):
|
||||
self.targets.append(CodeCommitPullRequestResponse.CodeCommitPullRequestTarget(target))
|
||||
|
||||
class CodeCommitPullRequestTarget:
|
||||
"""
|
||||
CodeCommitPullRequestTarget is a subclass of CodeCommitPullRequestResponse that
|
||||
holds details about an individual target commit.
|
||||
"""
|
||||
|
||||
def __init__(self, json: dict):
|
||||
self.source_commit = json.get("sourceCommit", "")
|
||||
self.source_branch = json.get("sourceReference", "")
|
||||
self.destination_commit = json.get("destinationCommit", "")
|
||||
self.destination_branch = json.get("destinationReference", "")
|
||||
|
||||
|
||||
class CodeCommitClient:
|
||||
"""
|
||||
CodeCommitClient is a wrapper around the AWS boto3 SDK for the CodeCommit client
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self.boto_client = None
|
||||
|
||||
def is_supported(self, capability: str) -> bool:
|
||||
if capability in ["gfm_markdown"]:
|
||||
return False
|
||||
return True
|
||||
|
||||
def _connect_boto_client(self):
|
||||
try:
|
||||
self.boto_client = boto3.client("codecommit")
|
||||
except Exception as e:
|
||||
raise ValueError(f"Failed to connect to AWS CodeCommit: {e}") from e
|
||||
|
||||
def get_differences(self, repo_name: int, destination_commit: str, source_commit: str):
|
||||
"""
|
||||
Get the differences between two commits in CodeCommit.
|
||||
|
||||
Args:
|
||||
- repo_name: Name of the repository
|
||||
- destination_commit: Commit hash you want to merge into (the "before" hash) (usually on the main or master branch)
|
||||
- source_commit: Commit hash of the code you are adding (the "after" branch)
|
||||
|
||||
Returns:
|
||||
- List of CodeCommitDifferencesResponse objects
|
||||
|
||||
Boto3 Documentation:
|
||||
- aws codecommit get-differences
|
||||
- https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_differences.html
|
||||
"""
|
||||
if self.boto_client is None:
|
||||
self._connect_boto_client()
|
||||
|
||||
# The differences response from AWS is paginated, so we need to iterate through the pages to get all the differences.
|
||||
differences = []
|
||||
try:
|
||||
paginator = self.boto_client.get_paginator("get_differences")
|
||||
for page in paginator.paginate(
|
||||
repositoryName=repo_name,
|
||||
beforeCommitSpecifier=destination_commit,
|
||||
afterCommitSpecifier=source_commit,
|
||||
):
|
||||
differences.extend(page.get("differences", []))
|
||||
except botocore.exceptions.ClientError as 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:
|
||||
output.append(CodeCommitDifferencesResponse(json))
|
||||
return output
|
||||
|
||||
def get_file(self, repo_name: str, file_path: str, sha_hash: str, optional: bool = False):
|
||||
"""
|
||||
Retrieve a file from CodeCommit.
|
||||
|
||||
Args:
|
||||
- repo_name: Name of the repository
|
||||
- file_path: Path to the file you are retrieving
|
||||
- sha_hash: Commit hash of the file you are retrieving
|
||||
|
||||
Returns:
|
||||
- File contents
|
||||
|
||||
Boto3 Documentation:
|
||||
- aws codecommit get_file
|
||||
- https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_file.html
|
||||
"""
|
||||
if not file_path:
|
||||
return ""
|
||||
|
||||
if self.boto_client is None:
|
||||
self._connect_boto_client()
|
||||
|
||||
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 ""
|
||||
raise ValueError(f"CodeCommit cannot retrieve file '{file_path}' from repository '{repo_name}'") from e
|
||||
except Exception as e:
|
||||
raise ValueError(f"CodeCommit cannot retrieve file '{file_path}' from repository '{repo_name}'") from e
|
||||
if "fileContent" not in response:
|
||||
raise ValueError(f"File content is empty for file: {file_path}")
|
||||
|
||||
return response.get("fileContent", "")
|
||||
|
||||
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:
|
||||
- CodeCommitPullRequestResponse object
|
||||
|
||||
Boto3 Documentation:
|
||||
- aws codecommit get_pull_request
|
||||
- https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_pull_request.html
|
||||
"""
|
||||
if self.boto_client is None:
|
||||
self._connect_boto_client()
|
||||
|
||||
try:
|
||||
response = self.boto_client.get_pull_request(pullRequestId=str(pr_number))
|
||||
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
|
||||
|
||||
if "pullRequest" not in response:
|
||||
raise ValueError("CodeCommit PR number not found: {pr_number}")
|
||||
|
||||
return CodeCommitPullRequestResponse(response.get("pullRequest", {}))
|
||||
|
||||
def publish_description(self, pr_number: int, pr_title: str, pr_body: str):
|
||||
"""
|
||||
Set the title and description on a pull request
|
||||
|
||||
Args:
|
||||
- pr_number: the AWS CodeCommit pull request number
|
||||
- pr_title: title of the pull request
|
||||
- pr_body: body of the pull request
|
||||
|
||||
Returns:
|
||||
- None
|
||||
|
||||
Boto3 Documentation:
|
||||
- aws codecommit update_pull_request_title
|
||||
- https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/update_pull_request_title.html
|
||||
- aws codecommit update_pull_request_description
|
||||
- https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/update_pull_request_description.html
|
||||
"""
|
||||
if self.boto_client is None:
|
||||
self._connect_boto_client()
|
||||
|
||||
try:
|
||||
self.boto_client.update_pull_request_title(pullRequestId=str(pr_number), title=pr_title)
|
||||
self.boto_client.update_pull_request_description(pullRequestId=str(pr_number), description=pr_body)
|
||||
except botocore.exceptions.ClientError as e:
|
||||
if e.response["Error"]["Code"] == 'PullRequestDoesNotExistException':
|
||||
raise ValueError(f"PR number does not exist: {pr_number}") from e
|
||||
if e.response["Error"]["Code"] == 'InvalidTitleException':
|
||||
raise ValueError(f"Invalid title for PR number: {pr_number}") from e
|
||||
if e.response["Error"]["Code"] == 'InvalidDescriptionException':
|
||||
raise ValueError(f"Invalid description for PR number: {pr_number}") from e
|
||||
if e.response["Error"]["Code"] == 'PullRequestAlreadyClosedException':
|
||||
raise ValueError(f"PR is already closed: PR number: {pr_number}") from e
|
||||
raise ValueError(f"Boto3 client error calling publish_description") from e
|
||||
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, annotation_file: str = None, annotation_line: int = None):
|
||||
"""
|
||||
Publish a comment to a pull request
|
||||
|
||||
Args:
|
||||
- repo_name: name of the repository
|
||||
- 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)
|
||||
- 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
|
||||
|
||||
Boto3 Documentation:
|
||||
- aws codecommit post_comment_for_pull_request
|
||||
- https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_pull_request.html
|
||||
"""
|
||||
if self.boto_client is None:
|
||||
self._connect_boto_client()
|
||||
|
||||
try:
|
||||
# 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
|
||||
if e.response["Error"]["Code"] == 'PullRequestDoesNotExistException':
|
||||
raise ValueError(f"PR number does not exist: {pr_number}") from e
|
||||
raise ValueError(f"Boto3 client error calling post_comment_for_pull_request") from e
|
||||
except Exception as e:
|
||||
raise ValueError(f"Error calling post_comment_for_pull_request") from e
|
||||
@ -1,495 +0,0 @@
|
||||
import os
|
||||
import re
|
||||
from collections import Counter
|
||||
from typing import List, Optional, Tuple
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from pr_agent.git_providers.codecommit_client import CodeCommitClient
|
||||
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
|
||||
from ..algo.utils import load_large_diff
|
||||
from .git_provider import GitProvider
|
||||
from ..config_loader import get_settings
|
||||
from ..log import get_logger
|
||||
from pr_agent.algo.language_handler import is_valid_file
|
||||
|
||||
class PullRequestCCMimic:
|
||||
"""
|
||||
This class mimics the PullRequest class from the PyGithub library for the CodeCommitProvider.
|
||||
"""
|
||||
|
||||
def __init__(self, title: str, diff_files: List[FilePatchInfo]):
|
||||
self.title = title
|
||||
self.diff_files = diff_files
|
||||
self.description = None
|
||||
self.source_commit = None
|
||||
self.source_branch = None # the branch containing your new code changes
|
||||
self.destination_commit = None
|
||||
self.destination_branch = None # the branch you are going to merge into
|
||||
|
||||
|
||||
class CodeCommitFile:
|
||||
"""
|
||||
This class represents a file in a pull request in CodeCommit.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
a_path: str,
|
||||
a_blob_id: str,
|
||||
b_path: str,
|
||||
b_blob_id: str,
|
||||
edit_type: EDIT_TYPE,
|
||||
):
|
||||
self.a_path = a_path
|
||||
self.a_blob_id = a_blob_id
|
||||
self.b_path = b_path
|
||||
self.b_blob_id = b_blob_id
|
||||
self.edit_type: EDIT_TYPE = edit_type
|
||||
self.filename = b_path if b_path else a_path
|
||||
|
||||
|
||||
class CodeCommitProvider(GitProvider):
|
||||
"""
|
||||
This class implements the GitProvider interface for AWS CodeCommit repositories.
|
||||
"""
|
||||
|
||||
def __init__(self, pr_url: Optional[str] = None, incremental: Optional[bool] = False):
|
||||
self.codecommit_client = CodeCommitClient()
|
||||
self.aws_client = None
|
||||
self.repo_name = None
|
||||
self.pr_num = None
|
||||
self.pr = None
|
||||
self.diff_files = None
|
||||
self.git_files = None
|
||||
self.pr_url = pr_url
|
||||
if pr_url:
|
||||
self.set_pr(pr_url)
|
||||
|
||||
def provider_name(self):
|
||||
return "CodeCommit"
|
||||
|
||||
def is_supported(self, capability: str) -> bool:
|
||||
if capability in [
|
||||
"get_issue_comments",
|
||||
"create_inline_comment",
|
||||
"publish_inline_comments",
|
||||
"get_labels",
|
||||
"gfm_markdown"
|
||||
]:
|
||||
return False
|
||||
return True
|
||||
|
||||
def set_pr(self, pr_url: str):
|
||||
self.repo_name, self.pr_num = self._parse_pr_url(pr_url)
|
||||
self.pr = self._get_pr()
|
||||
|
||||
def get_files(self) -> list[CodeCommitFile]:
|
||||
# bring files from CodeCommit only once
|
||||
if self.git_files:
|
||||
return self.git_files
|
||||
|
||||
self.git_files = []
|
||||
differences = self.codecommit_client.get_differences(self.repo_name, self.pr.destination_commit, self.pr.source_commit)
|
||||
for item in differences:
|
||||
self.git_files.append(CodeCommitFile(item.before_blob_path,
|
||||
item.before_blob_id,
|
||||
item.after_blob_path,
|
||||
item.after_blob_id,
|
||||
CodeCommitProvider._get_edit_type(item.change_type)))
|
||||
return self.git_files
|
||||
|
||||
def get_diff_files(self) -> list[FilePatchInfo]:
|
||||
"""
|
||||
Retrieves the list of files that have been modified, added, deleted, or renamed in a pull request in CodeCommit,
|
||||
along with their content and patch information.
|
||||
|
||||
Returns:
|
||||
diff_files (List[FilePatchInfo]): List of FilePatchInfo objects representing the modified, added, deleted,
|
||||
or renamed files in the merge request.
|
||||
"""
|
||||
# bring files from CodeCommit only once
|
||||
if self.diff_files:
|
||||
return self.diff_files
|
||||
|
||||
self.diff_files = []
|
||||
|
||||
files = self.get_files()
|
||||
for diff_item in files:
|
||||
patch_filename = ""
|
||||
if diff_item.a_blob_id is not None:
|
||||
patch_filename = diff_item.a_path
|
||||
original_file_content_str = self.codecommit_client.get_file(
|
||||
self.repo_name, diff_item.a_path, self.pr.destination_commit)
|
||||
if isinstance(original_file_content_str, (bytes, bytearray)):
|
||||
original_file_content_str = original_file_content_str.decode("utf-8")
|
||||
else:
|
||||
original_file_content_str = ""
|
||||
|
||||
if diff_item.b_blob_id is not None:
|
||||
patch_filename = diff_item.b_path
|
||||
new_file_content_str = self.codecommit_client.get_file(self.repo_name, diff_item.b_path, self.pr.source_commit)
|
||||
if isinstance(new_file_content_str, (bytes, bytearray)):
|
||||
new_file_content_str = new_file_content_str.decode("utf-8")
|
||||
else:
|
||||
new_file_content_str = ""
|
||||
|
||||
patch = load_large_diff(patch_filename, new_file_content_str, original_file_content_str)
|
||||
|
||||
# Store the diffs as a list of FilePatchInfo objects
|
||||
info = FilePatchInfo(
|
||||
original_file_content_str,
|
||||
new_file_content_str,
|
||||
patch,
|
||||
diff_item.b_path,
|
||||
edit_type=diff_item.edit_type,
|
||||
old_filename=None
|
||||
if diff_item.a_path == diff_item.b_path
|
||||
else diff_item.a_path,
|
||||
)
|
||||
# Only add valid files to the diff list
|
||||
# "bad extensions" are set in the language_extensions.toml file
|
||||
# a "valid file" is one that is not in the "bad extensions" list
|
||||
if is_valid_file(info.filename):
|
||||
self.diff_files.append(info)
|
||||
|
||||
return self.diff_files
|
||||
|
||||
def publish_description(self, pr_title: str, pr_body: str):
|
||||
try:
|
||||
self.codecommit_client.publish_description(
|
||||
pr_number=self.pr_num,
|
||||
pr_title=pr_title,
|
||||
pr_body=CodeCommitProvider._add_additional_newlines(pr_body),
|
||||
)
|
||||
except Exception as e:
|
||||
raise ValueError(f"CodeCommit Cannot publish description for PR: {self.pr_num}") from e
|
||||
|
||||
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
|
||||
if is_temporary:
|
||||
get_logger().info(pr_comment)
|
||||
return
|
||||
|
||||
pr_comment = CodeCommitProvider._remove_markdown_html(pr_comment)
|
||||
pr_comment = CodeCommitProvider._add_additional_newlines(pr_comment)
|
||||
|
||||
try:
|
||||
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=pr_comment,
|
||||
)
|
||||
except Exception as e:
|
||||
raise ValueError(f"CodeCommit Cannot publish comment for PR: {self.pr_num}") from e
|
||||
|
||||
def publish_code_suggestions(self, code_suggestions: list) -> bool:
|
||||
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"]):
|
||||
get_logger().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:
|
||||
get_logger().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
|
||||
|
||||
def get_pr_labels(self, update=False):
|
||||
return [""] # not implemented yet
|
||||
|
||||
def remove_initial_comment(self):
|
||||
return "" # not implemented yet
|
||||
|
||||
def remove_comment(self, comment):
|
||||
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 publish_inline_comments(self, comments: list[dict]):
|
||||
raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")
|
||||
|
||||
def get_title(self):
|
||||
return self.pr.title
|
||||
|
||||
def get_pr_id(self):
|
||||
"""
|
||||
Returns the PR ID in the format: "repo_name/pr_number".
|
||||
Note: This is an internal identifier for PR-Agent,
|
||||
and is not the same as the CodeCommit PR identifier.
|
||||
"""
|
||||
try:
|
||||
pr_id = f"{self.repo_name}/{self.pr_num}"
|
||||
return pr_id
|
||||
except:
|
||||
return ""
|
||||
|
||||
def get_languages(self):
|
||||
"""
|
||||
Returns a dictionary of languages, containing the percentage of each language used in the PR.
|
||||
|
||||
Returns:
|
||||
- dict: A dictionary where each key is a language name and the corresponding value is the percentage of that language in the PR.
|
||||
"""
|
||||
commit_files = self.get_files()
|
||||
filenames = [ item.filename for item in commit_files ]
|
||||
extensions = CodeCommitProvider._get_file_extensions(filenames)
|
||||
|
||||
# Calculate the percentage of each file extension in the PR
|
||||
percentages = CodeCommitProvider._get_language_percentages(extensions)
|
||||
|
||||
# The global language_extension_map is a dictionary of languages,
|
||||
# where each dictionary item is a BoxList of extensions.
|
||||
# We want a dictionary of extensions,
|
||||
# where each dictionary item is a language name.
|
||||
# We build that language->extension dictionary here in main_extensions_flat.
|
||||
main_extensions_flat = {}
|
||||
language_extension_map_org = get_settings().language_extension_map_org
|
||||
language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
|
||||
for language, extensions in language_extension_map.items():
|
||||
for ext in extensions:
|
||||
main_extensions_flat[ext] = language
|
||||
|
||||
# Map the file extension/languages to percentages
|
||||
languages = {}
|
||||
for ext, pct in percentages.items():
|
||||
languages[main_extensions_flat.get(ext, "")] = pct
|
||||
|
||||
return languages
|
||||
|
||||
def get_pr_branch(self):
|
||||
return self.pr.source_branch
|
||||
|
||||
def get_pr_description_full(self) -> str:
|
||||
return self.pr.description
|
||||
|
||||
def get_user_id(self):
|
||||
return -1 # not implemented yet
|
||||
|
||||
def get_issue_comments(self):
|
||||
raise NotImplementedError("CodeCommit provider does not support issue comments yet")
|
||||
|
||||
def get_repo_settings(self):
|
||||
# a local ".pr_agent.toml" settings file is optional
|
||||
settings_filename = ".pr_agent.toml"
|
||||
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, disable_eyes: bool = False) -> Optional[int]:
|
||||
get_logger().info("CodeCommit provider does not support eyes reaction yet")
|
||||
return True
|
||||
|
||||
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
|
||||
get_logger().info("CodeCommit provider does not support removing reactions yet")
|
||||
return True
|
||||
|
||||
@staticmethod
|
||||
def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
|
||||
"""
|
||||
Parse the CodeCommit PR URL and return the repository name and PR number.
|
||||
|
||||
Args:
|
||||
- pr_url: the full AWS CodeCommit pull request URL
|
||||
|
||||
Returns:
|
||||
- Tuple[str, int]: A tuple containing the repository name and PR number.
|
||||
"""
|
||||
# Example PR URL:
|
||||
# https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/__MY_REPO__/pull-requests/123456"
|
||||
parsed_url = urlparse(pr_url)
|
||||
|
||||
if not CodeCommitProvider._is_valid_codecommit_hostname(parsed_url.netloc):
|
||||
raise ValueError(f"The provided URL is not a valid CodeCommit URL: {pr_url}")
|
||||
|
||||
path_parts = parsed_url.path.strip("/").split("/")
|
||||
|
||||
if (
|
||||
len(path_parts) < 6
|
||||
or path_parts[0] != "codesuite"
|
||||
or path_parts[1] != "codecommit"
|
||||
or path_parts[2] != "repositories"
|
||||
or path_parts[4] != "pull-requests"
|
||||
):
|
||||
raise ValueError(f"The provided URL does not appear to be a CodeCommit PR URL: {pr_url}")
|
||||
|
||||
repo_name = path_parts[3]
|
||||
|
||||
try:
|
||||
pr_number = int(path_parts[5])
|
||||
except ValueError as e:
|
||||
raise ValueError(f"Unable to convert PR number to integer: '{path_parts[5]}'") from e
|
||||
|
||||
return repo_name, pr_number
|
||||
|
||||
@staticmethod
|
||||
def _is_valid_codecommit_hostname(hostname: str) -> bool:
|
||||
"""
|
||||
Check if the provided hostname is a valid AWS CodeCommit hostname.
|
||||
|
||||
This is not an exhaustive check of AWS region names,
|
||||
but instead uses a regex to check for matching AWS region patterns.
|
||||
|
||||
Args:
|
||||
- hostname: the hostname to check
|
||||
|
||||
Returns:
|
||||
- bool: True if the hostname is valid, False otherwise.
|
||||
"""
|
||||
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.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 targets in one CodeCommit PR
|
||||
# for now, we are only using the first target in the PR
|
||||
if len(response.targets) > 1:
|
||||
get_logger().warning(
|
||||
"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
|
||||
# (This strategy was copied from the LocalGitProvider)
|
||||
mimic = PullRequestCCMimic(response.title, self.diff_files)
|
||||
mimic.description = response.description
|
||||
mimic.source_commit = response.targets[0].source_commit
|
||||
mimic.source_branch = response.targets[0].source_branch
|
||||
mimic.destination_commit = response.targets[0].destination_commit
|
||||
mimic.destination_branch = response.targets[0].destination_branch
|
||||
|
||||
return mimic
|
||||
|
||||
def get_commit_messages(self):
|
||||
return "" # not implemented yet
|
||||
|
||||
@staticmethod
|
||||
def _add_additional_newlines(body: str) -> str:
|
||||
"""
|
||||
Replace single newlines in a PR body with double newlines.
|
||||
|
||||
CodeCommit Markdown does not seem to render as well as GitHub Markdown,
|
||||
so we add additional newlines to the PR body to make it more readable in CodeCommit.
|
||||
|
||||
Args:
|
||||
- body: the PR body
|
||||
|
||||
Returns:
|
||||
- str: the PR body with the double newlines added
|
||||
"""
|
||||
return re.sub(r'(?<!\n)\n(?!\n)', '\n\n', body)
|
||||
|
||||
@staticmethod
|
||||
def _remove_markdown_html(comment: str) -> str:
|
||||
"""
|
||||
Remove the HTML tags from a PR comment.
|
||||
|
||||
CodeCommit Markdown does not seem to render as well as GitHub Markdown,
|
||||
so we remove the HTML tags from the PR comment to make it more readable in CodeCommit.
|
||||
|
||||
Args:
|
||||
- comment: the PR comment
|
||||
|
||||
Returns:
|
||||
- str: the PR comment with the HTML tags removed
|
||||
"""
|
||||
comment = comment.replace("<details>", "")
|
||||
comment = comment.replace("</details>", "")
|
||||
comment = comment.replace("<summary>", "")
|
||||
comment = comment.replace("</summary>", "")
|
||||
return comment
|
||||
|
||||
@staticmethod
|
||||
def _get_edit_type(codecommit_change_type: str):
|
||||
"""
|
||||
Convert the CodeCommit change type string to the EDIT_TYPE enum.
|
||||
The CodeCommit change type string is returned from the get_differences SDK method.
|
||||
|
||||
Args:
|
||||
- codecommit_change_type: the CodeCommit change type string
|
||||
|
||||
Returns:
|
||||
- An EDIT_TYPE enum representing the modified, added, deleted, or renamed file in the PR diff.
|
||||
"""
|
||||
t = codecommit_change_type.upper()
|
||||
edit_type = None
|
||||
if t == "A":
|
||||
edit_type = EDIT_TYPE.ADDED
|
||||
elif t == "D":
|
||||
edit_type = EDIT_TYPE.DELETED
|
||||
elif t == "M":
|
||||
edit_type = EDIT_TYPE.MODIFIED
|
||||
elif t == "R":
|
||||
edit_type = EDIT_TYPE.RENAMED
|
||||
return edit_type
|
||||
|
||||
@staticmethod
|
||||
def _get_file_extensions(filenames):
|
||||
"""
|
||||
Return a list of file extensions from a list of filenames.
|
||||
The returned extensions will include the dot "." prefix,
|
||||
to accommodate for the dots in the existing language_extension_map settings.
|
||||
Filenames with no extension will return an empty string for the extension.
|
||||
|
||||
Args:
|
||||
- filenames: a list of filenames
|
||||
|
||||
Returns:
|
||||
- list: A list of file extensions, including the dot "." prefix.
|
||||
"""
|
||||
extensions = []
|
||||
for filename in filenames:
|
||||
filename, ext = os.path.splitext(filename)
|
||||
if ext:
|
||||
extensions.append(ext.lower())
|
||||
else:
|
||||
extensions.append("")
|
||||
return extensions
|
||||
|
||||
@staticmethod
|
||||
def _get_language_percentages(extensions):
|
||||
"""
|
||||
Return a dictionary containing the programming language name (as the key),
|
||||
and the percentage that language is used (as the value),
|
||||
given a list of file extensions.
|
||||
|
||||
Args:
|
||||
- extensions: a list of file extensions
|
||||
|
||||
Returns:
|
||||
- dict: A dictionary where each key is a language name and the corresponding value is the percentage of that language in the PR.
|
||||
"""
|
||||
total_files = len(extensions)
|
||||
if total_files == 0:
|
||||
return {}
|
||||
|
||||
# Identify language by file extension and count
|
||||
lang_count = Counter(extensions)
|
||||
# Convert counts to percentages
|
||||
lang_percentage = {
|
||||
lang: round(count / total_files * 100) for lang, count in lang_count.items()
|
||||
}
|
||||
return lang_percentage
|
||||
@ -1,399 +0,0 @@
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
import shutil
|
||||
import subprocess
|
||||
import uuid
|
||||
from collections import Counter, namedtuple
|
||||
from pathlib import Path
|
||||
from tempfile import NamedTemporaryFile, mkdtemp
|
||||
|
||||
import requests
|
||||
import urllib3.util
|
||||
from git import Repo
|
||||
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.git_providers.git_provider import GitProvider
|
||||
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
|
||||
from pr_agent.git_providers.local_git_provider import PullRequestMimic
|
||||
from pr_agent.log import get_logger
|
||||
|
||||
|
||||
def _call(*command, **kwargs) -> (int, str, str):
|
||||
res = subprocess.run(
|
||||
command,
|
||||
stdout=subprocess.PIPE,
|
||||
stderr=subprocess.PIPE,
|
||||
check=True,
|
||||
**kwargs,
|
||||
)
|
||||
return res.stdout.decode()
|
||||
|
||||
|
||||
def clone(url, directory):
|
||||
get_logger().info("Cloning %s to %s", url, directory)
|
||||
stdout = _call('git', 'clone', "--depth", "1", url, directory)
|
||||
get_logger().info(stdout)
|
||||
|
||||
|
||||
def fetch(url, refspec, cwd):
|
||||
get_logger().info("Fetching %s %s", url, refspec)
|
||||
stdout = _call(
|
||||
'git', 'fetch', '--depth', '2', url, refspec,
|
||||
cwd=cwd
|
||||
)
|
||||
get_logger().info(stdout)
|
||||
|
||||
|
||||
def checkout(cwd):
|
||||
get_logger().info("Checking out")
|
||||
stdout = _call('git', 'checkout', "FETCH_HEAD", cwd=cwd)
|
||||
get_logger().info(stdout)
|
||||
|
||||
|
||||
def show(*args, cwd=None):
|
||||
get_logger().info("Show")
|
||||
return _call('git', 'show', *args, cwd=cwd)
|
||||
|
||||
|
||||
def diff(*args, cwd=None):
|
||||
get_logger().info("Diff")
|
||||
patch = _call('git', 'diff', *args, cwd=cwd)
|
||||
if not patch:
|
||||
get_logger().warning("No changes found")
|
||||
return
|
||||
return patch
|
||||
|
||||
|
||||
def reset_local_changes(cwd):
|
||||
get_logger().info("Reset local changes")
|
||||
_call('git', 'checkout', "--force", cwd=cwd)
|
||||
|
||||
|
||||
def add_comment(url: urllib3.util.Url, refspec, message):
|
||||
*_, patchset, changenum = refspec.rsplit("/")
|
||||
message = "'" + message.replace("'", "'\"'\"'") + "'"
|
||||
return _call(
|
||||
"ssh",
|
||||
"-p", str(url.port),
|
||||
f"{url.auth}@{url.host}",
|
||||
"gerrit", "review",
|
||||
"--message", message,
|
||||
# "--code-review", score,
|
||||
f"{patchset},{changenum}",
|
||||
)
|
||||
|
||||
|
||||
def list_comments(url: urllib3.util.Url, refspec):
|
||||
*_, patchset, _ = refspec.rsplit("/")
|
||||
stdout = _call(
|
||||
"ssh",
|
||||
"-p", str(url.port),
|
||||
f"{url.auth}@{url.host}",
|
||||
"gerrit", "query",
|
||||
"--comments",
|
||||
"--current-patch-set", patchset,
|
||||
"--format", "JSON",
|
||||
)
|
||||
change_set, *_ = stdout.splitlines()
|
||||
return json.loads(change_set)["currentPatchSet"]["comments"]
|
||||
|
||||
|
||||
def prepare_repo(url: urllib3.util.Url, project, refspec):
|
||||
repo_url = (f"{url.scheme}://{url.auth}@{url.host}:{url.port}/{project}")
|
||||
|
||||
directory = pathlib.Path(mkdtemp())
|
||||
clone(repo_url, directory),
|
||||
fetch(repo_url, refspec, cwd=directory)
|
||||
checkout(cwd=directory)
|
||||
return directory
|
||||
|
||||
|
||||
def adopt_to_gerrit_message(message):
|
||||
lines = message.splitlines()
|
||||
buf = []
|
||||
for line in lines:
|
||||
# remove markdown formatting
|
||||
line = (line.replace("*", "")
|
||||
.replace("``", "`")
|
||||
.replace("<details>", "")
|
||||
.replace("</details>", "")
|
||||
.replace("<summary>", "")
|
||||
.replace("</summary>", ""))
|
||||
|
||||
line = line.strip()
|
||||
if line.startswith('#'):
|
||||
buf.append("\n" +
|
||||
line.replace('#', '').removesuffix(":").strip() +
|
||||
":")
|
||||
continue
|
||||
elif line.startswith('-'):
|
||||
buf.append(line.removeprefix('-').strip())
|
||||
continue
|
||||
else:
|
||||
buf.append(line)
|
||||
return "\n".join(buf).strip()
|
||||
|
||||
|
||||
def add_suggestion(src_filename, context: str, start, end: int):
|
||||
with (
|
||||
NamedTemporaryFile("w", delete=False) as tmp,
|
||||
open(src_filename, "r") as src
|
||||
):
|
||||
lines = src.readlines()
|
||||
tmp.writelines(lines[:start - 1])
|
||||
if context:
|
||||
tmp.write(context)
|
||||
tmp.writelines(lines[end:])
|
||||
|
||||
shutil.copy(tmp.name, src_filename)
|
||||
os.remove(tmp.name)
|
||||
|
||||
|
||||
def upload_patch(patch, path):
|
||||
patch_server_endpoint = get_settings().get(
|
||||
'gerrit.patch_server_endpoint')
|
||||
patch_server_token = get_settings().get(
|
||||
'gerrit.patch_server_token')
|
||||
|
||||
response = requests.post(
|
||||
patch_server_endpoint,
|
||||
json={
|
||||
"content": patch,
|
||||
"path": path,
|
||||
},
|
||||
headers={
|
||||
"Content-Type": "application/json",
|
||||
"Authorization": f"Bearer {patch_server_token}",
|
||||
}
|
||||
)
|
||||
response.raise_for_status()
|
||||
patch_server_endpoint = patch_server_endpoint.rstrip("/")
|
||||
return patch_server_endpoint + "/" + path
|
||||
|
||||
|
||||
class GerritProvider(GitProvider):
|
||||
|
||||
def __init__(self, key: str, incremental=False):
|
||||
self.project, self.refspec = key.split(':')
|
||||
assert self.project, "Project name is required"
|
||||
assert self.refspec, "Refspec is required"
|
||||
base_url = get_settings().get('gerrit.url')
|
||||
assert base_url, "Gerrit URL is required"
|
||||
user = get_settings().get('gerrit.user')
|
||||
assert user, "Gerrit user is required"
|
||||
|
||||
parsed = urllib3.util.parse_url(base_url)
|
||||
self.parsed_url = urllib3.util.parse_url(
|
||||
f"{parsed.scheme}://{user}@{parsed.host}:{parsed.port}"
|
||||
)
|
||||
|
||||
self.repo_path = prepare_repo(
|
||||
self.parsed_url, self.project, self.refspec
|
||||
)
|
||||
self.repo = Repo(self.repo_path)
|
||||
assert self.repo
|
||||
self.pr_url = base_url
|
||||
self.pr = PullRequestMimic(self.get_pr_title(), self.get_diff_files())
|
||||
|
||||
def get_pr_title(self):
|
||||
"""
|
||||
Substitutes the branch-name as the PR-mimic title.
|
||||
"""
|
||||
return self.repo.branches[0].name
|
||||
|
||||
def get_issue_comments(self):
|
||||
comments = list_comments(self.parsed_url, self.refspec)
|
||||
Comments = namedtuple('Comments', ['reversed'])
|
||||
Comment = namedtuple('Comment', ['body'])
|
||||
return Comments([Comment(c['message']) for c in reversed(comments)])
|
||||
|
||||
def get_pr_labels(self, update=False):
|
||||
raise NotImplementedError(
|
||||
'Getting labels is not implemented for the gerrit provider')
|
||||
|
||||
def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False):
|
||||
raise NotImplementedError(
|
||||
'Adding reactions is not implemented for the gerrit provider')
|
||||
|
||||
def remove_reaction(self, issue_comment_id: int, reaction_id: int):
|
||||
raise NotImplementedError(
|
||||
'Removing reactions is not implemented for the gerrit provider')
|
||||
|
||||
def get_commit_messages(self):
|
||||
return [self.repo.head.commit.message]
|
||||
|
||||
def get_repo_settings(self):
|
||||
try:
|
||||
with open(self.repo_path / ".pr_agent.toml", 'rb') as f:
|
||||
contents = f.read()
|
||||
return contents
|
||||
except OSError:
|
||||
return b""
|
||||
|
||||
def get_diff_files(self) -> list[FilePatchInfo]:
|
||||
diffs = self.repo.head.commit.diff(
|
||||
self.repo.head.commit.parents[0], # previous commit
|
||||
create_patch=True,
|
||||
R=True
|
||||
)
|
||||
|
||||
diff_files = []
|
||||
for diff_item in diffs:
|
||||
if diff_item.a_blob is not None:
|
||||
original_file_content_str = (
|
||||
diff_item.a_blob.data_stream.read().decode('utf-8')
|
||||
)
|
||||
else:
|
||||
original_file_content_str = "" # empty file
|
||||
if diff_item.b_blob is not None:
|
||||
new_file_content_str = diff_item.b_blob.data_stream.read(). \
|
||||
decode('utf-8')
|
||||
else:
|
||||
new_file_content_str = "" # empty file
|
||||
edit_type = EDIT_TYPE.MODIFIED
|
||||
if diff_item.new_file:
|
||||
edit_type = EDIT_TYPE.ADDED
|
||||
elif diff_item.deleted_file:
|
||||
edit_type = EDIT_TYPE.DELETED
|
||||
elif diff_item.renamed_file:
|
||||
edit_type = EDIT_TYPE.RENAMED
|
||||
diff_files.append(
|
||||
FilePatchInfo(
|
||||
original_file_content_str,
|
||||
new_file_content_str,
|
||||
diff_item.diff.decode('utf-8'),
|
||||
diff_item.b_path,
|
||||
edit_type=edit_type,
|
||||
old_filename=None
|
||||
if diff_item.a_path == diff_item.b_path
|
||||
else diff_item.a_path
|
||||
)
|
||||
)
|
||||
self.diff_files = diff_files
|
||||
return diff_files
|
||||
|
||||
def get_files(self):
|
||||
diff_index = self.repo.head.commit.diff(
|
||||
self.repo.head.commit.parents[0], # previous commit
|
||||
R=True
|
||||
)
|
||||
# Get the list of changed files
|
||||
diff_files = [item.a_path for item in diff_index]
|
||||
return diff_files
|
||||
|
||||
def get_languages(self):
|
||||
"""
|
||||
Calculate percentage of languages in repository. Used for hunk
|
||||
prioritisation.
|
||||
"""
|
||||
# Get all files in repository
|
||||
filepaths = [Path(item.path) for item in
|
||||
self.repo.tree().traverse() if item.type == 'blob']
|
||||
# Identify language by file extension and count
|
||||
lang_count = Counter(
|
||||
ext.lstrip('.') for filepath in filepaths for ext in
|
||||
[filepath.suffix.lower()])
|
||||
# Convert counts to percentages
|
||||
total_files = len(filepaths)
|
||||
lang_percentage = {lang: count / total_files * 100 for lang, count
|
||||
in lang_count.items()}
|
||||
return lang_percentage
|
||||
|
||||
def get_pr_description_full(self):
|
||||
return self.repo.head.commit.message
|
||||
|
||||
def get_user_id(self):
|
||||
return self.repo.head.commit.author.email
|
||||
|
||||
def is_supported(self, capability: str) -> bool:
|
||||
if capability in [
|
||||
# 'get_issue_comments',
|
||||
'create_inline_comment',
|
||||
'publish_inline_comments',
|
||||
'get_labels',
|
||||
'gfm_markdown'
|
||||
]:
|
||||
return False
|
||||
return True
|
||||
|
||||
def split_suggestion(self, msg) -> tuple[str, str]:
|
||||
is_code_context = False
|
||||
description = []
|
||||
context = []
|
||||
for line in msg.splitlines():
|
||||
if line.startswith('```suggestion'):
|
||||
is_code_context = True
|
||||
continue
|
||||
if line.startswith('```'):
|
||||
is_code_context = False
|
||||
continue
|
||||
if is_code_context:
|
||||
context.append(line)
|
||||
else:
|
||||
description.append(
|
||||
line.replace('*', '')
|
||||
)
|
||||
|
||||
return (
|
||||
'\n'.join(description),
|
||||
'\n'.join(context) + '\n' if context else ''
|
||||
)
|
||||
|
||||
def publish_code_suggestions(self, code_suggestions: list):
|
||||
msg = []
|
||||
for suggestion in code_suggestions:
|
||||
description, code = self.split_suggestion(suggestion['body'])
|
||||
add_suggestion(
|
||||
pathlib.Path(self.repo_path) / suggestion["relevant_file"],
|
||||
code,
|
||||
suggestion["relevant_lines_start"],
|
||||
suggestion["relevant_lines_end"],
|
||||
)
|
||||
patch = diff(cwd=self.repo_path)
|
||||
patch_id = uuid.uuid4().hex[0:4]
|
||||
path = "/".join(["codium-ai", self.refspec, patch_id])
|
||||
full_path = upload_patch(patch, path)
|
||||
reset_local_changes(self.repo_path)
|
||||
msg.append(f'* {description}\n{full_path}')
|
||||
|
||||
if msg:
|
||||
add_comment(self.parsed_url, self.refspec, "\n".join(msg))
|
||||
return True
|
||||
|
||||
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
|
||||
if not is_temporary:
|
||||
msg = adopt_to_gerrit_message(pr_comment)
|
||||
add_comment(self.parsed_url, self.refspec, msg)
|
||||
|
||||
def publish_description(self, pr_title: str, pr_body: str):
|
||||
msg = adopt_to_gerrit_message(pr_body)
|
||||
add_comment(self.parsed_url, self.refspec, pr_title + '\n' + msg)
|
||||
|
||||
def publish_inline_comments(self, comments: list[dict]):
|
||||
raise NotImplementedError(
|
||||
'Publishing inline comments is not implemented for the gerrit '
|
||||
'provider')
|
||||
|
||||
def publish_inline_comment(self, body: str, relevant_file: str,
|
||||
relevant_line_in_file: str):
|
||||
raise NotImplementedError(
|
||||
'Publishing inline comments is not implemented for the gerrit '
|
||||
'provider')
|
||||
|
||||
|
||||
def publish_labels(self, labels):
|
||||
# Not applicable to the local git provider,
|
||||
# but required by the interface
|
||||
pass
|
||||
|
||||
def remove_initial_comment(self):
|
||||
# remove repo, cloned in previous steps
|
||||
# shutil.rmtree(self.repo_path)
|
||||
pass
|
||||
|
||||
def remove_comment(self, comment):
|
||||
pass
|
||||
|
||||
def get_pr_branch(self):
|
||||
return self.repo.head
|
||||
@ -1,11 +1,26 @@
|
||||
from abc import ABC, abstractmethod
|
||||
from dataclasses import dataclass
|
||||
|
||||
# enum EDIT_TYPE (ADDED, DELETED, MODIFIED, RENAMED)
|
||||
from typing import Optional
|
||||
from enum import Enum
|
||||
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.algo.types import FilePatchInfo
|
||||
from pr_agent.log import get_logger
|
||||
|
||||
class EDIT_TYPE(Enum):
|
||||
ADDED = 1
|
||||
DELETED = 2
|
||||
MODIFIED = 3
|
||||
RENAMED = 4
|
||||
|
||||
|
||||
@dataclass
|
||||
class FilePatchInfo:
|
||||
base_file: str
|
||||
head_file: str
|
||||
patch: str
|
||||
filename: str
|
||||
tokens: int = -1
|
||||
edit_type: EDIT_TYPE = EDIT_TYPE.MODIFIED
|
||||
old_filename: str = None
|
||||
|
||||
|
||||
class GitProvider(ABC):
|
||||
@ -22,7 +37,31 @@ class GitProvider(ABC):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def publish_code_suggestions(self, code_suggestions: list) -> bool:
|
||||
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def publish_inline_comments(self, comments: list[dict]):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def publish_code_suggestions(self, code_suggestions: list):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def publish_labels(self, labels):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def remove_initial_comment(self):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
@ -38,236 +77,50 @@ class GitProvider(ABC):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def get_pr_description_full(self) -> str:
|
||||
pass
|
||||
|
||||
def edit_comment(self, comment, body: str):
|
||||
pass
|
||||
|
||||
def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
|
||||
pass
|
||||
|
||||
def get_pr_description(self, *, full: bool = True) -> str:
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.algo.utils import clip_tokens
|
||||
max_tokens_description = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
|
||||
description = self.get_pr_description_full() if full else self.get_user_description()
|
||||
if max_tokens_description:
|
||||
return clip_tokens(description, max_tokens_description)
|
||||
return description
|
||||
|
||||
def get_user_description(self) -> str:
|
||||
if hasattr(self, 'user_description') and not (self.user_description is None):
|
||||
return self.user_description
|
||||
|
||||
description = (self.get_pr_description_full() or "").strip()
|
||||
description_lowercase = description.lower()
|
||||
get_logger().debug(f"Existing description", description=description_lowercase)
|
||||
|
||||
# if the existing description wasn't generated by the pr-agent, just return it as-is
|
||||
if not self._is_generated_by_pr_agent(description_lowercase):
|
||||
get_logger().info(f"Existing description was not generated by the pr-agent")
|
||||
return description
|
||||
|
||||
# if the existing description was generated by the pr-agent, but it doesn't contain a user description,
|
||||
# return nothing (empty string) because it means there is no user description
|
||||
user_description_header = "### **user description**"
|
||||
if user_description_header not in description_lowercase:
|
||||
get_logger().info(f"Existing description was generated by the pr-agent, but it doesn't contain a user description")
|
||||
return ""
|
||||
|
||||
# otherwise, extract the original user description from the existing pr-agent description and return it
|
||||
# user_description_start_position = description_lowercase.find(user_description_header) + len(user_description_header)
|
||||
# return description[user_description_start_position:].split("\n", 1)[-1].strip()
|
||||
|
||||
# the 'user description' is in the beginning. extract and return it
|
||||
possible_headers = self._possible_headers()
|
||||
start_position = description_lowercase.find(user_description_header) + len(user_description_header)
|
||||
end_position = len(description)
|
||||
for header in possible_headers: # try to clip at the next header
|
||||
if header != user_description_header and header in description_lowercase:
|
||||
end_position = min(end_position, description_lowercase.find(header))
|
||||
if end_position != len(description) and end_position > start_position:
|
||||
original_user_description = description[start_position:end_position].strip()
|
||||
if original_user_description.endswith("___"):
|
||||
original_user_description = original_user_description[:-3].strip()
|
||||
else:
|
||||
original_user_description = description.split("___")[0].strip()
|
||||
if original_user_description.lower().startswith(user_description_header):
|
||||
original_user_description = original_user_description[len(user_description_header):].strip()
|
||||
|
||||
get_logger().info(f"Extracted user description from existing description",
|
||||
description=original_user_description)
|
||||
self.user_description = original_user_description
|
||||
return original_user_description
|
||||
|
||||
def _possible_headers(self):
|
||||
return ("### **user description**", "### **pr type**", "### **pr description**", "### **pr labels**", "### **type**", "### **description**",
|
||||
"### **labels**", "### 🤖 generated by pr agent")
|
||||
|
||||
def _is_generated_by_pr_agent(self, description_lowercase: str) -> bool:
|
||||
possible_headers = self._possible_headers()
|
||||
return any(description_lowercase.startswith(header) for header in possible_headers)
|
||||
|
||||
@abstractmethod
|
||||
def get_repo_settings(self):
|
||||
pass
|
||||
|
||||
def get_pr_id(self):
|
||||
return ""
|
||||
|
||||
def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
|
||||
return ""
|
||||
|
||||
#### comments operations ####
|
||||
@abstractmethod
|
||||
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
|
||||
pass
|
||||
|
||||
def publish_persistent_comment(self, pr_comment: str,
|
||||
initial_header: str,
|
||||
update_header: bool = True,
|
||||
name='review',
|
||||
final_update_message=True):
|
||||
self.publish_comment(pr_comment)
|
||||
|
||||
@abstractmethod
|
||||
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
pass
|
||||
|
||||
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
|
||||
absolute_position: int = None):
|
||||
raise NotImplementedError("This git provider does not support creating inline comments yet")
|
||||
|
||||
@abstractmethod
|
||||
def publish_inline_comments(self, comments: list[dict]):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def remove_initial_comment(self):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def remove_comment(self, comment):
|
||||
def get_pr_description(self):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def get_issue_comments(self):
|
||||
pass
|
||||
|
||||
def get_comment_url(self, comment) -> str:
|
||||
return ""
|
||||
|
||||
#### labels operations ####
|
||||
@abstractmethod
|
||||
def publish_labels(self, labels):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def get_pr_labels(self, update=False):
|
||||
pass
|
||||
|
||||
def get_repo_labels(self):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
|
||||
pass
|
||||
|
||||
#### commits operations ####
|
||||
@abstractmethod
|
||||
def get_commit_messages(self):
|
||||
pass
|
||||
|
||||
def get_pr_url(self) -> str:
|
||||
if hasattr(self, 'pr_url'):
|
||||
return self.pr_url
|
||||
return ""
|
||||
|
||||
def get_latest_commit_url(self) -> str:
|
||||
return ""
|
||||
|
||||
def auto_approve(self) -> bool:
|
||||
return False
|
||||
|
||||
def calc_pr_statistics(self, pull_request_data: dict):
|
||||
return {}
|
||||
|
||||
def get_num_of_files(self):
|
||||
try:
|
||||
return len(self.get_diff_files())
|
||||
except Exception as e:
|
||||
return -1
|
||||
|
||||
|
||||
def get_main_pr_language(languages, files) -> str:
|
||||
"""
|
||||
Get the main language of the commit. Return an empty string if cannot determine.
|
||||
"""
|
||||
main_language_str = ""
|
||||
if not languages:
|
||||
get_logger().info("No languages detected")
|
||||
return main_language_str
|
||||
if not files:
|
||||
get_logger().info("No files in diff")
|
||||
return main_language_str
|
||||
|
||||
try:
|
||||
top_language = max(languages, key=languages.get).lower()
|
||||
|
||||
# validate that the specific commit uses the main language
|
||||
extension_list = []
|
||||
for file in files:
|
||||
if not file:
|
||||
continue
|
||||
if isinstance(file, str):
|
||||
file = FilePatchInfo(base_file=None, head_file=None, patch=None, filename=file)
|
||||
extension_list.append(file.filename.rsplit('.')[-1])
|
||||
|
||||
# get the most common extension
|
||||
most_common_extension = '.' + max(set(extension_list), key=extension_list.count)
|
||||
try:
|
||||
language_extension_map_org = get_settings().language_extension_map_org
|
||||
language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
|
||||
most_common_extension = max(set(extension_list), key=extension_list.count)
|
||||
|
||||
if top_language in language_extension_map and most_common_extension in language_extension_map[top_language]:
|
||||
main_language_str = top_language
|
||||
else:
|
||||
for language, extensions in language_extension_map.items():
|
||||
if most_common_extension in extensions:
|
||||
main_language_str = language
|
||||
break
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to get main language: {e}")
|
||||
pass
|
||||
# look for a match. TBD: add more languages, do this systematically
|
||||
if most_common_extension == 'py' and top_language == 'python' or \
|
||||
most_common_extension == 'js' and top_language == 'javascript' or \
|
||||
most_common_extension == 'ts' and top_language == 'typescript' or \
|
||||
most_common_extension == 'go' and top_language == 'go' or \
|
||||
most_common_extension == 'java' and top_language == 'java' or \
|
||||
most_common_extension == 'c' and top_language == 'c' or \
|
||||
most_common_extension == 'cpp' and top_language == 'c++' or \
|
||||
most_common_extension == 'cs' and top_language == 'c#' or \
|
||||
most_common_extension == 'swift' and top_language == 'swift' or \
|
||||
most_common_extension == 'php' and top_language == 'php' or \
|
||||
most_common_extension == 'rb' and top_language == 'ruby' or \
|
||||
most_common_extension == 'rs' and top_language == 'rust' or \
|
||||
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':
|
||||
main_language_str = top_language
|
||||
|
||||
## old approach:
|
||||
# most_common_extension = max(set(extension_list), key=extension_list.count)
|
||||
# if most_common_extension == 'py' and top_language == 'python' or \
|
||||
# most_common_extension == 'js' and top_language == 'javascript' or \
|
||||
# most_common_extension == 'ts' and top_language == 'typescript' or \
|
||||
# most_common_extension == 'tsx' and top_language == 'typescript' or \
|
||||
# most_common_extension == 'go' and top_language == 'go' or \
|
||||
# most_common_extension == 'java' and top_language == 'java' or \
|
||||
# most_common_extension == 'c' and top_language == 'c' or \
|
||||
# most_common_extension == 'cpp' and top_language == 'c++' or \
|
||||
# most_common_extension == 'cs' and top_language == 'c#' or \
|
||||
# most_common_extension == 'swift' and top_language == 'swift' or \
|
||||
# most_common_extension == 'php' and top_language == 'php' or \
|
||||
# most_common_extension == 'rb' and top_language == 'ruby' or \
|
||||
# most_common_extension == 'rs' and top_language == 'rust' or \
|
||||
# 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 == top_language:
|
||||
# main_language_str = top_language
|
||||
|
||||
except Exception as e:
|
||||
get_logger().exception(e)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return main_language_str
|
||||
@ -277,13 +130,5 @@ class IncrementalPR:
|
||||
def __init__(self, is_incremental: bool = False):
|
||||
self.is_incremental = is_incremental
|
||||
self.commits_range = None
|
||||
self.first_new_commit = None
|
||||
self.last_seen_commit = None
|
||||
|
||||
@property
|
||||
def first_new_commit_sha(self):
|
||||
return None if self.first_new_commit is None else self.first_new_commit.sha
|
||||
|
||||
@property
|
||||
def last_seen_commit_sha(self):
|
||||
return None if self.last_seen_commit is None else self.last_seen_commit.sha
|
||||
self.first_new_commit_sha = None
|
||||
self.last_seen_commit_sha = None
|
||||
|
||||
@ -1,238 +1,113 @@
|
||||
import time
|
||||
import hashlib
|
||||
import logging
|
||||
from datetime import datetime
|
||||
from typing import Optional, Tuple
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from github import AppAuthentication, Auth, Github, GithubException
|
||||
from retry import retry
|
||||
from starlette_context import context
|
||||
from github import AppAuthentication, Github, Auth
|
||||
|
||||
from pr_agent.config_loader import settings
|
||||
|
||||
from .git_provider import FilePatchInfo, GitProvider, IncrementalPR
|
||||
from ..algo.language_handler import is_valid_file
|
||||
from ..algo.utils import load_large_diff, clip_tokens, find_line_number_of_relevant_line_in_file
|
||||
from ..config_loader import get_settings
|
||||
from ..log import get_logger
|
||||
from ..servers.utils import RateLimitExceeded
|
||||
from .git_provider import GitProvider, IncrementalPR
|
||||
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
|
||||
from ..algo.utils import load_large_diff
|
||||
|
||||
|
||||
class GithubProvider(GitProvider):
|
||||
def __init__(self, pr_url: Optional[str] = None, incremental=IncrementalPR(False)):
|
||||
self.repo_obj = None
|
||||
try:
|
||||
self.installation_id = context.get("installation_id", None)
|
||||
except Exception:
|
||||
self.installation_id = None
|
||||
self.base_url = get_settings().get("GITHUB.BASE_URL", "https://api.github.com").rstrip("/")
|
||||
self.base_url_html = self.base_url.split("api/")[0].rstrip("/") if "api/" in self.base_url else "https://github.com"
|
||||
self.installation_id = settings.get("GITHUB.INSTALLATION_ID")
|
||||
self.github_client = self._get_github_client()
|
||||
self.repo = None
|
||||
self.pr_num = None
|
||||
self.pr = None
|
||||
self.github_user_id = None
|
||||
self.diff_files = None
|
||||
self.git_files = None
|
||||
self.incremental = incremental
|
||||
if pr_url and 'pull' in pr_url:
|
||||
if pr_url:
|
||||
self.set_pr(pr_url)
|
||||
self.pr_commits = list(self.pr.get_commits())
|
||||
if self.incremental.is_incremental:
|
||||
self.unreviewed_files_set = dict()
|
||||
self.get_incremental_commits()
|
||||
self.last_commit_id = self.pr_commits[-1]
|
||||
self.pr_url = self.get_pr_url() # pr_url for github actions can be as api.github.com, so we need to get the url from the pr object
|
||||
else:
|
||||
self.pr_commits = None
|
||||
self.last_commit_id = list(self.pr.get_commits())[-1]
|
||||
|
||||
def is_supported(self, capability: str) -> bool:
|
||||
return True
|
||||
|
||||
def get_pr_url(self) -> str:
|
||||
return self.pr.html_url
|
||||
return f"https://github.com/{self.repo}/pull/{self.pr_num}"
|
||||
|
||||
def set_pr(self, pr_url: str):
|
||||
self.repo, self.pr_num = self._parse_pr_url(pr_url)
|
||||
self.pr = self._get_pr()
|
||||
if self.incremental.is_incremental:
|
||||
self.get_incremental_commits()
|
||||
|
||||
def get_incremental_commits(self):
|
||||
if not self.pr_commits:
|
||||
self.pr_commits = list(self.pr.get_commits())
|
||||
self.commits = list(self.pr.get_commits())
|
||||
|
||||
self.previous_review = self.get_previous_review(full=True, incremental=True)
|
||||
self.get_previous_review()
|
||||
if self.previous_review:
|
||||
self.incremental.commits_range = self.get_commit_range()
|
||||
# Get all files changed during the commit range
|
||||
|
||||
self.file_set = dict()
|
||||
for commit in self.incremental.commits_range:
|
||||
if commit.commit.message.startswith(f"Merge branch '{self._get_repo().default_branch}'"):
|
||||
get_logger().info(f"Skipping merge commit {commit.commit.message}")
|
||||
logging.info(f"Skipping merge commit {commit.commit.message}")
|
||||
continue
|
||||
self.unreviewed_files_set.update({file.filename: file for file in commit.files})
|
||||
else:
|
||||
get_logger().info("No previous review found, will review the entire PR")
|
||||
self.incremental.is_incremental = False
|
||||
self.file_set.update({file.filename: file for file in commit.files})
|
||||
|
||||
def get_commit_range(self):
|
||||
last_review_time = self.previous_review.created_at
|
||||
first_new_commit_index = None
|
||||
for index in range(len(self.pr_commits) - 1, -1, -1):
|
||||
if self.pr_commits[index].commit.author.date > last_review_time:
|
||||
self.incremental.first_new_commit = self.pr_commits[index]
|
||||
first_new_commit_index = 0
|
||||
for index in range(len(self.commits) - 1, -1, -1):
|
||||
if self.commits[index].commit.author.date > last_review_time:
|
||||
self.incremental.first_new_commit_sha = self.commits[index].sha
|
||||
first_new_commit_index = index
|
||||
else:
|
||||
self.incremental.last_seen_commit = self.pr_commits[index]
|
||||
self.incremental.last_seen_commit_sha = self.commits[index].sha
|
||||
break
|
||||
return self.pr_commits[first_new_commit_index:] if first_new_commit_index is not None else []
|
||||
return self.commits[first_new_commit_index:]
|
||||
|
||||
def get_previous_review(self, *, full: bool, incremental: bool):
|
||||
if not (full or incremental):
|
||||
raise ValueError("At least one of full or incremental must be True")
|
||||
if not getattr(self, "comments", None):
|
||||
self.comments = list(self.pr.get_issue_comments())
|
||||
prefixes = []
|
||||
if full:
|
||||
prefixes.append("## PR Review")
|
||||
if incremental:
|
||||
prefixes.append("## Incremental PR Review")
|
||||
def get_previous_review(self):
|
||||
self.previous_review = None
|
||||
self.comments = list(self.pr.get_issue_comments())
|
||||
for index in range(len(self.comments) - 1, -1, -1):
|
||||
if any(self.comments[index].body.startswith(prefix) for prefix in prefixes):
|
||||
return self.comments[index]
|
||||
if self.comments[index].body.startswith("## PR Analysis"):
|
||||
self.previous_review = self.comments[index]
|
||||
break
|
||||
|
||||
def get_files(self):
|
||||
if self.incremental.is_incremental and self.unreviewed_files_set:
|
||||
return self.unreviewed_files_set.values()
|
||||
try:
|
||||
git_files = context.get("git_files", None)
|
||||
if git_files:
|
||||
return git_files
|
||||
self.git_files = self.pr.get_files()
|
||||
context["git_files"] = self.git_files
|
||||
return self.git_files
|
||||
except Exception:
|
||||
if not self.git_files:
|
||||
self.git_files = self.pr.get_files()
|
||||
return self.git_files
|
||||
if self.incremental.is_incremental and self.file_set:
|
||||
return self.file_set.values()
|
||||
return self.pr.get_files()
|
||||
|
||||
def get_num_of_files(self):
|
||||
if self.git_files:
|
||||
return self.git_files.totalCount
|
||||
else:
|
||||
return -1
|
||||
|
||||
@retry(exceptions=RateLimitExceeded,
|
||||
tries=get_settings().github.ratelimit_retries, delay=2, backoff=2, jitter=(1, 3))
|
||||
def get_diff_files(self) -> list[FilePatchInfo]:
|
||||
"""
|
||||
Retrieves the list of files that have been modified, added, deleted, or renamed in a pull request in GitHub,
|
||||
along with their content and patch information.
|
||||
|
||||
Returns:
|
||||
diff_files (List[FilePatchInfo]): List of FilePatchInfo objects representing the modified, added, deleted,
|
||||
or renamed files in the merge request.
|
||||
"""
|
||||
try:
|
||||
try:
|
||||
diff_files = context.get("diff_files", None)
|
||||
if diff_files:
|
||||
return diff_files
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
if self.diff_files:
|
||||
return self.diff_files
|
||||
|
||||
files = self.get_files()
|
||||
diff_files = []
|
||||
|
||||
for file in files:
|
||||
if not is_valid_file(file.filename):
|
||||
continue
|
||||
|
||||
new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha) # communication with GitHub
|
||||
files = self.get_files()
|
||||
diff_files = []
|
||||
for file in files:
|
||||
if is_valid_file(file.filename):
|
||||
new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha)
|
||||
patch = file.patch
|
||||
|
||||
if self.incremental.is_incremental and self.unreviewed_files_set:
|
||||
if self.incremental.is_incremental and self.file_set:
|
||||
original_file_content_str = self._get_pr_file_content(file, self.incremental.last_seen_commit_sha)
|
||||
patch = load_large_diff(file.filename, new_file_content_str, original_file_content_str)
|
||||
self.unreviewed_files_set[file.filename] = patch
|
||||
patch = load_large_diff(file,
|
||||
new_file_content_str,
|
||||
original_file_content_str,
|
||||
None)
|
||||
self.file_set[file.filename] = patch
|
||||
else:
|
||||
original_file_content_str = self._get_pr_file_content(file, self.pr.base.sha)
|
||||
if not patch:
|
||||
patch = load_large_diff(file.filename, new_file_content_str, original_file_content_str)
|
||||
|
||||
if file.status == 'added':
|
||||
edit_type = EDIT_TYPE.ADDED
|
||||
elif file.status == 'removed':
|
||||
edit_type = EDIT_TYPE.DELETED
|
||||
elif file.status == 'renamed':
|
||||
edit_type = EDIT_TYPE.RENAMED
|
||||
elif file.status == 'modified':
|
||||
edit_type = EDIT_TYPE.MODIFIED
|
||||
else:
|
||||
get_logger().error(f"Unknown edit type: {file.status}")
|
||||
edit_type = EDIT_TYPE.UNKNOWN
|
||||
|
||||
# count number of lines added and removed
|
||||
patch_lines = patch.splitlines(keepends=True)
|
||||
num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
|
||||
num_minus_lines = len([line for line in patch_lines if line.startswith('-')])
|
||||
file_patch_canonical_structure = FilePatchInfo(original_file_content_str, new_file_content_str, patch,
|
||||
file.filename, edit_type=edit_type,
|
||||
num_plus_lines=num_plus_lines,
|
||||
num_minus_lines=num_minus_lines,)
|
||||
diff_files.append(file_patch_canonical_structure)
|
||||
|
||||
self.diff_files = diff_files
|
||||
try:
|
||||
context["diff_files"] = diff_files
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return diff_files
|
||||
|
||||
except GithubException.RateLimitExceededException as e:
|
||||
get_logger().error(f"Rate limit exceeded for GitHub API. Original message: {e}")
|
||||
raise RateLimitExceeded("Rate limit exceeded for GitHub API.") from e
|
||||
diff_files.append(
|
||||
FilePatchInfo(original_file_content_str, new_file_content_str, patch, file.filename))
|
||||
self.diff_files = diff_files
|
||||
return diff_files
|
||||
|
||||
def publish_description(self, pr_title: str, pr_body: str):
|
||||
self.pr.edit(title=pr_title, body=pr_body)
|
||||
|
||||
def get_latest_commit_url(self) -> str:
|
||||
return self.last_commit_id.html_url
|
||||
|
||||
def get_comment_url(self, comment) -> str:
|
||||
return comment.html_url
|
||||
|
||||
def publish_persistent_comment(self, pr_comment: str,
|
||||
initial_header: str,
|
||||
update_header: bool = True,
|
||||
name='review',
|
||||
final_update_message=True):
|
||||
prev_comments = list(self.pr.get_issue_comments())
|
||||
for comment in prev_comments:
|
||||
body = comment.body
|
||||
if body.startswith(initial_header):
|
||||
latest_commit_url = self.get_latest_commit_url()
|
||||
comment_url = self.get_comment_url(comment)
|
||||
if update_header:
|
||||
updated_header = f"{initial_header}\n\n### ({name.capitalize()} updated until commit {latest_commit_url})\n"
|
||||
pr_comment_updated = pr_comment.replace(initial_header, updated_header)
|
||||
else:
|
||||
pr_comment_updated = pr_comment
|
||||
get_logger().info(f"Persistent mode- updating comment {comment_url} to latest review message")
|
||||
response = comment.edit(pr_comment_updated)
|
||||
if final_update_message:
|
||||
self.publish_comment(
|
||||
f"**[Persistent {name}]({comment_url})** updated to latest commit {latest_commit_url}")
|
||||
return
|
||||
self.publish_comment(pr_comment)
|
||||
# self.pr.create_issue_comment(pr_comment)
|
||||
|
||||
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
|
||||
if is_temporary and not get_settings().config.publish_output_progress:
|
||||
get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
|
||||
if is_temporary and not settings.config.publish_output_progress:
|
||||
logging.debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
|
||||
return
|
||||
|
||||
response = self.pr.create_issue_comment(pr_comment)
|
||||
if hasattr(response, "user") and hasattr(response.user, "login"):
|
||||
self.github_user_id = response.user.login
|
||||
@ -240,137 +115,41 @@ class GithubProvider(GitProvider):
|
||||
if not hasattr(self.pr, 'comments_list'):
|
||||
self.pr.comments_list = []
|
||||
self.pr.comments_list.append(response)
|
||||
return response
|
||||
|
||||
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
self.publish_inline_comments([self.create_inline_comment(body, relevant_file, relevant_line_in_file)])
|
||||
|
||||
|
||||
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
|
||||
absolute_position: int = None):
|
||||
position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files,
|
||||
relevant_file.strip('`'),
|
||||
relevant_line_in_file,
|
||||
absolute_position)
|
||||
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
|
||||
position = -1
|
||||
for file in self.diff_files:
|
||||
if file.filename.strip() == relevant_file:
|
||||
patch = file.patch
|
||||
patch_lines = patch.splitlines()
|
||||
for i, line in enumerate(patch_lines):
|
||||
if relevant_line_in_file in line:
|
||||
position = i
|
||||
break
|
||||
elif relevant_line_in_file[0] == '+' and relevant_line_in_file[1:].lstrip() in line:
|
||||
# The model often adds a '+' to the beginning of the relevant_line_in_file even if originally
|
||||
# it's a context line
|
||||
position = i
|
||||
break
|
||||
if position == -1:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
|
||||
if settings.config.verbosity_level >= 2:
|
||||
logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
|
||||
subject_type = "FILE"
|
||||
else:
|
||||
subject_type = "LINE"
|
||||
path = relevant_file.strip()
|
||||
# placeholder for future API support (already supported in single inline comment)
|
||||
# return dict(body=body, path=path, position=position, subject_type=subject_type)
|
||||
return dict(body=body, path=path, position=position) if subject_type == "LINE" else {}
|
||||
|
||||
def publish_inline_comments(self, comments: list[dict], disable_fallback: bool = False):
|
||||
try:
|
||||
# publish all comments in a single message
|
||||
self.pr.create_review(commit=self.last_commit_id, comments=comments)
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to publish inline comments")
|
||||
def publish_inline_comments(self, comments: list[dict]):
|
||||
self.pr.create_review(commit=self.last_commit_id, comments=comments)
|
||||
|
||||
if (getattr(e, "status", None) == 422
|
||||
and get_settings().github.publish_inline_comments_fallback_with_verification and not disable_fallback):
|
||||
pass # continue to try _publish_inline_comments_fallback_with_verification
|
||||
else:
|
||||
raise e # will end up with publishing the comments one by one
|
||||
|
||||
try:
|
||||
self._publish_inline_comments_fallback_with_verification(comments)
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to publish inline code comments fallback, error: {e}")
|
||||
raise e
|
||||
|
||||
def _publish_inline_comments_fallback_with_verification(self, comments: list[dict]):
|
||||
"""
|
||||
Check each inline comment separately against the GitHub API and discard of invalid comments,
|
||||
then publish all the remaining valid comments in a single review.
|
||||
For invalid comments, also try removing the suggestion part and posting the comment just on the first line.
|
||||
"""
|
||||
verified_comments, invalid_comments = self._verify_code_comments(comments)
|
||||
|
||||
# publish as a group the verified comments
|
||||
if verified_comments:
|
||||
try:
|
||||
self.pr.create_review(commit=self.last_commit_id, comments=verified_comments)
|
||||
except:
|
||||
pass
|
||||
|
||||
# try to publish one by one the invalid comments as a one-line code comment
|
||||
if invalid_comments and get_settings().github.try_fix_invalid_inline_comments:
|
||||
fixed_comments_as_one_liner = self._try_fix_invalid_inline_comments(
|
||||
[comment for comment, _ in invalid_comments])
|
||||
for comment in fixed_comments_as_one_liner:
|
||||
try:
|
||||
self.publish_inline_comments([comment], disable_fallback=True)
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Published invalid comment as a single line comment: {comment}")
|
||||
except:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to publish invalid comment as a single line comment: {comment}")
|
||||
|
||||
def _verify_code_comment(self, comment: dict):
|
||||
is_verified = False
|
||||
e = None
|
||||
try:
|
||||
# event ="" # By leaving this blank, you set the review action state to PENDING
|
||||
input = dict(commit_id=self.last_commit_id.sha, comments=[comment])
|
||||
headers, data = self.pr._requester.requestJsonAndCheck(
|
||||
"POST", f"{self.pr.url}/reviews", input=input)
|
||||
pending_review_id = data["id"]
|
||||
is_verified = True
|
||||
except Exception as err:
|
||||
is_verified = False
|
||||
pending_review_id = None
|
||||
e = err
|
||||
if pending_review_id is not None:
|
||||
try:
|
||||
self.pr._requester.requestJsonAndCheck("DELETE", f"{self.pr.url}/reviews/{pending_review_id}")
|
||||
except Exception:
|
||||
pass
|
||||
return is_verified, e
|
||||
|
||||
def _verify_code_comments(self, comments: list[dict]) -> tuple[list[dict], list[tuple[dict, Exception]]]:
|
||||
"""Very each comment against the GitHub API and return 2 lists: 1 of verified and 1 of invalid comments"""
|
||||
verified_comments = []
|
||||
invalid_comments = []
|
||||
for comment in comments:
|
||||
time.sleep(1) # for avoiding secondary rate limit
|
||||
is_verified, e = self._verify_code_comment(comment)
|
||||
if is_verified:
|
||||
verified_comments.append(comment)
|
||||
else:
|
||||
invalid_comments.append((comment, e))
|
||||
return verified_comments, invalid_comments
|
||||
|
||||
def _try_fix_invalid_inline_comments(self, invalid_comments: list[dict]) -> list[dict]:
|
||||
"""
|
||||
Try fixing invalid comments by removing the suggestion part and setting the comment just on the first line.
|
||||
Return only comments that have been modified in some way.
|
||||
This is a best-effort attempt to fix invalid comments, and should be verified accordingly.
|
||||
"""
|
||||
import copy
|
||||
fixed_comments = []
|
||||
for comment in invalid_comments:
|
||||
try:
|
||||
fixed_comment = copy.deepcopy(comment) # avoid modifying the original comment dict for later logging
|
||||
if "```suggestion" in comment["body"]:
|
||||
fixed_comment["body"] = comment["body"].split("```suggestion")[0]
|
||||
if "start_line" in comment:
|
||||
fixed_comment["line"] = comment["start_line"]
|
||||
del fixed_comment["start_line"]
|
||||
if "start_side" in comment:
|
||||
fixed_comment["side"] = comment["start_side"]
|
||||
del fixed_comment["start_side"]
|
||||
if fixed_comment != comment:
|
||||
fixed_comments.append(fixed_comment)
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to fix inline comment, error: {e}")
|
||||
return fixed_comments
|
||||
|
||||
def publish_code_suggestions(self, code_suggestions: list) -> bool:
|
||||
def publish_code_suggestions(self, code_suggestions: list):
|
||||
"""
|
||||
Publishes code suggestions as comments on the PR.
|
||||
"""
|
||||
@ -382,14 +161,14 @@ class GithubProvider(GitProvider):
|
||||
relevant_lines_end = suggestion['relevant_lines_end']
|
||||
|
||||
if not relevant_lines_start or relevant_lines_start == -1:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().exception(
|
||||
if settings.config.verbosity_level >= 2:
|
||||
logging.exception(
|
||||
f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
|
||||
continue
|
||||
|
||||
if relevant_lines_end < relevant_lines_start:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().exception(f"Failed to publish code suggestion, "
|
||||
if settings.config.verbosity_level >= 2:
|
||||
logging.exception(f"Failed to publish code suggestion, "
|
||||
f"relevant_lines_end is {relevant_lines_end} and "
|
||||
f"relevant_lines_start is {relevant_lines_start}")
|
||||
continue
|
||||
@ -412,39 +191,20 @@ class GithubProvider(GitProvider):
|
||||
post_parameters_list.append(post_parameters)
|
||||
|
||||
try:
|
||||
self.publish_inline_comments(post_parameters_list)
|
||||
self.pr.create_review(commit=self.last_commit_id, comments=post_parameters_list)
|
||||
return True
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().error(f"Failed to publish code suggestion, error: {e}")
|
||||
if settings.config.verbosity_level >= 2:
|
||||
logging.error(f"Failed to publish code suggestion, error: {e}")
|
||||
return False
|
||||
|
||||
def edit_comment(self, comment, body: str):
|
||||
comment.edit(body=body)
|
||||
|
||||
def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
|
||||
try:
|
||||
# self.pr.get_issue_comment(comment_id).edit(body)
|
||||
headers, data_patch = self.pr._requester.requestJsonAndCheck(
|
||||
"POST", f"{self.base_url}/repos/{self.repo}/pulls/{self.pr_num}/comments/{comment_id}/replies",
|
||||
input={"body": body}
|
||||
)
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to reply comment, error: {e}")
|
||||
|
||||
def remove_initial_comment(self):
|
||||
try:
|
||||
for comment in getattr(self.pr, 'comments_list', []):
|
||||
if comment.is_temporary:
|
||||
self.remove_comment(comment)
|
||||
comment.delete()
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to remove initial comment, error: {e}")
|
||||
|
||||
def remove_comment(self, comment):
|
||||
try:
|
||||
comment.delete()
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to remove comment, error: {e}")
|
||||
logging.exception(f"Failed to remove initial comment, error: {e}")
|
||||
|
||||
def get_title(self):
|
||||
return self.pr.title
|
||||
@ -456,20 +216,19 @@ class GithubProvider(GitProvider):
|
||||
def get_pr_branch(self):
|
||||
return self.pr.head.ref
|
||||
|
||||
def get_pr_description_full(self):
|
||||
def get_pr_description(self):
|
||||
return self.pr.body
|
||||
|
||||
def get_user_id(self):
|
||||
if not self.github_user_id:
|
||||
try:
|
||||
self.github_user_id = self.github_client.get_user().raw_data['login']
|
||||
self.github_user_id = self.github_client.get_user().login
|
||||
except Exception as e:
|
||||
self.github_user_id = ""
|
||||
# logging.exception(f"Failed to get user id, error: {e}")
|
||||
logging.exception(f"Failed to get user id, error: {e}")
|
||||
return self.github_user_id
|
||||
|
||||
def get_notifications(self, since: datetime):
|
||||
deployment_type = get_settings().get("GITHUB.DEPLOYMENT_TYPE", "user")
|
||||
deployment_type = settings.get("GITHUB.DEPLOYMENT_TYPE", "user")
|
||||
|
||||
if deployment_type != 'user':
|
||||
raise ValueError("Deployment mode must be set to 'user' to get notifications")
|
||||
@ -480,41 +239,6 @@ class GithubProvider(GitProvider):
|
||||
def get_issue_comments(self):
|
||||
return self.pr.get_issue_comments()
|
||||
|
||||
def get_repo_settings(self):
|
||||
try:
|
||||
# contents = self.repo_obj.get_contents(".pr_agent.toml", ref=self.pr.head.sha).decoded_content
|
||||
|
||||
# more logical to take 'pr_agent.toml' from the default branch
|
||||
contents = self.repo_obj.get_contents(".pr_agent.toml").decoded_content
|
||||
return contents
|
||||
except Exception:
|
||||
return ""
|
||||
|
||||
def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
|
||||
if disable_eyes:
|
||||
return None
|
||||
try:
|
||||
headers, data_patch = self.pr._requester.requestJsonAndCheck(
|
||||
"POST", f"{self.base_url}/repos/{self.repo}/issues/comments/{issue_comment_id}/reactions",
|
||||
input={"content": "eyes"}
|
||||
)
|
||||
return data_patch.get("id", None)
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to add eyes reaction, error: {e}")
|
||||
return None
|
||||
|
||||
def remove_reaction(self, issue_comment_id: int, reaction_id: str) -> bool:
|
||||
try:
|
||||
# self.pr.get_issue_comment(issue_comment_id).delete_reaction(reaction_id)
|
||||
headers, data_patch = self.pr._requester.requestJsonAndCheck(
|
||||
"DELETE",
|
||||
f"{self.base_url}/repos/{self.repo}/issues/comments/{issue_comment_id}/reactions/{reaction_id}"
|
||||
)
|
||||
return True
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to remove eyes reaction, error: {e}")
|
||||
return False
|
||||
|
||||
@staticmethod
|
||||
def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
|
||||
parsed_url = urlparse(pr_url)
|
||||
@ -544,58 +268,29 @@ class GithubProvider(GitProvider):
|
||||
|
||||
return repo_name, pr_number
|
||||
|
||||
@staticmethod
|
||||
def _parse_issue_url(issue_url: str) -> Tuple[str, int]:
|
||||
parsed_url = urlparse(issue_url)
|
||||
|
||||
if 'github.com' not in parsed_url.netloc:
|
||||
raise ValueError("The provided URL is not a valid GitHub URL")
|
||||
|
||||
path_parts = parsed_url.path.strip('/').split('/')
|
||||
if 'api.github.com' in parsed_url.netloc:
|
||||
if len(path_parts) < 5 or path_parts[3] != 'issues':
|
||||
raise ValueError("The provided URL does not appear to be a GitHub ISSUE URL")
|
||||
repo_name = '/'.join(path_parts[1:3])
|
||||
try:
|
||||
issue_number = int(path_parts[4])
|
||||
except ValueError as e:
|
||||
raise ValueError("Unable to convert issue number to integer") from e
|
||||
return repo_name, issue_number
|
||||
|
||||
if len(path_parts) < 4 or path_parts[2] != 'issues':
|
||||
raise ValueError("The provided URL does not appear to be a GitHub PR issue")
|
||||
|
||||
repo_name = '/'.join(path_parts[:2])
|
||||
try:
|
||||
issue_number = int(path_parts[3])
|
||||
except ValueError as e:
|
||||
raise ValueError("Unable to convert issue number to integer") from e
|
||||
|
||||
return repo_name, issue_number
|
||||
|
||||
def _get_github_client(self):
|
||||
deployment_type = get_settings().get("GITHUB.DEPLOYMENT_TYPE", "user")
|
||||
deployment_type = settings.get("GITHUB.DEPLOYMENT_TYPE", "user")
|
||||
|
||||
if deployment_type == 'app':
|
||||
try:
|
||||
private_key = get_settings().github.private_key
|
||||
app_id = get_settings().github.app_id
|
||||
private_key = settings.github.private_key
|
||||
app_id = settings.github.app_id
|
||||
except AttributeError as e:
|
||||
raise ValueError("GitHub app ID and private key are required when using GitHub app deployment") from e
|
||||
if not self.installation_id:
|
||||
raise ValueError("GitHub app installation ID is required when using GitHub app deployment")
|
||||
auth = AppAuthentication(app_id=app_id, private_key=private_key,
|
||||
installation_id=self.installation_id)
|
||||
return Github(app_auth=auth, base_url=self.base_url)
|
||||
return Github(app_auth=auth)
|
||||
|
||||
if deployment_type == 'user':
|
||||
try:
|
||||
token = get_settings().github.user_token
|
||||
token = settings.github.user_token
|
||||
except AttributeError as e:
|
||||
raise ValueError(
|
||||
"GitHub token is required when using user deployment. See: "
|
||||
"https://github.com/Codium-ai/pr-agent#method-2-run-from-source") from e
|
||||
return Github(auth=Auth.Token(token), base_url=self.base_url)
|
||||
return Github(auth=Auth.Token(token))
|
||||
|
||||
def _get_repo(self):
|
||||
if hasattr(self, 'repo_obj') and \
|
||||
@ -610,41 +305,16 @@ class GithubProvider(GitProvider):
|
||||
def _get_pr(self):
|
||||
return self._get_repo().get_pull(self.pr_num)
|
||||
|
||||
def get_pr_file_content(self, file_path: str, branch: str) -> str:
|
||||
def _get_pr_file_content(self, file: FilePatchInfo, sha: str) -> str:
|
||||
try:
|
||||
file_content_str = str(
|
||||
self._get_repo()
|
||||
.get_contents(file_path, ref=branch)
|
||||
.decoded_content.decode()
|
||||
)
|
||||
file_content_str = str(self._get_repo().get_contents(file.filename, ref=sha).decoded_content.decode())
|
||||
except Exception:
|
||||
file_content_str = ""
|
||||
return file_content_str
|
||||
|
||||
def create_or_update_pr_file(
|
||||
self, file_path: str, branch: str, contents="", message=""
|
||||
) -> None:
|
||||
try:
|
||||
file_obj = self._get_repo().get_contents(file_path, ref=branch)
|
||||
sha1=file_obj.sha
|
||||
except Exception:
|
||||
sha1=""
|
||||
self.repo_obj.update_file(
|
||||
path=file_path,
|
||||
message=message,
|
||||
content=contents,
|
||||
sha=sha1,
|
||||
branch=branch,
|
||||
)
|
||||
|
||||
def _get_pr_file_content(self, file: FilePatchInfo, sha: str) -> str:
|
||||
return self.get_pr_file_content(file.filename, sha)
|
||||
|
||||
def publish_labels(self, pr_types):
|
||||
try:
|
||||
label_color_map = {"Bug fix": "1d76db", "Tests": "e99695", "Bug fix with tests": "c5def5",
|
||||
"Enhancement": "bfd4f2", "Documentation": "d4c5f9",
|
||||
"Other": "d1bcf9"}
|
||||
label_color_map = {"Bug fix": "1d76db", "Tests": "e99695", "Bug fix with tests": "c5def5", "Refactoring": "bfdadc", "Enhancement": "bfd4f2", "Documentation": "d4c5f9", "Other": "d1bcf9"}
|
||||
post_parameters = []
|
||||
for p in pr_types:
|
||||
color = label_color_map.get(p, "d1bcf9") # default to "Other" color
|
||||
@ -652,97 +322,5 @@ class GithubProvider(GitProvider):
|
||||
headers, data = self.pr._requester.requestJsonAndCheck(
|
||||
"PUT", f"{self.pr.issue_url}/labels", input=post_parameters
|
||||
)
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to publish labels, error: {e}")
|
||||
|
||||
def get_pr_labels(self, update=False):
|
||||
try:
|
||||
if not update:
|
||||
labels =self.pr.labels
|
||||
return [label.name for label in labels]
|
||||
else: # obtain the latest labels. Maybe they changed while the AI was running
|
||||
headers, labels = self.pr._requester.requestJsonAndCheck(
|
||||
"GET", f"{self.pr.issue_url}/labels")
|
||||
return [label['name'] for label in labels]
|
||||
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to get labels, error: {e}")
|
||||
return []
|
||||
|
||||
def get_repo_labels(self):
|
||||
labels = self.repo_obj.get_labels()
|
||||
return [label for label in labels]
|
||||
|
||||
def get_commit_messages(self):
|
||||
"""
|
||||
Retrieves the commit messages of a pull request.
|
||||
|
||||
Returns:
|
||||
str: A string containing the commit messages of the pull request.
|
||||
"""
|
||||
max_tokens = get_settings().get("CONFIG.MAX_COMMITS_TOKENS", None)
|
||||
try:
|
||||
commit_list = self.pr.get_commits()
|
||||
commit_messages = [commit.commit.message for commit in commit_list]
|
||||
commit_messages_str = "\n".join([f"{i + 1}. {message}" for i, message in enumerate(commit_messages)])
|
||||
except Exception:
|
||||
commit_messages_str = ""
|
||||
if max_tokens:
|
||||
commit_messages_str = clip_tokens(commit_messages_str, max_tokens)
|
||||
return commit_messages_str
|
||||
|
||||
def generate_link_to_relevant_line_number(self, suggestion) -> str:
|
||||
try:
|
||||
relevant_file = suggestion['relevant_file'].strip('`').strip("'").strip('\n')
|
||||
relevant_line_str = suggestion['relevant_line'].strip('\n')
|
||||
if not relevant_line_str:
|
||||
return ""
|
||||
|
||||
position, absolute_position = find_line_number_of_relevant_line_in_file \
|
||||
(self.diff_files, relevant_file, relevant_line_str)
|
||||
|
||||
if absolute_position != -1:
|
||||
# # link to right file only
|
||||
# link = f"https://github.com/{self.repo}/blob/{self.pr.head.sha}/{relevant_file}" \
|
||||
# + "#" + f"L{absolute_position}"
|
||||
|
||||
# link to diff
|
||||
sha_file = hashlib.sha256(relevant_file.encode('utf-8')).hexdigest()
|
||||
link = f"{self.base_url_html}/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{absolute_position}"
|
||||
return link
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Failed adding line link, error: {e}")
|
||||
|
||||
return ""
|
||||
|
||||
def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
|
||||
sha_file = hashlib.sha256(relevant_file.encode('utf-8')).hexdigest()
|
||||
if relevant_line_start == -1:
|
||||
link = f"{self.base_url_html}/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}"
|
||||
elif relevant_line_end:
|
||||
link = f"{self.base_url_html}/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{relevant_line_start}-R{relevant_line_end}"
|
||||
else:
|
||||
link = f"{self.base_url_html}/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{relevant_line_start}"
|
||||
return link
|
||||
|
||||
|
||||
def get_pr_id(self):
|
||||
try:
|
||||
pr_id = f"{self.repo}/{self.pr_num}"
|
||||
return pr_id
|
||||
except:
|
||||
return ""
|
||||
|
||||
def auto_approve(self) -> bool:
|
||||
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}")
|
||||
return False
|
||||
|
||||
def calc_pr_statistics(self, pull_request_data: dict):
|
||||
return {}
|
||||
logging.exception("Failed to publish labels")
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
import hashlib
|
||||
import logging
|
||||
import re
|
||||
from typing import Optional, Tuple
|
||||
from urllib.parse import urlparse
|
||||
@ -6,45 +6,36 @@ from urllib.parse import urlparse
|
||||
import gitlab
|
||||
from gitlab import GitlabGetError
|
||||
|
||||
from pr_agent.config_loader import settings
|
||||
|
||||
from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
|
||||
from ..algo.language_handler import is_valid_file
|
||||
from ..algo.utils import load_large_diff, clip_tokens, find_line_number_of_relevant_line_in_file
|
||||
from ..config_loader import get_settings
|
||||
from .git_provider import GitProvider
|
||||
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
|
||||
from ..log import get_logger
|
||||
|
||||
|
||||
class DiffNotFoundError(Exception):
|
||||
"""Raised when the diff for a merge request cannot be found."""
|
||||
pass
|
||||
|
||||
class GitLabProvider(GitProvider):
|
||||
|
||||
def __init__(self, merge_request_url: Optional[str] = None, incremental: Optional[bool] = False):
|
||||
gitlab_url = get_settings().get("GITLAB.URL", None)
|
||||
gitlab_url = settings.get("GITLAB.URL", None)
|
||||
if not gitlab_url:
|
||||
raise ValueError("GitLab URL is not set in the config file")
|
||||
gitlab_access_token = get_settings().get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
|
||||
gitlab_access_token = settings.get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
|
||||
if not gitlab_access_token:
|
||||
raise ValueError("GitLab personal access token is not set in the config file")
|
||||
self.gl = gitlab.Gitlab(
|
||||
url=gitlab_url,
|
||||
oauth_token=gitlab_access_token
|
||||
gitlab_url,
|
||||
gitlab_access_token
|
||||
)
|
||||
self.id_project = None
|
||||
self.id_mr = None
|
||||
self.mr = None
|
||||
self.diff_files = None
|
||||
self.git_files = None
|
||||
self.temp_comments = []
|
||||
self.pr_url = merge_request_url
|
||||
self._set_merge_request(merge_request_url)
|
||||
self.RE_HUNK_HEADER = re.compile(
|
||||
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
|
||||
self.incremental = incremental
|
||||
|
||||
def is_supported(self, capability: str) -> bool:
|
||||
if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments']: # gfm_markdown is supported in gitlab !
|
||||
if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments']:
|
||||
return False
|
||||
return True
|
||||
|
||||
@ -56,14 +47,9 @@ class GitLabProvider(GitProvider):
|
||||
def _set_merge_request(self, merge_request_url: str):
|
||||
self.id_project, self.id_mr = self._parse_merge_request_url(merge_request_url)
|
||||
self.mr = self._get_merge_request()
|
||||
try:
|
||||
self.last_diff = self.mr.diffs.list(get_all=True)[-1]
|
||||
except IndexError as e:
|
||||
get_logger().error(f"Could not get diff for merge request {self.id_mr}")
|
||||
raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}") from e
|
||||
self.last_diff = self.mr.diffs.list()[-1]
|
||||
|
||||
|
||||
def get_pr_file_content(self, file_path: str, branch: str) -> str:
|
||||
def _get_pr_file_content(self, file_path: str, branch: str) -> str:
|
||||
try:
|
||||
return self.gl.projects.get(self.id_project).files.get(file_path, branch).decode()
|
||||
except GitlabGetError:
|
||||
@ -72,34 +58,12 @@ class GitLabProvider(GitProvider):
|
||||
return ''
|
||||
|
||||
def get_diff_files(self) -> list[FilePatchInfo]:
|
||||
"""
|
||||
Retrieves the list of files that have been modified, added, deleted, or renamed in a pull request in GitLab,
|
||||
along with their content and patch information.
|
||||
|
||||
Returns:
|
||||
diff_files (List[FilePatchInfo]): List of FilePatchInfo objects representing the modified, added, deleted,
|
||||
or renamed files in the merge request.
|
||||
"""
|
||||
|
||||
if self.diff_files:
|
||||
return self.diff_files
|
||||
|
||||
diffs = self.mr.changes()['changes']
|
||||
diff_files = []
|
||||
for diff in diffs:
|
||||
if is_valid_file(diff['new_path']):
|
||||
original_file_content_str = self.get_pr_file_content(diff['old_path'], self.mr.diff_refs['base_sha'])
|
||||
new_file_content_str = self.get_pr_file_content(diff['new_path'], self.mr.diff_refs['head_sha'])
|
||||
|
||||
try:
|
||||
if isinstance(original_file_content_str, bytes):
|
||||
original_file_content_str = bytes.decode(original_file_content_str, 'utf-8')
|
||||
if isinstance(new_file_content_str, bytes):
|
||||
new_file_content_str = bytes.decode(new_file_content_str, 'utf-8')
|
||||
except UnicodeDecodeError:
|
||||
get_logger().warning(
|
||||
f"Cannot decode file {diff['old_path']} or {diff['new_path']} in merge request {self.id_mr}")
|
||||
|
||||
original_file_content_str = self._get_pr_file_content(diff['old_path'], self.mr.target_branch)
|
||||
new_file_content_str = self._get_pr_file_content(diff['new_path'], self.mr.source_branch)
|
||||
edit_type = EDIT_TYPE.MODIFIED
|
||||
if diff['new_file']:
|
||||
edit_type = EDIT_TYPE.ADDED
|
||||
@ -107,33 +71,23 @@ class GitLabProvider(GitProvider):
|
||||
edit_type = EDIT_TYPE.DELETED
|
||||
elif diff['renamed_file']:
|
||||
edit_type = EDIT_TYPE.RENAMED
|
||||
|
||||
filename = diff['new_path']
|
||||
patch = diff['diff']
|
||||
if not patch:
|
||||
patch = load_large_diff(filename, new_file_content_str, original_file_content_str)
|
||||
|
||||
|
||||
# count number of lines added and removed
|
||||
patch_lines = patch.splitlines(keepends=True)
|
||||
num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
|
||||
num_minus_lines = len([line for line in patch_lines if line.startswith('-')])
|
||||
try:
|
||||
if isinstance(original_file_content_str, bytes):
|
||||
original_file_content_str = bytes.decode(original_file_content_str, 'utf-8')
|
||||
if isinstance(new_file_content_str, bytes):
|
||||
new_file_content_str = bytes.decode(new_file_content_str, 'utf-8')
|
||||
except UnicodeDecodeError:
|
||||
logging.warning(
|
||||
f"Cannot decode file {diff['old_path']} or {diff['new_path']} in merge request {self.id_mr}")
|
||||
diff_files.append(
|
||||
FilePatchInfo(original_file_content_str, new_file_content_str,
|
||||
patch=patch,
|
||||
filename=filename,
|
||||
FilePatchInfo(original_file_content_str, new_file_content_str, diff['diff'], diff['new_path'],
|
||||
edit_type=edit_type,
|
||||
old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path'],
|
||||
num_plus_lines=num_plus_lines,
|
||||
num_minus_lines=num_minus_lines, ))
|
||||
|
||||
old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path']))
|
||||
self.diff_files = diff_files
|
||||
return diff_files
|
||||
|
||||
def get_files(self):
|
||||
if not self.git_files:
|
||||
self.git_files = [change['new_path'] for change in self.mr.changes()['changes']]
|
||||
return self.git_files
|
||||
return [change['new_path'] for change in self.mr.changes()['changes']]
|
||||
|
||||
def publish_description(self, pr_title: str, pr_body: str):
|
||||
try:
|
||||
@ -141,79 +95,36 @@ class GitLabProvider(GitProvider):
|
||||
self.mr.description = pr_body
|
||||
self.mr.save()
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Could not update merge request {self.id_mr} description: {e}")
|
||||
|
||||
def get_latest_commit_url(self):
|
||||
return self.mr.commits().next().web_url
|
||||
|
||||
def get_comment_url(self, comment):
|
||||
return f"{self.mr.web_url}#note_{comment.id}"
|
||||
|
||||
def publish_persistent_comment(self, pr_comment: str,
|
||||
initial_header: str,
|
||||
update_header: bool = True,
|
||||
name='review',
|
||||
final_update_message=True):
|
||||
try:
|
||||
for comment in self.mr.notes.list(get_all=True)[::-1]:
|
||||
if comment.body.startswith(initial_header):
|
||||
latest_commit_url = self.get_latest_commit_url()
|
||||
comment_url = self.get_comment_url(comment)
|
||||
if update_header:
|
||||
updated_header = f"{initial_header}\n\n### ({name.capitalize()} updated until commit {latest_commit_url})\n"
|
||||
pr_comment_updated = pr_comment.replace(initial_header, updated_header)
|
||||
else:
|
||||
pr_comment_updated = pr_comment
|
||||
get_logger().info(f"Persistent mode - updating comment {comment_url} to latest {name} message")
|
||||
response = self.mr.notes.update(comment.id, {'body': pr_comment_updated})
|
||||
if final_update_message:
|
||||
self.publish_comment(
|
||||
f"**[Persistent {name}]({comment_url})** updated to latest commit {latest_commit_url}")
|
||||
return
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to update persistent review, error: {e}")
|
||||
pass
|
||||
self.publish_comment(pr_comment)
|
||||
logging.exception(f"Could not update merge request {self.id_mr} description: {e}")
|
||||
|
||||
def publish_comment(self, mr_comment: str, is_temporary: bool = False):
|
||||
comment = self.mr.notes.create({'body': mr_comment})
|
||||
if is_temporary:
|
||||
self.temp_comments.append(comment)
|
||||
return comment
|
||||
|
||||
def edit_comment(self, comment, body: str):
|
||||
self.mr.notes.update(comment.id,{'body': body} )
|
||||
|
||||
def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
|
||||
discussion = self.mr.discussions.get(comment_id)
|
||||
discussion.notes.create({'body': body})
|
||||
|
||||
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
|
||||
edit_type, found, source_line_no, target_file, target_line_no = self.search_line(relevant_file,
|
||||
relevant_line_in_file)
|
||||
self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
|
||||
target_file, target_line_no)
|
||||
|
||||
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
|
||||
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
raise NotImplementedError("Gitlab provider does not support creating inline comments yet")
|
||||
|
||||
def create_inline_comments(self, comments: list[dict]):
|
||||
def create_inline_comment(self, comments: list[dict]):
|
||||
raise NotImplementedError("Gitlab provider does not support publishing inline comments yet")
|
||||
|
||||
def send_inline_comment(self,body: str,edit_type: str,found: bool,relevant_file: str,relevant_line_in_file: int,
|
||||
source_line_no: int, target_file: str,target_line_no: int) -> None:
|
||||
def send_inline_comment(self, body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
|
||||
target_file, target_line_no):
|
||||
if not found:
|
||||
get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
|
||||
logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
|
||||
else:
|
||||
# in order to have exact sha's we have to find correct diff for this change
|
||||
diff = self.get_relevant_diff(relevant_file, relevant_line_in_file)
|
||||
if diff is None:
|
||||
get_logger().error(f"Could not get diff for merge request {self.id_mr}")
|
||||
raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}")
|
||||
d = self.last_diff
|
||||
pos_obj = {'position_type': 'text',
|
||||
'new_path': target_file.filename,
|
||||
'old_path': target_file.old_filename if target_file.old_filename else target_file.filename,
|
||||
'base_sha': diff.base_commit_sha, 'start_sha': diff.start_commit_sha, 'head_sha': diff.head_commit_sha}
|
||||
'base_sha': d.base_commit_sha, 'start_sha': d.start_commit_sha, 'head_sha': d.head_commit_sha}
|
||||
if edit_type == 'deletion':
|
||||
pos_obj['old_line'] = source_line_no - 1
|
||||
elif edit_type == 'addition':
|
||||
@ -221,71 +132,38 @@ class GitLabProvider(GitProvider):
|
||||
else:
|
||||
pos_obj['new_line'] = target_line_no - 1
|
||||
pos_obj['old_line'] = source_line_no - 1
|
||||
get_logger().debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
|
||||
try:
|
||||
self.mr.discussions.create({'body': body, 'position': pos_obj})
|
||||
except Exception as e:
|
||||
get_logger().debug(
|
||||
f"Failed to create comment in {self.id_mr} with position {pos_obj} (probably not a '+' line)")
|
||||
self.mr.discussions.create({'body': body,
|
||||
'position': pos_obj})
|
||||
|
||||
def get_relevant_diff(self, relevant_file: str, relevant_line_in_file: int) -> Optional[dict]:
|
||||
changes = self.mr.changes() # Retrieve the changes for the merge request once
|
||||
if not changes:
|
||||
get_logger().error('No changes found for the merge request.')
|
||||
return None
|
||||
all_diffs = self.mr.diffs.list(get_all=True)
|
||||
if not all_diffs:
|
||||
get_logger().error('No diffs found for the merge request.')
|
||||
return None
|
||||
for diff in all_diffs:
|
||||
for change in changes['changes']:
|
||||
if change['new_path'] == relevant_file and relevant_line_in_file in change['diff']:
|
||||
return diff
|
||||
get_logger().debug(
|
||||
f'No relevant diff found for {relevant_file} {relevant_line_in_file}. Falling back to last diff.')
|
||||
return self.last_diff # fallback to last_diff if no relevant diff is found
|
||||
|
||||
def publish_code_suggestions(self, code_suggestions: list) -> bool:
|
||||
def publish_code_suggestions(self, code_suggestions: list):
|
||||
for suggestion in code_suggestions:
|
||||
try:
|
||||
body = suggestion['body']
|
||||
relevant_file = suggestion['relevant_file']
|
||||
relevant_lines_start = suggestion['relevant_lines_start']
|
||||
relevant_lines_end = suggestion['relevant_lines_end']
|
||||
body = suggestion['body']
|
||||
relevant_file = suggestion['relevant_file']
|
||||
relevant_lines_start = suggestion['relevant_lines_start']
|
||||
relevant_lines_end = suggestion['relevant_lines_end']
|
||||
|
||||
diff_files = self.get_diff_files()
|
||||
target_file = None
|
||||
for file in diff_files:
|
||||
self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
|
||||
target_file = None
|
||||
for file in self.diff_files:
|
||||
if file.filename == relevant_file:
|
||||
if file.filename == relevant_file:
|
||||
if file.filename == relevant_file:
|
||||
target_file = file
|
||||
break
|
||||
range = relevant_lines_end - relevant_lines_start # no need to add 1
|
||||
body = body.replace('```suggestion', f'```suggestion:-0+{range}')
|
||||
lines = target_file.head_file.splitlines()
|
||||
relevant_line_in_file = lines[relevant_lines_start - 1]
|
||||
target_file = file
|
||||
break
|
||||
range = relevant_lines_end - relevant_lines_start + 1
|
||||
body = body.replace('```suggestion', f'```suggestion:-0+{range}')
|
||||
|
||||
# edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(target_file,
|
||||
# relevant_line_in_file)
|
||||
# for code suggestions, we want to edit the new code
|
||||
source_line_no = None
|
||||
target_line_no = relevant_lines_start + 1
|
||||
found = True
|
||||
edit_type = 'addition'
|
||||
|
||||
self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
|
||||
target_file, target_line_no)
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")
|
||||
|
||||
# note that we publish suggestions one-by-one. so, if one fails, the rest will still be published
|
||||
return True
|
||||
lines = target_file.head_file.splitlines()
|
||||
relevant_line_in_file = lines[relevant_lines_start - 1]
|
||||
edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(target_file,
|
||||
relevant_line_in_file)
|
||||
self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
|
||||
target_file, target_line_no)
|
||||
|
||||
def search_line(self, relevant_file, relevant_line_in_file):
|
||||
target_file = None
|
||||
|
||||
edit_type = self.get_edit_type(relevant_line_in_file)
|
||||
for file in self.get_diff_files():
|
||||
for file in self.diff_files:
|
||||
if file.filename == relevant_file:
|
||||
edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(file,
|
||||
relevant_line_in_file)
|
||||
@ -338,15 +216,9 @@ class GitLabProvider(GitProvider):
|
||||
def remove_initial_comment(self):
|
||||
try:
|
||||
for comment in self.temp_comments:
|
||||
self.remove_comment(comment)
|
||||
comment.delete()
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to remove temp comments, error: {e}")
|
||||
|
||||
def remove_comment(self, comment):
|
||||
try:
|
||||
comment.delete()
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to remove comment, error: {e}")
|
||||
logging.exception(f"Failed to remove temp comments, error: {e}")
|
||||
|
||||
def get_title(self):
|
||||
return self.mr.title
|
||||
@ -358,49 +230,26 @@ class GitLabProvider(GitProvider):
|
||||
def get_pr_branch(self):
|
||||
return self.mr.source_branch
|
||||
|
||||
def get_pr_description_full(self):
|
||||
def get_pr_description(self):
|
||||
return self.mr.description
|
||||
|
||||
def get_issue_comments(self):
|
||||
raise NotImplementedError("GitLab provider does not support issue comments yet")
|
||||
|
||||
def get_repo_settings(self):
|
||||
try:
|
||||
contents = self.gl.projects.get(self.id_project).files.get(file_path='.pr_agent.toml', ref=self.mr.target_branch).decode()
|
||||
return contents
|
||||
except Exception:
|
||||
return ""
|
||||
|
||||
def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
|
||||
return True
|
||||
|
||||
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
|
||||
return True
|
||||
|
||||
def _parse_merge_request_url(self, merge_request_url: str) -> Tuple[str, int]:
|
||||
def _parse_merge_request_url(self, merge_request_url: str) -> Tuple[int, int]:
|
||||
parsed_url = urlparse(merge_request_url)
|
||||
|
||||
path_parts = parsed_url.path.strip('/').split('/')
|
||||
if 'merge_requests' not in path_parts:
|
||||
if path_parts[-2] != 'merge_requests':
|
||||
raise ValueError("The provided URL does not appear to be a GitLab merge request URL")
|
||||
|
||||
mr_index = path_parts.index('merge_requests')
|
||||
# Ensure there is an ID after 'merge_requests'
|
||||
if len(path_parts) <= mr_index + 1:
|
||||
raise ValueError("The provided URL does not contain a merge request ID")
|
||||
|
||||
try:
|
||||
mr_id = int(path_parts[mr_index + 1])
|
||||
mr_id = int(path_parts[-1])
|
||||
except ValueError as e:
|
||||
raise ValueError("Unable to convert merge request ID to integer") from e
|
||||
|
||||
# Handle special delimiter (-)
|
||||
project_path = "/".join(path_parts[:mr_index])
|
||||
if project_path.endswith('/-'):
|
||||
project_path = project_path[:-2]
|
||||
|
||||
# Return the path before 'merge_requests' and the ID
|
||||
return project_path, mr_id
|
||||
# Gitlab supports access by both project numeric ID as well as 'namespace/project_name'
|
||||
return "/".join(path_parts[:2]), mr_id
|
||||
|
||||
def _get_merge_request(self):
|
||||
mr = self.gl.projects.get(self.id_project).mergerequests.get(self.id_mr)
|
||||
@ -409,76 +258,8 @@ class GitLabProvider(GitProvider):
|
||||
def get_user_id(self):
|
||||
return None
|
||||
|
||||
def publish_labels(self, pr_types):
|
||||
try:
|
||||
self.mr.labels = list(set(pr_types))
|
||||
self.mr.save()
|
||||
except Exception as e:
|
||||
get_logger().exception(f"Failed to publish labels, error: {e}")
|
||||
|
||||
def publish_inline_comments(self, comments: list[dict]):
|
||||
def publish_labels(self, labels):
|
||||
pass
|
||||
|
||||
def get_pr_labels(self, update=False):
|
||||
return self.mr.labels
|
||||
|
||||
def get_repo_labels(self):
|
||||
return self.gl.projects.get(self.id_project).labels.list()
|
||||
|
||||
def get_commit_messages(self):
|
||||
"""
|
||||
Retrieves the commit messages of a pull request.
|
||||
|
||||
Returns:
|
||||
str: A string containing the commit messages of the pull request.
|
||||
"""
|
||||
max_tokens = get_settings().get("CONFIG.MAX_COMMITS_TOKENS", None)
|
||||
try:
|
||||
commit_messages_list = [commit['message'] for commit in self.mr.commits()._list]
|
||||
commit_messages_str = "\n".join([f"{i + 1}. {message}" for i, message in enumerate(commit_messages_list)])
|
||||
except Exception:
|
||||
commit_messages_str = ""
|
||||
if max_tokens:
|
||||
commit_messages_str = clip_tokens(commit_messages_str, max_tokens)
|
||||
return commit_messages_str
|
||||
|
||||
def get_pr_id(self):
|
||||
try:
|
||||
pr_id = self.mr.web_url
|
||||
return pr_id
|
||||
except:
|
||||
return ""
|
||||
|
||||
def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
|
||||
if relevant_line_start == -1:
|
||||
link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads"
|
||||
elif relevant_line_end:
|
||||
link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}-L{relevant_line_end}"
|
||||
else:
|
||||
link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}"
|
||||
return link
|
||||
|
||||
|
||||
def generate_link_to_relevant_line_number(self, suggestion) -> str:
|
||||
try:
|
||||
relevant_file = suggestion['relevant_file'].strip('`').strip("'").rstrip()
|
||||
relevant_line_str = suggestion['relevant_line'].rstrip()
|
||||
if not relevant_line_str:
|
||||
return ""
|
||||
|
||||
position, absolute_position = find_line_number_of_relevant_line_in_file \
|
||||
(self.diff_files, relevant_file, relevant_line_str)
|
||||
|
||||
if absolute_position != -1:
|
||||
# link to right file only
|
||||
link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{absolute_position}"
|
||||
|
||||
# # link to diff
|
||||
# sha_file = hashlib.sha1(relevant_file.encode('utf-8')).hexdigest()
|
||||
# link = f"{self.pr.web_url}/diffs#{sha_file}_{absolute_position}_{absolute_position}"
|
||||
return link
|
||||
except Exception as e:
|
||||
if get_settings().config.verbosity_level >= 2:
|
||||
get_logger().info(f"Failed adding line link, error: {e}")
|
||||
|
||||
return ""
|
||||
def publish_inline_comments(self, comments: list[dict]):
|
||||
pass
|
||||
@ -1,180 +0,0 @@
|
||||
from collections import Counter
|
||||
from pathlib import Path
|
||||
from typing import List
|
||||
|
||||
from git import Repo
|
||||
|
||||
from pr_agent.config_loader import _find_repository_root, get_settings
|
||||
from pr_agent.git_providers.git_provider import GitProvider
|
||||
from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
|
||||
from pr_agent.log import get_logger
|
||||
|
||||
|
||||
class PullRequestMimic:
|
||||
"""
|
||||
This class mimics the PullRequest class from the PyGithub library for the LocalGitProvider.
|
||||
"""
|
||||
|
||||
def __init__(self, title: str, diff_files: List[FilePatchInfo]):
|
||||
self.title = title
|
||||
self.diff_files = diff_files
|
||||
|
||||
|
||||
class LocalGitProvider(GitProvider):
|
||||
"""
|
||||
This class implements the GitProvider interface for local git repositories.
|
||||
It mimics the PR functionality of the GitProvider interface,
|
||||
but does not require a hosted git repository.
|
||||
Instead of providing a PR url, the user provides a local branch path to generate a diff-patch.
|
||||
For the MVP it only supports the /review and /describe capabilities.
|
||||
"""
|
||||
|
||||
def __init__(self, target_branch_name, incremental=False):
|
||||
self.repo_path = _find_repository_root()
|
||||
if self.repo_path is None:
|
||||
raise ValueError('Could not find repository root')
|
||||
self.repo = Repo(self.repo_path)
|
||||
self.head_branch_name = self.repo.head.ref.name
|
||||
self.target_branch_name = target_branch_name
|
||||
self._prepare_repo()
|
||||
self.diff_files = None
|
||||
self.pr = PullRequestMimic(self.get_pr_title(), self.get_diff_files())
|
||||
self.description_path = get_settings().get('local.description_path') \
|
||||
if get_settings().get('local.description_path') is not None else self.repo_path / 'description.md'
|
||||
self.review_path = get_settings().get('local.review_path') \
|
||||
if get_settings().get('local.review_path') is not None else self.repo_path / 'review.md'
|
||||
# inline code comments are not supported for local git repositories
|
||||
get_settings().pr_reviewer.inline_code_comments = False
|
||||
|
||||
def _prepare_repo(self):
|
||||
"""
|
||||
Prepare the repository for PR-mimic generation.
|
||||
"""
|
||||
get_logger().debug('Preparing repository for PR-mimic generation...')
|
||||
if self.repo.is_dirty():
|
||||
raise ValueError('The repository is not in a clean state. Please commit or stash pending changes.')
|
||||
if self.target_branch_name not in self.repo.heads:
|
||||
raise KeyError(f'Branch: {self.target_branch_name} does not exist')
|
||||
|
||||
def is_supported(self, capability: str) -> bool:
|
||||
if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels',
|
||||
'gfm_markdown']:
|
||||
return False
|
||||
return True
|
||||
|
||||
def get_diff_files(self) -> list[FilePatchInfo]:
|
||||
diffs = self.repo.head.commit.diff(
|
||||
self.repo.merge_base(self.repo.head, self.repo.branches[self.target_branch_name]),
|
||||
create_patch=True,
|
||||
R=True
|
||||
)
|
||||
diff_files = []
|
||||
for diff_item in diffs:
|
||||
if diff_item.a_blob is not None:
|
||||
original_file_content_str = diff_item.a_blob.data_stream.read().decode('utf-8')
|
||||
else:
|
||||
original_file_content_str = "" # empty file
|
||||
if diff_item.b_blob is not None:
|
||||
new_file_content_str = diff_item.b_blob.data_stream.read().decode('utf-8')
|
||||
else:
|
||||
new_file_content_str = "" # empty file
|
||||
edit_type = EDIT_TYPE.MODIFIED
|
||||
if diff_item.new_file:
|
||||
edit_type = EDIT_TYPE.ADDED
|
||||
elif diff_item.deleted_file:
|
||||
edit_type = EDIT_TYPE.DELETED
|
||||
elif diff_item.renamed_file:
|
||||
edit_type = EDIT_TYPE.RENAMED
|
||||
diff_files.append(
|
||||
FilePatchInfo(original_file_content_str,
|
||||
new_file_content_str,
|
||||
diff_item.diff.decode('utf-8'),
|
||||
diff_item.b_path,
|
||||
edit_type=edit_type,
|
||||
old_filename=None if diff_item.a_path == diff_item.b_path else diff_item.a_path
|
||||
)
|
||||
)
|
||||
self.diff_files = diff_files
|
||||
return diff_files
|
||||
|
||||
def get_files(self) -> List[str]:
|
||||
"""
|
||||
Returns a list of files with changes in the diff.
|
||||
"""
|
||||
diff_index = self.repo.head.commit.diff(
|
||||
self.repo.merge_base(self.repo.head, self.repo.branches[self.target_branch_name]),
|
||||
R=True
|
||||
)
|
||||
# Get the list of changed files
|
||||
diff_files = [item.a_path for item in diff_index]
|
||||
return diff_files
|
||||
|
||||
def publish_description(self, pr_title: str, pr_body: str):
|
||||
with open(self.description_path, "w") as file:
|
||||
# Write the string to the file
|
||||
file.write(pr_title + '\n' + pr_body)
|
||||
|
||||
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
|
||||
with open(self.review_path, "w") as file:
|
||||
# Write the string to the file
|
||||
file.write(pr_comment)
|
||||
|
||||
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
|
||||
raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')
|
||||
|
||||
def publish_inline_comments(self, comments: list[dict]):
|
||||
raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')
|
||||
|
||||
def publish_code_suggestion(self, body: str, relevant_file: str,
|
||||
relevant_lines_start: int, relevant_lines_end: int):
|
||||
raise NotImplementedError('Publishing code suggestions is not implemented for the local git provider')
|
||||
|
||||
def publish_code_suggestions(self, code_suggestions: list) -> bool:
|
||||
raise NotImplementedError('Publishing code suggestions is not implemented for the local git provider')
|
||||
|
||||
def publish_labels(self, labels):
|
||||
pass # Not applicable to the local git provider, but required by the interface
|
||||
|
||||
def remove_initial_comment(self):
|
||||
pass # Not applicable to the local git provider, but required by the interface
|
||||
|
||||
def remove_comment(self, comment):
|
||||
pass # Not applicable to the local git provider, but required by the interface
|
||||
|
||||
def get_languages(self):
|
||||
"""
|
||||
Calculate percentage of languages in repository. Used for hunk prioritisation.
|
||||
"""
|
||||
# Get all files in repository
|
||||
filepaths = [Path(item.path) for item in self.repo.tree().traverse() if item.type == 'blob']
|
||||
# Identify language by file extension and count
|
||||
lang_count = Counter(ext.lstrip('.') for filepath in filepaths for ext in [filepath.suffix.lower()])
|
||||
# Convert counts to percentages
|
||||
total_files = len(filepaths)
|
||||
lang_percentage = {lang: count / total_files * 100 for lang, count in lang_count.items()}
|
||||
return lang_percentage
|
||||
|
||||
def get_pr_branch(self):
|
||||
return self.repo.head
|
||||
|
||||
def get_user_id(self):
|
||||
return -1 # Not used anywhere for the local provider, but required by the interface
|
||||
|
||||
def get_pr_description_full(self):
|
||||
commits_diff = list(self.repo.iter_commits(self.target_branch_name + '..HEAD'))
|
||||
# Get the commit messages and concatenate
|
||||
commit_messages = " ".join([commit.message for commit in commits_diff])
|
||||
# TODO Handle the description better - maybe use gpt-3.5 summarisation here?
|
||||
return commit_messages[:200] # Use max 200 characters
|
||||
|
||||
def get_pr_title(self):
|
||||
"""
|
||||
Substitutes the branch-name as the PR-mimic title.
|
||||
"""
|
||||
return self.head_branch_name
|
||||
|
||||
def get_issue_comments(self):
|
||||
raise NotImplementedError('Getting issue comments is not implemented for the local git provider')
|
||||
|
||||
def get_pr_labels(self, update=False):
|
||||
raise NotImplementedError('Getting labels is not implemented for the local git provider')
|
||||
@ -1,49 +0,0 @@
|
||||
import copy
|
||||
import os
|
||||
import tempfile
|
||||
|
||||
from dynaconf import Dynaconf
|
||||
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.git_providers import get_git_provider
|
||||
from pr_agent.log import get_logger
|
||||
from starlette_context import context
|
||||
|
||||
|
||||
def apply_repo_settings(pr_url):
|
||||
if get_settings().config.use_repo_settings_file:
|
||||
repo_settings_file = None
|
||||
try:
|
||||
try:
|
||||
repo_settings = context.get("repo_settings", None)
|
||||
except Exception:
|
||||
repo_settings = None
|
||||
pass
|
||||
if repo_settings is None: # None is different from "", which is a valid value
|
||||
git_provider = get_git_provider()(pr_url)
|
||||
repo_settings = git_provider.get_repo_settings()
|
||||
try:
|
||||
context["repo_settings"] = repo_settings
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
if repo_settings:
|
||||
repo_settings_file = None
|
||||
fd, repo_settings_file = tempfile.mkstemp(suffix='.toml')
|
||||
os.write(fd, repo_settings)
|
||||
new_settings = Dynaconf(settings_files=[repo_settings_file])
|
||||
for section, contents in new_settings.as_dict().items():
|
||||
section_dict = copy.deepcopy(get_settings().as_dict().get(section, {}))
|
||||
for key, value in contents.items():
|
||||
section_dict[key] = value
|
||||
get_settings().unset(section)
|
||||
get_settings().set(section, section_dict, merge=False)
|
||||
get_logger().info(f"Applying repo settings:\n{new_settings.as_dict()}")
|
||||
except Exception as e:
|
||||
get_logger().exception("Failed to apply repo settings", e)
|
||||
finally:
|
||||
if repo_settings_file:
|
||||
try:
|
||||
os.remove(repo_settings_file)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to remove temporary settings file {repo_settings_file}", e)
|
||||
@ -1,13 +0,0 @@
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.identity_providers.default_identity_provider import DefaultIdentityProvider
|
||||
|
||||
_IDENTITY_PROVIDERS = {
|
||||
'default': DefaultIdentityProvider
|
||||
}
|
||||
|
||||
|
||||
def get_identity_provider():
|
||||
identity_provider_id = get_settings().get("CONFIG.IDENTITY_PROVIDER", "default")
|
||||
if identity_provider_id not in _IDENTITY_PROVIDERS:
|
||||
raise ValueError(f"Unknown identity provider: {identity_provider_id}")
|
||||
return _IDENTITY_PROVIDERS[identity_provider_id]()
|
||||
@ -1,9 +0,0 @@
|
||||
from pr_agent.identity_providers.identity_provider import Eligibility, IdentityProvider
|
||||
|
||||
|
||||
class DefaultIdentityProvider(IdentityProvider):
|
||||
def verify_eligibility(self, git_provider, git_provider_id, pr_url):
|
||||
return Eligibility.ELIGIBLE
|
||||
|
||||
def inc_invocation_count(self, git_provider, git_provider_id):
|
||||
pass
|
||||
@ -1,18 +0,0 @@
|
||||
from abc import ABC, abstractmethod
|
||||
from enum import Enum
|
||||
|
||||
|
||||
class Eligibility(Enum):
|
||||
NOT_ELIGIBLE = 0
|
||||
ELIGIBLE = 1
|
||||
TRIAL = 2
|
||||
|
||||
|
||||
class IdentityProvider(ABC):
|
||||
@abstractmethod
|
||||
def verify_eligibility(self, git_provider, git_provier_id, pr_url):
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def inc_invocation_count(self, git_provider, git_provider_id):
|
||||
pass
|
||||
@ -1,65 +0,0 @@
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
from enum import Enum
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from pr_agent.config_loader import get_settings
|
||||
|
||||
|
||||
class LoggingFormat(str, Enum):
|
||||
CONSOLE = "CONSOLE"
|
||||
JSON = "JSON"
|
||||
|
||||
|
||||
def json_format(record: dict) -> str:
|
||||
return record["message"]
|
||||
|
||||
|
||||
def analytics_filter(record: dict) -> bool:
|
||||
return record.get("extra", {}).get("analytics", False)
|
||||
|
||||
|
||||
def inv_analytics_filter(record: dict) -> bool:
|
||||
return not record.get("extra", {}).get("analytics", False)
|
||||
|
||||
|
||||
def setup_logger(level: str = "INFO", fmt: LoggingFormat = LoggingFormat.CONSOLE):
|
||||
level: int = logging.getLevelName(level.upper())
|
||||
if type(level) is not int:
|
||||
level = logging.INFO
|
||||
|
||||
if fmt == LoggingFormat.JSON and os.getenv("LOG_SANE", "0").lower() == "0": # better debugging github_app
|
||||
logger.remove(None)
|
||||
logger.add(
|
||||
sys.stdout,
|
||||
filter=inv_analytics_filter,
|
||||
level=level,
|
||||
format="{message}",
|
||||
colorize=False,
|
||||
serialize=True,
|
||||
)
|
||||
elif fmt == LoggingFormat.CONSOLE: # does not print the 'extra' fields
|
||||
logger.remove(None)
|
||||
logger.add(sys.stdout, level=level, colorize=True, filter=inv_analytics_filter)
|
||||
|
||||
log_folder = get_settings().get("CONFIG.ANALYTICS_FOLDER", "")
|
||||
if log_folder:
|
||||
pid = os.getpid()
|
||||
log_file = os.path.join(log_folder, f"pr-agent.{pid}.log")
|
||||
logger.add(
|
||||
log_file,
|
||||
filter=analytics_filter,
|
||||
level=level,
|
||||
format="{message}",
|
||||
colorize=False,
|
||||
serialize=True,
|
||||
)
|
||||
|
||||
return logger
|
||||
|
||||
|
||||
def get_logger(*args, **kwargs):
|
||||
return logger
|
||||
@ -1,19 +0,0 @@
|
||||
from pr_agent.config_loader import get_settings
|
||||
|
||||
|
||||
def get_secret_provider():
|
||||
if not get_settings().get("CONFIG.SECRET_PROVIDER"):
|
||||
return None
|
||||
|
||||
provider_id = get_settings().config.secret_provider
|
||||
if provider_id == 'google_cloud_storage':
|
||||
try:
|
||||
from pr_agent.secret_providers.google_cloud_storage_secret_provider import GoogleCloudStorageSecretProvider
|
||||
return GoogleCloudStorageSecretProvider()
|
||||
except Exception as e:
|
||||
raise ValueError(f"Failed to initialize google_cloud_storage secret provider {provider_id}") from e
|
||||
else:
|
||||
raise ValueError("Unknown SECRET_PROVIDER")
|
||||
|
||||
|
||||
|
||||
@ -1,34 +0,0 @@
|
||||
import ujson
|
||||
from google.cloud import storage
|
||||
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.log import get_logger
|
||||
from pr_agent.secret_providers.secret_provider import SecretProvider
|
||||
|
||||
|
||||
class GoogleCloudStorageSecretProvider(SecretProvider):
|
||||
def __init__(self):
|
||||
try:
|
||||
self.client = storage.Client.from_service_account_info(ujson.loads(get_settings().google_cloud_storage.
|
||||
service_account))
|
||||
self.bucket_name = get_settings().google_cloud_storage.bucket_name
|
||||
self.bucket = self.client.bucket(self.bucket_name)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to initialize Google Cloud Storage Secret Provider: {e}")
|
||||
raise e
|
||||
|
||||
def get_secret(self, secret_name: str) -> str:
|
||||
try:
|
||||
blob = self.bucket.blob(secret_name)
|
||||
return blob.download_as_string()
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to get secret {secret_name} from Google Cloud Storage: {e}")
|
||||
return ""
|
||||
|
||||
def store_secret(self, secret_name: str, secret_value: str):
|
||||
try:
|
||||
blob = self.bucket.blob(secret_name)
|
||||
blob.upload_from_string(secret_value)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to store secret {secret_name} in Google Cloud Storage: {e}")
|
||||
raise e
|
||||
@ -1,12 +0,0 @@
|
||||
from abc import ABC, abstractmethod
|
||||
|
||||
|
||||
class SecretProvider(ABC):
|
||||
|
||||
@abstractmethod
|
||||
def get_secret(self, secret_name: str) -> str:
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
def store_secret(self, secret_name: str, secret_value: str):
|
||||
pass
|
||||
@ -1,33 +0,0 @@
|
||||
{
|
||||
"name": "CodiumAI PR-Agent",
|
||||
"description": "CodiumAI PR-Agent",
|
||||
"key": "app_key",
|
||||
"vendor": {
|
||||
"name": "CodiumAI",
|
||||
"url": "https://codium.ai"
|
||||
},
|
||||
"authentication": {
|
||||
"type": "jwt"
|
||||
},
|
||||
"baseUrl": "base_url",
|
||||
"lifecycle": {
|
||||
"installed": "/installed",
|
||||
"uninstalled": "/uninstalled"
|
||||
},
|
||||
"scopes": [
|
||||
"account",
|
||||
"repository",
|
||||
"pullrequest"
|
||||
],
|
||||
"contexts": [
|
||||
"account"
|
||||
],
|
||||
"modules": {
|
||||
"webhooks": [
|
||||
{
|
||||
"event": "*",
|
||||
"url": "/webhook"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
@ -1,139 +0,0 @@
|
||||
# This file contains the code for the Azure DevOps Server webhook server.
|
||||
# The server listens for incoming webhooks from Azure DevOps Server and forwards them to the PR Agent.
|
||||
# ADO webhook documentation: https://learn.microsoft.com/en-us/azure/devops/service-hooks/services/webhooks?view=azure-devops
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import secrets
|
||||
from urllib.parse import unquote
|
||||
|
||||
import uvicorn
|
||||
from fastapi import APIRouter, Depends, FastAPI, HTTPException
|
||||
from fastapi.security import HTTPBasic, HTTPBasicCredentials
|
||||
from fastapi.encoders import jsonable_encoder
|
||||
from starlette import status
|
||||
from starlette.background import BackgroundTasks
|
||||
from starlette.middleware import Middleware
|
||||
from starlette.requests import Request
|
||||
from starlette.responses import JSONResponse
|
||||
from starlette_context.middleware import RawContextMiddleware
|
||||
|
||||
from pr_agent.agent.pr_agent import PRAgent, command2class
|
||||
from pr_agent.algo.utils import update_settings_from_args
|
||||
from pr_agent.config_loader import get_settings
|
||||
from pr_agent.git_providers.utils import apply_repo_settings
|
||||
from pr_agent.log import get_logger
|
||||
from fastapi import Request, Depends
|
||||
from fastapi.security import HTTPBasic, HTTPBasicCredentials
|
||||
from pr_agent.log import get_logger
|
||||
|
||||
security = HTTPBasic()
|
||||
router = APIRouter()
|
||||
available_commands_rgx = re.compile(r"^\/(" + "|".join(command2class.keys()) + r")\s*")
|
||||
azure_devops_server = get_settings().get("azure_devops_server")
|
||||
WEBHOOK_USERNAME = azure_devops_server.get("webhook_username")
|
||||
WEBHOOK_PASSWORD = azure_devops_server.get("webhook_password")
|
||||
|
||||
def handle_request(
|
||||
background_tasks: BackgroundTasks, url: str, body: str, log_context: dict
|
||||
):
|
||||
log_context["action"] = body
|
||||
log_context["api_url"] = url
|
||||
with get_logger().contextualize(**log_context):
|
||||
background_tasks.add_task(PRAgent().handle_request, url, body)
|
||||
|
||||
|
||||
# currently only basic auth is supported with azure webhooks
|
||||
# for this reason, https must be enabled to ensure the credentials are not sent in clear text
|
||||
def authorize(credentials: HTTPBasicCredentials = Depends(security)):
|
||||
is_user_ok = secrets.compare_digest(credentials.username, WEBHOOK_USERNAME)
|
||||
is_pass_ok = secrets.compare_digest(credentials.password, WEBHOOK_PASSWORD)
|
||||
if not (is_user_ok and is_pass_ok):
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_401_UNAUTHORIZED,
|
||||
detail='Incorrect username or password.',
|
||||
headers={'WWW-Authenticate': 'Basic'},
|
||||
)
|
||||
|
||||
|
||||
async def _perform_commands_azure(commands_conf: str, agent: PRAgent, api_url: str, log_context: dict):
|
||||
apply_repo_settings(api_url)
|
||||
commands = get_settings().get(f"azure_devops_server.{commands_conf}")
|
||||
for command in commands:
|
||||
try:
|
||||
split_command = command.split(" ")
|
||||
command = split_command[0]
|
||||
args = split_command[1:]
|
||||
other_args = update_settings_from_args(args)
|
||||
new_command = ' '.join([command] + other_args)
|
||||
get_logger().info(f"Performing command: {new_command}")
|
||||
with get_logger().contextualize(**log_context):
|
||||
await agent.handle_request(api_url, new_command)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to perform command {command}: {e}")
|
||||
|
||||
|
||||
@router.post("/", dependencies=[Depends(authorize)])
|
||||
async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
|
||||
log_context = {"server_type": "azure_devops_server"}
|
||||
data = await request.json()
|
||||
get_logger().info(json.dumps(data))
|
||||
|
||||
actions = []
|
||||
if data["eventType"] == "git.pullrequest.created":
|
||||
# API V1 (latest)
|
||||
pr_url = unquote(data["resource"]["_links"]["web"]["href"].replace("_apis/git/repositories", "_git"))
|
||||
log_context["event"] = data["eventType"]
|
||||
log_context["api_url"] = pr_url
|
||||
await _perform_commands_azure("pr_commands", PRAgent(), pr_url, log_context)
|
||||
return
|
||||
elif data["eventType"] == "ms.vss-code.git-pullrequest-comment-event" and "content" in data["resource"]["comment"]:
|
||||
if available_commands_rgx.match(data["resource"]["comment"]["content"]):
|
||||
if(data["resourceVersion"] == "2.0"):
|
||||
repo = data["resource"]["pullRequest"]["repository"]["webUrl"]
|
||||
pr_url = unquote(f'{repo}/pullrequest/{data["resource"]["pullRequest"]["pullRequestId"]}')
|
||||
actions = [data["resource"]["comment"]["content"]]
|
||||
else:
|
||||
# API V1 not supported as it does not contain the PR URL
|
||||
return JSONResponse(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
content=json.dumps({"message": "version 1.0 webhook for Azure Devops PR comment is not supported. please upgrade to version 2.0"})),
|
||||
else:
|
||||
return JSONResponse(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
content=json.dumps({"message": "Unsupported command"}),
|
||||
)
|
||||
else:
|
||||
return JSONResponse(
|
||||
status_code=status.HTTP_204_NO_CONTENT,
|
||||
content=json.dumps({"message": "Unsupported event"}),
|
||||
)
|
||||
|
||||
log_context["event"] = data["eventType"]
|
||||
log_context["api_url"] = pr_url
|
||||
|
||||
for action in actions:
|
||||
try:
|
||||
handle_request(background_tasks, pr_url, action, log_context)
|
||||
except Exception as e:
|
||||
get_logger().error("Azure DevOps Trigger failed. Error:" + str(e))
|
||||
return JSONResponse(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
content=json.dumps({"message": "Internal server error"}),
|
||||
)
|
||||
return JSONResponse(
|
||||
status_code=status.HTTP_202_ACCEPTED, content=jsonable_encoder({"message": "webhook triggerd successfully"})
|
||||
)
|
||||
|
||||
@router.get("/")
|
||||
async def root():
|
||||
return {"status": "ok"}
|
||||
|
||||
def start():
|
||||
app = FastAPI(middleware=[Middleware(RawContextMiddleware)])
|
||||
app.include_router(router)
|
||||
uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("PORT", "3000")))
|
||||
|
||||
if __name__ == "__main__":
|
||||
start()
|
||||
@ -1,210 +0,0 @@
|
||||
import base64
|
||||
import copy
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import time
|
||||
|
||||
import jwt
|
||||
import requests
|
||||
import uvicorn
|
||||
from fastapi import APIRouter, FastAPI, Request, Response
|
||||
from starlette.background import BackgroundTasks
|
||||
from starlette.middleware import Middleware
|
||||
from starlette.responses import JSONResponse
|
||||
from starlette_context import context
|
||||
from starlette_context.middleware import RawContextMiddleware
|
||||
|
||||
from pr_agent.agent.pr_agent import PRAgent
|
||||
from pr_agent.algo.utils import update_settings_from_args
|
||||
from pr_agent.config_loader import get_settings, global_settings
|
||||
from pr_agent.git_providers.utils import apply_repo_settings
|
||||
from pr_agent.identity_providers import get_identity_provider
|
||||
from pr_agent.identity_providers.identity_provider import Eligibility
|
||||
from pr_agent.log import LoggingFormat, get_logger, setup_logger
|
||||
from pr_agent.secret_providers import get_secret_provider
|
||||
from pr_agent.servers.github_action_runner import get_setting_or_env, is_true
|
||||
from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
|
||||
from pr_agent.tools.pr_description import PRDescription
|
||||
from pr_agent.tools.pr_reviewer import PRReviewer
|
||||
|
||||
setup_logger(fmt=LoggingFormat.JSON, level="DEBUG")
|
||||
router = APIRouter()
|
||||
secret_provider = get_secret_provider() if get_settings().get("CONFIG.SECRET_PROVIDER") else None
|
||||
|
||||
|
||||
async def get_bearer_token(shared_secret: str, client_key: str):
|
||||
try:
|
||||
now = int(time.time())
|
||||
url = "https://bitbucket.org/site/oauth2/access_token"
|
||||
canonical_url = "GET&/site/oauth2/access_token&"
|
||||
qsh = hashlib.sha256(canonical_url.encode("utf-8")).hexdigest()
|
||||
app_key = get_settings().bitbucket.app_key
|
||||
|
||||
payload = {
|
||||
"iss": app_key,
|
||||
"iat": now,
|
||||
"exp": now + 240,
|
||||
"qsh": qsh,
|
||||
"sub": client_key,
|
||||
}
|
||||
token = jwt.encode(payload, shared_secret, algorithm="HS256")
|
||||
payload = 'grant_type=urn%3Abitbucket%3Aoauth2%3Ajwt'
|
||||
headers = {
|
||||
'Authorization': f'JWT {token}',
|
||||
'Content-Type': 'application/x-www-form-urlencoded'
|
||||
}
|
||||
response = requests.request("POST", url, headers=headers, data=payload)
|
||||
bearer_token = response.json()["access_token"]
|
||||
return bearer_token
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to get bearer token: {e}")
|
||||
raise e
|
||||
|
||||
@router.get("/")
|
||||
async def handle_manifest(request: Request, response: Response):
|
||||
cur_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
manifest = open(os.path.join(cur_dir, "atlassian-connect.json"), "rt").read()
|
||||
try:
|
||||
manifest = manifest.replace("app_key", get_settings().bitbucket.app_key)
|
||||
manifest = manifest.replace("base_url", get_settings().bitbucket.base_url)
|
||||
except:
|
||||
get_logger().error("Failed to replace api_key in Bitbucket manifest, trying to continue")
|
||||
manifest_obj = json.loads(manifest)
|
||||
return JSONResponse(manifest_obj)
|
||||
|
||||
|
||||
async def _perform_commands_bitbucket(commands_conf: str, agent: PRAgent, api_url: str, log_context: dict):
|
||||
apply_repo_settings(api_url)
|
||||
commands = get_settings().get(f"bitbucket_app.{commands_conf}", {})
|
||||
for command in commands:
|
||||
try:
|
||||
split_command = command.split(" ")
|
||||
command = split_command[0]
|
||||
args = split_command[1:]
|
||||
other_args = update_settings_from_args(args)
|
||||
new_command = ' '.join([command] + other_args)
|
||||
get_logger().info(f"Performing command: {new_command}")
|
||||
with get_logger().contextualize(**log_context):
|
||||
await agent.handle_request(api_url, new_command)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to perform command {command}: {e}")
|
||||
|
||||
|
||||
@router.post("/webhook")
|
||||
async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Request):
|
||||
log_context = {"server_type": "bitbucket_app"}
|
||||
get_logger().debug(request.headers)
|
||||
jwt_header = request.headers.get("authorization", None)
|
||||
if jwt_header:
|
||||
input_jwt = jwt_header.split(" ")[1]
|
||||
data = await request.json()
|
||||
get_logger().debug(data)
|
||||
async def inner():
|
||||
try:
|
||||
try:
|
||||
if data["data"]["actor"]["type"] != "user":
|
||||
return "OK"
|
||||
except KeyError:
|
||||
get_logger().error("Failed to get actor type, check previous logs, this shouldn't happen.")
|
||||
try:
|
||||
owner = data["data"]["repository"]["owner"]["username"]
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to get owner, will continue: {e}")
|
||||
owner = "unknown"
|
||||
sender_id = data["data"]["actor"]["account_id"]
|
||||
log_context["sender"] = owner
|
||||
log_context["sender_id"] = sender_id
|
||||
jwt_parts = input_jwt.split(".")
|
||||
claim_part = jwt_parts[1]
|
||||
claim_part += "=" * (-len(claim_part) % 4)
|
||||
decoded_claims = base64.urlsafe_b64decode(claim_part)
|
||||
claims = json.loads(decoded_claims)
|
||||
client_key = claims["iss"]
|
||||
secrets = json.loads(secret_provider.get_secret(client_key))
|
||||
shared_secret = secrets["shared_secret"]
|
||||
jwt.decode(input_jwt, shared_secret, audience=client_key, algorithms=["HS256"])
|
||||
bearer_token = await get_bearer_token(shared_secret, client_key)
|
||||
context['bitbucket_bearer_token'] = bearer_token
|
||||
context["settings"] = copy.deepcopy(global_settings)
|
||||
event = data["event"]
|
||||
agent = PRAgent()
|
||||
if event == "pullrequest:created":
|
||||
pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
|
||||
log_context["api_url"] = pr_url
|
||||
log_context["event"] = "pull_request"
|
||||
if pr_url:
|
||||
with get_logger().contextualize(**log_context):
|
||||
apply_repo_settings(pr_url)
|
||||
if get_identity_provider().verify_eligibility("bitbucket",
|
||||
sender_id, pr_url) is not Eligibility.NOT_ELIGIBLE:
|
||||
if get_settings().get("bitbucket_app.pr_commands"):
|
||||
await _perform_commands_bitbucket("pr_commands", PRAgent(), pr_url, log_context)
|
||||
else: # backwards compatibility
|
||||
auto_review = get_setting_or_env("BITBUCKET_APP.AUTO_REVIEW", None)
|
||||
if is_true(auto_review): # by default, auto review is disabled
|
||||
await PRReviewer(pr_url).run()
|
||||
auto_improve = get_setting_or_env("BITBUCKET_APP.AUTO_IMPROVE", None)
|
||||
if is_true(auto_improve): # by default, auto improve is disabled
|
||||
await PRCodeSuggestions(pr_url).run()
|
||||
auto_describe = get_setting_or_env("BITBUCKET_APP.AUTO_DESCRIBE", None)
|
||||
if is_true(auto_describe): # by default, auto describe is disabled
|
||||
await PRDescription(pr_url).run()
|
||||
elif event == "pullrequest:comment_created":
|
||||
pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
|
||||
log_context["api_url"] = pr_url
|
||||
log_context["event"] = "comment"
|
||||
comment_body = data["data"]["comment"]["content"]["raw"]
|
||||
with get_logger().contextualize(**log_context):
|
||||
if get_identity_provider().verify_eligibility("bitbucket",
|
||||
sender_id, pr_url) is not Eligibility.NOT_ELIGIBLE:
|
||||
await agent.handle_request(pr_url, comment_body)
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to handle webhook: {e}")
|
||||
background_tasks.add_task(inner)
|
||||
return "OK"
|
||||
|
||||
@router.get("/webhook")
|
||||
async def handle_github_webhooks(request: Request, response: Response):
|
||||
return "Webhook server online!"
|
||||
|
||||
@router.post("/installed")
|
||||
async def handle_installed_webhooks(request: Request, response: Response):
|
||||
try:
|
||||
get_logger().info("handle_installed_webhooks")
|
||||
get_logger().info(request.headers)
|
||||
data = await request.json()
|
||||
get_logger().info(data)
|
||||
shared_secret = data["sharedSecret"]
|
||||
client_key = data["clientKey"]
|
||||
username = data["principal"]["username"]
|
||||
secrets = {
|
||||
"shared_secret": shared_secret,
|
||||
"client_key": client_key
|
||||
}
|
||||
secret_provider.store_secret(username, json.dumps(secrets))
|
||||
except Exception as e:
|
||||
get_logger().error(f"Failed to register user: {e}")
|
||||
return JSONResponse({"error": "Unable to register user"}, status_code=500)
|
||||
|
||||
@router.post("/uninstalled")
|
||||
async def handle_uninstalled_webhooks(request: Request, response: Response):
|
||||
get_logger().info("handle_uninstalled_webhooks")
|
||||
|
||||
data = await request.json()
|
||||
get_logger().info(data)
|
||||
|
||||
|
||||
def start():
|
||||
get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
|
||||
get_settings().set("CONFIG.GIT_PROVIDER", "bitbucket")
|
||||
get_settings().set("PR_DESCRIPTION.PUBLISH_DESCRIPTION_AS_COMMENT", True)
|
||||
middleware = [Middleware(RawContextMiddleware)]
|
||||
app = FastAPI(middleware=middleware)
|
||||
app.include_router(router)
|
||||
|
||||
uvicorn.run(app, host="0.0.0.0", port=int(os.getenv("PORT", "3000")))
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
start()
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user