xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-06 22:00:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into pre_pr

Browse Source
This commit is contained in:
Ori Kotek
2023-08-30 15:53:59 +03:00
parent c5d05d53cd f14c5d296a
commit 588eb6e97f
11 changed files with 412 additions and 127 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
INSTALL.md
View File

@ -1,9 +1,23 @@
## Installation
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.
2. A GitHub personal access token (classic) with the repo scope.
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)
- [Method 5: Run as a GitHub App](INSTALL.md#method-5-run-as-a-github-app)
- [Method 6: Deploy as a Lambda Function](INSTALL.md#method-6---deploy-as-a-lambda-function)
- [Method 7: AWS CodeCommit](INSTALL.md#method-7---aws-codecommit-setup)
---
#### Method 1: Use Docker image (no installation required)
### 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:
@ -41,7 +55,7 @@ Possible questions you can ask include:
---
#### Method 2: Run as a GitHub Action
### 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.
@ -111,7 +125,7 @@ When you open your next PR, you should see a comment from `github-actions` bot w
---
#### Method 3: Run from source
### Method 3: Run from source
1. Clone this repository:
@ -143,17 +157,9 @@ python pr_agent/cli.py --pr_url <pr_url> describe
python pr_agent/cli.py --pr_url <pr_url> improve
```
5. **Debugging LLM API Calls**
If you're testing your codium/pr-agent server, and need to see if calls were made successfully + the exact call logs, you can use the [LiteLLM Debugger tool](https://docs.litellm.ai/docs/debugging/hosted_debugging).
You can do this by setting `litellm_debugger=true` in configuration.toml. Your Logs will be viewable in real-time @ `admin.litellm.ai/<your_email>`. Set your email in the `.secrets.toml` under 'user_email'.
<img src="./pics/debugger.png" width="900"/>
---
#### Method 4: Run as a polling server
### Method 4: Run as a polling server
Request reviews by tagging your Github user on a PR
Follow steps 1-3 of method 2.
@ -165,7 +171,7 @@ python pr_agent/servers/github_polling.py
---
#### Method 5: Run as a GitHub App
### 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).
@ -247,7 +253,7 @@ docker push codiumai/pr-agent:github_app # Push to your Docker repository
---
#### Deploy as a Lambda Function
### Method 6 - 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
@ -266,7 +272,7 @@ docker push codiumai/pr-agent:github_app # Push to your Docker repository
---
#### AWS CodeCommit Setup
### Method 7 - 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:
@ -281,7 +287,7 @@ Not all features have been added to CodeCommit yet. As of right now, CodeCommit
* 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
##### AWS CodeCommit IAM Role Example
Example IAM permissions to that user to allow access to CodeCommit:
@ -311,7 +317,7 @@ Example IAM permissions to that user to allow access to CodeCommit:
}
```
#### AWS CodeCommit Access Key and Secret
##### AWS CodeCommit Access Key and Secret
Example setting the Access Key and Secret using environment variables
@ -321,7 +327,7 @@ export AWS_SECRET_ACCESS_KEY="XXXXXXXXXXXXXXXX"
export AWS_DEFAULT_REGION="us-east-1"
```
#### AWS CodeCommit CLI Example
##### 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)
@ -331,3 +337,10 @@ 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
```
### Appendix - **Debugging LLM API Calls**
If you're testing your codium/pr-agent server, and need to see if calls were made successfully + the exact call logs, you can use the [LiteLLM Debugger tool](https://docs.litellm.ai/docs/debugging/hosted_debugging).
You can do this by setting `litellm_debugger=true` in configuration.toml. Your Logs will be viewable in real-time @ `admin.litellm.ai/<your_email>`. Set your email in the `.secrets.toml` under 'user_email'.
<img src="./pics/debugger.png" width="800"/>

29
README.md
View File

@ -15,45 +15,45 @@ Making pull requests less painful with an AI agent
</div>
<div style="text-align:left;">
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:
CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull requests faster and more efficiently. It automatically analyzes the pull request and can provide several types of PR feedback:
**Auto-Description**: Automatically generating PR description - title, type, summary, code walkthrough and PR labels.
**Auto-Description**: Automatically generating [PR description](https://github.com/Codium-ai/pr-agent/pull/229#issue-1860711415) - title, type, summary, code walkthrough and labels.
\
**PR Review**: Adjustable feedback about the PR main theme, type, relevant tests, security issues, focus, score, and various suggestions for the PR content.
**Auto Review**: [Adjustable feedback](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695022908) about the PR main theme, type, relevant tests, security issues, score, and various suggestions for the PR content.
\
**Question Answering**: Answering free-text questions about the PR.
**Question Answering**: Answering [free-text questions](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021332) about the PR.
\
**Code Suggestions**: Committable code suggestions for improving the PR.
**Code Suggestions**: [Committable code suggestions](https://github.com/Codium-ai/pr-agent/pull/229#discussion_r1306919276) for improving the PR.
\
**Update Changelog**: Automatically updating the CHANGELOG.md file with the PR changes.
**Update Changelog**: Automatically updating the CHANGELOG.md file with the [PR changes](https://github.com/Codium-ai/pr-agent/pull/168#discussion_r1282077645).
<h3>Example results:</h2>
</div>
<h4>/describe:</h4>
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1687561986">/describe:</a></h4>
<div align="center">
<p float="center">
<img src="https://www.codium.ai/images/describe-2.gif" width="800">
</p>
</div>
<h4>/review:</h4>
<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901">/review:</a></h4>
<div align="center">
<p float="center">
<img src="https://www.codium.ai/images/review-2.gif" width="800">
</p>
</div>
<h4>/reflect_and_review:</h4>
<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>/ask:</h4>
<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>/improve:</h4>
<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">
@ -82,6 +82,7 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
| | Ask | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | Auto-Description | :white_check_mark: | :white_check_mark: | | |
| | Improve Code | :white_check_mark: | :white_check_mark: | | |
| | ⮑ Extended | :white_check_mark: | :white_check_mark: | | |
| | Reflect and Review | :white_check_mark: | | | |
| | Update CHANGELOG.md | :white_check_mark: | | | |
| | | | | | |
@ -134,7 +135,8 @@ There are several ways to use PR-Agent:
- 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
- [Method 6: Deploy as a Lambda Function](INSTALL.md#method-6---deploy-as-a-lambda-function)
- [Method 7: AWS CodeCommit](INSTALL.md#method-7---aws-codecommit-setup)
## How it works
@ -160,8 +162,9 @@ Here are some advantages of PR-Agent:
## Roadmap
- [x] Support additional models, as a replacement for OpenAI (see [here](https://github.com/Codium-ai/pr-agent/pull/172))
- [ ] Develop additional logic for handling large PRs
- [x] Develop additional logic for handling large PRs (see [here](https://github.com/Codium-ai/pr-agent/pull/229))
- [ ] Add additional context to the prompt. For example, repo (or relevant files) summarization, with tools such a [ctags](https://github.com/universal-ctags/ctags)
- [ ] PR-Agent for issues, and just for pull requests
- [ ] Adding more tools. Possible directions:
- [x] PR description
- [x] Inline code suggestions

3
docker/Dockerfile
View File

@ -2,7 +2,8 @@ FROM python:3.10 as base
WORKDIR /app
ADD pyproject.toml .
RUN pip install . && rm pyproject.toml
ADD requirements.txt .
RUN pip install . && rm pyproject.toml requirements.txt
ENV PYTHONPATH=/app
FROM base as github_app

3
pr_agent/algo/ai_handler.py
View File

@ -87,8 +87,6 @@ class AiHandler:
f"Generating completion with {model}"
f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
)
if self.azure:
model = self.azure + "/" + model
response = await acompletion(
model=model,
deployment_id=deployment_id,
@ -97,6 +95,7 @@ class AiHandler:
{"role": "user", "content": user}
],
temperature=temperature,
azure=self.azure,
force_timeout=get_settings().config.ai_timeout
)
except (APIError, Timeout, TryAgain) as e:

2
pr_agent/algo/utils.py
View File

@ -286,7 +286,7 @@ def _fix_key_value(key: str, value: str):
def load_yaml(review_text: str) -> dict:
review_text = review_text.removeprefix('```yaml').rstrip('`')
try:
data = yaml.load(review_text, Loader=yaml.SafeLoader)
data = yaml.safe_load(review_text)
except Exception as e:
logging.error(f"Failed to parse AI prediction: {e}")
data = try_fix_yaml(review_text)

2
pr_agent/git_providers/__init__.py
View File

@ -4,11 +4,13 @@ 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
_GIT_PROVIDERS = {
'github': GithubProvider,
'gitlab': GitLabProvider,
'bitbucket': BitbucketProvider,
'azure': AzureDevopsProvider,
'codecommit': CodeCommitProvider,
'local' : LocalGitProvider
}

269
pr_agent/git_providers/azuredevops_provider.py Normal file
View File

@ -0,0 +1,269 @@
import json
import logging
from typing import Optional, Tuple
from urllib.parse import urlparse
import os
AZURE_DEVOPS_AVAILABLE = True
try:
from msrest.authentication import BasicAuthentication
from azure.devops.connection import Connection
from azure.devops.v7_1.git.models import Comment, CommentThread, GitVersionDescriptor, GitPullRequest
except ImportError:
AZURE_DEVOPS_AVAILABLE = False
from ..algo.pr_processing import clip_tokens
from ..config_loader import get_settings
from ..algo.utils import load_large_diff
from ..algo.language_handler import is_valid_file
from .git_provider import EDIT_TYPE, FilePatchInfo
class AzureDevopsProvider:
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.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 is_supported(self, capability: str) -> bool:
if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels', 'remove_initial_comment']:
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 contents
except Exception as e:
logging.exception("get repo settings error")
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:
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:
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')
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
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')
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
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):
comment = Comment(content=pr_comment)
thread = CommentThread(comments=[comment])
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)
if is_temporary:
self.temp_comments.append({'thread_id': thread_response.id, 'comment_id': comment.id})
def publish_description(self, pr_title: str, pr_body: str):
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:
logging.exception(f"Could not update pull request {self.pr_num} description: {e}")
def remove_initial_comment(self):
return "" # not implemented yet
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
raise NotImplementedError("Azure DevOps provider does not support publishing inline comment yet")
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
raise NotImplementedError("Azure DevOps provider does not support creating inline comments yet")
def publish_inline_comments(self, comments: list[dict]):
raise NotImplementedError("Azure DevOps provider does not support publishing inline comments yet")
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):
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) -> Optional[int]:
return True
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
return True
def get_issue_comments(self):
raise NotImplementedError("Azure DevOps provider does not support issue comments yet")
@staticmethod
def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
parsed_url = urlparse(pr_url)
if 'azure.com' not in parsed_url.netloc:
raise ValueError("The provided URL is not a valid Azure DevOps 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
def _get_azure_devops_client(self):
try:
pat = get_settings().azure_devops.pat
org = get_settings().azure_devops.org
except AttributeError as e:
raise ValueError(
"Azure DevOps PAT token is required ") from e
credentials = BasicAuthentication('', pat)
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

9
pr_agent/git_providers/git_provider.py
View File

@ -1,3 +1,4 @@
import logging
from abc import ABC, abstractmethod
# enum EDIT_TYPE (ADDED, DELETED, MODIFIED, RENAMED)
@ -119,6 +120,8 @@ def get_main_pr_language(languages, files) -> str:
# validate that the specific commit uses the main language
extension_list = []
for file in files:
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
@ -140,10 +143,12 @@ def get_main_pr_language(languages, files) -> str:
most_common_extension == 'scala' and top_language == 'scala' or \
most_common_extension == 'kt' and top_language == 'kotlin' or \
most_common_extension == 'pl' and top_language == 'perl' or \
most_common_extension == 'swift' and top_language == 'swift':
most_common_extension == 'swift' and top_language == 'swift' or \
most_common_extension == top_language:
main_language_str = top_language
except Exception:
except Exception as e:
logging.exception(e)
pass
return main_language_str

129
pr_agent/settings/pr_code_suggestions_prompts.toml
View File

@ -1,8 +1,8 @@
[pr_code_suggestions_prompt]
system="""You are a language model called PR-Code-Reviewer.
Your task is to provide meaningful actionable code suggestions, to improve the new code presented in a PR.
system="""You are a language model called PR-Code-Reviewer, that specializes in suggesting code improvements for Pull Request (PR).
Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR.
Example PR Diff input:
Example for a PR Diff input:
'
## src/file1.py
@ -10,8 +10,8 @@ Example PR Diff input:
__new hunk__
12 code line that already existed in the file...
13 code line that already existed in the file....
14 +new code line added in the PR
15 code line that already existed in the file...
14 +new code line1 added in the PR
15 +new code line2 added in the PR
16 code line that already existed in the file...
__old hunk__
code line that already existed in the file...
@ -31,13 +31,17 @@ __old hunk__
'
Specific instructions:
- Focus on important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningful code improvements, like performance, vulnerability, modularity, and best practices.
- Suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
- Provide the exact line number range (inclusive) for each issue.
- Assume there is additional relevant code, that is not included in the diff.
- Provide up to {{ num_code_suggestions }} code suggestions.
- Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the '__new hunk__' code.
- Don't suggest to add docstring or type hints.
- Prioritize suggestions that address major problems, issues and bugs in the code.
As a second priority, suggestions should focus on best practices, code readability, maintainability, enhancments, performance, and other aspects.
Don't suggest to add docstring or type hints.
Try to provide diverse and insightful suggestions.
- Suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the '__new hunk__' code.
For each suggestion, make sure to take into consideration also the context, meaning the lines before and after the relevant code.
- Provide the exact line numbers range (inclusive) for each issue.
- Assume there is additional relevant code, that is not included in the diff.
{%- if extra_instructions %}
@ -45,63 +49,76 @@ Extra instructions from the user:
{{ extra_instructions }}
{%- endif %}
You must use the following JSON schema to format your answer:
```json
{
"Code suggestions": {
"type": "array",
"minItems": 1,
"maxItems": {{ num_code_suggestions }},
"uniqueItems": "true",
"items": {
"relevant file": {
"type": "string",
"description": "the relevant file full path"
},
"suggestion content": {
"type": "string",
"description": "a concrete suggestion for meaningfully improving the new PR code (lines from the '__new hunk__' sections, starting with '+')."
},
"existing code": {
"type": "string",
"description": "a code snippet showing the relevant code lines from a '__new hunk__' section. It must be continuous, correctly formatted and indented, and without line numbers."
},
"relevant lines": {
"type": "string",
"description": "the relevant lines from a '__new hunk__' section, in the format of 'start_line-end_line'. For example: '10-15'. They should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above."
},
"improved code": {
"type": "string",
"description": "a new code snippet that can be used to replace the relevant lines in '__new hunk__' code. Replacement suggestions should be complete, correctly formatted and indented, and without line numbers."
}
}
}
}
You must use the following YAML schema to format your answer:
```yaml
Code suggestions:
type: array
minItems: 1
maxItems: {{ num_code_suggestions }}
uniqueItems: true
items:
relevant file:
type: string
description: the relevant file full path
suggestion content:
type: string
description: |-
a concrete suggestion for meaningfully improving the new PR code.
existing code:
type: string
description: |-
a code snippet showing the relevant code lines from a '__new hunk__' section.
It must be continuous, correctly formatted and indented, and without line numbers.
relevant lines:
type: string
description: |-
the relevant lines from a '__new hunk__' section, in the format of 'start_line-end_line'.
For example: '10-15'. They should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above.
improved code:
type: string
description: |-
a new code snippet that can be used to replace the relevant lines in '__new hunk__' code.
Replacement suggestions should be complete, correctly formatted and indented, and without line numbers.
```
Don't output line numbers in the 'improved code' snippets.
Example output:
```yaml
Code suggestions:
- relevant file: |-
src/file1.py
suggestion content: |-
Add a docstring to func1()
existing code: |-
def func1():
relevant lines: '12-12'
improved code: |-
...
```
Each YAML output MUST be after a newline, indented, with block scalar indicator ('|-').
Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
"""
user="""PR Info:
Title: '{{title}}'
Branch: '{{branch}}'
Description: '{{description}}'
{%- if language %}
Main language: {{language}}
{%- endif %}
{%- if commit_messages_str %}
Commit messages:
{{commit_messages_str}}
Title: '{{title}}'
Branch: '{{branch}}'
Description: '{{description}}'
{%- if language %}
Main language: {{language}}
{%- endif %}
The PR Diff:
```
{{diff}}
{{- diff|trim }}
```
Response (should be a valid JSON, and nothing else):
```json
Response (should be a valid YAML, and nothing else):
```yaml
"""

20
pr_agent/tools/pr_code_suggestions.py
View File

@ -1,16 +1,13 @@
import copy
import json
import logging
import textwrap
from typing import List
import yaml
from typing import List, Dict
from jinja2 import Environment, StrictUndefined
from pr_agent.algo.ai_handler import AiHandler
from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, get_pr_multi_diffs
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import try_fix_json
from pr_agent.algo.utils import load_yaml
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import BitbucketProvider, get_git_provider
from pr_agent.git_providers.git_provider import get_main_pr_language
@ -96,14 +93,11 @@ class PRCodeSuggestions:
return response
def _prepare_pr_code_suggestions(self) -> str:
def _prepare_pr_code_suggestions(self) -> Dict:
review = self.prediction.strip()
try:
data = json.loads(review)
except json.decoder.JSONDecodeError:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Could not parse json response: {review}")
data = try_fix_json(review, code_suggestions=True)
data = load_yaml(review)
if isinstance(data, list):
data = {'Code suggestions': data}
return data
def push_inline_code_suggestions(self, data):
@ -225,7 +219,7 @@ class PRCodeSuggestions:
response, finish_reason = await self.ai_handler.chat_completion(model=model, system=system_prompt,
user=user_prompt)
sort_order = yaml.safe_load(response)
sort_order = load_yaml(response)
for s in sort_order['Sort Order']:
suggestion_number = s['suggestion number']
importance_order = s['importance order']

24
pyproject.toml
View File

@ -26,28 +26,10 @@ classifiers = [
"Operating System :: Independent",
"Programming Language :: Python :: 3",
]
dynamic = ["dependencies"]
dependencies = [
"dynaconf==3.1.12",
"fastapi==0.99.0",
"PyGithub==1.59.*",
"retry==0.9.2",
"openai==0.27.8",
"Jinja2==3.1.2",
"tiktoken==0.4.0",
"uvicorn==0.22.0",
"python-gitlab==3.15.0",
"pytest~=7.4.0",
"aiohttp~=3.8.4",
"atlassian-python-api==3.39.0",
"GitPython~=3.1.32",
"starlette-context==0.3.6",
"litellm~=0.1.445",
"PyYAML==6.0",
"boto3~=1.28.25",
"google-cloud-storage==2.10.0",
"ujson==5.8.0"
]
[tool.setuptools.dynamic]
dependencies = {file = ["requirements.txt"]}
[project.urls]
"Homepage" = "https://github.com/Codium-ai/pr-agent"