xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-03 04:10:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into main

Browse Source
This commit is contained in:
mrT23
2023-08-23 09:16:00 +03:00
committed by GitHub
parent dcad490513 f2ab623e76
commit 53108a9b20
28 changed files with 1309 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/build-and-test.yaml vendored
View File

@ -2,6 +2,8 @@ name: Build-and-test
on:
push:
pull_request:
types: [ opened, reopened ]
jobs:
build-and-test:

76
INSTALL.md
View File

@ -54,6 +54,10 @@ on:
jobs:
pr_agent_job:
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
@ -72,6 +76,10 @@ on:
jobs:
pr_agent_job:
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
@ -255,3 +263,71 @@ docker push codiumai/pr-agent:github_app # Push to your Docker repository
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`
---
#### 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"
],
"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
```

42
README.md
View File

@ -75,26 +75,26 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
## 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: | :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: | | |
| | Update CHANGELOG.md | :white_check_mark: | | |
| | | | | |
| USAGE | CLI | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | App / webhook | :white_check_mark: | :white_check_mark: | |
| | Tagging bot | :white_check_mark: | | |
| | Actions | :white_check_mark: | | |
| | | | | |
| CORE | PR compression | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | 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: |
| | Multiple models support | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | Incremental PR Review | :white_check_mark: | | |
| | | GitHub | Gitlab | Bitbucket | CodeCommit |
|-------|---------------------------------------------|:------:|:------:|:---------:|:----------:|
| TOOLS | Review | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | ⮑ Inline review | :white_check_mark: | :white_check_mark: | | |
| | Ask | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | Auto-Description | :white_check_mark: | :white_check_mark: | | |
| | Improve Code | :white_check_mark: | :white_check_mark: | | |
| | Reflect and Review | :white_check_mark: | | | |
| | Update CHANGELOG.md | :white_check_mark: | | | |
| | | | | | |
| USAGE | CLI | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
| | App / webhook | :white_check_mark: | :white_check_mark: | | |
| | Tagging bot | :white_check_mark: | | | |
| | Actions | :white_check_mark: | | | |
| | | | | | |
| CORE | PR compression | :white_check_mark: | :white_check_mark: | :white_check_mark: | |
| | 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: | |
| | Multiple models support | :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
@ -153,7 +153,7 @@ Here are some advantages of PR-Agent:
- We emphasize **real-life practical usage**. Each tool (review, improve, ask, ...) has a single GPT-4 call, no more. We feel that this is critical for realistic team usage - obtaining an answer quickly (~30 seconds) and affordably.
- Our [PR Compression strategy](./PR_COMPRESSION.md) is a core ability that enables to effectively tackle both short and long PRs.
- Our JSON prompting strategy enables to have **modular, customizable tools**. For example, the '/review' tool categories can be controlled via the [configuration](./CONFIGURATION.md) file. Adding additional categories is easy and accessible.
- 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).
- We support **multiple git providers** (GitHub, Gitlab, Bitbucket, CodeCommit), **multiple ways** to use the tool (CLI, GitHub Action, GitHub App, Docker, ...), and **multiple models** (GPT-4, GPT-3.5, Anthropic, Cohere, Llama2).
- We are open-source, and welcome contributions from the community.

2
pr_agent/algo/ai_handler.py
View File

@ -62,7 +62,7 @@ class AiHandler:
@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):
async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
"""
Performs a chat completion using the OpenAI ChatCompletion API.
Retries in case of API errors or timeouts.

26
pr_agent/algo/git_patch_processing.py
View File

@ -1,5 +1,4 @@
from __future__ import annotations
import logging
import re
@ -157,7 +156,7 @@ 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
@ -166,7 +165,7 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
889 line6
890 line7
...
--old hunk--
__old hunk__
line1
line2
- line3
@ -176,8 +175,7 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
...
"""
patch_with_lines_str = f"## {file.filename}\n"
import re
patch_with_lines_str = f"\n\n## {file.filename}\n"
patch_lines = patch.splitlines()
RE_HUNK_HEADER = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
@ -185,23 +183,30 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
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:
patch_with_lines_str += '\n--new hunk--\n'
if prev_header_line:
patch_with_lines_str += f'\n{prev_header_line}\n'
patch_with_lines_str += '__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 += '--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
try:
start1, size1, start2, size2 = map(int, match.groups()[:4])
except: # '@@ -0,0 +1 @@' case
@ -219,12 +224,13 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
# finishing last hunk
if match and new_content_lines:
if new_content_lines:
patch_with_lines_str += '\n--new hunk--\n'
patch_with_lines_str += f'\n{header_line}\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 += '\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.strip()
return patch_with_lines_str.rstrip()

106
pr_agent/algo/pr_processing.py
View File

@ -24,7 +24,7 @@ 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:
add_line_numbers_to_hunks: bool = True, disable_extra_lines: bool = True) -> str:
"""
Returns a string with the diff of the pull request, applying diff minimization techniques if needed.
@ -57,7 +57,7 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
# generate a standard diff string, with patch extension
patches_extended, total_tokens = pr_generate_extended_diff(pr_languages, token_handler,
patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(pr_languages, token_handler,
add_line_numbers_to_hunks)
# if we are under the limit, return the full diff
@ -78,9 +78,9 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
return final_diff
def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
add_line_numbers_to_hunks: bool) -> \
Tuple[list, int]:
def pr_generate_extended_diff(pr_languages: list,
token_handler: TokenHandler,
add_line_numbers_to_hunks: bool) -> Tuple[list, int, list]:
"""
Generate a standard diff string with patch extension, while counting the number of tokens used and applying diff
minimization techniques if needed.
@ -90,13 +90,10 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
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
@ -106,7 +103,7 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
# 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"## {file.filename}\n\n{extended_patch}\n"
full_extended_patch = f"\n\n## {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)
@ -114,9 +111,10 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
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
return patches_extended, total_tokens, patches_extended_tokens
def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, model: str,
@ -324,7 +322,9 @@ def clip_tokens(text: str, max_tokens: int) -> str:
Returns:
str: The clipped string.
"""
# We'll estimate the number of tokens by hueristically assuming 2.5 tokens per word
if not text:
return text
try:
encoder = get_token_encoder()
num_input_tokens = len(encoder.encode(text))
@ -337,4 +337,84 @@ def clip_tokens(text: str, max_tokens: int) -> str:
return clipped_text
except Exception as e:
logging.warning(f"Failed to clip tokens: {e}")
return text
return text
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:
logging.error(f"Rate limit exceeded for git provider API. original message {e}")
raise
# 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))
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:
logging.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)
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 (total_tokens + new_patch_tokens > 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:
logging.info(f"Call number: {call_number}")
if patch:
patches.append(patch)
total_tokens += new_patch_tokens
if get_settings().config.verbosity_level >= 2:
logging.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

3
pr_agent/algo/utils.py
View File

@ -247,7 +247,8 @@ def update_settings_from_args(args: List[str]) -> List[str]:
arg = arg.strip('-').strip()
vals = arg.split('=', 1)
if len(vals) != 2:
logging.error(f'Invalid argument format: {arg}')
if len(vals) > 2: # --extended is a valid argument
logging.error(f'Invalid argument format: {arg}')
other_args.append(arg)
continue
key, value = _fix_key_value(*vals)

20
pr_agent/cli.py
View File

@ -19,13 +19,21 @@ For example:
- 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.
reflect - Ask the PR author questions about the PR.
update_changelog - Update the changelog based on the PR's contents.
-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.
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: ..."'
""")

1
pr_agent/config_loader.py
View File

@ -19,6 +19,7 @@ global_settings = Dynaconf(
"settings/pr_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_prod/.secrets.toml"

2
pr_agent/git_providers/__init__.py
View File

@ -1,5 +1,6 @@
from pr_agent.config_loader import get_settings
from pr_agent.git_providers.bitbucket_provider import BitbucketProvider
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
@ -8,6 +9,7 @@ _GIT_PROVIDERS = {
'github': GithubProvider,
'gitlab': GitLabProvider,
'bitbucket': BitbucketProvider,
'codecommit': CodeCommitProvider,
'local' : LocalGitProvider
}

12
pr_agent/git_providers/bitbucket_provider.py
View File

@ -6,12 +6,11 @@ from urllib.parse import urlparse
import requests
from atlassian.bitbucket import Cloud
from ..algo.pr_processing import clip_tokens
from ..config_loader import get_settings
from .git_provider import FilePatchInfo
from .git_provider import FilePatchInfo, GitProvider
class BitbucketProvider:
class BitbucketProvider(GitProvider):
def __init__(self, pr_url: Optional[str] = None, incremental: Optional[bool] = False):
s = requests.Session()
s.headers['Authorization'] = f'Bearer {get_settings().get("BITBUCKET.BEARER_TOKEN", None)}'
@ -36,7 +35,7 @@ class BitbucketProvider:
except Exception:
return ""
def publish_code_suggestions(self, code_suggestions: list):
def publish_code_suggestions(self, code_suggestions: list) -> bool:
"""
Publishes code suggestions as comments on the PR.
"""
@ -156,10 +155,7 @@ class BitbucketProvider:
def get_pr_branch(self):
return self.pr.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)
def get_pr_description_full(self):
return self.pr.description
def get_user_id(self):

203
pr_agent/git_providers/codecommit_client.py Normal file
View File

@ -0,0 +1,203 @@
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 _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}")
def get_differences(self, repo_name: int, destination_commit: str, source_commit: str):
"""
Get the differences between two commits in CodeCommit.
Parameters:
- 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:
raise ValueError(f"Failed to retrieve differences from CodeCommit PR #{self.pr_num}") 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.
Parameters:
- 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 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, pr_number: int):
"""
Get a information about a CodeCommit PR.
Parameters:
- 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
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_comment(self, repo_name: str, pr_number: int, destination_commit: str, source_commit: str, comment: str):
"""
Publish a comment to a pull request
Parameters:
- 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)
- pr_comment: comment
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:
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

363
pr_agent/git_providers/codecommit_provider.py Normal file
View File

@ -0,0 +1,363 @@
import logging
import os
from collections import Counter
from typing import List, Optional, Tuple
from urllib.parse import urlparse
from ..algo.language_handler import is_valid_file, language_extension_map
from ..algo.pr_processing import clip_tokens
from ..algo.utils import load_large_diff
from ..config_loader import get_settings
from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider, IncrementalPR
from pr_agent.git_providers.codecommit_client import CodeCommitClient
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
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",
]:
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):
return "" # not implemented yet
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
if is_temporary:
logging.info(pr_comment)
return
try:
self.codecommit_client.publish_comment(
repo_name=self.repo_name,
pr_number=str(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 post comment for PR: {self.pr_num}") from e
def publish_code_suggestions(self, code_suggestions: list) -> bool:
return [""] # not implemented yet
def publish_labels(self, labels):
return [""] # not implemented yet
def get_labels(self):
return [""] # not implemented yet
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("CodeCommit provider does not support publishing inline comments yet")
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
raise NotImplementedError("CodeCommit provider does not support creating 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.get("title", "")
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 = {}
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) -> 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, int]:
# 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 "us-east-1.console.aws.amazon.com" not in 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
def _get_pr(self):
response = self.codecommit_client.get_pr(self.pr_num)
if len(response.targets) == 0:
raise ValueError(f"No files found in CodeCommit PR: {self.pr_num}")
# TODO: implement support for multiple commits in one CodeCommit PR
# for now, we are only using the first commit in the PR
if len(response.targets) > 1:
logging.warning(
"Multiple commits in one PR is not supported for CodeCommit yet. Continuing, using the first commit 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 _get_edit_type(codecommit_change_type):
"""
Convert the CodeCommit change type string to the EDIT_TYPE enum.
The CodeCommit change type string is returned from the get_differences SDK method.
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.
"""
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.
"""
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

25
pr_agent/git_providers/git_provider.py
View File

@ -54,7 +54,7 @@ class GitProvider(ABC):
pass
@abstractmethod
def publish_code_suggestions(self, code_suggestions: list):
def publish_code_suggestions(self, code_suggestions: list) -> bool:
pass
@abstractmethod
@ -82,9 +82,30 @@ class GitProvider(ABC):
pass
@abstractmethod
def get_pr_description(self):
def get_pr_description_full(self) -> str:
pass
def get_pr_description(self) -> str:
from pr_agent.config_loader import get_settings
from pr_agent.algo.pr_processing import clip_tokens
max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
description = self.get_pr_description_full()
if max_tokens:
return clip_tokens(description, max_tokens)
return description
def get_user_description(self) -> str:
description = (self.get_pr_description_full() or "").strip()
# if the existing description wasn't generated by the pr-agent, just return it as-is
if not description.startswith("## PR Type"):
return description
# if the existing description was generated by the pr-agent, but it doesn't contain the user description,
# return nothing (empty string) because it means there is no user description
if "## User Description:" not in description:
return ""
# otherwise, extract the original user description from the existing pr-agent description and return it
return description.split("## User Description:", 1)[1].strip()
@abstractmethod
def get_issue_comments(self):
pass

7
pr_agent/git_providers/github_provider.py
View File

@ -166,7 +166,7 @@ class GithubProvider(GitProvider):
def publish_inline_comments(self, comments: list[dict]):
self.pr.create_review(commit=self.last_commit_id, comments=comments)
def publish_code_suggestions(self, code_suggestions: list):
def publish_code_suggestions(self, code_suggestions: list) -> bool:
"""
Publishes code suggestions as comments on the PR.
"""
@ -233,10 +233,7 @@ class GithubProvider(GitProvider):
def get_pr_branch(self):
return self.pr.head.ref
def get_pr_description(self):
max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
if max_tokens:
return clip_tokens(self.pr.body, max_tokens)
def get_pr_description_full(self):
return self.pr.body
def get_user_id(self):

7
pr_agent/git_providers/gitlab_provider.py
View File

@ -195,7 +195,7 @@ class GitLabProvider(GitProvider):
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):
def publish_code_suggestions(self, code_suggestions: list) -> bool:
for suggestion in code_suggestions:
try:
body = suggestion['body']
@ -299,10 +299,7 @@ class GitLabProvider(GitProvider):
def get_pr_branch(self):
return self.mr.source_branch
def get_pr_description(self):
max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
if max_tokens:
return clip_tokens(self.mr.description, max_tokens)
def get_pr_description_full(self):
return self.mr.description
def get_issue_comments(self):

4
pr_agent/git_providers/local_git_provider.py
View File

@ -130,7 +130,7 @@ class LocalGitProvider(GitProvider):
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):
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):
@ -158,7 +158,7 @@ class LocalGitProvider(GitProvider):
def get_user_id(self):
return -1 # Not used anywhere for the local provider, but required by the interface
def get_pr_description(self):
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])

2
pr_agent/servers/help.py
View File

@ -1,7 +1,7 @@
commands_text = "> **/review [-i]**: Request a review of your Pull Request. For an incremental review, which only " \
"considers changes since the last review, include the '-i' option.\n" \
"> **/describe**: Modify the PR title and description based on the contents of the PR.\n" \
"> **/improve**: Suggest improvements to the code in the PR. \n" \
"> **/improve [--extended]**: Suggest improvements to the code in the PR. Extended mode employs several calls, and provides a more thorough feedback. \n" \
"> **/ask \\<QUESTION\\>**: Pose a question about the PR.\n" \
"> **/update_changelog**: Update the changelog based on the PR's contents.\n\n" \
">To edit any configuration parameter from **configuration.toml**, add --config_path=new_value\n" \

8
pr_agent/settings/configuration.toml
View File

@ -25,6 +25,8 @@ extra_instructions = ""
[pr_description] # /describe #
publish_description_as_comment=false
add_original_user_description=false
keep_original_user_title=false
extra_instructions = ""
[pr_questions] # /ask #
@ -32,6 +34,12 @@ extra_instructions = ""
[pr_code_suggestions] # /improve #
num_code_suggestions=4
extra_instructions = ""
rank_suggestions = false
# params for '/improve --extended' mode
num_code_suggestions_per_chunk=8
rank_extended_suggestions = true
max_number_of_calls = 5
final_clip_factor = 0.9
[pr_update_changelog] # /update_changelog #
push_changelog_changes=false

69
pr_agent/settings/pr_code_suggestions_prompts.toml
View File

@ -1,19 +1,49 @@
[pr_code_suggestions_prompt]
system="""You are a language model called CodiumAI-PR-Code-Reviewer.
Your task is to provide meaningfull non-trivial code suggestions to improve the new code in a PR (the '+' lines).
- Try to give important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningfull code improvements, like performance, vulnerability, modularity, and best practices.
- Suggestions should refer only to the 'new hunk' code, and focus on improving the new added code lines, with '+'.
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.
Example PR Diff input:
'
## src/file1.py
@@ -12,3 +12,5 @@ def func1():
__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...
16 code line that already existed in the file...
__old hunk__
code line that already existed in the file...
-code line that was removed in the PR
code line that already existed in the file...
@@ ... @@ def func2():
__new hunk__
...
__old hunk__
...
## src/file2.py
...
'
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 code in the relevant file that is not included in the diff.
- Assume there is additional relevant code, that is not included in the diff.
- Provide up to {{ num_code_suggestions }} code suggestions.
- Make sure not to provide suggestions repeating modifications already implemented in the new PR code (the '+' lines).
- Don't output line numbers in the 'improved code' snippets.
- 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.
{%- if extra_instructions %}
Extra instructions from the user:
{{ extra_instructions }}
{% endif %}
{%- endif %}
You must use the following JSON schema to format your answer:
```json
@ -30,39 +60,26 @@ You must use the following JSON schema to format your answer:
},
"suggestion content": {
"type": "string",
"description": "a concrete suggestion for meaningfully improving the new PR code."
"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 authentic relevant code lines from a 'new hunk' section. It must be continuous, correctly formatted and indented, and without line numbers."
"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 in the 'new hunk' sections, 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."
"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."
"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."
}
}
}
}
```
Example input:
'
## src/file1.py
---new_hunk---
```
[new hunk code, annotated with line numbers]
```
---old_hunk---
```
[old hunk code]
```
...
'
Don't output line numbers in the 'improved code' snippets.
Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
"""

4
pr_agent/settings/pr_reviewer_prompts.toml
View File

@ -1,9 +1,9 @@
[pr_review_prompt]
system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
Your task is to provide constructive and concise feedback for the PR, and also provide meaningfull code suggestions to improve the new PR code (the '+' lines).
Your task is to provide constructive and concise feedback for the PR, and also provide meaningful code suggestions to improve the new PR code (the '+' lines).
{%- if num_code_suggestions > 0 %}
- Provide up to {{ num_code_suggestions }} code suggestions.
- Try to focus on the most important suggestions, like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningfull code improvements, like performance, vulnerability, modularity, and best practices.
- Try to focus on the most 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 focus on improving the new added code lines.
- Make sure not to provide suggestions repeating modifications already implemented in the new PR code (the '+' lines).
{%- endif %}

46
pr_agent/settings/pr_sort_code_suggestions_prompts.toml Normal file
View File

@ -0,0 +1,46 @@
[pr_sort_code_suggestions_prompt]
system="""
"""
user="""You are given a list of code suggestions to improve a PR:
{{ suggestion_str|trim }}
Your task is to sort the code suggestions by their order of importance, and return a list with sorting order.
The sorting order is a list of pairs, where each pair contains the index of the suggestion in the original list.
Rank the suggestions based on their importance to improving the PR, with critical issues first and minor issues last.
You must use the following YAML schema to format your answer:
```yaml
Sort Order:
type: array
maxItems: {{ suggestion_list|length }}
uniqueItems: true
items:
suggestion number:
type: integer
minimum: 1
maximum: {{ suggestion_list|length }}
importance order:
type: integer
minimum: 1
maximum: {{ suggestion_list|length }}
```
Example output:
```yaml
Sort Order:
- suggestion number: 1
importance order: 2
- suggestion number: 2
importance order: 3
- suggestion number: 3
importance order: 1
```
Make sure to output a valid YAML. Use multi-line block scalar ('|') if needed.
Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
Response (should be a valid YAML, and nothing else):
```yaml
"""

115
pr_agent/tools/pr_code_suggestions.py
View File

@ -2,11 +2,13 @@ import copy
import json
import logging
import textwrap
from typing import List
import yaml
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
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.config_loader import get_settings
@ -22,6 +24,13 @@ class PRCodeSuggestions:
self.git_provider.get_languages(), self.git_provider.get_files()
)
# extended mode
self.is_extended = any(["extended" in arg for arg in args])
if self.is_extended:
num_code_suggestions = get_settings().pr_code_suggestions.num_code_suggestions_per_chunk
else:
num_code_suggestions = get_settings().pr_code_suggestions.num_code_suggestions
self.ai_handler = AiHandler()
self.patches_diff = None
self.prediction = None
@ -32,7 +41,7 @@ class PRCodeSuggestions:
"description": self.git_provider.get_pr_description(),
"language": self.main_language,
"diff": "", # empty diff for initial calculation
"num_code_suggestions": get_settings().pr_code_suggestions.num_code_suggestions,
"num_code_suggestions": num_code_suggestions,
"extra_instructions": get_settings().pr_code_suggestions.extra_instructions,
"commit_messages_str": self.git_provider.get_commit_messages(),
}
@ -42,18 +51,26 @@ class PRCodeSuggestions:
get_settings().pr_code_suggestions_prompt.user)
async def run(self):
# assert type(self.git_provider) != BitbucketProvider, "Bitbucket is not supported for now"
logging.info('Generating code suggestions for PR...')
if get_settings().config.publish_output:
self.git_provider.publish_comment("Preparing review...", is_temporary=True)
await retry_with_fallback_models(self._prepare_prediction)
logging.info('Preparing PR review...')
data = self._prepare_pr_code_suggestions()
if not self.is_extended:
await retry_with_fallback_models(self._prepare_prediction)
data = self._prepare_pr_code_suggestions()
else:
data = await retry_with_fallback_models(self._prepare_prediction_extended)
if (not self.is_extended and get_settings().pr_code_suggestions.rank_suggestions) or \
(self.is_extended and get_settings().pr_code_suggestions.rank_extended_suggestions):
logging.info('Ranking Suggestions...')
data['Code suggestions'] = await self.rank_suggestions(data['Code suggestions'])
if get_settings().config.publish_output:
logging.info('Pushing PR review...')
self.git_provider.remove_initial_comment()
logging.info('Pushing inline code comments...')
logging.info('Pushing inline code suggestions...')
self.push_inline_code_suggestions(data)
async def _prepare_prediction(self, model: str):
@ -121,7 +138,11 @@ class PRCodeSuggestions:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Could not parse suggestion: {d}")
self.git_provider.publish_code_suggestions(code_suggestions)
is_successful = self.git_provider.publish_code_suggestions(code_suggestions)
if not is_successful:
logging.info("Failed to publish code suggestions, trying to publish each suggestion separately")
for code_suggestion in code_suggestions:
self.git_provider.publish_code_suggestions([code_suggestion])
def dedent_code(self, relevant_file, relevant_lines_start, new_code_snippet):
try: # dedent code snippet
@ -145,3 +166,81 @@ class PRCodeSuggestions:
return new_code_snippet
async def _prepare_prediction_extended(self, model: str) -> dict:
logging.info('Getting PR diff...')
patches_diff_list = get_pr_multi_diffs(self.git_provider, self.token_handler, model,
max_calls=get_settings().pr_code_suggestions.max_number_of_calls)
logging.info('Getting multi AI predictions...')
prediction_list = []
for i, patches_diff in enumerate(patches_diff_list):
logging.info(f"Processing chunk {i + 1} of {len(patches_diff_list)}")
self.patches_diff = patches_diff
prediction = await self._get_prediction(model)
prediction_list.append(prediction)
self.prediction_list = prediction_list
data = {}
for prediction in prediction_list:
self.prediction = prediction
data_per_chunk = self._prepare_pr_code_suggestions()
if "Code suggestions" in data:
data["Code suggestions"].extend(data_per_chunk["Code suggestions"])
else:
data.update(data_per_chunk)
self.data = data
return data
async def rank_suggestions(self, data: List) -> List:
"""
Call a model to rank (sort) code suggestions based on their importance order.
Args:
data (List): A list of code suggestions to be ranked.
Returns:
List: The ranked list of code suggestions.
"""
suggestion_list = []
# remove invalid suggestions
for i, suggestion in enumerate(data):
if suggestion['existing code'] != suggestion['improved code']:
suggestion_list.append(suggestion)
data_sorted = [[]] * len(suggestion_list)
try:
suggestion_str = ""
for i, suggestion in enumerate(suggestion_list):
suggestion_str += f"suggestion {i + 1}: " + str(suggestion) + '\n\n'
variables = {'suggestion_list': suggestion_list, 'suggestion_str': suggestion_str}
model = get_settings().config.model
environment = Environment(undefined=StrictUndefined)
system_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_prompt.system).render(
variables)
user_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_prompt.user).render(variables)
if get_settings().config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
response, finish_reason = await self.ai_handler.chat_completion(model=model, system=system_prompt,
user=user_prompt)
sort_order = yaml.safe_load(response)
for s in sort_order['Sort Order']:
suggestion_number = s['suggestion number']
importance_order = s['importance order']
data_sorted[importance_order - 1] = suggestion_list[suggestion_number - 1]
if get_settings().pr_code_suggestions.final_clip_factor != 1:
new_len = int(0.5 + len(data_sorted) * get_settings().pr_code_suggestions.final_clip_factor)
data_sorted = data_sorted[:new_len]
except Exception as e:
if get_settings().config.verbosity_level >= 1:
logging.info(f"Could not sort suggestions, error: {e}")
data_sorted = suggestion_list
return data_sorted

21
pr_agent/tools/pr_description.py
View File

@ -42,6 +42,8 @@ class PRDescription:
"extra_instructions": get_settings().pr_description.extra_instructions,
"commit_messages_str": self.git_provider.get_commit_messages()
}
self.user_description = self.git_provider.get_user_description()
# Initialize the token handler
self.token_handler = TokenHandler(
@ -145,6 +147,9 @@ class PRDescription:
# Load the AI prediction data into a dictionary
data = load_yaml(self.prediction.strip())
if get_settings().pr_description.add_original_user_description and self.user_description:
data["User Description"] = self.user_description
# Initialization
pr_types = []
@ -161,13 +166,19 @@ class PRDescription:
elif type(data['PR Type']) == str:
pr_types = data['PR Type'].split(',')
# Assign the value of the 'PR Title' key to 'title' variable and remove it from the dictionary
title = data.pop('PR Title')
# Remove the 'PR Title' key from the dictionary
ai_title = data.pop('PR Title')
if get_settings().pr_description.keep_original_user_title:
# Assign the original PR title to the 'title' variable
title = self.vars["title"]
else:
# Assign the value of the 'PR Title' key to 'title' variable
title = ai_title
# Iterate over the remaining dictionary items and append the key and value to 'pr_body' in a markdown format,
# except for the items containing the word 'walkthrough'
pr_body = ""
for key, value in data.items():
for idx, (key, value) in enumerate(data.items()):
pr_body += f"## {key}:\n"
if 'walkthrough' in key.lower():
# for filename, description in value.items():
@ -179,7 +190,9 @@ class PRDescription:
# if the value is a list, join its items by comma
if type(value) == list:
value = ', '.join(v for v in value)
pr_body += f"{value}\n\n___\n"
pr_body += f"{value}\n"
if idx < len(data) - 1:
pr_body += "\n___\n"
if get_settings().config.verbosity_level >= 2:
logging.info(f"title:\n{title}\n{pr_body}")

3
pyproject.toml
View File

@ -43,7 +43,8 @@ dependencies = [
"GitPython~=3.1.32",
"starlette-context==0.3.6",
"litellm~=0.1.351",
"PyYAML==6.0"
"PyYAML==6.0",
"boto3~=1.28.25"
]
[project.urls]

2
requirements.txt
View File

@ -11,7 +11,7 @@ pytest~=7.4.0
aiohttp~=3.8.4
atlassian-python-api==3.39.0
GitPython~=3.1.32
litellm~=0.1.351
PyYAML==6.0
starlette-context==0.3.6
litellm~=0.1.445
boto3~=1.28.25

136
tests/unittest/test_codecommit_client.py Normal file
View File

@ -0,0 +1,136 @@
from unittest.mock import MagicMock
from pr_agent.git_providers.codecommit_client import CodeCommitClient
class TestCodeCommitProvider:
def test_get_differences(self):
# Create a mock CodeCommitClient instance and codecommit_client member
api = CodeCommitClient()
api.boto_client = MagicMock()
# Mock the response from the AWS client for get_differences method
api.boto_client.get_paginator.return_value.paginate.return_value = [
{
"differences": [
{
"beforeBlob": {
"path": "file1.py",
"blobId": "291b15c3ab4219e43a5f4f9091e5a97ee9d7400b",
},
"afterBlob": {
"path": "file1.py",
"blobId": "46ad86582da03cc34c804c24b17976571bca1eba",
},
"changeType": "M",
},
{
"beforeBlob": {"path": "", "blobId": ""},
"afterBlob": {
"path": "file2.py",
"blobId": "2404c7874fcbd684d6779c1420072f088647fd79",
},
"changeType": "A",
},
{
"beforeBlob": {
"path": "file3.py",
"blobId": "9af7989045ce40e9478ebb8089dfbadac19a9cde",
},
"afterBlob": {"path": "", "blobId": ""},
"changeType": "D",
},
{
"beforeBlob": {
"path": "file5.py",
"blobId": "738e36eec120ef9d6393a149252698f49156d5b4",
},
"afterBlob": {
"path": "file6.py",
"blobId": "faecdb85f7ba199df927a783b261378a1baeca85",
},
"changeType": "R",
},
]
}
]
diffs = api.get_differences("my_test_repo", "commit1", "commit2")
assert len(diffs) == 4
assert diffs[0].before_blob_path == "file1.py"
assert diffs[0].before_blob_id == "291b15c3ab4219e43a5f4f9091e5a97ee9d7400b"
assert diffs[0].after_blob_path == "file1.py"
assert diffs[0].after_blob_id == "46ad86582da03cc34c804c24b17976571bca1eba"
assert diffs[0].change_type == "M"
assert diffs[1].before_blob_path == ""
assert diffs[1].before_blob_id == ""
assert diffs[1].after_blob_path == "file2.py"
assert diffs[1].after_blob_id == "2404c7874fcbd684d6779c1420072f088647fd79"
assert diffs[1].change_type == "A"
assert diffs[2].before_blob_path == "file3.py"
assert diffs[2].before_blob_id == "9af7989045ce40e9478ebb8089dfbadac19a9cde"
assert diffs[2].after_blob_path == ""
assert diffs[2].after_blob_id == ""
assert diffs[2].change_type == "D"
assert diffs[3].before_blob_path == "file5.py"
assert diffs[3].before_blob_id == "738e36eec120ef9d6393a149252698f49156d5b4"
assert diffs[3].after_blob_path == "file6.py"
assert diffs[3].after_blob_id == "faecdb85f7ba199df927a783b261378a1baeca85"
assert diffs[3].change_type == "R"
def test_get_file(self):
# Create a mock CodeCommitClient instance and codecommit_client member
api = CodeCommitClient()
api.boto_client = MagicMock()
# Mock the response from the AWS client for get_pull_request method
# def get_file(self, repo_name: str, file_path: str, sha_hash: str):
api.boto_client.get_file.return_value = {
"commitId": "6335d6d4496e8d50af559560997604bb03abc122",
"blobId": "c172209495d7968a8fdad76469564fb708460bc1",
"filePath": "requirements.txt",
"fileSize": 65,
"fileContent": b"boto3==1.28.25\ndynaconf==3.1.12\nfastapi==0.99.0\nPyGithub==1.59.*\n",
}
repo_name = "my_test_repo"
file_path = "requirements.txt"
sha_hash = "84114a356ece1e5b7637213c8e486fea7c254656"
content = api.get_file(repo_name, file_path, sha_hash)
assert len(content) == 65
assert content == b"boto3==1.28.25\ndynaconf==3.1.12\nfastapi==0.99.0\nPyGithub==1.59.*\n"
assert content.decode("utf-8") == "boto3==1.28.25\ndynaconf==3.1.12\nfastapi==0.99.0\nPyGithub==1.59.*\n"
def test_get_pr(self):
# Create a mock CodeCommitClient instance and codecommit_client member
api = CodeCommitClient()
api.boto_client = MagicMock()
# Mock the response from the AWS client for get_pull_request method
api.boto_client.get_pull_request.return_value = {
"pullRequest": {
"pullRequestId": "3",
"title": "My PR",
"description": "My PR description",
"pullRequestTargets": [
{
"sourceCommit": "commit1",
"sourceReference": "branch1",
"destinationCommit": "commit2",
"destinationReference": "branch2",
"repositoryName": "my_test_repo",
}
],
}
}
pr = api.get_pr(321)
assert pr.title == "My PR"
assert pr.description == "My PR description"
assert len(pr.targets) == 1
assert pr.targets[0].source_commit == "commit1"
assert pr.targets[0].source_branch == "branch1"
assert pr.targets[0].destination_commit == "commit2"
assert pr.targets[0].destination_branch == "branch2"

119
tests/unittest/test_codecommit_provider.py Normal file
View File

@ -0,0 +1,119 @@
import pytest
from pr_agent.git_providers.codecommit_provider import CodeCommitFile
from pr_agent.git_providers.codecommit_provider import CodeCommitProvider
from pr_agent.git_providers.git_provider import EDIT_TYPE
class TestCodeCommitFile:
# Test that a CodeCommitFile object is created successfully with valid parameters.
# Generated by CodiumAI
def test_valid_parameters(self):
a_path = "path/to/file_a"
a_blob_id = "12345"
b_path = "path/to/file_b"
b_blob_id = "67890"
edit_type = EDIT_TYPE.ADDED
file = CodeCommitFile(a_path, a_blob_id, b_path, b_blob_id, edit_type)
assert file.a_path == a_path
assert file.a_blob_id == a_blob_id
assert file.b_path == b_path
assert file.b_blob_id == b_blob_id
assert file.edit_type == edit_type
assert file.filename == b_path
class TestCodeCommitProvider:
def test_parse_pr_url(self):
url = "https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/my_test_repo/pull-requests/321"
repo_name, pr_number = CodeCommitProvider._parse_pr_url(url)
assert repo_name == "my_test_repo"
assert pr_number == 321
# Test that an error is raised when an invalid CodeCommit URL is provided to the set_pr() method of the CodeCommitProvider class.
# Generated by CodiumAI
def test_invalid_codecommit_url(self):
provider = CodeCommitProvider()
with pytest.raises(ValueError):
provider.set_pr("https://example.com/codecommit/repositories/my_test_repo/pull-requests/4321")
def test_get_file_extensions(self):
filenames = [
"app.py",
"cli.py",
"composer.json",
"composer.lock",
"hello.py",
"image1.jpg",
"image2.JPG",
"index.js",
"provider.py",
"README",
"test.py",
]
expected_extensions = [
".py",
".py",
".json",
".lock",
".py",
".jpg",
".jpg",
".js",
".py",
"",
".py",
]
extensions = CodeCommitProvider._get_file_extensions(filenames)
assert extensions == expected_extensions
def test_get_language_percentages(self):
extensions = [
".py",
".py",
".json",
".lock",
".py",
".jpg",
".jpg",
".js",
".py",
"",
".py",
]
percentages = CodeCommitProvider._get_language_percentages(extensions)
assert percentages[".py"] == 45
assert percentages[".json"] == 9
assert percentages[".lock"] == 9
assert percentages[".jpg"] == 18
assert percentages[".js"] == 9
assert percentages[""] == 9
# The _get_file_extensions function needs the "." prefix on the extension,
# but the _get_language_percentages function will work with or without the "." prefix
extensions = [
"txt",
"py",
"py",
]
percentages = CodeCommitProvider._get_language_percentages(extensions)
assert percentages["py"] == 67
assert percentages["txt"] == 33
# test an empty list
percentages = CodeCommitProvider._get_language_percentages([])
assert percentages == {}
def test_get_edit_type(self):
assert CodeCommitProvider._get_edit_type("A") == EDIT_TYPE.ADDED
assert CodeCommitProvider._get_edit_type("D") == EDIT_TYPE.DELETED
assert CodeCommitProvider._get_edit_type("M") == EDIT_TYPE.MODIFIED
assert CodeCommitProvider._get_edit_type("R") == EDIT_TYPE.RENAMED
assert CodeCommitProvider._get_edit_type("a") == EDIT_TYPE.ADDED
assert CodeCommitProvider._get_edit_type("d") == EDIT_TYPE.DELETED
assert CodeCommitProvider._get_edit_type("m") == EDIT_TYPE.MODIFIED
assert CodeCommitProvider._get_edit_type("r") == EDIT_TYPE.RENAMED
assert CodeCommitProvider._get_edit_type("X") is None