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 feature_azure_devops

Browse Source
This commit is contained in:
Péter Szécsi
2023-08-24 16:41:33 +00:00
committed by GitHub
parent ceaff2a269 fd39c64bed
commit b94ed61219
36 changed files with 1723 additions and 226 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:

115
INSTALL.md
View File

@ -18,6 +18,18 @@ docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> c
```
docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> ask "<your question>"
```
Note: If you want to ensure you're running a specific version of the Docker image, consider using the image's digest.
The digest is a unique identifier for a specific version of an image. You can pull and run an image using its digest by referencing it like so: repository@sha256:digest. Always ensure you're using the correct and trusted digest for your operations.
1. To request a review for a PR using a specific digest, run the following command:
```bash
docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent@sha256:71b5ee15df59c745d352d84752d01561ba64b6d51327f97d46152f0c58a5f678 --pr_url <pr_url> review
```
2. To ask a question about a PR using the same digest, run the following command:
```bash
docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent@sha256:71b5ee15df59c745d352d84752d01561ba64b6d51327f97d46152f0c58a5f678 --pr_url <pr_url> ask "<your question>"
```
Possible questions you can ask include:
@ -42,6 +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
@ -51,7 +67,28 @@ jobs:
OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
```
** if you want to pin your action to a specific commit for stability reasons
```yaml
on:
pull_request:
issue_comment:
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
id: pragent
uses: Codium-ai/pr-agent@<commit_sha>
env:
OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
```
2. Add the following secret to your repository under `Settings > Secrets`:
```
@ -92,6 +129,7 @@ pip install -r requirements.txt
```
cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
chmod 600 pr_agent/settings/.secrets.toml
# Edit .secrets.toml file
```
@ -105,6 +143,14 @@ 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
@ -128,6 +174,7 @@ Allowing you to automate the review process on your private or public repositori
- Pull requests: Read & write
- Issue comment: Read & write
- Metadata: Read-only
- Contents: Read-only
- Set the following events:
- Issue comment
- Pull request
@ -216,3 +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: | |
| | 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.

BIN
pics/debugger.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 534 KiB

3
pr_agent/agent/pr_agent.py
View File

@ -15,6 +15,7 @@ from pr_agent.tools.pr_update_changelog import PRUpdateChangelog
from pr_agent.tools.pr_config import PRConfig
command2class = {
"auto_review": PRReviewer,
"answer": PRReviewer,
"review": PRReviewer,
"review_pr": PRReviewer,
@ -70,6 +71,8 @@ class PRAgent:
if notify:
notify()
await PRReviewer(pr_url, is_answer=True, args=args).run()
elif action == "auto_review":
await PRReviewer(pr_url, is_auto=True, args=args).run()
elif action in command2class:
if notify:
notify()

26
pr_agent/algo/ai_handler.py
View File

@ -26,10 +26,10 @@ class AiHandler:
try:
openai.api_key = get_settings().openai.key
litellm.openai_key = get_settings().openai.key
litellm.debugger = get_settings().config.litellm_debugger
self.azure = False
if get_settings().get("OPENAI.ORG", None):
litellm.organization = get_settings().openai.org
self.deployment_id = get_settings().get("OPENAI.DEPLOYMENT_ID", None)
if get_settings().get("OPENAI.API_TYPE", None):
if get_settings().openai.api_type == "azure":
self.azure = True
@ -44,12 +44,23 @@ class AiHandler:
litellm.cohere_key = get_settings().cohere.key
if get_settings().get("REPLICATE.KEY", None):
litellm.replicate_key = get_settings().replicate.key
if get_settings().get("REPLICATE.KEY", None):
litellm.replicate_key = get_settings().replicate.key
if get_settings().get("HUGGINGFACE.KEY", None):
litellm.huggingface_key = get_settings().huggingface.key
except AttributeError as e:
raise ValueError("OpenAI key is required") from e
@property
def deployment_id(self):
"""
Returns the deployment ID for the OpenAI API.
"""
return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
@retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
async def chat_completion(self, model: str, 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.
@ -70,15 +81,22 @@ class AiHandler:
TryAgain: If there is an attribute error during OpenAI inference.
"""
try:
deployment_id = self.deployment_id
if get_settings().config.verbosity_level >= 2:
logging.debug(
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=self.deployment_id,
deployment_id=deployment_id,
messages=[
{"role": "system", "content": system},
{"role": "user", "content": user}
],
temperature=temperature,
azure=self.azure,
force_timeout=get_settings().config.ai_timeout
)
except (APIError, Timeout, TryAgain) as e:

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()

147
pr_agent/algo/pr_processing.py
View File

@ -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,
@ -208,18 +206,45 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
async def retry_with_fallback_models(f: Callable):
all_models = _get_all_models()
all_deployments = _get_all_deployments(all_models)
# try each (model, deployment_id) pair until one is successful, otherwise raise exception
for i, (model, deployment_id) in enumerate(zip(all_models, all_deployments)):
try:
get_settings().set("openai.deployment_id", deployment_id)
return await f(model)
except Exception as e:
logging.warning(
f"Failed to generate prediction with {model}"
f"{(' from deployment ' + deployment_id) if deployment_id else ''}: "
f"{traceback.format_exc()}"
)
if i == len(all_models) - 1: # If it's the last iteration
raise # Re-raise the last exception
def _get_all_models() -> List[str]:
model = get_settings().config.model
fallback_models = get_settings().config.fallback_models
if not isinstance(fallback_models, list):
fallback_models = [fallback_models]
fallback_models = [m.strip() for m in fallback_models.split(",")]
all_models = [model] + fallback_models
for i, model in enumerate(all_models):
try:
return await f(model)
except Exception as e:
logging.warning(f"Failed to generate prediction with {model}: {traceback.format_exc()}")
if i == len(all_models) - 1: # If it's the last iteration
raise # Re-raise the last exception
return all_models
def _get_all_deployments(all_models: List[str]) -> List[str]:
deployment_id = get_settings().get("openai.deployment_id", None)
fallback_deployments = get_settings().get("openai.fallback_deployments", [])
if not isinstance(fallback_deployments, list) and fallback_deployments:
fallback_deployments = [d.strip() for d in fallback_deployments.split(",")]
if fallback_deployments:
all_deployments = [deployment_id] + fallback_deployments
if len(all_deployments) < len(all_models):
raise ValueError(f"The number of deployments ({len(all_deployments)}) "
f"is less than the number of models ({len(all_models)})")
else:
all_deployments = [deployment_id] * len(all_models)
return all_deployments
def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
@ -297,7 +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))
@ -310,4 +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

35
pr_agent/algo/utils.py
View File

@ -32,33 +32,37 @@ def convert_to_markdown(output_data: dict) -> str:
emojis = {
"Main theme": "🎯",
"PR summary": "📝",
"Type of PR": "📌",
"Score": "🏅",
"Relevant tests added": "🧪",
"Unrelated changes": "⚠️",
"Focused PR": "✨",
"Security concerns": "🔒",
"General PR suggestions": "💡",
"General suggestions": "💡",
"Insights from user's answers": "📝",
"Code feedback": "🤖",
}
for key, value in output_data.items():
if not value:
if value is None or value == '' or value == {}:
continue
if isinstance(value, dict):
markdown_text += f"## {key}\n\n"
markdown_text += convert_to_markdown(value)
elif isinstance(value, list):
if key.lower() == 'code feedback':
markdown_text += "\n" # just looks nicer with additional line breaks
emoji = emojis.get(key, "")
markdown_text += f"- {emoji} **{key}:**\n\n"
if key.lower() == 'code feedback':
markdown_text += f"\n\n- **<details><summary> { emoji } Code feedback:**</summary>\n\n"
else:
markdown_text += f"- {emoji} **{key}:**\n\n"
for item in value:
if isinstance(item, dict) and key.lower() == 'code feedback':
markdown_text += parse_code_suggestion(item)
elif item:
markdown_text += f" - {item}\n"
if key.lower() == 'code feedback':
markdown_text += "</details>\n\n"
elif value != 'n/a':
emoji = emojis.get(key, "")
markdown_text += f"- {emoji} **{key}:** {value}\n"
@ -245,14 +249,13 @@ def update_settings_from_args(args: List[str]) -> List[str]:
arg = arg.strip()
if arg.startswith('--'):
arg = arg.strip('-').strip()
vals = arg.split('=')
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 = vals
key = key.strip().upper()
value = value.strip()
key, value = _fix_key_value(*vals)
get_settings().set(key, value)
logging.info(f'Updated setting {key} to: "{value}"')
else:
@ -260,8 +263,18 @@ def update_settings_from_args(args: List[str]) -> List[str]:
return other_args
def _fix_key_value(key: str, value: str):
key = key.strip().upper()
value = value.strip()
try:
value = yaml.safe_load(value)
except Exception as e:
logging.error(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
return key, value
def load_yaml(review_text: str) -> dict:
review_text = review_text.lstrip('```yaml').rstrip('`')
review_text = review_text.removeprefix('```yaml').rstrip('`')
try:
data = yaml.load(review_text, Loader=yaml.SafeLoader)
except Exception as e:

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
@ -10,6 +11,7 @@ _GIT_PROVIDERS = {
'gitlab': GitLabProvider,
'bitbucket': BitbucketProvider,
'azure': AzureDevopsProvider,
'codecommit': CodeCommitProvider,
'local' : LocalGitProvider
}

99
pr_agent/git_providers/bitbucket_provider.py
View File

@ -1,3 +1,4 @@
import json
import logging
from typing import Optional, Tuple
from urllib.parse import urlparse
@ -5,17 +6,17 @@ 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)}'
s.headers['Content-Type'] = 'application/json'
self.headers = s.headers
self.bitbucket_client = Cloud(session=s)
self.workspace_slug = None
self.repo_slug = None
self.repo = None
@ -25,6 +26,64 @@ class BitbucketProvider:
self.incremental = incremental
if pr_url:
self.set_pr(pr_url)
self.bitbucket_comment_api_url = self.pr._BitbucketBase__data['links']['comments']['href']
def get_repo_settings(self):
try:
contents = self.repo_obj.get_contents(".pr_agent.toml", ref=self.pr.head.sha).decoded_content
return contents
except Exception:
return ""
def publish_code_suggestions(self, code_suggestions: list) -> bool:
"""
Publishes code suggestions as comments on the PR.
"""
post_parameters_list = []
for suggestion in code_suggestions:
body = suggestion['body']
relevant_file = suggestion['relevant_file']
relevant_lines_start = suggestion['relevant_lines_start']
relevant_lines_end = suggestion['relevant_lines_end']
if not relevant_lines_start or relevant_lines_start == -1:
if get_settings().config.verbosity_level >= 2:
logging.exception(
f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
continue
if relevant_lines_end < relevant_lines_start:
if get_settings().config.verbosity_level >= 2:
logging.exception(f"Failed to publish code suggestion, "
f"relevant_lines_end is {relevant_lines_end} and "
f"relevant_lines_start is {relevant_lines_start}")
continue
if relevant_lines_end > relevant_lines_start:
post_parameters = {
"body": body,
"path": relevant_file,
"line": relevant_lines_end,
"start_line": relevant_lines_start,
"start_side": "RIGHT",
}
else: # API is different for single line comments
post_parameters = {
"body": body,
"path": relevant_file,
"line": relevant_lines_start,
"side": "RIGHT",
}
post_parameters_list.append(post_parameters)
try:
self.publish_inline_comments(post_parameters_list)
return True
except Exception as e:
if get_settings().config.verbosity_level >= 2:
logging.error(f"Failed to publish code suggestion, error: {e}")
return False
def is_supported(self, capability: str) -> bool:
if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels']:
@ -62,14 +121,29 @@ class BitbucketProvider:
except Exception as e:
logging.exception(f"Failed to remove temp comments, error: {e}")
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
pass
def publish_inline_comment(self, comment: str, from_line: int, to_line: int, file: str):
payload = json.dumps( {
"content": {
"raw": comment,
},
"inline": {
"to": from_line,
"path": file
},
})
response = requests.request(
"POST",
self.bitbucket_comment_api_url,
data=payload,
headers=self.headers
)
return response
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
raise NotImplementedError("Bitbucket provider does not support creating inline comments yet")
def publish_inline_comments(self, comments: list[dict]):
raise NotImplementedError("Bitbucket provider does not support publishing inline comments yet")
for comment in comments:
self.publish_inline_comment(comment['body'], comment['start_line'], comment['line'], comment['path'])
def get_title(self):
return self.pr.title
@ -81,10 +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):
@ -104,7 +175,7 @@ class BitbucketProvider:
parsed_url = urlparse(pr_url)
if 'bitbucket.org' not in parsed_url.netloc:
raise ValueError("The provided URL is not a valid GitHub URL")
raise ValueError("The provided URL is not a valid Bitbucket URL")
path_parts = parsed_url.path.strip('/').split('/')

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

29
pr_agent/git_providers/git_provider.py
View File

@ -55,7 +55,7 @@ class GitProvider(ABC):
pass
@abstractmethod
def publish_code_suggestions(self, code_suggestions: list):
def publish_code_suggestions(self, code_suggestions: list) -> bool:
pass
@abstractmethod
@ -83,13 +83,38 @@ 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
@abstractmethod
def get_repo_settings(self):
pass
@abstractmethod
def add_eyes_reaction(self, issue_comment_id: int) -> Optional[int]:
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):

41
pr_agent/git_providers/gitlab_provider.py
View File

@ -14,6 +14,9 @@ from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
logger = logging.getLogger()
class DiffNotFoundError(Exception):
"""Raised when the diff for a merge request cannot be found."""
pass
class GitLabProvider(GitProvider):
@ -56,7 +59,7 @@ class GitLabProvider(GitProvider):
self.last_diff = self.mr.diffs.list(get_all=True)[-1]
except IndexError as e:
logger.error(f"Could not get diff for merge request {self.id_mr}")
raise ValueError(f"Could not get diff for merge request {self.id_mr}") from e
raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}") from e
def _get_pr_file_content(self, file_path: str, branch: str) -> str:
@ -150,16 +153,20 @@ class GitLabProvider(GitProvider):
def create_inline_comments(self, comments: list[dict]):
raise NotImplementedError("Gitlab provider does not support publishing inline comments yet")
def send_inline_comment(self, body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
target_file, target_line_no):
def send_inline_comment(self,body: str,edit_type: str,found: bool,relevant_file: str,relevant_line_in_file: int,
source_line_no: int, target_file: str,target_line_no: int) -> None:
if not found:
logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
else:
d = self.last_diff
# in order to have exact sha's we have to find correct diff for this change
diff = self.get_relevant_diff(relevant_file, relevant_line_in_file)
if diff is None:
logger.error(f"Could not get diff for merge request {self.id_mr}")
raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}")
pos_obj = {'position_type': 'text',
'new_path': target_file.filename,
'old_path': target_file.old_filename if target_file.old_filename else target_file.filename,
'base_sha': d.base_commit_sha, 'start_sha': d.start_commit_sha, 'head_sha': d.head_commit_sha}
'base_sha': diff.base_commit_sha, 'start_sha': diff.start_commit_sha, 'head_sha': diff.head_commit_sha}
if edit_type == 'deletion':
pos_obj['old_line'] = source_line_no - 1
elif edit_type == 'addition':
@ -171,7 +178,24 @@ class GitLabProvider(GitProvider):
self.mr.discussions.create({'body': body,
'position': pos_obj})
def publish_code_suggestions(self, code_suggestions: list):
def get_relevant_diff(self, relevant_file: str, relevant_line_in_file: int) -> Optional[dict]:
changes = self.mr.changes() # Retrieve the changes for the merge request once
if not changes:
logging.error('No changes found for the merge request.')
return None
all_diffs = self.mr.diffs.list(get_all=True)
if not all_diffs:
logging.error('No diffs found for the merge request.')
return None
for diff in all_diffs:
for change in changes['changes']:
if change['new_path'] == relevant_file and relevant_line_in_file in change['diff']:
return diff
logging.debug(
f'No relevant diff found for {relevant_file} {relevant_line_in_file}. Falling back to last diff.')
return self.last_diff # fallback to last_diff if no relevant diff is found
def publish_code_suggestions(self, code_suggestions: list) -> bool:
for suggestion in code_suggestions:
try:
body = suggestion['body']
@ -275,10 +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])

82
pr_agent/servers/github_app.py
View File

@ -1,6 +1,8 @@
import copy
import logging
import sys
import os
import time
from typing import Any, Dict
import uvicorn
@ -14,7 +16,7 @@ from pr_agent.config_loader import get_settings, global_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.servers.utils import verify_signature
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
router = APIRouter()
@ -34,7 +36,8 @@ async def handle_github_webhooks(request: Request, response: Response):
context["installation_id"] = installation_id
context["settings"] = copy.deepcopy(global_settings)
return await handle_request(body)
response = await handle_request(body, event=request.headers.get("X-GitHub-Event", None))
return response or {}
@router.post("/api/v1/marketplace_webhooks")
@ -48,70 +51,119 @@ async def get_body(request):
except Exception as e:
logging.error("Error parsing request body", e)
raise HTTPException(status_code=400, detail="Error parsing request body") from e
body_bytes = await request.body()
signature_header = request.headers.get('x-hub-signature-256', None)
webhook_secret = getattr(get_settings().github, 'webhook_secret', None)
if webhook_secret:
body_bytes = await request.body()
signature_header = request.headers.get('x-hub-signature-256', None)
verify_signature(body_bytes, webhook_secret, signature_header)
return body
_duplicate_requests_cache = {}
async def handle_request(body: Dict[str, Any]):
async def handle_request(body: Dict[str, Any], event: str):
"""
Handle incoming GitHub webhook requests.
Args:
body: The request body.
event: The GitHub event type.
"""
action = body.get("action")
if not action:
return {}
agent = PRAgent()
bot_user = get_settings().github_app.bot_user
logging.info(f"action: '{action}'")
logging.info(f"event: '{event}'")
if get_settings().github_app.duplicate_requests_cache and _is_duplicate_request(body):
return {}
# handle all sorts of comment events (e.g. issue_comment)
if action == 'created':
if "comment" not in body:
return {}
comment_body = body.get("comment", {}).get("body")
sender = body.get("sender", {}).get("login")
if sender and 'bot' in sender:
if sender and bot_user in sender:
logging.info(f"Ignoring comment from {bot_user} user")
return {}
if "issue" not in body or "pull_request" not in body["issue"]:
logging.info(f"Processing comment from {sender} user")
if "issue" in body and "pull_request" in body["issue"] and "url" in body["issue"]["pull_request"]:
api_url = body["issue"]["pull_request"]["url"]
elif "comment" in body and "pull_request_url" in body["comment"]:
api_url = body["comment"]["pull_request_url"]
else:
return {}
pull_request = body["issue"]["pull_request"]
api_url = pull_request.get("url")
logging.info(f"Handling comment because of event={event} and action={action}")
comment_id = body.get("comment", {}).get("id")
provider = get_git_provider()(pr_url=api_url)
await agent.handle_request(api_url, comment_body, notify=lambda: provider.add_eyes_reaction(comment_id))
elif action == "opened" or 'reopened' in action:
# handle pull_request event:
# automatically review opened/reopened/ready_for_review PRs as long as they're not in draft,
# as well as direct review requests from the bot
elif event == 'pull_request':
pull_request = body.get("pull_request")
if not pull_request:
return {}
api_url = pull_request.get("url")
if not api_url:
return {}
await agent.handle_request(api_url, "/review")
if pull_request.get("draft", True) or pull_request.get("state") != "open" or pull_request.get("user", {}).get("login", "") == bot_user:
return {}
if action in get_settings().github_app.handle_pr_actions:
if action == "review_requested":
if body.get("requested_reviewer", {}).get("login", "") != bot_user:
return {}
if pull_request.get("created_at") == pull_request.get("updated_at"):
# avoid double reviews when opening a PR for the first time
return {}
logging.info(f"Performing review because of event={event} and action={action}")
for command in get_settings().github_app.pr_commands:
logging.info(f"Performing command: {command}")
await agent.handle_request(api_url, command)
logging.info("event or action does not require handling")
return {}
def _is_duplicate_request(body: Dict[str, Any]) -> bool:
"""
In some deployments its possible to get duplicate requests if the handling is long,
This function checks if the request is duplicate and if so - ignores it.
"""
request_hash = hash(str(body))
logging.info(f"request_hash: {request_hash}")
request_time = time.monotonic()
ttl = get_settings().github_app.duplicate_requests_cache_ttl # in seconds
to_delete = [key for key, key_time in _duplicate_requests_cache.items() if request_time - key_time > ttl]
for key in to_delete:
del _duplicate_requests_cache[key]
is_duplicate = request_hash in _duplicate_requests_cache
_duplicate_requests_cache[request_hash] = request_time
if is_duplicate:
logging.info(f"Ignoring duplicate request {request_hash}")
return is_duplicate
@router.get("/")
async def root():
return {"status": "ok"}
def start():
# Override the deployment type to app
get_settings().set("GITHUB.DEPLOYMENT_TYPE", "app")
if get_settings().github_app.override_deployment_type:
# Override the deployment type to app
get_settings().set("GITHUB.DEPLOYMENT_TYPE", "app")
get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
middleware = [Middleware(RawContextMiddleware)]
app = FastAPI(middleware=middleware)
app.include_router(router)
uvicorn.run(app, host="0.0.0.0", port=3000)
uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("PORT", "3000")))
if __name__ == '__main__':

7
pr_agent/servers/help.py
View File

@ -1,9 +1,10 @@
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" \
"> **/ask \\<QUESTION\\>**: Pose a question about the PR.\n\n" \
">To edit any configuration parameter from 'configuration.toml', add --config_path=new_value\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" \
">For example: /review --pr_reviewer.extra_instructions=\"focus on the file: ...\" \n" \
">To list the possible configuration parameters, use the **/config** command.\n" \

1
pr_agent/settings/.secrets_template.toml
View File

@ -14,6 +14,7 @@ key = "" # Acquire through https://platform.openai.com
#api_version = '2023-05-15' # Check Azure documentation for the current API version
#api_base = "" # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
#deployment_id = "" # The deployment name you chose when you deployed the engine
#fallback_deployments = [] # For each fallback model specified in configuration.toml in the [config] section, specify the appropriate deployment_id
[anthropic]
key = "" # Optional, uncomment if you want to use Anthropic. Acquire through https://www.anthropic.com/

29
pr_agent/settings/configuration.toml
View File

@ -10,19 +10,23 @@ use_repo_settings_file=true
ai_timeout=180
max_description_tokens = 500
max_commits_tokens = 500
litellm_debugger=false
[pr_reviewer] # /review #
require_focused_review=true
require_focused_review=false
require_score_review=false
require_tests_review=true
require_security_review=true
num_code_suggestions=3
num_code_suggestions=4
inline_code_comments = false
ask_and_reflect=false
automatic_review=true
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 #
@ -30,6 +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
@ -42,6 +52,21 @@ extra_instructions = ""
deployment_type = "user"
ratelimit_retries = 5
[github_app]
# these toggles allows running the github app from custom deployments
bot_user = "github-actions[bot]"
override_deployment_type = true
# in some deployments it's possible to get duplicate requests if the handling is long,
# these settings are used to avoid handling duplicate requests.
duplicate_requests_cache = false
duplicate_requests_cache_ttl = 60 # in seconds
# settings for "pull_request" event
handle_pr_actions = ['opened', 'reopened', 'ready_for_review', 'review_requested']
pr_commands = [
"/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
"/auto_review",
]
[gitlab]
# URL to the gitlab service
url = "https://gitlab.com"

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.
"""

10
pr_agent/settings/pr_description_prompts.toml
View File

@ -3,7 +3,7 @@ system="""You are CodiumAI-PR-Reviewer, a language model designed to review git
Your task is to provide full description of the PR content.
- Make sure not to focus the new PR code (the '+' lines).
- Notice that the 'Previous title', 'Previous description' and 'Commit messages' sections may be partial, simplistic, non-informative or not up-to-date. Hence, compare them to the PR diff code, and use them only as a reference.
- If needed, each YAML output should be in block scalar format ('|-')
{%- if extra_instructions %}
Extra instructions from the user:
@ -33,7 +33,7 @@ PR Description:
PR Main Files Walkthrough:
type: array
maxItems: 10
description: >-
description: |-
a walkthrough of the PR changes. Review main files, and shortly describe the changes in each file (up to 10 most important files).
items:
filename:
@ -46,10 +46,12 @@ PR Main Files Walkthrough:
Example output:
```yaml
PR Title: ...
PR Title: |-
...
PR Type:
- Bug fix
PR Description: ...
PR Description: |-
...
PR Main Files Walkthrough:
- ...
- ...

79
pr_agent/settings/pr_reviewer_prompts.toml
View File

@ -1,11 +1,35 @@
[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).
system="""You are 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 meaningful code suggestions.
Example PR Diff input:
'
## src/file1.py
@@ -12,5 +12,5 @@ def func1():
code line that already existed in the file...
code line that already existed in the file....
-code line that was removed in the PR
+new code line added in the PR
code line that already existed in the file...
code line that already existed in the file...
@@ ... @@ def func2():
...
## src/file2.py
...
'
Thre review should focus on new code added in the PR (lines starting with '+'), and not on code that already existed in the file (lines starting with '-', or without prefix).
{%- 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.
- 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).
- 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.
- 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 PR code.
- Don't suggest to add docstring or type hints.
- Suggestions should focus on improving the new code added in the PR (lines starting with '+')
{%- endif %}
{%- if extra_instructions %}
@ -20,6 +44,9 @@ PR Analysis:
Main theme:
type: string
description: a short explanation of the PR
PR summary:
type: string
description: summary of the PR in 2-3 sentences.
Type of PR:
type: string
enum:
@ -32,7 +59,7 @@ PR Analysis:
{%- if require_score %}
Score:
type: int
description: >-
description: |-
Rate this PR on a scale of 0-100 (inclusive), where 0 means the worst
possible PR code, and 100 means PR code of the highest quality, without
any bugs or performance issues, that is ready to be merged immediately and
@ -46,13 +73,13 @@ PR Analysis:
{%- if question_str %}
Insights from user's answer:
type: string
description: >-
description: |-
shortly summarize the insights you gained from the user's answers to the questions
{%- endif %}
{%- if require_focused %}
Focused PR:
type: string
description: >-
description: |-
Is this a focused PR, in the sense that all the PR code diff changes are
united under a single focused theme ? If the theme is too broad, or the PR
code diff changes are too scattered, then the PR is not focused. Explain
@ -61,12 +88,11 @@ PR Analysis:
PR Feedback:
General suggestions:
type: string
description: >-
description: |-
General suggestions and feedback for the contributors and maintainers of
this PR. May include important suggestions for the overall structure,
primary purpose, best practices, critical bugs, and other aspects of the
PR. Don't address PR title and description, or lack of tests. Explain your
suggestions.
PR. Don't address PR title and description, or lack of tests. Explain your suggestions.
{%- if num_code_suggestions > 0 %}
Code feedback:
type: array
@ -78,7 +104,7 @@ PR Feedback:
description: the relevant file full path
suggestion:
type: string
description: >-
description: |-
a concrete suggestion for meaningfully improving the new PR code. Also
describe how, specifically, the suggestion can be applied to new PR
code. Add tags with importance measure that matches each suggestion
@ -86,10 +112,10 @@ PR Feedback:
adding docstrings, renaming PR title and description, or linter like.
relevant line:
type: string
description: >-
a single code line taken from the relevant file, to which the
suggestion applies. The line should be a '+' line. Make sure to output
the line exactly as it appears in the relevant file
description: |-
a single code line taken from the relevant file, to which the suggestion applies.
The code line should start with a '+'.
Make sure to output the line exactly as it appears in the relevant file
{%- endif %}
{%- if require_security %}
Security concerns:
@ -103,22 +129,29 @@ PR Feedback:
Example output:
```yaml
PR Analysis:
Main theme: xxx
Type of PR: Bug fix
Main theme: |-
xxx
PR summary: |-
xxx
Type of PR: |-
Bug fix
{%- if require_score %}
Score: 89
{%- endif %}
Relevant tests added: No
Relevant tests added: |-
No
{%- if require_focused %}
Focused PR: no, because ...
{%- endif %}
PR Feedback:
General PR suggestions: ...
General PR suggestions: |-
...
{%- if num_code_suggestions > 0 %}
Code feedback:
- relevant file: |-
directory/xxx.py
suggestion: xxx [important]
suggestion: |-
xxx [important]
relevant line: |-
xxx
...
@ -128,7 +161,7 @@ PR Feedback:
{%- endif %}
```
Make sure to output a valid YAML. Use multi-line block scalar ('|') if needed.
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.
"""
@ -160,7 +193,7 @@ The PR Git Diff:
```
{{diff}}
```
Note that lines in the diff body are prefixed with a symbol that represents the type of change: '-' for deletions, '+' for additions, and ' ' (a space) for unchanged lines.
Note that lines in the diff body are prefixed with a symbol that represents the type of change: '-' for deletions, '+' for additions. Focus on the '+' lines.
Response (should be a valid YAML, and nothing else):
```yaml

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
"""

119
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):
@ -93,6 +110,10 @@ class PRCodeSuggestions:
def push_inline_code_suggestions(self, data):
code_suggestions = []
if not data['Code suggestions']:
return self.git_provider.publish_comment('No suggestions found to improve this PR.')
for d in data['Code suggestions']:
try:
if get_settings().config.verbosity_level >= 2:
@ -117,7 +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
@ -141,3 +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}")

13
pr_agent/tools/pr_reviewer.py
View File

@ -23,7 +23,7 @@ class PRReviewer:
"""
The PRReviewer class is responsible for reviewing a pull request and generating feedback using an AI model.
"""
def __init__(self, pr_url: str, is_answer: bool = False, args: list = None):
def __init__(self, pr_url: str, is_answer: bool = False, is_auto: bool = False, args: list = None):
"""
Initialize the PRReviewer object with the necessary attributes and objects to review a pull request.
@ -40,6 +40,7 @@ class PRReviewer:
)
self.pr_url = pr_url
self.is_answer = is_answer
self.is_auto = is_auto
if self.is_answer and not self.git_provider.is_supported("get_issue_comments"):
raise Exception(f"Answer mode is not supported for {get_settings().config.git_provider} for now")
@ -93,8 +94,12 @@ class PRReviewer:
"""
Review the pull request and generate feedback.
"""
logging.info('Reviewing PR...')
if self.is_auto and not get_settings().pr_reviewer.automatic_review:
logging.info(f'Automatic review is disabled {self.pr_url}')
return None
logging.info(f'Reviewing PR: {self.pr_url} ...')
if get_settings().config.publish_output:
self.git_provider.publish_comment("Preparing review...", is_temporary=True)
@ -237,7 +242,7 @@ class PRReviewer:
return
review_text = self.prediction.strip()
review_text = review_text.lstrip('```yaml').rstrip('`')
review_text = review_text.removeprefix('```yaml').rstrip('`')
try:
data = yaml.load(review_text, Loader=SafeLoader)
except Exception as e:

5
pyproject.toml
View File

@ -42,8 +42,9 @@ dependencies = [
"atlassian-python-api==3.39.0",
"GitPython~=3.1.32",
"starlette-context==0.3.6",
"litellm~=0.1.351",
"PyYAML==6.0"
"litellm~=0.1.445",
"PyYAML==6.0",
"boto3~=1.28.25"
]
[project.urls]

4
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~=0.1.351
litellm~=0.1.445
boto3~=1.28.25

10
tests/unittest/test_bitbucket_provider.py Normal file
View File

@ -0,0 +1,10 @@
from pr_agent.git_providers.bitbucket_provider import BitbucketProvider
class TestBitbucketProvider:
def test_parse_pr_url(self):
url = "https://bitbucket.org/WORKSPACE_XYZ/MY_TEST_REPO/pull-requests/321"
workspace_slug, repo_slug, pr_number = BitbucketProvider._parse_pr_url(url)
assert workspace_slug == "WORKSPACE_XYZ"
assert repo_slug == "MY_TEST_REPO"
assert pr_number == 321

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

34
tests/unittest/test_convert_to_markdown.py
View File

@ -67,33 +67,11 @@ class TestConvertToMarkdown:
]
}
expected_output = """\
- 🎯 **Main theme:** Test
- 📌 **Type of PR:** Test type
- 🧪 **Relevant tests added:** no
- ✨ **Focused PR:** Yes
- 💡 **General PR suggestions:** general suggestion...
- 🤖 **Code feedback:**
- **Code example:**
- **Before:**
```
Code before
```
- **After:**
```
Code after
```
- **Code example:**
- **Before:**
```
Code before 2
```
- **After:**
```
Code after 2
```
- 🎯 **Main theme:** Test\n\
- 📌 **Type of PR:** Test type\n\
- 🧪 **Relevant tests added:** no\n\
- ✨ **Focused PR:** Yes\n\
- **General PR suggestions:** general suggestion...\n\n\n- **<details><summary> 🤖 Code feedback:**</summary>\n\n - **Code example:**\n - **Before:**\n ```\n Code before\n ```\n - **After:**\n ```\n Code after\n ```\n\n - **Code example:**\n - **Before:**\n ```\n Code before 2\n ```\n - **After:**\n ```\n Code after 2\n ```\n\n</details>\
"""
assert convert_to_markdown(input_data).strip() == expected_output.strip()
@ -113,5 +91,5 @@ class TestConvertToMarkdown:
'General PR suggestions': {},
'Code suggestions': {}
}
expected_output = ""
expected_output = ''
assert convert_to_markdown(input_data).strip() == expected_output.strip()