Compare commits

..

66 Commits

Author SHA1 Message Date
93311a9d9b Update GitHub app 2023-07-16 15:42:50 +03:00
704030230f Merge pull request #59 from Codium-ai/enhancement/github_action_apply
Update Github polling
2023-07-16 15:03:44 +03:00
60bce8f049 Update Github polling 2023-07-16 15:00:13 +03:00
e394cb7ddb Merge pull request #54 from Codium-ai/tr/readme_update
Update README.md with Detailed Tool Description and Images
2023-07-16 14:46:29 +03:00
a0e4fb01af Merge remote-tracking branch 'origin/main' into tr/readme_update 2023-07-16 14:42:42 +03:00
eb9190efa1 Merge pull request #56 from Codium-ai/hl/feature_comparison_readme
Add feature comparison overview to Readme file
2023-07-16 14:42:18 +03:00
8cc37d6f59 readme update
readme update
2023-07-16 14:37:59 +03:00
6cc9fe3d06 Merge pull request #57 from Codium-ai/enhancement/github_action_apply
Enhancement: Apply Github Action
2023-07-16 14:30:56 +03:00
0acf423450 Update comment 2023-07-16 14:30:34 +03:00
7958786b4c Github action to work with an image stored on Dockerhub for faster execution 2023-07-16 14:19:02 +03:00
719f3a9dd8 Update README.md 2023-07-16 14:18:48 +03:00
71efd84113 Merge pull request #52 from Codium-ai/enhancement/cli_update
cli.py - modify command line for a more coherent command invokation
2023-07-16 13:51:24 +03:00
25e46a99fd Merge pull request #55 from Codium-ai/enhancement/github_action_apply
Github action support for new style commands
2023-07-16 13:50:57 +03:00
2531849b73 Update usage instructions in PR comment 2023-07-16 13:45:20 +03:00
19f11f99ce Github action support for new style commands 2023-07-16 13:36:02 +03:00
87f978e816 Merge pull request #53 from Codium-ai/enhancement/github_action_apply
Run github action on this repo
2023-07-16 13:23:48 +03:00
7488eb8c9e Run github action on this repo 2023-07-16 13:21:26 +03:00
b3e79ed677 cli.py - modify command line for a more coherent command invokation 2023-07-16 13:18:29 +03:00
5d2fe07bf7 Merge pull request #47 from Codium-ai/feature/github_action
Github custom action development
2023-07-16 12:54:40 +03:00
84bf95e9ab Merge pull request #50 from Codium-ai/tr/numbered_hunks
Adding numbered hunks and code suggestions feature
2023-07-16 12:27:29 +03:00
4f4989af8c full code suggestions
full code suggestions
2023-07-16 09:01:57 +03:00
23a249ccdb Merge pull request #48 from Codium-ai/hl/gitlab_fix
Inline suggestion refactor + supporting GitLab
2023-07-14 22:53:52 +03:00
4a6bf4c55a Merge branch 'main' into hl/gitlab_fix 2023-07-14 22:48:13 +03:00
3f75b14ba3 small addition 2023-07-14 22:45:07 +03:00
ae9cedd50d Merge pull request #46 from Codium-ai/tr/description_tool
Add PR Description Tool
2023-07-13 21:00:50 +03:00
ae63833043 Merge commit '055a8ea8590fbe9078cdc6af6398df2f053b9ce7' into hl/gitlab_fix 2023-07-13 20:44:26 +03:00
da6828ad87 Inline suggestion refactor + Gitlab WORKS 2023-07-13 20:43:49 +03:00
ea1cd7ae45 Github custom action development - WIP 2023-07-13 19:14:44 +03:00
1c1aad2806 Github custom action development - WIP 2023-07-13 19:08:10 +03:00
f466d79031 Github custom action development - WIP 2023-07-13 18:59:54 +03:00
e2323dfb9f Github custom action development - WIP 2023-07-13 18:54:40 +03:00
e51e443adc Github custom action development - WIP 2023-07-13 18:54:11 +03:00
f6d4a214ca Github custom action development - WIP 2023-07-13 18:40:03 +03:00
4bb46d9faa Github custom action development - WIP 2023-07-13 18:37:32 +03:00
f337d76af6 Github custom action development - WIP 2023-07-13 18:32:28 +03:00
4e59693c76 diff_files 2023-07-13 18:26:35 +03:00
4033303c1f Github custom action development - WIP 2023-07-13 18:18:23 +03:00
38c8d187d2 Github custom action development - WIP 2023-07-13 18:16:25 +03:00
f8ddfd2f25 Merge remote-tracking branch 'origin/tr/description_tool' into feature/github_action 2023-07-13 18:06:35 +03:00
4b4fda37a6 publish_description as abstract method 2023-07-13 18:04:28 +03:00
9ca6b789a7 Github custom action development - WIP 2023-07-13 18:02:38 +03:00
0f73f5f906 set as title 2023-07-13 17:53:17 +03:00
055a8ea859 Merge pull request #44 from zmeir/patch-1
Typo when setting `openai.api_version`
2023-07-13 17:52:33 +03:00
5742a9be1e Github custom action development 2023-07-13 17:46:12 +03:00
914cc6639a ignore current title 2023-07-13 17:34:18 +03:00
f34cda126a stable 2023-07-13 17:31:28 +03:00
dece20c984 PRDescription 2023-07-13 17:24:56 +03:00
94c1f430af General PR suggestions prompt 2023-07-13 16:34:56 +03:00
9fadde388b remove title and description 2023-07-13 16:26:33 +03:00
d1b6b3bc95 Merge pull request #43 from Codium-ai/tr/inline_code_suggestions
Tr/inline code suggestions
2023-07-13 10:48:42 +03:00
f57d58ee7d Typo when setting openai.api_version 2023-07-13 10:22:57 +03:00
77a451ada0 inline_code_comments 2023-07-13 09:44:33 +03:00
4b8420aa16 remove suggestion number 2023-07-13 08:10:36 +03:00
25bc69f70e Merge pull request #41 from Codium-ai/gitlab_small_fix
Update gitlab config
2023-07-12 18:16:43 +03:00
e2faf117c5 Update gitlab config 2023-07-12 18:02:28 +03:00
aaff03bb60 Merge pull request #40 from Codium-ai/feature/support_azure_openai
Add Azure OpenAI support
2023-07-12 13:37:00 +03:00
cd1e62ec96 Add Azure OpenAI support 2023-07-12 11:53:46 +03:00
7767cae181 Merge pull request #39 from Codium-ai/bugfix/cli
Remove installation_id from cli
2023-07-12 11:31:43 +03:00
1bc206e7b2 Remove installation_id from cli 2023-07-12 11:31:06 +03:00
52a438b3c8 Merge pull request #38 from Codium-ai/hl/try_fix_when_broken_output
Try to fix json output when it's broken or incomplete
2023-07-11 22:23:07 +03:00
b8a71b369d add max_iter 2023-07-11 22:22:08 +03:00
72af2a1f9c Add tests 2023-07-11 22:11:55 +03:00
fd4a2bf7ff refactor try_fix_json, generalize finding the ending of a json item (support new lines, spaces tab) 2023-07-11 22:11:42 +03:00
a3211d4958 Merge commit '210d94f2aa6ebf872b9b85051d1842c32d4fc34e' into hl/try_fix_when_broken_output 2023-07-11 17:33:02 +03:00
86d7ed5f82 Try to fix broken json output 2023-07-11 17:32:48 +03:00
210d94f2aa Merge pull request #24 from Xyand/feature/gitlab_provider
Feature/gitlab provider
2023-07-11 16:56:44 +03:00
42 changed files with 1064 additions and 171 deletions

16
.github/workflows/review.yaml vendored Normal file
View File

@ -0,0 +1,16 @@
on:
pull_request:
issue_comment:
jobs:
pr_agent_job:
runs-on: ubuntu-latest
name: Run pr agent on every pull request
steps:
- name: PR Agent action step
id: pragent
uses: Codium-ai/pr-agent@main
env:
OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
OPENAI_ORG: ${{ secrets.OPENAI_ORG }}
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

View File

10
Dockerfile.github_action Normal file
View File

@ -0,0 +1,10 @@
FROM python:3.10 as base
WORKDIR /app
ADD requirements.txt .
RUN pip install -r requirements.txt && rm requirements.txt
ENV PYTHONPATH=/app
ADD pr_agent pr_agent
ADD github_action/entrypoint.sh /
RUN chmod +x /entrypoint.sh
ENTRYPOINT ["/entrypoint.sh"]

View File

@ -0,0 +1 @@
FROM codiumai/pr-agent:github_action

View File

@ -9,18 +9,40 @@
[![GitHub license](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://github.com/Codium-ai/pr-agent/blob/main/LICENSE) [![GitHub license](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://github.com/Codium-ai/pr-agent/blob/main/LICENSE)
[![Discord](https://badgen.net/badge/icon/discord?icon=discord&label&color=purple)](https://discord.com/channels/1057273017547378788/1126104260430528613) [![Discord](https://badgen.net/badge/icon/discord?icon=discord&label&color=purple)](https://discord.com/channels/1057273017547378788/1126104260430528613)
CodiumAI `pr-agent` is an open-source tool aiming to help developers review PRs faster and more efficiently. It automatically analyzes the PR, provides feedback and suggestions, and can answer free-text questions.
</div> </div>
<div align="left">
CodiumAI `pr-agent` is an open-source tool aiming to help developers review PRs faster and more efficiently. It automatically analyzes the PR and can provide several types of feedback:
**Auto-Description**: Automatically generating PR description - name, type, summary, and code walkthrough.
\
**PR Review**: Feedback about the PR main theme, type, relevant tests, security issues, focused, and various suggestions for the PR content.
\
**Question Answering**: Answering free-text questions about the PR.
\
**Code Suggestion**: Committable code suggestions for improving the PR.
Example results:
</div>
<div align="center">
<p float="center">
<img src="./pics/pr_reviewer_1.png" width="800">
</p>
<p float="center">
<img src="./pics/pr_code_suggestions.png" width="800">
</p>
</div>
<div align="left">
- [Live demo](#live-demo) - [Live demo](#live-demo)
- [Quickstart](#Quickstart) - [Overview](#overview)
- [Quickstart](#quickstart)
- [Usage and tools](#usage-and-tools) - [Usage and tools](#usage-and-tools)
- [Configuration](#Configuration) - [Configuration](#configuration)
- [How it works](#how-it-works) - [How it works](#how-it-works)
- [Roadmap](#roadmap) - [Roadmap](#roadmap)
- [Similar projects](#similar-projects) - [Similar projects](#similar-projects)
</div>
## Live demo ## Live demo
@ -31,6 +53,25 @@ Experience GPT-4 powered PR review on your public GitHub repository with our hos
To set up your own pr-agent, see the [Quickstart](#Quickstart) section To set up your own pr-agent, see the [Quickstart](#Quickstart) section
--- ---
## Overview
`pr-agent` offers extensive pull request functionalities across various git providers:
| | | Github | Gitlab | Bitbucket |
|-------|---------------------------------------------|--------|--------|-----------|
| TOOLS | Review | ✓ | ✓ | ✓ |
| | ⮑ Inline review | ✓ | ✓ | |
| | Ask | ✓ | ✓ | |
| | Auto-Description | ✓ | | |
| | Improve Code | ✓ | | |
| | | | | |
| USAGE | CLI | ✓ | ✓ | ✓ |
| | Tagging bot | ✓ | ✓ | |
| | Actions | ✓ | | |
| | | | | |
| CORE | PR compression | ✓ | ✓ | ✓ |
| | Repo language prioritization | ✓ | ✓ | ✓ |
| | Adaptive and token-aware<br />file patch fitting | ✓ | ✓ | ✓ |
## Quickstart ## Quickstart
@ -183,7 +224,6 @@ Here is a quick overview of the different sub-tools of PR Reviewer:
- PR Analysis - PR Analysis
- Summarize main theme - Summarize main theme
- PR description and title
- PR type classification - PR type classification
- Is the PR covered by relevant tests - Is the PR covered by relevant tests
- Is this a focused PR - Is this a focused PR
@ -199,7 +239,6 @@ This is how a typical output of the PR Reviewer looks like:
#### PR Analysis #### PR Analysis
- 🎯 **Main theme:** Adding language extension handler and token handler - 🎯 **Main theme:** Adding language extension handler and token handler
- 🔍 **Description and title:** Yes
- 📌 **Type of PR:** Enhancement - 📌 **Type of PR:** Enhancement
- 🧪 **Relevant tests added:** No - 🧪 **Relevant tests added:** No
-**Focused PR:** Yes, the PR is focused on adding two new handlers for language extension and token counting. -**Focused PR:** Yes, the PR is focused on adding two new handlers for language extension and token counting.
@ -250,45 +289,6 @@ require_tests_review=true
require_security_review=true require_security_review=true
``` ```
#### Code Suggestions configuration:
There are also configuration options to control different aspects of the `code suggestions` feature.
The number of suggestions provided can be controlled by adjusting the following parameter:
```
num_code_suggestions=4
```
You can also enable more verbose and informative mode of code suggestions:
```
extended_code_suggestions=false
```
This is a comparison of the regular and extended code suggestions modes:
- **relevant file:** sql.py
- **suggestion content:** Remove hardcoded sensitive information like username and password. Use environment variables or a secure method to store these values. [important]
Example for extended suggestion:
- **relevant file:** sql.py
- **suggestion content:** Remove hardcoded sensitive information (username and password) [important]
- **why:** Hardcoding sensitive information is a security risk. It's better to use environment variables or a secure way to store these values.
- **code example:**
- **before code:**
```
user = "root",
password = "Mysql@123",
```
- **after code:**
```
user = os.getenv('DB_USER'),
password = os.getenv('DB_PASSWORD'),
```
---
## How it works ## How it works
![PR-Agent Tools](./pics/pr_agent_overview.png) ![PR-Agent Tools](./pics/pr_agent_overview.png)

5
action.yaml Normal file
View File

@ -0,0 +1,5 @@
name: 'PR Agent'
description: 'Summarize, review and suggest improvements for pull requests'
runs:
using: 'docker'
image: 'Dockerfile.github_action_dockerhub'

View File

@ -0,0 +1,2 @@
#!/bin/bash
python /app/pr_agent/servers/github_action_runner.py

Binary file not shown.

Before

Width:  |  Height:  |  Size: 100 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 102 KiB

BIN
pics/main_pic_4_tools.gif Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 260 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 335 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 193 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 137 KiB

After

Width:  |  Height:  |  Size: 161 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 267 KiB

BIN
pics/pr_reviewer_1.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 185 KiB

BIN
pics/pr_reviewer_2.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 162 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 42 KiB

View File

@ -1,5 +1,7 @@
import re import re
from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
from pr_agent.tools.pr_description import PRDescription
from pr_agent.tools.pr_questions import PRQuestions from pr_agent.tools.pr_questions import PRQuestions
from pr_agent.tools.pr_reviewer import PRReviewer from pr_agent.tools.pr_reviewer import PRReviewer
@ -8,17 +10,20 @@ class PRAgent:
def __init__(self): def __init__(self):
pass pass
async def handle_request(self, pr_url, request): async def handle_request(self, pr_url, request) -> bool:
if 'please review' in request.lower() or 'review' == request.lower().strip() or len(request) == 0: if any(cmd in request for cmd in ["/review", "/review_pr"]):
reviewer = PRReviewer(pr_url) await PRReviewer(pr_url).review()
await reviewer.review() elif any(cmd in request for cmd in ["/describe", "/describe_pr"]):
await PRDescription(pr_url).describe()
elif any(cmd in request for cmd in ["/improve", "/improve_code"]):
await PRCodeSuggestions(pr_url).suggest()
elif any(cmd in request for cmd in ["/ask", "/ask_question"]):
pattern = r'(/ask|/ask_question)\s*(.*)'
matches = re.findall(pattern, request, re.IGNORECASE)
if matches:
question = matches[0][1]
await PRQuestions(pr_url, question).answer()
else: else:
if "please answer" in request.lower(): return False
question = re.split(r'(?i)please answer', request)[1].strip()
elif request.lower().strip().startswith("answer"): return True
question = re.split(r'(?i)answer', request)[1].strip()
else:
question = request
answerer = PRQuestions(pr_url, question)
await answerer.answer()

View File

@ -14,6 +14,13 @@ class AiHandler:
openai.api_key = settings.openai.key openai.api_key = settings.openai.key
if settings.get("OPENAI.ORG", None): if settings.get("OPENAI.ORG", None):
openai.organization = settings.openai.org openai.organization = settings.openai.org
self.deployment_id = settings.get("OPENAI.DEPLOYMENT_ID", None)
if settings.get("OPENAI.API_TYPE", None):
openai.api_type = settings.openai.api_type
if settings.get("OPENAI.API_VERSION", None):
openai.api_version = settings.openai.api_version
if settings.get("OPENAI.API_BASE", None):
openai.api_base = settings.openai.api_base
except AttributeError as e: except AttributeError as e:
raise ValueError("OpenAI key is required") from e raise ValueError("OpenAI key is required") from e
@ -23,6 +30,7 @@ class AiHandler:
try: try:
response = await openai.ChatCompletion.acreate( response = await openai.ChatCompletion.acreate(
model=model, model=model,
deployment_id=self.deployment_id,
messages=[ messages=[
{"role": "system", "content": system}, {"role": "system", "content": system},
{"role": "user", "content": user} {"role": "user", "content": user}

View File

@ -13,6 +13,9 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
if not patch_str or num_lines == 0: if not patch_str or num_lines == 0:
return patch_str return patch_str
if type(original_file_str) == bytes:
original_file_str = original_file_str.decode('utf-8')
original_lines = original_file_str.splitlines() original_lines = original_file_str.splitlines()
patch_lines = patch_str.splitlines() patch_lines = patch_str.splitlines()
extended_patch_lines = [] extended_patch_lines = []
@ -105,3 +108,78 @@ def handle_patch_deletions(patch: str, original_file_content_str: str,
logging.info(f"Processing file: {file_name}, hunks were deleted") logging.info(f"Processing file: {file_name}, hunks were deleted")
patch = patch_new patch = patch_new
return patch return patch
def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
# toDO: (maybe remove '-' and '+' from the beginning of the line)
"""
## src/file.ts
--new hunk--
881 line1
882 line2
883 line3
884 line4
885 line6
886 line7
887 + line8
888 + line9
889 line10
890 line11
...
--old hunk--
line1
line2
- line3
- line4
line5
line6
...
"""
patch_with_lines_str = f"## {file.filename}\n"
import re
patch_lines = patch.splitlines()
RE_HUNK_HEADER = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
new_content_lines = []
old_content_lines = []
match = None
start1, size1, start2, size2 = -1, -1, -1, -1
for line in patch_lines:
if 'no newline at end of file' in line.lower():
continue
if line.startswith('@@'):
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'
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'
for i, line_old in enumerate(old_content_lines):
patch_with_lines_str += f"{line_old}\n"
new_content_lines = []
old_content_lines = []
start1, size1, start2, size2 = map(int, match.groups()[:4])
elif line.startswith('+'):
new_content_lines.append(line)
elif line.startswith('-'):
old_content_lines.append(line)
else:
new_content_lines.append(line)
old_content_lines.append(line)
# finishing last hunk
if match and new_content_lines:
if new_content_lines:
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'
for i, line_old in enumerate(old_content_lines):
patch_with_lines_str += f"{line_old}\n"
return patch_with_lines_str.strip()

View File

@ -4,7 +4,8 @@ import difflib
import logging import logging
from typing import Any, Tuple, Union from typing import Any, Tuple, Union
from pr_agent.algo.git_patch_processing import extend_patch, handle_patch_deletions from pr_agent.algo.git_patch_processing import extend_patch, handle_patch_deletions, \
convert_to_hunks_with_lines_numbers
from pr_agent.algo.language_handler import sort_files_by_main_languages from pr_agent.algo.language_handler import sort_files_by_main_languages
from pr_agent.algo.token_handler import TokenHandler from pr_agent.algo.token_handler import TokenHandler
from pr_agent.config_loader import settings from pr_agent.config_loader import settings
@ -19,26 +20,33 @@ OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD = 600
PATCH_EXTRA_LINES = 3 PATCH_EXTRA_LINES = 3
def get_pr_diff(git_provider: Union[GithubProvider, Any], token_handler: TokenHandler) -> str: def get_pr_diff(git_provider: Union[GithubProvider, Any], token_handler: TokenHandler,
add_line_numbers_to_hunks: bool = False, disable_extra_lines: bool =False) -> str:
""" """
Returns a string with the diff of the PR. Returns a string with the diff of the PR.
If needed, apply diff minimization techniques to reduce the number of tokens If needed, apply diff minimization techniques to reduce the number of tokens
""" """
files = list(git_provider.get_diff_files()) if disable_extra_lines:
global PATCH_EXTRA_LINES
PATCH_EXTRA_LINES = 0
git_provider.pr.diff_files = list(git_provider.get_diff_files())
# get pr languages # get pr languages
pr_languages = sort_files_by_main_languages(git_provider.get_languages(), files) pr_languages = sort_files_by_main_languages(git_provider.get_languages(), git_provider.pr.diff_files)
# generate a standard diff string, with patch extension # generate a standard diff string, with patch extension
patches_extended, total_tokens = pr_generate_extended_diff(pr_languages, token_handler) patches_extended, total_tokens = pr_generate_extended_diff(pr_languages, token_handler,
add_line_numbers_to_hunks)
# if we are under the limit, return the full diff # if we are under the limit, return the full diff
if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < token_handler.limit: if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < token_handler.limit:
return "\n".join(patches_extended) return "\n".join(patches_extended)
# if we are over the limit, start pruning # if we are over the limit, start pruning
patches_compressed, modified_file_names, deleted_file_names = pr_generate_compressed_diff(pr_languages, patches_compressed, modified_file_names, deleted_file_names = \
token_handler) pr_generate_compressed_diff(pr_languages, token_handler, add_line_numbers_to_hunks)
final_diff = "\n".join(patches_compressed) final_diff = "\n".join(patches_compressed)
if modified_file_names: if modified_file_names:
modified_list_str = MORE_MODIFIED_FILES_ + "\n".join(modified_file_names) modified_list_str = MORE_MODIFIED_FILES_ + "\n".join(modified_file_names)
@ -49,7 +57,8 @@ def get_pr_diff(git_provider: Union[GithubProvider, Any], token_handler: TokenHa
return final_diff return final_diff
def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler) -> \ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
add_line_numbers_to_hunks: bool) -> \
Tuple[list, int]: Tuple[list, int]:
""" """
Generate a standard diff string, with patch extension Generate a standard diff string, with patch extension
@ -72,6 +81,9 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler) -
extended_patch = extend_patch(original_file_content_str, patch, num_lines=PATCH_EXTRA_LINES) 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"## {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)
patch_tokens = token_handler.count_tokens(full_extended_patch) patch_tokens = token_handler.count_tokens(full_extended_patch)
file.tokens = patch_tokens file.tokens = patch_tokens
total_tokens += patch_tokens total_tokens += patch_tokens
@ -80,7 +92,8 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler) -
return patches_extended, total_tokens return patches_extended, total_tokens
def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) -> Tuple[list, list, list]: def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler,
convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list]:
# Apply Diff Minimization techniques to reduce the number of tokens: # Apply Diff Minimization techniques to reduce the number of tokens:
# 0. Start from the largest diff patch to smaller ones # 0. Start from the largest diff patch to smaller ones
# 1. Don't use extend context lines around diff # 1. Don't use extend context lines around diff
@ -114,6 +127,10 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) ->
deleted_files_list.append(file.filename) deleted_files_list.append(file.filename)
total_tokens += token_handler.count_tokens(file.filename) + 1 total_tokens += token_handler.count_tokens(file.filename) + 1
continue continue
if convert_hunks_to_line_numbers:
patch = convert_to_hunks_with_lines_numbers(patch, file)
new_patch_tokens = token_handler.count_tokens(patch) new_patch_tokens = token_handler.count_tokens(patch)
# Hard Stop, no more tokens # Hard Stop, no more tokens
@ -135,7 +152,10 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) ->
continue continue
if patch: if patch:
patch_final = f"## {file.filename}\n\n{patch}\n" if not convert_hunks_to_line_numbers:
patch_final = f"## {file.filename}\n\n{patch}\n"
else:
patch_final = patch
patches.append(patch_final) patches.append(patch_final)
total_tokens += token_handler.count_tokens(patch_final) total_tokens += token_handler.count_tokens(patch_final)
if settings.config.verbosity_level >= 2: if settings.config.verbosity_level >= 2:

View File

@ -1,5 +1,8 @@
from __future__ import annotations from __future__ import annotations
import json
import logging
import re
import textwrap import textwrap
@ -8,7 +11,6 @@ def convert_to_markdown(output_data: dict) -> str:
emojis = { emojis = {
"Main theme": "🎯", "Main theme": "🎯",
"Description and title": "🔍",
"Type of PR": "📌", "Type of PR": "📌",
"Relevant tests added": "🧪", "Relevant tests added": "🧪",
"Unrelated changes": "⚠️", "Unrelated changes": "⚠️",
@ -50,10 +52,7 @@ def parse_code_suggestion(code_suggestions: dict) -> str:
code_str_indented = textwrap.indent(code_str, ' ') code_str_indented = textwrap.indent(code_str, ' ')
markdown_text += f" - **{code_key}:**\n{code_str_indented}\n" markdown_text += f" - **{code_key}:**\n{code_str_indented}\n"
else: else:
if "suggestion number" in sub_key.lower(): if "relevant file" in sub_key.lower():
# markdown_text += f"- **suggestion {sub_value}:**\n" # prettier formatting
pass
elif "relevant file" in sub_key.lower():
markdown_text += f"\n - **{sub_key}:** {sub_value}\n" markdown_text += f"\n - **{sub_key}:** {sub_value}\n"
else: else:
markdown_text += f" **{sub_key}:** {sub_value}\n" markdown_text += f" **{sub_key}:** {sub_value}\n"
@ -61,3 +60,25 @@ def parse_code_suggestion(code_suggestions: dict) -> str:
markdown_text += "\n" markdown_text += "\n"
return markdown_text return markdown_text
def try_fix_json(review, max_iter=10):
# Try to fix JSON if it is broken/incomplete: parse until the last valid code suggestion
data = {}
if review.rfind("'Code suggestions': [") > 0 or review.rfind('"Code suggestions": [') > 0:
last_code_suggestion_ind = [m.end() for m in re.finditer(r"\}\s*,", review)][-1] - 1
valid_json = False
iter_count = 0
while last_code_suggestion_ind > 0 and not valid_json and iter_count < max_iter:
try:
data = json.loads(review[:last_code_suggestion_ind] + "]}}")
valid_json = True
review = review[:last_code_suggestion_ind].strip() + "]}}"
except json.decoder.JSONDecodeError:
review = review[:last_code_suggestion_ind]
# Use regular expression to find the last occurrence of "}," with any number of whitespaces or newlines
last_code_suggestion_ind = [m.end() for m in re.finditer(r"\}\s*,", review)][-1] - 1
iter_count += 1
if not valid_json:
logging.error("Unable to decode JSON response from AI")
data = {}
return data

View File

@ -3,24 +3,55 @@ import asyncio
import logging import logging
import os import os
from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
from pr_agent.tools.pr_description import PRDescription
from pr_agent.tools.pr_questions import PRQuestions from pr_agent.tools.pr_questions import PRQuestions
from pr_agent.tools.pr_reviewer import PRReviewer from pr_agent.tools.pr_reviewer import PRReviewer
def run(): def run():
parser = argparse.ArgumentParser(description='AI based pull request analyzer') parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage="""\
Usage: cli.py --pr-url <URL on supported git hosting service> <command> [<args>].
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.
""")
parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', required=True) parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', required=True)
parser.add_argument('--question', type=str, help='Optional question to ask', required=False) parser.add_argument('command', type=str, help='The', choices=['review', 'review_pr',
'ask', 'ask_question',
'describe', 'describe_pr',
'improve', 'improve_code'], default='review')
parser.add_argument('rest', nargs=argparse.REMAINDER, default=[])
args = parser.parse_args() args = parser.parse_args()
logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO")) logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
if args.question: command = args.command.lower()
print(f"Question: {args.question} about PR {args.pr_url}") if command in ['ask', 'ask_question']:
reviewer = PRQuestions(args.pr_url, args.question, installation_id=None) question = ' '.join(args.rest).strip()
if len(question) == 0:
print("Please specify a question")
parser.print_help()
return
print(f"Question: {question} about PR {args.pr_url}")
reviewer = PRQuestions(args.pr_url, question)
asyncio.run(reviewer.answer()) asyncio.run(reviewer.answer())
else: elif command in ['describe', 'describe_pr']:
print(f"PR description: {args.pr_url}")
reviewer = PRDescription(args.pr_url)
asyncio.run(reviewer.describe())
elif command in ['improve', 'improve_code']:
print(f"PR code suggestions: {args.pr_url}")
reviewer = PRCodeSuggestions(args.pr_url)
asyncio.run(reviewer.suggest())
elif command in ['review', 'review_pr']:
print(f"Reviewing PR: {args.pr_url}") print(f"Reviewing PR: {args.pr_url}")
reviewer = PRReviewer(args.pr_url, installation_id=None, cli_mode=True) reviewer = PRReviewer(args.pr_url, cli_mode=True)
asyncio.run(reviewer.review()) asyncio.run(reviewer.review())
else:
print(f"Unknown command: {command}")
parser.print_help()
if __name__ == '__main__': if __name__ == '__main__':

View File

@ -11,6 +11,8 @@ settings = Dynaconf(
"settings/configuration.toml", "settings/configuration.toml",
"settings/pr_reviewer_prompts.toml", "settings/pr_reviewer_prompts.toml",
"settings/pr_questions_prompts.toml", "settings/pr_questions_prompts.toml",
"settings/pr_description_prompts.toml",
"settings/pr_code_suggestions_prompts.toml",
"settings_prod/.secrets.toml" "settings_prod/.secrets.toml"
]] ]]
) )

View File

@ -1,6 +1,13 @@
from abc import ABC, abstractmethod from abc import ABC, abstractmethod
from dataclasses import dataclass from dataclasses import dataclass
# enum EDIT_TYPE (ADDED, DELETED, MODIFIED, RENAMED)
from enum import Enum
class EDIT_TYPE(Enum):
ADDED = 1
DELETED = 2
MODIFIED = 3
RENAMED = 4
@dataclass @dataclass
class FilePatchInfo: class FilePatchInfo:
@ -9,6 +16,8 @@ class FilePatchInfo:
patch: str patch: str
filename: str filename: str
tokens: int = -1 tokens: int = -1
edit_type: EDIT_TYPE = EDIT_TYPE.MODIFIED
old_filename: str = None
class GitProvider(ABC): class GitProvider(ABC):
@ -16,10 +25,23 @@ class GitProvider(ABC):
def get_diff_files(self) -> list[FilePatchInfo]: def get_diff_files(self) -> list[FilePatchInfo]:
pass pass
@abstractmethod
def publish_description(self, pr_title: str, pr_body: str):
pass
@abstractmethod @abstractmethod
def publish_comment(self, pr_comment: str, is_temporary: bool = False): def publish_comment(self, pr_comment: str, is_temporary: bool = False):
pass pass
@abstractmethod
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
pass
@abstractmethod
def publish_code_suggestion(self, body: str, relevant_file: str,
relevant_lines_start: int, relevant_lines_end: int):
pass
@abstractmethod @abstractmethod
def remove_initial_comment(self): def remove_initial_comment(self):
pass pass

View File

@ -7,10 +7,10 @@ from github import AppAuthentication, Github
from pr_agent.config_loader import settings from pr_agent.config_loader import settings
from .git_provider import FilePatchInfo from .git_provider import FilePatchInfo, GitProvider
class GithubProvider: class GithubProvider(GitProvider):
def __init__(self, pr_url: Optional[str] = None): def __init__(self, pr_url: Optional[str] = None):
self.installation_id = settings.get("GITHUB.INSTALLATION_ID") self.installation_id = settings.get("GITHUB.INSTALLATION_ID")
self.github_client = self._get_github_client() self.github_client = self._get_github_client()
@ -18,8 +18,10 @@ class GithubProvider:
self.pr_num = None self.pr_num = None
self.pr = None self.pr = None
self.github_user_id = None self.github_user_id = None
self.diff_files = None
if pr_url: if pr_url:
self.set_pr(pr_url) self.set_pr(pr_url)
self.last_commit_id = list(self.pr.get_commits())[-1]
def set_pr(self, pr_url: str): def set_pr(self, pr_url: str):
self.repo, self.pr_num = self._parse_pr_url(pr_url) self.repo, self.pr_num = self._parse_pr_url(pr_url)
@ -35,8 +37,13 @@ class GithubProvider:
original_file_content_str = self._get_pr_file_content(file, self.pr.base.sha) original_file_content_str = self._get_pr_file_content(file, self.pr.base.sha)
new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha) new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha)
diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str, file.patch, file.filename)) diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str, file.patch, file.filename))
self.diff_files = diff_files
return diff_files return diff_files
def publish_description(self, pr_title: str, pr_body: str):
self.pr.edit(title=pr_title, body=pr_body)
# self.pr.create_issue_comment(pr_comment)
def publish_comment(self, pr_comment: str, is_temporary: bool = False): def publish_comment(self, pr_comment: str, is_temporary: bool = False):
response = self.pr.create_issue_comment(pr_comment) response = self.pr.create_issue_comment(pr_comment)
if hasattr(response, "user") and hasattr(response.user, "login"): if hasattr(response, "user") and hasattr(response.user, "login"):
@ -46,6 +53,76 @@ class GithubProvider:
self.pr.comments_list = [] self.pr.comments_list = []
self.pr.comments_list.append(response) self.pr.comments_list.append(response)
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
position = -1
for file in self.diff_files:
if file.filename.strip() == relevant_file:
patch = file.patch
patch_lines = patch.splitlines()
for i, line in enumerate(patch_lines):
if relevant_line_in_file in line:
position = i
break
elif relevant_line_in_file[0] == '+' and relevant_line_in_file[1:] in line:
# The model often adds a '+' to the beginning of the relevant_line_in_file even if originally
# it's a context line
position = i
break
if position == -1:
if settings.config.verbosity_level >= 2:
logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
else:
path = relevant_file.strip()
self.pr.create_review_comment(body=body, commit_id=self.last_commit_id, path=path, position=position)
def publish_code_suggestion(self, body: str,
relevant_file: str,
relevant_lines_start: int,
relevant_lines_end: int):
if not relevant_lines_start or relevant_lines_start == -1:
if settings.config.verbosity_level >= 2:
logging.exception(f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
return False
if relevant_lines_end<relevant_lines_start:
if settings.config.verbosity_level >= 2:
logging.exception(f"Failed to publish code suggestion, "
f"relevant_lines_end is {relevant_lines_end} and "
f"relevant_lines_start is {relevant_lines_start}")
return False
try:
import github.PullRequestComment
if relevant_lines_end > relevant_lines_start:
post_parameters = {
"body": body,
"commit_id": self.last_commit_id._identity,
"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,
"commit_id": self.last_commit_id._identity,
"path": relevant_file,
"line": relevant_lines_start,
"side": "RIGHT",
}
headers, data = self.pr._requester.requestJsonAndCheck(
"POST", f"{self.pr.url}/comments", input=post_parameters
)
github.PullRequestComment.PullRequestComment(
self.pr._requester, headers, data, completed=True
)
return True
except Exception as e:
if settings.config.verbosity_level >= 2:
logging.error(f"Failed to publish code suggestion, error: {e}")
return False
def remove_initial_comment(self): def remove_initial_comment(self):
try: try:
for comment in self.pr.comments_list: for comment in self.pr.comments_list:
@ -146,9 +223,9 @@ class GithubProvider:
def _get_pr(self): def _get_pr(self):
return self._get_repo().get_pull(self.pr_num) return self._get_repo().get_pull(self.pr_num)
def _get_pr_file_content(self, file: FilePatchInfo, sha: str): def _get_pr_file_content(self, file: FilePatchInfo, sha: str) -> str:
try: try:
file_content_str = self._get_repo().get_contents(file.filename, ref=sha).decoded_content.decode() file_content_str = str(self._get_repo().get_contents(file.filename, ref=sha).decoded_content.decode())
except Exception: except Exception:
file_content_str = "" file_content_str = ""
return file_content_str return file_content_str

View File

@ -1,4 +1,5 @@
import logging import logging
import re
from typing import Optional, Tuple from typing import Optional, Tuple
from urllib.parse import urlparse from urllib.parse import urlparse
@ -6,7 +7,7 @@ import gitlab
from pr_agent.config_loader import settings from pr_agent.config_loader import settings
from .git_provider import FilePatchInfo, GitProvider from .git_provider import FilePatchInfo, GitProvider, EDIT_TYPE
class GitLabProvider(GitProvider): class GitLabProvider(GitProvider):
@ -24,6 +25,7 @@ class GitLabProvider(GitProvider):
self.id_project = None self.id_project = None
self.id_mr = None self.id_mr = None
self.mr = None self.mr = None
self.diff_files = None
self.temp_comments = [] self.temp_comments = []
self._set_merge_request(merge_request_url) self._set_merge_request(merge_request_url)
@ -35,20 +37,130 @@ class GitLabProvider(GitProvider):
def _set_merge_request(self, merge_request_url: str): def _set_merge_request(self, merge_request_url: str):
self.id_project, self.id_mr = self._parse_merge_request_url(merge_request_url) self.id_project, self.id_mr = self._parse_merge_request_url(merge_request_url)
self.mr = self._get_merge_request() self.mr = self._get_merge_request()
self.last_diff = self.mr.diffs.list()[-1]
def _get_pr_file_content(self, file_path: str, branch: str) -> str:
return self.gl.projects.get(self.id_project).files.get(file_path, branch).decode()
def get_diff_files(self) -> list[FilePatchInfo]: def get_diff_files(self) -> list[FilePatchInfo]:
diffs = self.mr.changes()['changes'] diffs = self.mr.changes()['changes']
diff_files = [FilePatchInfo("", "", diff['diff'], diff['new_path']) for diff in diffs] diff_files = []
for diff in diffs:
original_file_content_str = self._get_pr_file_content(diff['old_path'], self.mr.target_branch)
new_file_content_str = self._get_pr_file_content(diff['new_path'], self.mr.source_branch)
edit_type = EDIT_TYPE.MODIFIED
if diff['new_file']:
edit_type = EDIT_TYPE.ADDED
elif diff['deleted_file']:
edit_type = EDIT_TYPE.DELETED
elif diff['renamed_file']:
edit_type = EDIT_TYPE.RENAMED
try:
original_file_content_str = bytes.decode(original_file_content_str, 'utf-8')
new_file_content_str = bytes.decode(new_file_content_str, 'utf-8')
except UnicodeDecodeError:
logging.warning(
f"Cannot decode file {diff['old_path']} or {diff['new_path']} in merge request {self.id_mr}")
diff_files.append(
FilePatchInfo(original_file_content_str, new_file_content_str, diff['diff'], diff['new_path'],
edit_type=edit_type,
old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path']))
self.diff_files = diff_files
return diff_files return diff_files
def get_files(self): def get_files(self):
return [change['new_path'] for change in self.mr.changes()['changes']] return [change['new_path'] for change in self.mr.changes()['changes']]
def publish_description(self, pr_title: str, pr_body: str):
logging.exception("Not implemented yet")
pass
def publish_comment(self, mr_comment: str, is_temporary: bool = False): def publish_comment(self, mr_comment: str, is_temporary: bool = False):
comment = self.mr.notes.create({'body': mr_comment}) comment = self.mr.notes.create({'body': mr_comment})
if is_temporary: if is_temporary:
self.temp_comments.append(comment) self.temp_comments.append(comment)
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
edit_type, found, source_line_no, target_file, target_line_no = self.search_line(relevant_file,
relevant_line_in_file)
if not found:
logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
else:
if edit_type == 'addition':
position = target_line_no - 1
else:
position = source_line_no - 1
d = self.last_diff
pos_obj = {'position_type': 'text',
'new_path': target_file.filename,
'old_path': target_file.old_filename if target_file.old_filename else target_file.filename,
'base_sha': d.base_commit_sha, 'start_sha': d.start_commit_sha, 'head_sha': d.head_commit_sha}
if edit_type == 'deletion':
pos_obj['old_line'] = position
elif edit_type == 'addition':
pos_obj['new_line'] = position
else:
pos_obj['new_line'] = position
pos_obj['old_line'] = position
self.mr.discussions.create({'body': body,
'position': pos_obj})
def publish_code_suggestion(self, body: str,
relevant_file: str,
relevant_lines_start: int,
relevant_lines_end: int):
raise "not implemented yet for gitlab"
def search_line(self, relevant_file, relevant_line_in_file):
RE_HUNK_HEADER = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
target_file = None
source_line_no = 0
target_line_no = 0
found = False
edit_type = self.get_edit_type(relevant_line_in_file)
for file in self.diff_files:
if file.filename == relevant_file:
target_file = file
patch = file.patch
patch_lines = patch.splitlines()
for i, line in enumerate(patch_lines):
if line.startswith('@@'):
match = RE_HUNK_HEADER.match(line)
if not match:
continue
start_old, size_old, start_new, size_new, _ = match.groups()
source_line_no = int(start_old)
target_line_no = int(start_new)
continue
if line.startswith('-'):
source_line_no += 1
elif line.startswith('+'):
target_line_no += 1
elif line.startswith(' '):
source_line_no += 1
target_line_no += 1
if relevant_line_in_file in line:
found = True
edit_type = self.get_edit_type(line)
break
elif relevant_line_in_file[0] == '+' and relevant_line_in_file[1:] in line:
# The model often adds a '+' to the beginning of the relevant_line_in_file even if originally
# it's a context line
found = True
edit_type = self.get_edit_type(line)
break
return edit_type, found, source_line_no, target_file, target_line_no
def get_edit_type(self, relevant_line_in_file):
edit_type = 'context'
if relevant_line_in_file[0] == '-':
edit_type = 'deletion'
elif relevant_line_in_file[0] == '+':
edit_type = 'addition'
return edit_type
def remove_initial_comment(self): def remove_initial_comment(self):
try: try:
for comment in self.temp_comments: for comment in self.temp_comments:
@ -90,3 +202,6 @@ class GitLabProvider(GitProvider):
def _get_merge_request(self): def _get_merge_request(self):
mr = self.gl.projects.get(self.id_project).mergerequests.get(self.id_mr) mr = self.gl.projects.get(self.id_project).mergerequests.get(self.id_mr)
return mr return mr
def get_user_id(self):
return None

View File

@ -0,0 +1,73 @@
import asyncio
import json
import os
import re
from pr_agent.config_loader import settings
from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
from pr_agent.tools.pr_description import PRDescription
from pr_agent.tools.pr_questions import PRQuestions
from pr_agent.tools.pr_reviewer import PRReviewer
async def run_action():
GITHUB_EVENT_NAME = os.environ.get('GITHUB_EVENT_NAME', None)
if not GITHUB_EVENT_NAME:
print("GITHUB_EVENT_NAME not set")
return
GITHUB_EVENT_PATH = os.environ.get('GITHUB_EVENT_PATH', None)
if not GITHUB_EVENT_PATH:
print("GITHUB_EVENT_PATH not set")
return
try:
event_payload = json.load(open(GITHUB_EVENT_PATH, 'r'))
except json.decoder.JSONDecodeError as e:
print(f"Failed to parse JSON: {e}")
return
OPENAI_KEY = os.environ.get('OPENAI_KEY', None)
if not OPENAI_KEY:
print("OPENAI_KEY not set")
return
OPENAI_ORG = os.environ.get('OPENAI_ORG', None)
GITHUB_TOKEN = os.environ.get('GITHUB_TOKEN', None)
if not GITHUB_TOKEN:
print("GITHUB_TOKEN not set")
return
settings.set("OPENAI.KEY", OPENAI_KEY)
if OPENAI_ORG:
settings.set("OPENAI.ORG", OPENAI_ORG)
settings.set("GITHUB.USER_TOKEN", GITHUB_TOKEN)
settings.set("GITHUB.DEPLOYMENT_TYPE", "user")
if GITHUB_EVENT_NAME == "pull_request":
action = event_payload.get("action", None)
if action in ["opened", "reopened"]:
pr_url = event_payload.get("pull_request", {}).get("url", None)
if pr_url:
await PRReviewer(pr_url).review()
elif GITHUB_EVENT_NAME == "issue_comment":
action = event_payload.get("action", None)
if action in ["created", "edited"]:
comment_body = event_payload.get("comment", {}).get("body", None)
if comment_body:
pr_url = event_payload.get("issue", {}).get("pull_request", {}).get("url", None)
if pr_url:
body = comment_body.strip().lower()
if any(cmd in body for cmd in ["/review", "/review_pr"]):
await PRReviewer(pr_url).review()
elif any(cmd in body for cmd in ["/describe", "/describe_pr"]):
await PRDescription(pr_url).describe()
elif any(cmd in body for cmd in ["/improve", "/improve_code"]):
await PRCodeSuggestions(pr_url).suggest()
elif any(cmd in body for cmd in ["/ask", "/ask_question"]):
pattern = r'(/ask|/ask_question)\s*(.*)'
matches = re.findall(pattern, comment_body, re.IGNORECASE)
if matches:
question = matches[0][1]
await PRQuestions(pr_url, question).answer()
else:
print(f"Unknown command: {body}")
if __name__ == '__main__':
asyncio.run(run_action())

View File

@ -56,7 +56,7 @@ async def handle_request(body):
api_url = pull_request.get("url", None) api_url = pull_request.get("url", None)
if api_url is None: if api_url is None:
return {} return {}
await agent.handle_request(api_url, "please review") await agent.handle_request(api_url, "/review")
else: else:
return {} return {}

View File

@ -1,5 +1,6 @@
import asyncio import asyncio
import logging import logging
import re
import sys import sys
from datetime import datetime, timezone from datetime import datetime, timezone
@ -8,6 +9,11 @@ import aiohttp
from pr_agent.agent.pr_agent import PRAgent from pr_agent.agent.pr_agent import PRAgent
from pr_agent.config_loader import settings from pr_agent.config_loader import settings
from pr_agent.git_providers import get_git_provider from pr_agent.git_providers import get_git_provider
from pr_agent.servers.help import bot_help_text
from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
from pr_agent.tools.pr_description import PRDescription
from pr_agent.tools.pr_questions import PRQuestions
from pr_agent.tools.pr_reviewer import PRReviewer
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG) logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
NOTIFICATION_URL = "https://api.github.com/notifications" NOTIFICATION_URL = "https://api.github.com/notifications"
@ -25,6 +31,7 @@ async def polling_loop():
last_modified = [None] last_modified = [None]
git_provider = get_git_provider()() git_provider = get_git_provider()()
user_id = git_provider.get_user_id() user_id = git_provider.get_user_id()
agent = PRAgent()
try: try:
deployment_type = settings.github.deployment_type deployment_type = settings.github.deployment_type
token = settings.github.user_token token = settings.github.user_token
@ -83,8 +90,13 @@ async def polling_loop():
if user_tag not in comment_body: if user_tag not in comment_body:
continue continue
rest_of_comment = comment_body.split(user_tag)[1].strip() rest_of_comment = comment_body.split(user_tag)[1].strip()
agent = PRAgent()
await agent.handle_request(pr_url, rest_of_comment) success = await agent.handle_request(pr_url, rest_of_comment)
if not success:
git_provider.set_pr(pr_url)
git_provider.publish_comment("### How to user PR-Agent\n" +
bot_help_text(user_id))
elif response.status != 304: elif response.status != 304:
print(f"Failed to fetch notifications. Status code: {response.status}") print(f"Failed to fetch notifications. Status code: {response.status}")

14
pr_agent/servers/help.py Normal file
View File

@ -0,0 +1,14 @@
commands_text = "> /review - Ask for a new review after your update the PR\n" \
"> /describe - Modify the PR title and description based " \
"on the PR's contents.\n" \
"> /improve - Suggest improvements to the code in the PR as pull " \
"request comments ready to commit.\n" \
"> /ask <QUESTION> - Ask a question about the PR.\n"
def bot_help_text(user: str):
return f"> Tag me in a comment '@{user}' and add one of the following commands:\n" + commands_text
actions_help_text = "> Add a comment to to invoke PR-Agent, use one of the following commands:\n" + \
commands_text

View File

@ -9,6 +9,11 @@
[openai] [openai]
key = "<API_KEY>" # Acquire through https://platform.openai.com key = "<API_KEY>" # Acquire through https://platform.openai.com
org = "<ORGANIZATION>" # Optional, may be commented out. org = "<ORGANIZATION>" # Optional, may be commented out.
# Uncomment the following for Azure OpenAI
#api_type = "azure"
#api_version = '2023-05-15' # Check Azure documentation for the current API version
#api_base = "<API_BASE>" # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
#deployment_id = "<DEPLOYMENT_ID>" # The deployment name you chose when you deployed the engine
[github] [github]
# ---- Set the following only for deployment type == "user" # ---- Set the following only for deployment type == "user"

View File

@ -2,24 +2,27 @@
model="gpt-4-0613" model="gpt-4-0613"
git_provider="github" git_provider="github"
publish_review=true publish_review=true
verbosity_level=0 # 0,1,2 verbosity_level=0 # 0,1,2
[pr_reviewer] [pr_reviewer]
require_focused_review=true require_focused_review=true
require_tests_review=true require_tests_review=true
require_security_review=true require_security_review=true
extended_code_suggestions=false num_code_suggestions=3
num_code_suggestions=4 inline_code_comments = true
[pr_questions] [pr_questions]
[pr_code_suggestions]
num_code_suggestions=4
[github] [github]
# The type of deployment to create. Valid values are 'app' or 'user'. # The type of deployment to create. Valid values are 'app' or 'user'.
deployment_type = "user" deployment_type = "user"
[gitlab] [gitlab]
# URL to the gitlab service # URL to the gitlab service
gitlab_url = "https://gitlab.com" url = "https://gitlab.com"
# Polling (either project id or namespace/project_name) syntax can be used # Polling (either project id or namespace/project_name) syntax can be used
projects_to_monitor = ['org_name/repo_name'] projects_to_monitor = ['org_name/repo_name']

View File

@ -0,0 +1,79 @@
[pr_code_suggestions_prompt]
system="""You are a language model called CodiumAI-PR-Code-Reviewer.
Your task is to provide 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 '+'.
- 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.
- Provide up to {{ num_code_suggestions }} code suggestions.
- Make sure not to provide suggestion repeating modifications already implemented in the new PR code (the '+' lines).
- Don't output line numbers in the 'improved code' snippets.
You must use the following JSON schema to format your answer:
```json
{
"Code suggestions": {
"type": "array",
"minItems": 1,
"maxItems": {{ num_code_suggestions }},
"uniqueItems": "true",
"items": {
"relevant file": {
"type": "string",
"description": "the relevant file full path"
},
"suggestion content": {
"type": "string",
"description": "a concrete suggestion for meaningfully improving the new PR code."
},
"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."
},
"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."
},
"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."
}
}
}
}
```
Example input:
'
## src/file1.py
---new_hunk---
```
[new hunk code, annotated with line numbers]
```
---old_hunk---
```
[old hunk code]
```
...
'
Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
"""
user="""PR Info:
Title: '{{title}}'
Branch: '{{branch}}'
Description: '{{description}}'
{%- if language %}
Main language: {{language}}
{%- endif %}
The PR Diff:
```
{{diff}}
```
Response (should be a valid JSON, and nothing else):
```json
"""

View File

@ -0,0 +1,45 @@
[pr_description_prompt]
system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
Your task is to provide full description of the PR content.
- Make sure not to focus the new PR code (the '+' lines).
You must use the following JSON schema to format your answer:
```json
{
"PR Title": {
"type": "string",
"description": "an informative title for the PR, describing its main theme"
},
"Type of PR": {
"type": "string",
"enum": ["Bug fix", "Tests", "Bug fix with tests", "Refactoring", "Enhancement", "Documentation", "Other"]
},
"PR Description": {
"type": "string",
"description": "an informative and concise description of the PR"
},
"PR Main Files Walkthrough": {
"type": "string",
"description": "a walkthrough of the PR changes. Review main files, in bullet points, and shortly describe the changes in each file (up to 10 most important files). Format: -`filename`: description of changes\n..."
}
}
Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
"""
user="""PR Info:
Branch: '{{branch}}'
{%- if language %}
Main language: {{language}}
{%- endif %}
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.
Response (should be a valid JSON, and nothing else):
```json
"""

View File

@ -3,9 +3,6 @@ system="""You are CodiumAI-PR-Reviewer, a language model designed to review git
Your task is to provide constructive and concise feedback for the PR, and also provide meaningfull code suggestions to improve the new PR code (the '+' lines). Your task is to provide constructive and concise feedback for the PR, and also provide meaningfull code suggestions to improve the new PR code (the '+' lines).
- Provide up to {{ num_code_suggestions }} code suggestions. - Provide up to {{ num_code_suggestions }} code suggestions.
- Try to focus on important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningfull code improvements, like performance, vulnerability, modularity, and best practices. - Try to focus on 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.
{%- if extended_code_suggestions %}
- For each suggestion, provide a short and concise code snippet to illustrate the existing code, and the improved code.
{%- endif %}
- Make sure not to provide suggestion repeating modifications already implemented in the new PR code (the '+' lines). - Make sure not to provide suggestion repeating modifications already implemented in the new PR code (the '+' lines).
You must use the following JSON schema to format your answer: You must use the following JSON schema to format your answer:
@ -16,10 +13,6 @@ You must use the following JSON schema to format your answer:
"type": "string", "type": "string",
"description": "a short explanation of the PR" "description": "a short explanation of the PR"
}, },
"Description and title": {
"type": "string",
"description": "yes\\no question: does this PR have a relevant description and title"
},
"Type of PR": { "Type of PR": {
"type": "string", "type": "string",
"enum": ["Bug fix", "Tests", "Bug fix with tests", "Refactoring", "Enhancement", "Documentation", "Other"] "enum": ["Bug fix", "Tests", "Bug fix with tests", "Refactoring", "Enhancement", "Documentation", "Other"]
@ -40,48 +33,25 @@ You must use the following JSON schema to format your answer:
"PR Feedback": { "PR Feedback": {
"General PR suggestions": { "General PR suggestions": {
"type": "string", "type": "string",
"description": "important suggestions for the contributors and maintainers of this PR, may include overall structure, primary purpose and best practices. consider using specific filenames, classes and functions names. explain yourself!" "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. Explain your suggestions."
}, },
"Code suggestions": { "Code suggestions": {
"type": "array", "type": "array",
"maxItems": {{ num_code_suggestions }}, "maxItems": {{ num_code_suggestions }},
"uniqueItems": true, "uniqueItems": true,
"items": { "items": {
"suggestion number": {
"type": "int",
"description": "suggestion number, starting from 1"
},
"relevant file": { "relevant file": {
"type": "string", "type": "string",
"description": "the relevant file name" "description": "the relevant file full path"
}, },
"suggestion content": { "suggestion content": {
"type": "string", "type": "string",
{%- if extended_code_suggestions %}
"description": "a concrete suggestion for meaningfully improving the new PR code. Don't repeat previous suggestions. Add tags with importance measure that matches each suggestion ('important' or 'medium'). Do not make suggestions for updating or adding docstrings, renaming PR title and description, or linter like.
{%- else %}
"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 ('important' or 'medium'). Do not make suggestions for updating or adding docstrings, renaming PR title and description, or linter like. "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 ('important' or 'medium'). Do not make suggestions for updating or adding docstrings, renaming PR title and description, or linter like.
{%- endif %}
}, },
{%- if extended_code_suggestions %} "relevant line in file": {
"why": {
"type": "string", "type": "string",
"description": "shortly explain why this suggestion is important" "description": "an authentic single code line from the PR git diff section, to which the suggestion applies."
},
"code example": {
"type": "object",
"properties": {
"before code": {
"type": "string",
"description": "Short and concise code snippet, to illustrate the existing code"
},
"after code": {
"type": "string",
"description": "Short and concise code snippet, to illustrate the improved code"
}
}
} }
{%- endif %}
} }
}, },
{%- if require_security %} {%- if require_security %}
@ -101,7 +71,6 @@ Example output:
"PR Analysis": "PR Analysis":
{ {
"Main theme": "xxx", "Main theme": "xxx",
"Description and title": "Yes",
"Type of PR": "Bug fix", "Type of PR": "Bug fix",
{%- if require_tests %} {%- if require_tests %}
"Relevant tests added": "No", "Relevant tests added": "No",
@ -115,17 +84,9 @@ Example output:
"General PR suggestions": "..., `xxx`...", "General PR suggestions": "..., `xxx`...",
"Code suggestions": [ "Code suggestions": [
{ {
"suggestion number": 1, "relevant file": "directory/xxx.py",
"relevant file": "xxx.py",
"suggestion content": "xxx [important]", "suggestion content": "xxx [important]",
{%- if extended_code_suggestions %} "relevant line in file": "xxx",
"why": "xxx",
"code example":
{
"before code": "xxx",
"after code": "xxx"
}
{%- endif %}
}, },
... ...
] ]

View File

@ -0,0 +1,127 @@
import copy
import json
import logging
import textwrap
from jinja2 import Environment, StrictUndefined
from pr_agent.algo.ai_handler import AiHandler
from pr_agent.algo.pr_processing import get_pr_diff
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import convert_to_markdown, try_fix_json
from pr_agent.config_loader import settings
from pr_agent.git_providers import get_git_provider, GithubProvider
from pr_agent.git_providers.git_provider import get_main_pr_language
class PRCodeSuggestions:
def __init__(self, pr_url: str, cli_mode=False):
self.git_provider = get_git_provider()(pr_url)
self.main_language = get_main_pr_language(
self.git_provider.get_languages(), self.git_provider.get_files()
)
self.ai_handler = AiHandler()
self.patches_diff = None
self.prediction = None
self.cli_mode = cli_mode
self.vars = {
"title": self.git_provider.pr.title,
"branch": self.git_provider.get_pr_branch(),
"description": self.git_provider.get_pr_description(),
"language": self.main_language,
"diff": "", # empty diff for initial calculation
'num_code_suggestions': settings.pr_code_suggestions.num_code_suggestions,
}
self.token_handler = TokenHandler(self.git_provider.pr,
self.vars,
settings.pr_code_suggestions_prompt.system,
settings.pr_code_suggestions_prompt.user)
async def suggest(self):
assert type(self.git_provider) == GithubProvider, "Only Github is supported for now"
logging.info('Generating code suggestions for PR...')
if settings.config.publish_review:
self.git_provider.publish_comment("Preparing review...", is_temporary=True)
logging.info('Getting PR diff...')
# we are using extended hunk with line numbers for code suggestions
self.patches_diff = get_pr_diff(self.git_provider,
self.token_handler,
add_line_numbers_to_hunks=True,
disable_extra_lines=True)
logging.info('Getting AI prediction...')
self.prediction = await self._get_prediction()
logging.info('Preparing PR review...')
data = self._prepare_pr_code_suggestions()
if settings.config.publish_review:
logging.info('Pushing PR review...')
self.git_provider.remove_initial_comment()
logging.info('Pushing inline code comments...')
self.push_inline_code_suggestions(data)
async def _get_prediction(self):
variables = copy.deepcopy(self.vars)
variables["diff"] = self.patches_diff # update diff
environment = Environment(undefined=StrictUndefined)
system_prompt = environment.from_string(settings.pr_code_suggestions_prompt.system).render(variables)
user_prompt = environment.from_string(settings.pr_code_suggestions_prompt.user).render(variables)
if settings.config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
model = settings.config.model
response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
system=system_prompt, user=user_prompt)
return response
def _prepare_pr_code_suggestions(self) -> str:
review = self.prediction.strip()
data = None
try:
data = json.loads(review)
except json.decoder.JSONDecodeError:
if settings.config.verbosity_level >= 2:
logging.info(f"Could not parse json response: {review}")
data = try_fix_json(review)
return data
def push_inline_code_suggestions(self, data):
for d in data['Code suggestions']:
if settings.config.verbosity_level >= 2:
logging.info(f"suggestion: {d}")
relevant_file = d['relevant file'].strip()
relevant_lines_str = d['relevant lines'].strip()
relevant_lines_start = int(relevant_lines_str.split('-')[0]) # absolute position
relevant_lines_end = int(relevant_lines_str.split('-')[-1])
content = d['suggestion content']
existing_code_snippet = d['existing code']
new_code_snippet = d['improved code']
if new_code_snippet:
try: # dedent code snippet
self.diff_files = self.git_provider.diff_files if self.git_provider.diff_files else self.git_provider.get_diff_files()
original_initial_line = None
for file in self.diff_files:
if file.filename.strip() == relevant_file:
original_initial_line = file.head_file.splitlines()[relevant_lines_start - 1]
break
if original_initial_line:
suggested_initial_line = new_code_snippet.splitlines()[0]
original_initial_spaces = len(original_initial_line) - len(original_initial_line.lstrip())
suggested_initial_spaces = len(suggested_initial_line) - len(suggested_initial_line.lstrip())
delta_spaces = original_initial_spaces - suggested_initial_spaces
if delta_spaces > 0:
new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
except Exception as e:
if settings.config.verbosity_level >= 2:
logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
body = f"**Suggestion:** {content}\n```suggestion\n" + new_code_snippet + "\n```"
success = self.git_provider.publish_code_suggestion(body=body,
relevant_file=relevant_file,
relevant_lines_start=relevant_lines_start,
relevant_lines_end=relevant_lines_end)

View File

@ -0,0 +1,83 @@
import copy
import json
import logging
from jinja2 import Environment, StrictUndefined
from pr_agent.algo.ai_handler import AiHandler
from pr_agent.algo.pr_processing import get_pr_diff
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import convert_to_markdown
from pr_agent.config_loader import settings
from pr_agent.git_providers import get_git_provider
from pr_agent.git_providers.git_provider import get_main_pr_language
class PRDescription:
def __init__(self, pr_url: str):
self.git_provider = get_git_provider()(pr_url)
self.main_pr_language = get_main_pr_language(
self.git_provider.get_languages(), self.git_provider.get_files()
)
self.ai_handler = AiHandler()
self.vars = {
"title": self.git_provider.pr.title,
"branch": self.git_provider.get_pr_branch(),
"description": self.git_provider.get_description(),
"language": self.main_pr_language,
"diff": "", # empty diff for initial calculation
}
self.token_handler = TokenHandler(self.git_provider.pr,
self.vars,
settings.pr_description_prompt.system,
settings.pr_description_prompt.user)
self.patches_diff = None
self.prediction = None
async def describe(self):
logging.info('Generating a PR description...')
if settings.config.publish_review:
self.git_provider.publish_comment("Preparing pr description...", is_temporary=True)
logging.info('Getting PR diff...')
self.patches_diff = get_pr_diff(self.git_provider, self.token_handler)
logging.info('Getting AI prediction...')
self.prediction = await self._get_prediction()
logging.info('Preparing answer...')
pr_title, pr_body = self._prepare_pr_answer()
if settings.config.publish_review:
logging.info('Pushing answer...')
self.git_provider.publish_description(pr_title, pr_body)
self.git_provider.remove_initial_comment()
return ""
async def _get_prediction(self):
variables = copy.deepcopy(self.vars)
variables["diff"] = self.patches_diff # update diff
environment = Environment(undefined=StrictUndefined)
system_prompt = environment.from_string(settings.pr_description_prompt.system).render(variables)
user_prompt = environment.from_string(settings.pr_description_prompt.user).render(variables)
if settings.config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
model = settings.config.model
response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
system=system_prompt, user=user_prompt)
return response
def _prepare_pr_answer(self):
data = json.loads(self.prediction)
pr_body = ""
# for key, value in data.items():
# markdown_text += f"## {key}\n\n"
# markdown_text += f"{value}\n\n"
title = data['PR Title']
del data['PR Title']
for key, value in data.items():
pr_body += f"{key}:\n"
if 'walkthrough' in key.lower():
pr_body += f"{value}\n"
else:
pr_body += f"**{value}**\n\n___\n"
if settings.config.verbosity_level >= 2:
logging.info(f"title:\n{title}\n{pr_body}")
return title, pr_body

View File

@ -7,10 +7,11 @@ from jinja2 import Environment, StrictUndefined
from pr_agent.algo.ai_handler import AiHandler from pr_agent.algo.ai_handler import AiHandler
from pr_agent.algo.pr_processing import get_pr_diff from pr_agent.algo.pr_processing import get_pr_diff
from pr_agent.algo.token_handler import TokenHandler from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import convert_to_markdown from pr_agent.algo.utils import convert_to_markdown, try_fix_json
from pr_agent.config_loader import settings from pr_agent.config_loader import settings
from pr_agent.git_providers import get_git_provider from pr_agent.git_providers import get_git_provider
from pr_agent.git_providers.git_provider import get_main_pr_language from pr_agent.git_providers.git_provider import get_main_pr_language
from pr_agent.servers.help import bot_help_text, actions_help_text
class PRReviewer: class PRReviewer:
@ -33,7 +34,6 @@ class PRReviewer:
"require_tests": settings.pr_reviewer.require_tests_review, "require_tests": settings.pr_reviewer.require_tests_review,
"require_security": settings.pr_reviewer.require_security_review, "require_security": settings.pr_reviewer.require_security_review,
"require_focused": settings.pr_reviewer.require_focused_review, "require_focused": settings.pr_reviewer.require_focused_review,
'extended_code_suggestions': settings.pr_reviewer.extended_code_suggestions,
'num_code_suggestions': settings.pr_reviewer.num_code_suggestions, 'num_code_suggestions': settings.pr_reviewer.num_code_suggestions,
} }
self.token_handler = TokenHandler(self.git_provider.pr, self.token_handler = TokenHandler(self.git_provider.pr,
@ -44,7 +44,7 @@ class PRReviewer:
async def review(self): async def review(self):
logging.info('Reviewing PR...') logging.info('Reviewing PR...')
if settings.config.publish_review: if settings.config.publish_review:
self.git_provider.publish_comment("Preparing review...", is_temporary=True) self.git_provider.publish_comment("Preparing review...", is_temporary=True)
logging.info('Getting PR diff...') logging.info('Getting PR diff...')
self.patches_diff = get_pr_diff(self.git_provider, self.token_handler) self.patches_diff = get_pr_diff(self.git_provider, self.token_handler)
logging.info('Getting AI prediction...') logging.info('Getting AI prediction...')
@ -55,6 +55,9 @@ class PRReviewer:
logging.info('Pushing PR review...') logging.info('Pushing PR review...')
self.git_provider.publish_comment(pr_comment) self.git_provider.publish_comment(pr_comment)
self.git_provider.remove_initial_comment() self.git_provider.remove_initial_comment()
if settings.pr_reviewer.inline_code_comments:
logging.info('Pushing inline code comments...')
self._publish_inline_code_comments()
return "" return ""
async def _get_prediction(self): async def _get_prediction(self):
@ -69,11 +72,7 @@ class PRReviewer:
model = settings.config.model model = settings.config.model
response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2, response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
system=system_prompt, user=user_prompt) system=system_prompt, user=user_prompt)
try:
json.loads(response)
except json.decoder.JSONDecodeError:
logging.warning("Could not decode JSON")
response = {}
return response return response
def _prepare_pr_review(self) -> str: def _prepare_pr_review(self) -> str:
@ -81,8 +80,7 @@ class PRReviewer:
try: try:
data = json.loads(review) data = json.loads(review)
except json.decoder.JSONDecodeError: except json.decoder.JSONDecodeError:
logging.error("Unable to decode JSON response from AI") data = try_fix_json(review)
data = {}
# reordering for nicer display # reordering for nicer display
if 'PR Feedback' in data: if 'PR Feedback' in data:
@ -91,21 +89,33 @@ class PRReviewer:
del data['PR Feedback']['Security concerns'] del data['PR Feedback']['Security concerns']
data['PR Analysis']['Security concerns'] = val data['PR Analysis']['Security concerns'] = val
if settings.config.git_provider == 'github' and settings.pr_reviewer.inline_code_comments:
del data['PR Feedback']['Code suggestions']
markdown_text = convert_to_markdown(data) markdown_text = convert_to_markdown(data)
user = self.git_provider.get_user_id() user = self.git_provider.get_user_id()
if not self.cli_mode: if not self.cli_mode:
markdown_text += "\n### How to use\n" markdown_text += "\n### How to use\n"
if user and '[bot]' not in user: if user and '[bot]' not in user:
markdown_text += f"> Tag me in a comment '@{user}' to ask for a new review after you update the PR.\n" markdown_text += bot_help_text(user)
markdown_text += "> You can also tag me and ask any question, " \
f"for example '@{user} is the PR ready for merge?'"
else: else:
markdown_text += "> Add a comment that says 'review' to ask for a new review " \ markdown_text += actions_help_text
"after you update the PR.\n"
markdown_text += "> You can also add a comment that says 'answer QUESTION', " \
"for example 'answer is the PR ready for merge?'"
if settings.config.verbosity_level >= 2: if settings.config.verbosity_level >= 2:
logging.info(f"Markdown response:\n{markdown_text}") logging.info(f"Markdown response:\n{markdown_text}")
return markdown_text return markdown_text
def _publish_inline_code_comments(self):
review = self.prediction.strip()
try:
data = json.loads(review)
except json.decoder.JSONDecodeError:
data = try_fix_json(review)
for d in data['PR Feedback']['Code suggestions']:
relevant_file = d['relevant file'].strip()
relevant_line_in_file = d['relevant line in file'].strip()
content = d['suggestion content']
self.git_provider.publish_inline_comment(content, relevant_file, relevant_line_in_file)

View File

@ -46,7 +46,6 @@ class TestConvertToMarkdown:
def test_simple_dictionary_input(self): def test_simple_dictionary_input(self):
input_data = { input_data = {
'Main theme': 'Test', 'Main theme': 'Test',
'Description and title': 'Test description',
'Type of PR': 'Test type', 'Type of PR': 'Test type',
'Relevant tests added': 'no', 'Relevant tests added': 'no',
'Unrelated changes': 'n/a', # won't be included in the output 'Unrelated changes': 'n/a', # won't be included in the output
@ -54,14 +53,12 @@ class TestConvertToMarkdown:
'General PR suggestions': 'general suggestion...', 'General PR suggestions': 'general suggestion...',
'Code suggestions': [ 'Code suggestions': [
{ {
'Suggestion number': 1,
'Code example': { 'Code example': {
'Before': 'Code before', 'Before': 'Code before',
'After': 'Code after' 'After': 'Code after'
} }
}, },
{ {
'Suggestion number': 2,
'Code example': { 'Code example': {
'Before': 'Code before 2', 'Before': 'Code before 2',
'After': 'Code after 2' 'After': 'Code after 2'
@ -71,7 +68,6 @@ class TestConvertToMarkdown:
} }
expected_output = """\ expected_output = """\
- 🎯 **Main theme:** Test - 🎯 **Main theme:** Test
- 🔍 **Description and title:** Test description
- 📌 **Type of PR:** Test type - 📌 **Type of PR:** Test type
- 🧪 **Relevant tests added:** no - 🧪 **Relevant tests added:** no
- ✨ **Focused PR:** Yes - ✨ **Focused PR:** Yes
@ -110,7 +106,6 @@ class TestConvertToMarkdown:
def test_dictionary_input_containing_only_empty_dictionaries(self): def test_dictionary_input_containing_only_empty_dictionaries(self):
input_data = { input_data = {
'Main theme': {}, 'Main theme': {},
'Description and title': {},
'Type of PR': {}, 'Type of PR': {},
'Relevant tests added': {}, 'Relevant tests added': {},
'Unrelated changes': {}, 'Unrelated changes': {},

View File

@ -0,0 +1,83 @@
# Generated by CodiumAI
from pr_agent.algo.utils import try_fix_json
import pytest
class TestTryFixJson:
# Tests that JSON with complete 'Code suggestions' section returns expected output
def test_incomplete_code_suggestions(self):
review = '{"PR Analysis": {"Main theme": "xxx", "Type of PR": "Bug fix"}, "PR Feedback": {"General PR suggestions": "..., `xxx`...", "Code suggestions": [{"relevant file": "xxx.py", "suggestion content": "xxx [important]"}, {"suggestion number": 2, "relevant file": "yyy.py", "suggestion content": "yyy [incomp...'
expected_output = {
'PR Analysis': {
'Main theme': 'xxx',
'Type of PR': 'Bug fix'
},
'PR Feedback': {
'General PR suggestions': '..., `xxx`...',
'Code suggestions': [
{
'relevant file': 'xxx.py',
'suggestion content': 'xxx [important]'
}
]
}
}
assert try_fix_json(review) == expected_output
def test_incomplete_code_suggestions_new_line(self):
review = '{"PR Analysis": {"Main theme": "xxx", "Type of PR": "Bug fix"}, "PR Feedback": {"General PR suggestions": "..., `xxx`...", "Code suggestions": [{"relevant file": "xxx.py", "suggestion content": "xxx [important]"} \n\t, {"suggestion number": 2, "relevant file": "yyy.py", "suggestion content": "yyy [incomp...'
expected_output = {
'PR Analysis': {
'Main theme': 'xxx',
'Type of PR': 'Bug fix'
},
'PR Feedback': {
'General PR suggestions': '..., `xxx`...',
'Code suggestions': [
{
'relevant file': 'xxx.py',
'suggestion content': 'xxx [important]'
}
]
}
}
assert try_fix_json(review) == expected_output
def test_incomplete_code_suggestions_many_close_brackets(self):
review = '{"PR Analysis": {"Main theme": "xxx", "Type of PR": "Bug fix"}, "PR Feedback": {"General PR suggestions": "..., `xxx`...", "Code suggestions": [{"relevant file": "xxx.py", "suggestion content": "xxx [important]"} \n, {"suggestion number": 2, "relevant file": "yyy.py", "suggestion content": "yyy }, [}\n ,incomp.} ,..'
expected_output = {
'PR Analysis': {
'Main theme': 'xxx',
'Type of PR': 'Bug fix'
},
'PR Feedback': {
'General PR suggestions': '..., `xxx`...',
'Code suggestions': [
{
'relevant file': 'xxx.py',
'suggestion content': 'xxx [important]'
}
]
}
}
assert try_fix_json(review) == expected_output
def test_incomplete_code_suggestions_relevant_file(self):
review = '{"PR Analysis": {"Main theme": "xxx", "Type of PR": "Bug fix"}, "PR Feedback": {"General PR suggestions": "..., `xxx`...", "Code suggestions": [{"relevant file": "xxx.py", "suggestion content": "xxx [important]"}, {"suggestion number": 2, "relevant file": "yyy.p'
expected_output = {
'PR Analysis': {
'Main theme': 'xxx',
'Type of PR': 'Bug fix'
},
'PR Feedback': {
'General PR suggestions': '..., `xxx`...',
'Code suggestions': [
{
'relevant file': 'xxx.py',
'suggestion content': 'xxx [important]'
}
]
}
}
assert try_fix_json(review) == expected_output

View File

@ -41,14 +41,6 @@ class TestParseCodeSuggestion:
expected_output = "\n" # modified to expect a newline character expected_output = "\n" # modified to expect a newline character
assert parse_code_suggestion(input_data) == expected_output assert parse_code_suggestion(input_data) == expected_output
# Tests that function returns correct output when 'suggestion number' key has a non-integer value
def test_non_integer_suggestion_number(self):
input_data = {
"Suggestion number": "one",
"Description": "This is a suggestion"
}
expected_output = " **Description:** This is a suggestion\n\n"
assert parse_code_suggestion(input_data) == expected_output
# Tests that function returns correct output when 'before' or 'after' key has a non-string value # Tests that function returns correct output when 'before' or 'after' key has a non-string value
def test_non_string_before_or_after(self): def test_non_string_before_or_after(self):
@ -64,7 +56,6 @@ class TestParseCodeSuggestion:
# Tests that function returns correct output when input dictionary does not have 'code example' key # Tests that function returns correct output when input dictionary does not have 'code example' key
def test_no_code_example_key(self): def test_no_code_example_key(self):
code_suggestions = { code_suggestions = {
'suggestion number': 1,
'suggestion': 'Suggestion 1', 'suggestion': 'Suggestion 1',
'description': 'Description 1', 'description': 'Description 1',
'before': 'Before 1', 'before': 'Before 1',
@ -76,7 +67,6 @@ class TestParseCodeSuggestion:
# Tests that function returns correct output when input dictionary has 'code example' key # Tests that function returns correct output when input dictionary has 'code example' key
def test_with_code_example_key(self): def test_with_code_example_key(self):
code_suggestions = { code_suggestions = {
'suggestion number': 2,
'suggestion': 'Suggestion 2', 'suggestion': 'Suggestion 2',
'description': 'Description 2', 'description': 'Description 2',
'code example': { 'code example': {