Compare commits
24 Commits
hl/refacto
...
ok/remove_
Author | SHA1 | Date | |
---|---|---|---|
b7172df700 | |||
768bd40ad8 | |||
fa421fd169 | |||
e0ae5c945e | |||
865888e4e8 | |||
3b7cfe7bc5 | |||
262f9dddbc | |||
fa706b6e96 | |||
ff51ab0946 | |||
7884aa2348 | |||
8f3520807c | |||
2dfd34bd61 | |||
48f569bef0 | |||
a20fb9cc0c | |||
c58e1f90e7 | |||
d363f148f0 | |||
cbf96a2e67 | |||
4d87c3ec6a | |||
c13c52d733 | |||
fc309f69b9 | |||
7efb5cf74e | |||
8e200197c5 | |||
e638dc075c | |||
f4de3d2899 |
@ -1,2 +1,3 @@
|
||||
venv/
|
||||
pr_agent/settings/.secrets.toml
|
||||
pr_agent/settings/.secrets.toml
|
||||
pics/
|
@ -39,4 +39,4 @@ We use [tiktoken](https://github.com/openai/tiktoken) to tokenize the patches af
|
||||
4. If we haven't reached the max token length, add the `deleted files` to the prompt until the prompt reaches the max token length (hard stop), skip the rest of the patches.
|
||||
|
||||
### Example
|
||||

|
||||

|
52
README.md
@ -27,25 +27,25 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review PRs
|
||||
<h4>Describe:</h4>
|
||||
<div align="center">
|
||||
<p float="center">
|
||||
<img src="./pics/describe.gif" width="800">
|
||||
<img src="https://codium.ai/images/describe.gif" width="800">
|
||||
</p>
|
||||
</div>
|
||||
<h4>Review:</h4>
|
||||
<div align="center">
|
||||
<p float="center">
|
||||
<img src="./pics/review.gif" width="800">
|
||||
<img src="https://codium.ai/images/review.gif" width="800">
|
||||
</p>
|
||||
</div>
|
||||
<h4>Ask:</h4>
|
||||
<div align="center">
|
||||
<p float="center">
|
||||
<img src="./pics/ask.gif" width="800">
|
||||
<img src="https://codium.ai/images/ask.gif" width="800">
|
||||
</p>
|
||||
</div>
|
||||
<h4>Improve:</h4>
|
||||
<div align="center">
|
||||
<p float="center">
|
||||
<img src="./pics/improve.gif" width="800">
|
||||
<img src="https://codium.ai/images/improve.gif" width="800">
|
||||
</p>
|
||||
</div>
|
||||
<div align="left">
|
||||
@ -62,30 +62,30 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review PRs
|
||||
|
||||
## Live demo
|
||||
|
||||
Experience GPT-4 powered PR review on your public GitHub repository with our hosted PR-Agent. To try it, just mention `@CodiumAI-Agent` in any PR comment! The agent will generate a PR review in response.
|
||||
Experience GPT-4 powered PR review on your public GitHub repository with our hosted PR-Agent. To try it, just mention `@CodiumAI-Agent` and add the desired command in any PR comment! The agent will generate a response based on your command.
|
||||
|
||||

|
||||

|
||||
|
||||
To set up your own PR-Agent, see the [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 | ✓ | | |
|
||||
| | | 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: | | |
|
||||
| | Improve Code | :white_check_mark: | :white_check_mark: | |
|
||||
| | | | | |
|
||||
| USAGE | CLI | ✓ | ✓ | ✓ |
|
||||
| | Tagging bot | ✓ | ✓ | |
|
||||
| | Actions | ✓ | | |
|
||||
| USAGE | CLI | :white_check_mark: | :white_check_mark: | :white_check_mark: |
|
||||
| | Tagging bot | :white_check_mark: | :white_check_mark: | |
|
||||
| | Actions | :white_check_mark: | | |
|
||||
| | | | | |
|
||||
| CORE | PR compression | ✓ | ✓ | ✓ |
|
||||
| | Repo language prioritization | ✓ | ✓ | ✓ |
|
||||
| | Adaptive and token-aware<br />file patch fitting | ✓ | ✓ | ✓ |
|
||||
| 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: |
|
||||
|
||||
Examples for invoking the different tools via the [CLI](#quickstart):
|
||||
- **Review**: python cli.py --pr-url=<pr_url> review
|
||||
@ -95,7 +95,7 @@ Examples for invoking the different tools via the [CLI](#quickstart):
|
||||
|
||||
"<pr_url>" is the url of the relevant PR (for example: https://github.com/Codium-ai/pr-agent/pull/50).
|
||||
|
||||
In the [configuration](./CONFIGURATION.md) file you can select your git provider (Github, Gitlab, Bitbucket), and further configure the different tools.
|
||||
In the [configuration](./CONFIGURATION.md) file you can select your git provider (GitHub, Gitlab, Bitbucket), and further configure the different tools.
|
||||
|
||||
## Quickstart
|
||||
|
||||
@ -111,25 +111,25 @@ There are several ways to use PR-Agent. Let's start with the simplest one:
|
||||
Here are several ways to install and run PR-Agent:
|
||||
|
||||
- [Method 1: Use Docker image (no installation required)](INSTALL.md#method-1-use-docker-image-no-installation-required)
|
||||
- [Method 2: Run as a Github Action](INSTALL.md#method-2-run-as-a-github-action)
|
||||
- [Method 2: Run as a GitHub Action](INSTALL.md#method-2-run-as-a-github-action)
|
||||
- [Method 3: Run from source](INSTALL.md#method-3-run-from-source)
|
||||
- [Method 4: Run as a polling server](INSTALL.md#method-4-run-as-a-polling-server)
|
||||
- Request reviews by tagging your Github user on a PR
|
||||
- [Method 5: Run as a Github App](INSTALL.md#method-5-run-as-a-github-app)
|
||||
- Request reviews by tagging your GitHub user on a PR
|
||||
- [Method 5: Run as a GitHub App](INSTALL.md#method-5-run-as-a-github-app)
|
||||
- Allowing you to automate the review process on your private or public repositories
|
||||
|
||||
## Usage and Tools
|
||||
|
||||
**PR-Agent** provides four types of interactions ("tools"): `"PR Reviewer"`, `"PR Q&A"`, `"PR Description"` and `"PR Code Sueggestions"`.
|
||||
|
||||
- The "PR Reviewer" tool automatically analyzes PRs, and provides different types of feedback.
|
||||
- The "PR Ask" tool answers free-text questions about the PR.
|
||||
- The "PR Reviewer" tool automatically analyzes PRs, and provides various types of feedback.
|
||||
- The "PR Q&A" tool answers free-text questions about the PR.
|
||||
- The "PR Description" tool automatically sets the PR Title and body.
|
||||
- The "PR Code Suggestion" tool provide inline code suggestions for the PR that can be applied and committed.
|
||||
|
||||
## How it works
|
||||
|
||||

|
||||

|
||||
|
||||
Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more details on how we convert a code diff to a manageable LLM prompt
|
||||
|
||||
|
BIN
pics/ask.gif
Before Width: | Height: | Size: 3.8 MiB |
Before Width: | Height: | Size: 13 MiB |
Before Width: | Height: | Size: 346 KiB |
BIN
pics/improve.gif
Before Width: | Height: | Size: 9.3 MiB |
Before Width: | Height: | Size: 260 KiB |
Before Width: | Height: | Size: 1.4 MiB |
Before Width: | Height: | Size: 316 KiB |
Before Width: | Height: | Size: 335 KiB |
Before Width: | Height: | Size: 193 KiB |
Before Width: | Height: | Size: 161 KiB |
Before Width: | Height: | Size: 185 KiB |
Before Width: | Height: | Size: 162 KiB |
BIN
pics/review.gif
Before Width: | Height: | Size: 20 MiB |
@ -61,18 +61,24 @@ def parse_code_suggestion(code_suggestions: dict) -> str:
|
||||
return markdown_text
|
||||
|
||||
|
||||
def try_fix_json(review, max_iter=10):
|
||||
def try_fix_json(review, max_iter=10, code_suggestions=False):
|
||||
if review.endswith("}"):
|
||||
return fix_json_escape_char(review)
|
||||
# Try to fix JSON if it is broken/incomplete: parse until the last valid code suggestion
|
||||
data = {}
|
||||
if code_suggestions:
|
||||
closing_bracket = "]}"
|
||||
else:
|
||||
closing_bracket = "]}}"
|
||||
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] + "]}}")
|
||||
data = json.loads(review[:last_code_suggestion_ind] + closing_bracket)
|
||||
valid_json = True
|
||||
review = review[:last_code_suggestion_ind].strip() + "]}}"
|
||||
review = review[:last_code_suggestion_ind].strip() + closing_bracket
|
||||
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
|
||||
@ -82,3 +88,17 @@ def try_fix_json(review, max_iter=10):
|
||||
logging.error("Unable to decode JSON response from AI")
|
||||
data = {}
|
||||
return data
|
||||
|
||||
def fix_json_escape_char(json_message=None):
|
||||
result = None
|
||||
try:
|
||||
result = json.loads(json_message)
|
||||
except Exception as e:
|
||||
# Find the offending character index:
|
||||
idx_to_replace = int(str(e).split(' ')[-1].replace(')', ''))
|
||||
# Remove the offending character:
|
||||
json_message = list(json_message)
|
||||
json_message[idx_to_replace] = ' '
|
||||
new_message = ''.join(json_message)
|
||||
return fix_JSON(json_message=new_message)
|
||||
return result
|
@ -5,6 +5,7 @@ import os
|
||||
|
||||
from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
|
||||
from pr_agent.tools.pr_description import PRDescription
|
||||
from pr_agent.tools.pr_information_from_user import PRInformationFromUser
|
||||
from pr_agent.tools.pr_questions import PRQuestions
|
||||
from pr_agent.tools.pr_reviewer import PRReviewer
|
||||
|
||||
@ -13,10 +14,10 @@ def run():
|
||||
parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage="""\
|
||||
Usage: cli.py --pr-url <URL on supported git hosting service> <command> [<args>].
|
||||
For example:
|
||||
- cli.py --pr-url xxx review
|
||||
- cli.py --pr-url xxx describe
|
||||
- cli.py --pr-url xxx improve
|
||||
- cli.py --pr-url xxx ask "write me a poem about this PR"
|
||||
- cli.py --pr-url=... review
|
||||
- cli.py --pr-url=... describe
|
||||
- cli.py --pr-url=... improve
|
||||
- cli.py --pr-url=... ask "write me a poem about this PR"
|
||||
|
||||
Supported commands:
|
||||
review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
|
||||
@ -28,7 +29,8 @@ improve / improve_code - Suggest improvements to the code in the PR as pull requ
|
||||
parser.add_argument('command', type=str, help='The', choices=['review', 'review_pr',
|
||||
'ask', 'ask_question',
|
||||
'describe', 'describe_pr',
|
||||
'improve', 'improve_code'], default='review')
|
||||
'improve', 'improve_code',
|
||||
'user_questions'], default='review')
|
||||
parser.add_argument('rest', nargs=argparse.REMAINDER, default=[])
|
||||
args = parser.parse_args()
|
||||
logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
|
||||
@ -54,6 +56,10 @@ improve / improve_code - Suggest improvements to the code in the PR as pull requ
|
||||
print(f"Reviewing PR: {args.pr_url}")
|
||||
reviewer = PRReviewer(args.pr_url, cli_mode=True)
|
||||
asyncio.run(reviewer.review())
|
||||
elif command in ['user_questions']:
|
||||
print(f"Asking the PR author questions: {args.pr_url}")
|
||||
reviewer = PRInformationFromUser(args.pr_url)
|
||||
asyncio.run(reviewer.generate_questions())
|
||||
else:
|
||||
print(f"Unknown command: {command}")
|
||||
parser.print_help()
|
||||
|
@ -13,6 +13,7 @@ settings = Dynaconf(
|
||||
"settings/pr_questions_prompts.toml",
|
||||
"settings/pr_description_prompts.toml",
|
||||
"settings/pr_code_suggestions_prompts.toml",
|
||||
"settings/pr_information_from_user_prompts.toml",
|
||||
"settings_prod/.secrets.toml"
|
||||
]]
|
||||
)
|
||||
|
@ -61,9 +61,6 @@ class BitbucketProvider:
|
||||
def get_title(self):
|
||||
return self.pr.title
|
||||
|
||||
def get_description(self):
|
||||
return self.pr.body
|
||||
|
||||
def get_languages(self):
|
||||
languages = {self._get_repo().get_data('language'): 0}
|
||||
return languages
|
||||
|
@ -134,9 +134,6 @@ class GithubProvider(GitProvider):
|
||||
def get_title(self):
|
||||
return self.pr.title
|
||||
|
||||
def get_description(self):
|
||||
return self.pr.body
|
||||
|
||||
def get_languages(self):
|
||||
languages = self._get_repo().get_languages()
|
||||
return languages
|
||||
|
@ -28,6 +28,8 @@ class GitLabProvider(GitProvider):
|
||||
self.diff_files = None
|
||||
self.temp_comments = []
|
||||
self._set_merge_request(merge_request_url)
|
||||
self.RE_HUNK_HEADER = re.compile(
|
||||
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
|
||||
|
||||
@property
|
||||
def pr(self):
|
||||
@ -84,25 +86,26 @@ class GitLabProvider(GitProvider):
|
||||
self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
|
||||
edit_type, found, source_line_no, target_file, target_line_no = self.search_line(relevant_file,
|
||||
relevant_line_in_file)
|
||||
self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
|
||||
target_file, target_line_no)
|
||||
|
||||
def send_inline_comment(self, body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
|
||||
target_file, target_line_no):
|
||||
if not found:
|
||||
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}
|
||||
'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
|
||||
pos_obj['old_line'] = source_line_no - 1
|
||||
elif edit_type == 'addition':
|
||||
pos_obj['new_line'] = position
|
||||
pos_obj['new_line'] = target_line_no - 1
|
||||
else:
|
||||
pos_obj['new_line'] = position
|
||||
pos_obj['old_line'] = position
|
||||
pos_obj['new_line'] = target_line_no - 1
|
||||
pos_obj['old_line'] = source_line_no - 1
|
||||
self.mr.discussions.create({'body': body,
|
||||
'position': pos_obj})
|
||||
|
||||
@ -110,47 +113,66 @@ class GitLabProvider(GitProvider):
|
||||
relevant_file: str,
|
||||
relevant_lines_start: int,
|
||||
relevant_lines_end: int):
|
||||
raise "not implemented yet for gitlab"
|
||||
self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
|
||||
target_file = None
|
||||
for file in self.diff_files:
|
||||
if file.filename == relevant_file:
|
||||
if file.filename == relevant_file:
|
||||
target_file = file
|
||||
break
|
||||
range = relevant_lines_end - relevant_lines_start + 1
|
||||
body = body.replace('```suggestion', f'```suggestion:-0+{range}')
|
||||
|
||||
lines = target_file.head_file.splitlines()
|
||||
relevant_line_in_file = lines[relevant_lines_start - 1]
|
||||
edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(target_file, relevant_line_in_file)
|
||||
self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
|
||||
target_file, target_line_no)
|
||||
|
||||
def search_line(self, relevant_file, relevant_line_in_file):
|
||||
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
|
||||
edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(file,
|
||||
relevant_line_in_file)
|
||||
return edit_type, found, source_line_no, target_file, target_line_no
|
||||
|
||||
def find_in_file(self, file, relevant_line_in_file):
|
||||
edit_type = 'context'
|
||||
source_line_no = 0
|
||||
target_line_no = 0
|
||||
found = False
|
||||
target_file = file
|
||||
patch = file.patch
|
||||
patch_lines = patch.splitlines()
|
||||
for i, line in enumerate(patch_lines):
|
||||
if line.startswith('@@'):
|
||||
match = self.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):
|
||||
@ -171,9 +193,6 @@ class GitLabProvider(GitProvider):
|
||||
def get_title(self):
|
||||
return self.mr.title
|
||||
|
||||
def get_description(self):
|
||||
return self.mr.description
|
||||
|
||||
def get_languages(self):
|
||||
languages = self.gl.projects.get(self.id_project).languages()
|
||||
return languages
|
||||
|
@ -1,7 +1,7 @@
|
||||
[config]
|
||||
model="gpt-4-0613"
|
||||
git_provider="github"
|
||||
publish_review=true
|
||||
publish_output=true
|
||||
verbosity_level=0 # 0,1,2
|
||||
|
||||
[pr_reviewer]
|
||||
@ -11,6 +11,9 @@ require_security_review=true
|
||||
num_code_suggestions=3
|
||||
inline_code_comments = true
|
||||
|
||||
[pr_description]
|
||||
publish_description_as_comment=false
|
||||
|
||||
[pr_questions]
|
||||
|
||||
[pr_code_suggestions]
|
||||
|
33
pr_agent/settings/pr_information_from_user_prompts.toml
Normal file
@ -0,0 +1,33 @@
|
||||
[pr_information_from_user_prompt]
|
||||
system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
|
||||
Given the PR Info and the PR Git Diff, generate 4 questions about the PR for the PR author.
|
||||
The goal of the questions is to help the language model understand the PR better, so the questions should be insightful, informative, non-trivial, and relevant to the PR.
|
||||
Prefer yes\\no or multiple choice questions. If you have to ask open-ended questions, make sure they are not too difficult, and can be answered in a sentence or two.
|
||||
|
||||
|
||||
Example output:
|
||||
'
|
||||
Questions to better understand the PR:
|
||||
1. ...
|
||||
2. ...
|
||||
...
|
||||
"""
|
||||
|
||||
user="""PR Info:
|
||||
Title: '{{title}}'
|
||||
Branch: '{{branch}}'
|
||||
Description: '{{description}}'
|
||||
{%- 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:
|
||||
"""
|
@ -2,8 +2,11 @@
|
||||
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).
|
||||
- Provide up to {{ num_code_suggestions }} code suggestions.
|
||||
{%- if num_code_suggestions > 0 %}
|
||||
- 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.
|
||||
- Suggestions should focus on improving the new added code lines.
|
||||
- Make sure not to provide suggestions repeating modifications already implemented in the new PR code (the '+' lines).
|
||||
{%- endif %}
|
||||
|
||||
You must use the following JSON schema to format your answer:
|
||||
```json
|
||||
@ -35,6 +38,7 @@ You must use the following JSON schema to format your answer:
|
||||
"type": "string",
|
||||
"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."
|
||||
},
|
||||
{%- if num_code_suggestions > 0 %}
|
||||
"Code suggestions": {
|
||||
"type": "array",
|
||||
"maxItems": {{ num_code_suggestions }},
|
||||
@ -54,6 +58,7 @@ You must use the following JSON schema to format your answer:
|
||||
}
|
||||
}
|
||||
},
|
||||
{%- endif %}
|
||||
{%- if require_security %}
|
||||
"Security concerns": {
|
||||
"type": "string",
|
||||
@ -82,6 +87,7 @@ Example output:
|
||||
"PR Feedback":
|
||||
{
|
||||
"General PR suggestions": "..., `xxx`...",
|
||||
{%- if num_code_suggestions > 0 %}
|
||||
"Code suggestions": [
|
||||
{
|
||||
"relevant file": "directory/xxx.py",
|
||||
@ -90,6 +96,7 @@ Example output:
|
||||
},
|
||||
...
|
||||
]
|
||||
{%- endif %}
|
||||
{%- if require_security %},
|
||||
"Security concerns": "No, because ..."
|
||||
{%- endif %}
|
||||
|
@ -10,7 +10,7 @@ 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 import get_git_provider, BitbucketProvider
|
||||
from pr_agent.git_providers.git_provider import get_main_pr_language
|
||||
|
||||
|
||||
@ -39,10 +39,10 @@ class PRCodeSuggestions:
|
||||
settings.pr_code_suggestions_prompt.user)
|
||||
|
||||
async def suggest(self):
|
||||
assert type(self.git_provider) == GithubProvider, "Only Github is supported for now"
|
||||
assert type(self.git_provider) != BitbucketProvider, "Bitbucket is not supported for now"
|
||||
|
||||
logging.info('Generating code suggestions for PR...')
|
||||
if settings.config.publish_review:
|
||||
if settings.config.publish_output:
|
||||
self.git_provider.publish_comment("Preparing review...", is_temporary=True)
|
||||
logging.info('Getting PR diff...')
|
||||
|
||||
@ -56,7 +56,7 @@ class PRCodeSuggestions:
|
||||
self.prediction = await self._get_prediction()
|
||||
logging.info('Preparing PR review...')
|
||||
data = self._prepare_pr_code_suggestions()
|
||||
if settings.config.publish_review:
|
||||
if settings.config.publish_output:
|
||||
logging.info('Pushing PR review...')
|
||||
self.git_provider.remove_initial_comment()
|
||||
logging.info('Pushing inline code comments...')
|
||||
@ -86,7 +86,7 @@ class PRCodeSuggestions:
|
||||
except json.decoder.JSONDecodeError:
|
||||
if settings.config.verbosity_level >= 2:
|
||||
logging.info(f"Could not parse json response: {review}")
|
||||
data = try_fix_json(review)
|
||||
data = try_fix_json(review, code_suggestions=True)
|
||||
return data
|
||||
|
||||
def push_inline_code_suggestions(self, data):
|
||||
|
@ -23,7 +23,7 @@ class PRDescription:
|
||||
self.vars = {
|
||||
"title": self.git_provider.pr.title,
|
||||
"branch": self.git_provider.get_pr_branch(),
|
||||
"description": self.git_provider.get_description(),
|
||||
"description": self.git_provider.get_pr_description(),
|
||||
"language": self.main_pr_language,
|
||||
"diff": "", # empty diff for initial calculation
|
||||
}
|
||||
@ -36,17 +36,20 @@ class PRDescription:
|
||||
|
||||
async def describe(self):
|
||||
logging.info('Generating a PR description...')
|
||||
if settings.config.publish_review:
|
||||
if settings.config.publish_output:
|
||||
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:
|
||||
pr_title, pr_body, markdown_text = self._prepare_pr_answer()
|
||||
if settings.config.publish_output:
|
||||
logging.info('Pushing answer...')
|
||||
self.git_provider.publish_description(pr_title, pr_body)
|
||||
if settings.pr_description.publish_description_as_comment:
|
||||
self.git_provider.publish_comment(markdown_text)
|
||||
else:
|
||||
self.git_provider.publish_description(pr_title, pr_body)
|
||||
self.git_provider.remove_initial_comment()
|
||||
return ""
|
||||
|
||||
@ -66,10 +69,11 @@ class PRDescription:
|
||||
|
||||
def _prepare_pr_answer(self):
|
||||
data = json.loads(self.prediction)
|
||||
markdown_text = ""
|
||||
for key, value in data.items():
|
||||
markdown_text += f"## {key}\n\n"
|
||||
markdown_text += f"{value}\n\n"
|
||||
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():
|
||||
@ -80,4 +84,4 @@ class PRDescription:
|
||||
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
|
||||
return title, pr_body, markdown_text
|
||||
|
71
pr_agent/tools/pr_information_from_user.py
Normal file
@ -0,0 +1,71 @@
|
||||
import copy
|
||||
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.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 PRInformationFromUser:
|
||||
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_pr_description(),
|
||||
"language": self.main_pr_language,
|
||||
"diff": "", # empty diff for initial calculation
|
||||
}
|
||||
self.token_handler = TokenHandler(self.git_provider.pr,
|
||||
self.vars,
|
||||
settings.pr_information_from_user_prompt.system,
|
||||
settings.pr_information_from_user_prompt.user)
|
||||
self.patches_diff = None
|
||||
self.prediction = None
|
||||
|
||||
async def generate_questions(self):
|
||||
logging.info('Generating question to the user...')
|
||||
if settings.config.publish_output:
|
||||
self.git_provider.publish_comment("Preparing answer...", 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 questions...')
|
||||
pr_comment = self._prepare_pr_answer()
|
||||
if settings.config.publish_output:
|
||||
logging.info('Pushing questions...')
|
||||
self.git_provider.publish_comment(pr_comment)
|
||||
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_information_from_user_prompt.system).render(variables)
|
||||
user_prompt = environment.from_string(settings.pr_information_from_user_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) -> str:
|
||||
model_output = self.prediction.strip()
|
||||
if settings.config.verbosity_level >= 2:
|
||||
logging.info(f"answer_str:\n{model_output}")
|
||||
answer_str = f"{model_output}\n\n Please respond to the question above in the following format:\n\n" + \
|
||||
f"/answer <question_id> <answer>\n\n" + f"Example:\n'\n/answer\n1. Yes, because ...\n2. No, because ...\n'"
|
||||
return answer_str
|
@ -22,7 +22,7 @@ class PRQuestions:
|
||||
self.vars = {
|
||||
"title": self.git_provider.pr.title,
|
||||
"branch": self.git_provider.get_pr_branch(),
|
||||
"description": self.git_provider.get_description(),
|
||||
"description": self.git_provider.get_pr_description(),
|
||||
"language": self.main_pr_language,
|
||||
"diff": "", # empty diff for initial calculation
|
||||
"questions": self.question_str,
|
||||
@ -36,7 +36,7 @@ class PRQuestions:
|
||||
|
||||
async def answer(self):
|
||||
logging.info('Answering a PR question...')
|
||||
if settings.config.publish_review:
|
||||
if settings.config.publish_output:
|
||||
self.git_provider.publish_comment("Preparing answer...", is_temporary=True)
|
||||
logging.info('Getting PR diff...')
|
||||
self.patches_diff = get_pr_diff(self.git_provider, self.token_handler)
|
||||
@ -44,7 +44,7 @@ class PRQuestions:
|
||||
self.prediction = await self._get_prediction()
|
||||
logging.info('Preparing answer...')
|
||||
pr_comment = self._prepare_pr_answer()
|
||||
if settings.config.publish_review:
|
||||
if settings.config.publish_output:
|
||||
logging.info('Pushing answer...')
|
||||
self.git_provider.publish_comment(pr_comment)
|
||||
self.git_provider.remove_initial_comment()
|
||||
|
@ -43,7 +43,7 @@ class PRReviewer:
|
||||
|
||||
async def review(self):
|
||||
logging.info('Reviewing PR...')
|
||||
if settings.config.publish_review:
|
||||
if settings.config.publish_output:
|
||||
self.git_provider.publish_comment("Preparing review...", is_temporary=True)
|
||||
logging.info('Getting PR diff...')
|
||||
self.patches_diff = get_pr_diff(self.git_provider, self.token_handler)
|
||||
@ -51,7 +51,7 @@ class PRReviewer:
|
||||
self.prediction = await self._get_prediction()
|
||||
logging.info('Preparing PR review...')
|
||||
pr_comment = self._prepare_pr_review()
|
||||
if settings.config.publish_review:
|
||||
if settings.config.publish_output:
|
||||
logging.info('Pushing PR review...')
|
||||
self.git_provider.publish_comment(pr_comment)
|
||||
self.git_provider.remove_initial_comment()
|
||||
@ -89,7 +89,9 @@ class PRReviewer:
|
||||
del data['PR Feedback']['Security concerns']
|
||||
data['PR Analysis']['Security concerns'] = val
|
||||
|
||||
if settings.config.git_provider == 'github' and settings.pr_reviewer.inline_code_comments:
|
||||
if settings.config.git_provider == 'github' and \
|
||||
settings.pr_reviewer.inline_code_comments and \
|
||||
'Code suggestions' in data['PR Feedback']:
|
||||
del data['PR Feedback']['Code suggestions']
|
||||
|
||||
markdown_text = convert_to_markdown(data)
|
||||
@ -107,6 +109,9 @@ class PRReviewer:
|
||||
return markdown_text
|
||||
|
||||
def _publish_inline_code_comments(self):
|
||||
if settings.pr_reviewer.num_code_suggestions == 0:
|
||||
return
|
||||
|
||||
review = self.prediction.strip()
|
||||
try:
|
||||
data = json.loads(review)
|
||||
|