xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-02 03:40:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

enable ai_metadata

Browse Source
This commit is contained in:
mrT23
2024-09-07 17:25:05 +03:00
parent 24f7e8622f
commit 8706f643ef
32 changed files with 338 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/docs/core-abilities/code_oriented_yaml.md Normal file
View File

@ -0,0 +1,2 @@
## Overview
TBD

47
docs/docs/core-abilities/compression_strategy.md Normal file
View File

@ -0,0 +1,47 @@
## Overview - PR Compression Strategy
There are two scenarios:
1. The PR is small enough to fit in a single prompt (including system and user prompt)
2. The PR is too large to fit in a single prompt (including system and user prompt)
For both scenarios, we first use the following strategy
#### Repo language prioritization strategy
We prioritize the languages of the repo based on the following criteria:
1. Exclude binary files and non code files (e.g. images, pdfs, etc)
2. Given the main languages used in the repo
3. We sort the PR files by the most common languages in the repo (in descending order):
* ```[[file.py, file2.py],[file3.js, file4.jsx],[readme.md]]```
### Small PR
In this case, we can fit the entire PR in a single prompt:
1. Exclude binary files and non code files (e.g. images, pdfs, etc)
2. We Expand the surrounding context of each patch to 3 lines above and below the patch
### Large PR
#### Motivation
Pull Requests can be very long and contain a lot of information with varying degree of relevance to the pr-agent.
We want to be able to pack as much information as possible in a single LMM prompt, while keeping the information relevant to the pr-agent.
#### Compression strategy
We prioritize additions over deletions:
- Combine all deleted files into a single list (`deleted files`)
- File patches are a list of hunks, remove all hunks of type deletion-only from the hunks in the file patch
#### Adaptive and token-aware file patch fitting
We use [tiktoken](https://github.com/openai/tiktoken) to tokenize the patches after the modifications described above, and we use the following strategy to fit the patches into the prompt:
1. Within each language we sort the files by the number of tokens in the file (in descending order):
- ```[[file2.py, file.py],[file4.jsx, file3.js],[readme.md]]```
2. Iterate through the patches in the order described above
3. Add the patches to the prompt until the prompt reaches a certain buffer from the max token length
4. If there are still patches left, add the remaining patches as a list called `other modified files` to the prompt until the prompt reaches the max token length (hard stop), skip the rest of the patches.
5. 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
![Core Abilities](https://codium.ai/images/git_patch_logic.png){width=768}

2
docs/docs/core-abilities/dynamic_context.md Normal file
View File

@ -0,0 +1,2 @@
## Overview - Asymmetric and dynamic PR context
TBD

2
docs/docs/core-abilities/impact_evaluation.md Normal file
View File

@ -0,0 +1,2 @@
## Overview - Impact evaluation 💎
TBD

62
docs/docs/core-abilities/index.md
View File

@ -1,52 +1,10 @@
## PR Compression Strategy
There are two scenarios:
1. The PR is small enough to fit in a single prompt (including system and user prompt)
2. The PR is too large to fit in a single prompt (including system and user prompt)
For both scenarios, we first use the following strategy
#### Repo language prioritization strategy
We prioritize the languages of the repo based on the following criteria:
1. Exclude binary files and non code files (e.g. images, pdfs, etc)
2. Given the main languages used in the repo
3. We sort the PR files by the most common languages in the repo (in descending order):
* ```[[file.py, file2.py],[file3.js, file4.jsx],[readme.md]]```
### Small PR
In this case, we can fit the entire PR in a single prompt:
1. Exclude binary files and non code files (e.g. images, pdfs, etc)
2. We Expand the surrounding context of each patch to 3 lines above and below the patch
### Large PR
#### Motivation
Pull Requests can be very long and contain a lot of information with varying degree of relevance to the pr-agent.
We want to be able to pack as much information as possible in a single LMM prompt, while keeping the information relevant to the pr-agent.
#### Compression strategy
We prioritize additions over deletions:
- Combine all deleted files into a single list (`deleted files`)
- File patches are a list of hunks, remove all hunks of type deletion-only from the hunks in the file patch
#### Adaptive and token-aware file patch fitting
We use [tiktoken](https://github.com/openai/tiktoken) to tokenize the patches after the modifications described above, and we use the following strategy to fit the patches into the prompt:
1. Within each language we sort the files by the number of tokens in the file (in descending order):
- ```[[file2.py, file.py],[file4.jsx, file3.js],[readme.md]]```
2. Iterate through the patches in the order described above
3. Add the patches to the prompt until the prompt reaches a certain buffer from the max token length
4. If there are still patches left, add the remaining patches as a list called `other modified files` to the prompt until the prompt reaches the max token length (hard stop), skip the rest of the patches.
5. 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
![Core Abilities](https://codium.ai/images/git_patch_logic.png){width=768}
## YAML Prompting
TBD
## Static Code Analysis 💎
TBD
# Core Abilities
PR-Agent utilizes a variety of core abilities to provide a comprehensive and efficient code review experience. These abilities include:
- [Local and global metadata](core-abilities/metadata.md)
- [Line localization](core-abilities/line_localization.md)
- [Dynamic context](core-abilities/dynamic_context.md)
- [Self-reflection](core-abilities/self_reflection.md)
- [Interactivity](core-abilities/interactivity.md)
- [Compression strategy](core-abilities/compression_strategy.md)
- [Code-oriented YAML](core-abilities/code_oriented_yaml.md)
- [Static code analysis](core-abilities/static_code_analysis.md)

2
docs/docs/core-abilities/interactivity.md Normal file
View File

@ -0,0 +1,2 @@
## Interactive invocation 💎
TBD

2
docs/docs/core-abilities/line_localization.md Normal file
View File

@ -0,0 +1,2 @@
## Overview - Line localization
TBD

56
docs/docs/core-abilities/metadata.md Normal file
View File

@ -0,0 +1,56 @@
## Overview - Local and global metadata injection with multi-stage analysis
(1)
PR-Agent initially retrieves for each PR the following data:
- PR title and branch name
- PR original description
- Commit messages history
- PR diff patches, in [hunk diff](https://loicpefferkorn.net/2014/02/diff-files-what-are-hunks-and-how-to-extract-them/) format
- The entire content of the files that were modified in the PR
In addition, PR-Agent is able to receive from the user additional data, like [`extra_instructions` and `best practices`](https://pr-agent-docs.codium.ai/tools/improve/#extra-instructions-and-best-practices) that can be used to enhance the PR analysis.
(2)
By default, the first command that PR-Agent executes is [`describe`](https://pr-agent-docs.codium.ai/tools/describe/), which generates three types of outputs:
- PR Type (e.g. bug fix, feature, refactor, etc)
- PR Description - a bullet points summary of the PR
- Changes walkthrough - going file-by-file, PR-Agent generate a one-line summary and longer bullet points summary of the changes in the file
These AI-generated outputs are now considered part of the PR metadata, and can be used in subsequent commands like `review` and `improve`.
This effectively enables chain-of-thought analysis, without doing any additional API calls which will cost time and money.
(3)
For example, when generating code suggestions for different files, PR-Agent can inject the AI-generated file summary in the prompt:
```
## File: 'src/file1.py'
### AI-generated file summary:
- edited function `func1` that does X
- Removed function `func2` that was not used
- ....
@@ ... @@ def func1():
__new hunk__
11 unchanged code line0 in the PR
12 unchanged code line1 in the PR
13 +new code line2 added in the PR
14 unchanged code line3 in the PR
__old hunk__
unchanged code line0
unchanged code line1
-old code line2 removed in the PR
unchanged code line3
@@ ... @@ def func2():
__new hunk__
...
__old hunk__
...
```
(4) The entire PR files that were retrieved are used to expand and enhance the PR context (see [Dynamic Context](https://pr-agent-docs.codium.ai/core-abilities/dynamic-context/)).
(5) All the metadata described above represent several level of analysis - from hunk level, to file level, to PR level, and enables PR-Agent AI models to generate more accurate and relevant suggestions.
## Example result for prompt with metadata injection
TBD

2
docs/docs/core-abilities/self_reflection.md Normal file
View File

@ -0,0 +1,2 @@
## Overview - Self-reflection and suggestion cleaning and re-ranking
TBD

2
docs/docs/core-abilities/static_code_analysis.md Normal file
View File

@ -0,0 +1,2 @@
## Overview - Static Code Analysis 💎
TBD

11
docs/mkdocs.yml
View File

@ -41,7 +41,16 @@ nav:
- 💎 Custom Prompt: 'tools/custom_prompt.md'
- 💎 CI Feedback: 'tools/ci_feedback.md'
- 💎 Similar Code: 'tools/similar_code.md'
- Core Abilities: 'core-abilities/index.md'
- Core Abilities:
- 'core-abilities/index.md'
- Local and global metadata: 'core-abilities/metadata.md'
- Line localization: 'core-abilities/line_localization.md'
- Dynamic context: 'core-abilities/dynamic_context.md'
- Self-reflection: 'core-abilities/self_reflection.md'
- Interactivity: 'core-abilities/interactivity.md'
- Compression strategy: 'core-abilities/compression_strategy.md'
- Code-oriented YAML: 'core-abilities/code_oriented_yaml.md'
- Static code analysis: 'core-abilities/static_code_analysis.md'
- Chrome Extension:
- PR-Agent Chrome Extension: 'chrome-extension/index.md'
- Features: 'chrome-extension/features.md'

4
pr_agent/algo/git_patch_processing.py
View File

@ -243,7 +243,7 @@ __old hunk__
if hasattr(file, 'edit_type') and file.edit_type == EDIT_TYPE.DELETED:
return f"\n\n## file '{file.filename.strip()}' was deleted\n"
patch_with_lines_str = f"\n\n## file: '{file.filename.strip()}'\n"
patch_with_lines_str = f"\n\n## File: '{file.filename.strip()}'\n"
patch_lines = patch.splitlines()
RE_HUNK_HEADER = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
@ -319,7 +319,7 @@ __old hunk__
def extract_hunk_lines_from_patch(patch: str, file_name, line_start, line_end, side) -> tuple[str, str]:
patch_with_lines_str = f"\n\n## file: '{file_name.strip()}'\n\n"
patch_with_lines_str = f"\n\n## File: '{file_name.strip()}'\n\n"
selected_lines = ""
patch_lines = patch.splitlines()
RE_HUNK_HEADER = re.compile(

43
pr_agent/algo/pr_processing.py
View File

@ -200,6 +200,10 @@ def pr_generate_extended_diff(pr_languages: list,
if add_line_numbers_to_hunks:
full_extended_patch = convert_to_hunks_with_lines_numbers(extended_patch, file)
# add AI-summary metadata to the patch
if file.ai_file_summary and get_settings().get("config.enable_ai_metadata", False):
full_extended_patch = add_ai_summary_top_patch(file, full_extended_patch)
patch_tokens = token_handler.count_tokens(full_extended_patch)
file.tokens = patch_tokens
total_tokens += patch_tokens
@ -239,6 +243,10 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
if convert_hunks_to_line_numbers:
patch = convert_to_hunks_with_lines_numbers(patch, file)
## add AI-summary metadata to the patch (disabled, since we are in the compressed diff)
# if file.ai_file_summary and get_settings().config.get('config.is_auto_command', False):
# patch = add_ai_summary_top_patch(file, patch)
new_patch_tokens = token_handler.count_tokens(patch)
file_dict[file.filename] = {'patch': patch, 'tokens': new_patch_tokens, 'edit_type': file.edit_type}
@ -304,7 +312,7 @@ def generate_full_patch(convert_hunks_to_line_numbers, file_dict, max_tokens_mod
if patch:
if not convert_hunks_to_line_numbers:
patch_final = f"\n\n## file: '{filename.strip()}\n\n{patch.strip()}\n'"
patch_final = f"\n\n## File: '{filename.strip()}\n\n{patch.strip()}\n'"
else:
patch_final = "\n\n" + patch.strip()
patches.append(patch_final)
@ -432,6 +440,9 @@ def get_pr_multi_diffs(git_provider: GitProvider,
continue
patch = convert_to_hunks_with_lines_numbers(patch, file)
# add AI-summary metadata to the patch
if file.ai_file_summary and get_settings().get("config.enable_ai_metadata", False):
patch = add_ai_summary_top_patch(file, patch)
new_patch_tokens = token_handler.count_tokens(patch)
if patch and (token_handler.prompt_tokens + new_patch_tokens) > get_max_tokens(
@ -479,3 +490,33 @@ def get_pr_multi_diffs(git_provider: GitProvider,
final_diff_list.append(final_diff)
return final_diff_list
def add_ai_metadata_to_diff_files(git_provider, pr_description_files):
"""
Adds AI metadata to the diff files based on the PR description files (FilePatchInfo.ai_file_summary).
"""
diff_files = git_provider.get_diff_files()
for file in diff_files:
filename = file.filename.strip()
found = False
for pr_file in pr_description_files:
if filename == pr_file['full_file_name'].strip():
file.ai_file_summary = pr_file
found = True
break
if not found:
get_logger().info(f"File {filename} not found in the PR description files",
artifacts=pr_description_files)
def add_ai_summary_top_patch(file, full_extended_patch):
# below every instance of '## File: ...' in the patch, add the ai-summary metadata
full_extended_patch_lines = full_extended_patch.split("\n")
for i, line in enumerate(full_extended_patch_lines):
if line.startswith("## File:") or line.startswith("## file:"):
full_extended_patch_lines.insert(i + 1,
f"### AI-generated file summary:\n{file.ai_file_summary['long_summary']}")
break
full_extended_patch = "\n".join(full_extended_patch_lines)
return full_extended_patch

1
pr_agent/algo/types.py
View File

@ -21,3 +21,4 @@ class FilePatchInfo:
old_filename: str = None
num_plus_lines: int = -1
num_minus_lines: int = -1
ai_file_summary: str = None

77
pr_agent/algo/utils.py
View File

@ -1,4 +1,5 @@
from __future__ import annotations
import html2text
import html
import copy
@ -214,19 +215,6 @@ def convert_to_markdown_v2(output_data: dict,
reference_link = git_provider.get_line_link(relevant_file, start_line, end_line)
if gfm_supported:
if get_settings().pr_reviewer.extra_issue_links:
issue_content_linked =copy.deepcopy(issue_content)
referenced_variables_list = issue.get('referenced_variables', [])
for component in referenced_variables_list:
name = component['variable_name'].strip().strip('`')
ind = issue_content.find(name)
if ind != -1:
reference_link_component = git_provider.get_line_link(relevant_file, component['relevant_line'], component['relevant_line'])
issue_content_linked = issue_content_linked[:ind-1] + f"[`{name}`]({reference_link_component})" + issue_content_linked[ind+len(name)+1:]
else:
get_logger().info(f"Failed to find variable in issue content: {component['variable_name'].strip()}")
issue_content = issue_content_linked
issue_str = f"<a href='{reference_link}'><strong>{issue_header}</strong></a><br>{issue_content}"
else:
issue_str = f"[**{issue_header}**]({reference_link})\n\n{issue_content}\n\n"
@ -945,3 +933,66 @@ def is_value_no(value):
if value_str == 'no' or value_str == 'none' or value_str == 'false':
return True
return False
def process_description(description_full: str):
split_str = "### **Changes walkthrough** 📝"
description_split = description_full.split(split_str)
base_description_str = description_split[0]
changes_walkthrough_str = ""
files = []
if len(description_split) > 1:
changes_walkthrough_str = description_split[1]
else:
get_logger().debug("No changes walkthrough found")
try:
if changes_walkthrough_str:
# get the end of the table
if '</table>\n\n___' in changes_walkthrough_str:
end = changes_walkthrough_str.index("</table>\n\n___")
elif '\n___' in changes_walkthrough_str:
end = changes_walkthrough_str.index("\n___")
else:
end = len(changes_walkthrough_str)
changes_walkthrough_str = changes_walkthrough_str[:end]
h = html2text.HTML2Text()
h.body_width = 0 # Disable line wrapping
# find all the files
pattern = r'<tr>\s*<td>\s*(<details>\s*<summary>(.*?)</summary>(.*?)</details>)\s*</td>'
files_found = re.findall(pattern, changes_walkthrough_str, re.DOTALL)
for file_data in files_found:
try:
if isinstance(file_data, tuple):
file_data = file_data[0]
# pattern = r'<details>\s*<summary><strong>(.*?)</strong><dd><code>(.*?)</code>.*?</summary>\s*<hr>\s*(.*?)\s*((?:\*.*\s*)*)</details>'
pattern = r'<details>\s*<summary><strong>(.*?)</strong><dd><code>(.*?)</code>.*?</summary>\s*<hr>\s*(.*?)\n\n\s*(.*?)</details>'
res = re.search(pattern, file_data, re.DOTALL)
if res and res.lastindex == 4:
short_filename = res.group(1).strip()
short_summary = res.group(2).strip()
long_filename = res.group(3).strip()
long_summary = res.group(4).strip()
long_summary = long_summary.replace('<br> *', '\n*').replace('<br>','').replace('\n','<br>')
long_summary = h.handle(long_summary).strip()
if not long_summary.startswith('*'):
long_summary = f"* {long_summary}"
files.append({
'short_file_name': short_filename,
'full_file_name': long_filename,
'short_summary': short_summary,
'long_summary': long_summary
})
else:
get_logger().error(f"Failed to parse description", artifact={'description': file_data})
except Exception as e:
get_logger().exception(f"Failed to process description: {e}", artifact={'description': file_data})
except Exception as e:
get_logger().exception(f"Failed to process description: {e}")
return base_description_str, files

2
pr_agent/git_providers/azuredevops_provider.py
View File

@ -516,7 +516,7 @@ class AzureDevopsProvider(GitProvider):
source_branch = pr_info.source_ref_name.split("/")[-1]
return source_branch
def get_pr_description(self, *, full: bool = True) -> str:
def get_pr_description(self, full: bool = True, split_changes_walkthrough=False) -> str:
max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
if max_tokens:
return clip_tokens(self.pr.description, max_tokens)

16
pr_agent/git_providers/git_provider.py
View File

@ -3,7 +3,7 @@ from abc import ABC, abstractmethod
# enum EDIT_TYPE (ADDED, DELETED, MODIFIED, RENAMED)
from typing import Optional
from pr_agent.algo.utils import Range
from pr_agent.algo.utils import Range, process_description
from pr_agent.config_loader import get_settings
from pr_agent.algo.types import FilePatchInfo
from pr_agent.log import get_logger
@ -61,14 +61,20 @@ class GitProvider(ABC):
def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
pass
def get_pr_description(self, *, full: bool = True) -> str:
def get_pr_description(self, full: bool = True, split_changes_walkthrough=False) -> str or tuple:
from pr_agent.config_loader import get_settings
from pr_agent.algo.utils import clip_tokens
max_tokens_description = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
description = self.get_pr_description_full() if full else self.get_user_description()
if max_tokens_description:
return clip_tokens(description, max_tokens_description)
return description
if split_changes_walkthrough:
description, files = process_description(description)
if max_tokens_description:
description = clip_tokens(description, max_tokens_description)
return description, files
else:
if max_tokens_description:
description = clip_tokens(description, max_tokens_description)
return description
def get_user_description(self) -> str:
if hasattr(self, 'user_description') and not (self.user_description is None):

1
pr_agent/servers/azuredevops_server_webhook.py
View File

@ -68,6 +68,7 @@ def authorize(credentials: HTTPBasicCredentials = Depends(security)):
async def _perform_commands_azure(commands_conf: str, agent: PRAgent, api_url: str, log_context: dict):
apply_repo_settings(api_url)
commands = get_settings().get(f"azure_devops_server.{commands_conf}")
get_settings().set("config.is_auto_command", True)
for command in commands:
try:
split_command = command.split(" ")

1
pr_agent/servers/bitbucket_app.py
View File

@ -78,6 +78,7 @@ async def handle_manifest(request: Request, response: Response):
async def _perform_commands_bitbucket(commands_conf: str, agent: PRAgent, api_url: str, log_context: dict):
apply_repo_settings(api_url)
commands = get_settings().get(f"bitbucket_app.{commands_conf}", {})
get_settings().set("config.is_auto_command", True)
for command in commands:
try:
split_command = command.split(" ")

5
pr_agent/servers/github_app.py
View File

@ -128,7 +128,6 @@ async def handle_new_pr_opened(body: Dict[str, Any],
log_context: Dict[str, Any],
agent: PRAgent):
title = body.get("pull_request", {}).get("title", "")
get_settings().config.is_auto_command = True
pull_request, api_url = _check_pull_request_event(action, body, log_context)
if not (pull_request and api_url):
@ -371,12 +370,14 @@ def _check_pull_request_event(action: str, body: dict, log_context: dict) -> Tup
return pull_request, api_url
async def _perform_auto_commands_github(commands_conf: str, agent: PRAgent, body: dict, api_url: str, log_context: dict):
async def _perform_auto_commands_github(commands_conf: str, agent: PRAgent, body: dict, api_url: str,
log_context: dict):
apply_repo_settings(api_url)
commands = get_settings().get(f"github_app.{commands_conf}")
if not commands:
get_logger().info(f"New PR, but no auto commands configured")
return
get_settings().set("config.is_auto_command", True)
for command in commands:
split_command = command.split(" ")
command = split_command[0]

2
pr_agent/servers/gitlab_webhook.py
View File

@ -62,6 +62,7 @@ async def _perform_commands_gitlab(commands_conf: str, agent: PRAgent, api_url:
log_context: dict):
apply_repo_settings(api_url)
commands = get_settings().get(f"gitlab.{commands_conf}", {})
get_settings().set("config.is_auto_command", True)
for command in commands:
try:
split_command = command.split(" ")
@ -75,6 +76,7 @@ async def _perform_commands_gitlab(commands_conf: str, agent: PRAgent, api_url:
except Exception as e:
get_logger().error(f"Failed to perform command {command}: {e}")
def is_bot_user(data) -> bool:
try:
# logic to ignore bot users (unlike Github, no direct flag for bot users in gitlab)

5
pr_agent/settings/configuration.toml
View File

@ -31,7 +31,6 @@ ai_disclaimer_title="" # Pro feature, title for a collapsible disclaimer to AI
ai_disclaimer="" # Pro feature, full text for the AI disclaimer
output_relevant_configurations=false
large_patch_policy = "clip" # "clip", "skip"
is_auto_command=false
# seed
seed=-1 # set positive value to fix the seed (and ensure temperature=0)
temperature=0.2
@ -40,6 +39,9 @@ ignore_pr_title = ["^\\[Auto\\]", "^Auto"] # a list of regular expressions to ma
ignore_pr_target_branches = [] # a list of regular expressions of target branches to ignore from PR agent when an PR is created
ignore_pr_source_branches = [] # a list of regular expressions of source branches to ignore from PR agent when an PR is created
ignore_pr_labels = [] # labels to ignore from PR agent when an PR is created
#
is_auto_command = false # will be auto-set to true if the command is triggered by an automation
enable_ai_metadata = false # will enable adding ai metadata
[pr_reviewer] # /review #
# enable/disable features
@ -48,7 +50,6 @@ require_tests_review=true
require_estimate_effort_to_review=true
require_can_be_split_review=false
require_security_review=true
extra_issue_links=false
# soc2
require_soc2_ticket=false
soc2_ticket_prompt="Does the PR description include a link to ticket in a project management system (e.g., Jira, Asana, Trello, etc.) ?"

4
pr_agent/settings/pr_add_docs.toml
View File

@ -5,7 +5,7 @@ Your task is to generate {{ docs_for_language }} for code components in the PR D
Example for the PR Diff format:
======
## file: 'src/file1.py'
## File: 'src/file1.py'
@@ -12,3 +12,4 @@ def func1():
__new hunk__
@ -25,7 +25,7 @@ __old hunk__
...
## file: 'src/file2.py'
## File: 'src/file2.py'
...
======

26
pr_agent/settings/pr_code_suggestions_prompts.toml
View File

@ -5,7 +5,12 @@ Your task is to provide meaningful and actionable code suggestions, to improve t
The format we will use to present the PR code diff:
======
## file: 'src/file1.py'
## File: 'src/file1.py'
{%- if is_ai_metadata %}
### AI-generated file summary:
* ...
* ...
{%- endif %}
@@ ... @@ def func1():
__new hunk__
@ -26,14 +31,16 @@ __old hunk__
...
## file: 'src/file2.py'
## File: 'src/file2.py'
...
======
- In this format, we separate each hunk of diff code to '__new hunk__' and '__old hunk__' sections. The '__new hunk__' section contains the new code of the chunk, and the '__old hunk__' section contains the old code, that was removed. If no new code was added in a specific hunk, '__new hunk__' section will not be presented. If no code was removed, '__old hunk__' section will not be presented.
- We also added line numbers for the '__new hunk__' code, to help you refer to the code lines in your suggestions. These line numbers are not part of the actual code, and should only used for reference.
- Code lines are prefixed with symbols ('+', '-', ' '). The '+' symbol indicates new code added in the PR, the '-' symbol indicates code removed in the PR, and the ' ' symbol indicates unchanged code. \
{%- if is_ai_metadata %}
- If available, an AI-generated summary will appear and provide a high-level overview of the file changes.
{%- endif %}
Specific instructions for generating code suggestions:
- Provide up to {{ num_code_suggestions }} code suggestions.
@ -122,7 +129,12 @@ Your task is to provide meaningful and actionable code suggestions, to improve t
The format we will use to present the PR code diff:
======
## file: 'src/file1.py'
## File: 'src/file1.py'
{%- if is_ai_metadata %}
### AI-generated file summary:
* ...
* ...
{%- endif %}
@@ ... @@ def func1():
__new hunk__
@ -143,14 +155,16 @@ __old hunk__
...
## file: 'src/file2.py'
## File: 'src/file2.py'
...
======
- In this format, we separate each hunk of diff code to '__new hunk__' and '__old hunk__' sections. The '__new hunk__' section contains the new code of the chunk, and the '__old hunk__' section contains the old code, that was removed. If no new code was added in a specific hunk, '__new hunk__' section will not be presented. If no code was removed, '__old hunk__' section will not be presented.
- We also added line numbers for the '__new hunk__' code, to help you refer to the code lines in your suggestions. These line numbers are not part of the actual code, and should only used for reference.
- Code lines are prefixed with symbols ('+', '-', ' '). The '+' symbol indicates new code added in the PR, the '-' symbol indicates code removed in the PR, and the ' ' symbol indicates unchanged code. \
{%- if is_ai_metadata %}
- If available, an AI-generated summary will appear and provide a high-level overview of the file changes.
{%- endif %}
Specific instructions for generating code suggestions:
- Provide up to {{ num_code_suggestions }} code suggestions.

4
pr_agent/settings/pr_code_suggestions_reflect_prompts.toml
View File

@ -16,7 +16,7 @@ Specific instructions:
The format that is used to present the PR code diff is as follows:
======
## file: 'src/file1.py'
## File: 'src/file1.py'
@@ ... @@ def func1():
__new hunk__
@ -35,7 +35,7 @@ __old hunk__
...
## file: 'src/file2.py'
## File: 'src/file2.py'
...
======
- In this format, we separated each hunk of code to '__new hunk__' and '__old hunk__' sections. The '__new hunk__' section contains the new code of the chunk, and the '__old hunk__' section contains the old code that was removed.

2
pr_agent/settings/pr_line_questions_prompts.toml
View File

@ -12,7 +12,7 @@ Additional guidelines:
Example Hunk Structure:
======
## file: 'src/file1.py'
## File: 'src/file1.py'
@@ -12,5 +12,5 @@ def func1():
code line 1 that remained unchanged in the PR

28
pr_agent/settings/pr_reviewer_prompts.toml
View File

@ -10,7 +10,13 @@ The review should focus on new code added in the PR code diff (lines starting wi
The format we will use to present the PR code diff:
======
## file: 'src/file1.py'
## File: 'src/file1.py'
{%- if is_ai_metadata %}
### AI-generated file summary:
* ...
* ...
{%- endif %}
@@ ... @@ def func1():
__new hunk__
@ -31,7 +37,7 @@ __old hunk__
...
## file: 'src/file2.py'
## File: 'src/file2.py'
...
======
@ -39,6 +45,9 @@ __old hunk__
- We also added line numbers for the '__new hunk__' code, to help you refer to the code lines in your suggestions. These line numbers are not part of the actual code, and should only used for reference.
- Code lines are prefixed with symbols ('+', '-', ' '). The '+' symbol indicates new code added in the PR, the '-' symbol indicates code removed in the PR, and the ' ' symbol indicates unchanged code. \
The review should address new code added in the PR code diff (lines starting with '+')
{%- if is_ai_metadata %}
- If available, an AI-generated summary will appear and provide a high-level overview of the file changes.
{%- endif %}
- When quoting variables or names from the code, use backticks (`) instead of single quote (').
{%- if num_code_suggestions > 0 %}
@ -76,15 +85,6 @@ class KeyIssuesComponentLink(BaseModel):
issue_content: str = Field(description="a short and concise description of the issue that needs to be reviewed")
start_line: int = Field(description="the start line that corresponds to this issue in the relevant file")
end_line: int = Field(description="the end line that corresponds to this issue in the relevant file")
{%- if extra_issue_links %}
referenced_variables: List[Refs] = Field(description="a list of relevant variables or names that appear in the 'issue_content' output. For each variable, output is name, and the line number where it appears in the relevant file")
{% endif %}
{%- if extra_issue_links %}
class Refs(BaseModel):
variable_name: str = Field(description="the name of a variable or name that appears in the relevant 'issue_content' output.")
relevant_line: int = Field(description="the line number where the variable or name appears in the relevant file")
{%- endif %}
class Review(BaseModel):
{%- if require_estimate_effort_to_review %}
@ -149,12 +149,6 @@ review:
...
start_line: 12
end_line: 14
{%- if extra_issue_links %}
referenced_variables:
- variable_name: |
...
relevant_line: 13
{%- endif %}
- ...
security_concerns: |
No

19
pr_agent/tools/pr_code_suggestions.py
View File

@ -7,7 +7,8 @@ from jinja2 import Environment, StrictUndefined
from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
from pr_agent.algo.pr_processing import get_pr_diff, get_pr_multi_diffs, retry_with_fallback_models
from pr_agent.algo.pr_processing import get_pr_diff, get_pr_multi_diffs, retry_with_fallback_models, \
add_ai_metadata_to_diff_files
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import load_yaml, replace_code_tags, ModelType, show_relevant_configurations
from pr_agent.config_loader import get_settings
@ -54,16 +55,27 @@ class PRCodeSuggestions:
self.prediction = None
self.pr_url = pr_url
self.cli_mode = cli_mode
self.pr_description, self.pr_description_files = (
self.git_provider.get_pr_description(split_changes_walkthrough=True))
if (self.pr_description_files and get_settings().get("config.is_auto_command", False) and
get_settings().get("config.enable_ai_metadata", False)):
add_ai_metadata_to_diff_files(self.git_provider, self.pr_description_files)
get_logger().debug(f"AI metadata added to the this command")
else:
get_settings().set("config.enable_ai_metadata", False)
get_logger().debug(f"AI metadata is disabled for this command")
self.vars = {
"title": self.git_provider.pr.title,
"branch": self.git_provider.get_pr_branch(),
"description": self.git_provider.get_pr_description(),
"description": self.pr_description,
"language": self.main_language,
"diff": "", # empty diff for initial calculation
"num_code_suggestions": num_code_suggestions,
"extra_instructions": get_settings().pr_code_suggestions.extra_instructions,
"commit_messages_str": self.git_provider.get_commit_messages(),
"relevant_best_practices": "",
"is_ai_metadata": get_settings().get("config.enable_ai_metadata", False),
}
if 'claude' in get_settings().config.model:
# prompt for Claude, with minor adjustments
@ -505,7 +517,8 @@ class PRCodeSuggestions:
async def _prepare_prediction_extended(self, model: str) -> dict:
self.patches_diff_list = get_pr_multi_diffs(self.git_provider, self.token_handler, model,
max_calls=get_settings().pr_code_suggestions.max_number_of_calls)
max_calls=get_settings().pr_code_suggestions.max_number_of_calls,
pr_description_files =self.pr_description_files)
if self.patches_diff_list:
get_logger().info(f"Number of PR chunk calls: {len(self.patches_diff_list)}")
get_logger().debug(f"PR diff:", artifact=self.patches_diff_list)

3
pr_agent/tools/pr_description.py
View File

@ -638,9 +638,10 @@ def insert_br_after_x_chars(text, x=70):
text = replace_code_tags(text)
# convert list items to <li>
if text.startswith("- "):
if text.startswith("- ") or text.startswith("* "):
text = "<li>" + text[2:]
text = text.replace("\n- ", '<br><li> ').replace("\n - ", '<br><li> ')
text = text.replace("\n* ", '<br><li> ').replace("\n * ", '<br><li> ')
# convert new lines to <br>
text = text.replace("\n", '<br>')

18
pr_agent/tools/pr_reviewer.py
View File

@ -6,7 +6,7 @@ from typing import List, Tuple
from jinja2 import Environment, StrictUndefined
from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, add_ai_metadata_to_diff_files
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import github_action_output, load_yaml, ModelType, \
show_relevant_configurations, convert_to_markdown_v2, PRReviewHeader
@ -51,15 +51,23 @@ class PRReviewer:
raise Exception(f"Answer mode is not supported for {get_settings().config.git_provider} for now")
self.ai_handler = ai_handler()
self.ai_handler.main_pr_language = self.main_language
self.patches_diff = None
self.prediction = None
answer_str, question_str = self._get_user_answers()
self.pr_description, self.pr_description_files = (
self.git_provider.get_pr_description(split_changes_walkthrough=True))
if (self.pr_description_files and get_settings().get("config.is_auto_command", False) and
get_settings().get("config.enable_ai_metadata", False)):
add_ai_metadata_to_diff_files(self.git_provider, self.pr_description_files)
get_logger().debug(f"AI metadata added to the this command")
else:
get_settings().set("config.enable_ai_metadata", False)
get_logger().debug(f"AI metadata is disabled for this command")
self.vars = {
"title": self.git_provider.pr.title,
"branch": self.git_provider.get_pr_branch(),
"description": self.git_provider.get_pr_description(),
"description": self.pr_description,
"language": self.main_language,
"diff": "", # empty diff for initial calculation
"num_pr_files": self.git_provider.get_num_of_files(),
@ -75,7 +83,7 @@ class PRReviewer:
"commit_messages_str": self.git_provider.get_commit_messages(),
"custom_labels": "",
"enable_custom_labels": get_settings().config.enable_custom_labels,
"extra_issue_links": get_settings().pr_reviewer.extra_issue_links,
"is_ai_metadata": get_settings().get("config.enable_ai_metadata", False),
}
self.token_handler = TokenHandler(

1
requirements.txt
View File

@ -27,6 +27,7 @@ tenacity==8.2.3
gunicorn==22.0.0
pytest-cov==5.0.0
pydantic==2.8.2
html2text==2024.2.26
# Uncomment the following lines to enable the 'similar issue' tool
# pinecone-client
# pinecone-datasets @ git+https://github.com/mrT23/pinecone-datasets.git@main

3
tests/unittest/test_extend_patch.py
View File

@ -94,10 +94,11 @@ class TestExtendedPatchMoreLines:
get_settings().config.allow_dynamic_context = False
class File:
def __init__(self, base_file, patch, filename):
def __init__(self, base_file, patch, filename, ai_file_summary=None):
self.base_file = base_file
self.patch = patch
self.filename = filename
self.ai_file_summary = ai_file_summary
@pytest.fixture
def token_handler(self):