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

Refactor logging system to use custom logger across the codebase

Browse Source
This commit is contained in:
Ori Kotek
2023-10-16 14:56:00 +03:00
parent 41166dc271
commit c324d88be3
32 changed files with 340 additions and 311 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
pr_agent/agent/pr_agent.py
View File

@ -1,21 +1,17 @@
import logging
import os
import shlex
import tempfile
from pr_agent.algo.utils import update_settings_from_args
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.git_providers.utils import apply_repo_settings
from pr_agent.tools.pr_add_docs import PRAddDocs
from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
from pr_agent.tools.pr_config import PRConfig
from pr_agent.tools.pr_description import PRDescription
from pr_agent.tools.pr_information_from_user import PRInformationFromUser
from pr_agent.tools.pr_similar_issue import PRSimilarIssue
from pr_agent.tools.pr_questions import PRQuestions
from pr_agent.tools.pr_reviewer import PRReviewer
from pr_agent.tools.pr_similar_issue import PRSimilarIssue
from pr_agent.tools.pr_update_changelog import PRUpdateChangelog
from pr_agent.tools.pr_config import PRConfig
command2class = {
"auto_review": PRReviewer,

21
pr_agent/algo/ai_handler.py
View File

@ -1,4 +1,3 @@
import logging
import os
import litellm
@ -7,6 +6,8 @@ from litellm import acompletion
from openai.error import APIError, RateLimitError, Timeout, TryAgain
from retry import retry
from pr_agent.config_loader import get_settings
from pr_agent.log import get_logger
OPENAI_RETRIES = 5
@ -88,34 +89,34 @@ class AiHandler:
try:
deployment_id = self.deployment_id
if get_settings().config.verbosity_level >= 2:
logging.debug(
get_logger().debug(
f"Generating completion with {model}"
f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
)
if self.azure:
model = 'azure/' + model
messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
response = await acompletion(
model=model,
deployment_id=deployment_id,
messages=[
{"role": "system", "content": system},
{"role": "user", "content": user}
],
messages=messages,
temperature=temperature,
force_timeout=get_settings().config.ai_timeout
)
except (APIError, Timeout, TryAgain) as e:
logging.error("Error during OpenAI inference: ", e)
get_logger().error("Error during OpenAI inference: ", e)
raise
except (RateLimitError) as e:
logging.error("Rate limit error during OpenAI inference: ", e)
get_logger().error("Rate limit error during OpenAI inference: ", e)
raise
except (Exception) as e:
logging.error("Unknown error during OpenAI inference: ", e)
get_logger().error("Unknown error during OpenAI inference: ", e)
raise TryAgain from e
if response is None or len(response["choices"]) == 0:
raise TryAgain
resp = response["choices"][0]['message']['content']
finish_reason = response["choices"][0]["finish_reason"]
print(resp, finish_reason)
usage = response.get("usage")
get_logger().info("AI response", response=resp, messages=messages, finish_reason=finish_reason,
model=model, usage=usage)
return resp, finish_reason

9
pr_agent/algo/git_patch_processing.py
View File

@ -1,8 +1,9 @@
from __future__ import annotations
import logging
import re
from pr_agent.config_loader import get_settings
from pr_agent.log import get_logger
def extend_patch(original_file_str, patch_str, num_lines) -> str:
@ -63,7 +64,7 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
extended_patch_lines.append(line)
except Exception as e:
if get_settings().config.verbosity_level >= 2:
logging.error(f"Failed to extend patch: {e}")
get_logger().error(f"Failed to extend patch: {e}")
return patch_str
# finish previous hunk
@ -134,14 +135,14 @@ def handle_patch_deletions(patch: str, original_file_content_str: str,
if not new_file_content_str:
# logic for handling deleted files - don't show patch, just show that the file was deleted
if get_settings().config.verbosity_level > 0:
logging.info(f"Processing file: {file_name}, minimizing deletion file")
get_logger().info(f"Processing file: {file_name}, minimizing deletion file")
patch = None # file was deleted
else:
patch_lines = patch.splitlines()
patch_new = omit_deletion_hunks(patch_lines)
if patch != patch_new:
if get_settings().config.verbosity_level > 0:
logging.info(f"Processing file: {file_name}, hunks were deleted")
get_logger().info(f"Processing file: {file_name}, hunks were deleted")
patch = patch_new
return patch

22
pr_agent/algo/pr_processing.py
View File

@ -1,7 +1,6 @@
from __future__ import annotations
import difflib
import logging
import re
import traceback
from typing import Any, Callable, List, Tuple
@ -15,6 +14,7 @@ from pr_agent.algo.file_filter import filter_ignored
from pr_agent.algo.token_handler import TokenHandler, get_token_encoder
from pr_agent.config_loader import get_settings
from pr_agent.git_providers.git_provider import FilePatchInfo, GitProvider
from pr_agent.log import get_logger
DELETED_FILES_ = "Deleted files:\n"
@ -51,7 +51,7 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
try:
diff_files = git_provider.get_diff_files()
except RateLimitExceededException as e:
logging.error(f"Rate limit exceeded for git provider API. original message {e}")
get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
raise
diff_files = filter_ignored(diff_files)
@ -180,7 +180,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
# Hard Stop, no more tokens
if total_tokens > MAX_TOKENS[model] - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
logging.warning(f"File was fully skipped, no more tokens: {file.filename}.")
get_logger().warning(f"File was fully skipped, no more tokens: {file.filename}.")
continue
# If the patch is too large, just show the file name
@ -189,7 +189,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
# TODO: Option for alternative logic to remove hunks from the patch to reduce the number of tokens
# until we meet the requirements
if get_settings().config.verbosity_level >= 2:
logging.warning(f"Patch too large, minimizing it, {file.filename}")
get_logger().warning(f"Patch too large, minimizing it, {file.filename}")
if not modified_files_list:
total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
modified_files_list.append(file.filename)
@ -204,7 +204,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
patches.append(patch_final)
total_tokens += token_handler.count_tokens(patch_final)
if get_settings().config.verbosity_level >= 2:
logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
return patches, modified_files_list, deleted_files_list
@ -218,7 +218,7 @@ async def retry_with_fallback_models(f: Callable):
get_settings().set("openai.deployment_id", deployment_id)
return await f(model)
except Exception as e:
logging.warning(
get_logger().warning(
f"Failed to generate prediction with {model}"
f"{(' from deployment ' + deployment_id) if deployment_id else ''}: "
f"{traceback.format_exc()}"
@ -340,7 +340,7 @@ def clip_tokens(text: str, max_tokens: int) -> str:
clipped_text = text[:num_output_chars]
return clipped_text
except Exception as e:
logging.warning(f"Failed to clip tokens: {e}")
get_logger().warning(f"Failed to clip tokens: {e}")
return text
@ -367,7 +367,7 @@ def get_pr_multi_diffs(git_provider: GitProvider,
try:
diff_files = git_provider.get_diff_files()
except RateLimitExceededException as e:
logging.error(f"Rate limit exceeded for git provider API. original message {e}")
get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
raise
diff_files = filter_ignored(diff_files)
@ -387,7 +387,7 @@ def get_pr_multi_diffs(git_provider: GitProvider,
for file in sorted_files:
if call_number > max_calls:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Reached max calls ({max_calls})")
get_logger().info(f"Reached max calls ({max_calls})")
break
original_file_content_str = file.base_file
@ -410,13 +410,13 @@ def get_pr_multi_diffs(git_provider: GitProvider,
total_tokens = token_handler.prompt_tokens
call_number += 1
if get_settings().config.verbosity_level >= 2:
logging.info(f"Call number: {call_number}")
get_logger().info(f"Call number: {call_number}")
if patch:
patches.append(patch)
total_tokens += new_patch_tokens
if get_settings().config.verbosity_level >= 2:
logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
# Add the last chunk
if patches:

16
pr_agent/algo/utils.py
View File

@ -2,7 +2,6 @@ from __future__ import annotations
import difflib
import json
import logging
import re
import textwrap
from datetime import datetime
@ -11,6 +10,7 @@ from typing import Any, List
import yaml
from starlette_context import context
from pr_agent.config_loader import get_settings, global_settings
from pr_agent.log import get_logger
def get_setting(key: str) -> Any:
@ -159,7 +159,7 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
iter_count += 1
if not valid_json:
logging.error("Unable to decode JSON response from AI")
get_logger().error("Unable to decode JSON response from AI")
data = {}
return data
@ -230,7 +230,7 @@ def load_large_diff(filename, new_file_content_str: str, original_file_content_s
diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
new_file_content_str.splitlines(keepends=True))
if get_settings().config.verbosity_level >= 2:
logging.warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
get_logger().warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
patch = ''.join(diff)
except Exception:
pass
@ -262,12 +262,12 @@ def update_settings_from_args(args: List[str]) -> List[str]:
vals = arg.split('=', 1)
if len(vals) != 2:
if len(vals) > 2: # --extended is a valid argument
logging.error(f'Invalid argument format: {arg}')
get_logger().error(f'Invalid argument format: {arg}')
other_args.append(arg)
continue
key, value = _fix_key_value(*vals)
get_settings().set(key, value)
logging.info(f'Updated setting {key} to: "{value}"')
get_logger().info(f'Updated setting {key} to: "{value}"')
else:
other_args.append(arg)
return other_args
@ -279,7 +279,7 @@ def _fix_key_value(key: str, value: str):
try:
value = yaml.safe_load(value)
except Exception as e:
logging.error(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
get_logger().error(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
return key, value
@ -288,7 +288,7 @@ def load_yaml(review_text: str) -> dict:
try:
data = yaml.safe_load(review_text)
except Exception as e:
logging.error(f"Failed to parse AI prediction: {e}")
get_logger().error(f"Failed to parse AI prediction: {e}")
data = try_fix_yaml(review_text)
return data
@ -299,7 +299,7 @@ def try_fix_yaml(review_text: str) -> dict:
review_text_lines_tmp = '\n'.join(review_text_lines[:-i])
try:
data = yaml.load(review_text_lines_tmp, Loader=yaml.SafeLoader)
logging.info(f"Successfully parsed AI prediction after removing {i} lines")
get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
break
except:
pass

4
pr_agent/cli.py
View File

@ -1,11 +1,12 @@
import argparse
import asyncio
import logging
import os
from pr_agent.agent.pr_agent import PRAgent, commands
from pr_agent.config_loader import get_settings
from pr_agent.log import setup_logger
setup_logger()
def run(inargs=None):
parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage=
@ -47,7 +48,6 @@ For example: 'python cli.py --pr_url=... review --pr_reviewer.extra_instructions
parser.print_help()
return
logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
command = args.command.lower()
get_settings().set("CONFIG.CLI_MODE", True)
if args.issue_url:

11
pr_agent/git_providers/azuredevops_provider.py
View File

@ -1,10 +1,11 @@
import json
import logging
from typing import Optional, Tuple
from urllib.parse import urlparse
import os
from ..log import get_logger
AZURE_DEVOPS_AVAILABLE = True
try:
from msrest.authentication import BasicAuthentication
@ -55,7 +56,7 @@ class AzureDevopsProvider:
path=".pr_agent.toml")
return contents
except Exception as e:
logging.exception("get repo settings error")
get_logger().exception("get repo settings error")
return ""
def get_files(self):
@ -110,7 +111,7 @@ class AzureDevopsProvider:
new_file_content_str = new_file_content_str.content
except Exception as error:
logging.error("Failed to retrieve new file content of %s at version %s. Error: %s", file, version, str(error))
get_logger().error("Failed to retrieve new file content of %s at version %s. Error: %s", file, version, str(error))
new_file_content_str = ""
edit_type = EDIT_TYPE.MODIFIED
@ -131,7 +132,7 @@ class AzureDevopsProvider:
include_content=True)
original_file_content_str = original_file_content_str.content
except Exception as error:
logging.error("Failed to retrieve original file content of %s at version %s. Error: %s", file, version, str(error))
get_logger().error("Failed to retrieve original file content of %s at version %s. Error: %s", file, version, str(error))
original_file_content_str = ""
patch = load_large_diff(file, new_file_content_str, original_file_content_str)
@ -166,7 +167,7 @@ class AzureDevopsProvider:
pull_request_id=self.pr_num,
git_pull_request_to_update=updated_pr)
except Exception as e:
logging.exception(f"Could not update pull request {self.pr_num} description: {e}")
get_logger().exception(f"Could not update pull request {self.pr_num} description: {e}")
def remove_initial_comment(self):
return "" # not implemented yet

14
pr_agent/git_providers/bitbucket_provider.py
View File

@ -1,5 +1,4 @@
import json
import logging
from typing import Optional, Tuple
from urllib.parse import urlparse
@ -7,8 +6,9 @@ import requests
from atlassian.bitbucket import Cloud
from starlette_context import context
from ..algo.pr_processing import clip_tokens, find_line_number_of_relevant_line_in_file
from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
from ..config_loader import get_settings
from ..log import get_logger
from .git_provider import FilePatchInfo, GitProvider
@ -61,14 +61,14 @@ class BitbucketProvider(GitProvider):
if not relevant_lines_start or relevant_lines_start == -1:
if get_settings().config.verbosity_level >= 2:
logging.exception(
get_logger().exception(
f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
)
continue
if relevant_lines_end < relevant_lines_start:
if get_settings().config.verbosity_level >= 2:
logging.exception(
get_logger().exception(
f"Failed to publish code suggestion, "
f"relevant_lines_end is {relevant_lines_end} and "
f"relevant_lines_start is {relevant_lines_start}"
@ -97,7 +97,7 @@ class BitbucketProvider(GitProvider):
return True
except Exception as e:
if get_settings().config.verbosity_level >= 2:
logging.error(f"Failed to publish code suggestion, error: {e}")
get_logger().error(f"Failed to publish code suggestion, error: {e}")
return False
def is_supported(self, capability: str) -> bool:
@ -144,7 +144,7 @@ class BitbucketProvider(GitProvider):
for comment in self.temp_comments:
self.pr.delete(f"comments/{comment}")
except Exception as e:
logging.exception(f"Failed to remove temp comments, error: {e}")
get_logger().exception(f"Failed to remove temp comments, error: {e}")
# funtion to create_inline_comment
@ -152,7 +152,7 @@ class BitbucketProvider(GitProvider):
position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(), relevant_file.strip('`'), relevant_line_in_file)
if position == -1:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
subject_type = "FILE"
else:
subject_type = "LINE"

23
pr_agent/git_providers/codecommit_provider.py
View File

@ -1,17 +1,16 @@
import logging
import os
import re
from collections import Counter
from typing import List, Optional, Tuple
from urllib.parse import urlparse
from ..algo.language_handler import is_valid_file, language_extension_map
from ..algo.pr_processing import clip_tokens
from ..algo.utils import load_large_diff
from ..config_loader import get_settings
from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider, IncrementalPR
from pr_agent.git_providers.codecommit_client import CodeCommitClient
from ..algo.language_handler import is_valid_file, language_extension_map
from ..algo.utils import load_large_diff
from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
from ..log import get_logger
class PullRequestCCMimic:
"""
@ -166,7 +165,7 @@ class CodeCommitProvider(GitProvider):
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
if is_temporary:
logging.info(pr_comment)
get_logger().info(pr_comment)
return
pr_comment = CodeCommitProvider._remove_markdown_html(pr_comment)
@ -188,12 +187,12 @@ class CodeCommitProvider(GitProvider):
for suggestion in code_suggestions:
# Verify that each suggestion has the required keys
if not all(key in suggestion for key in ["body", "relevant_file", "relevant_lines_start"]):
logging.warning(f"Skipping code suggestion #{counter}: Each suggestion must have 'body', 'relevant_file', 'relevant_lines_start' keys")
get_logger().warning(f"Skipping code suggestion #{counter}: Each suggestion must have 'body', 'relevant_file', 'relevant_lines_start' keys")
continue
# Publish the code suggestion to CodeCommit
try:
logging.debug(f"Code Suggestion #{counter} in file: {suggestion['relevant_file']}: {suggestion['relevant_lines_start']}")
get_logger().debug(f"Code Suggestion #{counter} in file: {suggestion['relevant_file']}: {suggestion['relevant_lines_start']}")
self.codecommit_client.publish_comment(
repo_name=self.repo_name,
pr_number=self.pr_num,
@ -296,11 +295,11 @@ class CodeCommitProvider(GitProvider):
return self.codecommit_client.get_file(self.repo_name, settings_filename, self.pr.source_commit, optional=True)
def add_eyes_reaction(self, issue_comment_id: int) -> Optional[int]:
logging.info("CodeCommit provider does not support eyes reaction yet")
get_logger().info("CodeCommit provider does not support eyes reaction yet")
return True
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
logging.info("CodeCommit provider does not support removing reactions yet")
get_logger().info("CodeCommit provider does not support removing reactions yet")
return True
@staticmethod
@ -366,7 +365,7 @@ class CodeCommitProvider(GitProvider):
# TODO: implement support for multiple targets in one CodeCommit PR
# for now, we are only using the first target in the PR
if len(response.targets) > 1:
logging.warning(
get_logger().warning(
"Multiple targets in one PR is not supported for CodeCommit yet. Continuing, using the first target only..."
)

29
pr_agent/git_providers/gerrit_provider.py
View File

@ -1,5 +1,4 @@
import json
import logging
import os
import pathlib
import shutil
@ -7,18 +6,16 @@ import subprocess
import uuid
from collections import Counter, namedtuple
from pathlib import Path
from tempfile import mkdtemp, NamedTemporaryFile
from tempfile import NamedTemporaryFile, mkdtemp
import requests
import urllib3.util
from git import Repo
from pr_agent.config_loader import get_settings
from pr_agent.git_providers.git_provider import GitProvider, FilePatchInfo, \
EDIT_TYPE
from pr_agent.git_providers.git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
from pr_agent.git_providers.local_git_provider import PullRequestMimic
logger = logging.getLogger(__name__)
from pr_agent.log import get_logger
def _call(*command, **kwargs) -> (int, str, str):
@ -33,42 +30,42 @@ def _call(*command, **kwargs) -> (int, str, str):
def clone(url, directory):
logger.info("Cloning %s to %s", url, directory)
get_logger().info("Cloning %s to %s", url, directory)
stdout = _call('git', 'clone', "--depth", "1", url, directory)
logger.info(stdout)
get_logger().info(stdout)
def fetch(url, refspec, cwd):
logger.info("Fetching %s %s", url, refspec)
get_logger().info("Fetching %s %s", url, refspec)
stdout = _call(
'git', 'fetch', '--depth', '2', url, refspec,
cwd=cwd
)
logger.info(stdout)
get_logger().info(stdout)
def checkout(cwd):
logger.info("Checking out")
get_logger().info("Checking out")
stdout = _call('git', 'checkout', "FETCH_HEAD", cwd=cwd)
logger.info(stdout)
get_logger().info(stdout)
def show(*args, cwd=None):
logger.info("Show")
get_logger().info("Show")
return _call('git', 'show', *args, cwd=cwd)
def diff(*args, cwd=None):
logger.info("Diff")
get_logger().info("Diff")
patch = _call('git', 'diff', *args, cwd=cwd)
if not patch:
logger.warning("No changes found")
get_logger().warning("No changes found")
return
return patch
def reset_local_changes(cwd):
logger.info("Reset local changes")
get_logger().info("Reset local changes")
_call('git', 'checkout', "--force", cwd=cwd)

7
pr_agent/git_providers/git_provider.py
View File

@ -1,4 +1,3 @@
import logging
from abc import ABC, abstractmethod
from dataclasses import dataclass
@ -6,6 +5,8 @@ from dataclasses import dataclass
from enum import Enum
from typing import Optional
from pr_agent.log import get_logger
class EDIT_TYPE(Enum):
ADDED = 1
@ -136,7 +137,7 @@ def get_main_pr_language(languages, files) -> str:
"""
main_language_str = ""
if not languages:
logging.info("No languages detected")
get_logger().info("No languages detected")
return main_language_str
try:
@ -172,7 +173,7 @@ def get_main_pr_language(languages, files) -> str:
main_language_str = top_language
except Exception as e:
logging.exception(e)
get_logger().exception(e)
pass
return main_language_str

37
pr_agent/git_providers/github_provider.py
View File

@ -1,20 +1,19 @@
import logging
import hashlib
from datetime import datetime
from typing import Optional, Tuple, Any
from typing import Optional, Tuple
from urllib.parse import urlparse
from github import AppAuthentication, Auth, Github, GithubException, Reaction
from github import AppAuthentication, Auth, Github, GithubException
from retry import retry
from starlette_context import context
from .git_provider import FilePatchInfo, GitProvider, IncrementalPR
from ..algo.language_handler import is_valid_file
from ..algo.pr_processing import clip_tokens, find_line_number_of_relevant_line_in_file
from ..algo.utils import load_large_diff
from ..algo.pr_processing import find_line_number_of_relevant_line_in_file, clip_tokens
from ..config_loader import get_settings
from ..log import get_logger
from ..servers.utils import RateLimitExceeded
from .git_provider import FilePatchInfo, GitProvider, IncrementalPR
class GithubProvider(GitProvider):
@ -58,7 +57,7 @@ class GithubProvider(GitProvider):
self.file_set = dict()
for commit in self.incremental.commits_range:
if commit.commit.message.startswith(f"Merge branch '{self._get_repo().default_branch}'"):
logging.info(f"Skipping merge commit {commit.commit.message}")
get_logger().info(f"Skipping merge commit {commit.commit.message}")
continue
self.file_set.update({file.filename: file for file in commit.files})
@ -130,7 +129,7 @@ class GithubProvider(GitProvider):
return diff_files
except GithubException.RateLimitExceededException as e:
logging.error(f"Rate limit exceeded for GitHub API. Original message: {e}")
get_logger().error(f"Rate limit exceeded for GitHub API. Original message: {e}")
raise RateLimitExceeded("Rate limit exceeded for GitHub API.") from e
def publish_description(self, pr_title: str, pr_body: str):
@ -138,7 +137,7 @@ class GithubProvider(GitProvider):
def publish_comment(self, pr_comment: str, is_temporary: bool = False):
if is_temporary and not get_settings().config.publish_output_progress:
logging.debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
return
response = self.pr.create_issue_comment(pr_comment)
if hasattr(response, "user") and hasattr(response.user, "login"):
@ -156,7 +155,7 @@ class GithubProvider(GitProvider):
position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files, relevant_file.strip('`'), relevant_line_in_file)
if position == -1:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
subject_type = "FILE"
else:
subject_type = "LINE"
@ -179,13 +178,13 @@ class GithubProvider(GitProvider):
if not relevant_lines_start or relevant_lines_start == -1:
if get_settings().config.verbosity_level >= 2:
logging.exception(
get_logger().exception(
f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
continue
if relevant_lines_end < relevant_lines_start:
if get_settings().config.verbosity_level >= 2:
logging.exception(f"Failed to publish code suggestion, "
get_logger().exception(f"Failed to publish code suggestion, "
f"relevant_lines_end is {relevant_lines_end} and "
f"relevant_lines_start is {relevant_lines_start}")
continue
@ -212,7 +211,7 @@ class GithubProvider(GitProvider):
return True
except Exception as e:
if get_settings().config.verbosity_level >= 2:
logging.error(f"Failed to publish code suggestion, error: {e}")
get_logger().error(f"Failed to publish code suggestion, error: {e}")
return False
def remove_initial_comment(self):
@ -221,7 +220,7 @@ class GithubProvider(GitProvider):
if comment.is_temporary:
comment.delete()
except Exception as e:
logging.exception(f"Failed to remove initial comment, error: {e}")
get_logger().exception(f"Failed to remove initial comment, error: {e}")
def get_title(self):
return self.pr.title
@ -269,7 +268,7 @@ class GithubProvider(GitProvider):
reaction = self.pr.get_issue_comment(issue_comment_id).create_reaction("eyes")
return reaction.id
except Exception as e:
logging.exception(f"Failed to add eyes reaction, error: {e}")
get_logger().exception(f"Failed to add eyes reaction, error: {e}")
return None
def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
@ -277,7 +276,7 @@ class GithubProvider(GitProvider):
self.pr.get_issue_comment(issue_comment_id).delete_reaction(reaction_id)
return True
except Exception as e:
logging.exception(f"Failed to remove eyes reaction, error: {e}")
get_logger().exception(f"Failed to remove eyes reaction, error: {e}")
return False
@ -396,13 +395,13 @@ class GithubProvider(GitProvider):
"PUT", f"{self.pr.issue_url}/labels", input=post_parameters
)
except Exception as e:
logging.exception(f"Failed to publish labels, error: {e}")
get_logger().exception(f"Failed to publish labels, error: {e}")
def get_labels(self):
try:
return [label.name for label in self.pr.labels]
except Exception as e:
logging.exception(f"Failed to get labels, error: {e}")
get_logger().exception(f"Failed to get labels, error: {e}")
return []
def get_commit_messages(self):
@ -444,7 +443,7 @@ class GithubProvider(GitProvider):
return link
except Exception as e:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Failed adding line link, error: {e}")
get_logger().info(f"Failed adding line link, error: {e}")
return ""

29
pr_agent/git_providers/gitlab_provider.py
View File

@ -1,5 +1,4 @@
import hashlib
import logging
import re
from typing import Optional, Tuple
from urllib.parse import urlparse
@ -12,8 +11,8 @@ from ..algo.pr_processing import clip_tokens, find_line_number_of_relevant_line_
from ..algo.utils import load_large_diff
from ..config_loader import get_settings
from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
from ..log import get_logger
logger = logging.getLogger()
class DiffNotFoundError(Exception):
"""Raised when the diff for a merge request cannot be found."""
@ -59,7 +58,7 @@ class GitLabProvider(GitProvider):
try:
self.last_diff = self.mr.diffs.list(get_all=True)[-1]
except IndexError as e:
logger.error(f"Could not get diff for merge request {self.id_mr}")
get_logger().error(f"Could not get diff for merge request {self.id_mr}")
raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}") from e
@ -99,7 +98,7 @@ class GitLabProvider(GitProvider):
if isinstance(new_file_content_str, bytes):
new_file_content_str = bytes.decode(new_file_content_str, 'utf-8')
except UnicodeDecodeError:
logging.warning(
get_logger().warning(
f"Cannot decode file {diff['old_path']} or {diff['new_path']} in merge request {self.id_mr}")
edit_type = EDIT_TYPE.MODIFIED
@ -135,7 +134,7 @@ class GitLabProvider(GitProvider):
self.mr.description = pr_body
self.mr.save()
except Exception as e:
logging.exception(f"Could not update merge request {self.id_mr} description: {e}")
get_logger().exception(f"Could not update merge request {self.id_mr} description: {e}")
def publish_comment(self, mr_comment: str, is_temporary: bool = False):
comment = self.mr.notes.create({'body': mr_comment})
@ -157,12 +156,12 @@ class GitLabProvider(GitProvider):
def send_inline_comment(self,body: str,edit_type: str,found: bool,relevant_file: str,relevant_line_in_file: int,
source_line_no: int, target_file: str,target_line_no: int) -> None:
if not found:
logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
else:
# in order to have exact sha's we have to find correct diff for this change
diff = self.get_relevant_diff(relevant_file, relevant_line_in_file)
if diff is None:
logger.error(f"Could not get diff for merge request {self.id_mr}")
get_logger().error(f"Could not get diff for merge request {self.id_mr}")
raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}")
pos_obj = {'position_type': 'text',
'new_path': target_file.filename,
@ -175,23 +174,23 @@ class GitLabProvider(GitProvider):
else:
pos_obj['new_line'] = target_line_no - 1
pos_obj['old_line'] = source_line_no - 1
logging.debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
get_logger().debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
self.mr.discussions.create({'body': body, 'position': pos_obj})
def get_relevant_diff(self, relevant_file: str, relevant_line_in_file: int) -> Optional[dict]:
changes = self.mr.changes() # Retrieve the changes for the merge request once
if not changes:
logging.error('No changes found for the merge request.')
get_logger().error('No changes found for the merge request.')
return None
all_diffs = self.mr.diffs.list(get_all=True)
if not all_diffs:
logging.error('No diffs found for the merge request.')
get_logger().error('No diffs found for the merge request.')
return None
for diff in all_diffs:
for change in changes['changes']:
if change['new_path'] == relevant_file and relevant_line_in_file in change['diff']:
return diff
logging.debug(
get_logger().debug(
f'No relevant diff found for {relevant_file} {relevant_line_in_file}. Falling back to last diff.')
return self.last_diff # fallback to last_diff if no relevant diff is found
@ -226,7 +225,7 @@ class GitLabProvider(GitProvider):
self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
target_file, target_line_no)
except Exception as e:
logging.exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")
get_logger().exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")
# note that we publish suggestions one-by-one. so, if one fails, the rest will still be published
return True
@ -290,7 +289,7 @@ class GitLabProvider(GitProvider):
for comment in self.temp_comments:
comment.delete()
except Exception as e:
logging.exception(f"Failed to remove temp comments, error: {e}")
get_logger().exception(f"Failed to remove temp comments, error: {e}")
def get_title(self):
return self.mr.title
@ -358,7 +357,7 @@ class GitLabProvider(GitProvider):
self.mr.labels = list(set(pr_types))
self.mr.save()
except Exception as e:
logging.exception(f"Failed to publish labels, error: {e}")
get_logger().exception(f"Failed to publish labels, error: {e}")
def publish_inline_comments(self, comments: list[dict]):
pass
@ -410,6 +409,6 @@ class GitLabProvider(GitProvider):
return link
except Exception as e:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Failed adding line link, error: {e}")
get_logger().info(f"Failed adding line link, error: {e}")
return ""

4
pr_agent/git_providers/local_git_provider.py
View File

@ -1,4 +1,3 @@
import logging
from collections import Counter
from pathlib import Path
from typing import List
@ -7,6 +6,7 @@ from git import Repo
from pr_agent.config_loader import _find_repository_root, get_settings
from pr_agent.git_providers.git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
from pr_agent.log import get_logger
class PullRequestMimic:
@ -49,7 +49,7 @@ class LocalGitProvider(GitProvider):
"""
Prepare the repository for PR-mimic generation.
"""
logging.debug('Preparing repository for PR-mimic generation...')
get_logger().debug('Preparing repository for PR-mimic generation...')
if self.repo.is_dirty():
raise ValueError('The repository is not in a clean state. Please commit or stash pending changes.')
if self.target_branch_name not in self.repo.heads:

4
pr_agent/git_providers/utils.py
View File

@ -1,5 +1,4 @@
import copy
import logging
import os
import tempfile
@ -7,6 +6,7 @@ from dynaconf import Dynaconf
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.log import get_logger
def apply_repo_settings(pr_url):
@ -32,4 +32,4 @@ def apply_repo_settings(pr_url):
try:
os.remove(repo_settings_file)
except Exception as e:
logging.error(f"Failed to remove temporary settings file {repo_settings_file}", e)
get_logger().error(f"Failed to remove temporary settings file {repo_settings_file}", e)

40
pr_agent/log/__init__.py Normal file
View File

@ -0,0 +1,40 @@
import json
import logging
import sys
from enum import Enum
from loguru import logger
class LoggingFormat(str, Enum):
CONSOLE = "CONSOLE"
JSON = "JSON"
def json_format(record: dict) -> str:
return record["message"]
def setup_logger(level: str = "INFO", fmt: LoggingFormat = LoggingFormat.CONSOLE):
level: int = logging.getLevelName(level.upper())
if type(level) is not int:
level = logging.INFO
if fmt == LoggingFormat.JSON:
logger.remove(None)
logger.add(
sys.stdout,
level=level,
format="{message}",
colorize=False,
serialize=True,
)
elif fmt == LoggingFormat.CONSOLE:
logger.remove(None)
logger.add(sys.stdout, level=level, colorize=True)
return logger
def get_logger(*args, **kwargs):
return logger

13
pr_agent/servers/bitbucket_app.py
View File

@ -1,9 +1,7 @@
import copy
import hashlib
import json
import logging
import os
import sys
import time
import jwt
@ -18,9 +16,10 @@ from starlette_context.middleware import RawContextMiddleware
from pr_agent.agent.pr_agent import PRAgent
from pr_agent.config_loader import get_settings, global_settings
from pr_agent.log import LoggingFormat, get_logger, setup_logger
from pr_agent.secret_providers import get_secret_provider
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
setup_logger(fmt=LoggingFormat.JSON)
router = APIRouter()
secret_provider = get_secret_provider()
@ -49,7 +48,7 @@ async def get_bearer_token(shared_secret: str, client_key: str):
bearer_token = response.json()["access_token"]
return bearer_token
except Exception as e:
logging.error(f"Failed to get bearer token: {e}")
get_logger().error(f"Failed to get bearer token: {e}")
raise e
@router.get("/")
@ -60,7 +59,7 @@ async def handle_manifest(request: Request, response: Response):
manifest = manifest.replace("app_key", get_settings().bitbucket.app_key)
manifest = manifest.replace("base_url", get_settings().bitbucket.base_url)
except:
logging.error("Failed to replace api_key in Bitbucket manifest, trying to continue")
get_logger().error("Failed to replace api_key in Bitbucket manifest, trying to continue")
manifest_obj = json.loads(manifest)
return JSONResponse(manifest_obj)
@ -92,7 +91,7 @@ async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Req
comment_body = data["data"]["comment"]["content"]["raw"]
await agent.handle_request(pr_url, comment_body)
except Exception as e:
logging.error(f"Failed to handle webhook: {e}")
get_logger().error(f"Failed to handle webhook: {e}")
background_tasks.add_task(inner)
return "OK"
@ -115,7 +114,7 @@ async def handle_installed_webhooks(request: Request, response: Response):
}
secret_provider.store_secret(username, json.dumps(secrets))
except Exception as e:
logging.error(f"Failed to register user: {e}")
get_logger().error(f"Failed to register user: {e}")
return JSONResponse({"error": "Unable to register user"}, status_code=500)
@router.post("/uninstalled")

11
pr_agent/servers/gerrit_server.py
View File

@ -1,6 +1,4 @@
import copy
import logging
import sys
from enum import Enum
from json import JSONDecodeError
@ -12,9 +10,10 @@ from starlette_context import context
from starlette_context.middleware import RawContextMiddleware
from pr_agent.agent.pr_agent import PRAgent
from pr_agent.config_loader import global_settings, get_settings
from pr_agent.config_loader import get_settings, global_settings
from pr_agent.log import get_logger, setup_logger
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
setup_logger()
router = APIRouter()
@ -35,7 +34,7 @@ class Item(BaseModel):
@router.post("/api/v1/gerrit/{action}")
async def handle_gerrit_request(action: Action, item: Item):
logging.debug("Received a Gerrit request")
get_logger().debug("Received a Gerrit request")
context["settings"] = copy.deepcopy(global_settings)
if action == Action.ask:
@ -54,7 +53,7 @@ async def get_body(request):
try:
body = await request.json()
except JSONDecodeError as e:
logging.error("Error parsing request body", e)
get_logger().error("Error parsing request body", e)
return {}
return body

47
pr_agent/servers/github_app.py
View File

@ -1,6 +1,4 @@
import copy
import logging
import sys
import os
import time
from typing import Any, Dict
@ -16,9 +14,11 @@ from pr_agent.algo.utils import update_settings_from_args
from pr_agent.config_loader import get_settings, global_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.git_providers.utils import apply_repo_settings
from pr_agent.log import LoggingFormat, get_logger, setup_logger
from pr_agent.servers.utils import verify_signature
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
setup_logger(fmt=LoggingFormat.JSON)
router = APIRouter()
@ -29,11 +29,11 @@ async def handle_github_webhooks(request: Request, response: Response):
Verifies the request signature, parses the request body, and passes it to the handle_request function for further
processing.
"""
logging.debug("Received a GitHub webhook")
get_logger().debug("Received a GitHub webhook")
body = await get_body(request)
logging.debug(f'Request body:\n{body}')
get_logger().debug(f'Request body:\n{body}')
installation_id = body.get("installation", {}).get("id")
context["installation_id"] = installation_id
context["settings"] = copy.deepcopy(global_settings)
@ -45,13 +45,13 @@ async def handle_github_webhooks(request: Request, response: Response):
@router.post("/api/v1/marketplace_webhooks")
async def handle_marketplace_webhooks(request: Request, response: Response):
body = await get_body(request)
logging.info(f'Request body:\n{body}')
get_logger().info(f'Request body:\n{body}')
async def get_body(request):
try:
body = await request.json()
except Exception as e:
logging.error("Error parsing request body", e)
get_logger().error("Error parsing request body", e)
raise HTTPException(status_code=400, detail="Error parsing request body") from e
webhook_secret = getattr(get_settings().github, 'webhook_secret', None)
if webhook_secret:
@ -77,8 +77,8 @@ async def handle_request(body: Dict[str, Any], event: str):
return {}
agent = PRAgent()
bot_user = get_settings().github_app.bot_user
logging.info(f"action: '{action}'")
logging.info(f"event: '{event}'")
sender = body.get("sender", {}).get("login")
log_context = {"action": action, "event": event, "sender": sender}
if get_settings().github_app.duplicate_requests_cache and _is_duplicate_request(body):
return {}
@ -88,22 +88,23 @@ async def handle_request(body: Dict[str, Any], event: str):
if "comment" not in body:
return {}
comment_body = body.get("comment", {}).get("body")
sender = body.get("sender", {}).get("login")
if sender and bot_user in sender:
logging.info(f"Ignoring comment from {bot_user} user")
get_logger().info(f"Ignoring comment from {bot_user} user")
return {}
logging.info(f"Processing comment from {sender} user")
get_logger().info(f"Processing comment from {sender} user")
if "issue" in body and "pull_request" in body["issue"] and "url" in body["issue"]["pull_request"]:
api_url = body["issue"]["pull_request"]["url"]
elif "comment" in body and "pull_request_url" in body["comment"]:
api_url = body["comment"]["pull_request_url"]
else:
return {}
logging.info(body)
logging.info(f"Handling comment because of event={event} and action={action}")
log_context["api_url"] = api_url
get_logger().info(body)
get_logger().info(f"Handling comment because of event={event} and action={action}")
comment_id = body.get("comment", {}).get("id")
provider = get_git_provider()(pr_url=api_url)
await agent.handle_request(api_url, comment_body, notify=lambda: provider.add_eyes_reaction(comment_id))
with get_logger().contextualize(**log_context):
await agent.handle_request(api_url, comment_body, notify=lambda: provider.add_eyes_reaction(comment_id))
# handle pull_request event:
# automatically review opened/reopened/ready_for_review PRs as long as they're not in draft,
@ -115,6 +116,7 @@ async def handle_request(body: Dict[str, Any], event: str):
api_url = pull_request.get("url")
if not api_url:
return {}
log_context["api_url"] = api_url
if pull_request.get("draft", True) or pull_request.get("state") != "open" or pull_request.get("user", {}).get("login", "") == bot_user:
return {}
if action in get_settings().github_app.handle_pr_actions:
@ -124,7 +126,7 @@ async def handle_request(body: Dict[str, Any], event: str):
if pull_request.get("created_at") == pull_request.get("updated_at"):
# avoid double reviews when opening a PR for the first time
return {}
logging.info(f"Performing review because of event={event} and action={action}")
get_logger().info(f"Performing review because of event={event} and action={action}")
apply_repo_settings(api_url)
for command in get_settings().github_app.pr_commands:
split_command = command.split(" ")
@ -132,11 +134,12 @@ async def handle_request(body: Dict[str, Any], event: str):
args = split_command[1:]
other_args = update_settings_from_args(args)
new_command = ' '.join([command] + other_args)
logging.info(body)
logging.info(f"Performing command: {new_command}")
await agent.handle_request(api_url, new_command)
get_logger().info(body)
get_logger().info(f"Performing command: {new_command}")
with get_logger().contextualize(**log_context):
await agent.handle_request(api_url, new_command)
logging.info("event or action does not require handling")
get_logger().info("event or action does not require handling")
return {}
@ -146,7 +149,7 @@ def _is_duplicate_request(body: Dict[str, Any]) -> bool:
This function checks if the request is duplicate and if so - ignores it.
"""
request_hash = hash(str(body))
logging.info(f"request_hash: {request_hash}")
get_logger().info(f"request_hash: {request_hash}")
request_time = time.monotonic()
ttl = get_settings().github_app.duplicate_requests_cache_ttl # in seconds
to_delete = [key for key, key_time in _duplicate_requests_cache.items() if request_time - key_time > ttl]
@ -155,7 +158,7 @@ def _is_duplicate_request(body: Dict[str, Any]) -> bool:
is_duplicate = request_hash in _duplicate_requests_cache
_duplicate_requests_cache[request_hash] = request_time
if is_duplicate:
logging.info(f"Ignoring duplicate request {request_hash}")
get_logger().info(f"Ignoring duplicate request {request_hash}")
return is_duplicate

9
pr_agent/servers/github_polling.py
View File

@ -1,6 +1,4 @@
import asyncio
import logging
import sys
from datetime import datetime, timezone
import aiohttp
@ -8,9 +6,10 @@ import aiohttp
from pr_agent.agent.pr_agent import PRAgent
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.log import LoggingFormat, get_logger, setup_logger
from pr_agent.servers.help import bot_help_text
logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
setup_logger(fmt=LoggingFormat.JSON)
NOTIFICATION_URL = "https://api.github.com/notifications"
@ -94,7 +93,7 @@ async def polling_loop():
comment_body = comment['body'] if 'body' in comment else ''
commenter_github_user = comment['user']['login'] \
if 'user' in comment else ''
logging.info(f"Commenter: {commenter_github_user}\nComment: {comment_body}")
get_logger().info(f"Commenter: {commenter_github_user}\nComment: {comment_body}")
user_tag = "@" + user_id
if user_tag not in comment_body:
continue
@ -112,7 +111,7 @@ async def polling_loop():
print(f"Failed to fetch notifications. Status code: {response.status}")
except Exception as e:
logging.error(f"Exception during processing of a notification: {e}")
get_logger().error(f"Exception during processing of a notification: {e}")
if __name__ == '__main__':

11
pr_agent/servers/gitlab_webhook.py
View File

@ -1,7 +1,5 @@
import copy
import json
import logging
import sys
import uvicorn
from fastapi import APIRouter, FastAPI, Request, status
@ -14,9 +12,10 @@ from starlette_context.middleware import RawContextMiddleware
from pr_agent.agent.pr_agent import PRAgent
from pr_agent.config_loader import get_settings, global_settings
from pr_agent.log import get_logger, setup_logger
from pr_agent.secret_providers import get_secret_provider
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
setup_logger()
router = APIRouter()
secret_provider = get_secret_provider() if get_settings().get("CONFIG.SECRET_PROVIDER") else None
@ -33,7 +32,7 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
context["settings"] = copy.deepcopy(global_settings)
context["settings"].gitlab.personal_access_token = gitlab_token
except Exception as e:
logging.error(f"Failed to validate secret {request_token}: {e}")
get_logger().error(f"Failed to validate secret {request_token}: {e}")
return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
elif get_settings().get("GITLAB.SHARED_SECRET"):
secret = get_settings().get("GITLAB.SHARED_SECRET")
@ -45,9 +44,9 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
if not gitlab_token:
return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
data = await request.json()
logging.info(json.dumps(data))
get_logger().info(json.dumps(data))
if data.get('object_kind') == 'merge_request' and data['object_attributes'].get('action') in ['open', 'reopen']:
logging.info(f"A merge request has been opened: {data['object_attributes'].get('title')}")
get_logger().info(f"A merge request has been opened: {data['object_attributes'].get('title')}")
url = data['object_attributes'].get('url')
background_tasks.add_task(PRAgent().handle_request, url, "/review")
elif data.get('object_kind') == 'note' and data['event_type'] == 'note':

6
pr_agent/servers/serverless.py
View File

@ -1,12 +1,10 @@
import logging
from fastapi import FastAPI
from mangum import Mangum
from pr_agent.log import setup_logger
from pr_agent.servers.github_app import router
logger = logging.getLogger()
logger.setLevel(logging.DEBUG)
setup_logger()
app = FastAPI()
app.include_router(router)

37
pr_agent/tools/pr_add_docs.py
View File

@ -1,16 +1,17 @@
import copy
import logging
import textwrap
from typing import List, Dict
from typing import Dict
from jinja2 import Environment, StrictUndefined
from pr_agent.algo.ai_handler import AiHandler
from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, get_pr_multi_diffs
from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import load_yaml
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import BitbucketProvider, 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.log import get_logger
class PRAddDocs:
@ -43,34 +44,34 @@ class PRAddDocs:
async def run(self):
try:
logging.info('Generating code Docs for PR...')
get_logger().info('Generating code Docs for PR...')
if get_settings().config.publish_output:
self.git_provider.publish_comment("Generating Documentation...", is_temporary=True)
logging.info('Preparing PR documentation...')
get_logger().info('Preparing PR documentation...')
await retry_with_fallback_models(self._prepare_prediction)
data = self._prepare_pr_code_docs()
if (not data) or (not 'Code Documentation' in data):
logging.info('No code documentation found for PR.')
get_logger().info('No code documentation found for PR.')
return
if get_settings().config.publish_output:
logging.info('Pushing PR documentation...')
get_logger().info('Pushing PR documentation...')
self.git_provider.remove_initial_comment()
logging.info('Pushing inline code documentation...')
get_logger().info('Pushing inline code documentation...')
self.push_inline_docs(data)
except Exception as e:
logging.error(f"Failed to generate code documentation for PR, error: {e}")
get_logger().error(f"Failed to generate code documentation for PR, error: {e}")
async def _prepare_prediction(self, model: str):
logging.info('Getting PR diff...')
get_logger().info('Getting PR diff...')
self.patches_diff = get_pr_diff(self.git_provider,
self.token_handler,
model,
add_line_numbers_to_hunks=True,
disable_extra_lines=False)
logging.info('Getting AI prediction...')
get_logger().info('Getting AI prediction...')
self.prediction = await self._get_prediction(model)
async def _get_prediction(self, model: str):
@ -80,8 +81,8 @@ class PRAddDocs:
system_prompt = environment.from_string(get_settings().pr_add_docs_prompt.system).render(variables)
user_prompt = environment.from_string(get_settings().pr_add_docs_prompt.user).render(variables)
if get_settings().config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
get_logger().info(f"\nSystem prompt:\n{system_prompt}")
get_logger().info(f"\nUser prompt:\n{user_prompt}")
response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
system=system_prompt, user=user_prompt)
@ -103,7 +104,7 @@ class PRAddDocs:
for d in data['Code Documentation']:
try:
if get_settings().config.verbosity_level >= 2:
logging.info(f"add_docs: {d}")
get_logger().info(f"add_docs: {d}")
relevant_file = d['relevant file'].strip()
relevant_line = int(d['relevant line']) # absolute position
documentation = d['documentation']
@ -118,11 +119,11 @@ class PRAddDocs:
'relevant_lines_end': relevant_line})
except Exception:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Could not parse code docs: {d}")
get_logger().info(f"Could not parse code docs: {d}")
is_successful = self.git_provider.publish_code_suggestions(docs)
if not is_successful:
logging.info("Failed to publish code docs, trying to publish each docs separately")
get_logger().info("Failed to publish code docs, trying to publish each docs separately")
for doc_suggestion in docs:
self.git_provider.publish_code_suggestions([doc_suggestion])
@ -154,7 +155,7 @@ class PRAddDocs:
new_code_snippet = new_code_snippet.rstrip() + "\n" + original_initial_line
except Exception as e:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
get_logger().info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
return new_code_snippet

51
pr_agent/tools/pr_code_suggestions.py
View File

@ -1,16 +1,17 @@
import copy
import logging
import textwrap
from typing import List, Dict
from typing import Dict, List
from jinja2 import Environment, StrictUndefined
from pr_agent.algo.ai_handler import AiHandler
from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, get_pr_multi_diffs
from pr_agent.algo.pr_processing import get_pr_diff, get_pr_multi_diffs, retry_with_fallback_models
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import load_yaml
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import BitbucketProvider, 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.log import get_logger
class PRCodeSuggestions:
@ -52,42 +53,42 @@ class PRCodeSuggestions:
async def run(self):
try:
logging.info('Generating code suggestions for PR...')
get_logger().info('Generating code suggestions for PR...')
if get_settings().config.publish_output:
self.git_provider.publish_comment("Preparing review...", is_temporary=True)
logging.info('Preparing PR review...')
get_logger().info('Preparing PR review...')
if not self.is_extended:
await retry_with_fallback_models(self._prepare_prediction)
data = self._prepare_pr_code_suggestions()
else:
data = await retry_with_fallback_models(self._prepare_prediction_extended)
if (not data) or (not 'Code suggestions' in data):
logging.info('No code suggestions found for PR.')
get_logger().info('No code suggestions found for PR.')
return
if (not self.is_extended and get_settings().pr_code_suggestions.rank_suggestions) or \
(self.is_extended and get_settings().pr_code_suggestions.rank_extended_suggestions):
logging.info('Ranking Suggestions...')
get_logger().info('Ranking Suggestions...')
data['Code suggestions'] = await self.rank_suggestions(data['Code suggestions'])
if get_settings().config.publish_output:
logging.info('Pushing PR review...')
get_logger().info('Pushing PR review...')
self.git_provider.remove_initial_comment()
logging.info('Pushing inline code suggestions...')
get_logger().info('Pushing inline code suggestions...')
self.push_inline_code_suggestions(data)
except Exception as e:
logging.error(f"Failed to generate code suggestions for PR, error: {e}")
get_logger().error(f"Failed to generate code suggestions for PR, error: {e}")
async def _prepare_prediction(self, model: str):
logging.info('Getting PR diff...')
get_logger().info('Getting PR diff...')
self.patches_diff = get_pr_diff(self.git_provider,
self.token_handler,
model,
add_line_numbers_to_hunks=True,
disable_extra_lines=True)
logging.info('Getting AI prediction...')
get_logger().info('Getting AI prediction...')
self.prediction = await self._get_prediction(model)
async def _get_prediction(self, model: str):
@ -97,8 +98,8 @@ class PRCodeSuggestions:
system_prompt = environment.from_string(get_settings().pr_code_suggestions_prompt.system).render(variables)
user_prompt = environment.from_string(get_settings().pr_code_suggestions_prompt.user).render(variables)
if get_settings().config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
get_logger().info(f"\nSystem prompt:\n{system_prompt}")
get_logger().info(f"\nUser prompt:\n{user_prompt}")
response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
system=system_prompt, user=user_prompt)
@ -120,7 +121,7 @@ class PRCodeSuggestions:
for d in data['Code suggestions']:
try:
if get_settings().config.verbosity_level >= 2:
logging.info(f"suggestion: {d}")
get_logger().info(f"suggestion: {d}")
relevant_file = d['relevant file'].strip()
relevant_lines_start = int(d['relevant lines start']) # absolute position
relevant_lines_end = int(d['relevant lines end'])
@ -136,11 +137,11 @@ class PRCodeSuggestions:
'relevant_lines_end': relevant_lines_end})
except Exception:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Could not parse suggestion: {d}")
get_logger().info(f"Could not parse suggestion: {d}")
is_successful = self.git_provider.publish_code_suggestions(code_suggestions)
if not is_successful:
logging.info("Failed to publish code suggestions, trying to publish each suggestion separately")
get_logger().info("Failed to publish code suggestions, trying to publish each suggestion separately")
for code_suggestion in code_suggestions:
self.git_provider.publish_code_suggestions([code_suggestion])
@ -162,19 +163,19 @@ class PRCodeSuggestions:
new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
except Exception as e:
if get_settings().config.verbosity_level >= 2:
logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
get_logger().info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
return new_code_snippet
async def _prepare_prediction_extended(self, model: str) -> dict:
logging.info('Getting PR diff...')
get_logger().info('Getting PR diff...')
patches_diff_list = get_pr_multi_diffs(self.git_provider, self.token_handler, model,
max_calls=get_settings().pr_code_suggestions.max_number_of_calls)
logging.info('Getting multi AI predictions...')
get_logger().info('Getting multi AI predictions...')
prediction_list = []
for i, patches_diff in enumerate(patches_diff_list):
logging.info(f"Processing chunk {i + 1} of {len(patches_diff_list)}")
get_logger().info(f"Processing chunk {i + 1} of {len(patches_diff_list)}")
self.patches_diff = patches_diff
prediction = await self._get_prediction(model)
prediction_list.append(prediction)
@ -222,8 +223,8 @@ class PRCodeSuggestions:
variables)
user_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_prompt.user).render(variables)
if get_settings().config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
get_logger().info(f"\nSystem prompt:\n{system_prompt}")
get_logger().info(f"\nUser prompt:\n{user_prompt}")
response, finish_reason = await self.ai_handler.chat_completion(model=model, system=system_prompt,
user=user_prompt)
@ -238,7 +239,7 @@ class PRCodeSuggestions:
data_sorted = data_sorted[:new_len]
except Exception as e:
if get_settings().config.verbosity_level >= 1:
logging.info(f"Could not sort suggestions, error: {e}")
get_logger().info(f"Could not sort suggestions, error: {e}")
data_sorted = suggestion_list
return data_sorted

11
pr_agent/tools/pr_config.py
View File

@ -1,7 +1,6 @@
import logging
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.log import get_logger
class PRConfig:
@ -19,11 +18,11 @@ class PRConfig:
self.git_provider = get_git_provider()(pr_url)
async def run(self):
logging.info('Getting configuration settings...')
logging.info('Preparing configs...')
get_logger().info('Getting configuration settings...')
get_logger().info('Preparing configs...')
pr_comment = self._prepare_pr_configs()
if get_settings().config.publish_output:
logging.info('Pushing configs...')
get_logger().info('Pushing configs...')
self.git_provider.publish_comment(pr_comment)
self.git_provider.remove_initial_comment()
return ""
@ -44,5 +43,5 @@ class PRConfig:
comment_str += f"\n{header.lower()}.{key.lower()} = {repr(value) if isinstance(value, str) else value}"
comment_str += " "
if get_settings().config.verbosity_level >= 2:
logging.info(f"comment_str:\n{comment_str}")
get_logger().info(f"comment_str:\n{comment_str}")
return comment_str

23
pr_agent/tools/pr_description.py
View File

@ -1,7 +1,5 @@
import copy
import json
import re
import logging
from typing import List, Tuple
from jinja2 import Environment, StrictUndefined
@ -13,6 +11,7 @@ from pr_agent.algo.utils import load_yaml
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.git_providers.git_provider import get_main_pr_language
from pr_agent.log import get_logger
class PRDescription:
@ -65,13 +64,13 @@ class PRDescription:
"""
try:
logging.info(f"Generating a PR description {self.pr_id}")
get_logger().info(f"Generating a PR description {self.pr_id}")
if get_settings().config.publish_output:
self.git_provider.publish_comment("Preparing PR description...", is_temporary=True)
await retry_with_fallback_models(self._prepare_prediction)
logging.info(f"Preparing answer {self.pr_id}")
get_logger().info(f"Preparing answer {self.pr_id}")
if self.prediction:
self._prepare_data()
else:
@ -88,7 +87,7 @@ class PRDescription:
full_markdown_description = f"## Title\n\n{pr_title}\n\n___\n{pr_body}"
if get_settings().config.publish_output:
logging.info(f"Pushing answer {self.pr_id}")
get_logger().info(f"Pushing answer {self.pr_id}")
if get_settings().pr_description.publish_description_as_comment:
self.git_provider.publish_comment(full_markdown_description)
else:
@ -100,7 +99,7 @@ class PRDescription:
self.git_provider.publish_labels(pr_labels + current_labels)
self.git_provider.remove_initial_comment()
except Exception as e:
logging.error(f"Error generating PR description {self.pr_id}: {e}")
get_logger().error(f"Error generating PR description {self.pr_id}: {e}")
return ""
@ -121,9 +120,9 @@ class PRDescription:
if get_settings().pr_description.use_description_markers and 'pr_agent:' not in self.user_description:
return None
logging.info(f"Getting PR diff {self.pr_id}")
get_logger().info(f"Getting PR diff {self.pr_id}")
self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
logging.info(f"Getting AI prediction {self.pr_id}")
get_logger().info(f"Getting AI prediction {self.pr_id}")
self.prediction = await self._get_prediction(model)
async def _get_prediction(self, model: str) -> str:
@ -144,8 +143,8 @@ class PRDescription:
user_prompt = environment.from_string(get_settings().pr_description_prompt.user).render(variables)
if get_settings().config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
get_logger().info(f"\nSystem prompt:\n{system_prompt}")
get_logger().info(f"\nUser prompt:\n{user_prompt}")
response, finish_reason = await self.ai_handler.chat_completion(
model=model,
@ -178,7 +177,7 @@ class PRDescription:
return pr_types
def _prepare_pr_answer_with_markers(self) -> Tuple[str, str]:
logging.info(f"Using description marker replacements {self.pr_id}")
get_logger().info(f"Using description marker replacements {self.pr_id}")
title = self.vars["title"]
body = self.user_description
if get_settings().pr_description.include_generated_by_header:
@ -252,6 +251,6 @@ class PRDescription:
pr_body += "\n___\n"
if get_settings().config.verbosity_level >= 2:
logging.info(f"title:\n{title}\n{pr_body}")
get_logger().info(f"title:\n{title}\n{pr_body}")
return title, pr_body

18
pr_agent/tools/pr_information_from_user.py
View File

@ -1,5 +1,4 @@
import copy
import logging
from jinja2 import Environment, StrictUndefined
@ -9,6 +8,7 @@ from pr_agent.algo.token_handler import TokenHandler
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.git_providers.git_provider import get_main_pr_language
from pr_agent.log import get_logger
class PRInformationFromUser:
@ -34,22 +34,22 @@ class PRInformationFromUser:
self.prediction = None
async def run(self):
logging.info('Generating question to the user...')
get_logger().info('Generating question to the user...')
if get_settings().config.publish_output:
self.git_provider.publish_comment("Preparing questions...", is_temporary=True)
await retry_with_fallback_models(self._prepare_prediction)
logging.info('Preparing questions...')
get_logger().info('Preparing questions...')
pr_comment = self._prepare_pr_answer()
if get_settings().config.publish_output:
logging.info('Pushing questions...')
get_logger().info('Pushing questions...')
self.git_provider.publish_comment(pr_comment)
self.git_provider.remove_initial_comment()
return ""
async def _prepare_prediction(self, model):
logging.info('Getting PR diff...')
get_logger().info('Getting PR diff...')
self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
logging.info('Getting AI prediction...')
get_logger().info('Getting AI prediction...')
self.prediction = await self._get_prediction(model)
async def _get_prediction(self, model: str):
@ -59,8 +59,8 @@ class PRInformationFromUser:
system_prompt = environment.from_string(get_settings().pr_information_from_user_prompt.system).render(variables)
user_prompt = environment.from_string(get_settings().pr_information_from_user_prompt.user).render(variables)
if get_settings().config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
get_logger().info(f"\nSystem prompt:\n{system_prompt}")
get_logger().info(f"\nUser prompt:\n{user_prompt}")
response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
system=system_prompt, user=user_prompt)
return response
@ -68,7 +68,7 @@ class PRInformationFromUser:
def _prepare_pr_answer(self) -> str:
model_output = self.prediction.strip()
if get_settings().config.verbosity_level >= 2:
logging.info(f"answer_str:\n{model_output}")
get_logger().info(f"answer_str:\n{model_output}")
answer_str = f"{model_output}\n\n Please respond to the questions above in the following format:\n\n" +\
"\n>/answer\n>1) ...\n>2) ...\n>...\n"
return answer_str

18
pr_agent/tools/pr_questions.py
View File

@ -1,5 +1,4 @@
import copy
import logging
from jinja2 import Environment, StrictUndefined
@ -9,6 +8,7 @@ from pr_agent.algo.token_handler import TokenHandler
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.git_providers.git_provider import get_main_pr_language
from pr_agent.log import get_logger
class PRQuestions:
@ -44,22 +44,22 @@ class PRQuestions:
return question_str
async def run(self):
logging.info('Answering a PR question...')
get_logger().info('Answering a PR question...')
if get_settings().config.publish_output:
self.git_provider.publish_comment("Preparing answer...", is_temporary=True)
await retry_with_fallback_models(self._prepare_prediction)
logging.info('Preparing answer...')
get_logger().info('Preparing answer...')
pr_comment = self._prepare_pr_answer()
if get_settings().config.publish_output:
logging.info('Pushing answer...')
get_logger().info('Pushing answer...')
self.git_provider.publish_comment(pr_comment)
self.git_provider.remove_initial_comment()
return ""
async def _prepare_prediction(self, model: str):
logging.info('Getting PR diff...')
get_logger().info('Getting PR diff...')
self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
logging.info('Getting AI prediction...')
get_logger().info('Getting AI prediction...')
self.prediction = await self._get_prediction(model)
async def _get_prediction(self, model: str):
@ -69,8 +69,8 @@ class PRQuestions:
system_prompt = environment.from_string(get_settings().pr_questions_prompt.system).render(variables)
user_prompt = environment.from_string(get_settings().pr_questions_prompt.user).render(variables)
if get_settings().config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
get_logger().info(f"\nSystem prompt:\n{system_prompt}")
get_logger().info(f"\nUser prompt:\n{user_prompt}")
response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
system=system_prompt, user=user_prompt)
return response
@ -79,5 +79,5 @@ class PRQuestions:
answer_str = f"Question: {self.question_str}\n\n"
answer_str += f"Answer:\n{self.prediction.strip()}\n\n"
if get_settings().config.verbosity_level >= 2:
logging.info(f"answer_str:\n{answer_str}")
get_logger().info(f"answer_str:\n{answer_str}")
return answer_str

34
pr_agent/tools/pr_reviewer.py
View File

@ -1,6 +1,4 @@
import copy
import json
import logging
from collections import OrderedDict
from typing import List, Tuple
@ -9,13 +7,13 @@ from jinja2 import Environment, StrictUndefined
from yaml import SafeLoader
from pr_agent.algo.ai_handler import AiHandler
from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, \
find_line_number_of_relevant_line_in_file, clip_tokens
from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.algo.utils import convert_to_markdown, try_fix_json, try_fix_yaml, load_yaml
from pr_agent.algo.utils import convert_to_markdown, load_yaml, try_fix_yaml
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import get_git_provider
from pr_agent.git_providers.git_provider import IncrementalPR, get_main_pr_language
from pr_agent.log import get_logger
from pr_agent.servers.help import actions_help_text, bot_help_text
@ -98,29 +96,29 @@ class PRReviewer:
try:
if self.is_auto and not get_settings().pr_reviewer.automatic_review:
logging.info(f'Automatic review is disabled {self.pr_url}')
get_logger().info(f'Automatic review is disabled {self.pr_url}')
return None
logging.info(f'Reviewing PR: {self.pr_url} ...')
get_logger().info(f'Reviewing PR: {self.pr_url} ...')
if get_settings().config.publish_output:
self.git_provider.publish_comment("Preparing review...", is_temporary=True)
await retry_with_fallback_models(self._prepare_prediction)
logging.info('Preparing PR review...')
get_logger().info('Preparing PR review...')
pr_comment = self._prepare_pr_review()
if get_settings().config.publish_output:
logging.info('Pushing PR review...')
get_logger().info('Pushing PR review...')
self.git_provider.publish_comment(pr_comment)
self.git_provider.remove_initial_comment()
if get_settings().pr_reviewer.inline_code_comments:
logging.info('Pushing inline code comments...')
get_logger().info('Pushing inline code comments...')
self._publish_inline_code_comments()
except Exception as e:
logging.error(f"Failed to review PR: {e}")
get_logger().error(f"Failed to review PR: {e}")
async def _prepare_prediction(self, model: str) -> None:
"""
@ -132,9 +130,9 @@ class PRReviewer:
Returns:
None
"""
logging.info('Getting PR diff...')
get_logger().info('Getting PR diff...')
self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
logging.info('Getting AI prediction...')
get_logger().info('Getting AI prediction...')
self.prediction = await self._get_prediction(model)
async def _get_prediction(self, model: str) -> str:
@ -155,8 +153,8 @@ class PRReviewer:
user_prompt = environment.from_string(get_settings().pr_review_prompt.user).render(variables)
if get_settings().config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
get_logger().info(f"\nSystem prompt:\n{system_prompt}")
get_logger().info(f"\nUser prompt:\n{user_prompt}")
response, finish_reason = await self.ai_handler.chat_completion(
model=model,
@ -249,7 +247,7 @@ class PRReviewer:
# Log markdown response if verbosity level is high
if get_settings().config.verbosity_level >= 2:
logging.info(f"Markdown response:\n{markdown_text}")
get_logger().info(f"Markdown response:\n{markdown_text}")
if markdown_text == None or len(markdown_text) == 0:
markdown_text = ""
@ -268,7 +266,7 @@ class PRReviewer:
try:
data = yaml.load(review_text, Loader=SafeLoader)
except Exception as e:
logging.error(f"Failed to parse AI prediction: {e}")
get_logger().error(f"Failed to parse AI prediction: {e}")
data = try_fix_yaml(review_text)
comments: List[str] = []
@ -277,7 +275,7 @@ class PRReviewer:
relevant_line_in_file = suggestion.get('relevant line', '').strip()
content = suggestion.get('suggestion', '')
if not relevant_file or not relevant_line_in_file or not content:
logging.info("Skipping inline comment with missing file/line/content")
get_logger().info("Skipping inline comment with missing file/line/content")
continue
if self.git_provider.is_supported("create_inline_comment"):

55
pr_agent/tools/pr_similar_issue.py
View File

@ -1,18 +1,17 @@
import copy
import json
import logging
from enum import Enum
from typing import List, Tuple
import pinecone
from typing import List
import openai
import pandas as pd
import pinecone
from pinecone_datasets import Dataset, DatasetMetadata
from pydantic import BaseModel, Field
from pr_agent.algo import MAX_TOKENS
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import get_git_provider
from pinecone_datasets import Dataset, DatasetMetadata
from pr_agent.log import get_logger
MODEL = "text-embedding-ada-002"
@ -62,11 +61,11 @@ class PRSimilarIssue:
upsert = False
if run_from_scratch or upsert: # index the entire repo
logging.info('Indexing the entire repo...')
get_logger().info('Indexing the entire repo...')
logging.info('Getting issues...')
get_logger().info('Getting issues...')
issues = list(repo_obj.get_issues(state='all'))
logging.info('Done')
get_logger().info('Done')
self._update_index_with_issues(issues, repo_name_for_index, upsert=upsert)
else: # update index if needed
pinecone_index = pinecone.Index(index_name=index_name)
@ -92,20 +91,20 @@ class PRSimilarIssue:
break
if issues_to_update:
logging.info(f'Updating index with {counter} new issues...')
get_logger().info(f'Updating index with {counter} new issues...')
self._update_index_with_issues(issues_to_update, repo_name_for_index, upsert=True)
else:
logging.info('No new issues to update')
get_logger().info('No new issues to update')
async def run(self):
logging.info('Getting issue...')
get_logger().info('Getting issue...')
repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
issue_main = self.git_provider.repo_obj.get_issue(original_issue_number)
issue_str, comments, number = self._process_issue(issue_main)
openai.api_key = get_settings().openai.key
logging.info('Done')
get_logger().info('Done')
logging.info('Querying...')
get_logger().info('Querying...')
res = openai.Embedding.create(input=[issue_str], engine=MODEL)
embeds = [record['embedding'] for record in res['data']]
pinecone_index = pinecone.Index(index_name=self.index_name)
@ -127,9 +126,9 @@ class PRSimilarIssue:
else:
relevant_comment_number_list.append(-1)
score_list.append(str("{:.2f}".format(r['score'])))
logging.info('Done')
get_logger().info('Done')
logging.info('Publishing response...')
get_logger().info('Publishing response...')
similar_issues_str = "### Similar Issues\n___\n\n"
for i, issue_number_similar in enumerate(relevant_issues_number_list):
issue = self.git_provider.repo_obj.get_issue(issue_number_similar)
@ -140,8 +139,8 @@ class PRSimilarIssue:
similar_issues_str += f"{i + 1}. **[{title}]({url})** (score={score_list[i]})\n\n"
if get_settings().config.publish_output:
response = issue_main.create_comment(similar_issues_str)
logging.info(similar_issues_str)
logging.info('Done')
get_logger().info(similar_issues_str)
get_logger().info('Done')
def _process_issue(self, issue):
header = issue.title
@ -155,7 +154,7 @@ class PRSimilarIssue:
return issue_str, comments, number
def _update_index_with_issues(self, issues_list, repo_name_for_index, upsert=False):
logging.info('Processing issues...')
get_logger().info('Processing issues...')
corpus = Corpus()
example_issue_record = Record(
id=f"example_issue_{repo_name_for_index}",
@ -171,9 +170,9 @@ class PRSimilarIssue:
counter += 1
if counter % 100 == 0:
logging.info(f"Scanned {counter} issues")
get_logger().info(f"Scanned {counter} issues")
if counter >= self.max_issues_to_scan:
logging.info(f"Scanned {self.max_issues_to_scan} issues, stopping")
get_logger().info(f"Scanned {self.max_issues_to_scan} issues, stopping")
break
issue_str, comments, number = self._process_issue(issue)
@ -210,9 +209,9 @@ class PRSimilarIssue:
)
corpus.append(comment_record)
df = pd.DataFrame(corpus.dict()["documents"])
logging.info('Done')
get_logger().info('Done')
logging.info('Embedding...')
get_logger().info('Embedding...')
openai.api_key = get_settings().openai.key
list_to_encode = list(df["text"].values)
try:
@ -220,7 +219,7 @@ class PRSimilarIssue:
embeds = [record['embedding'] for record in res['data']]
except:
embeds = []
logging.error('Failed to embed entire list, embedding one by one...')
get_logger().error('Failed to embed entire list, embedding one by one...')
for i, text in enumerate(list_to_encode):
try:
res = openai.Embedding.create(input=[text], engine=MODEL)
@ -231,21 +230,21 @@ class PRSimilarIssue:
meta = DatasetMetadata.empty()
meta.dense_model.dimension = len(embeds[0])
ds = Dataset.from_pandas(df, meta)
logging.info('Done')
get_logger().info('Done')
api_key = get_settings().pinecone.api_key
environment = get_settings().pinecone.environment
if not upsert:
logging.info('Creating index from scratch...')
get_logger().info('Creating index from scratch...')
ds.to_pinecone_index(self.index_name, api_key=api_key, environment=environment)
else:
logging.info('Upserting index...')
get_logger().info('Upserting index...')
namespace = ""
batch_size: int = 100
concurrency: int = 10
pinecone.init(api_key=api_key, environment=environment)
ds._upsert_to_index(self.index_name, namespace, batch_size, concurrency)
logging.info('Done')
get_logger().info('Done')
class IssueLevel(str, Enum):

26
pr_agent/tools/pr_update_changelog.py
View File

@ -1,5 +1,4 @@
import copy
import logging
from datetime import date
from time import sleep
from typing import Tuple
@ -10,8 +9,9 @@ from pr_agent.algo.ai_handler import AiHandler
from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
from pr_agent.algo.token_handler import TokenHandler
from pr_agent.config_loader import get_settings
from pr_agent.git_providers import GithubProvider, 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.log import get_logger
CHANGELOG_LINES = 50
@ -48,26 +48,26 @@ class PRUpdateChangelog:
async def run(self):
# assert type(self.git_provider) == GithubProvider, "Currently only Github is supported"
logging.info('Updating the changelog...')
get_logger().info('Updating the changelog...')
if get_settings().config.publish_output:
self.git_provider.publish_comment("Preparing changelog updates...", is_temporary=True)
await retry_with_fallback_models(self._prepare_prediction)
logging.info('Preparing PR changelog updates...')
get_logger().info('Preparing PR changelog updates...')
new_file_content, answer = self._prepare_changelog_update()
if get_settings().config.publish_output:
self.git_provider.remove_initial_comment()
logging.info('Publishing changelog updates...')
get_logger().info('Publishing changelog updates...')
if self.commit_changelog:
logging.info('Pushing PR changelog updates to repo...')
get_logger().info('Pushing PR changelog updates to repo...')
self._push_changelog_update(new_file_content, answer)
else:
logging.info('Publishing PR changelog as comment...')
get_logger().info('Publishing PR changelog as comment...')
self.git_provider.publish_comment(f"**Changelog updates:**\n\n{answer}")
async def _prepare_prediction(self, model: str):
logging.info('Getting PR diff...')
get_logger().info('Getting PR diff...')
self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
logging.info('Getting AI prediction...')
get_logger().info('Getting AI prediction...')
self.prediction = await self._get_prediction(model)
async def _get_prediction(self, model: str):
@ -77,8 +77,8 @@ class PRUpdateChangelog:
system_prompt = environment.from_string(get_settings().pr_update_changelog_prompt.system).render(variables)
user_prompt = environment.from_string(get_settings().pr_update_changelog_prompt.user).render(variables)
if get_settings().config.verbosity_level >= 2:
logging.info(f"\nSystem prompt:\n{system_prompt}")
logging.info(f"\nUser prompt:\n{user_prompt}")
get_logger().info(f"\nSystem prompt:\n{system_prompt}")
get_logger().info(f"\nUser prompt:\n{user_prompt}")
response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
system=system_prompt, user=user_prompt)
@ -100,7 +100,7 @@ class PRUpdateChangelog:
"\n>'/update_changelog --pr_update_changelog.push_changelog_changes=true'\n"
if get_settings().config.verbosity_level >= 2:
logging.info(f"answer:\n{answer}")
get_logger().info(f"answer:\n{answer}")
return new_file_content, answer
@ -149,7 +149,7 @@ Example:
except Exception:
self.changelog_file_str = ""
if self.commit_changelog:
logging.info("No CHANGELOG.md file found in the repository. Creating one...")
get_logger().info("No CHANGELOG.md file found in the repository. Creating one...")
changelog_file = self.git_provider.repo_obj.create_file(path="CHANGELOG.md",
message='add CHANGELOG.md',
content="",

1
requirements.txt
View File

@ -21,3 +21,4 @@ azure-devops==7.1.0b3
msrest==0.7.1
pinecone-client
pinecone-datasets @ git+https://github.com/mrT23/pinecone-datasets.git@main
loguru==0.7.2