xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-02 20:00:41 +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

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(