xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-20 04:20:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' of github.com:PrashantDixit0/pr-agent

Browse Source
This commit is contained in:
PrashantDixit-dev
2023-12-25 00:41:28 +05:30
parent d8d954bb0f 08e9a91021
commit 1632696c2f
27 changed files with 353 additions and 262 deletions
Download Patch File Download Diff File Expand all files Collapse all files

80
pr_agent/algo/pr_processing.py
View File

@ -264,20 +264,11 @@ def _get_all_deployments(all_models: List[str]) -> List[str]:
def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
relevant_file: str,
relevant_line_in_file: str) -> Tuple[int, int]:
"""
Find the line number and absolute position of a relevant line in a file.
Args:
diff_files (List[FilePatchInfo]): A list of FilePatchInfo objects representing the patches of files.
relevant_file (str): The name of the file where the relevant line is located.
relevant_line_in_file (str): The content of the relevant line.
Returns:
Tuple[int, int]: A tuple containing the line number and absolute position of the relevant line in the file.
"""
relevant_line_in_file: str,
absolute_position: int = None) -> Tuple[int, int]:
position = -1
absolute_position = -1
if absolute_position is None:
absolute_position = -1
re_hunk_header = re.compile(
r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
@ -285,30 +276,32 @@ def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
if file.filename and (file.filename.strip() == relevant_file):
patch = file.patch
patch_lines = patch.splitlines()
# try to find the line in the patch using difflib, with some margin of error
matches_difflib: list[str | Any] = difflib.get_close_matches(relevant_line_in_file,
patch_lines, n=3, cutoff=0.93)
if len(matches_difflib) == 1 and matches_difflib[0].startswith('+'):
relevant_line_in_file = matches_difflib[0]
delta = 0
start1, size1, start2, size2 = 0, 0, 0, 0
for i, line in enumerate(patch_lines):
if line.startswith('@@'):
delta = 0
match = re_hunk_header.match(line)
start1, size1, start2, size2 = map(int, match.groups()[:4])
elif not line.startswith('-'):
delta += 1
if absolute_position != -1: # matching absolute to relative
for i, line in enumerate(patch_lines):
# new hunk
if line.startswith('@@'):
delta = 0
match = re_hunk_header.match(line)
start1, size1, start2, size2 = map(int, match.groups()[:4])
elif not line.startswith('-'):
delta += 1
#
absolute_position_curr = start2 + delta - 1
if absolute_position_curr == absolute_position:
position = i
break
else:
# try to find the line in the patch using difflib, with some margin of error
matches_difflib: list[str | Any] = difflib.get_close_matches(relevant_line_in_file,
patch_lines, n=3, cutoff=0.93)
if len(matches_difflib) == 1 and matches_difflib[0].startswith('+'):
relevant_line_in_file = matches_difflib[0]
if relevant_line_in_file in line and line[0] != '-':
position = i
absolute_position = start2 + delta - 1
break
if position == -1 and relevant_line_in_file[0] == '+':
no_plus_line = relevant_line_in_file[1:].lstrip()
for i, line in enumerate(patch_lines):
if line.startswith('@@'):
delta = 0
@ -317,12 +310,27 @@ def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
elif not line.startswith('-'):
delta += 1
if no_plus_line in line and line[0] != '-':
# The model might add a '+' to the beginning of the relevant_line_in_file even if originally
# it's a context line
if relevant_line_in_file in line and line[0] != '-':
position = i
absolute_position = start2 + delta - 1
break
if position == -1 and relevant_line_in_file[0] == '+':
no_plus_line = relevant_line_in_file[1:].lstrip()
for i, line in enumerate(patch_lines):
if line.startswith('@@'):
delta = 0
match = re_hunk_header.match(line)
start1, size1, start2, size2 = map(int, match.groups()[:4])
elif not line.startswith('-'):
delta += 1
if no_plus_line in line and line[0] != '-':
# The model might add a '+' to the beginning of the relevant_line_in_file even if originally
# it's a context line
position = i
absolute_position = start2 + delta - 1
break
return position, absolute_position

40
pr_agent/algo/utils.py
View File

@ -102,7 +102,7 @@ def parse_code_suggestion(code_suggestions: dict, i: int = 0, gfm_supported: boo
markdown_text += f"<tr><td>{sub_key}</td><td>{relevant_file}</td></tr>"
# continue
elif sub_key.lower() == 'suggestion':
markdown_text += f"<tr><td>{sub_key} &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</td><td><strong>{sub_value}</strong></td></tr>"
markdown_text += f"<tr><td>{sub_key} &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</td><td><strong>\n\n{sub_value}</strong></td></tr>"
elif sub_key.lower() == 'relevant line':
markdown_text += f"<tr><td>relevant line</td>"
sub_value_list = sub_value.split('](')
@ -316,19 +316,21 @@ def _fix_key_value(key: str, value: str):
return key, value
def load_yaml(response_text: str) -> dict:
def load_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
response_text = response_text.removeprefix('```yaml').rstrip('`')
try:
data = yaml.safe_load(response_text)
except Exception as e:
get_logger().error(f"Failed to parse AI prediction: {e}")
data = try_fix_yaml(response_text)
data = try_fix_yaml(response_text, keys_fix_yaml=keys_fix_yaml)
return data
def try_fix_yaml(response_text: str) -> dict:
def try_fix_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
response_text_lines = response_text.split('\n')
keys = ['relevant line:', 'suggestion content:', 'relevant file:', 'existing code:', 'improved code:']
keys = keys + keys_fix_yaml
# first fallback - try to convert 'relevant line: ...' to relevant line: |-\n ...'
response_text_lines_copy = response_text_lines.copy()
for i in range(0, len(response_text_lines_copy)):
@ -343,18 +345,19 @@ def try_fix_yaml(response_text: str) -> dict:
except:
get_logger().info(f"Failed to parse AI prediction after adding |-\n")
# second fallback - try to remove last lines
data = {}
for i in range(1, len(response_text_lines)):
response_text_lines_tmp = '\n'.join(response_text_lines[:-i])
# second fallback - try to extract only range from first ```yaml to ````
snippet_pattern = r'```(yaml)?[\s\S]*?```'
snippet = re.search(snippet_pattern, '\n'.join(response_text_lines_copy))
if snippet:
snippet_text = snippet.group()
try:
data = yaml.safe_load(response_text_lines_tmp,)
get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
break
data = yaml.safe_load(snippet_text.removeprefix('```yaml').rstrip('`'))
get_logger().info(f"Successfully parsed AI prediction after extracting yaml snippet")
return data
except:
pass
# thrid fallback - try to remove leading and trailing curly brackets
# third fallback - try to remove leading and trailing curly brackets
response_text_copy = response_text.strip().rstrip().removeprefix('{').removesuffix('}')
try:
data = yaml.safe_load(response_text_copy,)
@ -363,6 +366,17 @@ def try_fix_yaml(response_text: str) -> dict:
except:
pass
# fourth fallback - try to remove last lines
data = {}
for i in range(1, len(response_text_lines)):
response_text_lines_tmp = '\n'.join(response_text_lines[:-i])
try:
data = yaml.safe_load(response_text_lines_tmp,)
get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
return data
except:
pass
def set_custom_labels(variables, git_provider=None):
if not get_settings().config.enable_custom_labels:

3
pr_agent/git_providers/azuredevops_provider.py
View File

@ -174,9 +174,6 @@ class AzureDevopsProvider:
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
raise NotImplementedError("Azure DevOps provider does not support publishing inline comment yet")
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
raise NotImplementedError("Azure DevOps provider does not support creating inline comments yet")
def publish_inline_comments(self, comments: list[dict]):
raise NotImplementedError("Azure DevOps provider does not support publishing inline comments yet")

6
pr_agent/git_providers/bitbucket_provider.py
View File

@ -201,8 +201,10 @@ class BitbucketProvider(GitProvider):
get_logger().exception(f"Failed to remove comment, error: {e}")
# funtion to create_inline_comment
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(), relevant_file.strip('`'), relevant_line_in_file)
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(),
relevant_file.strip('`'),
relevant_line_in_file, absolute_position)
if position == -1:
if get_settings().config.verbosity_level >= 2:
get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")

7
pr_agent/git_providers/bitbucket_server_provider.py
View File

@ -210,11 +210,14 @@ class BitbucketServerProvider(GitProvider):
pass
# funtion to create_inline_comment
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
absolute_position: int = None):
position, absolute_position = find_line_number_of_relevant_line_in_file(
self.get_diff_files(),
relevant_file.strip('`'),
relevant_line_in_file
relevant_line_in_file,
absolute_position
)
if position == -1:
if get_settings().config.verbosity_level >= 2:

3
pr_agent/git_providers/codecommit_provider.py
View File

@ -229,9 +229,6 @@ class CodeCommitProvider(GitProvider):
# https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_compared_commit.html
raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
raise NotImplementedError("CodeCommit provider does not support creating inline comments yet")
def publish_inline_comments(self, comments: list[dict]):
raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")

5
pr_agent/git_providers/gerrit_provider.py
View File

@ -380,11 +380,6 @@ class GerritProvider(GitProvider):
'Publishing inline comments is not implemented for the gerrit '
'provider')
def create_inline_comment(self, body: str, relevant_file: str,
relevant_line_in_file: str):
raise NotImplementedError(
'Creating inline comments is not implemented for the gerrit '
'provider')
def publish_labels(self, labels):
# Not applicable to the local git provider,

6
pr_agent/git_providers/git_provider.py
View File

@ -106,9 +106,9 @@ class GitProvider(ABC):
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
pass
@abstractmethod
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
pass
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
absolute_position: int = None):
raise NotImplementedError("This git provider does not support creating inline comments yet")
@abstractmethod
def publish_inline_comments(self, comments: list[dict]):

8
pr_agent/git_providers/github_provider.py
View File

@ -206,8 +206,12 @@ class GithubProvider(GitProvider):
self.publish_inline_comments([self.create_inline_comment(body, relevant_file, relevant_line_in_file)])
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files, relevant_file.strip('`'), relevant_line_in_file)
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
absolute_position: int = None):
position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files,
relevant_file.strip('`'),
relevant_line_in_file,
absolute_position)
if position == -1:
if get_settings().config.verbosity_level >= 2:
get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")

2
pr_agent/git_providers/gitlab_provider.py
View File

@ -183,7 +183,7 @@ 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)
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
raise NotImplementedError("Gitlab provider does not support creating inline comments yet")
def create_inline_comments(self, comments: list[dict]):

3
pr_agent/git_providers/local_git_provider.py
View File

@ -121,9 +121,6 @@ class LocalGitProvider(GitProvider):
def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')
def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
raise NotImplementedError('Creating inline comments is not implemented for the local git provider')
def publish_inline_comments(self, comments: list[dict]):
raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')

2
pr_agent/servers/help.py
View File

@ -3,8 +3,6 @@ commands_text = "> **/review**: Request a review of your Pull Request. \n" \
"> **/improve [--extended]**: Suggest code improvements. Extended mode provides a higher quality feedback. \n" \
"> **/ask \\<QUESTION\\>**: Ask a question about the PR. \n" \
"> **/update_changelog**: Update the changelog based on the PR's contents. \n" \
"> **/add_docs**: Generate docstring for new components introduced in the PR. \n" \
"> **/generate_labels**: Generate labels for the PR based on the PR's contents. \n" \
"> see the [tools guide](https://github.com/Codium-ai/pr-agent/blob/main/docs/TOOLS_GUIDE.md) for more details.\n\n" \
">To edit any configuration parameter from the [configuration.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml), add --config_path=new_value. \n" \
">For example: /review --pr_reviewer.extra_instructions=\"focus on the file: ...\" \n" \

3
pr_agent/settings/configuration.toml
View File

@ -62,6 +62,7 @@ include_generated_by_header=true
[pr_code_suggestions] # /improve #
num_code_suggestions=4
summarize = false
include_improved_code = true
extra_instructions = ""
rank_suggestions = false
# params for '/improve --extended' mode
@ -78,6 +79,8 @@ docs_style = "Sphinx Style" # "Google Style with Args, Returns, Attributes...etc
push_changelog_changes=false
extra_instructions = ""
[pr_analyze] # /analyze #
[pr_config] # /config #
[github]

74
pr_agent/settings/pr_code_suggestions_prompts.toml
View File

@ -32,13 +32,13 @@ __old hunk__
Specific instructions:
- Provide up to {{ num_code_suggestions }} code suggestions. Try to provide diverse and insightful suggestions.
- Prioritize suggestions that address major problems, issues and bugs in the code. As a second priority, suggestions should focus on best practices, code readability, maintainability, enhancments, performance, and other aspects.
- Prioritize suggestions that address major problems, issues and bugs in the code. As a second priority, suggestions should focus on enhancment, best practice, performance, maintainability, and other aspects.
- Don't suggest to add docstring, type hints, or comments.
- Suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
- Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the '__new hunk__' code.
- For each suggestion, make sure to take into consideration also the context, meaning the lines before and after the relevant code.
- Provide the exact line numbers range (inclusive) for each suggestion.
- Assume there is additional relevant code, that is not included in the diff.
- When quoting variables or names from the code, use backticks (`) instead of single quote (').
{%- if extra_instructions %}
@ -49,65 +49,41 @@ Extra instructions from the user:
======
{%- endif %}
The output must be a YAML object equivalent to type PRCodeSuggestions, according to the following Pydantic definitions:
=====
class CodeSuggestion(BaseModel):
relevant_file: str = Field(description="the relevant file full path")
suggestion_content: str = Field(description="an actionable suggestion for meaningfully improving the new code introduced in the PR")
existing_code: str = Field(description="a code snippet, showing the relevant code lines from a '__new hunk__' section. It must be contiguous, correctly formatted and indented, and without line numbers")
relevant_lines_start: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion starts (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
relevant_lines_end: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion ends (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
improved_code: str = Field(description="a new code snippet, that can be used to replace the relevant lines in '__new hunk__' code. Replacement suggestions should be complete, correctly formatted and indented, and without line numbers")
label: str = Field(description="a single label for the suggestion, to help the user understand the suggestion type. For example: 'security', 'bug', 'performance', 'enhancement', 'possible issue', 'best practice', 'maintainability', etc. Other labels are also allowed")
class PRCodeSuggestions(BaseModel):
code_suggestions: List[CodeSuggestion]
=====
You must use the following YAML schema to format your answer:
```yaml
Code suggestions:
type: array
minItems: 1
maxItems: {{ num_code_suggestions }}
uniqueItems: true
items:
relevant file:
type: string
description: the relevant file full path
suggestion content:
type: string
description: |-
a concrete suggestion for meaningfully improving the new PR code.
existing code:
type: string
description: |-
a code snippet showing the relevant code lines from a '__new hunk__' section.
It must be contiguous, correctly formatted and indented, and without line numbers.
relevant lines start:
type: integer
description: |-
The relevant line number from a '__new hunk__' section where the suggestion starts (inclusive).
Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above.
relevant lines end:
type: integer
description: |-
The relevant line number from a '__new hunk__' section where the suggestion ends (inclusive).
Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above.
improved code:
type: string
description: |-
a new code snippet that can be used to replace the relevant lines in '__new hunk__' code.
Replacement suggestions should be complete, correctly formatted and indented, and without line numbers.
```
Example output:
```yaml
Code suggestions:
- relevant file: |-
code_suggestions:
- relevant_file: |-
src/file1.py
suggestion content: |-
suggestion_content: |-
Add a docstring to func1()
existing code: |-
existing_code: |-
def func1():
relevant lines start: |-
12
relevant lines end: |-
12
improved code: |-
relevant_lines_start: 12
relevant_lines_end: 12
improved_code: |-
...
label: |-
...
...
```
Each YAML output MUST be after a newline, indented, with block scalar indicator ('|-').
Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
"""
user="""PR Info:

47
pr_agent/settings/pr_description_prompts.toml
View File

@ -1,10 +1,15 @@
[pr_description_prompt]
system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
Your task is to provide a full description for the PR content - title, type, description, and main files walkthrough.
{%- if enable_custom_labels %}
Your task is to provide a full description for the PR content - files walkthrough, title, type, description and labels.
{%- else %}
Your task is to provide a full description for the PR content - files walkthrough, title, type, and description.
{%- endif %}
- Focus on the new PR code (lines starting with '+').
- Keep in mind that the 'Previous title', 'Previous description' and 'Commit messages' sections may be partial, simplistic, non-informative or out of date. Hence, compare them to the PR diff code, and use them only as a reference.
- The generated title and description should prioritize the most significant changes.
- If needed, each YAML output should be in block scalar indicator ('|-')
- When quoting variables or names from the code, use backticks (`) instead of single quote (').
{%- if extra_instructions %}
@ -45,43 +50,24 @@ Class FileDescription(BaseModel):
{%- endif %}
Class PRDescription(BaseModel):
type: List[PRType] = Field(description="one or more types that describe the PR content. Return the label value, not the name.")
{%- if enable_semantic_files_types %}
pr_files[List[FileDescription]] = Field(max_items=15, description="a list of the files in the PR, and their changes summary.")
{%- endif %}
description: str = Field(description="an informative and concise description of the PR. Use bullet points. Display first the most significant changes.")
title: str = Field(description="an informative title for the PR, describing its main theme")
type: List[PRType] = Field(description="one or more types that describe the PR type. Return the label value, not the name.")
description: str = Field(description="an informative and concise description of the PR. {%- if use_bullet_points %} Use bullet points.{% endif %}")
{%- if enable_custom_labels %}
labels: List[Label] = Field(min_items=0, description="choose the relevant custom labels that describe the PR content, and return their keys. Use the value field of the Label object to better understand the label meaning.")
{%- endif %}
{%- if enable_file_walkthrough %}
main_files_walkthrough: List[FileWalkthrough] = Field(max_items=10)
{%- endif %}
{%- if enable_semantic_files_types %}
pr_files[List[FileDescription]] = Field(max_items=15")
{%- endif %}
=====
Example output:
```yaml
title: |-
...
type:
- ...
- ...
{%- if enable_custom_labels %}
labels:
- |
...
- |
...
{%- endif %}
description: |-
...
{%- if enable_file_walkthrough %}
main_files_walkthrough:
- ...
- ...
{%- endif %}
{%- if enable_semantic_files_types %}
pr_files:
- filename: |
@ -92,6 +78,17 @@ pr_files:
...
...
{%- endif %}
description: |-
...
title: |-
...
{%- if enable_custom_labels %}
labels:
- |
...
- |
...
{%- endif %}
```
Answer should be a valid YAML, and nothing else. Each YAML output MUST be after a newline, with proper indent, and block scalar indicator ('|-')

1
pr_agent/settings/pr_reviewer_prompts.toml
View File

@ -32,6 +32,7 @@ Code suggestions guidelines:
- Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the PR code.
- Don't suggest to add docstring, type hints, or comments.
- Suggestions should focus on the new code added in the PR diff (lines starting with '+')
- When quoting variables or names from the code, use backticks (`) instead of single quote (').
{%- endif %}
{%- if extra_instructions %}

95
pr_agent/tools/pr_code_suggestions.py
View File

@ -65,14 +65,14 @@ class PRCodeSuggestions:
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):
if (not data) or (not 'code_suggestions' in data):
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):
get_logger().info('Ranking Suggestions...')
data['Code suggestions'] = await self.rank_suggestions(data['Code suggestions'])
data['code_suggestions'] = await self.rank_suggestions(data['code_suggestions'])
if get_settings().config.publish_output:
get_logger().info('Pushing PR code suggestions...')
@ -116,44 +116,73 @@ class PRCodeSuggestions:
def _prepare_pr_code_suggestions(self) -> Dict:
review = self.prediction.strip()
data = load_yaml(review)
data = load_yaml(review,
keys_fix_yaml=["relevant_file", "suggestion_content", "existing_code", "improved_code"])
if isinstance(data, list):
data = {'Code suggestions': data}
data = {'code_suggestions': data}
# remove invalid suggestions
suggestion_list = []
for i, suggestion in enumerate(data['code_suggestions']):
if suggestion['existing_code'] != suggestion['improved_code']:
suggestion_list.append(suggestion)
else:
get_logger().debug(
f"Skipping suggestion {i + 1}, because existing code is equal to improved code {suggestion['existing_code']}")
data['code_suggestions'] = suggestion_list
return data
def push_inline_code_suggestions(self, data):
code_suggestions = []
if not data['Code suggestions']:
if not data['code_suggestions']:
get_logger().info('No suggestions found to improve this PR.')
return self.git_provider.publish_comment('No suggestions found to improve this PR.')
for d in data['Code suggestions']:
for d in data['code_suggestions']:
try:
if get_settings().config.verbosity_level >= 2:
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'])
content = d['suggestion content']
new_code_snippet = d['improved code']
relevant_file = d['relevant_file'].strip()
relevant_lines_start = int(d['relevant_lines_start']) # absolute position
relevant_lines_end = int(d['relevant_lines_end'])
content = d['suggestion_content'].rstrip()
new_code_snippet = d['improved_code'].rstrip()
label = d['label'].strip()
if new_code_snippet:
new_code_snippet = self.dedent_code(relevant_file, relevant_lines_start, new_code_snippet)
body = f"**Suggestion:** {content}\n```suggestion\n" + new_code_snippet + "\n```"
code_suggestions.append({'body': body, 'relevant_file': relevant_file,
'relevant_lines_start': relevant_lines_start,
'relevant_lines_end': relevant_lines_end})
if get_settings().pr_code_suggestions.include_improved_code:
body = f"**Suggestion:** {content} [{label}]\n```suggestion\n" + new_code_snippet + "\n```"
code_suggestions.append({'body': body, 'relevant_file': relevant_file,
'relevant_lines_start': relevant_lines_start,
'relevant_lines_end': relevant_lines_end})
else:
if self.git_provider.is_supported("create_inline_comment"):
body = f"**Suggestion:** {content} [{label}]"
comment = self.git_provider.create_inline_comment(body, relevant_file, "",
absolute_position=relevant_lines_end)
if comment:
code_suggestions.append(comment)
else:
get_logger().error("Inline comments are not supported by the git provider")
except Exception:
if get_settings().config.verbosity_level >= 2:
get_logger().info(f"Could not parse suggestion: {d}")
is_successful = self.git_provider.publish_code_suggestions(code_suggestions)
if get_settings().pr_code_suggestions.include_improved_code:
is_successful = self.git_provider.publish_code_suggestions(code_suggestions)
else:
is_successful = self.git_provider.publish_inline_comments(code_suggestions)
if not is_successful:
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])
if get_settings().pr_code_suggestions.include_improved_code:
self.git_provider.publish_code_suggestions([code_suggestion])
else:
self.git_provider.publish_inline_comments([code_suggestion])
def dedent_code(self, relevant_file, relevant_lines_start, new_code_snippet):
try: # dedent code snippet
@ -195,8 +224,8 @@ class PRCodeSuggestions:
for prediction in prediction_list:
self.prediction = prediction
data_per_chunk = self._prepare_pr_code_suggestions()
if "Code suggestions" in data:
data["Code suggestions"].extend(data_per_chunk["Code suggestions"])
if "code_suggestions" in data:
data["code_suggestions"].extend(data_per_chunk["code_suggestions"])
else:
data.update(data_per_chunk)
self.data = data
@ -214,11 +243,8 @@ class PRCodeSuggestions:
"""
suggestion_list = []
# remove invalid suggestions
for i, suggestion in enumerate(data):
if suggestion['existing code'] != suggestion['improved code']:
suggestion_list.append(suggestion)
for suggestion in data:
suggestion_list.append(suggestion)
data_sorted = [[]] * len(suggestion_list)
try:
@ -264,24 +290,25 @@ class PRCodeSuggestions:
for ext in extensions:
extension_to_language[ext] = language
for s in data['Code suggestions']:
for s in data['code_suggestions']:
try:
extension_s = s['relevant file'].rsplit('.')[-1]
code_snippet_link = self.git_provider.get_line_link(s['relevant file'], s['relevant lines start'],
s['relevant lines end'])
data_markdown += f"\n💡 Suggestion:\n\n**{s['suggestion content']}**\n\n"
extension_s = s['relevant_file'].rsplit('.')[-1]
code_snippet_link = self.git_provider.get_line_link(s['relevant_file'], s['relevant_lines_start'],
s['relevant_lines_end'])
label = s['label'].strip()
data_markdown += f"\n💡 [{label}]\n\n**{s['suggestion_content'].rstrip().rstrip()}**\n\n"
if code_snippet_link:
data_markdown += f" File: [{s['relevant file']} ({s['relevant lines start']}-{s['relevant lines end']})]({code_snippet_link})\n\n"
data_markdown += f" File: [{s['relevant_file']} ({s['relevant_lines_start']}-{s['relevant_lines_end']})]({code_snippet_link})\n\n"
else:
data_markdown += f"File: {s['relevant file']} ({s['relevant lines start']}-{s['relevant lines end']})\n\n"
data_markdown += f"File: {s['relevant_file']} ({s['relevant_lines_start']}-{s['relevant_lines_end']})\n\n"
if self.git_provider.is_supported("gfm_markdown"):
data_markdown += "<details> <summary> Example code:</summary>\n\n"
data_markdown += f"___\n\n"
language_name = "python"
if extension_s and (extension_s in extension_to_language):
language_name = extension_to_language[extension_s]
data_markdown += f"Existing code:\n```{language_name}\n{s['existing code']}\n```\n"
data_markdown += f"Improved code:\n```{language_name}\n{s['improved code']}\n```\n"
data_markdown += f"Existing code:\n```{language_name}\n{s['existing_code'].rstrip()}\n```\n"
data_markdown += f"Improved code:\n```{language_name}\n{s['improved_code'].rstrip()}\n```\n"
if self.git_provider.is_supported("gfm_markdown"):
data_markdown += "</details>\n"
data_markdown += "\n___\n\n"
@ -290,5 +317,3 @@ class PRCodeSuggestions:
self.git_provider.publish_comment(data_markdown)
except Exception as e:
get_logger().info(f"Failed to publish summarized code suggestions, error: {e}")

18
pr_agent/tools/pr_description.py
View File

@ -48,7 +48,6 @@ class PRDescription:
"description": self.git_provider.get_pr_description(full=False),
"language": self.main_pr_language,
"diff": "", # empty diff for initial calculation
"use_bullet_points": get_settings().pr_description.use_bullet_points,
"extra_instructions": get_settings().pr_description.extra_instructions,
"commit_messages_str": self.git_provider.get_commit_messages(),
"enable_custom_labels": get_settings().config.enable_custom_labels,
@ -187,6 +186,18 @@ class PRDescription:
# Load the AI prediction data into a dictionary
self.data = load_yaml(self.prediction.strip())
# re-order keys
if 'title' in self.data:
self.data['title'] = self.data.pop('title')
if 'type' in self.data:
self.data['type'] = self.data.pop('type')
if 'labels' in self.data:
self.data['labels'] = self.data.pop('labels')
if 'description' in self.data:
self.data['description'] = self.data.pop('description')
if 'pr_files' in self.data:
self.data['pr_files'] = self.data.pop('pr_files')
if get_settings().pr_description.add_original_user_description and self.user_description:
self.data["User Description"] = self.user_description
@ -371,8 +382,9 @@ class PRDescription:
<summary><strong>{filename_publish}</strong></summary>
<ul>
{filename}<br><br>
<strong>{file_change_description}</strong>
</ul>
**{file_change_description}**
</ul>
</details>
</td>
<td><a href="{link}"> {diff_plus_minus}</a></td>

1
pr_agent/tools/pr_generate_labels.py
View File

@ -43,7 +43,6 @@ class PRGenerateLabels:
"description": self.git_provider.get_pr_description(full=False),
"language": self.main_pr_language,
"diff": "", # empty diff for initial calculation
"use_bullet_points": get_settings().pr_description.use_bullet_points,
"extra_instructions": get_settings().pr_description.extra_instructions,
"commit_messages_str": self.git_provider.get_commit_messages(),
"enable_custom_labels": get_settings().config.enable_custom_labels,