xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-03 04:10:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: Refactor code suggestion handling and update YAML schema in pr_code_suggestions.py and pr_code_suggestions_prompts.toml

Browse Source 
- Update key names in pr_code_suggestions.py to use snake_case for consistency
- Implement removal of invalid suggestions where existing code is equal to improved code
- Update YAML parsing in _prepare_pr_code_suggestions method to include keys_fix_yaml parameter
- Refactor push_inline_code_suggestions method to use updated key names
- Update _prepare_prediction_extended method to use new key names
- Refactor _prepare_markdown method to include suggestion label and use updated key names
- Update instructions and YAML schema in pr_code_suggestions_prompts.toml to reflect changes in pr_code_suggestions.py
- Remove redundant removal of invalid suggestions in rank_suggestions method
This commit is contained in:
mrT23
2023-12-24 08:30:35 +02:00
parent ba7781ba00
commit 5dc2595dcf
2 changed files with 57 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

72
pr_agent/settings/pr_code_suggestions_prompts.toml
View File

@ -32,7 +32,7 @@ __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.
@ -49,65 +49,41 @@ Extra instructions from the user:
======
{%- endif %}
The output must be a YAML object equivalent to type $PRCodeSuggestins, according to the following Pydantic definitions:
=====
class CodeSuggestion(BaseModel):
relevant_file: str = Field(description="the relevant file full path")
suggestion_content: str = Field(description="a concrete 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 PRCodeSuggestins(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:

60
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...')
@ -116,27 +116,37 @@ 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()
if new_code_snippet:
new_code_snippet = self.dedent_code(relevant_file, relevant_lines_start, new_code_snippet)
@ -195,8 +205,8 @@ 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 +224,6 @@ class PRCodeSuggestions:
"""
suggestion_list = []
# remove invalid suggestions
for i, suggestion in enumerate(data):
if suggestion['existing code'] != suggestion['improved code']:
suggestion_list.append(suggestion)
data_sorted = [[]] * len(suggestion_list)
try:
@ -264,24 +269,25 @@ 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💡 Type: [{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"