xiaxinhang/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-07-16 10:40:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into introduce-pre-commit

Browse Source
This commit is contained in:
Tal
2024-11-08 09:54:21 +02:00
committed by GitHub
parent 852bb371af f9380c2440
commit 5c5a3e267c
21 changed files with 377 additions and 132 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
pr_agent/settings/configuration.toml
View File

@ -7,6 +7,7 @@ fallback_models=["gpt-4o-2024-05-13"]
git_provider="github"
publish_output=true
publish_output_progress=true
publish_output_no_suggestions=true
verbosity_level=0 # 0,1,2
use_extra_bad_extensions=false
# Configurations
@ -106,10 +107,11 @@ enable_help_text=false
[pr_code_suggestions] # /improve #
max_context_tokens=14000
max_context_tokens=16000
#
commitable_code_suggestions = false
dual_publishing_score_threshold=-1 # -1 to disable, [0-10] to set the threshold (>=) for publishing a code suggestion both in a table and as commitable
focus_only_on_problems=false
#
extra_instructions = ""
rank_suggestions = false
@ -121,7 +123,6 @@ max_history_len=4
# enable to apply suggestion 💎
apply_suggestions_checkbox=true
# suggestions scoring
self_reflect_on_suggestions=true
suggestions_score_threshold=0 # [0-10]| recommend not to set this value above 8, since above it may clip highly relevant suggestions
# params for '/improve --extended' mode
auto_extended_mode=true

40
pr_agent/settings/pr_code_suggestions_prompts.toml
View File

@ -1,7 +1,10 @@
[pr_code_suggestions_prompt]
system="""You are PR-Reviewer, an AI specializing in Pull Request (PR) code analysis and suggestions.
Your task is to examine the provided code diff, focusing on new code (lines prefixed with '+'), and offer concise, actionable suggestions to fix possible bugs and problems, and enhance code quality, readability, and performance.
{%- if not focus_only_on_problems %}
Your task is to examine the provided code diff, focusing on new code (lines prefixed with '+'), and offer concise, actionable suggestions to fix possible bugs and problems, and enhance code quality and performance.
{%- else %}
Your task is to examine the provided code diff, focusing on new code (lines prefixed with '+'), and offer concise, actionable suggestions to fix critical bugs and problems.
{%- endif %}
The PR code diff will be in the following structured format:
======
@ -14,10 +17,10 @@ The PR code diff will be in the following structured format:
@@ ... @@ def func1():
__new hunk__
11 unchanged code line0 in the PR
12 unchanged code line1 in the PR
13 +new code line2 added in the PR
14 unchanged code line3 in the PR
unchanged code line0 in the PR
unchanged code line1 in the PR
+new code line2 added in the PR
unchanged code line3 in the PR
__old hunk__
unchanged code line0
unchanged code line1
@ -35,7 +38,6 @@ __new hunk__
======
- In the format above, the diff is organized into separate '__new hunk__' and '__old hunk__' sections for each code chunk. '__new hunk__' contains the updated code, while '__old hunk__' shows the removed code. If no code was removed in a specific chunk, the __old hunk__ section will be omitted.
- Line numbers were added for the '__new hunk__' sections to help referencing specific lines in the code suggestions. These numbers are for reference only and are not part of the actual code.
- Code lines are prefixed with symbols: '+' for new code added in the PR, '-' for code removed, and ' ' for unchanged code.
{%- if is_ai_metadata %}
- When available, an AI-generated summary will precede each file's diff, with a high-level overview of the changes. Note that this summary may not be fully accurate or complete.
@ -43,9 +45,17 @@ __new hunk__
Specific guidelines for generating code suggestions:
{%- if not focus_only_on_problems %}
- Provide up to {{ num_code_suggestions }} distinct and insightful code suggestions.
- Focus solely on enhancing new code introduced in the PR, identified by '+' prefixes in '__new hunk__' sections (after the line numbers).
{%- else %}
- Provide up to {{ num_code_suggestions }} distinct and insightful code suggestions. Return less suggestions if no pertinent ones are applicable.
{%- endif %}
- Focus solely on enhancing new code introduced in the PR, identified by '+' prefixes in '__new hunk__' sections.
{%- if not focus_only_on_problems %}
- Prioritize suggestions that address potential issues, critical problems, and bugs in the PR code. Avoid repeating changes already implemented in the PR. If no pertinent suggestions are applicable, return an empty list.
{%- else %}
- Only give suggestions that address critical problems and bugs in the PR code. If no relevant suggestions are applicable, return an empty list.
{%- endif %}
- Don't suggest to add docstring, type hints, or comments, to remove unused imports, or to use more specific exception types.
- When referencing variables or names from the code, enclose them in backticks (`). Example: "ensure that `variable_name` is..."
- Be mindful you are viewing a partial PR code diff, not the full codebase. Avoid suggestions that might conflict with unseen code or alerting variables not declared in the visible scope, as the context is incomplete.
@ -67,12 +77,14 @@ class CodeSuggestion(BaseModel):
relevant_file: str = Field(description="Full path of the relevant file")
language: str = Field(description="Programming language used by the relevant file")
suggestion_content: str = Field(description="An actionable suggestion to enhance, improve or fix the new code introduced in the PR. Don't present here actual code snippets, just the suggestion. Be short and concise")
existing_code: str = Field(description="A short code snippet from a '__new hunk__' section that the suggestion aims to enhance or fix. Include only complete code lines, without line numbers. Use ellipsis (...) for brevity if needed. This snippet should represent the specific PR code targeted for improvement.")
existing_code: str = Field(description="A short code snippet from a '__new hunk__' section that the suggestion aims to enhance or fix. Include only complete code lines. Use ellipsis (...) for brevity if needed. This snippet should represent the specific PR code targeted for improvement.")
improved_code: str = Field(description="A refined code snippet that replaces the 'existing_code' snippet after implementing the suggestion.")
one_sentence_summary: str = Field(description="A concise, single-sentence overview of the suggested improvement. Focus on the 'what'. Be general, and avoid method or variable names.")
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 beginning of 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 end of the 'existing code' snippet above")
label: str = Field(description="A single, descriptive label that best characterizes the suggestion type. Possible labels include 'security', 'possible bug', 'possible issue', 'performance', 'enhancement', 'best practice', 'maintainability'. Other relevant labels are also acceptable.")
{%- if not focus_only_on_problems %}
label: str = Field(description="A single, descriptive label that best characterizes the suggestion type. Possible labels include 'security', 'possible bug', 'possible issue', 'performance', 'enhancement', 'best practice', 'maintainability', 'typo'. Other relevant labels are also acceptable.")
{%- else %}
label: str = Field(description="A single, descriptive label that best characterizes the suggestion type. Possible labels include 'security', 'critical bug', 'general'. The 'general' section should be used for suggestions that address a major issue, but are necessarily on a critical level.")
{%- endif %}
class PRCodeSuggestions(BaseModel):
@ -95,8 +107,6 @@ code_suggestions:
...
one_sentence_summary: |
...
relevant_lines_start: 12
relevant_lines_end: 13
label: |
...
```
@ -112,7 +122,7 @@ Title: '{{title}}'
The PR Diff:
======
{{ diff|trim }}
{{ diff_no_line_numbers|trim }}
======

8
pr_agent/settings/pr_code_suggestions_reflect_prompts.toml
View File

@ -15,8 +15,8 @@ Be particularly vigilant for suggestions that:
- Contradict or ignore parts of the PR's modifications
In such cases, assign the suggestion a score of 0.
For valid suggestions, your role is to provide an impartial and precise score assessment that accurately reflects each suggestion's potential impact on the PR's correctness, quality and functionality.
Evaluate each valid suggestion by scoring its potential impact on the PR's correctness, quality and functionality.
In addition, you should also detect the line numbers in the '__new hunk__' section that correspond to the 'existing_code' snippet.
Key guidelines for evaluation:
- Thoroughly examine both the suggestion content and the corresponding PR code diff. Be vigilant for potential errors in each suggestion, ensuring they are logically sound, accurate, and directly derived from the PR code diff.
@ -82,6 +82,8 @@ The output must be a YAML object equivalent to type $PRCodeSuggestionsFeedback,
class CodeSuggestionFeedback(BaseModel):
suggestion_summary: str = Field(description="Repeated from the input")
relevant_file: str = Field(description="Repeated from the input")
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 beginning of the relevant 'existing code' snippet")
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 end of the relevant 'existing code' snippet")
suggestion_score: int = Field(description="Evaluate the suggestion and assign a score from 0 to 10. Give 0 if the suggestion is wrong. For valid suggestions, score from 1 (lowest impact/importance) to 10 (highest impact/importance).")
why: str = Field(description="Briefly explain the score given in 1-2 sentences, focusing on the suggestion's impact, relevance, and accuracy.")
@ -96,6 +98,8 @@ code_suggestions:
- suggestion_summary: |
Use a more descriptive variable name here
relevant_file: "src/file1.py"
relevant_lines_start: 13
relevant_lines_end: 14
suggestion_score: 6
why: |
The variable name 't' is not descriptive enough