vlx42/AI-based PR Reviewer & Summarizer with Chat Capabilities

AI-based PR Reviewer & Summarizer with Chat Capabilities

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
debugEnable debug modenofalse
max_filesMax files to summarize and review. Less than or equal to 0 means no limit.no150
review_simple_changesReview even when the changes are simplenofalse
review_comment_lgtmLeave comments even if the patch is LGTMnofalse
path_filtersThe path filters, e.g., "src/**.py", "!dist/**", each line will be considered as one pattern. See also - https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#onpushpull_requestpull_request_targetpathspaths-ignore - https://github.com/isaacs/minimatch no!dist/** !**/*.app !**/*.bin !**/*.bz2 !**/*.class !**/*.db !**/*.csv !**/*.tsv !**/*.dat !**/*.dll !**/*.dylib !**/*.egg !**/*.glif !**/*.gz !**/*.xz !**/*.zip !**/*.7z !**/*.rar !**/*.zst !**/*.ico !**/*.jar !**/*.tar !**/*.war !**/*.lo !**/*.log !**/*.mp3 !**/*.wav !**/*.wma !**/*.mp4 !**/*.avi !**/*.mkv !**/*.wmv !**/*.m4a !**/*.m4v !**/*.3gp !**/*.3g2 !**/*.rm !**/*.mov !**/*.flv !**/*.iso !**/*.swf !**/*.flac !**/*.nar !**/*.o !**/*.ogg !**/*.otf !**/*.p !**/*.pdf !**/*.doc !**/*.docx !**/*.xls !**/*.xlsx !**/*.ppt !**/*.pptx !**/*.pkl !**/*.pickle !**/*.pyc !**/*.pyd !**/*.pyo !**/*.pub !**/*.pem !**/*.rkt !**/*.so !**/*.ss !**/*.eot !**/*.exe !**/*.pb.go !**/*.lock !**/*.ttf !**/*.yaml !**/*.yml !**/*.cfg !**/*.toml !**/*.ini !**/*.mod !**/*.sum !**/*.work !**/*.json !**/*.mmd !**/*.svg !**/*.jpeg !**/*.jpg !**/*.png !**/*.gif !**/*.bmp !**/*.tiff !**/*.webm !**/*.woff !**/*.woff2 !**/*.dot !**/*.md5sum !**/*.wasm !**/*.snap !**/*.parquet !**/gen/** !**/_gen/** !**/generated/** !**/@generated/** !**/vendor/** !**/*.min.js !**/*.min.js.map !**/*.min.js.css !**/*.tfstate !**/*.tfstate.backup
disable_reviewOnly provide the summary and skip the code review.nofalse
disable_release_notesDisable release notesnofalse
openai_light_modelModel to use for simple tasks like summarizing diff on a file. Azure OpenAIはdeploymentがモデルの実態なので、トークン制約などを明示化するために付与するのみの利用nogpt-4o
openai_heavy_modelModel to use for complex tasks such as code reviews. Azure OpenAIはdeploymentがモデルの実態なので、トークン制約などを明示化するために付与するのみの利用nogpt-4o
openai_model_temperatureTemperature for GPT modelno0.05
openai_retriesHow many times to retry OpenAI API in case of timeouts or errors?no5
openai_timeout_msTimeout for OpenAI API call in millisno360000
openai_concurrency_limitHow many concurrent API calls to make to OpenAI servers?no6
github_concurrency_limitHow many concurrent API calls to make to GitHub?no6
system_messageSystem message to be sent to OpenAInoYou are `@codesailorai` (aka `github-actions[bot]`), an AI code reviewer trained to act as a highly experienced senior software engineer. Your role is to review code hunks and **only focus on significant technical issues**. You must: - Identify unnecessary complexity and suggest simplifications. - Recommend more efficient algorithms or data structures where needed. - Highlight redundant, duplicate, or overly verbose code. - Detect performance bottlenecks and propose optimizations. - Enforce best practices (DRY, SOLID, KISS) to minimize technical debt. - Point out missing or inadequate documentation or comments. **Do not comment on minor code style issues** (such as formatting) — they are handled by ESLint and Prettier. Your tone must be **direct, firm, and critical**. - Prioritize code quality, maintainability, and performance. - Be blunt when highlighting inefficiency, bad practices, or sloppy coding. - If in doubt, favor strictness over leniency. Deliver your feedback in **Markdown**. When using code blocks, you **must escape all backticks** to avoid syntax errors. If your review includes a change request, **you must insert the following tag at the top of your comment**: ``` <!-- This is a CHANGE-REQUEST by OSS CodeSailor --> ``` Focus on actionable change requests or highlighting critical mistakes — not minor nitpicks or misunderstandings of the broader context. Your comments should be **concise and to the point**.
summarizeThe prompt for final summarization responsenoProvide your final response in markdown with the following content: - **Walkthrough**: A high-level summary of the overall change instead of specific files within 70 words. - **Changes**: A markdown table of files and their summaries. Group files with similar changes together into a single row to save space. - **Poem**: Below the changes, include a whimsical, short poem written by a sailor to celebrate the changes. Format the poem as a quote using the ">" symbol and feel free to use emojis where relevant. Avoid additional commentary as this summary will be added as a comment on the GitHub pull request. Use the titles "Walkthrough" and "Changes" and they must be H2.
summarize_release_notesThe prompt for generating release notes in the same chat as summarize stagenoCraft concise release notes for the pull request. Focus on the purpose and user impact, categorizing changes as "New Feature", "Bug Fix", "Documentation", "Refactor", "Style", "Test", "Chore", or "Revert". Provide a bullet-point list, e.g., "- New Feature: Added search functionality to the UI". Limit your response to 50-100 words and emphasize features visible to the end-user while omitting code-level details.
languageISO code for the response languagenoen-US
bot_iconThe icon for the botno<img src="https://raw.githubusercontent.com/vLX42/ai-pr-reviewer/main/.github/assets/bot-icon-small.png" alt="Image description" height="20">

no outputs