andy-c-jones/PR Performance Reviewer

Reviews pull requests for performance issues using Copilot/GitHub Models.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
github-tokenGitHub token used for GitHub API + Copilot/GitHub Models callsyes
modelModel identifier for the Copilot/GitHub Models endpointnoopenai/gpt-4.1
copilot-api-urlCopilot/GitHub Models chat completions endpoint URLnohttps://models.github.ai/inference/chat/completions
min-severityMinimum severity for posting review comments (low|medium|high|critical)nomedium
min-confidenceMinimum confidence for posting review comments (low|medium|high)nohigh
impact-levelMinimum impact level for posting review comments (all|low|medium|high)nomedium
max-findings-per-fileMaximum number of findings to keep per analyzed fileno3
max-patch-charactersSkip files when patch text exceeds this character limitno6000
max-file-charactersSkip files when full file content exceeds this character limitno12000
skip-generated-artifactsWhen true, skips generated/bundled artifact paths such as dist/, coverage/, *.map, and *.min.*notrue
skipComma-separated directory prefixes to skip for supported language files (for example: dist,build,generated)no""
review-summaryAdditional body text appended after the action attribution header in the submitted pull request reviewnoPerformance review suggestions from Copilot. Address only if the impact aligns with your workload profile.
namedescription
supported-files-detectedNumber of changed files with supported language extensions
analyzed-filesNumber of files sent to Copilot analysis
comments-postedNumber of inline comments posted
skipped-reasonReason no comments were posted (including model_access_denied, copilot_unavailable, or all_supported_files_skipped)
analysis-overviewJSON summary of model, checks, file-level findings, and filtering outcomes