mariorazo97/AI CI Healer

🚑 Stops builds from failing. Analyzes logs & auto-fixes errors using AI (Groq/Gemini/Ollama).

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
github-tokenGitHub Token to post comments (use secrets.GITHUB_TOKEN)yes
llm-providerAI Brain to use: "groq" (fastest), "gemini" (smartest), or "ollama" (private)nogroq
modelSpecific model to use (e.g., "llama-3.1-70b-versatile" or "gemini-1.5-flash")no""
groq-api-keyGroq API Key (Required if provider is groq)no
gemini-api-keyGemini API Key (Required if provider is gemini)no
ollama-endpointOllama Endpoint for self-hosted execution (e.g., http://localhost:11434)no
custom-contextTeach the AI your coding standards (e.g., "Always use TypeScript strict mode")no""
max-log-linesHow much log history to read (Increase for complex errors)no500
confidence-thresholdMinimum confidence % required to post a commentno50
enable-commentsPost the fix as a comment on the PR? (true/false)notrue
namedescription
suggestionThe raw Markdown fix suggestion generated by AI
confidenceConfidence score (0-100)
error-typeDetected error category (e.g., build-error, test-failure)