useqai/QAI Agent

Stop guessing why CI failed. QAI posts root cause, fix suggestions, and a merge verdict directly on your PR — automatically.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
junit-pathPath or glob to JUnit XML file(s), e.g. "test-results/results.xml" or "**/junit-*.xml"yes
github-tokenGitHub token for posting PR comments. Defaults to the built-in GITHUB_TOKEN.no${{ github.token }}
post-commentWhether to post a PR comment with the analysis results (true/false)notrue
qai-urlQAI cloud platform ingest URL for historical intelligence (optional). Example: https://ingest.your-domain.comno
qai-api-keyQAI API key for cloud platform (required when qai-url is set)no
trace-pathGlob to Playwright trace zip files for RCA analysis, e.g. "test-results/**/*.zip"no
playwright-reportPath to Playwright JSON report file for richer AI fix suggestions, e.g. "test-results/report.json". Requires qai-url and qai-api-key.no
fail-on-high-riskFail the action step when risk level is high (true/false). Default false — the action reports but never blocks.nofalse
suite-nameDisplay name for this test suite (e.g. "Selenium Python", "WebdriverIO"). When set, each suite gets its own PR comment instead of overwriting others.no""
slack-webhook-urlSlack incoming webhook URL. When provided, posts a plain-text High Risk alert when risk level is high. For richer alerts with cluster trends and AI analysis, use the QAI platform.no
namedescription
risk-levelComputed risk level: low | medium | high
risk-scoreComputed risk score: 0.0–1.0
failed-testsNumber of failed tests
total-testsTotal number of tests
cluster-countNumber of unique failure clusters detected