cenbonew/zing relay audit

Audit whether an LLM relay serves its claimed model (货不对板检测); fail CI when risk meets your threshold.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Activelast commit Jun 8, 2026
License
Apache 2.0

Pinned Snippet

workflow.ymlSHA-pinned
uses: cenbonew/zing@fadd570cbea4d6af6180bbab97ae658430d1df30 # v0.11.0

tags can be moved; commit SHAs can't. why a SHA?

namedescriptionrequireddefault
base-urlRelay base URL, e.g. https://relay.example.com/v1.yes
api-keyRelay API key. Pass a caller secret (e.g. ${{ secrets.RELAY_API_KEY }}). It is forwarded to zing via an environment variable and is never echoed.yes
modelModel id actually sent in requests.yes
claimed-modelModel the relay claims to serve, if different from `model`.no""
apiWire protocol: auto | openai | anthropic.noauto
declared-providerProvider hint for KB lookup (openai, anthropic, deepseek, ...).no""
suiteDetector suite: smoke | standard | deep | full.nostandard
fail-on-riskFail the job when risk >= this level: low | medium | high.nohigh
python-versionPython version used to install and run zing.no3.12
versionpip install spec for zing. Defaults to the latest published `zing-audit`. Pin it for reproducible runs, e.g. `zing-audit==0.8.0`.nozing-audit
namedescription
riskRisk level reported by zing (clean | low | medium | high | inconclusive).
scoreOverall score 0-100 (may be empty if zing could not score the relay).
ratingHuman-readable rating from the verdict (may be empty).