sumo_qa_format_qa_scorecard
Compose a QA readiness scorecard from test evidence and risk coverage to derive a four-state recommendation (ready, blocked, insufficient evidence) without numeric scoring.
Instructions
Compose a QA READINESS SCORECARD from already-produced evidence and DERIVE a readiness recommendation (issue #151). EVIDENCE SUMMARY, NOT a predictive quality score — it infers no risk, invents no numeric score, and the host can never assert "ready": the verdict is computed.
Common natural-language phrasings that map to this tool: "is this ready to merge/release", "give me a readiness scorecard", "summarise QA readiness", "release review summary".
Inputs are all optional and reuse the existing artifacts — nothing is re-defined here:
ledger_rows— the #144 risk-to-test rows (same shape assumo_qa_format_risk_ledger); supplies risk coverage + blockers.context_bundle— the #149 bundle (same shape assumo_qa_format_context_bundle); supplies test/CI evidence freshness.coverage/mutation— optional{..., freshness}signals; absent ⇒ reported as "not measured", never assumed passing, and never allowed to outweigh an uncovered high-impact risk.scope— optional label (a PR title, a release name).local_head_sha— optional live local head, to flag a stale bundle.
Returns the four-state recommendation (ready / ready_with_accepted_
residuals / blocked / insufficient_evidence), is_ready (true only for
the two ready states), the uncovered-blocker / residual counts, the
stale-evidence and not-measured dimension lists, the rendered markdown,
a one-line compact_summary to drop inline in short answers, and a
JSON-able serialized snapshot a downstream report (#157) can render.
Readiness is refused whenever a risk is an uncovered blocker or evidence
is stale — that guarantee is structural, not advisory.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| scope | No | ||
| coverage | No | ||
| mutation | No | ||
| ledger_rows | No | ||
| max_reasons | No | ||
| context_bundle | No | ||
| local_head_sha | No |