WFM Time-Off — release gate
Everything that must hold before a WFM Assistant time-off build ships: the golden request/policy set, exact accrual math, and confirmed side-effects on every write. Time-off approval reduces to a decision, so cohort fairness gates here too (§66) — bound during this arc.
Release gate — PASS
Last run run_5528 · pull-request · 24 / 24 cases clean · every concern above its threshold.
24
cases
3
concerns
1
judges
κ .87
agreement
Reproducibility chain— selector → policy → run, pinned into every evidence packet
1Selector
agent:wfm-assistant AND tier:golden AND topic:time_off
resolves to 24 cases
2Policy
3 concerns · release gate thresholds
3 of 3 hard-required
3Environment
Calendar@2026.2 + 1 overlay
tenant-scoped · acme-mfg-oh
4Judges
1 bound · SME-calibrated
gate-eligible
5Evidence
run_5528 · sealed packet
reproducible, auditable
Policy
thresholds by context — same cases, different strictness| Concern | Metric | Dev loop | Release gate | Required |
|---|---|---|---|---|
| Numeric | numeric_exact | 100% | 100% | hard |
| Action | side-effect asserts | 100% | 100% | hard |
| Functional | trajectory + semantic | ≥ 0.70 | ≥ 0.85 | hard |
Thresholds live here, not in cases — the same case faces lenient dev-loop checks and strict release gates without being edited.
Recent runs
each a sealed evidence packet| run_5528 | 2026-07-07 10:24 4m 02s | pull-request | 24✓ | pass |
Selector
which cases belong — resolved live from the registryagent:wfm-assistant AND tier:golden AND topic:time_offExplicit includes
+ wfm.request_time_off_012
Excludes
noneCases promoted from production traces with matching tags join this suite automatically. Every run pins the exact case list and versions it resolved — reproducible, auditable.
Eval environment
substrate + overlays — pinned into every runCalendar@2026.2+wfm/timeoff-scenarios@v1
tenant-scoped · acme-mfg-oh (sandbox, synthetic)
Golden datasets in scope
Cases reference these overlays by logical handle — the run pins the exact composition (substrate@version + overlay@version + case set) into its evidence packet.
Judges bound
SME-calibrated, versionedaag/task-completion-judge@v3gate-eligibleκ 0.87 · certified until 2026-11-30
A shadow judge scores everything but gates nothing until it clears the agreement bar and an SME signs off.
Where this suite runs
manual and pipeline — same assetUKGEPIC/wfm-agents
quality-gate.yml
trigger: pull request → main, nightly
$ quality run wfm-timeoff-release-gate --context dev-loop
The identical suite, from any engineer's terminal — minimum friction is the point.
Prototype cases in scope
2 of the 24 resolved cases exist in this demoAgent: WFM Assistant · Workforce Management · Google ADK