Align no-op tracker expiry with maintenance workflow generation

[Copilot]

No-op tracker issues are stamped at runtime with a 30-day expiry, but maintenance workflow generation previously ignored that path unless an explicit expires: existed elsewhere. This change makes compile-time expiry detection account for safe-outputs.noop.report-as-issue (including default-enabled behavior), so stamped no-op expirations are actually enforced.

• Expiry source parity (runtime ↔ compile-time)

  • Updated scanWorkflowsForExpires to treat no-op issue reporting as an expiry source.
  • When no-op reporting is enabled (default or explicit true), it contributes a 30-day expiry window (24 * 30 hours), matching the runtime footer behavior.

• No-op report-as-issue semantics

  • Added isNoOpReportAsIssueEnabled(*string) bool to centralize the enablement rule:
    • nil => enabled (default)
    • "false" (case-insensitive, trimmed) => disabled
    • other values => enabled

• Focused maintenance workflow coverage

  • Extended maintenance workflow tests to cover:
    • no-op default (unset report-as-issue) => maintenance workflow generated
    • explicit report-as-issue: true => maintenance workflow generated
    • explicit report-as-issue: false => maintenance workflow not generated

const defaultNoOpIssueExpirationHours = 24 * 30

if workflowData.SafeOutputs.NoOp != nil &&
   isNoOpReportAsIssueEnabled(workflowData.SafeOutputs.NoOp.ReportAsIssue) {
    hasExpires = true
    if minExpires == 0 || defaultNoOpIssueExpirationHours < minExpires {
        minExpires = defaultNoOpIssueExpirationHours
    }
}

[github-actions]

🧠 Matt Pocock Skills Reviewer failed during the skills-based review.

[github-actions]

⚠️ PR Code Quality Reviewer failed during code quality review.

[github-actions]

✅ Design Decision Gate 🏗️ completed the design decision gate check.

No ADR enforcement needed: PR #37965 does not have the 'implementation' label and has only 61 new lines of code in business logic directories (≤100 threshold).

[github-actions]

🧪 Test Quality Sentinel completed test quality analysis.

[Copilot]

Pull request overview

This PR aligns maintenance workflow generation with the runtime behavior of no-op tracker issue expiry by treating safe-outputs.noop.report-as-issue (including its default-enabled behavior) as an expiry source during compile-time scanning.

Changes:

• Added centralized isNoOpReportAsIssueEnabled(*string) bool logic and a 30-day default no-op issue expiry constant (in hours).
• Updated scanWorkflowsForExpires to flag expiry when no-op issue reporting is enabled and to factor its 30-day window into minExpires.
• Expanded maintenance workflow tests to cover no-op default/true/false behavior for workflow generation.

Show a summary per file

File	Description
pkg/workflow/maintenance_workflow.go	Detects enabled no-op report-as-issue as an expiry source (30-day window) when deciding whether to generate maintenance workflows.
pkg/workflow/maintenance_workflow_test.go	Adds test cases verifying maintenance workflow generation behavior for default/explicit no-op report-as-issue settings.

Copilot's findings

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

• Files reviewed: 2/2 changed files
• Comments generated: 0

[pelikhan]

@copilot run pr-finisher skill

[github-actions]

🧪 Test Quality Sentinel Report

✅ Test Quality Score: 80/100 — Excellent

Analyzed 3 test(s) (new table rows in TestGenerateMaintenanceWorkflow_WithExpires): 3 design, 0 implementation, 0 guideline violations.

📊 Metrics & Test Classification (3 tests analyzed)

Metric	Value
New/modified tests analyzed	3
✅ Design tests (behavioral contracts)	3 (100%)
⚠️ Implementation tests (low value)	0 (0%)
Tests with error/edge cases	2 (67%)
Duplicate test clusters	0
Test inflation detected	Yes — 43 test lines / 18 prod lines ≈ 2.4:1 (threshold 2:1)
🚨 Coding-guideline violations	0

Test Classification Details

Test	File	Classification	Issues Detected
noop report-as-issue default	pkg/workflow/maintenance_workflow_test.go:148	✅ Design	Happy path — no edge case
noop report-as-issue false	pkg/workflow/maintenance_workflow_test.go:161	✅ Design	Disabled path (edge case ✅)
noop report-as-issue true	pkg/workflow/maintenance_workflow_test.go:176	✅ Design	Explicit-enabled path (edge case ✅)

Language Support

Tests analyzed:

• 🐹 Go (*_test.go): 3 tests — unit (//go:build !integration)
• 🟨 JavaScript (*.test.cjs, *.test.js): 0 tests

Verdict

✅ Check passed. 0% of new tests are implementation tests (threshold: 30%). Build tag present ✅, no mock libraries ✅.

i️ Minor note: test/production line-addition ratio is ≈ 2.4:1 (43 test lines vs 18 production lines), which triggers the inflation flag and costs 10 points. This is largely due to Go struct-literal verbosity for table rows — not a real quality concern here, but worth noting if the table continues to grow.

📖 Understanding Test Classifications

Design Tests (High Value) verify what the system does:

• Assert on observable outputs, return values, or state changes
• Cover error paths and boundary conditions
• Would catch a behavioral regression if deleted
• Remain valid even after internal refactoring

Implementation Tests (Low Value) verify how the system does it:

• Assert on internal function calls (mocking internals)
• Only test the happy path with typical inputs
• Break during legitimate refactoring even when behavior is correct
• Give false assurance: they pass even when the system is wrong

Goal: Shift toward tests that describe the system's behavioral contract — the promises it makes to its users and collaborators.

References: §27173437921

🧪 Test quality analysis by Test Quality Sentinel · 301.2 AIC · ⌖ 49.3 AIC · ◷

[github-actions]

✅ Test Quality Sentinel: 80/100. Test quality is excellent — 0% of new tests are implementation tests (threshold: 30%). All 3 new table rows verify observable behavioral contracts; no mock libraries; build tag present.

[Copilot]

@copilot run pr-finisher skill

Done in 4d06484.

I ran the pr-finisher pass, fixed the actionable failure (TestCompileSpecificFiles_DeletesMaintenanceWorkflow) by updating the no-expires fixture to set safe-outputs.noop: false, and re-ran local validation: make fmt, make lint, make test-unit, make test, make recompile (all passing).

Since agent pushes don’t retrigger CI, checks on this new HEAD need a maintainer re-trigger.