test(constants): table-driven assertions and extend octal-literal check to cmd/

[Copilot]

permissions_policy_test.go used raw if/t.Fatalf guards inconsistent with sibling tests, and the raw-octal AST walker only covered pkg/, leaving cmd/ unprotected.

Changes

• Table-driven TestPermissionConstantsValues — replaces five if/t.Fatalf blocks with a []struct{name, got, want fs.FileMode} table + assert.Equal; the typed struct field also gives compile-time verification that constants are fs.FileMode (not untyped int)
• Extend octal walker to cmd/ — TestNoRawOctalPermissionLiteralsInOSCalls now iterates over {pkg/, cmd/} roots so raw permission literals in cmd/ are caught
• Testify imports — adds assert/require to align with spec_test.go; replaces the runtime.Caller guard with require.True

// Before: five sequential if/t.Fatalf blocks
if FilePermSensitive != 0o600 {
    t.Fatalf("FilePermSensitive = %v, want 0o600", FilePermSensitive)
}

// After: table-driven with testify
tests := []struct {
    name string
    got  fs.FileMode
    want fs.FileMode
}{
    {name: "FilePermSensitive", got: FilePermSensitive, want: 0o600},
    ...
}
for _, tt := range tests {
    t.Run(tt.name, func(t *testing.T) {
        assert.Equal(t, tt.want, tt.got)
    })
}

---

Generated by 👨‍🍳 PR Sous Chef · 7.79 AIC · ⌖ 6.55 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

---

Generated by 👨‍🍳 PR Sous Chef · 8.05 AIC · ⌖ 8.96 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

---

Generated by 👨‍🍳 PR Sous Chef · 9.66 AIC · ⌖ 5.93 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

---

pr-sous-chef run: https://github.com/github/gh-aw/actions/runs/28907709886

Generated by 👨‍🍳 PR Sous Chef · 13 AIC · ⌖ 12.3 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

[Copilot]

Pull request overview

This PR improves the consistency and coverage of permission-policy tests in pkg/constants by refactoring constant assertions into a table-driven style and extending the existing AST-based “no raw octal permission literals” check to also scan cmd/.

Changes:

• Refactors TestPermissionConstantsValues into a table-driven test using testify/assert for consistent assertions.
• Expands TestNoRawOctalPermissionLiteralsInOSCalls to walk both pkg/ and cmd/ when checking for raw octal permission literals in relevant os.* calls.
• Introduces testify/require for the runtime.Caller guard (matching patterns used in other tests in the repo).

Show a summary per file

File	Description
pkg/constants/permissions_policy_test.go	Refactors permission constant assertions and expands the repo-wide raw-octal permission literal guard to include cmd/.

Review details

Tip

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

• Files reviewed: 1/1 changed files
• Comments generated: 0
• Review effort level: Low

[gh-aw-bot]

@copilot please run the pr-finisher skill, make the PR merge-ready, and rerun checks once the branch is up to date.

Generated by 👨‍🍳 PR Sous Chef · 7.79 AIC · ⌖ 6.55 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

[github-actions]

Hey @Copilot (and @pelikhan) 👋 — great cleanup of permissions_policy_test.go! The switch to table-driven assert.Equal assertions and the extension of the octal-literal AST walker to cover cmd/ are exactly the kind of incremental quality improvements that keep the test suite consistent and complete.

This looks ready for review. ✅

Generated by ✅ Contribution Check · 219.1 AIC · ⌖ 17 AIC · ⊞ 6.2K · ◷

[Copilot]

@copilot please run the pr-finisher skill, make the PR merge-ready, and rerun checks once the branch is up to date.

...

HEAD remains b9637e9; the branch was already up to date with main, and there were no unresolved in-scope review threads to address.

Local merge-readiness validation passed: make fmt, make lint, make test-unit, make test, and make recompile.

The last known PR checks for the code/test workflows were green on this head; the remaining status is stale/agent-side only. I can’t re-run CI from the cloud agent in a way that verifies this HEAD, so a maintainer still needs to re-trigger checks before merge.

[gh-aw-bot]

@copilot please run the pr-finisher skill, make this PR merge-ready, address all unresolved review feedback, and rerun checks once the branch is up to date.

Generated by 👨‍🍳 PR Sous Chef · 8.05 AIC · ⌖ 8.96 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

[Copilot]

@copilot please run the pr-finisher skill, make this PR merge-ready, address all unresolved review feedback, and rerun checks once the branch is up to date.

...

HEAD is still b9637e9; the branch is already up to date with main (ahead 2, behind 0).

I re-checked the review surface: there are no unresolved review threads or in-scope review comments to address. The remaining recent bot comments are approval/praise-only, not change requests.

I also re-ran local merge-readiness validation on this HEAD: make fmt, make lint, make test-unit, make test, and make recompile all passed.

The last known code/test checks on this HEAD are green. The remaining GitHub status is agent-side/pending automation, and I can’t re-trigger CI from the cloud agent in a way that verifies this HEAD, so a maintainer still needs to re-run checks before merge.

[gh-aw-bot]

@copilot please run the pr-finisher skill, make this PR merge-ready, address all unresolved review feedback, and rerun checks once the branch is up to date.

Generated by 👨‍🍳 PR Sous Chef · 9.66 AIC · ⌖ 5.93 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

[Copilot]

@copilot please run the pr-finisher skill, make this PR merge-ready, address all unresolved review feedback, and rerun checks once the branch is up to date.

...

No code changes were needed here; HEAD is still b9637e9 and the PR is already up to date with main.

I re-checked the review surface and there are no unresolved in-scope review threads or review comments to address. I also re-ran local merge-readiness validation on this HEAD: make fmt, make lint, make test-unit, make test, and make recompile all passed.

The last code/test workflow runs for b9637e9 are green. The remaining active check is the agent-side copilot run for this comment; if a fresh CI cycle is still required before merge, a maintainer will need to trigger it manually.

[gh-aw-bot]

\n@copilot please run the skill, make this PR merge-ready, address all unresolved review feedback, and rerun checks once the branch is up to date.

Generated by 👨‍🍳 PR Sous Chef · 13 AIC · ⌖ 12.3 AIC · ⊞ 7.1K · ◷
_{Comment /souschef to run again}

[github-actions]

🤖 PR Triage

Field	Value
Category	test
Risk	🟢 Low
Score	48/100 (impact:20 urgency:10 quality:18)
Action	✅ auto_merge

Rationale: CI passing. Test-only change (76+/68−) — converts raw if/t.Fatalf guards to table-driven tests, extends octal-literal coverage to cmd/. Zero production-code risk. Auto-merge candidate.

Run §28909358158

Generated by 🔧 PR Triage Agent · 112.1 AIC · ⌖ 6.5 AIC · ⊞ 5.4K · ◷

[gh-aw-bot]

@copilot please run the pr-finisher skill, make this PR merge-ready, address unresolved review feedback, and rerun checks once the branch is up to date.

Generated by 👨‍🍳 PR Sous Chef · 9.99 AIC · ⌖ 9.17 AIC · ⊞ 4.7K · ◷
_{Comment /souschef to run again}

[github-actions]

🎉 This pull request is included in a new release.

Release: v0.82.4