diff --git a/test/skill-e2e-plan-ceo-plan-mode.test.ts b/test/skill-e2e-plan-ceo-plan-mode.test.ts index 1392dca6b..b75f5d6f3 100644 --- a/test/skill-e2e-plan-ceo-plan-mode.test.ts +++ b/test/skill-e2e-plan-ceo-plan-mode.test.ts @@ -152,6 +152,12 @@ describeE2E('plan-ceo-review plan-mode smoke (gate)', () => { } } expect(['asked', 'plan_ready', 'exited']).toContain(obs.outcome); - assertReportAtBottomIfPlanWritten(obs); + // NOTE: assertReportAtBottomIfPlanWritten is intentionally NOT called + // here. This test runs --disallowedTools AskUserQuestion and only + // checks "did the question surface" — the model can't run the full + // multi-section review without AUQ tools, so no review report exists + // to enforce the at-bottom contract against. The contract is + // exercised by the periodic finding-count tests, which DO run the + // full review. }, 360_000); }); diff --git a/test/skill-e2e-plan-design-plan-mode.test.ts b/test/skill-e2e-plan-design-plan-mode.test.ts index 9ac3ee9b6..fcf1fd94b 100644 --- a/test/skill-e2e-plan-design-plan-mode.test.ts +++ b/test/skill-e2e-plan-design-plan-mode.test.ts @@ -85,6 +85,9 @@ describeE2E('plan-design-review plan-mode smoke (gate)', () => { ); } expect(['asked', 'plan_ready', 'exited']).toContain(obs.outcome); - assertReportAtBottomIfPlanWritten(obs); + // NOTE: assertReportAtBottomIfPlanWritten intentionally not called — + // see skill-e2e-plan-ceo-plan-mode test 2 for the full rationale. Under + // --disallowedTools the model can't run a full review, so the + // report-at-bottom contract doesn't apply. }, 360_000); });