From 8560e54b69c3c28fa87be1428cebed915bfa1526 Mon Sep 17 00:00:00 2001
From: Dotta <bippadotta@protonmail.com>
Date: Sat, 19 Sep 2026 10:02:58 -0500
Subject: [PATCH] test(runner-e2e): report unexercised review boundaries
 promptly

Co-Authored-By: Paperclip <noreply@paperclip.ing>
---
 tests/runner-e2e/README.md                |  5 +++++
 tests/runner-e2e/everyday-flow.ts         |  3 ++-
 tests/runner-e2e/everyday-observations.ts | 13 +++++++++++++
 tests/runner-e2e/everyday.test.ts         | 16 ++++++++++++++++
 4 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/tests/runner-e2e/README.md b/tests/runner-e2e/README.md
index 21a180d96b2..ecd5953029d 100644
--- a/tests/runner-e2e/README.md
+++ b/tests/runner-e2e/README.md
@@ -791,3 +791,8 @@ Everyday restart and Stop scenarios exempt only their recorded cancellation,
 graceful-shutdown interruption, or process-loss outcome. A later adapter error
 on that same run still fails immediately and fails the lifecycle grader. The
 run ID alone is not an exemption from recovery failures.
+
+The review-handoff case also requires proof that the parent was blocked before
+the review wake. If all tasks finish without that ordering, the harness fails
+promptly with an unexercised-boundary diagnostic. Successful work alone does not
+prove that this recovery path was tested.
diff --git a/tests/runner-e2e/everyday-flow.ts b/tests/runner-e2e/everyday-flow.ts
index 17404855784..9b11c328e3c 100644
--- a/tests/runner-e2e/everyday-flow.ts
+++ b/tests/runner-e2e/everyday-flow.ts
@@ -24,6 +24,7 @@ import {
   isStoryWorkspaceDeferral,
   isExpectedStoryInterruption,
   storyUnexpectedRunFailure,
+  storyUnexercisedReviewBoundary,
   storyLifecycleChecks,
   storyRepliesConsumed,
   storyHasAgentReply,
@@ -693,7 +694,7 @@ export async function runEverydayFlow(input: Input) {
           );
           return failed
             ? `Review handoff prerequisite failed: ${failed.errorCode}: ${failed.error}`
-            : undefined;
+            : storyUnexercisedReviewBoundary(state.issues, state.runs);
         },
       });
       const child = boundary.issues.find((issue) => issue.parentId === parent!.id)!;
diff --git a/tests/runner-e2e/everyday-observations.ts b/tests/runner-e2e/everyday-observations.ts
index 542212278d8..5fb35cee388 100644
--- a/tests/runner-e2e/everyday-observations.ts
+++ b/tests/runner-e2e/everyday-observations.ts
@@ -229,6 +229,19 @@ export function storyUnexpectedRunFailure(runs: StoryRun[], allowedRunIds: reado
   );
 }
 
+/** Called only after the required review boundary did not match. */
+export function storyUnexercisedReviewBoundary(
+  issues: StoryIssue[],
+  runs: StoryRun[],
+): string | undefined {
+  if (issues.length === 0 || runs.length === 0) return;
+  if (!issues.every((issue) =>
+    issue.status === "done" && !issue.scheduledRetry && !issue.activeRecoveryAction,
+  )) return;
+  if (!runs.every((run) => run.status === "succeeded")) return;
+  return "Review handoff boundary not exercised: all tasks finished without evidence of a blocked parent before the review wake.";
+}
+
 export function storyLifecycleChecks(input: {
   issues: StoryIssue[];
   runs: StoryRun[];
diff --git a/tests/runner-e2e/everyday.test.ts b/tests/runner-e2e/everyday.test.ts
index b422083b306..6f08592011d 100644
--- a/tests/runner-e2e/everyday.test.ts
+++ b/tests/runner-e2e/everyday.test.ts
@@ -5,6 +5,7 @@ import { everydayTasks, productionStoryProfile } from "./everyday-cases.js";
 import {
   isStoryWorkspaceDeferral,
   storyUnexpectedRunFailure,
+  storyUnexercisedReviewBoundary,
   storyLifecycleChecks,
   storyRepliesConsumed,
   storyHasAgentReply,
@@ -54,6 +55,21 @@ describe("everyday workflow grader and review timing", () => {
   });
 });
 
+describe("unexercised review boundary diagnostics", () => {
+  const done = { id: "parent", companyId: "company", title: "task", status: "done" };
+  const completed = { id: "run", companyId: "company", agentId: "lead", status: "succeeded" };
+  it("fails promptly when all work finishes without the required review ordering", () => {
+    expect(storyUnexercisedReviewBoundary([done], [completed])).toContain("not exercised");
+  });
+  it("does not preempt in-flight finalization, recovery, or unfinished work", () => {
+    expect(storyUnexercisedReviewBoundary([done], [{ ...completed, status: "running" }])).toBeUndefined();
+    expect(storyUnexercisedReviewBoundary([{ ...done, scheduledRetry: {} }], [completed])).toBeUndefined();
+    expect(storyUnexercisedReviewBoundary([{ ...done, activeRecoveryAction: {} }], [completed])).toBeUndefined();
+    expect(storyUnexercisedReviewBoundary([{ ...done, status: "blocked" }], [completed])).toBeUndefined();
+    expect(storyUnexercisedReviewBoundary([], [])).toBeUndefined();
+  });
+});
+
 describe("multi-round agent review handoff", () => {
   const child = {
     id: "child",