diff --git a/tests/runner-e2e/chat-catalog-domains/runtime-delegation.test.ts b/tests/runner-e2e/chat-catalog-domains/runtime-delegation.test.ts
index e56645ce14e..3dcbd9f9d70 100644
--- a/tests/runner-e2e/chat-catalog-domains/runtime-delegation.test.ts
+++ b/tests/runner-e2e/chat-catalog-domains/runtime-delegation.test.ts
@@ -1,5 +1,5 @@
import { expect, it } from "vitest";
-import { gradeDelegation, hasLaunchHeadline } from "./runtime-delegation.js";
+import { gradeDelegation, hasLaunchHeadline, completeLaunchBrief, launchPageReflectsBrief } from "./runtime-delegation.js";
function valid() {
const task = { id: "website", parentId: "launch", companyId: "company", assigneeAgentId: "morgan", status: "done", description: "Implement the approved design brief and report the completed result back." };
return { scenarioId: "task-coordination.delegate-with-context", companyId: "company", leadId: "ceo", agents: [], links: [], humanQueries: [], reply: "",
@@ -8,7 +8,7 @@ function valid() {
{ id: "implement", agentId: "morgan", status: "succeeded", contextSnapshot: { issueId: "website" } }, { id: "report", agentId: "ceo", status: "succeeded", contextSnapshot: { issueId: "chat" } }],
state: { parent: { id: "launch" }, task, worker: { id: "morgan" }, humanId: "human", briefCommentId: "human-brief", briefHash: "original-hash", briefDownloadedHash: "original-hash",
briefAttachment: { id: "brief", issueId: "launch", companyId: "company", createdByAgentId: null, createdByUserId: "human", issueCommentId: "human-brief", sha256: "original-hash" },
- parentOwnedByCeo: true, parentContextRetained: true, createdFromSource: true, childHasBrief: true, linkedToLaunch: false, workerBriefReadStatus: 200, workerBriefHash: "original-hash",
+ parentOwnedByCeo: true, parentContextRetained: true, createdFromSource: true, childHasBrief: true, linkedToLaunch: false, workerBriefReadStatus: 200, workerBriefHash: "original-hash", briefContextKind: "direct-attachment-reference", workerTaskReadStatus: 200, workerParentReadStatus: 200, parentLinkInspectable: true, durableBriefComplete: false,
workerWasReallyWaiting: true, actualWebsiteArtifact: true,
delivery: { checks: [{ id: "correlated", passed: true }], response: { body: "Morgan completed Website; the actual saved page is available on the child task." } } } };
}
@@ -27,3 +27,15 @@ it("rejects a result reported on an uncorrelated source", () => { const o = vali
it("rejects saying the parent executed Morgan's work", () => { const o = valid(); o.state.delivery.response.body = "I ran the parent Launch task and built the site myself. It is complete."; expect(gradeDelegation(o).passed).toBe(false); });
it("rejects a hidden actual parent execution", () => { const o = valid(); o.runs[2]!.contextSnapshot.issueId = "launch"; expect(gradeDelegation(o).passed).toBe(false); });
it("rejects duplicate work tasks", () => { const o = valid(); o.tasks.push({ id: "duplicate" }); expect(gradeDelegation(o).passed).toBe(false); });
+
+it("accepts an actual worker-readable parent reference and its exact human attachment", () => { const o = valid(); o.state.briefContextKind = "readable-parent-reference"; expect(gradeDelegation(o).passed).toBe(true); });
+it("rejects an inaccessible parent even when the board can read its attachment", () => { const o = valid(); o.state.briefContextKind = "readable-parent-reference"; o.state.workerParentReadStatus = 403; expect(gradeDelegation(o).passed).toBe(false); });
+it("rejects a parent reference with the wrong brief bytes", () => { const o = valid(); o.state.briefContextKind = "readable-parent-reference"; o.state.workerBriefHash = "other-design"; expect(gradeDelegation(o).passed).toBe(false); });
+it("accepts a complete durable brief with actual grounded delivery without copying its attachment", () => { const o = valid(); o.state.briefContextKind = "faithful-durable-copy"; o.state.durableBriefComplete = true; o.state.workerBriefReadStatus = 404; o.state.workerBriefHash = ""; expect(gradeDelegation(o).passed).toBe(true); });
+it("rejects an incomplete durable brief", () => { const o = valid(); o.state.briefContextKind = "faithful-durable-copy"; expect(gradeDelegation(o).passed).toBe(false); });
+it("rejects a durable copy without the worker's actual access to its task", () => { const o = valid(); o.state.briefContextKind = "faithful-durable-copy"; o.state.durableBriefComplete = true; o.state.workerTaskReadStatus = 403; expect(gradeDelegation(o).passed).toBe(false); });
+it.each(["Notify the CEO in this conversation when the page is ready", "Implement the brief and let me know when done"])("accepts a clear natural completion request: %s", description => { const o = valid(); o.state.task.description = description; expect(gradeDelegation(o).passed).toBe(true); });
+it("recognizes complete substantive durable brief content", () => expect(completeLaunchBrief("Reference: Launch brief nonce. Build semantic markup with accessible input labels, one primary join button, and the headline Research without the busywork.", "Launch brief nonce")).toBe(true));
+it.each(["Unrelated headline; semantic HTML, accessible labels, one primary signup action. Launch brief nonce", "Research without the busywork. Launch brief nonce", "Research without the busywork; semantic HTML, accessible labels, one primary signup action. Other reference"])("rejects wrong or incomplete durable content", text => expect(completeLaunchBrief(text, "Launch brief nonce")).toBe(false));
+it("verifies actual semantic output and its labelled signup control", () => expect(launchPageReflectsBrief('Research without the busywork
')).toBe(true));
+it("rejects output whose signup input lost its accessible label", () => expect(launchPageReflectsBrief('Research without the busywork
')).toBe(false));
diff --git a/tests/runner-e2e/chat-catalog-domains/runtime-delegation.ts b/tests/runner-e2e/chat-catalog-domains/runtime-delegation.ts
index 29f6c6e7815..f1deb4b702b 100644
--- a/tests/runner-e2e/chat-catalog-domains/runtime-delegation.ts
+++ b/tests/runner-e2e/chat-catalog-domains/runtime-delegation.ts
@@ -18,18 +18,32 @@ export function hasLaunchHeadline(html: string) {
const heading = html.match(/
]*>([\s\S]*?)<\/h1>/i)?.[1];
return heading?.replace(/<[^>]+>/g, " ").replace(/ | |*a0;/gi, " ").replace(/\s+/g, " ").trim().toLowerCase() === "research without the busywork";
}
+export function completeLaunchBrief(context: string, marker: string) {
+ return context.includes(marker) && /Research without the busywork/i.test(context) && /\bsemantic\b.{0,30}\b(?:html|markup|structure)\b/i.test(context)
+ && /\b(?:accessible|labelled|labeled)\b.{0,30}\b(?:label|input|control|form)|\blabel.{0,30}accessib/i.test(context)
+ && /\b(?:primary|one|single)\b.{0,35}\b(?:sign.?up|signup|join|subscribe)\b.{0,30}\b(?:action|cta|button|link)\b/i.test(context);
+}
+export function launchPageReflectsBrief(html: string) {
+ if (!hasLaunchHeadline(html) || !/<(?:main|section|header)\b/i.test(html)
+ || !/<(?:a|button)\b[^>]*>[\s\S]{0,400}?(?:sign.?up|join|subscribe|early access)[\s\S]{0,100}?<\/(?:a|button)>/i.test(html)) return false;
+ return [...html.matchAll(/]*>/gi)].every(([input]) => /type\s*=\s*["']?hidden\b|aria-label(?:ledby)?\s*=\s*["'][^"']+/i.test(input)
+ || !!input.match(/\bid\s*=\s*["']([^"']+)["']/)?.[1] && [...html.matchAll(/