diff --git a/ai_evals/adapters/frontend/mockBackend.ts b/ai_evals/adapters/frontend/mockBackend.ts
index b6dbe042b8..692a83edeb 100644
--- a/ai_evals/adapters/frontend/mockBackend.ts
+++ b/ai_evals/adapters/frontend/mockBackend.ts
@@ -1556,14 +1556,16 @@ export function handleBenchmarkApiFetch(url: string, init?: RequestInit): Respon
 	}
 	if (path === '/api/integrations/hub/list') {
 		const apps = [...new Set(BENCHMARK_HUB_SCRIPTS.map((script) => script.app))].sort()
-		// Only the integrations lifted whole from the content repo have a meta.json, so
-		// the flag separates them from the rest here the way it does on the hub, where
-		// 18 of ~216 qualify.
-		const documented = new Set(
-			REAL_HUB_INTEGRATIONS.filter((integration) => integration.meta).map(
+		// Read off both fixtures the metadata endpoint serves from, or the list would
+		// call an integration undocumented and then hand back its authored notes.
+		const documented = new Set([
+			...REAL_HUB_INTEGRATIONS.filter((integration) => integration.meta).map(
 				(integration) => integration.app
-			)
-		)
+			),
+			...Object.entries(BENCHMARK_HUB_INTEGRATION_META)
+				.filter(([, entry]) => entry.meta)
+				.map(([app]) => app)
+		])
 		return Response.json(apps.map((name) => ({ name, documented: documented.has(name) })))
 	}
 	if (path.startsWith('/api/scripts/hub/get_full/')) {
diff --git a/ai_evals/adapters/frontend/mockBackendApi.test.ts b/ai_evals/adapters/frontend/mockBackendApi.test.ts
index d9cfa08bf4..a50a66e1f5 100644
--- a/ai_evals/adapters/frontend/mockBackendApi.test.ts
+++ b/ai_evals/adapters/frontend/mockBackendApi.test.ts
@@ -81,3 +81,23 @@ describe('benchmark API catalog', () => {
 		expect(handleBenchmarkApiFetch(`/api/w/${WORKSPACE}/jobs_u/get/missing`).status).toBe(404)
 	})
 })
+
+// A benchmark whose list calls an integration undocumented while its metadata endpoint
+// hands back authored notes teaches the model the flag means nothing.
+describe('benchmark hub integration list', () => {
+	beforeEach(() => resetBenchmarkMockBackend())
+
+	it('flags exactly the integrations whose metadata carries authored notes', async () => {
+		const listed = (await handleBenchmarkApiFetch('/api/integrations/hub/list').json()) as Array<{
+			name: string
+			documented: boolean
+		}>
+		expect(listed.length).toBeGreaterThan(0)
+
+		for (const { name, documented } of listed) {
+			const res = handleBenchmarkApiFetch(`/api/integrations/hub/${name}/meta`)
+			const authored = res.status === 200 && !!((await res.json()) as { meta?: unknown }).meta
+			expect(authored).toBe(documented)
+		}
+	})
+})
diff --git a/frontend/src/lib/components/copilot/chat/shared.ts b/frontend/src/lib/components/copilot/chat/shared.ts
index 1c814cbc83..66711acee3 100644
--- a/frontend/src/lib/components/copilot/chat/shared.ts
+++ b/frontend/src/lib/components/copilot/chat/shared.ts
@@ -1415,12 +1415,9 @@ async function loadHubIntegrations(): Promise<HubIntegration[]> {
 	return hubIntegrationsCache
 }
 
-/** Which integrations carry hand-written provider knowledge, lowercased because a
- * hub slug is case-sensitive and both casings of one vendor can exist. The mark says
- * get_hub_integration has verified pagination, enums and gotchas to add for this one.
- * It must never become a reason to skip the call for the others: that call still
- * carries the resource type and the usage-ranked examples, neither of which is
- * guessable from a search result. */
+/** Which integrations carry provider knowledge checked against the live API,
+ * lowercased because a hub slug is case-sensitive and both casings can exist. The
+ * mark means there is more to read, never that the call is skippable elsewhere. */
 async function documentedIntegrations(): Promise<Set<string>> {
 	const available = await loadHubIntegrations()
 	return new Set(available.filter((i) => i.documented).map((i) => i.name.toLowerCase()))