test: harden qa-lab concurrent web scenarios

extensions/qa-lab/src/suite.test.ts

@@ -214,6 +214,16 @@ describe("qa suite failure reply handling", () => {
     });
   });
 
+  it("enables Control UI only for Control UI scenario workers", () => {
+    expect(
+      qaSuiteTesting.scenarioRequiresControlUi({
+        ...makeScenario("control-ui"),
+        surface: "control-ui",
+      }),
+    ).toBe(true);
+    expect(qaSuiteTesting.scenarioRequiresControlUi(makeScenario("plain"))).toBe(false);
+  });
+
   it("filters provider-specific scenarios from an implicit live lane", () => {
     const scenarios = [
       makeScenario("generic"),

extensions/qa-lab/src/suite.ts

@@ -68,7 +68,7 @@ import { readQaBootstrapScenarioCatalog } from "./scenario-catalog.js";
 import { runScenarioFlow } from "./scenario-flow-runner.js";
 import { createQaScenarioRuntimeApi } from "./scenario-runtime-api.js";
 import {
-  closeAllQaWebSessions,
+  closeQaWebSessions,
   qaWebEvaluate,
   qaWebOpenPage,
   qaWebSnapshot,
@@ -98,6 +98,7 @@ type QaSuiteEnvironment = {
   providerMode: "mock-openai" | "live-frontier";
   primaryModel: string;
   alternateModel: string;
+  webSessionIds: Set<string>;
 };
 
 export type QaSuiteStartLabFn = (params?: QaLabServerStartParams) => Promise<QaLabServerHandle>;
@@ -340,6 +341,12 @@ function collectQaSuiteGatewayRuntimeOptions(
   return forwardHostHome ? { forwardHostHome: true } : undefined;
 }
 
+function scenarioRequiresControlUi(
+  scenario: ReturnType<typeof readQaBootstrapScenarioCatalog>["scenarios"][number],
+) {
+  return normalizeLowercaseStringOrEmpty(scenario.surface) === "control-ui";
+}
+
 function liveTurnTimeoutMs(env: QaSuiteEnvironment, fallbackMs: number) {
   return resolveQaLiveTurnTimeoutMs(env, fallbackMs);
 }
@@ -1268,7 +1275,11 @@ function createScenarioFlowApi(
       browserOpenTab: qaBrowserOpenTab,
       browserSnapshot: qaBrowserSnapshot,
       browserAct: qaBrowserAct,
-      webOpenPage: qaWebOpenPage,
+      webOpenPage: async (params: Parameters<typeof qaWebOpenPage>[0]) => {
+        const opened = await qaWebOpenPage(params);
+        env.webSessionIds.add(opened.pageId);
+        return opened;
+      },
       webWait: qaWebWait,
       webType: qaWebType,
       webSnapshot: qaWebSnapshot,
@@ -1330,6 +1341,7 @@ export const qaSuiteTesting = {
   mapQaSuiteWithConcurrency,
   normalizeQaSuiteConcurrency,
   scenarioMatchesLiveLane,
+  scenarioRequiresControlUi,
   selectQaSuiteScenarios,
   readTransportTranscript,
   formatTransportTranscript,
@@ -1575,10 +1587,10 @@ export async function runQaSuite(params?: QaSuiteRunParams): Promise<QaSuiteResu
               scenarioIds: [scenario.id],
               concurrency: 1,
               startLab,
-              // Isolated workers do not need their own Control UI proxy. The
-              // outer lab already owns the watch surface, so skip per-worker
-              // Control UI asset resolution and startup overhead.
-              controlUiEnabled: false,
+              // Most isolated workers do not need their own Control UI proxy.
+              // Control UI scenarios do, because they open the worker's
+              // gateway-backed app directly.
+              controlUiEnabled: scenarioRequiresControlUi(scenario),
             });
             const scenarioResult: QaSuiteScenarioResult =
               result.scenarios[0] ??
@@ -1740,6 +1752,7 @@ export async function runQaSuite(params?: QaSuiteRunParams): Promise<QaSuiteResu
     providerMode,
     primaryModel,
     alternateModel,
+    webSessionIds: new Set(),
   };
 
   let preserveGatewayRuntimeDir: string | undefined;
@@ -1849,7 +1862,7 @@ export async function runQaSuite(params?: QaSuiteRunParams): Promise<QaSuiteResu
     preserveGatewayRuntimeDir = path.join(outputDir, "artifacts", "gateway-runtime");
     throw error;
   } finally {
-    await closeAllQaWebSessions();
+    await closeQaWebSessions(env.webSessionIds);
     const keepTemp = process.env.OPENCLAW_QA_KEEP_TEMP === "1" || false;
     await gateway.stop({
       keepTemp,

extensions/qa-lab/src/web-runtime.test.ts

@@ -44,6 +44,7 @@ vi.mock("playwright-core", () => ({
 
 import {
   closeAllQaWebSessions,
+  closeQaWebSessions,
   qaWebEvaluate,
   qaWebOpenPage,
   qaWebSnapshot,
@@ -114,4 +115,19 @@ describe("qa web runtime", () => {
     expect(contextClose).toHaveBeenCalledTimes(1);
     expect(browserClose).toHaveBeenCalledTimes(1);
   });
+
+  it("can close only selected page sessions", async () => {
+    const first = await qaWebOpenPage({ url: "http://127.0.0.1:3000/one" });
+    const second = await qaWebOpenPage({ url: "http://127.0.0.1:3000/two" });
+
+    await closeQaWebSessions([first.pageId]);
+
+    await expect(qaWebSnapshot({ pageId: first.pageId })).rejects.toThrow(
+      `unknown web session: ${first.pageId}`,
+    );
+    await expect(qaWebSnapshot({ pageId: second.pageId })).resolves.toMatchObject({
+      text: "hello from body",
+    });
+    await closeAllQaWebSessions();
+  });
 });

extensions/qa-lab/src/web-runtime.ts

@@ -144,11 +144,23 @@ export async function qaWebEvaluate<T = unknown>(params: QaWebEvaluateParams): P
   ])) as T;
 }
 
-export async function closeAllQaWebSessions(): Promise<void> {
-  const active = [...sessions.values()];
-  sessions.clear();
+export async function closeQaWebSessions(pageIds?: Iterable<string>): Promise<void> {
+  const active = pageIds
+    ? [...pageIds].flatMap((pageId) => {
+        const session = sessions.get(pageId);
+        sessions.delete(pageId);
+        return session ? [session] : [];
+      })
+    : [...sessions.values()];
+  if (!pageIds) {
+    sessions.clear();
+  }
   for (const session of active) {
     await session.context.close().catch(() => {});
     await session.browser.close().catch(() => {});
   }
 }
+
+export async function closeAllQaWebSessions(): Promise<void> {
+  await closeQaWebSessions();
+}

qa/scenarios/active-memory-preprompt-recall.md

@@ -207,7 +207,7 @@ steps:
         args:
           - lambda:
               async: true
-              expr: "await (async () => { const store = await readRawQaSessionStore(env); const entry = store[activeSessionKey]; if (!entry || !Array.isArray(entry.pluginDebugEntries)) return undefined; return entry.pluginDebugEntries.some((pluginEntry) => pluginEntry?.pluginId === 'active-memory' && Array.isArray(pluginEntry.lines) && pluginEntry.lines.some((line) => line.includes('Active Memory: ok'))) ? entry : undefined; })()"
+              expr: "await (async () => { const store = await readRawQaSessionStore(env); const entry = store[activeSessionKey]; if (!entry || !Array.isArray(entry.pluginDebugEntries)) return undefined; return entry.pluginDebugEntries.some((pluginEntry) => pluginEntry?.pluginId === 'active-memory' && Array.isArray(pluginEntry.lines) && pluginEntry.lines.some((line) => line.includes('Active Memory: status=ok'))) ? entry : undefined; })()"
           - 10000
       - if:
           expr: "Boolean(env.mock)"