From 3eb06e305e69ba0cfd47c7f1f949d0832b3683de Mon Sep 17 00:00:00 2001
From: Vincent Koc <vincentkoc@ieee.org>
Date: Mon, 25 May 2026 18:35:50 +0200
Subject: [PATCH] fix(qa): harden restart inflight Windows scenario

---
 CHANGELOG.md                                   |  1 +
 extensions/qa-lab/src/scenario-catalog.test.ts |  4 ++++
 .../runtime/gateway-restart-inflight-run.md    | 18 +++++++++---------
 3 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index cadd4fb140e5..454ce5f70bf6 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -61,6 +61,7 @@ Docs: https://docs.openclaw.ai
 - Docker E2E: avoid rebuilding the Control UI twice while preparing the shared OpenClaw package tarball for package-backed scenario runs.
 - Tests: avoid rebuilding the Control UI twice during the installer Docker smoke now that `pnpm build` includes `ui:build`.
 - Tests: give QA config mutation RPCs enough native Windows budget to finish gateway config writes and restart settle after hot scenario runs.
+- Tests: keep the gateway restart-inflight QA scenario focused on restart recovery on native Windows by allowing expected embedded prompt handoff errors and using the Windows-safe timeout budget.
 - Crabbox: sync clean sparse worktrees through a temporary full checkout even when reusing an existing lease so tracked build-time files are not omitted.
 - Build: route `scripts/ui.js` through the shared pnpm runner and keep Control UI chunking helpers in sparse-included source so native Windows Corepack builds can produce `dist/control-ui`.
 - Tests: give the memory fallback QA scenario enough turn budget to exercise native Windows gateway runs instead of failing on the client timeout while the mock agent is still dispatching.
diff --git a/extensions/qa-lab/src/scenario-catalog.test.ts b/extensions/qa-lab/src/scenario-catalog.test.ts
index d038a521e2ad..7b9e1d3b905f 100644
--- a/extensions/qa-lab/src/scenario-catalog.test.ts
+++ b/extensions/qa-lab/src/scenario-catalog.test.ts
@@ -197,6 +197,10 @@ describe("qa scenario catalog", () => {
     expect(readQaScenarioById("long-context-progress-watchdog").sourcePath).toBe(
       "qa/scenarios/runtime/long-context-progress-watchdog.md",
     );
+    expect(JSON.stringify(readQaScenarioById("gateway-restart-inflight-run").execution.flow))
+      .toContain("EmbeddedAttemptSessionTakeoverError");
+    expect(JSON.stringify(readQaScenarioById("gateway-restart-inflight-run").execution.flow))
+      .toContain("liveTurnTimeoutMs(env, 180000)");
     expect(readQaScenarioExecutionConfig("long-context-progress-watchdog")).toMatchObject({
       requiredProviderMode: "live-frontier",
       harnessRuntime: "codex",
diff --git a/qa/scenarios/runtime/gateway-restart-inflight-run.md b/qa/scenarios/runtime/gateway-restart-inflight-run.md
index 1f71cac8794c..6bcc499885a2 100644
--- a/qa/scenarios/runtime/gateway-restart-inflight-run.md
+++ b/qa/scenarios/runtime/gateway-restart-inflight-run.md
@@ -41,11 +41,11 @@ steps:
       - call: waitForGatewayHealthy
         args:
           - ref: env
-          - 60000
+          - 180000
       - call: waitForQaChannelReady
         args:
           - ref: env
-          - 60000
+          - 180000
       - call: reset
       - set: startIndex
         value:
@@ -62,7 +62,7 @@ steps:
             message:
               expr: config.prompt
             timeoutMs:
-              expr: liveTurnTimeoutMs(env, 30000)
+              expr: liveTurnTimeoutMs(env, 180000)
       - call: readConfigSnapshot
         saveAs: current
         args:
@@ -86,19 +86,19 @@ steps:
       - call: waitForGatewayHealthy
         args:
           - ref: env
-          - 60000
+          - 180000
       - call: waitForQaChannelReady
         args:
           - ref: env
-          - 60000
+          - 180000
       - call: waitForAgentRun
         saveAs: waited
         args:
           - ref: env
           - expr: started.runId
-          - expr: liveTurnTimeoutMs(env, 20000)
+          - expr: liveTurnTimeoutMs(env, 180000)
       - assert:
-          expr: "waited.status === 'ok' || waited.status === 'timeout'"
+          expr: "waited.status === 'ok' || waited.status === 'timeout' || (waited.status === 'error' && String(waited.error ?? '').includes('EmbeddedAttemptSessionTakeoverError'))"
           message:
             expr: "`interrupted agent run ended with unexpected status: ${JSON.stringify(waited)}`"
       - set: interruptedMatches
@@ -116,7 +116,7 @@ steps:
             message:
               expr: config.recoveryPrompt
             timeoutMs:
-              expr: liveTurnTimeoutMs(env, 45000)
+              expr: liveTurnTimeoutMs(env, 180000)
       - call: waitForOutboundMessage
         saveAs: outbound
         args:
@@ -124,7 +124,7 @@ steps:
           - lambda:
               params: [candidate]
               expr: "candidate.conversation.id === 'qa-operator' && candidate.text.includes(config.recoveryMarker)"
-          - expr: liveTurnTimeoutMs(env, 30000)
+          - expr: liveTurnTimeoutMs(env, 180000)
           - sinceIndex:
               ref: startIndex
       - set: matchingOutbounds