test(diagnostics): cover stale active run recovery

steipete · steipete · commit 09084c5e1da4 · 2026-05-25T14:05:06.000+01:00
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -39,6 +39,7 @@ Docs: https://docs.openclaw.ai
 - 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.
 - Tests: collect QA gateway CPU/RSS metrics on native Windows and give the channel baseline enough turn budget to report slow gateway runs instead of timing out before proof.
 - Install/update: bypass npm `min-release-age` policies with `--min-release-age=0` instead of `--before` so hosted installers keep working on npm versions that reject the combined config. (#84749) Thanks @TeodoroRodrigo.
+- Diagnostics: reclaim wedged session lanes when stale active-run bookkeeping blocks queued work despite no forward progress. Fixes #85639. Thanks @openperf.
 - WebChat: keep message-tool replies visible in the chat while still summarizing internal tool results for the model. Fixes #86347. Thanks @shakkernerd.
 - Gateway/perf: fail startup benchmark samples when the Gateway process exits before benchmark teardown, including signal deaths after readiness probes.
 - Gateway/perf: fail restart benchmark samples when the Gateway exits before benchmark teardown, including clean exits and signal deaths after successful restart probes.
diff --git a/src/logging/diagnostic-stuck-session-recovery.runtime.test.ts b/src/logging/diagnostic-stuck-session-recovery.runtime.test.ts
@@ -130,6 +130,26 @@ describe("stuck session recovery", () => {
     ]);
   });
 
+  it("reclaims a stale active embedded run with queued work and no forward progress (#85639)", async () => {
+    mocks.resolveActiveEmbeddedRunHandleSessionId.mockReturnValue("session-1");
+    mocks.getDiagnosticSessionActivitySnapshot.mockReturnValue({
+      lastProgressAgeMs: 10 * 60_000,
+    });
+    mocks.abortEmbeddedPiRun.mockReturnValue(true);
+    mocks.waitForEmbeddedPiRunEnd.mockResolvedValue(true);
+
+    const outcome = await recoverStuckDiagnosticSession({
+      sessionId: "session-1",
+      sessionKey: "agent:main:main",
+      ageMs: 180_000,
+      queueDepth: 1,
+    });
+
+    expect(mocks.abortEmbeddedPiRun).toHaveBeenCalledWith("session-1");
+    expect(outcome.status).toBe("aborted");
+    expect(warnLogMessages().some((m) => m.includes("reclaiming stale active run"))).toBe(true);
+  });
+
   it("aborts an active embedded run when active abort recovery is enabled", async () => {
     mocks.resolveActiveEmbeddedRunHandleSessionId.mockReturnValue("session-1");
     mocks.abortEmbeddedPiRun.mockReturnValue(true);
