fix: make codex harness live test portable

CHANGELOG.md

@@ -11,6 +11,7 @@ Docs: https://docs.openclaw.ai
 - Telegram: detect polling stalls from `getUpdates` liveness only, so outbound API calls no longer mask dead inbound polling; log polling-cycle starts after transport rebuilds. Fixes #78473.
 - fix(plugins): scan installed dependency runtime code [AI]. (#81066) Thanks @pgondhi987.
 - Inherit tool restrictions for delegated sessions [AI]. (#80979) Thanks @pgondhi987.
+- Codex harness: make the live test wrapper portable to Windows and defer locked temp cleanup so native Windows and WSL2 live runs complete.
 - Telegram: discard legacy long-poll update offsets that cannot be tied to the current bot token, so token rotation no longer leaves bots silently skipping new messages. (#80671) Thanks @sxxtony.
 - browser: enforce navigation checks for act interactions [AI]. (#81070) Thanks @pgondhi987.
 - Validate node exec event provenance [AI]. (#81071) Thanks @pgondhi987.

package.json

@@ -1643,7 +1643,7 @@
     "test:install:smoke": "bash scripts/test-install-sh-docker.sh",
     "test:live": "node scripts/test-live.mjs",
     "test:live:cache": "node --import tsx scripts/check-live-cache.ts",
-    "test:live:codex-harness": "OPENCLAW_LIVE_CODEX_HARNESS=1 node scripts/test-live.mjs -- src/gateway/gateway-codex-harness.live.test.ts",
+    "test:live:codex-harness": "node scripts/test-live.mjs --codex-harness -- src/gateway/gateway-codex-harness.live.test.ts",
     "test:live:crestodian-rescue-channel": "OPENCLAW_LIVE_CRESTODIAN_RESCUE_CHANNEL=1 node scripts/test-live.mjs -- src/crestodian/rescue-channel.live.test.ts",
     "test:live:gateway-profiles": "node scripts/test-live.mjs -- src/gateway/gateway-models.profiles.live.test.ts",
     "test:live:media": "node --import tsx scripts/test-live-media.ts",

scripts/test-live.mjs

@@ -2,11 +2,16 @@ import { spawnPnpmRunner } from "./pnpm-runner.mjs";
 
 const forwardedArgs = [];
 let quietOverride;
+let forceCodexHarness = false;
 
 for (const arg of process.argv.slice(2)) {
   if (arg === "--") {
     continue;
   }
+  if (arg === "--codex-harness") {
+    forceCodexHarness = true;
+    continue;
+  }
   if (arg === "--quiet" || arg === "--quiet-live") {
     quietOverride = "1";
     continue;
@@ -25,6 +30,7 @@ const env = {
   pnpm_config_verify_deps_before_run: process.env.pnpm_config_verify_deps_before_run || "false",
   OPENCLAW_LIVE_TEST: process.env.OPENCLAW_LIVE_TEST || "1",
   OPENCLAW_LIVE_TEST_QUIET: quietOverride ?? process.env.OPENCLAW_LIVE_TEST_QUIET ?? "1",
+  ...(forceCodexHarness ? { OPENCLAW_LIVE_CODEX_HARNESS: "1" } : {}),
 };
 
 function parsePositiveInt(value, fallback) {

src/gateway/gateway-codex-harness.live.test.ts

@@ -162,6 +162,31 @@ async function createLiveWorkspace(tempDir: string): Promise<string> {
   return workspace;
 }
 
+async function removeLiveTempDir(dir: string): Promise<void> {
+  let lastError: unknown;
+  for (let attempt = 0; attempt < 100; attempt += 1) {
+    try {
+      await fs.rm(dir, { recursive: true, force: true });
+      return;
+    } catch (error) {
+      lastError = error;
+      const code = (error as { code?: unknown } | null)?.code;
+      if (code !== "EBUSY" && code !== "ENOTEMPTY" && code !== "EPERM" && code !== "EACCES") {
+        throw error;
+      }
+      await delay(100);
+    }
+  }
+  if (process.platform === "win32") {
+    logCodexLiveStep("temp-cleanup-deferred", {
+      dir,
+      error: lastError instanceof Error ? lastError.message : String(lastError),
+    });
+    return;
+  }
+  await fs.rm(dir, { recursive: true, force: true });
+}
+
 function parseModelKey(modelKey: string): { provider: string; modelId: string } {
   const [provider, ...modelParts] = modelKey.split("/");
   const modelId = modelParts.join("/");
@@ -935,8 +960,15 @@ describeLive("gateway live (Codex harness)", () => {
         clearRuntimeConfigSnapshot();
         await client.stopAndWait();
         await server.close();
+        const [{ resetTaskRegistryForTests }, { resetTaskFlowRegistryForTests }] =
+          await Promise.all([
+            import("../tasks/runtime-internal.js"),
+            import("../tasks/task-flow-runtime-internal.js"),
+          ]);
+        resetTaskRegistryForTests({ persist: false });
+        resetTaskFlowRegistryForTests({ persist: false });
         restoreEnv(previousEnv);
-        await fs.rm(tempDir, { recursive: true, force: true, maxRetries: 5, retryDelay: 100 });
+        await removeLiveTempDir(tempDir);
       }
     },
     CODEX_HARNESS_TIMEOUT_MS,