test: unload chat client before restarting its server

Co-Authored-By: Paperclip <noreply@paperclip.ing>

tests/runner-e2e/README.md

@@ -176,6 +176,9 @@ fails the case instead of silently testing another phase.
 Restart continuity requires the agent to recall a phrase after the server
 restarts. The final prompt does not reveal that phrase. A generic successful
 reply after restart cannot pass this check.
+The browser leaves the old development client before the server stops, then
+opens the canonical chat route and waits for the composer. This avoids racing
+Vite's automatic reconnect navigation against the test's explicit navigation.
 
 The blocker query requests a JSON status snapshot. It must name the current
 recorded blocker and report zero active runs independently of the task's blocked

tests/runner-e2e/chat-restart.spec.ts

@@ -0,0 +1,31 @@
+import { createServer } from "node:http";
+import { expect, test } from "@playwright/test";
+import { restartChatServer } from "./chat-restart.js";
+
+test("unloads the old browser client before server restart and opens the new document", async ({ page }) => {
+  let generation = 1;
+  const server = createServer((_req, res) => {
+    res.writeHead(200, { "content-type": "text/html" });
+    res.end(`<input data-testid="composer" value="server generation ${generation}"><script>setInterval(() => fetch('/probe').catch(() => {}), 50)</script>`);
+  });
+  await new Promise<void>(resolve => server.listen(0, "127.0.0.1", resolve));
+  const address = server.address();
+  if (!address || typeof address === "string") throw new Error("Missing listener");
+  const url = `http://127.0.0.1:${address.port}`;
+  try {
+    await page.goto(url);
+    await expect(page.getByTestId("composer")).toHaveValue("server generation 1");
+    await restartChatServer(page, async () => {
+      expect(page.url(), "The old client must be gone before it can auto-reload").toBe("about:blank");
+      server.closeAllConnections();
+      await new Promise<void>((resolve, reject) => server.close(error => error ? reject(error) : resolve()));
+      generation += 1;
+      await new Promise<void>(resolve => server.listen(address.port, "127.0.0.1", resolve));
+    });
+    await page.goto(url, { waitUntil: "commit" });
+    await expect(page.getByTestId("composer")).toHaveValue("server generation 2");
+  } finally {
+    server.closeAllConnections();
+    await new Promise<void>((resolve, reject) => server.close(error => error ? reject(error) : resolve()));
+  }
+});

tests/runner-e2e/chat-restart.ts

@@ -0,0 +1,7 @@
+import type { Page } from "@playwright/test";
+
+/** Restart the test server without letting the old Vite client race navigation. */
+export async function restartChatServer(page: Page, restart: () => Promise<void>) {
+  await page.goto("about:blank", { waitUntil: "commit", timeout: 30_000 });
+  await restart();
+}

tests/runner-e2e/playwright-support.config.ts

@@ -3,7 +3,7 @@ import { defineConfig } from "@playwright/test";
 /** Browser-only harness regressions: no Paperclip instance or provider credentials. */
 export default defineConfig({
   testDir: ".",
-  testMatch: ["screenshot-readiness.spec.ts", "lost-send.spec.ts"],
+  testMatch: ["screenshot-readiness.spec.ts", "lost-send.spec.ts", "chat-restart.spec.ts"],
   workers: 1,
   retries: 0,
   timeout: 10_000,

tests/runner-e2e/runner.spec.ts

@@ -4,6 +4,7 @@ import { createTaskThroughUi, submitTaskReply } from "./user-actions.js";
 
 import { runFirstTaskFlow, setupFirstTaskFixtures } from "./first-task-flow.js";
 import { runChatFlow } from "./chat-flow.js";
+import { restartChatServer } from "./chat-restart.js";
 import { createHash, randomBytes } from "node:crypto";
 import { mkdir, readFile, rename, writeFile } from "node:fs/promises";
 import path from "node:path";
@@ -832,7 +833,7 @@ for (const execution of executions) {
       } else if (execution.task.flow === "agent_chat") {
         const chat = await runChatFlow({
           page, api, fixtures, execution, nonce, workspacePath,
-          restart: () => restartIsolatedPaperclipServer({ api, requestId: `chat-${nonce}`, deadlineAt: startedAtMs + deadlineMs }),
+          restart: () => restartChatServer(page, () => restartIsolatedPaperclipServer({ api, requestId: `chat-${nonce}`, deadlineAt: startedAtMs + deadlineMs })),
           observe: (chatIssue, chatRuns) => { issue = chatIssue; selectedRuns = chatRuns; },
           capture: captureScreenshot,
           evidence: (name, data) => writeSanitizedJson(snapshotsDir, name, data, secrets),