docs: 交付文档、维护指引与端到端回归

补齐 README、开发计划、维护交接与 E2E 用例，执行最终验收。

e2e/specs/perf/budgets.spec.ts

@@ -0,0 +1,40 @@
+import { test, expect, env, AI_REPLY } from '@e2e'
+
+// Size and speed budgets for what every customer's visitor downloads and waits
+// for. About 15% headroom over today; raise a budget on purpose, in review, never
+// to make a red run green.
+
+const KB = 1024
+const BUDGETS = [
+  { file: 'embed loader (replypier.min.js)', url: `${env.frontendUrl}/webclient/replypier.min.js`, maxBytes: 60 * KB },
+  { file: 'widget script (widget.js)', url: `${env.backendUrl}/assets/widget.js`, maxBytes: 500 * KB },
+  { file: 'widget styles (widget.css)', url: `${env.backendUrl}/assets/widget.css`, maxBytes: 135 * KB },
+]
+
+test.describe('performance budgets', () => {
+  for (const { file, url, maxBytes } of BUDGETS) {
+    test(`${file} stays under ${maxBytes / KB} KB @perf`, async ({ request }) => {
+      const body = await (await request.get(url, { headers: { 'Accept-Encoding': 'identity' } })).body()
+      expect(body.length, `${file} is ${Math.round(body.length / KB)} KB`).toBeLessThanOrEqual(maxBytes)
+    })
+  }
+
+  test('the widget is ready and answers within budget, with an instant model @perf @widget', async ({ agent, llm, widget }) => {
+    await llm.script(agent, (s) => s.otherwise().reply('Happy to help!'))
+
+    const loadStart = Date.now()
+    await widget.embed()
+    await widget.open()
+    const readyMs = Date.now() - loadStart
+
+    // The fake model answers at once, so this is the platform's own overhead.
+    const sendStart = Date.now()
+    await widget.send('Hello')
+    await expect(widget.lastAgentMessage()).toHaveText('Happy to help!', AI_REPLY)
+    const replyMs = Date.now() - sendStart
+
+    test.info().annotations.push({ type: 'timing', description: `ready ${readyMs} ms, reply ${replyMs} ms` })
+    expect(readyMs, 'embed → chat ready').toBeLessThan(8_000)
+    expect(replyMs, 'send → reply').toBeLessThan(5_000)
+  })
+})