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/widget/rating.spec.ts

@@ -0,0 +1,26 @@
+import { test, expect } from '@e2e'
+
+interface AgentPerformance { bot_agents: Array<{ id: string; avg_rating: number; rating_count: number }> }
+
+test.describe('chat rating', () => {
+  test.use({ agentSettings: { askForRating: true } })
+
+  test('a customer rates the chat when the agent wraps up, and the rating is recorded against the agent @widget', async ({ agent, widget, llm, adminApi }) => {
+    await llm.script(agent, (s) => s
+      .when(/that is all|thanks/i).endChat('Glad I could help. Goodbye!')
+      .otherwise().reply('Sure thing.'))
+
+    await widget.embed()
+    await widget.open()
+    await widget.send('That is all, thanks')
+
+    await expect(widget.ratingPrompt).toBeVisible()
+    await widget.rate(4)
+    await expect(widget.ratingThanks).toBeVisible()
+
+    // The thanks is client-side; the agent's numbers are what the team actually sees.
+    const ratingOf = async () => (await adminApi.get<AgentPerformance>('/analytics/agent-performance', { params: { time_range: '24h' } }))
+      .bot_agents.find((a) => a.id === agent.id)
+    await expect.poll(ratingOf).toMatchObject({ rating_count: 1, avg_rating: 4 })
+  })
+})